Artificial intelligence-based infectious disease prediction methods and related equipment

Abstract

The present application proposes an artificial intelligence-based infectious disease prediction method, device, electronic device and storage medium. The artificial intelligence-based infectious disease prediction method includes: constructing a graph structure based on the geographical location of a preset area; storing the number of infectious disease cases in the preset area and the population flow data between adjacent preset areas within a historical period to obtain a training set; building an initial infectious disease prediction model based on the graph structure, the initial infectious disease prediction model includes a spatial association module, a time series processing module and a prediction module; training the initial infectious disease prediction model based on the training set to obtain an infectious disease prediction optimization model; collecting the number of infectious disease cases in all preset areas within a preset time period and the population flow data between adjacent preset areas, and inputting them into the infectious disease prediction optimization model to obtain infectious disease prediction results for each preset area. The present application can integrate the spatial and temporal correlation of infectious disease data to improve the accuracy of infectious disease prediction in the field of digital medicine.

Description

Technical Field

[0001] The present application relates to the fields of artificial intelligence and digital medical technology, and in particular to an artificial intelligence-based infectious disease prediction method, device, electronic device, and storage medium. Background Art

[0002] In the digital healthcare field, infectious diseases like viral influenza can be spread through airborne droplets and interpersonal contact, resulting in high rates of infection and morbidity. Once infected, patients are likely to experience exacerbations of their primary illness, leading to secondary bacterial pneumonia and chronic cardiopulmonary diseases, resulting in significant direct and indirect medical expenses and a greater socioeconomic burden. Therefore, accurate, real-time monitoring and early warning of infectious diseases are of great practical significance to public health and epidemic prevention departments.

[0003] At present, infectious disease prediction results are often obtained by using time series models based on autocorrelation or by establishing regression models using exogenous features such as weather data and public opinion data. However, this method ignores the impact of population mobility on infectious disease predictions and cannot accurately capture the spatiotemporal correlation of infectious disease data in different regions and at different times, resulting in low accuracy of infectious disease prediction results. Summary of the Invention

[0004] In view of the above, it is necessary to propose an artificial intelligence-based infectious disease prediction method and related equipment to solve the technical problem of how to improve the accuracy of infectious disease prediction results. The related equipment includes an artificial intelligence-based infectious disease prediction device, electronic equipment and storage medium.

[0005] This application provides an artificial intelligence-based infectious disease prediction method, which includes:

[0006] Building a graph structure based on the geographical location of at least one preset area;

[0007] Storing the number of infectious disease cases in the preset area and population flow data between adjacent preset areas over a historical period to obtain a training set;

[0008] Building an initial infectious disease prediction model based on the graph structure, the initial infectious disease prediction model includes a spatial association module, a time series processing module and a prediction module;

[0009] Training the infectious disease prediction initial model based on the training set to obtain an infectious disease prediction optimization model;

[0010] The number of infectious disease cases in all preset areas within a preset time period and the population flow data between adjacent preset areas are collected and input into the infectious disease prediction optimization model to obtain the infectious disease prediction results for each preset area.

[0011] In some embodiments, constructing a graph structure based on the geographic location of at least one preset area includes:

[0012] Assigning an area ID as a unique identifier to each preset area, and using the area ID as node information to obtain a plurality of nodes, wherein the nodes correspond one-to-one to the preset areas;

[0013] For any preset area, obtain all adjacent preset areas of the preset area based on the geographical location, and draw undirected edges connecting the node of the preset area with the nodes of each adjacent preset area;

[0014] Traverse all preset areas and continuously draw undirected edges between nodes. When all preset areas are traversed, the construction of the graph structure is completed.

[0015] In some embodiments, the storing of the number of infectious disease cases in the preset area and the population flow data between adjacent preset areas in the historical period to obtain the training set includes:

[0016] Collect the number of infectious disease cases in each preset area and the population flow data between adjacent preset areas in T consecutive time periods in the historical time, and arrange them in the order of time periods to obtain a sample data;

[0017] Collect the number of infectious disease cases in each preset area in the next adjacent time period of the T consecutive time periods in the historical time as the label data of the sample data;

[0018] Taking the sample data and the label data as a set of sample pairs;

[0019] A plurality of sample pairs are obtained from historical time using the same method, and the plurality of sample pairs are stored to obtain a training set.

[0020] In some embodiments, the input of the initial infectious disease prediction model is the number of infectious disease cases in each preset area in T consecutive time periods and population flow data between adjacent preset areas, and the output is the infectious disease prediction result for each preset area, and the infectious disease prediction result of the preset area is the number of infectious disease cases in the preset area in the next adjacent time period of the T consecutive time periods; the construction of the initial infectious disease prediction model based on the graph structure includes:

[0021] The number of infectious disease cases in the same preset area in T consecutive time periods is used as the infectious disease sequence data of the preset area, and the infectious disease sequence data corresponds to the preset area one by one;

[0022] The time series processing module includes a plurality of time series processing layers, each of which corresponds to the preset areas one by one, and is used to extract features from the corresponding infectious disease sequence data to obtain time series features of each preset area;

[0023] The spatial association module receives the graph structure and calculates the edge weight of each undirected edge in the graph structure based on the infectious disease sequence data and the population flow data between adjacent preset areas to obtain a spatial association graph structure, wherein the edge weight of any undirected edge in the spatial association graph structure represents the correlation coefficient between the two preset areas connected by the undirected edge;

[0024] The prediction module is used to obtain infectious disease prediction results for each preset area based on the spatial association graph structure and the temporal characteristics of the preset area.

