WO2021180245A1 - Server, data processing method and apparatus, and readable storage medium - Google Patents

Abstract

A server, a data processing method and apparatus, and a readable storage medium, which are applied in the field of medical technology. The server comprises a communication interface, a processor and a memory, the processor being configured to invoke program instructions in the memory for execution of: receiving a first infection prediction request by means of the communication interface; acquiring infection statistical data and an implementation state of a first management and control measure of a target infectious disease in a region to be predicted at a target time, and invoking a target prediction model to perform data analysis; and determining first cumulative data of confirmed cases on the basis of a first data analysis result outputted by the target prediction model. In this way, the accuracy of prediction of confirmed data of the target infectious disease is improved for regions in the early stage of the epidemic. The present invention relates to the blockchain technology, for example, the infection statistical data and the implementation state of the first management and control measure associated with the target infectious disease and the region to be predicted can be written into a blockchain for data analysis and prediction of the target infectious disease.

Description

Server, data processing method, device and readable storage medium

This application claims the priority of the Chinese patent application filed with the Chinese Patent Office on November 2, 2020, the application number is 202011203198.5, and the invention title is "a server, data processing method, device, and readable storage medium", and its entire content Incorporated in this application by reference.

Technical field

This application relates to the field of intelligent decision-making, and is specifically applied to the field of medical technology, and in particular to a server, a data processing method, a device, and a readable storage medium.

Background technique

Infectious diseases are a type of diseases caused by pathogens that can be transmitted from person to person, animal to animal, or person to animal, and they are usually highly transmissible. For example, in 2019, the new coronavirus (Corona Virus Disease 2019, COVID-19) broke out on a large scale in countries around the world. As of August 3, 2020, more than 18 million confirmed cases have been reported in more than 220 countries and regions around the world. More than 680,000 patients have died, and the spread is still ongoing. In order to formulate better management and control strategies and medical resource allocation strategies during the epidemic, it is urgent to establish a prediction model to estimate the development status of the epidemic in each epidemic area.

However, the inventor realized that due to the different outbreak periods corresponding to each epidemic area, the model training sample data corresponding to the epidemic area in the early stage of the epidemic is much lower than the epidemic area in the late epidemic period, resulting in the prediction model corresponding to the epidemic area in the early epidemic period. , There is a problem of low accuracy in predicting the epidemic diagnosis data, which makes it impossible to accurately formulate a response control strategy and medical resource allocation strategy for the epidemic area during the epidemic.

It can be seen that how to provide a data processing method for the epidemic area in the early stage of the epidemic to improve the accuracy of the prediction of the confirmed data of the target infectious disease is an urgent problem to be solved.

Summary of the invention

The embodiments of the present application provide a server, a data processing method, a device, and a readable storage medium. Using this method, a data processing method is provided for an epidemic area in the early stage of an epidemic (that is, an epidemic area with fewer training samples) , This method improves the accuracy of predicting the confirmed data of the target infectious disease.

In the first aspect, an embodiment of the present application provides a server, the server includes a communication interface, a processor, and a memory, where:

The memory is used to store a computer program, and the computer program includes program instructions;

The processor is configured to call the program instructions for receiving, through the communication interface, a first infection prediction request associated with the area to be predicted and the target infectious disease, and the first infection prediction request is used to instruct to predict the Predict the first cumulative diagnosis data associated with the target infectious disease at the predicted time in the predicted area; obtain the infection statistics data associated with the target infectious disease at the target time in the to-be-predicted area and the implementation status of the first control measures, and Calling a target prediction model to perform data analysis on the infection statistics and the implementation status of the first control measures, the target time is determined based on the predicted time; determined based on the first data analysis result output by the target prediction model The first cumulative diagnosis data;

Wherein, the target prediction model is obtained by revising the prediction model according to the historical infection statistics of the target infectious disease and the implementation status of historical control measures in the area to be predicted. The historical infection statistics of the target infectious disease and the implementation status of historical management and control measures are determined; the occurrence time of the target infectious disease in the predicted reference area is earlier than the occurrence time of the target infectious disease in the area to be predicted.

In the second aspect, an embodiment of the present application provides a data processing method, the data processing method is executed by a server, and the method includes:

Receive a first infection prediction request associated with the area to be predicted and the target infectious disease, where the first infection prediction request is used to instruct to predict the first cumulative confirmed data associated with the target infectious disease in the area to be predicted at the predicted time ；

Acquire the infection statistics data and the implementation status of the first control measures associated with the target infectious disease at the target time in the region to be predicted, and call the target prediction model to perform the statistics on the infection statistics and the implementation status of the first control measures Data analysis, the target time is determined based on the predicted time;

Determining the first cumulative diagnosis data based on the first data analysis result output by the target prediction model;

Wherein, the target prediction model is obtained by revising the prediction model according to the historical infection statistics of the target infectious disease and the implementation status of historical control measures in the area to be predicted. The historical infection statistics of the target infectious disease and the implementation status of historical management and control measures are determined; the occurrence time of the target infectious disease in the predicted reference area is earlier than the occurrence time of the target infectious disease in the area to be predicted.

