An AI-based real-time monitoring and early warning system and application for infectious diseases

Abstract

This invention provides an artificial intelligence-based method and system for real-time monitoring and early warning of infectious diseases. Based on historical transmission data of infectious diseases and viral evolution data caused by gene mutations and genotyping, a corresponding infectious disease mutation prediction model, Qfa, is constructed and deployed on a backend server. Real-time monitoring data of infectious diseases is collected and imported into the infectious disease mutation prediction model Qfa. The Qfa model performs bidirectional fusion prediction of infectious diseases in both real-time and evolutionary directions. Based on the prediction results in different directions, corresponding Class I and / or Class II infectious disease warnings are issued to the front end. This system combines real-time and evolutionary prediction models to predict the current and future spread of infectious diseases, integrating future viral transmission and evolutionary characteristics. It provides management departments with intelligent epidemic transmission analysis and early warning, and infectious disease outbreak trend prediction, enabling management departments to make early warning judgments and reduce the difficulty of prevention and control.

Description

Technical Field

[0001] This invention relates to the field of intelligent medical technology, and in particular to an artificial intelligence-based method for real-time monitoring and early warning of infectious diseases, an artificial intelligence-based system for real-time monitoring and early warning of infectious diseases, its applications, and electronic devices. Background Technology

[0002] The surveillance and prevention of infectious diseases is a crucial task in the field of public health, involving multiple strategies and practices. Below are some key infectious disease surveillance and prevention measures:

[0003] 1. Epidemic monitoring: By collecting and analyzing disease data, health departments can promptly detect outbreaks, assess the scale of the epidemic, predict disease trends, and provide a basis for formulating prevention and control strategies.

[0004] 2. Vaccination: Vaccination is the most economical and effective means of preventing infectious diseases. By regularly providing vaccination services to the public, the incidence and mortality rates of some serious infectious diseases can be greatly reduced.

[0005] 3. Health Education: Through extensive health education activities, raise public awareness of infectious diseases, help them understand preventive measures, and enhance their self-protection awareness.

[0006] 4. Control the source of infection: Isolate and treat infected patients to prevent the spread of pathogens to others.

[0007] 5. Cut off transmission routes: Improve environmental sanitation, strengthen food and drinking water hygiene management, and eliminate vectors for pathogen transmission, such as mosquitoes, flies, and rats.

[0008] 6. Protect vulnerable populations: Certain groups may be more susceptible to some infectious diseases. By providing special protective measures, such as special vaccination services for vulnerable groups like the elderly, children, and pregnant women, their risk of infection can be reduced.

[0009] However, the above are traditional methods of infectious disease control, which can only be implemented after an outbreak, and cannot prevent infectious diseases in advance. Because infectious diseases are characterized by their suddenness and randomness, it is often impossible to monitor their development and specific virus types in real time, thus making it impossible to recommend timely and effective prevention and warning measures.

[0010] Among the existing infectious disease monitoring and early warning technologies, intelligent early warning technology for infectious diseases is mainly used for monitoring and early warning.

[0011] Intelligent early warning technology for infectious diseases is a technology that uses artificial intelligence (AI) for epidemic prediction and prevention. By analyzing multi-dimensional environmental and epidemic factors, this technology can quickly locate high-incidence areas of epidemics, providing governments and epidemic prevention personnel with a basis for rapid epidemic screening and disease diagnosis, thus playing an important role in urban epidemic prevention and control.

[0012] Intelligent early warning technology for infectious diseases typically employs two approaches. One approach involves using individual monitoring on public terminals to analyze the probability of infection for each individual, thus achieving the goal of individual epidemic early warning and management. The other approach utilizes macro-level big data analysis of the population, employing artificial intelligence algorithms to identify the relationship between multi-dimensional data and epidemic spread, thereby enabling the analysis and early warning of epidemic transmission.

[0013] However, existing intelligent early warning technologies for infectious diseases can only perform deep learning from existing historical data, enabling predictive models to predict the symptoms and types of infectious diseases. But they lack the ability to predict the development of future infectious diseases and cannot provide users with possible future trends of infectious disease outbreaks or provide early warnings of outbreaks. Summary of the Invention

[0014] To address the technical problems existing in the prior art, embodiments of the present invention provide an artificial intelligence-based real-time monitoring and early warning system for infectious diseases, its application, and electronic equipment. The technical solution is as follows:

[0015] On the one hand, an artificial intelligence-based method for real-time monitoring and early warning of infectious diseases is provided, including the following steps:

[0016] S1. Based on historical transmission data of infectious diseases and viral evolution data caused by gene mutation and genotyping, construct the corresponding infectious disease variation prediction model Qfa and deploy it on the backend server.

[0017] S2. Real-time monitoring data of infectious diseases are collected and imported into the infectious disease variation prediction model Qfa. The infectious disease variation prediction model Qfa performs real-time and evolutionary bidirectional fusion prediction of infectious diseases.

[0018] S3. Based on the prediction results in different directions, issue corresponding Class I infectious disease warnings and / or Class II infectious disease warnings to the front end respectively.

[0019] As an optional embodiment of the present invention, optionally, S1, based on historical transmission data of infectious diseases and viral evolution data caused by gene mutations and genotyping, a corresponding infectious disease variation prediction model Qfa is constructed and deployed on a backend server, including:

[0020] S101. Collect historical transmission data of infectious diseases, wherein the historical transmission data includes different infectious disease virus types and the corresponding infectious disease virus gene sequence-GS and transmission attribute-AT, as well as the corresponding infectious disease type.