[0025] In some embodiments, the step of calculating the edge weight of each undirected edge in the graph structure based on the infectious disease sequence data and the population flow data between adjacent preset areas to obtain a spatial association graph structure includes:

[0026] The population flow data of the same group of adjacent preset areas in T consecutive time periods are used as the population flow sequence data of the adjacent preset areas, and the population flow sequence data corresponds one-to-one to the undirected edges in the graph structure;

[0027] For any undirected edge in the graph structure, the edge weight of the undirected edge satisfies the relationship:

[0028] e i,j =a([((W1h i )||(W1h j ))·(W2b ij )])

[0029] Wherein, a, W1, W2 are the trainable parameters of the spatial association module 20, h i and h j The infectious disease sequence data of the preset area i and the preset area j are respectively, (W1h i )||(W1h j ) means to convert the vector (W1h i ) and vector (W1h j ) for splicing, b ij is the population flow sequence data of the undirected edge between adjacent preset areas i and j, e i,j represents the edge weight of the undirected edge between adjacent preset regions i and j;

[0030] All undirected edges in the graph structure are traversed to obtain the edge weight of each undirected edge, and the edge weight of each undirected edge is written into the graph structure to obtain a spatial association graph structure.

[0031] In some embodiments, obtaining an infectious disease prediction result for each preset area based on the spatial correlation graph structure and the temporal characteristics of the preset area includes:

[0032] Taking any node in the spatial association graph structure as a target node;

[0033] Storing the edge weights of all undirected edges connected to the target node to obtain an edge weight set of the target node;

[0034] The representation vector of the target node is calculated based on the edge weight set, and the representation vector of the target node satisfies the relationship:

[0035]

[0036] Among them, N m Represents all edge weights in the edge weight set, e mk represents the edge weight between the target node m and node k in the edge weight set, v k is the temporal feature of the preset area corresponding to node k, LeakyReLU() is the activation function, and e represents any edge weight in the edge weight set; v m is the temporal characteristics of the preset area corresponding to the target node, is the representation vector of the target node;

[0037] Inputting the representation vector of the target node into the prediction layer in the prediction module to output the infectious disease prediction result of the preset area corresponding to the target node;

[0038] All nodes in the spatial association graph structure are traversed to output infectious disease prediction results for each preset area.

[0039] In some embodiments, training the initial infectious disease prediction model based on the training set to obtain an optimized infectious disease prediction model includes:

[0040] Selecting a preset number of sample pairs from the training set as a training batch, each of the sample pairs comprising sample data and label data;

[0041] Inputting all sample data in the training batch into the infectious disease prediction initial model to obtain an output result for each sample data, wherein the output result includes an infectious disease prediction result for each preset area;

[0042] The mean square error loss is calculated based on the output results and label data of the same sample data in the training batch, and the mean square error loss satisfies the relationship:

[0043]

[0044] Among them, BS is the number of sample pairs in a training batch, M is the number of all preset regions, and y p (q) is the infectious disease prediction result of the preset area p in the output result of sample data q, is the number of infectious disease cases in the preset region p in the label data of sample data q, and MSE is the mean square error loss;

[0045] Using the gradient descent method to find the partial derivative of the mean square error loss to update the parameters of the initial infectious disease prediction model;

[0046] Continuously obtaining training batches from the training set to update the parameters in the initial infectious disease prediction model until the mean square error loss no longer changes, stopping the updating, and obtaining an infectious disease prediction optimization model.

[0047] The present application also provides an artificial intelligence-based infectious disease prediction device, comprising:

[0048] A construction unit, configured to construct a graph structure based on a geographical location of at least one preset area;

[0049] A storage unit is used to store the number of infectious disease cases in the preset area and population flow data between adjacent preset areas in a historical period to obtain a training set;

[0050] A building unit, configured to build an initial infectious disease prediction model based on the graph structure, wherein the initial infectious disease prediction model includes a spatial association module, a time series processing module, and a prediction module;

[0051] A training unit, configured to train the initial infectious disease prediction model based on the training set to obtain an optimized infectious disease prediction model;

[0052] The prediction unit is used to collect the number of infectious disease cases in all preset areas within a preset time period and the population flow data between adjacent preset areas, and input them into the infectious disease prediction optimization model to obtain the infectious disease prediction results for each preset area.

[0053] An embodiment of the present application further provides an electronic device, comprising:

[0054] a memory storing at least one instruction;

[0055] A processor executes instructions stored in the memory to implement the artificial intelligence-based infectious disease prediction method.

[0056] An embodiment of the present application also provides a computer-readable storage medium, which stores at least one instruction, and the at least one instruction is executed by a processor in an electronic device to implement the artificial intelligence-based infectious disease prediction method.

[0057] In summary, the present application directly outputs the infectious disease prediction results for each preset area through an end-to-end infectious disease prediction optimization model. The infectious disease prediction optimization model includes a time series processing module, a spatial correlation module and a prediction module; the time series processing module can capture the time correlation of the number of infectious disease cases in each preset area and obtain the time series characteristics of each preset area; the spatial correlation module can capture the spatial correlation between any preset area and the adjacent preset area with the help of a graph neural network, and the prediction module integrates the time correlation of the same preset area and the spatial correlation between adjacent preset areas to obtain the infectious disease prediction results for each preset area, thereby improving the accuracy of infectious disease prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 This is a flowchart of a preferred embodiment of the artificial intelligence-based infectious disease prediction method involved in this application.

[0059] Figure 2 It is a structural diagram of the initial model for infectious disease prediction involved in this application.

[0060] Figure 3 It is a schematic diagram of the graph structure and spatial association graph structure involved in this application.

[0061] Figure 4 This is a functional module diagram of a preferred embodiment of the artificial intelligence-based infectious disease prediction device involved in this application.

[0062] Figure 5 It is a structural diagram of an electronic device of a preferred embodiment of the artificial intelligence-based infectious disease prediction method involved in this application. DETAILED DESCRIPTION

[0063] In order to more clearly understand the purpose, features and advantages of the present application, the present application is described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that, in the case of no conflict, the embodiments of the present application and the features in the embodiments can be combined with each other. In the following description, many specific details are set forth to facilitate a full understanding of the present application. The embodiments described are only a part of the embodiments of the present application, rather than all of the embodiments.

[0064] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the described features. Throughout the description of this application, "plurality" means two or more, unless otherwise specifically defined.

[0065] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application pertains. The terms used herein in the specification of this application are for the purpose of describing specific embodiments only and are not intended to limit this application. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0066] An embodiment of the present application provides an artificial intelligence-based infectious disease prediction method that can be applied to one or more electronic devices. An electronic device is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions. Its hardware includes but is not limited to a microprocessor, an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), a digital signal processor (DSP), an embedded device, etc.

