CN116434973A

CN116434973A - Infectious disease early warning method, device, equipment and medium based on artificial intelligence

Info

Publication number: CN116434973A
Application number: CN202310332784.7A
Authority: CN
Inventors: 宋亚男
Original assignee: Ping An Technology Shenzhen Co Ltd
Current assignee: Ping An Technology Shenzhen Co Ltd
Priority date: 2023-03-23
Filing date: 2023-03-23
Publication date: 2023-07-14

Abstract

The application relates to digital medical treatment, and provides an infectious disease early warning method and device based on artificial intelligence, electronic equipment and a storage medium, wherein the infectious disease early warning method based on artificial intelligence comprises the following steps: collecting infectious disease characteristic data and tag data in a plurality of sampling areas; constructing a space-time correlation matrix of the infectious disease characteristic data according to the tag data; training an infectious disease early warning model according to the infectious disease characteristic data, the tag data and the space-time correlation matrix; inputting the infectious disease characteristic data of each sampling area acquired in real time into the infectious disease early warning model to obtain a real-time prediction result; and evaluating the real-time prediction results according to the number of the historical contemporaneous cases in each sampling area to obtain evaluation results, and carrying out infectious disease early warning according to the evaluation results. The method can be used for predicting the infectious diseases by combining the space-time correlation characteristics of the infectious disease related data, so that the accuracy of infectious disease early warning can be improved.

Description

Infectious disease early warning method, device, equipment and medium based on artificial intelligence

Technical Field

The application relates to the technical field of artificial intelligence and digital medical treatment, in particular to an infectious disease early warning method, device, electronic equipment and storage medium based on artificial intelligence.

Background

In the medical field, early warning of infectious diseases can provide an important reference for prevention and control of infectious diseases. However, factors affecting the trend of infectious disease are complex, such as uncontrolled climate factors such as atmospheric temperature, air humidity, wind power, wind speed, wind direction, and geographical factors including the spread of infectious disease, which cause great challenges in the prevention and control of infectious disease.

Currently, there are three main types of common models for predicting and warning infectious diseases: firstly, constructing a transmission dynamics model of infectious diseases, secondly, constructing a regression prediction model based on the monitored disease number and related risk factors, and thirdly, controlling a graph method, wherein the methods have certain limitations and mainly comprise the following steps: 1) The model is simple, the influence of threshold setting is large, misdiagnosis cases are increased due to unsuitable thresholds, and social resource waste is generated; 2) The model cannot realize early warning of two dimensions in time and space at the same time; 3) Some regression prediction models, such as differential autoregressive moving average models, can only make short-term predictions.

Disclosure of Invention

In view of the foregoing, it is necessary to provide an artificial intelligence-based infectious disease early warning method, apparatus, electronic device and storage medium, so as to solve the technical problem of how to improve the accuracy of infectious disease early warning.

The embodiment of the application provides an infectious disease early warning method based on artificial intelligence, which comprises the following steps:

collecting infectious disease characterization data and tag data at a plurality of sampling regions, the tag data being used to characterize the number of cases within each of the sampling regions;

constructing a space-time correlation matrix of the infectious disease characteristic data according to the tag data;

training an infectious disease early warning model according to the infectious disease characteristic data, the tag data and the space-time correlation matrix;

inputting the infectious disease characteristic data of each sampling area acquired in real time into the infectious disease early warning model to obtain a real-time prediction result, wherein the real-time prediction result is used for representing the number of cases of each sampling area obtained in real time;

and evaluating the real-time prediction results according to the number of the historical contemporaneous cases in each sampling area to obtain evaluation results, and carrying out infectious disease early warning according to the evaluation results.

In some embodiments, the collecting infectious disease characterization data and tag data at a plurality of sampling regions comprises:

collecting infectious disease related data in a plurality of sampling areas at preset sampling moments;

integrating the infectious disease related data collected by each sampling area into infectious disease characteristic data corresponding to the sampling time aiming at each sampling time;

And collecting the number of cases of infectious diseases in each sampling area according to each sampling time, and combining the number of cases collected in each sampling area into label data corresponding to the sampling time.

In some embodiments, the constructing the space-time correlation matrix of the infectious disease characterization data from the tag data comprises:

combining the tag data into a case change sequence corresponding to each sampling region according to the sequence from the early to the late of the sampling time for each sampling region;

constructing an initial empty matrix, and arranging the names of the sampling areas according to a preset sequence to serve as row names and column names of the initial empty matrix;

traversing each element in the initial empty matrix in any sequence, and calculating the correlation between a case change sequence corresponding to the row of the traversed element and a case change sequence corresponding to the column according to a preset correlation measurement algorithm to serve as the value of the traversed element;

and stopping traversing and obtaining the space-time correlation matrix until all elements in the initial empty matrix are traversed.

