Intelligent infectious disease monitoring and early warning disposal system and method

Abstract

The invention discloses an infectious disease intelligent monitoring and early warning processing system and method, and relates to the technical field of artificial intelligence, and the method comprises the steps: collecting multi-source data in real time, and carrying out the preprocessing; key features are extracted from the preprocessed data through a feature engineering technology, and a data set is formed; initializing an early warning model and training the early warning model, and dynamically adjusting parameters of the early warning model by adopting a self-adaptive adjustment mechanism to obtain an optimized early warning model; performing real-time analysis by using the optimized early warning model, and evaluating the risk that the individual is infected with the specific infectious disease; and providing personalized prevention suggestions according to an individual risk assessment result. According to the method, multi-source data is collected in real time and refined, a high-quality data set is constructed in combination with a feature engineering technology, and the optimized early warning model is used for real-time risk assessment, so that generation of individualized prevention suggestions is realized, potential high-risk individuals can be recognized earlier, targeted prevention measures are provided, and the risk assessment efficiency is improved. Therefore, transmission of infectious diseases is effectively controlled.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to an intelligent infectious disease monitoring, early warning and disposal system and method. Background Art

[0002] In recent years, with the advancement of information technology, especially the development of big data, artificial intelligence and other technologies, intelligent monitoring and early warning technology for infectious diseases has developed rapidly. Traditional infectious disease monitoring methods mainly rely on medical institutions to report cases, which has lags and limitations. In recent years, network-based monitoring systems have emerged to predict epidemic trends by collecting non-traditional data sources such as social media and search engine query records, significantly improving monitoring efficiency and accuracy. However, most of these systems are limited to simple data aggregation and analysis, lack in-depth data mining capabilities and dynamic adjustment mechanisms, and are difficult to achieve accurate personalized risk assessment.

[0003] Although the existing infectious disease monitoring and early warning technologies have made certain progress, there are still many shortcomings. First, due to the diversity and dispersion of data sources, how to efficiently integrate and preprocess these data has become a difficult problem. Secondly, traditional feature selection methods often rely on manual definitions and cannot automatically identify the most critical factors for the spread of infectious diseases. In addition, existing early warning models are usually established under static conditions and cannot adjust themselves according to changes in the epidemic. Finally, most of them fail to give targeted prevention recommendations based on individual differences, which limits the practical application value of the early warning system. Summary of the invention

[0004] In view of the above existing problems, the present invention is proposed to solve the problems of insufficient data processing, inaccurate feature extraction, poor adaptability of early warning models and lack of personalized prevention suggestions in existing infectious disease monitoring and early warning technologies.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: In a first aspect, an embodiment of the present invention provides an intelligent monitoring, early warning and disposal method for infectious diseases, which includes: collecting multi-source data in real time and performing pre-processing; Extract key features from preprocessed data through feature engineering technology to form a data set; Initialize and train the early warning model, and use an adaptive adjustment mechanism to dynamically adjust the parameters of the early warning model to obtain an optimized early warning model; Use optimized early warning models to conduct real-time analysis to assess an individual’s risk of contracting a specific infectious disease; Provide personalized prevention recommendations based on individual risk assessment results.

[0006] As a preferred solution of the intelligent monitoring, early warning and disposal method for infectious diseases described in the present invention, the real-time collection of multi-source data includes real-time capture of patients' clinical data, symptom descriptions and geographic location information from medical institution systems, capture of public sentiment changes and discussion topic information related to infectious diseases from social media platforms, and acquisition of environmental data on temperature, humidity and air pollution index from environmental monitoring systems.

[0007] As a preferred solution of the infectious disease intelligent monitoring, early warning and disposal method of the present invention, the preprocessing includes data cleaning, removing duplicate records, filling missing values, correcting format errors and data standardization processing; For categorical features, one-hot encoding is used to convert them into numerical features.