[0021] S102. Based on the convolutional neural network (CNN) model, perform deep learning on the historical transmission data to obtain a real-time prediction model Qa for real-time prediction of infectious diseases, and save the model file of the real-time prediction model Qa to the model database.

[0022] S103. Configure the corresponding viral evolution data caused by gene mutation and genotyping;

[0023] S104. Perform deep learning on the virus evolution data to construct a virus evolution model Qf for infectious disease viruses. The virus evolution model Qf is used to predict the future mutation and spread of infectious diseases.

[0024] S105. The virus evolution model Qf is integrated into the real-time prediction model Qa to obtain the infectious disease mutation prediction model Qfa, which is used to provide real-time and future prediction and early warning services for infectious diseases.

[0025] As an optional embodiment of the present invention, step S101, after collecting historical transmission data of infectious diseases, may further include:

[0026] The historical transmission data is preprocessed, and gene sequence markers are performed on different types of infectious disease viruses, wherein:

[0027] (1) The gene sequences that need to be labeled include:

[0028] Normal gene sequence - Nt and mutant gene sequence - M;

[0029] (2) The marked content includes:

[0030] The infectious disease virus type of the normal gene sequence -Nt, the corresponding infectious disease virus gene sequence -Nt.GS and transmission attribute -Nt.AT, and the corresponding first infectious disease type are labeled;

[0031] The infectious disease virus type of the mutant gene sequence -M, the corresponding infectious disease virus gene sequence -M.GS and transmission attribute -M.AT, and the corresponding secondary infectious disease type are labeled;

[0032] The preprocessed historical propagation data is saved to the background database.

[0033] As an optional embodiment of the present invention, optionally, S103, configuring corresponding viral evolution data due to gene mutation and genotyping, includes:

[0034] A trend prediction model Tp based on a trend prediction algorithm is pre-constructed;

[0035] Based on evolutionary theory, corresponding viral evolution data caused by gene mutation and genotyping were prepared and configured respectively.

[0036] The virus evolution data is imported into the trend prediction model Tp model. The trend prediction model Tp model learns the virus evolution data caused by gene mutation and genotyping based on the trend prediction algorithm, and learns and generates corresponding virus evolution data.

[0037] The virus evolution data is cached in the background database.

[0038] As an optional embodiment of the present invention, optionally, in step S104, deep learning is performed on the virus evolution data to construct a virus evolution model Qf for infectious disease viruses. The virus evolution model Qf is used to predict future mutations and spread of infectious diseases, including:

[0039] The virus evolution data is imported into a preset deep learning model;

[0040] The virus evolution data is learned by using a convolutional neural network to study the infectious disease evolution trend characteristics based on mutation and genotyping, and the corresponding virus evolution model Qf is generated. The model file of the virus evolution model Qf is then saved to the model database.

[0041] As an optional embodiment of the present invention, step S105, after integrating the virus evolution model Qf into the real-time prediction model Qa, further includes:

[0042] Internal communication between the virus evolution model Qf and the real-time prediction model Qa is established through an API interface;

[0043] After the real-time prediction model Qa receives the collected real-time monitoring data of infectious diseases, it synchronizes it to the virus evolution model Qf through the API interface.

[0044] As an optional embodiment of the present invention, step S105, after integrating the virus evolution model Qf into the real-time prediction model Qa, further includes:

[0045] External communication between the infectious disease variation prediction model Qfa and the backend database is established via a USB interface.

[0046] When the background database is updated with new viral evolution data caused by gene mutations and genotyping, the viral evolution model Qf is trained using the new viral evolution data caused by gene mutations and genotyping.

[0047] On the other hand, an artificial intelligence-based real-time monitoring and early warning system for infectious diseases is provided to implement the aforementioned artificial intelligence-based real-time monitoring and early warning method for infectious diseases, including:

[0048] An infectious disease surveillance system is used to collect real-time monitoring data on infectious diseases and transmit it to a back-end server.

[0049] The backend server is used to import the real-time monitoring data into the pre-deployed infectious disease mutation prediction model Qfa. The infectious disease mutation prediction model Qfa performs real-time and evolutionary bidirectional fusion prediction of infectious diseases, and issues corresponding Class I infectious disease warnings and / or Class II infectious disease warnings to the front end according to the prediction results in different directions.

[0050] The front-end large screen is used to display the prediction results in different directions and to respond to the warning of the first type of infectious disease and / or the warning of the second type of infectious disease;

[0051] The infectious disease monitoring system and the front-end large screen are respectively connected to the back-end server.

[0052] On the other hand, an application of an artificial intelligence-based method for real-time monitoring and early warning of infectious diseases is provided. The application involves using the disease mutation prediction model Qfa to perform real-time and evolutionary bidirectional fusion prediction of infectious diseases.

[0053] On the other hand, an electronic device is provided, comprising: a processor; and a memory storing computer-readable instructions, which, when executed by the processor, implement any of the methods described above for real-time monitoring and early warning of infectious diseases based on artificial intelligence.

[0054] On the other hand, a computer-readable storage medium is provided, wherein at least one instruction is stored in the storage medium, the at least one instruction being loaded and executed by a processor to implement any of the above-described methods for real-time monitoring and early warning of infectious diseases based on artificial intelligence.