In some embodiments, the training an infection early warning model according to the infection characteristic data, the tag data and the space-time correlation matrix comprises:

Constructing a training data set according to the tag data, the infectious disease characteristic data and the space-time correlation matrix, wherein the training data set comprises first input data, second input data and tag data;

simultaneously inputting the first input data and the second input data of each sampling moment into a preset initial prediction model to obtain a prediction result;

calculating a loss value of the initial prediction model according to the prediction result and the tag data;

and updating the initial prediction model by using a gradient descent method, and stopping updating and obtaining an infectious disease early warning model in response to the loss value of the initial prediction model being smaller than a preset termination threshold value.

In some embodiments, said constructing a training data set from said tag data, said infectious disease characterization data, and said spatiotemporal correlation matrix comprises:

taking the prediction result corresponding to the infectious disease characteristic data at the current sampling time and the last sampling time as first input data at the current sampling time;

multiplying the infectious disease characteristic data corresponding to the current sampling time by the space-time correlation matrix to obtain space-time correlation characteristics of the current sampling time, and combining the space-time correlation characteristics with a prediction result corresponding to the last sampling time to serve as second input data of the current sampling time;

And combining the first input data and the second input data of the current sampling moment to be used as input data of the current sampling moment, corresponding the input data to the tag data of the current sampling moment to be used as training data of the current sampling moment, and taking the training data corresponding to all the sampling moments as a training data set.

In some embodiments, the inputting the real-time collected infectious disease feature data of each sampling area into the infectious disease early warning model to obtain a real-time prediction result includes:

collecting infectious disease characteristic data in real time in the plurality of sampling areas, and combining the infectious disease characteristic data collected in real time with the number of infectious disease cases collected in real time at the previous moment to serve as real-time first input data;

calculating the product of the space-time correlation matrix and the infectious disease characteristic data acquired in real time to obtain real-time space-time correlation characteristics, and combining the real-time space-time correlation characteristics with the number of infectious disease cases acquired in real time at the last moment to obtain real-time second input data;

and inputting the real-time first input data and the real-time second input data into the infectious disease early warning model simultaneously to obtain a real-time prediction result, wherein the real-time prediction result is used for representing the case number in the plurality of sampling areas.

In some embodiments, the evaluating the real-time prediction result according to the number of the historical contemporaneous cases of each sampling region to obtain an evaluation result, and performing early warning of infectious diseases according to the evaluation result comprises:

acquiring the number of historical contemporaneous cases of each sampling area;

calculating a difference value between the real-time prediction result and the number of the historical contemporaneous cases for each sampling region;

if the real-time prediction result is greater than the number of the historical contemporaneous cases, carrying out advanced early warning on infectious diseases in the sampling area;

if the real-time prediction result is smaller than the number of the historical contemporaneous cases and the difference value between the real-time prediction result and the number of the historical contemporaneous cases is smaller than a preset safety threshold value, carrying out low-level early warning on infectious diseases in the sampling area;

and if the real-time prediction result is smaller than the number of the historical contemporaneous cases and the difference between the real-time prediction result and the number of the historical contemporaneous cases is larger than a preset safety threshold, carrying out no infectious disease early warning on the sampling area.

The embodiment of the application also provides an infectious disease early warning device based on artificial intelligence, which comprises:

A sampling unit for collecting infectious disease characteristic data and tag data in a plurality of sampling regions, the tag data being used to characterize the number of cases within each of the sampling regions;

the construction unit is used for constructing a space-time correlation matrix of the infectious disease characteristic data according to the tag data;

the training unit is used for training an infectious disease early warning model according to the infectious disease characteristic data, the tag data and the space-time correlation matrix;

the real-time prediction unit is used for inputting the real-time acquired infectious disease characteristic data of each sampling area into the infectious disease early warning model to obtain a real-time prediction result, and the real-time prediction result is used for representing the number of cases of each sampling area obtained in real time;

and the early warning unit is used for evaluating the real-time prediction result according to the number of the historical contemporaneous cases in each sampling area to obtain an evaluation result and carrying out infectious disease early warning according to the evaluation result.

The embodiment of the application also provides electronic equipment, which comprises:

a memory storing computer readable instructions; a kind of electronic device with high-pressure air-conditioning system

And a processor executing computer readable instructions stored in the memory to implement the artificial intelligence based infectious disease early warning method.

Embodiments of the present application also provide a computer-readable storage medium having computer-readable instructions stored therein, the computer-readable instructions being executed by a processor in an electronic device to implement the artificial intelligence-based infectious disease early warning method.