[0067] An electronic device can be any electronic product that can interact with a user, such as a personal computer, tablet computer, smartphone, personal digital assistant (PDA), game console, Internet Protocol Television (IPTV), smart wearable device, etc.

[0068] The electronic device may also include a network device and / or a client device, wherein the network device includes, but is not limited to, a single network server, a server group consisting of multiple network servers, or a cloud based on cloud computing consisting of a large number of hosts or network servers.

[0069] The network where the electronic device is located includes but is not limited to the Internet, wide area network, metropolitan area network, local area network, virtual private network (VPN), etc.

[0070] like Figure 1The figure shows a flowchart of a preferred embodiment of the artificial intelligence-based infectious disease prediction method of the present application. Depending on different needs, the order of the steps in the flowchart can be changed, and some steps can be omitted. The artificial intelligence-based infectious disease prediction method provided in the embodiment of the present application can be applied to any scenario requiring infectious disease prediction and control, and the method can be applied to products in these scenarios, such as infectious disease prevention in the field of digital medicine.

[0071] S10: Construct a graph structure based on the geographical location of at least one preset area.

[0072] In an optional embodiment, the preset areas are all areas where infectious disease prediction is required, and the number of the preset areas is at least one. The preset areas can be provinces, countries, factories, schools, etc., and this application does not impose any restrictions.

[0073] In an optional embodiment, constructing a graph structure based on the geographical location of at least one preset area includes:

[0074] Assigning an area ID as a unique identifier to each preset area, and using the area ID as node information to obtain a plurality of nodes, wherein the nodes correspond one-to-one to the preset areas;

[0075] For any preset area, obtain all adjacent preset areas of the preset area based on the geographical location, and draw undirected edges connecting the node of the preset area with the nodes of each adjacent preset area;

[0076] Traverse all preset areas and continuously draw undirected edges between nodes. When all preset areas are traversed, the construction of the graph structure is completed.

[0077] The number of adjacent preset areas of a preset area may be 0 or one or more. The graph structure includes all nodes and undirected edges between nodes, wherein undirected edges exist only between nodes corresponding to two adjacent preset areas.

[0078] In this way, a graph structure is obtained according to the geographical locations of different preset areas. The graph structure can reflect the adjacency information of different preset areas, provide spatial correlation between different preset areas, and provide a data basis for infectious disease prediction.

[0079] S11, storing the number of infectious disease cases in the preset area and the population flow data between adjacent preset areas in the historical period to obtain a training set.

[0080] In an optional embodiment, the population flow data reflects the population flow situation between any preset area and an adjacent area of ​​the preset area, and the population flow data can be directly obtained from an electronic map server.

[0081] In an optional embodiment, the storing of the number of infectious disease cases in the preset area and the population flow data between adjacent preset areas in the historical period to obtain the training set includes:

[0082] Collect the number of infectious disease cases in each preset area and the population flow data between adjacent preset areas in T consecutive time periods in the historical time, and arrange them in the order of time periods to obtain a sample data;

[0083] Collect the number of infectious disease cases in each preset area in the next adjacent time period of the T consecutive time periods in the historical time as the label data of the sample data;

[0084] Taking the sample data and the label data as a set of sample pairs;

[0085] A plurality of sample pairs are obtained from historical time using the same method, and the plurality of sample pairs are stored to obtain a training set.

[0086] The length of the time period is one week, and T is a preset setting.

[0087] In this optional embodiment, the number of the preset areas is recorded as M, and the number of infectious disease cases in each preset area in the t-th time period in the historical time is recorded as in, represents the number of infectious disease cases in the jth preset area in the tth time period; the population flow data between adjacent preset areas i and j in the tth time period in the historical time is recorded as The number of infectious disease cases in each preset area and the population flow data between adjacent preset areas in T consecutive time periods are collected, and arranged in the order of the time periods to obtain a sample data.

[0088] It should be noted that the number of population flow data collected in a time period is the same as the number of undirected edges in the graph structure, and the population flow data corresponds one-to-one to the undirected edges in the graph structure.

[0089] For example, assuming that the number of preset areas is 3, and there is only an adjacent relationship between preset area 1 and preset area 2, and the number of time periods T is set to 3, then the number of infectious disease cases in the three preset areas and the population flow data between preset area 1 and preset area 2 can be collected in each time period, and a sample data with a size of 3 rows and 4 columns is obtained. The sample data is as follows:

[0090]

[0091] Among them, each row from top to bottom corresponds to 3 time periods in sequence, and each row includes the number of infectious disease cases in 3 preset areas and population flow data between preset area 1 and preset area 2.

[0092] In this way, a training set is constructed based on data within a historical period, which provides a data basis for subsequent training of the initial infectious disease prediction model and realizing infectious disease prediction.

[0093] S12, building an initial infectious disease prediction model based on the graph structure, wherein the initial infectious disease prediction model includes a spatial association module, a time series processing module, and a prediction module.

[0094] See Figure 2 , is a structural diagram of the initial model for infectious disease prediction involved in this application. In an optional embodiment, the input of the initial model for infectious disease prediction is the number of infectious disease cases in each preset area in T consecutive time periods and the population flow data between adjacent preset areas, and the output is the infectious disease prediction result for each preset area. The infectious disease prediction result of the preset area is the number of infectious disease cases in the preset area in the next adjacent time period of the T consecutive time periods.

[0095] The constructing of an initial infectious disease prediction model based on the graph structure includes:

[0096] The number of infectious disease cases in the same preset area in T consecutive time periods is used as the infectious disease sequence data of the preset area, and the infectious disease sequence data corresponds to the preset area one by one;

[0097] The time series processing module 10 includes a plurality of time series processing layers, each of which corresponds to the preset regions one by one, and is used to extract features from the corresponding infectious disease sequence data to obtain time series features of each preset region;

[0098] The spatial association module 20 receives the graph structure and calculates the edge weight of each undirected edge in the graph structure based on the infectious disease sequence data and the population flow data between adjacent preset areas to obtain a spatial association graph structure, wherein the edge weight of any undirected edge in the spatial association graph structure represents the correlation coefficient between the two preset areas connected by the undirected edge;

[0099] The prediction module 30 is used to obtain an infectious disease prediction result for each preset area based on the spatial correlation graph structure and the temporal characteristics of the preset area.