[0055] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0056] This invention constructs a corresponding infectious disease mutation prediction model, Qfa, based on historical transmission data of infectious diseases and viral evolution data caused by gene mutations and genotyping, and deploys it on a backend server. Real-time monitoring data of infectious diseases is collected and imported into the Qfa model, which then performs bidirectional fusion predictions of infectious diseases in both real-time and evolutionary directions. Based on the prediction results in different directions, corresponding Class I and / or Class II infectious disease warnings are issued to the front end. This invention combines real-time and evolutionary prediction models to predict the current and future spread of infectious diseases, integrating future viral transmission and evolutionary characteristics. It provides management departments with intelligent epidemic transmission analysis and early warning, as well as infectious disease outbreak trend prediction, enabling them to make early warning judgments and reduce the difficulty of prevention and control. Attached Figure Description

[0057] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0058] Figure 1 This is a flowchart of a method for real-time monitoring and early warning of infectious diseases based on artificial intelligence, provided by an embodiment of the present invention.

[0059] Figure 2 This is a schematic diagram of the Qfa prediction model for infectious disease mutations provided in an embodiment of the present invention;

[0060] Figure 3 This is a block diagram of an artificial intelligence-based real-time monitoring and early warning system for infectious diseases provided in an embodiment of the present invention;

[0061] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0062] The technical solution of the present invention is described below in conjunction with the accompanying drawings.

[0063] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as an "exemplary" in the present invention should not be interpreted as being preferred or advantageous over other embodiments or designs. Rather, the use of the word "exemplary" is intended to present concepts in a concrete manner. Furthermore, in the embodiments of the present invention, "and / or" can mean both or either of the two.

[0064] In the embodiments of the present invention, the terms "image" and "picture" may be used interchangeably. It should be noted that, when the distinction between them is not emphasized, their intended meanings are the same. The terms "of," "corresponding," and "corresponding" may be used interchangeably. It should be noted that, when the distinction between them is not emphasized, their intended meanings are the same.

[0065] In this embodiment of the invention, sometimes a subscript such as W1 may be mistakenly written as a non-subscript form such as W1. When the difference is not emphasized, the meaning they express is the same.

[0066] In order to make the technical problems, technical solutions and advantages to be solved by the present invention clearer, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0067] Example 1

[0068] This invention provides a method for real-time monitoring and early warning of infectious diseases based on artificial intelligence. This method can be implemented by an electronic device, which can be a terminal or a server. Figure 1 The flowchart shown is for a real-time monitoring and early warning method for infectious diseases based on artificial intelligence. The processing flow of this method may include the following steps:

[0069] like Figure 1 As shown, on the one hand, an artificial intelligence-based method for real-time monitoring and early warning of infectious diseases is provided, including the following steps:

[0070] S1. Based on historical transmission data of infectious diseases and viral evolution data caused by gene mutation and genotyping, construct the corresponding infectious disease variation prediction model Qfa and deploy it on the backend server.

[0071] S2. Real-time monitoring data of infectious diseases are collected and imported into the infectious disease variation prediction model Qfa. The infectious disease variation prediction model Qfa performs real-time and evolutionary bidirectional fusion prediction of infectious diseases.

[0072] S3. Based on the prediction results in different directions, issue corresponding Class I infectious disease warnings and / or Class II infectious disease warnings to the front end respectively.

[0073] This solution combines real-time and evolutionary prediction models to predict the current and future spread of infectious diseases. It integrates the future spread and evolutionary characteristics of viruses to provide management departments with intelligent epidemic spread analysis and early warning, as well as prediction of infectious disease outbreak trends. This enables management departments to make early warning judgments and reduce the difficulty of prevention and control.

[0074] The main technical approach involves using two models to predict and control current and future infectious diseases.

[0075] First, future predictions of infectious diseases are generated based on historical infectious disease data (mainly based on the mutation of viral genes of infectious diseases that may result from the training and learning process). These predictions are used to provide infectious disease prediction data for infectious disease early warning models and to provide data on possible future infectious disease mutations.

[0076] Second, by using clinical infectious disease prediction models built from historical infectious disease data, current real-time monitoring data is used to predict and monitor the emergence of known infectious diseases and unknown new infectious diseases.

[0077] For known infectious diseases, issue a Level 1 infectious disease warning;

[0078] For unknown new infectious diseases, issue a Level II infectious disease warning and feed it back into future prediction models.

[0079] Therefore, the model issues a Level 1 infectious disease warning for infectious diseases predicted based on historical transmission data characteristics, and a Level 2 infectious disease warning for infectious diseases predicted based on viral evolution data characteristics caused by gene mutations and genotyping.

[0080] Historical transmission data of infectious diseases can be obtained from the database of the Center for Disease Control and Prevention, and the specific selection can be done by the administrator.

[0081] Both gene mutation and genotyping can lead to the generation and variation of viruses. First, gene mutation refers to a chemical reaction that alters the base sequence of a gene's DNA. This change can be a single base shift or the deletion or displacement of thousands of bases. These changes can alter the characteristics of a virus, such as its mode of transmission, mode of infection, and symptoms.

[0082] Viruses are the smallest microorganisms in the world; they must parasitize the cells of organic matter to survive and reproduce. The viral life cycle includes steps such as entering a host cell, replicating the viral genome, producing viral proteins, and assembling viral particles. During this process, the viral genome may mutate, leading to the creation of new viral strains. These new strains may possess different characteristics, such as stronger transmissibility, higher infectivity, or stronger drug resistance.