In a third aspect, an embodiment of the present application provides a data processing device, the data processing device is deployed on a server, and the device includes:

The acquisition module is configured to receive a first infection prediction request associated with the area to be predicted and the target infectious disease, where the first infection prediction request is used to instruct to predict the area to be predicted that is associated with the target infectious disease at the predicted time The first cumulative confirmed data;

The acquisition module is also used to acquire the infection statistics data associated with the target infectious disease at the target time in the area to be predicted and the implementation status of the first management and control measures, and call the target prediction model to analyze the infection statistics and the infection statistics. Perform data analysis on the implementation status of the first control measure, and the target time is determined based on the predicted time;

A processing module, configured to determine the first cumulative diagnosis data based on the first data analysis result output by the target prediction model;

Wherein, the target prediction model is obtained by revising the prediction model according to the historical infection statistics of the target infectious disease and the implementation status of historical control measures in the area to be predicted. The historical infection statistics of the target infectious disease and the implementation status of historical management and control measures are determined; the occurrence time of the target infectious disease in the predicted reference area is earlier than the occurrence time of the target infectious disease in the area to be predicted.

In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium that stores instructions in the computer-readable storage medium, which when run on a computer, causes the computer to execute the following method:

Receive a first infection prediction request associated with the area to be predicted and the target infectious disease, where the first infection prediction request is used to instruct to predict the first cumulative confirmed data associated with the target infectious disease in the area to be predicted at the predicted time ；

Acquire the infection statistics data and the implementation status of the first control measures associated with the target infectious disease at the target time in the region to be predicted, and call the target prediction model to perform the statistics on the infection statistics and the implementation status of the first control measures Data analysis, the target time is determined based on the predicted time;

Determining the first cumulative diagnosis data based on the first data analysis result output by the target prediction model;

Wherein, the target prediction model is obtained by revising the prediction model according to the historical infection statistics of the target infectious disease and the implementation status of historical control measures in the area to be predicted. The historical infection statistics of the target infectious disease and the implementation status of historical management and control measures are determined; the occurrence time of the target infectious disease in the predicted reference area is earlier than the occurrence time of the target infectious disease in the area to be predicted.

In the embodiments of this application, a prediction model with higher accuracy is obtained based on the historical infection statistics of the target infectious disease in the predicted reference area and the implementation status of historical control measures, and further based on the historical infection statistics of the target infectious disease in the area to be predicted and The implementation status of historical control measures revises the prediction model to obtain the target prediction model corresponding to the area to be predicted. Through this data processing method, the accuracy of the prediction model corresponding to the epidemic area in the early stage of the epidemic is improved.

Description of the drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only These are some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work.

FIG. 1 is a schematic flowchart of a data processing method provided by an embodiment of the present application;

2 is a schematic flowchart of another data processing method provided by an embodiment of the present application;

Fig. 3a is a schematic diagram of a training process of a prediction model provided by an embodiment of the present application;

FIG. 3b is a schematic diagram of obtaining sequence data according to a preset time sliding window according to an embodiment of the present application; FIG.

FIG. 3c is a schematic diagram of a process of correcting a prediction model to obtain a target prediction model according to an embodiment of the present application;

FIG. 3d is a schematic diagram of changing from the implementation state of the first control measure to the implementation state of the second control measure according to an embodiment of the present application;

FIG. 4 is a schematic structural diagram of a data processing device provided by an embodiment of the present application;

Fig. 5 is a schematic structural diagram of a server provided by an embodiment of the present application.

Detailed ways

The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of this application.

The technical solution of the present application may involve the field of artificial intelligence technology, for example, it may specifically involve neural network technology, and can be applied to scenarios such as smart medical care, so as to realize digital medical care and push the construction of smart cities. Optionally, the data involved in this application, such as diagnosis data, infection statistics, time information, and/or models, etc., can be stored in a database, or can be stored in a blockchain, which is not limited in this application.

It should be known that the server mentioned in the embodiment of the present application is not limited to one server, and may also be a server cluster.

Please refer to FIG. 1, which is a schematic flowchart of a data processing method provided by an embodiment of the present application. The data processing method is executed by a server, and the data processing method includes the following steps:

S101: Receive a first infection prediction request associated with the area to be predicted and the target infectious disease, where the first infection prediction request is used to instruct to predict that the area to be predicted is associated with the first cumulative diagnosis data of the target infectious disease at the predicted time.

The server receives a first infection prediction request input by a user through a terminal device connected to the server, and the first infection prediction request is used to instruct to predict the first cumulative diagnosis data associated with the target infectious disease at the predicted time in the area to be predicted. Wherein, the first infection prediction request includes one or more of the identification information of the area to be predicted, the time to be predicted, and the identification information of the target infectious disease. Among them, the predicted time is set by the user according to specific application scenarios.

Exemplarily, infectious disease 1 occurred in city A in August 2019, and infectious disease 2 occurred in September 2019. On March 4, 2020, the user entered the first infection prediction request: "March 5, for infection The cumulative diagnosis data of disease 1 city A".

S102: Obtain the infection statistics data and the implementation status of the first control measures associated with the target infectious disease at the target time in the area to be predicted, and call the target prediction model to perform data analysis on the infection statistics and the implementation status of the first control measures. The target time is determined based on the predicted time.

Among them, the target prediction model is obtained by revising the prediction model based on the historical infection statistics of the target infectious disease in the area to be predicted and the implementation status of historical control measures. The prediction model is based on the historical infection statistics of the target infectious disease in the predicted reference area. The implementation status of historical control measures is determined, and the occurrence time of the target infectious disease in the reference area for prediction is earlier than the occurrence time of the target infectious disease in the area to be predicted.