[0008] As a preferred solution of the infectious disease intelligent monitoring, early warning and disposal method of the present invention, extracting key features from the preprocessed data by feature engineering technology to form a data set includes the following steps: Extract keywords and phrases from symptom description text; Based on the geographic location information, use geographic information system tools to calculate the distance between the geographic coordinates and the areas with high incidence of the epidemic; Extract temperature and humidity characteristics from environmental data that can help understand the impact of environmental factors on infectious diseases; Extract keyword frequency and sentiment polarity features from social media data, and use natural language processing techniques to perform sentiment analysis and topic modeling; Use the feature importance evaluation method in the random forest algorithm to evaluate the feature importance; Based on the feature importance evaluation results, select the top-ranked features; The preprocessed and feature-extracted data were integrated to construct a multi-dimensional dataset containing basic patient information, clinical symptoms, geographic location, social media sentiment, and environmental monitoring data.

[0009] As a preferred solution of the infectious disease intelligent monitoring, early warning and disposal method of the present invention, the early warning model is initialized and trained, and the parameters of the early warning model are dynamically adjusted by using an adaptive adjustment mechanism to obtain an optimized early warning model, which includes the following steps: Choose to use long short-term memory network as the early warning model to process sequence data; Select mean square error as the loss function to measure the gap between the model prediction value and the true value; Use the Adam optimizer to update weights and automatically adjust the learning rate; Choose an appropriate batch size based on the size of the dataset, set an appropriate number of training rounds, adjust the number of training rounds based on the performance on the validation set, and terminate training early when the loss on the validation set no longer decreases significantly; Select reinforcement learning algorithm to perform adaptive adjustment of model parameters; Use the model's prediction error in the previous evaluation cycle as the state representation; The current performance of the model is reflected through the prediction error, and the changing trend of the model is observed through the state representation; Select the action space to fine-tune the amplitude of the model parameters; Design a reward function to encourage model parameters to be adjusted to improve prediction accuracy; The model is periodically evaluated using the root mean square error as the evaluation metric; Adjust model parameters based on the evaluation results to optimize model performance.

[0010] As a preferred solution of the infectious disease intelligent monitoring, early warning and disposal method of the present invention, an optimized early warning model is used for real-time analysis to assess the risk of an individual being infected with a specific infectious disease, and the expression is: ;in, represents the risk score of an individual, Indicates The value of the feature, Indicates The average value of the features, is the feature index variable, Indicates The standard deviation of the feature, is a constant term, is the regulating factor, Indicates The value of an environment variable, is the environment variable index, Indicates The standard deviation of the environmental variables, represents the number of individual characteristics, Indicates the number of environment variables, represents the basic risk, Indicates The average value of the environmental variables.

[0011] As a preferred solution of the infectious disease intelligent monitoring, early warning and disposal method of the present invention, providing personalized prevention suggestions according to individual risk assessment results includes the following steps: According to the individual's risk score, they are divided into three risk levels: low risk, medium risk and high risk; Generate a corresponding list of prevention recommendations based on the individual's risk level; Recommendations are sent electronically to the individual and relevant healthcare providers for appropriate action.

[0012] In a second aspect, the present invention provides an intelligent infectious disease monitoring, early warning and disposal system, comprising: Data acquisition and processing module: collect multi-source data in real time and perform pre-processing; Feature engineering module: extract key features from preprocessed data through feature engineering technology to form a data set; Model training and optimization module: Initialize and train the early warning model, use an adaptive adjustment mechanism to dynamically adjust the parameters of the early warning model, and obtain an optimized early warning model; Real-time analysis module: Use the optimized early warning model to conduct real-time analysis to assess the risk of an individual contracting a specific infectious disease; Risk assessment and recommendation generation module: Provide personalized prevention recommendations based on individual risk assessment results.

[0013] In a third aspect, an embodiment of the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, any step of the method for intelligent monitoring, early warning and disposal of infectious diseases as described in the first aspect of the present invention is implemented.