[0083] Genotyping refers to the genetic differences between different individuals or populations. In viruses, genotyping can lead to differences between viral strains, which may affect aspects such as viral transmission, infection, and pathogenicity. For example, the novel coronavirus has undergone multiple mutations, resulting in various different viral strains, including alpha, beta, gamma, and delta strains. These different strains differ in transmissibility, infectivity, and pathogenicity, posing challenges to epidemic prevention and control and vaccine development.

[0084] Gene mutations and genotyping can both lead to the generation and variation of viruses, and these changes may affect the spread, infection, and pathogenicity of viruses.

[0085] Viral evolution data resulting from gene mutations and genotyping can be combined with historical data from virology laboratories and viral evolution to screen and analyze, thereby obtaining corresponding viral evolution data resulting from gene mutations and genotyping.

[0086] Viral evolution occurs primarily through two mechanisms: gene mutation and gene recombination.

[0087] Genetic mutation refers to the natural variation of a virus's genes, resulting in the formation of new viral species. This mutation may be due to errors occurring during viral replication, causing changes in the viral gene sequence. These changes may endow the virus with new characteristics, such as stronger pathogenicity or higher transmission efficiency.

[0088] Gene recombination refers to the merging of a portion of the genes of two different viruses, resulting in a new virus. This usually occurs when viruses simultaneously infect the same cell, and their gene sequences are exchanged within the cell, thus creating a new type of virus.

[0089] Both of these evolutionary pathways result from viral self-replication, enabling viruses to adapt to different environments, survive, and create new species. Meanwhile, human activity is also a major contributing factor to viral evolution. Therefore, research into viral evolutionary types helps us better understand the mechanisms of viral transmission and pathogenesis, and to implement effective prevention and control measures.

[0090] Furthermore, based on the type of viral nucleic acid, viral evolution can be divided into two types: DNA viruses and RNA viruses. RNA viruses evolve relatively quickly because errors are more likely to occur during their replication process, leading to more frequent changes in their viral gene sequences. Therefore, RNA viruses are more prone to developing new variants and subtypes.

[0091] Therefore, viral evolution data resulting from gene mutations and genotyping can be collected using virus tracking and monitoring methods employed by virology laboratories and disease control centers.

[0092] The infectious disease mutation prediction model Qfa is generated by training based on the historical transmission data of the aforementioned infectious diseases and the viral evolution data caused by gene mutations and genotyping.

[0093] This AI-based method for dynamic monitoring of infectious diseases mainly includes the following steps:

[0094] 1. Data Collection: First, it is necessary to collect various data on infectious diseases, including but not limited to information on the number of cases, the rate of transmission, geographical location, population distribution, and medical resources. This data can come from multiple sources, such as public health departments, medical institutions, and social media.

[0095] 2. Data Preprocessing: The collected data needs to undergo preprocessing steps such as cleaning, organizing, and normalization to facilitate subsequent analysis and modeling. For example, it is necessary to remove duplicate, erroneous, or invalid data, and to standardize the data to eliminate dimensional differences between different data sources.

[0096] 3. Feature Extraction: Extract features related to the dynamics of the infectious disease from the preprocessed data. These features may include time series data on the number of cases, trends in the rate of transmission, and geographic spatial distribution. These features will be used as input for subsequent model training.

[0097] 4. Model Construction: Based on the extracted features, a dynamic monitoring model for infectious diseases is constructed using machine learning or deep learning algorithms. The goal of the model is to predict future trends in infectious diseases based on historical data.

[0098] The operation process will be described in detail below.

[0099] As an optional embodiment of the present invention, optionally, S1, based on historical transmission data of infectious diseases and viral evolution data caused by gene mutations and genotyping, a corresponding infectious disease variation prediction model Qfa is constructed and deployed on a backend server, including:

[0100] S101. Collect historical transmission data of infectious diseases, wherein the historical transmission data includes different infectious disease virus types and the corresponding infectious disease virus gene sequence-GS and transmission attribute-AT, as well as the corresponding infectious disease type.

[0101] S102. Based on the convolutional neural network (CNN) model, perform deep learning on the historical transmission data to obtain a real-time prediction model Qa for real-time prediction of infectious diseases, and save the model file of the real-time prediction model Qa to the model database.

[0102] S103. Configure the corresponding viral evolution data caused by gene mutation and genotyping;

[0103] S104. Perform deep learning on the virus evolution data to construct a virus evolution model Qf for infectious disease viruses. The virus evolution model Qf is used to predict the future mutation and spread of infectious diseases.

[0104] S105. The virus evolution model Qf is integrated into the real-time prediction model Qa to obtain the infectious disease mutation prediction model Qfa, which is used to provide real-time and future prediction and early warning services for infectious diseases.

[0105] The main steps are as follows: learning and recognizing the features of the two types of data respectively.

[0106] First, we learn the data characteristics in historical transmission data, especially the gene sequences (GS) and transmission attributes (AT) of different infectious disease virus types and their corresponding infectious disease types, as well as the types of infectious diseases they cause, to obtain a real-time prediction model Qa.

[0107] Second, the second step is to train and identify the characteristics of the viral evolution data caused by gene mutation and genotyping to obtain the viral evolution model Qf.