According to the artificial intelligence-based infectious disease early warning method, a large number of infectious disease characteristic data and case numbers are collected in a plurality of sampling areas, a space-time correlation matrix is constructed based on the correlation of the case numbers among the sampling areas, an infectious disease early warning model is trained according to the infectious disease characteristic data, the tag data and the space-time correlation matrix, the infectious disease characteristic data of each sampling area collected at the time is input into the infectious disease early warning model to obtain a real-time prediction result, finally, the real-time prediction result is evaluated according to the historical contemporaneous case numbers of each sampling area to obtain an evaluation result, and infectious disease early warning is carried out according to the evaluation result. The real-time prediction result combines the space-time correlation characteristics of the related data of the infectious diseases, so that the accuracy of early warning of the infectious diseases can be improved.

Drawings

FIG. 1 is a flow chart of a preferred embodiment of an artificial intelligence based method for early warning of infectious diseases.

Fig. 2 is a functional block diagram of a preferred embodiment of an artificial intelligence based infectious disease early warning apparatus according to the present application.

Fig. 3 is a schematic structural diagram of an electronic device according to a preferred embodiment of the artificial intelligence-based infectious disease early warning method according to the present application.

Fig. 4 is a schematic diagram of infectious disease characterization data provided in an embodiment of the present application.

Fig. 5 is a schematic structural diagram of an initial prediction model provided in an embodiment of the present application.

Fig. 6 is a schematic structural diagram of any one of the calculation elements in the initial prediction model provided in the embodiment of the present application.

Fig. 7 is a schematic diagram of real-time acquired infectious disease feature data provided in an embodiment of the present application.

Detailed Description

In order that the objects, features and advantages of the present application may be more clearly understood, a more particular description of the invention will be rendered by reference to specific embodiments thereof which are illustrated in the appended drawings. It should be noted that, without conflict, the embodiments of the present application and features of the embodiments may be combined with each other. In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application, the described embodiments are merely some, rather than all, of the embodiments of the present application.

Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more of the described features. In the description of the present application, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.

Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein in the description of the application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The term "and/or" as used herein includes any and all combinations of one or more of the associated listed items.

The embodiment of the application provides an infectious disease early warning method based on artificial intelligence, which can be applied to one or more electronic devices, wherein the electronic devices are devices capable of automatically performing numerical calculation and/or information processing according to preset or stored instructions, and the hardware comprises, but is not limited to, a microprocessor, an application specific integrated circuit (Application Specific Integrated Circuit, an ASIC), a programmable gate array (Field-Programmable Gate Array, FPGA), a digital processor (Digital Signal Processor, DSP), an embedded device and the like.

The electronic device may be any electronic product that can interact with a user in a human-computer manner, such as a personal computer, tablet computer, smart phone, personal digital assistant (Personal Digital Assistant, PDA), game console, interactive internet protocol television (Internet Protocol Television, IPTV), smart wearable device, etc.

The electronic device may also include a network device and/or a user device. Wherein the network device includes, but is not limited to, a single network server, a server group composed of a plurality of network servers, or a Cloud based Cloud Computing (Cloud Computing) composed of a large number of hosts or network servers.

The network in which the electronic device is located includes, but is not limited to, the internet, a wide area network, a metropolitan area network, a local area network, a virtual private network (Virtual Private Network, VPN), and the like.

Example 1

The infectious disease early warning method based on artificial intelligence provided by the embodiment of the application can be applied to prediction of the transmission condition of periodic infectious diseases, wherein the periodic infectious diseases comprise hand-foot-and-mouth disease, influenza and the like.

Referring to FIG. 1, a flowchart of a preferred embodiment of an artificial intelligence based infectious disease early warning method is shown. The order of the steps in the flowchart may be changed and some steps may be omitted according to various needs.

S10, acquiring infectious disease characteristic data and label data in a plurality of sampling areas, wherein the label data is used for representing the number of cases in each sampling area.

In an alternative embodiment, the collecting the infectious disease characterization data and the tag data at a plurality of sampling regions includes:

In this alternative embodiment, the infectious disease related data may be collected at each preset sampling time in a plurality of sampling regions, where the plurality of sampling regions may be a plurality of administrative regions or a plurality of regions divided according to geographic factors, which is not limited in this application.

The infectious disease related data may be weather data such as temperature and humidity of the sampling area at the sampling time, and may further include the number of cases of the sampling area in the previous 1 day, the number of cases of the sampling area in the previous 2 days, and the like, where the type of each item of data in the infectious disease related data is not limited.