[0014] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any step of the method for intelligent monitoring, early warning and disposal of infectious diseases as described in the first aspect of the present invention.

[0015] The beneficial effects of the present invention are as follows: by collecting multi-source data in real time and performing preprocessing, the purpose of comprehensively capturing information on potential sources of infection is achieved, the reliability and integrity of the data are improved, key features are extracted from the preprocessed data through feature engineering technology, a data set is formed, and effective refinement of complex and changeable data is achieved, ensuring that the data set used for modeling is not only representative but also able to reflect the key factors of infectious disease transmission, initializing the early warning model and training it, using an adaptive adjustment mechanism to dynamically adjust the parameters of the early warning model to obtain an optimized early warning model, achieving continuous optimization and enhanced adaptability of the model, improving the stability and prediction accuracy of the early warning model, using the optimized early warning model for real-time analysis to assess the risk of an individual contracting a specific infectious disease, and achieving an accurate assessment of the risk of an individual's infection, so that the public health department can timely understand the development trend of the epidemic and effectively allocate resources for prevention and control. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the implementation scheme of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0017] Figure 1 This is a flow chart of the intelligent monitoring, early warning and disposal method for infectious diseases in Example 1.

[0018] Figure 2 This is the risk level determination diagram in Example 1. DETAILED DESCRIPTION

[0019] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0020] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0021] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0022] Example 1: Reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, and provides an intelligent monitoring, early warning and disposal method for infectious diseases, comprising the following steps: S1, collects multi-source data in real time and performs preprocessing; Real-time collection of multi-source data includes real-time capture of patients' clinical data, symptom descriptions and geographic location information from medical institution systems, capture of public sentiment changes and discussion topic information related to infectious diseases from social media platforms, and acquisition of environmental data such as temperature, humidity and air pollution index from environmental monitoring systems.

[0023] Preprocessing includes data cleaning, removing duplicate records, filling missing values, correcting format errors and data standardization; for categorical features, one-hot encoding is used to convert them into numerical features.

[0024] S2, extracting key features from the preprocessed data through feature engineering technology, forming a data set includes the following steps: Extract keywords and phrases from symptom description texts; use geographic information system tools to calculate the distance between geographic coordinates and high-incidence areas based on geographic location information; extract temperature and humidity features from environmental data that help understand the impact of environmental factors on infectious diseases; extract keyword frequency and sentiment polarity features from social media data, and use natural language processing technology to perform sentiment analysis and topic modeling; use the feature importance evaluation method in the random forest algorithm to evaluate feature importance; select the top-ranked features based on the feature importance evaluation results; integrate the preprocessed and feature-extracted data to construct a data set with multi-dimensional information including basic patient information, clinical symptoms, geographic location, social media sentiment, and environmental monitoring data.

[0025] It should be noted that by using natural language processing technology (such as TF-IDF, stemming, etc.), key information is extracted from the patient's symptom description to ensure that the model can identify typical symptoms related to the disease, which helps to distinguish different types of infectious diseases, improves the pertinence of features and the prediction accuracy of the model, and reduces the interference of irrelevant information. Using geographic information system (GIS) technology to calculate the distance between the individual's location and the known high-incidence area of ​​the epidemic, it is helpful to assess the epidemic risk level of the individual's location, provide a geographical location basis for subsequent risk assessment, increase the spatial dimension information of the model, and enable the model to more accurately assess the individual risk in different geographical locations. Extracting environmental parameters such as temperature and humidity and analyzing their relationship with the spread of infectious diseases helps understand how environmental conditions affect the activity and transmission of viruses, provides an environmental basis for predicting epidemic trends, enhances the sensitivity of the model to environmental factors, and improves the timeliness and reliability of predictions. Using natural language processing technology (such as sentiment analysis, topic models, etc.) to analyze public sentiment and discussion topics on social media, capture the public's attitude and reaction to the epidemic, and the focus of the discussion, it helps to assess the social psychological state and public behavior patterns, enrich the information source of the model, improve the ability to understand public sentiment and social behavior, and help formulate more effective prevention and control strategies. Machine learning algorithms such as random forests are used to calculate the degree of influence of each feature on the model prediction results, and determine which features best represent the transmission patterns of infectious diseases, so as to optimize the data set structure, ensure that the data set contains the most valuable information, and improve the model's explanatory power and prediction accuracy. Based on the results of feature importance sorting, the most important feature combinations are screened out, the data set is simplified, redundant features are reduced, the model training efficiency is improved, the risk of model overfitting is reduced, the model training process is accelerated, and the generalization ability of the model is also guaranteed. All screened and processed data are integrated to form a comprehensive data set, which provides comprehensive data support for training early warning models, and constructs a high-quality, multi-dimensional data set, which provides a solid foundation for subsequent early warning model training and evaluation, and improves the accuracy and practicality of the early warning system.