What needs to be known is that the stage of infectious disease can be divided into early stage and late stage of the epidemic. The area in the early stage of the epidemic refers to the time when the infectious disease was found in the area (the time to determine the specific infectious disease stage in the area) is relatively long. Short, and/or the number of newly diagnosed infectious diseases daily is higher than the daily cured number of infectious diseases, and/or the daily newly diagnosed number is higher than the daily newly diagnosed number of the previous day. The area in the late stage of the epidemic means that the time since the infectious disease was found in the area (the time to determine the specific infectious disease stage in the area) is longer, and/or the spread of the infectious disease has been controlled, and / Or the daily number of newly diagnosed infectious diseases is less than the daily cured number of infectious diseases, and/or the daily newly diagnosed number is lower than the daily newly diagnosed number of the previous day. The prediction reference area mentioned in the embodiment of this application is the area in the late stage of the epidemic of the target infectious disease, and the area to be predicted is the area in the early stage of the epidemic of the target infectious disease, that is, the predicted reference area has an early occurrence time of the target infectious disease. In the region to be predicted.

In this way, it can be known that the historical statistical data (including historical infection statistics and the implementation status of historical control measures) for the target infectious disease in the predicted reference area is relatively sufficient, and the prediction model obtained according to the predicted reference area has a higher accuracy. The historical infection statistics of the target infectious disease in the area to be predicted and the implementation status of historical control measures are revised to the prediction model (that is, the migration of the prediction model), and the target prediction model corresponding to the area to be predicted is obtained, and this data processing method is used to improve The accuracy of the target prediction model corresponding to the epidemic area in the early stage of the epidemic is determined.

After the server receives the first infection prediction request, it determines the target time according to the prediction time included in the first infection prediction request. For example, if the prediction time in the first infection prediction request is March 8, 2020, it can be set to March 1, 2020. Date to March 7, 2020 is determined as the target time. Further, the server obtains the infection statistics data and the implementation status of the first control measures associated with the target infectious disease at the target time in the area to be predicted, and calls the target prediction model to perform data analysis on the infection statistics and the implementation status of the first control measures .

In one embodiment, the server may determine the target time according to the prediction time included in the first infection prediction request and a preset duration, where the preset duration may be related to training data used by the target prediction model. For example, if the sequence duration of the sequence data (including training data and test data) used by the target prediction model is 7 days, the preset duration is 7 days. Further, the server can obtain historical statistical data and the status of management and control measures 7 days before the forecast time.

S103: Determine the first cumulative diagnosis data based on the first data analysis result output by the target prediction model.

The server outputs the first data analysis result and determines the first cumulative diagnosis data according to the analysis of the infection statistics data associated with the target infectious disease at the target time and the implementation status of the first control measures in the area to be predicted in the target prediction model. For example, if the first data analysis result of the target prediction model is 250,000, the server determines the first cumulative confirmed data according to the first infection prediction: the cumulative number of confirmed diagnoses in city A on March 8, 2020 is 250,000.

In this embodiment of the application, the server receives the first infection prediction request associated with the area to be predicted and the target infectious disease, and the first infection prediction request is used to instruct to predict the first infection prediction request associated with the target infectious disease in the area to be predicted at the predicted time. Accumulated confirmed data. Furthermore, the server can obtain the infection statistics data and the implementation status of the first control measures associated with the target infectious disease at the target time in the area to be predicted, and call the target prediction model to perform data on the statistics data and the implementation status of the first control measures. Analysis, where the target time is determined based on the predicted time. Further, the server determines the first cumulative diagnosis data based on the first data analysis result output by the target prediction model. What needs to be known is that the target prediction model is obtained by revising the prediction model based on the historical infection statistics of the target infectious disease in the area to be predicted and the implementation status of historical control measures. The prediction model is based on the history of the target infectious disease in the predicted reference area. Infection statistics and the implementation status of historical control measures are determined. The occurrence time of the target infectious disease in the reference area for prediction is earlier than the occurrence time of the target infectious disease in the area to be predicted. In this way, a data processing method is provided for epidemic areas in the early stage of the epidemic (that is, epidemic areas with fewer training samples), which improves the accuracy of predicting the confirmed data of the target infectious disease.

Please refer to FIG. 2, which is a schematic flowchart of another data processing method provided by an embodiment of the present application. The data processing method is executed by a server, and the data processing method includes the following steps:

S201: Obtain historical infection statistics and historical control measures implementation status of the target infectious disease in the region to be predicted, and obtain historical infection statistics of the target infectious disease in the prediction reference region and a prediction model for determining the implementation status of historical control measures.

Among them, historical infection statistics are the daily cumulative number of confirmed diagnoses of the target infectious disease in the area to be predicted; the implementation status of historical control measures is the implementation status of the daily control measures for the target infectious disease in the area to be predicted, and the implementation status of the daily control measures in the area to be predicted Either the state of implementing control and the state of not implementing control.