For example, for a certain sampling area, the infectious disease related data collected at a certain sampling time includes: the temperature is 36 degrees celsius, the humidity is 27%, the previous-day case number is 100, and the previous-day case number is 200, then the dimension of the infectious disease related data at this sampling time is 4, and the form is [36, 27, 100, 200].

In this alternative embodiment, for each sampling time, the infectious disease related data collected in each sampling area may be integrated into infectious disease feature data corresponding to the sampling time.

For example, when the sampling areas are 3 and are respectively area 1, area 2 and area 3, the dimension of the infectious disease related data is 4, and the dimension is respectively temperature, humidity, the number of cases of the previous day and the number of cases of the previous two days, the infectious disease characteristic data corresponding to a certain sampling time is shown in fig. 4.

In this alternative embodiment, for each sampling time, the number of cases of infectious disease may be collected in each sampling area, and the number of cases collected in all the sampling areas may be combined into the label data corresponding to the sampling time.

For example, when the sampling areas are 3 and area 1, area 2 and area 3, respectively, then for a certain sampling time, when the number of cases acquired in area 1 is 150, the number of cases acquired in area 2 is 151 and the number of cases acquired in area 3 is 152, the label data corresponding to the sampling time is [150,151,152].

Thus, a large amount of data related to infectious diseases are obtained through periodically collecting data, and data support is provided for training of a subsequent infectious disease model, so that the accuracy of predicting the infectious disease model can be improved.

S11, constructing a space-time correlation matrix of the infectious disease characteristic data according to the tag data.

In an alternative embodiment, the constructing the space-time correlation matrix of the infectious disease feature data according to the tag data includes:

In this alternative embodiment, for each sampling region, the collected tag data may be ordered according to the order from early to late of the sampling time, so as to obtain a case change sequence with order, where the case change sequence is used to characterize the trend of the number of cases changing with the sampling time.

Illustratively, when sampling region 1 has a case number of 151 at sampling time 1, a case number of 152 at sampling time 2, and a case number of 153 at sampling time 3, the corresponding case change sequence of sampling region 1 is [151,152,153].

In this alternative embodiment, in order to construct the space-time correlation matrix, an initial empty matrix may be constructed first, the names of the sampling regions are arranged according to a preset sequence, the arranged sampling region names are used as row names from top to bottom and column names from left to right of the initial empty matrix, and when sampling regions are three and are respectively region 1, region 2 and region 3, and the preset sequence is [ region 1, region 2 and region 3], the column names of the initial empty matrix are sequentially [ region 1, region 2 and region 3] from left to right, and the row names of the initial empty matrix are sequentially [ region 1, region 2 and region 3] from top to bottom.

In this optional embodiment, each element in the initial empty matrix may be traversed in any order, for the traversed element, a correlation between a case change sequence corresponding to a row name where the element is located and a case change sequence corresponding to a column name where the element is located is calculated according to a preset correlation measurement algorithm, and a value of the correlation is used as a value of the traversed element. The preset correlation measurement algorithm may be an existing correlation measurement algorithm such as a cosine similarity algorithm, a euclidean distance algorithm, a hamming distance algorithm, and the like, which is not limited in this application.

For example, if the preset relevance metric algorithm is a cosine similarity algorithm, the row name of the element in the traversed initial empty matrix is region a and the column name is region B, and if the case change sequence corresponding to region a is [100,150,200] and the case change sequence corresponding to region B is [150,200,100], the calculation manner of the relevance between the case change sequence of region a and the case change sequence of region B is:

the spatial correlation between the region a and the region B is 0.89, and the higher the correlation is, the higher the similarity degree of the case change sequences between the sampling regions is, and the case change trends between the sampling regions have stronger correlation. The value of the correlation may further be taken as the value of the element in the null matrix traversed.

In this alternative embodiment, when each element in the initial empty matrix is traversed, the traversal is stopped and a space-time correlation matrix is obtained, where the space-time correlation matrix is used to characterize the degree of interaction of case change trends between the sampling regions.

Therefore, the spatial correlation among the sampling areas is obtained by calculating the similarity among the change trends of the number of cases in the sampling areas, and the spatial characteristic information can be provided for the training data set for subsequently constructing the infectious disease early warning model, so that the accuracy of the infectious disease early warning model is improved.

S12, training an infectious disease early warning model according to the infectious disease characteristic data, the tag data and the space-time correlation matrix.