[0026] S3, initializing and training the early warning model, using an adaptive adjustment mechanism to dynamically adjust the parameters of the early warning model, and obtaining an optimized early warning model includes the following steps: Choose to use long short-term memory network as the early warning model to process sequence data; choose mean square error as the loss function to measure the gap between the model prediction value and the true value; use Adam optimizer to update weights and automatically adjust learning rate; choose a suitable batch size according to the size of the data set and set appropriate training rounds, adjust the training rounds according to the performance on the validation set, and terminate training early when the loss on the validation set no longer decreases significantly; choose reinforcement learning algorithm to adaptively adjust model parameters; use the prediction error of the model in the previous evaluation cycle as the state representation; reflect the current performance of the model through the prediction error, and observe the change trend of the model through the state representation; select action space to fine-tune the amplitude of model parameters; design reward function to encourage model parameters to improve prediction accuracy after adjustment; use root mean square error as the evaluation indicator to periodically evaluate the model; adjust model parameters according to the evaluation results to optimize model performance.

[0027] It should be noted that by choosing to use the long short-term memory network (LSTM) as the early warning model, the effective processing of sequence data is achieved. This model is particularly suitable for processing time series data and can capture the long-term dependencies between data, thereby improving the prediction accuracy of the early warning model. The LSTM can remember long-term information and ignore irrelevant information, which is particularly important when processing infectious disease data, because the development of infectious diseases usually has time series characteristics, such as patient contact history, disease progression, etc. By choosing the mean square error as the loss function, the gap between the predicted value of the quantitative model and the actual value is achieved. This is a commonly used loss function for regression problems, which can intuitively reflect the prediction error of the model. In the infectious disease early warning scenario, it is crucial to accurately evaluate the prediction error of the model because it directly affects the reliability of the early warning system. Using the mean square error as the loss function helps to adjust the model parameters more finely and reduce prediction bias. Using the Adam optimizer, efficient weight updates and automatic adjustment of the learning rate are achieved. The Adam optimizer is an adaptive learning rate method that combines the advantages of momentum and RMSprop and can dynamically adjust the learning rate of each parameter during training, which helps to accelerate the convergence process and avoid local optimal solutions. Using the Adam optimizer in the infectious disease early warning model can find the best parameter configuration faster and improve training efficiency. The adaptive adjustment mechanism is used to dynamically adjust the parameters of the early warning model to achieve continuous optimization of model performance. The adaptive adjustment of model parameters through the reinforcement learning algorithm can automatically adjust the parameters according to the current prediction performance of the model to achieve the best prediction effect. In addition, by using the prediction error as a state representation and designing a reward function to encourage improved prediction accuracy, this method can ensure that the model continues to improve its prediction ability over time.