The server obtains the historical daily cumulative number of confirmed diagnoses of the target infectious disease in the area to be predicted (that is, historical infection statistics) and the status of daily control measures (that is, the implementation status of historical control and control). For example, the date of discovery of the target infectious disease in the area to be predicted is On X 1st, obtain the historical infection statistics data and historical control measures implementation status of the target infectious disease in the region to be predicted so far (X 7th), that is, obtain the daily cumulative number of confirmed diagnoses from X 1 to X 7 The implementation status of daily control measures, in which data 0 and 1 indicate the implementation status of the control measures, and the server obtains historical infection statistics and historical control measures implementation status of the target infectious disease in the area to be predicted as shown in Table 1:

Table 1

date	Daily confirmed number (10,000 people)	Whether to implement control measures
X month 1	1	0
X month 2	2.5	0
X month 3	4	0
X month 4	6.5	0
X month 5	7.5	0
X month 6	9	0
X 7th	12	0

The server obtains the historical infection statistics of the target infectious disease in the predicted reference area and the specific method of determining the prediction model for the implementation status of historical control measures. The server can determine at least one area in the late stage of the epidemic as the prediction reference area, and obtain the prediction reference area about the target. Historical infection statistics and the implementation status of historical control measures. Further, the server trains the preset network model according to the historical infection statistics of the target in the predicted reference area and the implementation status of historical control measures to obtain a prediction model. Among them, the preset network model can be one of Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU). Any kind.

Specifically, the server obtains the historical infection statistics and historical control measures implementation status of the target in the predicted reference region, and preprocesses the historical infection statistics and historical control measures implementation status of the target in the predicted reference region according to a preset time sliding window. Obtain at least one piece of sequence data about the target infectious disease in the prediction reference area, and further, the server trains a preset network model according to the at least one piece of sequence data to obtain a prediction model. Among them, the preset time sliding window includes the size of the time sliding window and the sliding step length. The preset time sliding window can be set by the developer according to the experimental application scenario, and subsequent adjustments can be made according to the specific application scenario. Specific restrictions. For example, the size of the preset time sliding window can be 7 days or 10 days, and the step size is 1.

Illustratively, as shown in FIG. 3a, it is the training process of the prediction model, where the module 30 is the historical infection statistics data and the historical control measures implementation status of the target infectious disease in the three prediction reference regions, and the module 31 is the preset network model. Module 32 is a predictive model. The server obtains the historical infection statistics data and the historical control measures implementation status of the predicted reference area as follows: the daily cumulative number of confirmed cases of the target infectious disease and the implementation status of the daily control measures from July 1st to July 10th. At the preset time, the size of the sliding window is 7 days and the step length is 1 o'clock. As shown in Figure 3b, the server can compare the daily cumulative number of confirmed diagnoses from July 1 to July 7 in at least one prediction reference area and the The implementation status of daily control measures, the daily cumulative number of confirmed diagnoses from July 2 to July 8 and the implementation status of daily control measures, the daily cumulative number of confirmed diagnoses and the implementation of daily control measures from July 3 to July 9 The status, the daily cumulative number of confirmed diagnoses from July 4th to July 10th, and the implementation status of daily control measures are respectively determined as serial data. Furthermore, the server can take the daily cumulative number of confirmed diagnoses and the implementation status of daily control measures from July 1 to July 7 as input to the preset network model, and the daily cumulative number of confirmed diagnoses and daily control measures on July 8 The implementation state of the measure is the output of the preset network model, and the preset network model 31 is trained in an analogous manner to obtain the prediction model 32. The prediction model 32 can analyze and obtain the daily cumulative number of diagnoses and the implementation status of daily control measures at the predicted time point based on the daily cumulative number of confirmed diagnoses in the first 7 days of the forecast time point and the implementation status of daily control measures.

In one embodiment, the specific implementation manner for the server to obtain historical infection statistics on the target infectious disease in the area to be predicted and the implementation status of historical control measures may be that the server obtains historical consultation information about the target infectious disease in the area to be predicted. The information includes historical infection statistical data consultation information and historical control measures implementation status consultation information. Further, the server may call the text recognition algorithm model to obtain historical infection statistics of the target infectious disease from the historical infection statistical data consultation information, and call the text recognition algorithm model to obtain the pending information from the historical control measures implementation status consultation information. Forecast the implementation status of the historical control measures for the target infectious diseases in the region.

Among them, the text recognition algorithm may be a neural network model algorithm pre-trained by the developer based on experimental measurement data, such as a convolutional neural network algorithm, etc., which is not specifically limited here. Historical consultation information can be news consultation information, government public consultation information, and so on.

Exemplarily, the historical consultation information is news information, and the server obtains the news information of target area A on the 1st of X: "As of 12:00 today, the number of confirmed cases in target area A is 83,000. In order to do our best To do a good job in the prevention and control of the epidemic to ensure the safety and health of the people, the following notice is hereby issued: urban buses, subways, ferries, and long-distance passenger transportation will be suspended, and the resumption time will be notified separately." The server calls the convolutional neural network text recognition algorithm model from this According to the consultation information, the number of people diagnosed on X on 1st was 83,000, and the consultation information on the implementation of management and control measures is "Urban buses, subways, ferries, and long-distance passenger transportation are suspended." Further, the server can match the implementation information of the management and control measures with the preset text feature information (here can be channel closure, passenger suspension operation, isolation, prohibition of gathering, and flight limit). It can be seen that the matching is successful, and the server will confirm The implementation status of the control measures for the target area A on X 1st is: implementation control status. That is, the server obtains the epidemic data of the target area A on the 1st of X: the daily cumulative number of confirmed diagnoses is 83,000, and the state of control is implemented. It should be known that the preset text feature information can be set by the developer according to the experimental application scenario, and subsequent adjustments can be made according to the specific application scenario, which is not specifically limited here.