[0100] Among them, the time series processing layer can adopt existing recurrent neural network structures such as LSTM and GRU, and this application does not impose any restrictions; the infectious disease sequence data includes the number of infectious disease cases in the same preset area in T consecutive time periods.

[0101] It should be noted that, in another optional embodiment, the time series processing module 10 includes a time series processing layer, and the infectious disease sequence data of all preset areas are input into the time series processing layer to obtain the time series characteristics of each preset area.

[0102] In this optional embodiment, the step of calculating the edge weight of each undirected edge in the graph structure based on the infectious disease sequence data and the population flow data between adjacent preset areas to obtain a spatial association graph structure includes:

[0103] The population flow data of the same group of adjacent preset areas in T consecutive time periods are used as the population flow sequence data of the adjacent preset areas, and the population flow sequence data corresponds one-to-one to the undirected edges in the graph structure;

[0104] For any undirected edge in the graph structure, the edge weight of the undirected edge satisfies the relationship:

[0105] e i,j =a([((W1h i )||(W1h j ))·(W2b ij )])

[0106] Wherein, a, W1, W2 are the trainable parameters of the spatial association module 20, h i and h j The infectious disease sequence data of the preset area i and the preset area j are respectively, (W1h i )||(W1h j ) means to convert the vector (W1h i ) and vector (W1h j ) for splicing, b ij is the population flow sequence data of the undirected edge between adjacent preset areas i and j, e i,j represents the edge weight of the undirected edge between adjacent preset regions i and j;

[0107] All undirected edges in the graph structure are traversed to obtain the edge weight of each undirected edge, and the edge weight of each undirected edge is written into the graph structure to obtain a spatial association graph structure.

[0108] Among them, the edge weight e i,j Represents the correlation coefficient between adjacent preset areas i and j; the vector (W1h i ) and the vector (W1h j ) are all 1 row and C columns, then the concatenated vector (W1h i )||(W1h j ) is 1 row and 2C columns, and (W2b ij) is 2C rows and 1 column, and the specific value of C is related to W1 and W2; the structure of the spatial association module 20 is a graph neural network, and the values ​​of its trainable parameters a, W1, and W2 can be obtained through training.

[0109] In this optional embodiment, adjacent preset areas i and j are taken as a group of adjacent preset areas, and the population flow data of the adjacent preset areas i and j in T consecutive time periods are collected as the population flow sequence data of the group of adjacent preset areas. Each group of adjacent preset areas corresponds one-to-one to the undirected edges in the graph structure, and the population flow sequence data corresponds one-to-one to the undirected edges in the graph structure.

[0110] For example, assuming that the number of the preset areas is 3 and there is only an adjacent relationship between preset area 1 and preset area 2, the corresponding graph structure and spatial association graph structure are as follows: Figure 3 shown.

[0111] In this optional embodiment, obtaining the infectious disease prediction result for each preset area based on the spatial correlation graph structure and the temporal characteristics of the preset area includes:

[0112] Taking any node in the spatial association graph structure as a target node;

[0113] Storing the edge weights of all undirected edges connected to the target node to obtain an edge weight set of the target node;

[0114] The representation vector of the target node is calculated based on the edge weight set, and the representation vector of the target node satisfies the relationship:

[0115]

[0116] Among them, N m Represents all edge weights in the edge weight set, e mk represents the edge weight between the target node m and node k in the edge weight set, v k is the temporal feature of the preset area corresponding to node k, LeakyReLU() is the activation function, and e represents any edge weight in the edge weight set; v m is the temporal characteristics of the preset area corresponding to the target node, is the representation vector of the target node;

[0117] Inputting the representation vector of the target node into the prediction layer in the prediction module to output the infectious disease prediction result of the preset area corresponding to the target node;

[0118] All nodes in the spatial association graph structure are traversed to output infectious disease prediction results for each preset area.

[0119] Among them, the structure of the prediction layer is a fully connected layer, the number of the prediction layers can be one, and the representation vectors of all nodes are input into the same prediction layer to predict the number of infectious disease cases in each preset area; the number of the prediction layers can also be the same as the number of nodes, that is, the prediction layers correspond one-to-one to the nodes in the spatial association graph structure, and the representation vector of any node is input into the corresponding prediction layer to predict the number of infectious disease cases in each preset area.

[0120] In this way, the initial model for infectious disease prediction is completed. The time series processing module in the initial model for infectious disease prediction can capture the temporal correlation of the number of infectious disease cases in each preset area and obtain the temporal characteristics of each preset area; the spatial correlation module in the initial model for infectious disease prediction can capture the spatial correlation between any preset area and the adjacent preset area with the help of the graph neural network, thereby improving the accuracy of infectious disease prediction in each preset area.

[0121] S13, training the infectious disease prediction initial model based on the training set to obtain an infectious disease prediction optimization model.

[0122] In an optional embodiment, the parameters in the initial infectious disease prediction model are initialized random parameters. In order for the initial infectious disease prediction model to obtain accurate infectious disease prediction results, the initial infectious disease prediction model needs to be trained to update the parameters in the initial infectious disease prediction model. The parameters in the initial infectious disease prediction model include the trainable parameters of all time series processing layers in the time series processing module, the trainable parameters a, W1, W2 in the spatial association module, and the trainable parameters of the prediction layer in the prediction module.