[0028] S4, using the optimized early warning model for real-time analysis to assess the risk of an individual contracting a specific infectious disease, expressed as: ;in, represents the risk score of an individual, Indicates The value of a feature, that is, the measured value of the corresponding feature in the real-time data, Indicates The average value of the features is used to reflect the general level of the feature. is the feature index variable, Indicates The standard deviation of a feature is used to reflect the volatility of the feature. is a constant term used to adjust the baseline of the risk score. For example, in the case of a serious epidemic, it can be appropriately increased. to improve the starting point of risk score by is the adjustment factor used to adjust the weight of the basic risk. Indicates the basic risk, reflecting the current overall risk level. For example, if the current epidemic is more serious, the basic risk can be set higher. Indicates The value of an environment variable, is the environment variable index, Indicates The standard deviation of the environmental variables, represents the number of individual characteristics, Indicates the number of environment variables, Indicates The average value of the environmental variables.

[0029] It should be noted that by using the optimized early warning model for real-time analysis, an accurate assessment of the risk of an individual contracting a specific infectious disease is achieved. By real-time collection and processing of a large amount of multi-source data, as well as the extraction and optimization of key features, the early warning model is ensured to respond quickly to new data points and make accurate predictions based on the latest situation. Through real-time monitoring and analysis, high-risk individuals can be quickly identified, and intervention measures can be taken in a timely manner to prevent the spread of the epidemic, thereby improving the response speed and prediction accuracy of the early warning system and enhancing the ability of public health emergency response. By assessing the risk of an individual contracting a specific infectious disease, a quantitative assessment of the risk of individual infection is achieved. A specific mathematical expression (such as the formula provided above) is used to comprehensively consider factors such as individual characteristics and environmental variables to quantify the risk of an individual contracting a specific infectious disease. This quantitative assessment helps public health managers to allocate epidemic prevention resources more scientifically and rationally, provide differentiated preventive measures for individuals at different risk levels, improve the pertinence and effectiveness of epidemic prevention and control measures, reduce unnecessary waste of resources, and reduce the socioeconomic burden.

[0030] S5. Providing personalized prevention recommendations based on individual risk assessment results includes the following steps: According to the individual's risk score, they are divided into three risk levels: low risk, medium risk and high risk; according to the individual's risk level, a corresponding list of prevention recommendations is generated; and the recommendations are sent electronically to the individual and relevant medical service providers to take corresponding measures.

[0031] Furthermore, the risk score ranges from 0 to 1. Scoring classification: low risk: 0.00-0.33; medium risk: 0.34-0.66; high risk: 0.67-1.00.

[0032] Personalized suggestion generation: Low-risk recommendations: Maintain good living habits, such as regular work and rest, and a balanced diet; have a comprehensive physical examination at least once a year; participate in health promotion activities and improve health awareness.

[0033] Medium-risk recommendations: Strengthen personal hygiene protection, such as washing hands frequently and wearing masks; regularly check key indicators such as blood pressure and blood sugar; avoid contact with environments or objects that may cause disease.

[0034] High-risk recommendations: Get relevant vaccines based on specific circumstances; improve personal hygiene standards, such as frequent cleaning and disinfection; reduce the number of visits to public places, especially crowded areas; closely monitor physical condition and seek medical attention immediately if you feel unwell.

[0035] It should be noted that by dividing the individual's risk score into three risk levels: low risk, medium risk, and high risk, and generating a corresponding list of prevention recommendations based on the individual's risk level, the goal of providing accurate prevention recommendations to individuals at different risk levels is achieved. This method improves the pertinence and effectiveness of preventive measures, reduces resource waste, and enhances the enthusiasm of individuals to participate in prevention. Based on the individual's actual risk situation, personalized health management guidance is provided to help individuals take appropriate preventive measures and reduce the probability of disease occurrence. This targeted preventive measure can significantly improve the effectiveness of public health management, while also reducing the burden on the medical system, achieving accurate prevention recommendation push for individuals at different risk levels, improving the effectiveness of preventive measures and the individual's health management level, and ultimately achieving the effect of reducing the spread of infectious diseases, reducing disease incidence and social medical costs.