S202: Correct the prediction model according to the historical infection statistics of the target infectious disease in the region to be predicted and the implementation status of historical control measures to obtain a target prediction model corresponding to the region to be predicted.

The server obtains historical infection statistics of the target infectious disease in the area to be predicted and the implementation status of historical control measures to correct the weight parameters of the fully connected layer of the prediction model to obtain the target prediction model corresponding to the area to be predicted.

In one embodiment, after the server obtains the historical infection statistics data and historical control measures implementation status of the target infectious disease in the area to be predicted, the server slides the window according to a preset time to predict the historical infection statistics data and historical control measures of the target infectious disease in the predicted area. The implementation status of the measures is preprocessed to obtain at least one sequence data of the target infectious disease in the area to be predicted. Further, the server modifies the aforementioned prediction model according to at least one sequence data of the target infectious disease in the area to be predicted to obtain the target prediction model corresponding to the area to be predicted. Among them, the preset time sliding window includes the size of the time sliding window and the sliding step length. The preset time sliding window can be set by the developer according to the experimental application scenario, and subsequent adjustments can be made according to the specific application scenario. Specific restrictions.

Illustratively, as shown in FIG. 3c, it is the process of revising the prediction model to obtain the target prediction model. Module 33 is the historical infection statistics and historical control measures implementation status of the target infectious disease in the area to be predicted. Module 34 is the prediction Model, module 35 is a target prediction model corresponding to the area to be predicted. After the server obtains the historical infection statistics of the target infectious disease in the region to be predicted and the implementation status of historical control measures, it uses a preset sliding window with a window size of 7 steps and 1 to convert the historical infection statistics of the target infectious disease in the region to be predicted And the historical control measures are processed as the sequence data shown in module 33. Further, the prediction model 34 is trained according to the sequence data, and the weight corresponding to the fully connected layer of the prediction model 34 is corrected to obtain the target corresponding to the area to be predicted Forecast model 35.

In one embodiment, the server may divide at least one piece of sequence data about the target infectious disease in the area to be predicted into a training sequence data set and a test sequence data set. Further, the server can modify the prediction model according to the training sequence data set. The candidate prediction model corresponding to the area to be predicted is obtained, and the candidate prediction model is verified according to the test sequence data set and preset evaluation rules. If the verification is passed, it is determined that the candidate prediction model is the target prediction model corresponding to the area to be predicted.

What needs to be known is that the server can divide at least one piece of sequence data into a training sequence data set and a test sequence data set according to a preset segmentation ratio. The segmentation ratio is the number of training sequence data sets and the number of test sequence data sets. The ratio can be calculated and set by the developer based on experimental test data, and subsequent adjustments can be made according to specific application scenarios. For example, when the number of at least one piece of sequence data about the target infectious disease in the area to be predicted is 1,200 pieces, the segmentation ratio can be 5:1, and the server can segment at least one piece of sequence data into training according to the segmentation ratio of 5:1 1000 sequence data sets and 200 test sequence data sets.

Among them, the preset evaluation rule is the evaluation rule corresponding to the predictive evaluation index. The predictive evaluation index includes: Root Mean Square Error (RMSE), Mean Square Error (MSE), Mean Absolute Error (Mean Absolute Error, MAE, Mean Absolute Percentage Error (MAPE), and Symmetric Mean Absolute Percentage Error (SMAPE).

Exemplarily, when the predictive evaluation index is MAPE, the evaluation rule is that the model evaluation score of the candidate prediction model obtained according to the preset evaluation index MAPE calculation formula is less than the preset evaluation score threshold, then the candidate prediction model is determined, wherein the preset evaluation The score threshold is set by the developer after calculation based on experimental data, and can be adjusted accordingly according to specific application scenarios in the future, and there is no specific restriction here. The calculation formula of the preset evaluation index MAPE is as follows:

Among them, MAPE is the model evaluation score corresponding to the candidate prediction model, n is the number of sequence data samples in the test sequence sample, and i represents the i-th sequence data sample. Y _i is the actual value corresponding to the i-th sequence data, and g _i (x) is the predicted value corresponding to the i-th sequence data.

S203: Receive a first infection prediction request associated with the area to be predicted and the target infectious disease, where the first infection prediction request is used to instruct to predict that the area to be predicted is associated with the first cumulative diagnosis data of the target infectious disease at the predicted time.

S204: Obtain the infection statistics data and the implementation status of the first control measures associated with the target infectious disease at the target time in the area to be predicted, and call the target prediction model to perform data analysis on the infection statistics and the implementation status of the first control measures. The target time is determined based on the predicted time.

S205: Determine the first cumulative diagnosis data based on the first data analysis result output by the target prediction model.

For the specific implementation manners of step S203 to step S205, please refer to the specific implementation manners of step S101 to step S103 in the foregoing embodiment, which will not be described in detail.