[0123] In an optional embodiment, training the initial infectious disease prediction model based on the training set to obtain an optimized infectious disease prediction model includes:

[0124] Selecting a preset number of sample pairs from the training set as a training batch, each of the sample pairs comprising sample data and label data;

[0125] Inputting all sample data in the training batch into the infectious disease prediction initial model to obtain an output result for each sample data, wherein the output result includes an infectious disease prediction result for each preset area;

[0126] The mean square error loss is calculated based on the output results and label data of the same sample data in the training batch, and the mean square error loss satisfies the relationship:

[0127]

[0128] Among them, BS is the number of sample pairs in a training batch, M is the number of all preset regions, and y p (q) is the infectious disease prediction result of the preset area p in the output result of sample data q, is the number of infectious disease cases in the preset region p in the label data of sample data q, and MSE is the mean square error loss;

[0129] Using the gradient descent method to find the partial derivative of the mean square error loss to update the parameters of the initial infectious disease prediction model;

[0130] Continuously obtaining training batches from the training set to update the parameters in the initial infectious disease prediction model until the mean square error loss no longer changes, stopping the updating, and obtaining an infectious disease prediction optimization model.

[0131] The value of BS is set to 10, that is, a training batch includes 10 sample pairs, and each sample pair includes a sample data and label data corresponding to the sample data.

[0132] In this way, the training of the infectious disease prediction initial model is completed to obtain the infectious disease prediction optimization model. The infectious disease prediction optimization model can output accurate infectious disease prediction results for each preset area based on the number of infectious disease cases in each preset area in T consecutive time periods input and the population flow data between adjacent preset areas.

[0133] S14, collecting the number of infectious disease cases in all preset areas within a preset time period and the population flow data between adjacent preset areas, and inputting them into the infectious disease prediction optimization model to obtain the infectious disease prediction results for each preset area.

[0134] In an optional embodiment, the preset time period is the most recent T consecutive time periods. The number of infectious disease cases in all preset areas within the preset time period and the population flow data between adjacent preset areas are input into the infectious disease prediction optimization model, and the infectious disease prediction results for each preset area in the next time period can be output. The infectious disease prediction results for the preset areas are the number of infectious disease cases in the preset areas.

[0135] For example, the time period is one week, and the value of T is set to 3. Then, by collecting the number of infectious disease cases in all preset areas in the past three weeks and the population flow data between adjacent preset areas, the number of infectious disease cases in each preset area in the next week can be predicted.

[0136] It can be seen from the above technical solution that the present application directly outputs the infectious disease prediction results for each preset area through an end-to-end infectious disease prediction optimization model. The infectious disease prediction optimization model includes a time series processing module, a spatial correlation module and a prediction module; the time series processing module can capture the time correlation of the number of infectious disease cases in each preset area and obtain the time series characteristics of each preset area; the spatial correlation module can capture the spatial correlation between any preset area and the adjacent preset area with the help of a graph neural network. The prediction module integrates the time series characteristics of the same preset area and the spatial correlation between adjacent preset areas to obtain the infectious disease prediction results for each preset area, thereby improving the accuracy of infectious disease prediction.

[0137] See Figure 4 , Figure 4 This is a functional block diagram of a preferred embodiment of the artificial intelligence-based infectious disease prediction device of this application. The artificial intelligence-based infectious disease prediction device 11 includes a construction unit 110, a storage unit 111, a construction unit 112, a training unit 113, and a prediction unit 114. The modules / units referred to herein are a series of computer-readable instruction segments that can be executed by the processor 13 and perform a fixed function, and are stored in the memory 12. In this embodiment, the functions of each module / unit will be described in detail in subsequent embodiments.

[0138] In an optional embodiment, the constructing unit 110 is configured to construct a graph structure based on a geographical location of at least one preset area.

[0139] In an optional embodiment, constructing a graph structure based on the geographical location of at least one preset area includes:

[0140] Assigning an area ID as a unique identifier to each preset area, and using the area ID as node information to obtain a plurality of nodes, wherein the nodes correspond one-to-one to the preset areas;

[0141] For any preset area, obtain all adjacent preset areas of the preset area based on the geographical location, and draw undirected edges connecting the node of the preset area with the nodes of each adjacent preset area;

[0142] Traverse all preset areas and continuously draw undirected edges between nodes. When all preset areas are traversed, the construction of the graph structure is completed.

[0143] In an optional embodiment, the storage unit 111 is used to store the number of infectious disease cases in the preset area and population flow data between adjacent preset areas in a historical period to obtain a training set.

[0144] In an optional embodiment, the storing of the number of infectious disease cases in the preset area and the population flow data between adjacent preset areas in the historical period to obtain the training set includes:

[0145] Collect the number of infectious disease cases in each preset area and the population flow data between adjacent preset areas in T consecutive time periods in the historical time, and arrange them in the order of time periods to obtain a sample data;

[0146] Collect the number of infectious disease cases in each preset area in the next adjacent time period of the T consecutive time periods in the historical time as the label data of the sample data;

[0147] Taking the sample data and the label data as a set of sample pairs;

[0148] A plurality of sample pairs are obtained from historical time using the same method, and the plurality of sample pairs are stored to obtain a training set.

[0149] In an optional embodiment, the building unit 112 is configured to build an initial infectious disease prediction model based on the graph structure, wherein the initial infectious disease prediction model includes a spatial association module, a time series processing module, and a prediction module.

[0150] In an optional embodiment, the input of the initial infectious disease prediction model is the number of infectious disease cases in each preset area in T consecutive time periods and the population flow data between adjacent preset areas, and the output is the infectious disease prediction result for each preset area. The infectious disease prediction result of the preset area is the number of infectious disease cases in the preset area in the next adjacent time period of the T consecutive time periods.

[0151] The constructing of an initial infectious disease prediction model based on the graph structure includes:

[0152] The number of infectious disease cases in the same preset area in T consecutive time periods is used as the infectious disease sequence data of the preset area, and the infectious disease sequence data corresponds to the preset area one by one;

[0153] The time series processing module includes a plurality of time series processing layers, each of which corresponds to the preset areas one by one, and is used to extract features from the corresponding infectious disease sequence data to obtain time series features of each preset area;

[0154] The spatial association module receives the graph structure and calculates the edge weight of each undirected edge in the graph structure based on the infectious disease sequence data and the population flow data between adjacent preset areas to obtain a spatial association graph structure, wherein the edge weight of any undirected edge in the spatial association graph structure represents the correlation coefficient between the two preset areas connected by the undirected edge;

[0155] The prediction module is used to obtain infectious disease prediction results for each preset area based on the spatial association graph structure and the temporal characteristics of the preset area.