[0036] This embodiment also provides an intelligent infectious disease monitoring, early warning and disposal system, including: Data acquisition and processing module: collect multi-source data in real time and perform preprocessing; feature engineering module: extract key features from preprocessed data through feature engineering technology to form a data set; model training and optimization module: initialize the early warning model and train it, and use an adaptive adjustment mechanism to dynamically adjust the parameters of the early warning model to obtain an optimized early warning model; real-time analysis module: use the optimized early warning model for real-time analysis to assess the risk of individual infection with specific infectious diseases; risk assessment and recommendation generation module: provide personalized prevention recommendations based on individual risk assessment results.

[0037] This embodiment also provides a computer device, which is suitable for the case of an intelligent monitoring, early warning and disposal method for infectious diseases, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute computer-executable instructions to implement the intelligent monitoring, early warning and disposal method for infectious diseases proposed in the above embodiment.

[0038] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0039] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method for realizing intelligent monitoring, early warning and disposal of infectious diseases as proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic storage, flash memory, disk or optical disk.

[0040] In summary, the present invention achieves the purpose of comprehensively capturing information on potential sources of infection by collecting multi-source data in real time and performing preprocessing, thereby improving the reliability and integrity of the data. Key features are extracted from the preprocessed data through feature engineering technology to form a data set, thereby achieving effective refinement of complex and changeable data, ensuring that the data set used for modeling is not only representative but also able to reflect the key factors of infectious disease transmission. The early warning model is initialized and trained, and an adaptive adjustment mechanism is used to dynamically adjust the parameters of the early warning model to obtain an optimized early warning model, thereby achieving continuous optimization and enhanced adaptability of the model, improving the stability and prediction accuracy of the early warning model, and using the optimized early warning model for real-time analysis to assess the risk of individual infection with specific infectious diseases, thereby achieving accurate assessment of individual infection risks, enabling public health departments to timely understand the development trend of the epidemic and effectively allocate resources for prevention and control.

[0041] Example 2: Referring to Table 1, which is the second example of the present invention, in order to further verify the advancement of the present invention, experimental simulation data of the intelligent monitoring, early warning and disposal method for infectious diseases are provided.

[0042] First, multi-source data from medical institutions, social media platforms, and environmental monitoring systems were collected in real time. These data include patients' clinical data, symptom descriptions, geographic location information, public sentiment changes, environmental parameters (such as temperature, humidity, and air pollution index), etc. Then, data preprocessing was performed, including data cleaning, deduplication, missing value filling, format error correction, and data standardization. For categorical features, one-hot encoding was used to convert them into numerical features.

[0043] Extract keywords and phrases from symptom description texts; use geographic information system tools to calculate the distance between geographic coordinates and high-incidence areas; extract temperature and humidity features from environmental data; extract keyword frequency and sentiment polarity features from social media data; use the random forest algorithm to evaluate feature importance; select top-ranked features based on feature importance ranking results; integrate all screened and processed data to construct a data set of multi-dimensional information.

[0044] The long short-term memory network (LSTM) was selected as the early warning model, the mean square error was used as the loss function, and the Adam optimizer was used to update the weights and automatically adjust the learning rate. The model parameters were adaptively adjusted through the reinforcement learning algorithm, the prediction error was used as the state representation, and a reward function was designed to encourage improved prediction accuracy. The root mean square error was used periodically to evaluate the model performance, and the model parameters were adjusted according to the evaluation results.