In one embodiment, after the server determines the first cumulative diagnosis data based on the first data analysis result output by the target prediction model, the server may also receive a second infection prediction request associated with the area to be predicted and the target infectious disease. The prediction request is used to indicate the second cumulative diagnosis data associated with the target infectious disease at the predicted time in the predicted region. Further, the server may change the implementation status of the first control measure associated with the target infectious disease at the target time in the area to be predicted to the implementation status of the second control measure, and call the target prediction model for the infection statistics and the second control measure. Data analysis is performed on the implementation status of the measures, where the target time is determined based on the predicted time. The server determines the second cumulative diagnosis data based on the second data analysis result output by the target prediction model. In this way, the first cumulative diagnosis data is compared with the second cumulative diagnosis data to help decision makers decide whether to continue to implement control.

Illustratively, as shown in FIG. 3d, the infection statistics data associated with the target infectious disease at the target time and the implementation status of the first control measures obtained by the server in the area to be predicted at the target time are shown in module 36, and the implementation status of the first control measure is implementation Control status. As shown in module 37, the server changes the state of the first control measure to the state of implementation of the second control measure according to the second infection prediction request, that is, the state of no control measure. Further, the target prediction model is invoked to perform data analysis on the infection statistics and the implementation status of the second control measure to obtain a second data analysis result, and determine the second cumulative diagnosis data according to the second data analysis result. The server can also obtain the impact ratio of the implementation of control measures on the cumulative number of diagnoses based on the second cumulative diagnosis data and the aforementioned first cumulative diagnosis data. The formula for calculating the impact ratio is as follows:

G=(pred _switched -pred _actual )/pred _actual

Among them, pred _switched is the second cumulative diagnosis data, pred _actual is the first cumulative diagnosis data, and G is the ratio of the increase or decrease of the cumulative number of diagnoses. By implementing such a method, the user can make a decision whether to continue to implement the control or whether to implement the control based on the G value.

In the embodiment of this application, the server obtains historical infection statistics and historical control measures implementation status of the target infectious disease in the area to be predicted, and obtains historical infection statistics of the target infectious disease in the prediction reference area and the prediction of the determination of the historical control measure implementation status Model, further, the server can revise the prediction model according to the historical infection statistics of the target infectious disease in the area to be predicted and the implementation status of historical control measures to obtain the target prediction model corresponding to the area to be predicted. The server receives a first infection prediction request associated with the area to be predicted and the target infectious disease, where the first infection prediction request is used to instruct to predict the first cumulative confirmed data associated with the target infectious disease in the area to be predicted at the predicted time. Furthermore, the server can obtain the infection statistics data and the implementation status of the first control measures associated with the target infectious disease at the target time in the area to be predicted, and call the target prediction model to perform data on the statistics data and the implementation status of the first control measures. Analysis, where the target time is determined based on the predicted time. Further, the server determines the first cumulative diagnosis data based on the first data analysis result output by the target prediction model. Through this method, the server obtains a highly accurate prediction model based on the historical infection statistics of the target infectious disease in the predicted reference region and the implementation status of historical control measures, and further based on the historical infection statistics of the target infectious disease in the region to be predicted and The implementation status of historical control measures revises the prediction model to obtain the target prediction model corresponding to the area to be predicted. Furthermore, it provides a data processing method for the epidemic area in the early stage of the epidemic (that is, the epidemic area with fewer training samples). This method improves the accuracy of predicting the confirmed data of the target infectious disease under the prediction time.

Please refer to FIG. 4, which is a schematic structural diagram of a data processing device provided by an embodiment of this application. The data processing device is deployed on a server, and the device includes:

The obtaining module 40 is configured to receive a first infection prediction request associated with the area to be predicted and the target infectious disease, where the first infection prediction request is used to instruct to predict that the area to be predicted is associated with the target infectious disease at the predicted time The first cumulative confirmed data;

The acquisition module 40 is also used to acquire the infection statistics data and the implementation status of the first control measures associated with the target infectious disease at the target time in the area to be predicted, and call the target prediction model to analyze the infection statistics data and Performing data analysis on the implementation status of the first control measure, and the target time is determined based on the predicted time;

The processing module 41 is configured to determine the first cumulative diagnosis data based on the first data analysis result output by the target prediction model;

Wherein, the target prediction model is obtained by revising the prediction model according to the historical infection statistics of the target infectious disease and the implementation status of historical control measures in the area to be predicted. The historical infection statistics of the target infectious disease and the implementation status of historical management and control measures are determined; the occurrence time of the target infectious disease in the predicted reference area is earlier than the occurrence time of the target infectious disease in the area to be predicted.

In one embodiment, before the target prediction model is invoked to analyze the infection statistics and the implementation status of the first management and control measures, the acquisition module 40 is further configured to acquire information about the target infection in the area to be predicted. The historical infection statistics of the disease and the implementation status of historical management and control measures, and to obtain a prediction model determined based on the historical infection statistics of the target infectious disease and the implementation status of the historical management and control measures in the predicted reference area; the processing module 41 is also used for The prediction model is revised according to the historical infection statistics of the target infectious disease and the implementation status of historical management and control measures in the region to be predicted to obtain a target prediction model corresponding to the region to be predicted.

In one embodiment, the acquisition module 40 is specifically configured to acquire historical consultation information about the target infectious disease in the area to be predicted, and the historical consultation information includes historical infection statistical data consultation information and historical control measures implementation status Consulting information; the processing module 41 is specifically configured to call a text recognition algorithm model to obtain historical infection statistics of the target infectious disease in the area to be predicted from the historical infection statistics consulting information; the processing module 41 , Specifically used to call the text recognition algorithm model to obtain the historical control measure implementation status of the target infectious disease in the area to be predicted from the historical control measure implementation status consultation information.