In an alternative embodiment, the training the infection early warning model according to the infection characteristic data, the tag data and the space-time correlation matrix includes:

In an alternative embodiment, in order to fit a more accurate prediction model to accurately predict a trend of change in the number of cases by using all the collected data, a training data set is constructed by using the collected data, and the constructing a training data set according to the tag data, the infectious disease feature data and the space-time correlation matrix includes:

In this optional embodiment, the prediction result of the infectious disease feature data corresponding to the current sampling time and the last sampling time is taken as the first input data of the current sampling time, and if the current sampling time is t, the last sampling time is t-1, and the infectious disease feature data corresponding to the current sampling time is:

The prediction result corresponding to the last sampling time is: [100,150,200] then the first input data for the current sample time is:

in this optional embodiment, the space-time correlation matrix may be multiplied by the infectious disease feature data corresponding to the current sampling time to obtain a space-time correlation feature of the current sampling time, where, by way of example, the infectious disease feature data corresponding to the current sampling time is:

and the space-time correlation matrix is:

the calculation mode of the space-time correlation feature corresponding to the current sampling time is as follows:

in this alternative embodiment, the first input data and the second input data may be combined to be input data of the current sampling time, and the input data and the tag data of the current sampling time may be corresponding to be training data corresponding to the current sampling time, and all the training data may be stored to obtain a training data set.

In this alternative embodiment, the preset initial prediction model is formed by connecting a plurality of computing elements in series, and fig. 5 is a schematic structural diagram of the initial prediction model. Each computing element corresponds to one sampling time, the input of each computing element is input data of the corresponding sampling time, and the input data is output as the case number of each sampling region corresponding to the sampling time predicted by the initial prediction model.

Fig. 6 shows a schematic structural diagram of any one of the preset initial prediction models, and as shown in fig. 6, each of the calculation units includes a first cell and a second cell, and the structures and functions of the first cell and the second cell are the same as those of the cells in the long short term memory model (LSTM, long Short Term Memory). The input of the first cell is the first input data at the current moment and the cell state at the last moment, and the output of the first cell is the first cell state at the current moment and a first prediction result; the input of the second cell is the second input data at the current moment and the cell state at the last moment, and the output of the second cell is the second cell state at the current moment and a second prediction result; the cell state is a variable output by the first cell and the second cell, and the function of the cell state is to store the information of the infectious disease characteristic data corresponding to all sampling moments before the current sampling moment, so that the information related to infectious disease at the earlier sampling moment can be transmitted to the later sampling moment, thereby overcoming the negative influence of short-time memory on the prediction result.

In this alternative embodiment, the output of the computing element is weighted sum data of the first prediction result and the second prediction result, and the output result of the computing element satisfies the following relation:

wherein Out _t Representing the output result of the corresponding computing element at the t sampling moment, namely the predicted first of the initial prediction modelthe number of cases in each sampling area at t sampling moments;

representing a first prediction result corresponding to the t sampling moment; />

Representing a second prediction result corresponding to the t sampling moment; alpha ¹ And alpha ² All are preset blending weights, and after multiple experiments, the alpha is calculated by ¹ And alpha ² The values of (2) may be 0.5.

In this optional embodiment, the prediction result of the current sampling time refers to the number of cases predicted at the current sampling time and corresponding to the data related to the infectious disease, and the prediction result of the previous time refers to the number of predicted cases corresponding to the previous time of the current sampling time.

In this alternative embodiment, the prediction result and the tag data may be input into a preset loss function to calculate the loss value of the initial prediction model, where the preset loss function may be an existing loss function such as a root-mean-square error function, a cosine distance function, and the like, which is not limited in this application.

For example, when the preset loss function is a root mean square error and the number of cases predicted at the sampling time is Out, and the tag data is obtained at the same sampling time as a, the loss value of the initial prediction model is calculated in a manner satisfying the following relation:

wherein Loss represents a Loss value of the initial predictive model; m represents the number of training data, i.e. the number of sampling instants; out is provided with _i Representing the predicted result of the initial prediction model at the ith sampling time, namely the predicted case number at the ith sampling time; a is that _i Representing label data corresponding to the ith sampling moment,i.e. the number of cases acquired at the i-th sampling instant.

For example, when the sampling area is 3, the sampling time is two and is respectively 1 time and 2 time, when the number of cases acquired at the 1 time and the 2 time is [200,150,300], [200,200,300], and the number of cases predicted at the 1 time and the 2 time is [190,140,200], [200,150,300], the loss value of the initial prediction model is calculated in the following manner:

the loss value of the initial predictive model is 75.49.

In this alternative embodiment, the initial prediction model may be updated by using a gradient descent method until the loss value of the initial prediction model is less than a preset termination threshold, and updating is stopped and an infectious disease early warning model is obtained. When the loss value of the initial prediction model is smaller than a preset termination threshold, the difference between the number of cases predicted by the initial prediction model and the number of cases acquired in each region is smaller, and further the accuracy of the prediction result output by the initial prediction model is higher, and in order to consider the model training speed and the model performance, the preset termination threshold can be set to be 0.001 according to experimental experience.