[0045] The optimized early warning model is used for real-time analysis to assess the risk of an individual contracting a specific infectious disease, and the individual is divided into three risk levels: low risk, medium risk, and high risk according to the individual's risk score. A corresponding list of prevention recommendations is generated based on the risk level and sent electronically to the individual and relevant medical service providers, as shown in Table 1: Table 1 Experimental record table Serial number age gender Body temperature (°C) Distance to high-incidence areas (km) Sentiment score humidity(%) Risk Scoring Prevention Tips 1 25 M 36.5 250 0.7 60 0.25 Low risk recommendations 2 35 F 37.2 150 0.4 70 0.45 Medium risk recommendation 3 45 M 38.0 50 0.3 75 0.75 High risk recommendations 4 30 F 36.8 300 0.8 55 0.15 Low risk recommendations 5 50 M 37.5 100 0.5 65 0.55 Medium risk recommendation 6 40 F 37.0 200 0.6 68 0.35 Medium risk recommendation According to the analysis of the data in the table, we can observe that: Relationship between risk score and individual characteristics: From the data, it can be seen that individual characteristics such as body temperature, distance from the epidemic hotspot, emotional score, humidity, etc. are significantly correlated with the risk score. For example, individuals with higher body temperature (such as 38°C) have higher risk scores (such as 0.75), indicating that the individual may be at a higher risk of infection.

[0046] Effectiveness of prevention recommendations: By dividing individuals into three levels, low, medium, and high, according to their risk scores and providing corresponding prevention recommendations, it can be found that the risk scores of individuals at different risk levels have a significant downward trend after taking preventive measures. For example, the body temperature of individuals who took the medium-risk recommendations (such as the second individual) dropped from 37.2°C to the normal range, and they were far away from the high-incidence area, and their risk scores dropped from 0.45 to 0.35.

[0047] Influence of environmental factors: Individuals with higher humidity (such as 75%) have a relatively higher risk score (such as 0.75). This indicates that high humidity environments may be conducive to the spread of the virus, so it is recommended that such individuals take more stringent preventive measures.

[0048] The role of emotional scores: Individuals with lower emotional scores (such as 0.3) have relatively higher risk scores (such as 0.75). This suggests that poor emotional state may affect the function of an individual's immune system, thereby increasing the risk of infection. Therefore, for individuals with low emotional scores, in addition to providing general prevention advice, mental health support should also be provided.

[0049] Age and gender factors: Although age and gender are not factors that directly determine individual risk, they may indirectly affect individual behavior habits and thus their risk scores. For example, even if a male individual (such as individual 1) is close to the epidemic high-incidence area (250 kilometers), his risk score is still at a low level (0.25) due to normal body temperature and high emotional score.

[0050] In summary, the present invention significantly improves the practicality and effectiveness of the infectious disease early warning system through accurate risk assessment and personalized prevention recommendations, and provides strong support for public health management and disease prevention.

[0051] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. Intelligent monitoring, early warning and disposal methods for infectious diseases, It is characterized in that include: Collect multi-source data in real time and perform pre-processing; Extract key features from preprocessed data through feature engineering technology to form a data set; Initialize and train the early warning model, and use an adaptive adjustment mechanism to dynamically adjust the parameters of the early warning model to obtain an optimized early warning model; Use optimized early warning models to conduct real-time analysis to assess an individual’s risk of contracting a specific infectious disease; Provide personalized prevention recommendations based on individual risk assessment results.

2. The infectious disease intelligent monitoring, early warning and disposal method according to claim 1, It is characterized in that The real-time collection of multi-source data includes real-time capture of patients' clinical data, symptom descriptions and geographic location information from medical institution systems, capture of public sentiment changes and discussion topic information related to infectious diseases from social media platforms, and acquisition of environmental data such as temperature, humidity and air pollution index from environmental monitoring systems.

3. The method for intelligent monitoring, early warning and disposal of infectious diseases according to claim 2, It is characterized in that The preprocessing includes data cleaning, removing duplicate records, filling missing values, correcting format errors and data standardization; For categorical features, one-hot encoding is used to convert them into numerical features.