In one embodiment, after the acquisition of historical infection statistics on the target infectious disease and the implementation status of historical management and control measures in the area to be predicted, the processing module 41 is further configured to respond to the target infectious disease according to a preset time sliding window. Preprocess the historical infection statistics and historical control measures of the target infectious disease in the predicted region to obtain at least one sequence data of the target infectious disease in the region to be predicted; At least one piece of sequence data of the target infectious disease modifies the prediction model to obtain the target prediction model corresponding to the region to be predicted.

In one embodiment, the processing module 41 is specifically configured to divide at least one piece of sequence data about the target infectious disease in the area to be predicted into a training sequence data set and a test sequence data set;

Correct the prediction model according to the training sequence data set to obtain the candidate prediction model corresponding to the area to be predicted; verify the candidate prediction model according to the test sequence data set and preset evaluation rules; if the verification passes , It is determined that the candidate prediction model is the target prediction model corresponding to the region to be predicted.

In one embodiment, the preset evaluation rule is an evaluation rule corresponding to a predictive evaluation index, wherein the predictive evaluation index includes: root mean square error, mean square error, average absolute error, and symmetric average absolute percentage error. Any kind.

In one embodiment, after the first cumulative diagnosis data is determined based on the first data analysis result output by the target prediction model, the acquisition module 40 is further configured to receive the data related to the area to be predicted and the A second infection prediction request associated with the target infectious disease, where the second infection prediction request is used to instruct to predict the second cumulative confirmed data associated with the target infectious disease in the area to be predicted at the predicted time; the processing Module 41 is also used to change the implementation state of the first control measure associated with the target infectious disease at the target time in the area to be predicted to the implementation state of the second control measure, and call the target prediction model Perform data analysis on the infection statistics and the implementation status of the second control measures, the target time is determined based on the predicted time; the second data analysis result is determined based on the second data analysis result output by the target prediction model Accumulated confirmed data.

It should be noted that the functions of the unit modules of the data processing device described in the embodiment of the present application can be specifically implemented according to the method in the method embodiment described in FIG. 1 or FIG. 2, and the specific implementation process can refer to FIG. 1 or FIG. The related description of the method embodiment of 2 will not be repeated here.

Based on the description of the foregoing method embodiment and the device item embodiment, an embodiment of the present application also provides a server. Referring to FIG. 5, the server may at least include a processor 501, a communication interface 502, and a memory 503; wherein the processor 501, the communication interface 502, and the memory 503 may be connected through a bus or other connection methods. The memory 503 may also include a computer-readable storage medium, the computer-readable storage medium is used to store a computer program, the computer program includes program instructions, and the processor 501 is configured to execute the program instructions stored in the memory 503 . The processor 501 (or CPU (Central Processing Unit, central processing unit)) is the computing core and control core of the server. It is suitable for implementing one or more instructions, and specifically for loading and executing one or more instructions to achieve the above The corresponding method flow or corresponding function in the data processing method embodiment. Wherein, the processor 501 is configured to call the program instructions to execute: receive a first infection prediction request associated with the area to be predicted and the target infectious disease through the communication interface 502, and the first infection prediction request is used to instruct to predict the to be predicted The first cumulative diagnosis data associated with the target infectious disease in the region at the predicted time; obtain the infection statistics data associated with the target infectious disease in the region to be predicted at the target time and the implementation status of the first control measures, and call The target prediction model performs data analysis on the infection statistics and the implementation status of the first management and control measures. The target time is determined based on the predicted time; the target time is determined based on the first data analysis result output by the target prediction model. The first cumulative diagnosis data; wherein, the target prediction model is obtained by revising the prediction model according to the historical infection statistics of the target infectious disease and the implementation status of historical control measures in the area to be predicted, the prediction model It is determined based on the historical infection statistics of the target infectious disease in the predicted reference area and the implementation status of historical control measures; the occurrence time of the target infectious disease in the predicted reference area is earlier than the target infectious disease in the to-be-predicted area. When the infectious disease occurred. In specific implementation, the processor 501, the communication interface 502, and the memory 503 described in the embodiment of the present application can execute the implementation described in the method embodiment described in FIG. 1 or FIG. The implementation method of the data processing device described in FIG. 4 in the embodiment of the present application will not be repeated here.

In one embodiment, before the target prediction model is invoked to analyze the infection statistics and the implementation status of the first control measures, the processor 501 is further configured to obtain information about the target infection in the area to be predicted. The historical infection statistics of the disease and the implementation status of historical control measures, and the prediction model determined based on the historical infection statistics of the target infectious disease and the implementation status of the historical control measures in the predicted reference area; The historical infection statistics of the target infectious disease and the implementation status of historical management and control measures modify the prediction model to obtain the target prediction model corresponding to the region to be predicted. In specific implementation, the specific implementation manner of the processor 501 described in the embodiment of the present application can perform the related implementation manner described in step S201 of the foregoing embodiment, and details are not described herein again.