In this alternative embodiment, the infection early warning model may predict the number of cases in a plurality of sampling regions based on the characteristic data of the infection acquired in real time in the plurality of sampling regions.

In this way, the space-time correlation matrix among different sampling areas is used for correcting the related data of the infectious disease, a training data set is constructed, and the training data set is input into the initial prediction model comprising two channels to train the model, so that the model can comprise space-time correlation information, and the accuracy of infectious disease early warning is improved.

S13, inputting the infectious disease characteristic data of each sampling area acquired in real time into the infectious disease early warning model to obtain a real-time prediction result, wherein the real-time prediction result is used for representing the case number of the sampling area.

In an alternative embodiment, the inputting the acquired infectious disease characteristic data of each sampling area into the infectious disease early warning model to obtain a real-time prediction result includes:

In this alternative embodiment, in order to predict the number of infection cases of the infectious disease in a large scale, the infectious disease feature data may be collected in real time in the plurality of sampling regions, and the infectious disease feature data collected in real time and the number of infectious disease cases collected in real time at the previous time may be used as the real-time first input data, and when there are 3 sampling regions, namely, region 1, region 2 and region 3, the infectious disease feature data collected in real time and the number of infectious disease cases collected in real time at each time are exemplified as shown in fig. 7, that is, the real-time first input data.

In this alternative embodiment, the product of the space-time correlation matrix and the infectious disease feature data acquired in real time may be calculated to obtain a real-time space-time correlation feature, and the real-time space-time correlation feature and the number of infectious disease cases acquired at the previous time are combined to form real-time second input data.

Inputting the real-time first input data and the real-time second input data into the infectious disease early warning model to obtain real-time prediction results corresponding to infectious disease characteristic data collected in real time, wherein the real-time prediction results are used for representing the real-time case numbers corresponding to all sampling areas predicted by the infectious disease early warning model.

Illustratively, when the sampling region is three and is region 1, region 2 and region 3, respectively, the real-time prediction result is [100,200,300] when the real-time prediction result is region 1 case count 100, region 2 case count 200 and region 3 case count 300.

Therefore, the real-time prediction result corresponding to the infectious disease characteristic data acquired in real time is predicted through the infectious disease early warning model, the timeliness of infectious disease early warning can be improved, and data support is provided for preventing and treating infectious diseases.

And S14, evaluating the real-time prediction results according to the number of the historical contemporaneous cases in each sampling area to obtain evaluation results, and carrying out infectious disease early warning according to the evaluation results.

In an optional embodiment, the evaluating the real-time prediction result according to the number of the historical contemporaneous cases of each sampling area to obtain an evaluation result, and performing early warning of infectious diseases according to the evaluation result includes:

Acquiring the number of historical contemporaneous cases of each sampling area;

In this alternative embodiment, the number of contemporaneous cases refers to the number of cases in the sampling area at the same time in the last year as the time when the characteristic data of the infectious disease was collected in real time. Illustratively, when the moment of acquiring the infectious disease characteristic data in real time is 2022, 9, then the history is 2021, 9.

In this alternative embodiment, for a certain sampling area, if the real-time prediction result is greater than the number of the historical contemporaneous cases, it indicates that the infection spread condition of the area is serious, and advanced early warning of the infection needs to be performed on the sampling area.

In this alternative embodiment, the preset safety threshold may be set by a medical expert according to the category of infectious diseases, and the preset safety threshold may be 5%, 6% or the like of the number of historical contemporaneous cases, which is not limited in this application.

In this optional embodiment, when the real-time prediction result is smaller than the number of the historical contemporaneous cases, if the difference between the real-time prediction result and the number of the historical contemporaneous cases is smaller than the preset safety threshold, it indicates that the real-time prediction result does not exceed the historical contemporaneous level, but there is still a risk of an infection spread outbreak, and then low-level early warning of the infection is required in the sampling area.

If the difference between the real-time prediction result and the number of the historical contemporaneous cases is larger than the preset safety threshold, the fact that the number of cases in the sampling area is smaller and the probability of infection outbreak is lower is indicated, and infection early warning is not needed in the sampling area.

Therefore, by comparing the real-time prediction result with the historical contemporaneous case data to make an infectious disease early warning decision, more accurate infectious disease prevention and control can be performed according to the predicted case data, and the accuracy of infectious disease prevention and control is improved.