[0156] In this optional embodiment, the step of calculating the edge weight of each undirected edge in the graph structure based on the infectious disease sequence data and the population flow data between adjacent preset areas to obtain a spatial association graph structure includes:

[0157] The population flow data of the same group of adjacent preset areas in T consecutive time periods are used as the population flow sequence data of the adjacent preset areas, and the population flow sequence data corresponds one-to-one to the undirected edges in the graph structure;

[0158] For any undirected edge in the graph structure, the edge weight of the undirected edge satisfies the relationship:

[0159] e i,j =a([((W1h i )||(W1h j ))·(W2b ij )])

[0160] Wherein, a, W1, W2 are the trainable parameters of the spatial association module 20, h i and h j The infectious disease sequence data of the preset area i and the preset area j are respectively, (W1h i )||(W1h j ) means to convert the vector (W1h i ) and vector (W1h j ) for splicing, b ij is the population flow sequence data of the undirected edge between adjacent preset areas i and j, e i,j represents the edge weight of the undirected edge between adjacent preset regions i and j;

[0161] All undirected edges in the graph structure are traversed to obtain the edge weight of each undirected edge, and the edge weight of each undirected edge is written into the graph structure to obtain a spatial association graph structure.

[0162] In this optional embodiment, obtaining the infectious disease prediction result for each preset area based on the spatial correlation graph structure and the temporal characteristics of the preset area includes:

[0163] Taking any node in the spatial association graph structure as a target node;

[0164] Storing the edge weights of all undirected edges connected to the target node to obtain an edge weight set of the target node;

[0165] The representation vector of the target node is calculated based on the edge weight set, and the representation vector of the target node satisfies the relationship:

[0166]

[0167] Among them, N m Represents all edge weights in the edge weight set, e mk represents the edge weight between the target node m and node k in the edge weight set, v k is the temporal feature of the preset area corresponding to node k, LeakyReLU() is the activation function, and e represents any edge weight in the edge weight set; v m is the temporal characteristics of the preset area corresponding to the target node, is the representation vector of the target node;

[0168] Inputting the representation vector of the target node into the prediction layer in the prediction module to output the infectious disease prediction result of the preset area corresponding to the target node;

[0169] All nodes in the spatial association graph structure are traversed to output infectious disease prediction results for each preset area.

[0170] In an optional embodiment, the training unit 113 is configured to train the initial infectious disease prediction model based on the training set to obtain an optimized infectious disease prediction model.

[0171] In an optional embodiment, training the initial infectious disease prediction model based on the training set to obtain an optimized infectious disease prediction model includes:

[0172] Selecting a preset number of sample pairs from the training set as a training batch, each of the sample pairs comprising sample data and label data;

[0173] Inputting all sample data in the training batch into the infectious disease prediction initial model to obtain an output result for each sample data, wherein the output result includes an infectious disease prediction result for each preset area;

[0174] The mean square error loss is calculated based on the output results and label data of the same sample data in the training batch, and the mean square error loss satisfies the relationship:

[0175]

[0176] Among them, BS is the number of sample pairs in a training batch, M is the number of all preset regions, and y p (q) is the infectious disease prediction result of the preset area p in the output result of sample data q, is the number of infectious disease cases in the preset region p in the label data of sample data q, and MSE is the mean square error loss;

[0177] Using the gradient descent method to find the partial derivative of the mean square error loss to update the parameters of the initial infectious disease prediction model;

[0178] Continuously obtaining training batches from the training set to update the parameters in the initial infectious disease prediction model until the mean square error loss no longer changes, stopping the updating, and obtaining an infectious disease prediction optimization model.

[0179] In an optional embodiment, the prediction unit 114 is used to collect the number of infectious disease cases in all preset areas within a preset time period and the population flow data between adjacent preset areas, and input them into the infectious disease prediction optimization model to obtain the infectious disease prediction results for each preset area.

[0180] It can be seen from the above technical solution that the present application directly outputs the infectious disease prediction results for each preset area through an end-to-end infectious disease prediction optimization model. The infectious disease prediction optimization model includes a time series processing module, a spatial correlation module and a prediction module; the time series processing module can capture the time correlation of the number of infectious disease cases in each preset area and obtain the time series characteristics of each preset area; the spatial correlation module can capture the spatial correlation between any preset area and the adjacent preset area with the help of a graph neural network. The prediction module integrates the time series characteristics of the same preset area and the spatial correlation between adjacent preset areas to obtain the infectious disease prediction results for each preset area, thereby improving the accuracy of infectious disease prediction.

[0181] See Figure 5 , is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Electronic device 1 includes memory 12 and processor 13. Memory 12 is used to store computer-readable instructions, and processor 13 is used to execute the computer-readable instructions stored in the memory to implement the artificial intelligence-based infectious disease prediction method described in any of the above embodiments.

[0182] In an optional embodiment, the electronic device 1 further includes a bus, a computer program stored in the memory 12 and executable on the processor 13, such as an artificial intelligence-based infectious disease prediction program.

[0183] Figure 5 Only the electronic device 1 having the memory 12 and the processor 13 is shown. It can be understood by those skilled in the art that Figure 5 The structure shown does not constitute a limitation on the electronic device 1 , and the electronic device 1 may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0184] Combine Figure 1 The memory 12 in the electronic device 1 stores a plurality of computer-readable instructions to implement an artificial intelligence-based infectious disease prediction method, and the processor 13 can execute the plurality of instructions to implement:

[0185] Building a graph structure based on the geographical location of at least one preset area;

[0186] Storing the number of infectious disease cases in the preset area and population flow data between adjacent preset areas over a historical period to obtain a training set;

[0187] Building an initial infectious disease prediction model based on the graph structure, the initial infectious disease prediction model includes a spatial association module, a time series processing module and a prediction module;

[0188] Training the infectious disease prediction initial model based on the training set to obtain an infectious disease prediction optimization model;

[0189] The number of infectious disease cases in all preset areas within a preset time period and the population flow data between adjacent preset areas are collected and input into the infectious disease prediction optimization model to obtain the infectious disease prediction results for each preset area.