[0108] Third, the virus evolution model Qf is integrated into the real-time prediction model Qa to obtain the infectious disease mutation prediction model Qfa.

[0109] There are several main ways to fuse two CNN models into one model:

[0110] 1. Feature Fusion: This method fuses features from different levels of two CNN models. This can be achieved by concatenating or weighting the feature maps of the two models after a convolutional or fully connected layer, and then processing them through subsequent network layers. This utilizes the features extracted by each model, improving the model's expressive power and robustness.

[0111] 2. Decision Fusion: This method fuses the outputs of two CNN models. After the final layer of each model, their outputs are weighted and summed or voted on to obtain the final decision. This approach fully utilizes the prediction results of both models, improving prediction accuracy and stability.

[0112] Specifically, the feature maps of the virus evolution model Qf can be connected in parallel and spliced ​​onto the neural network of the real-time prediction model Qa, so that the real-time prediction model Qa can simultaneously possess the feature maps that the virus evolution model Qf can recognize.

[0113] The training method for the convolutional neural network model will not be elaborated in this embodiment. Deep learning methods can include self-supervised learning or other models. We preferentially use two CNN models to train simultaneously on the data features of two categories.

[0114] As an optional embodiment of the present invention, step S101, after collecting historical transmission data of infectious diseases, may further include:

[0115] The historical transmission data is preprocessed, and gene sequence markers are performed on different types of infectious disease viruses, wherein:

[0116] (1) The gene sequences that need to be labeled include:

[0117] Normal gene sequence - Nt and mutant gene sequence - M;

[0118] (2) The marked content includes:

[0119] The infectious disease virus type of the normal gene sequence -Nt, the corresponding infectious disease virus gene sequence -Nt.GS and transmission attribute -Nt.AT, and the corresponding first infectious disease type are labeled;

[0120] The infectious disease virus type of the mutant gene sequence -M, the corresponding infectious disease virus gene sequence -M.GS and transmission attribute -M.AT, and the corresponding secondary infectious disease type are labeled;

[0121] The preprocessed historical propagation data is saved to the background database.

[0122] Infectious diseases are also divided into normal gene sequences (Nt) and mutant gene sequences (M). Therefore, when constructing the real-time prediction model Qa, its training dataset is divided into normal gene sequences (Nt) and mutant gene sequences (M), and corresponding historical transmission data subsets are constructed by labeling them respectively.

[0123] Each subset contains corresponding labeling data for the first infectious disease type and labeling data for the second infectious disease type.

[0124] The administrator can manually mark it.

[0125] The real-time prediction model Qa can identify the first infectious disease type labeled data and the second infectious disease type labeled data respectively, thereby improving the identification accuracy.

[0126] As an optional embodiment of the present invention, optionally, S103, configuring corresponding viral evolution data due to gene mutation and genotyping, includes:

[0127] A trend prediction model Tp based on a trend prediction algorithm is pre-constructed;

[0128] Based on evolutionary theory, corresponding viral evolution data caused by gene mutation and genotyping were prepared and configured respectively.

[0129] The virus evolution data is imported into the trend prediction model Tp model. The trend prediction model Tp model learns the virus evolution data caused by gene mutation and genotyping based on the trend prediction algorithm, and learns and generates corresponding virus evolution data.

[0130] The virus evolution data is cached in the background database.

[0131] Viral data resulting from gene mutations and genotyping can be obtained by combining virus prevention data from virology laboratories and disease control centers, thus providing data on virus transmission caused by gene mutations and genotyping.

[0132] In order to obtain the virus evolution model Qf generated by training based on virus evolution data caused by gene mutation and genotyping, a trend prediction algorithm was used to acquire virus evolution data, thereby obtaining data such as the virus types that may evolve in the future.

[0133] Based on evolutionary theory, corresponding viral evolution data caused by gene mutation and genotyping are prepared and configured. This is set by the administrator of the biological laboratory according to viral evolution experiments and theories. Alternatively, a predictive model can be used to learn from historical viral data and generate possible viral evolution data.

[0134] In this embodiment, trend prediction algorithms are also used in the medical field, where artificial intelligence is used to predict certain health conditions. For example, Google has developed a trend prediction algorithm that can predict a person's time of death with an accuracy rate of up to 95%. This algorithm analyzes data from electronic health records to predict a patient's risk of death, readmission risk, prolonged hospital stay, and discharge diagnosis.

[0135] In summary, AI-based future prediction technology is a rapidly developing field. As technology advances and data accumulates, the accuracy and reliability of these predictive models will continue to improve. However, we also need to be aware of the inherent uncertainties in prediction and maintain a cautious and objective attitude when using these technologies.

[0136] Trend forecasting algorithms are statistical forecasting methods used to predict future trends based on historical data. These algorithms are based on the assumption that future trends will follow similar patterns to past trends. Trend forecasting algorithms are commonly used for time series data, such as stock prices, sales data, and temperatures.

[0137] The main types of trend prediction algorithms include:

[0138] 1. Linear Regression: Linear regression is a predictive model that assumes a linear relationship between the dependent variable (the value to be predicted) and the independent variables (predictors). By fitting a straight line to minimize the error between the predicted and actual values, linear regression can predict future trends.

[0139] 2. Exponential Smoothing: Exponential smoothing is a simple time series forecasting method that predicts future values ​​by calculating a weighted average of historical data. The weights decrease over time, so more recent data has a greater impact on the forecast.