Fig. 2 is a functional block diagram of a preferred embodiment of an artificial intelligence-based infectious disease early warning apparatus according to an embodiment of the present application. The infectious disease early warning device 11 based on artificial intelligence comprises a sampling unit 110, a construction unit 111, a training unit 112, a real-time prediction unit 113 and an early warning unit 114. The module/unit referred to in this application refers to a series of computer program segments capable of being executed by the processor 13 and of performing fixed functions, which are stored in the memory 12. In the present embodiment, the functions of the respective modules/units will be described in detail in the following embodiments.

The sampling unit 110 is configured to collect infectious disease feature data and tag data in a plurality of sampling regions, where the tag data is used to characterize the number of cases in each of the sampling regions;

the construction unit 111 is configured to construct a space-time correlation matrix of the infectious disease feature data according to the tag data;

the training unit 112 is configured to train an infectious disease early warning model according to the infectious disease feature data, the tag data and the space-time correlation matrix;

the real-time prediction unit 113 is configured to input the real-time collected infectious disease feature data of each sampling area into the infectious disease early-warning model to obtain a real-time prediction result, where the real-time prediction result is used to characterize the number of cases of each sampling area obtained in real time;

the early warning unit 114 is configured to evaluate the real-time prediction result according to the number of the historical contemporaneous cases in each sampling area to obtain an evaluation result, and perform early warning on infectious diseases according to the evaluation result.

In some alternative embodiments, the sampling unit 110 is further configured to:

In some alternative embodiments, the construction unit 111 is further configured to:

In some alternative embodiments, the training unit 112 is further configured to:

In some alternative embodiments, the real-time prediction unit 113 is further configured to:

In some alternative embodiments, the pre-warning unit 114 is further configured to:

Acquiring the number of historical contemporaneous cases of each sampling area;

Fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present application. The electronic device 1 comprises a memory 12 and a processor 13. The memory 12 is used for storing computer readable instructions, and the processor 13 is used for executing the computer readable instructions stored in the memory to implement the artificial intelligence based infectious disease early warning method of any of the above embodiments.

In an alternative embodiment, the electronic device 1 further comprises a bus, a computer program stored in the memory 12 and executable on the processor 13, such as an artificial intelligence based infectious disease early warning program.

Fig. 3 shows only an electronic device 1 with a memory 12 and a processor 13, it being understood by a person skilled in the art that the structure shown in fig. 3 does not constitute a limitation of the electronic device 1, and may comprise fewer or more components than shown, or may combine certain components, or a different arrangement of components.

In connection with fig. 1, the memory 12 in the electronic device 1 stores a plurality of computer readable instructions to implement an artificial intelligence based infectious disease early warning method, the processor 13 may execute the plurality of instructions to implement:

Specifically, the specific implementation method of the above instructions by the processor 13 may refer to the description of the relevant steps in the corresponding embodiment of fig. 1, which is not repeated herein.

It will be appreciated by those skilled in the art that the schematic diagram is merely an example of the electronic device 1 and does not constitute a limitation of the electronic device 1, the electronic device 1 may be a bus type structure, a star type structure, the electronic device 1 may further comprise more or less other hardware or software than illustrated, or a different arrangement of components, e.g. the electronic device 1 may further comprise an input-output device, a network access device, etc.

It should be noted that the electronic device 1 is only used as an example, and other electronic products that may be present in the present application or may be present in the future are also included in the scope of the present application and are incorporated herein by reference.

The memory 12 includes at least one type of readable storage medium, which may be non-volatile or volatile. The readable storage medium includes flash memory, a removable hard disk, a multimedia card, a card type memory (e.g., SD or DX memory, etc.), a magnetic memory, a magnetic disk, an optical disk, etc. The memory 12 may in some embodiments be an internal storage unit of the electronic device 1, such as a mobile hard disk of the electronic device 1. The memory 12 may in other embodiments also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like, which are provided on the electronic device 1. Further, the memory 12 may also include both an internal storage unit and an external storage device of the electronic device 1. The memory 12 may be used not only for storing application software installed in the electronic device 1 and various types of data, such as codes of an artificial intelligence-based infectious disease warning program, etc., but also for temporarily storing data that has been output or is to be output.

The processor 13 may be comprised of integrated circuits in some embodiments, for example, a single packaged integrated circuit, or may be comprised of multiple integrated circuits packaged with the same or different functions, including one or more central processing units (Central Processing unit, CPU), microprocessors, digital processing chips, graphics processors, a combination of various control chips, and the like. The processor 13 is a Control Unit (Control Unit) of the electronic device 1, connects the respective components of the entire electronic device 1 using various interfaces and lines, executes or executes programs or modules stored in the memory 12 (for example, executes an artificial intelligence-based infectious disease warning program or the like), and invokes data stored in the memory 12 to perform various functions of the electronic device 1 and process the data.