[0190] Specifically, the specific implementation method of the processor 13 for the above instructions can refer to Figure 1 The description of the relevant steps in the corresponding embodiments will not be repeated here.

[0191] Those skilled in the art will understand that the schematic diagram is merely an example of the electronic device 1 and does not constitute a limitation on the electronic device 1. The electronic device 1 may have a bus structure or a star structure. The electronic device 1 may also include more or less other hardware or software than shown in the figure, or a different arrangement of components. For example, the electronic device 1 may also include input and output devices, network access devices, etc.

[0192] It should be noted that the electronic device 1 is only an example, and other existing or future electronic products that are suitable for this application should also be included in the scope of protection of this application and incorporated herein by reference.

[0193] Among them, the memory 12 includes at least one type of readable storage medium, and the readable storage medium can be non-volatile or volatile. The readable storage medium includes flash memory, mobile hard disk, multimedia card, card-type memory (for example: SD or DX memory, etc.), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 12 can be an internal storage unit of the electronic device 1, such as a mobile hard disk of the electronic device 1. In other embodiments, the memory 12 can also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, smart memory card (Smart Media Card, SMC), secure digital (Secure Digital, SD) card, flash card (Flash Card), etc. equipped on the electronic device 1. The memory 12 can not only be used to store application software and various types of data installed on the electronic device 1, such as the code of an infectious disease prediction program based on artificial intelligence, but can also be used to temporarily store data that has been output or is to be output.

[0194] In some embodiments, the processor 13 may be composed of an integrated circuit, such as a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and a combination of various control chips. The processor 13 is the control core (Control Unit) of the electronic device 1, connecting the various components of the entire electronic device 1 using various interfaces and lines. It executes or executes programs or modules stored in the memory 12 (such as executing an artificial intelligence-based infectious disease prediction program) and calls data stored in the memory 12 to perform various functions of the electronic device 1 and process data.

[0195] The processor 13 executes the operating system of the electronic device 1 and various installed applications. The processor 13 executes the applications to implement the steps in the above-mentioned embodiments of the infectious disease prediction method based on artificial intelligence, such as Figure 1 Steps shown.

[0196] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory 12 and executed by the processor 13 to complete the present application. The one or more modules / units may be a series of computer-readable instruction segments capable of performing specific functions, which are used to describe the execution process of the computer program in the electronic device 1. For example, the computer program may be divided into a construction unit 110, a storage unit 111, a construction unit 112, a training unit 113, and a prediction unit 114.

[0197] The above-mentioned integrated unit implemented in the form of a software function module can be stored in a computer-readable storage medium. The above-mentioned software function module is stored in a storage medium and includes a number of instructions for causing a computer device (which can be a personal computer, computer device, or network device, etc.) or a processor to execute the portion of the artificial intelligence-based infectious disease prediction method described in each embodiment of the present application.

[0198] If the modules / units integrated in the electronic device 1 are implemented in the form of 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 present application implements all or part of the processes in the above-mentioned embodiment methods, and can also instruct the relevant hardware devices to complete them through a computer program. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by a processor, it can implement the steps of each of the above-mentioned method embodiments.

[0199] The computer program includes computer program code, which may be in source code form, object code form, executable file, or some intermediate form. The computer-readable medium may include any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory, or other memory.

[0200] Furthermore, the computer-readable storage medium may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function, etc.; the data storage area may store data created according to the use of the blockchain node, etc.

[0201] The blockchain referred to in this application is a new application model for computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and encryption algorithms. Blockchain is essentially a decentralized database, a series of data blocks generated using cryptographic methods. Each data block contains information about a batch of network transactions, which is used to verify the validity of this information (to prevent counterfeiting) and generate the next block. Blockchain can include the underlying blockchain platform, the platform product service layer, and the application service layer.

[0202] The bus can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 5 The diagram is represented by only one arrow, but it does not mean that there is only one bus or one type of bus. The bus is configured to implement connection and communication between the memory 12 and at least one processor 13, etc.

[0203] An embodiment of the present application also provides a computer-readable storage medium (not shown), which stores computer-readable instructions. The computer-readable instructions are executed by a processor in an electronic device to implement the artificial intelligence-based infectious disease prediction method described in any of the above embodiments.

[0204] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the module division is merely a logical function division, and other division methods may be used in actual implementation.

[0205] The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed across multiple network elements. Some or all of the modules may be selected to achieve the purpose of the solution of this embodiment according to actual needs.

[0206] In addition, the functional modules in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0207] Furthermore, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices listed in the specification may also be implemented by a single unit or device through software or hardware. Terms such as first and second are used to indicate names and do not imply any particular order.

[0208] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application and are not intended to limit the present application. Although the present application 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 application may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present application.