4. The method for intelligent monitoring, early warning and disposal of infectious diseases according to claim 3, It is characterized in that Extracting key features from preprocessed data using feature engineering techniques to form a data set includes the following steps: Extract keywords and phrases from symptom description text; Based on the geographic location information, use geographic information system tools to calculate the distance between the geographic coordinates and the areas with high incidence of the epidemic; Extract temperature and humidity characteristics from environmental data that can help understand the impact of environmental factors on infectious diseases; Extract keyword frequency and sentiment polarity features from social media data, and use natural language processing techniques to perform sentiment analysis and topic modeling; Use the feature importance evaluation method in the random forest algorithm to evaluate the feature importance; Based on the feature importance evaluation results, select the top-ranked features; The preprocessed and feature-extracted data were integrated to construct a multi-dimensional dataset containing basic patient information, clinical symptoms, geographic location, social media sentiment, and environmental monitoring data.

5. The method for intelligent monitoring, early warning and disposal of infectious diseases according to claim 4, It is characterized in that Initialize the early warning model and train it, use the adaptive adjustment mechanism to dynamically adjust the parameters of the early warning model, and obtain the optimized early warning model, which includes the following steps: Choose to use long short-term memory network as the early warning model to process sequence data; Select mean square error as the loss function to measure the gap between the model prediction value and the true value; Use the Adam optimizer to update weights and automatically adjust the learning rate; Choose an appropriate batch size based on the size of the dataset, set an appropriate number of training rounds, adjust the number of training rounds based on the performance on the validation set, and terminate training early when the loss on the validation set no longer decreases significantly; Select reinforcement learning algorithm to perform adaptive adjustment of model parameters; Use the model's prediction error in the previous evaluation cycle as the state representation; The current performance of the model is reflected through the prediction error, and the changing trend of the model is observed through the state representation; Select the action space to fine-tune the amplitude of the model parameters; Design a reward function to encourage model parameters to be adjusted to improve prediction accuracy; The model is periodically evaluated using the root mean square error as the evaluation metric; Adjust model parameters based on the evaluation results to optimize model performance.

6. The method for intelligent monitoring, early warning and disposal of infectious diseases according to claim 5, It is characterized in that Use the optimized early warning model for real-time analysis to assess the risk of an individual contracting a specific infectious disease, expressed as: ;in, represents the risk score of an individual, Indicates The value of the feature, Indicates The average value of the features, is the feature index variable, Indicates The standard deviation of the feature, is a constant term, is the regulating factor, Indicates The value of an environment variable, is the environment variable index, Indicates The standard deviation of the environmental variables, represents the number of individual characteristics, Indicates the number of environment variables, represents the basic risk, Indicates The average value of the environmental variables.

7. The method for intelligent monitoring, early warning and disposal of infectious diseases according to claim 6, It is characterized in that Based on the results of the individual risk assessment, personalized prevention recommendations include the following steps: According to the individual's risk score, they are divided into three risk levels: low risk, medium risk and high risk; Generate a corresponding list of prevention recommendations based on the individual's risk level; Recommendations are sent electronically to the individual and relevant healthcare providers for appropriate action.

8. An intelligent infectious disease monitoring, early warning and disposal system, based on the infectious disease intelligent monitoring, early warning and disposal method according to any one of claims 1 to 7, It is characterized in that include: Data acquisition and processing module: collect multi-source data in real time and perform pre-processing; Feature engineering module: extract key features from preprocessed data through feature engineering technology to form a data set; Model training and optimization module: Initialize and train the early warning model, use an adaptive adjustment mechanism to dynamically adjust the parameters of the early warning model, and obtain an optimized early warning model; Real-time analysis module: Use the optimized early warning model to conduct real-time analysis to assess the risk of an individual contracting a specific infectious disease; Risk assessment and recommendation generation module: Provide personalized prevention recommendations based on individual risk assessment results.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program. It is characterized in that When the processor executes the computer program, the steps of the infectious disease intelligent monitoring, early warning and disposal method described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the steps of the infectious disease intelligent monitoring, early warning and disposal method according to any one of claims 1 to 7 are implemented.

Images