[0140] 3. ARIMA Model: ARIMA (Autoregressive Integral Moving Average) is a powerful time series forecasting method that can handle data with trends and seasonal effects. It describes the historical behavior of data by fitting a model and uses that model to predict future values.

[0141] 4. Neural Networks: Neural networks are machine learning algorithms that can learn and simulate complex data patterns. For nonlinear or complex time series data, neural networks can be an effective predictive tool.

[0142] Trend prediction algorithms can help us understand the past of data and predict the future.

[0143] Therefore, the trend prediction model Tp model in this scheme can be either a linear regression model or an ARIMA model to predict virus evolution data.

[0144] As an optional embodiment of the present invention, optionally, in step S104, deep learning is performed on the virus evolution data to construct a virus evolution model Qf for infectious disease viruses. The virus evolution model Qf is used to predict future mutations and spread of infectious diseases, including:

[0145] The virus evolution data is imported into a preset deep learning model;

[0146] The virus evolution data is learned by using a convolutional neural network to study the infectious disease evolution trend characteristics based on mutation and genotyping, and the corresponding virus evolution model Qf is generated. The model file of the virus evolution model Qf is then saved to the model database.

[0147] Deep learning models are a type of machine learning method based on artificial neural networks. They simulate the connection patterns of neurons in the human brain, constructing a network structure with multiple hidden layers to achieve efficient feature learning and classification of complex data. The core of deep learning models lies in their powerful feature extraction capabilities, automatically learning useful information from raw data and avoiding the tedious process of manually designing features required in traditional machine learning methods.

[0148] Common deep learning model architectures include Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Long Short-Term Memory Networks (LSTMs), Gated Recurrent Units (GRUs), and Generative Adversarial Networks (GANs). CNNs are primarily used for image and video processing tasks, extracting local features and spatial relationships from images and videos. Recurrent Neural Networks are mainly used for processing sequential data, such as text and speech, learning contextual information within sequences and capturing long-term dependencies in input data. Autoencoders are unsupervised learning models used for tasks such as data compression, denoising, and feature extraction, learning low-dimensional representations of input data. Residual Networks are used to address the vanishing gradient problem in deep neural networks, enabling the training of deeper neural networks.

[0149] Deep learning models play a crucial role in various artificial intelligence applications, such as image classification, object detection and localization, facial recognition, and biometrics. Furthermore, there are diverse optimization methods for deep learning models, including data preprocessing, model design, hyperparameter tuning, regularization, model ensemble, data augmentation, and fine-tuning.

[0150] This solution primarily utilizes recurrent neural networks (RNNs) to train the virus evolution model Qf. For specific instructions, please refer to the training methods for RNNs.

[0151] As an optional embodiment of the present invention, step S105, after integrating the virus evolution model Qf into the real-time prediction model Qa, further includes:

[0152] Internal communication between the virus evolution model Qf and the real-time prediction model Qa is established through an API interface;

[0153] After the real-time prediction model Qa receives the collected real-time monitoring data of infectious diseases, it synchronizes it to the virus evolution model Qf through the API interface.

[0154] As an optional embodiment of the present invention, step S105, after integrating the virus evolution model Qf into the real-time prediction model Qa, further includes:

[0155] External communication between the infectious disease variation prediction model Qfa and the backend database is established via a USB interface.

[0156] When the background database is updated with new viral evolution data caused by gene mutations and genotyping, the viral evolution model Qf is trained using the new viral evolution data caused by gene mutations and genotyping.

[0157] like Figure 2As shown, the infectious disease mutation prediction model Qfa includes a virus evolution model Qf connected via an API interface and the real-time prediction model Qa. Its operating mechanism is as follows:

[0158] After the real-time prediction model Qa receives the collected real-time monitoring data of infectious diseases, it synchronizes it to the virus evolution model Qf through the API interface;

[0159] After the two models make predictions, the infectious disease mutation prediction model Qfa transmits the prediction results of the virus evolution model Qf and the real-time prediction model Qa to the background database via USB interface for storage.

[0160] The model's data interfaces, etc., can be implemented by the corresponding interface programs.

[0161] After a disease control center collects real-time monitoring data of infectious diseases, it can import the infectious disease mutation prediction model Qfa. The infectious disease mutation prediction model Qfa performs bidirectional fusion prediction of infectious diseases in real time and in the direction of evolution (the virus evolution model Qf and the real-time prediction model Qa process and identify the corresponding data in the real-time monitoring data and output prediction results respectively). Based on the prediction results in different directions, corresponding Class I infectious disease warnings and / or Class II infectious disease warnings are issued to the front end respectively.

[0162] The prediction results can be sent and displayed on the 320-inch large screen at the CDC for data visualization analysis. The data visualization process will not be elaborated upon in this embodiment.

[0163] Example 2

[0164] On the other hand, it provides an artificial intelligence-based real-time monitoring and early warning system for infectious diseases.

[0165] Figure 3 This is a block diagram illustrating an artificial intelligence-based real-time monitoring and early warning system for infectious diseases, according to an exemplary embodiment. The device is used for an artificial intelligence-based real-time monitoring and early warning method for infectious diseases. (Refer to...) Figure 3 The device includes an infectious disease monitoring system 300, a back-end server 310, and a front-end large screen 320.

[0166] in:

[0167] The Infectious Disease Surveillance System 300 is used to collect real-time monitoring data of infectious diseases and transmit it to the back-end server.