Claims

1. An artificial intelligence-based infectious disease prediction method, characterized in that: The method comprises: Building a graph structure based on the geographical location of at least one preset area; Storing the number of infectious disease cases in the preset area and population flow data between adjacent preset areas over a historical period to obtain a training set; An initial infectious disease prediction model is constructed based on the graph structure, and the initial infectious disease prediction model includes a spatial association module, a time series processing module, and a prediction module; the input of the initial infectious disease prediction model is the number of infectious disease cases in each preset area in T consecutive time periods and population flow data between adjacent preset areas, and the output is the infectious disease prediction result for each preset area, and the infectious disease prediction result of the preset area is the number of infectious disease cases in the preset area in the next adjacent time period of the T consecutive time periods; the construction of the initial infectious disease prediction model based on the graph structure includes: The number of infectious disease cases in the same preset area in T consecutive time periods is used as the infectious disease sequence data of the preset area, and the infectious disease sequence data corresponds to the preset area one by one; The time series processing module includes a plurality of time series processing layers, each of which corresponds to the preset areas one by one, and is used to extract features from the corresponding infectious disease sequence data to obtain time series features of each preset area; The spatial association module receives the graph structure and calculates the edge weight of each undirected edge in the graph structure based on the infectious disease sequence data and the population flow data between adjacent preset areas to obtain a spatial association graph structure, including: using the population flow data of the same group of adjacent preset areas in T consecutive time periods as the population flow sequence data of the adjacent preset areas, and the population flow sequence data corresponds one-to-one to the undirected edges in the graph structure; for any undirected edge in the graph structure, the edge weight of the undirected edge satisfies the relationship: ,in, are the trainable parameters of the spatial association module, and are the infectious disease sequence data of preset area i and preset area j respectively, Indicates that the vector and vector To splice, is the population flow sequence data of the undirected edge between adjacent preset areas i and j, Represents the edge weight of the undirected edge between adjacent preset areas i and j; traverses all undirected edges in the graph structure to obtain the edge weight of each undirected edge, and writes the edge weight of each undirected edge into the graph structure to obtain a spatial association graph structure; the edge weight of any undirected edge in the spatial association graph structure represents the correlation coefficient between the two preset areas connected by the undirected edge; The prediction module is used to obtain an infectious disease prediction result for each preset area based on the spatial correlation graph structure and the temporal characteristics of the preset area; Training the infectious disease prediction initial model based on the training set to obtain an infectious disease prediction optimization model; The number of infectious disease cases in all preset areas within a preset time period and the population flow data between adjacent preset areas are collected and input into the infectious disease prediction optimization model to obtain the infectious disease prediction results for each preset area.

2. The artificial intelligence-based infectious disease prediction method according to claim 1, characterized in that: The constructing of a graph structure based on the geographical location of at least one preset area includes: Assigning an area ID as a unique identifier to each preset area, and using the area ID as node information to obtain a plurality of nodes, wherein the nodes correspond one-to-one to the preset areas; For any preset area, obtain all adjacent preset areas of the preset area based on the geographical location, and draw undirected edges connecting the node of the preset area with the nodes of each adjacent preset area; Traverse all preset areas and continuously draw undirected edges between nodes. When all preset areas are traversed, the construction of the graph structure is completed.

3. The artificial intelligence-based infectious disease prediction method according to claim 1, wherein: The training set is obtained by storing the number of infectious disease cases in the preset area and the population flow data between adjacent preset areas during the historical period, including: Collect the number of infectious disease cases in each preset area and the population flow data between adjacent preset areas in T consecutive time periods in the historical time, and arrange them in the order of time periods to obtain a sample data; Collect the number of infectious disease cases in each preset area in the next adjacent time period of the T consecutive time periods in the historical time as the label data of the sample data; Taking the sample data and the label data as a set of sample pairs; A plurality of sample pairs are obtained from historical time using the same method, and the plurality of sample pairs are stored to obtain a training set.

4. The artificial intelligence-based infectious disease prediction method according to claim 1, wherein: The obtaining of infectious disease prediction results for each preset area based on the spatial correlation graph structure and the temporal characteristics of the preset area includes: Taking any node in the spatial association graph structure as a target node; Storing the edge weights of all undirected edges connected to the target node to obtain an edge weight set of the target node; The representation vector of the target node is calculated based on the edge weight set, and the representation vector of the target node satisfies the relationship: in, represents all edge weights in the edge weight set, represents the edge weight between the target node m and the node k in the edge weight set, is the temporal feature of the preset area corresponding to node k, is the activation function, e represents any edge weight in the edge weight set; is the temporal characteristics of the preset area corresponding to the target node, is the representation vector of the target node; Inputting the representation vector of the target node into the prediction layer in the prediction module to output the infectious disease prediction result of the preset area corresponding to the target node; All nodes in the spatial association graph structure are traversed to output infectious disease prediction results for each preset area.

5. The artificial intelligence-based infectious disease prediction method according to claim 1, wherein: The step of training the initial infectious disease prediction model based on the training set to obtain an optimized infectious disease prediction model comprises: Selecting a preset number of sample pairs from the training set as a training batch, each of the sample pairs comprising sample data and label data; Inputting all sample data in the training batch into the infectious disease prediction initial model to obtain an output result for each sample data, wherein the output result includes an infectious disease prediction result for each preset area; The mean square error loss is calculated based on the output results and label data of the same sample data in the training batch, and the mean square error loss satisfies the relationship: in, is the number of sample pairs in a training batch, M is the number of all preset regions, is the infectious disease prediction result of the preset area p in the output result of sample data q, is the number of infectious disease cases in the preset region p in the label data of sample data q, is the mean square error loss; Using the gradient descent method to find the partial derivative of the mean square error loss to update the parameters of the initial infectious disease prediction model; Continuously obtaining training batches from the training set to update the parameters in the initial infectious disease prediction model until the mean square error loss no longer changes, stopping the updating, and obtaining an infectious disease prediction optimization model.

6. An artificial intelligence-based infectious disease prediction device for implementing the method according to claim 1, characterized in that: The device comprises: A construction unit, configured to construct a graph structure based on a geographical location of at least one preset area; A storage unit is used to store the number of infectious disease cases in the preset area and population flow data between adjacent preset areas in a historical period to obtain a training set; A building unit, configured to build an initial infectious disease prediction model based on the graph structure, wherein the initial infectious disease prediction model includes a spatial association module, a time series processing module, and a prediction module; A training unit, configured to train the initial infectious disease prediction model based on the training set to obtain an optimized infectious disease prediction model; The prediction unit is used to collect the number of infectious disease cases in all preset areas within a preset time period and the population flow data between adjacent preset areas, and input them into the infectious disease prediction optimization model to obtain the infectious disease prediction results for each preset area.

7. An electronic device, characterized in that: The electronic device comprises: a memory storing computer-readable instructions; and A processor that executes computer-readable instructions stored in the memory to implement the artificial intelligence-based infectious disease prediction method as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-readable instructions, which, when executed by a processor, implement the artificial intelligence-based infectious disease prediction method according to any one of claims 1 to 5.

Images