The processor 13 executes an operating system of the electronic device 1 and various types of applications installed. The processor 13 executes the application program to implement the steps of the various embodiments of the artificial intelligence based infectious disease early warning method described above, such as the steps shown in fig. 1.

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, for example. The one or more modules/units may be a series of computer readable instruction segments capable of performing the specified functions, which instruction segments describe the execution of the computer program in the electronic device 1. For example, the computer program may be divided into a sampling unit 110, a construction unit 111, a training unit 112, a real-time prediction unit 113, an early warning unit 114.

The integrated units implemented in the form of software functional modules described above may be stored in a computer readable storage medium. The software functional modules are stored in a storage medium and include instructions for causing a computer device (which may be a personal computer, a computer device, or a network device, etc.) or a processor (processor) to perform portions of the artificial intelligence-based infectious disease early warning method described in various embodiments of the present application.

The integrated modules/units of the electronic device 1 may be stored in a computer readable storage medium if implemented in the form of software functional units and sold or used as a stand alone product. Based on such understanding, the present application may implement all or part of the flow of the method of the above embodiment, or may be implemented by instructing the relevant hardware device by a computer program, where the computer program may be stored in a computer readable storage medium, and the computer program may implement the steps of each method embodiment described above when executed by a processor.

Wherein the computer program comprises computer program code which may be in source code form, object code form, executable file or some intermediate form etc. The computer readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory, other memories, and the like.

Further, the computer-readable storage medium may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function, and the like; the storage data area may store data created from the use of blockchain nodes, and the like.

The bus may be a peripheral component interconnect standard (Peripheral Component Interconnect, PCI) bus or an extended industry standard architecture (Extended Industry Standard Architecture, EISA) bus, among others. The bus may be classified as an address bus, a data bus, a control bus, etc. For ease of illustration, only one arrow is shown in FIG. 3, but only one bus or one type of bus is not shown. The bus is arranged to enable a connection communication between the memory 12 and the at least one processor 13 etc.

The embodiment of the application further provides a computer readable storage medium (not shown), in which computer readable instructions are stored, and the computer readable instructions are executed by a processor in an electronic device to implement the method for early warning infectious diseases based on artificial intelligence according to any one of the embodiments.

Furthermore, it is evident that the word "comprising" does not exclude other elements or steps, and that the singular does not exclude a plurality. Several of the elements or devices described in the specification may be embodied by one and the same item of software or hardware. The terms first, second, etc. are used to denote a name, but not any particular order.

Finally, it should be noted that the above embodiments are merely for illustrating the technical solution of the present application and not for limiting, and although the present application has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present application may be modified or substituted without departing from the spirit and scope of the technical solution of the present application.

Claims

1. An artificial intelligence-based infectious disease early warning method, which is characterized by comprising the following steps:

2. The artificial intelligence based infectious disease early warning method of claim 1, wherein the collecting infectious disease characterization data and tag data at a plurality of sampling areas comprises:

3. The artificial intelligence based infectious disease early warning method of claim 1, wherein constructing a spatiotemporal correlation matrix of the infectious disease characterization data based on the tag data comprises:

4. The artificial intelligence based infectious disease early warning method of claim 1, wherein training an infectious disease early warning model based on the infectious disease characterization data, the tag data, and the spatiotemporal correlation matrix comprises:

5. The artificial intelligence based infectious disease early warning method of claim 4 wherein constructing a training data set based on the tag data, the infectious disease characterization data, and the spatiotemporal correlation matrix comprises:

6. The artificial intelligence based infectious disease early warning method of claim 1, wherein inputting the infectious disease characteristic data of each of the sampling regions collected in real time into the infectious disease early warning model to obtain a real-time prediction result, comprises:

7. The method for early warning infectious diseases based on artificial intelligence according to claim 1, wherein the evaluating the real-time prediction result according to the number of the historical contemporaneous cases of each sampling region to obtain an evaluation result, and performing early warning of infectious diseases according to the evaluation result comprises:

acquiring the number of historical contemporaneous cases of each sampling area;

8. An artificial intelligence based infectious disease early warning device, the device comprising:

9. An electronic device, the electronic device comprising:

A processor executing computer readable instructions stored in the memory to implement the artificial intelligence based infectious disease early warning method as claimed in any one of claims 1 to 7.

10. A computer readable storage medium having computer readable instructions stored therein, the computer readable instructions being executable by a processor in an electronic device to implement the artificial intelligence based infectious disease early warning method of any one of claims 1 to 7.