[0168] The backend server 310 is used to import the real-time monitoring data into the pre-deployed infectious disease mutation prediction model Qfa. The infectious disease mutation prediction model Qfa performs real-time and evolutionary bidirectional fusion prediction of infectious diseases, and issues corresponding Class I infectious disease warnings and / or Class II infectious disease warnings to the front end according to the prediction results in different directions.

[0169] The front-end large screen 320 is used to display the prediction results in different directions and respond to the warning of the first type of infectious disease and / or the warning of the second type of infectious disease;

[0170] The infectious disease monitoring system and the front-end large screen are respectively connected to the back-end server.

[0171] Please understand the specific system interactions by referring to the methods described above.

[0172] Example 3

[0173] On the other hand, an application of an artificial intelligence-based method for real-time monitoring and early warning of infectious diseases is provided. The application involves using the disease mutation prediction model Qfa to perform real-time and evolutionary bidirectional fusion prediction of infectious diseases.

[0174] Example 4

[0175] On the other hand, a computer-readable storage medium is provided, wherein at least one instruction is stored in the storage medium, the at least one instruction being loaded and executed by a processor to implement any of the above-described methods for real-time monitoring and early warning of infectious diseases based on artificial intelligence.

[0176] Example 5

[0177] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention, such as... Figure 4 As shown, the electronic device may include the above-mentioned Figure 3 The illustrated system is an artificial intelligence-based real-time monitoring and early warning system for infectious diseases. Optionally, the electronic device 410 may include a first processor 2001.

[0178] Optionally, the electronic device 410 may also include a memory 2002 and a transceiver 2003.

[0179] The first processor 2001, memory 2002, and transceiver 2003 can be connected via a communication bus.

[0180] The following combination Figure 4 A detailed description of each component of electronic device 410 is provided below:

[0181] The first processor 2001 is the control center of the electronic device 410. It can be a single processor or a collective term for multiple processing elements. For example, the first processor 2001 can be one or more central processing units (CPUs), application-specific integrated circuits (ASICs), or one or more integrated circuits configured to implement embodiments of the present invention, such as one or more digital signal processors (DSPs), or one or more field-programmable gate arrays (FPGAs).

[0182] Optionally, the first processor 2001 can perform various functions of the electronic device 410 by running or executing software programs stored in the memory 2002 and calling data stored in the memory 2002.

[0183] In a specific implementation, as one example, the first processor 2001 may include one or more CPUs, for example... Figure 4 CPU0 and CPU1 are shown in the diagram.

[0184] In a specific implementation, as one example, the electronic device 410 may also include multiple processors, for example... Figure 4 The first processor 2001 and the second processor 2004 are shown in the diagram. Each of these processors can be a single-core processor (single-CPU) or a multi-core processor (multi-CPU). Here, "processor" can refer to one or more devices, circuits, and / or processing cores used to process data (e.g., computer program instructions).

[0185] The memory 2002 is used to store the software program that executes the present invention, and is controlled by the first processor 2001 to execute it. The specific implementation method can be referred to the above method embodiment, and will not be repeated here.

[0186] Optionally, the memory 2002 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto. The memory 2002 may be integrated with the first processor 2001 or may exist independently and be connected via the interface circuit of the electronic device 410. Figure 4 (Not shown in the figure) is coupled to the first processor 2001, and the embodiments of the present invention do not specifically limit this.

[0187] The transceiver 2003 is used to communicate with network devices or with terminal devices.

[0188] Alternatively, transceiver 2003 may include a receiver and a transmitter. Figure 4 (Not shown separately). The receiver is used to implement the receiving function, and the transmitter is used to implement the sending function.

[0189] Optionally, the transceiver 2003 can be integrated with the first processor 2001, or it can exist independently and be connected via the interface circuit of the electronic device 410. Figure 4 (Not shown in the figure) is coupled to the first processor 2001, and the embodiments of the present invention do not specifically limit this.

[0190] It should be noted that, Figure 4 The structure of the electronic device 410 shown does not constitute a limitation on the router. Actual knowledge structure identification devices may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0191] Furthermore, the technical effects of the electronic device 410 can be referenced from the technical effects of the artificial intelligence-based real-time monitoring and early warning method for infectious diseases described in the above method embodiments, and will not be repeated here.

[0192] It should be understood that the first processor 2001 in this embodiment of the invention may be a central processing unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0193] It should also be understood that the memory in the embodiments of the present invention can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous DRAM (DDR SDRAM), enhanced synchronous DRAM (ESDRAM), synchronous linked DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0194] The above embodiments can be implemented, in whole or in part, by software, hardware (such as circuits), firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0195] It should be understood that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. A and B can be singular or plural. Additionally, the character " / " in this article generally indicates an "or" relationship between the preceding and following related objects, but it can also represent an "and / or" relationship. Please refer to the context for a more accurate understanding.

[0196] In this invention, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of a single item or a plurality of items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be a single item or multiple items.

[0197] It should be understood that, in various embodiments of the present invention, the order of the above-mentioned process numbers does not imply 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 on the implementation process of the embodiments of the present invention.

[0198] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0199] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the devices, apparatuses, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0200] In the several embodiments provided by this invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0201] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0202] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0203] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0204] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for real-time monitoring and early warning of infectious diseases based on artificial intelligence, characterized in that, Includes the following steps: S1. Based on historical transmission data of infectious diseases and viral evolution data caused by gene mutations and genotyping, construct a corresponding infectious disease variation prediction model Qfa and deploy it on the backend server, including: S101. Collect historical transmission data of infectious diseases, wherein the historical transmission data includes different infectious disease virus types and the corresponding infectious disease virus gene sequence-GS and transmission attribute-AT, as well as the corresponding infectious disease type. S102. Based on the convolutional neural network (CNN) model, perform deep learning on the historical transmission data to obtain a real-time prediction model Qa for real-time prediction of infectious diseases, and save the model file of the real-time prediction model Qa to the model database. S103. Configure the corresponding viral evolution data caused by gene mutation and genotyping, including: A trend prediction model Tp based on a trend prediction algorithm is pre-constructed; Based on evolutionary theory, corresponding viral evolution data caused by gene mutation and genotyping were prepared and configured respectively. The virus evolution data is imported into the trend prediction model Tp model. The trend prediction model Tp model learns the virus evolution data caused by gene mutation and genotyping based on the trend prediction algorithm, and learns and generates corresponding virus evolution data. Cache the virus evolution data to the backend database; S104. Perform deep learning on the virus evolution data to construct a virus evolution model Qf for infectious disease viruses. The virus evolution model Qf is used to predict the future mutation and spread of infectious diseases, including: The virus evolution data is imported into a preset deep learning model; Based on the convolutional neural network, the virus evolution data is used to learn the characteristics of infectious disease evolution trends in terms of mutation and genotyping, and the corresponding virus evolution model Qf is generated. The model file of the virus evolution model Qf is then saved to the model database. S105. The virus evolution model Qf is integrated into the real-time prediction model Qa to obtain the infectious disease mutation prediction model Qfa, which is used to provide real-time and future prediction and early warning services for infectious diseases. S2. Real-time monitoring data of infectious diseases are collected and imported into the infectious disease variation prediction model Qfa. The infectious disease variation prediction model Qfa performs real-time and evolutionary bidirectional fusion prediction of infectious diseases. S3. Based on the prediction results in different directions, issue corresponding Class I infectious disease warnings and / or Class II infectious disease warnings to the front end respectively.

2. The method for real-time monitoring and early warning of infectious diseases based on artificial intelligence according to claim 1, characterized in that, In step S101, after collecting historical transmission data of infectious diseases, the following steps are also included: The historical transmission data is preprocessed, and gene sequence markers are performed on different types of infectious disease viruses, wherein: (1) The gene sequences that need to be labeled include: Normal gene sequence - Nt and mutant gene sequence - M; (2) The marked content includes: The infectious disease virus type of the normal gene sequence -Nt, the corresponding infectious disease virus gene sequence -Nt.GS and transmission attribute -Nt.AT, and the corresponding first infectious disease type are labeled; The infectious disease virus type of the mutant gene sequence -M, the corresponding infectious disease virus gene sequence -M.GS and transmission attribute -M.AT, and the corresponding secondary infectious disease type are labeled; The preprocessed historical propagation data is saved to the background database.

3. The method for real-time monitoring and early warning of infectious diseases based on artificial intelligence according to claim 1, characterized in that, In step S105, after integrating the virus evolution model Qf into the real-time prediction model Qa, the following is also included: Internal communication between the virus evolution model Qf and the real-time prediction model Qa is established through an API interface; After the real-time prediction model Qa receives the collected real-time monitoring data of infectious diseases, it synchronizes it to the virus evolution model Qf through the API interface.

4. The method for real-time monitoring and early warning of infectious diseases based on artificial intelligence according to claim 1, characterized in that, In step S105, after integrating the virus evolution model Qf into the real-time prediction model Qa, the following is also included: External communication between the infectious disease variation prediction model Qfa and the backend database is established via a USB interface. When the background database is updated with new viral evolution data caused by gene mutations and genotyping, the viral evolution model Qf is trained using the new viral evolution data caused by gene mutations and genotyping.

5. The method for real-time monitoring and early warning of infectious diseases based on artificial intelligence according to claim 1, characterized in that, The application of the method lies in using the disease variation prediction model Qfa to perform real-time and evolutionary bidirectional fusion prediction of infectious diseases.

6. An artificial intelligence-based real-time monitoring and early warning system for infectious diseases, used to implement the artificial intelligence-based real-time monitoring and early warning method for infectious diseases as described in any one of claims 1-5, characterized in that, include: An infectious disease surveillance system is used to collect real-time monitoring data on infectious diseases and transmit it to a back-end server. The backend server is used to import the real-time monitoring data into the pre-deployed infectious disease mutation prediction model Qfa. The infectious disease mutation prediction model Qfa performs real-time and evolutionary bidirectional fusion prediction of infectious diseases, and issues corresponding Class I infectious disease warnings and / or Class II infectious disease warnings to the front end according to the prediction results in different directions. The front-end large screen is used to display the prediction results in different directions and to respond to the warning of the first type of infectious disease and / or the warning of the second type of infectious disease; The infectious disease monitoring system and the front-end large screen are respectively connected to the back-end server.

7. An electronic device, characterized in that, include: processor; Memory used to store processor-executable instructions; The processor is configured to implement, when executing the executable instructions, the method for real-time monitoring and early warning of infectious diseases based on artificial intelligence as described in any one of claims 1-5.

Images