In an implementation, the processor 501 is specifically configured to obtain historical consultation information about the target infectious disease in the area to be predicted, and the historical consultation information includes consultation information on historical infection statistical data and consultation on the implementation status of historical management and control measures. Information; call the text recognition algorithm model to obtain the historical infection statistics of the target infectious disease in the area to be predicted from the historical infection statistical data consultation information; call the text recognition algorithm model from the historical control measures implementation status Obtain the implementation status of historical control measures for the target infectious disease in the region to be predicted from the consultation information. In specific implementation, the specific implementation manner of the processor 501 described in the embodiment of the present application can perform the related implementation manner described in step S201 of the foregoing embodiment, and details are not described herein again.

In one embodiment, after the acquisition of historical infection statistics on the target infectious disease and the implementation status of historical management and control measures in the area to be predicted, the processor 501 is further configured to compare the to-be-predicted area according to a sliding window of a preset time. The area’s historical infection statistics on the target infectious disease and the implementation status of historical control measures are preprocessed to obtain at least one piece of sequence data about the target infectious disease in the area to be predicted; At least one piece of serial data of infectious diseases is modified to the prediction model to obtain the target prediction model corresponding to the region to be predicted. In the specific implementation, the specific implementation manner of the processor 501 described in the embodiment of the present application can perform the related implementation manner described in step S202 of the foregoing embodiment, and details are not described herein again.

In one embodiment, the processor 501 is specifically configured to divide at least one piece of sequence data about the target infectious disease in the area to be predicted into a training sequence data set and a test sequence data set; according to the training sequence The data set modifies the prediction model to obtain the candidate prediction model corresponding to the area to be predicted; verifies the candidate prediction model according to the test sequence data set and preset evaluation rules; if the verification passes, the candidate prediction model is determined The candidate prediction model is a target prediction model corresponding to the region to be predicted. In the specific implementation, the specific implementation manner of the processor 501 described in the embodiment of the present application can perform the related implementation manner described in step S202 of the foregoing embodiment, and details are not described herein again.

In one embodiment, the preset evaluation rule is an evaluation rule corresponding to a predictive evaluation index, wherein the predictive evaluation index includes: root mean square error, mean square error, average absolute error, and symmetric average absolute percentage error. Any kind. In specific implementation, the specific implementation described in the embodiment of the present application can implement the related implementation described in step S202 of the foregoing embodiment, and details are not described herein again.

In one embodiment, after the first cumulative diagnosis data is determined based on the first data analysis result output by the target prediction model, the processor 501 is further configured to receive data related to the area to be predicted and the A second infection prediction request associated with the target infectious disease, where the second infection prediction request is used to instruct to predict the second cumulative diagnosis data associated with the target infectious disease in the area to be predicted at the predicted time; The implementation status of the first control measure associated with the target infectious disease in the area to be predicted is changed to the implementation status of the second control measure at the target time, and the target prediction model is called to analyze the infection statistics and the infection statistics. Data analysis is performed on the implementation status of the second control measure, the target time is determined based on the predicted time; the second cumulative diagnosis data is determined based on the second data analysis result output by the target prediction model. In the specific implementation, the specific implementation manner of the processor 501 described in the embodiment of the present application can perform the related implementation manner described in step S205 of the foregoing embodiment, and details are not described herein again.

It should be understood that in the embodiments of the present application, the processor 501 may be a central processing unit (Central Processing Unit, CPU), and the processor 501 may also be other general-purpose processors or digital signal processors (Digital Signal Processors, DSPs). ), Application Specific Integrated Circuit (ASIC), off-the-shelf programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete a hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor or the like.

The memory 503 may include a read-only memory and a random access memory, and provides instructions and data to the processor 501. A part of the memory 503 may also include a non-volatile random access memory. For example, the memory 503 may also store device type information.

In another embodiment of the present application, a computer storage medium such as a computer-readable storage medium is provided, the computer-readable storage medium stores a computer program, the computer program includes program instructions, and the program instructions are executed by a processor The method described in FIG. 1 or FIG. 2 provided in the embodiment of the present application is implemented in the described implementation manner.

Optionally, the storage medium involved in this application, such as a computer-readable storage medium, may be non-volatile or volatile.

The computer-readable storage medium may be the internal storage unit of the server described in any of the foregoing embodiments, such as the hard disk or memory of the server. The computer-readable storage medium may also be an external storage device of the server, such as a plug-in hard disk equipped on the server, a smart memory card (SMC), or a secure digital (SD) card. , Flash Card, etc. Further, the computer-readable storage medium may also include both an internal storage unit of the server and an external storage device. The computer-readable storage medium is used to store the computer program and other programs and data required by the server. The computer-readable storage medium can also be used to temporarily store data that has been output or will be output.

A person of ordinary skill in the art can understand that all or part of the processes in the methods of the above-mentioned embodiments can be implemented by instructing relevant hardware through a computer program. The program can be stored in a computer readable and readable storage medium. When the program is executed, it may include the processes of the above-mentioned method embodiments.

Wherein, the readable storage medium may be a magnetic disk, an optical disk, a read-only memory (Read-Only Memory, ROM), or a random access memory (Random Access Memory, RAM), etc. The computer-readable storage medium may mainly include a storage program area and a storage data area, where the storage program area may store an operating system, an application program required by at least one function, etc.; the storage data area may store information based on the blockchain node Use the created data, etc.

Among them, the blockchain referred to in this application is a new application mode of computer technology such as distributed data storage, point-to-point transmission, consensus mechanism, and encryption algorithm. Blockchain, essentially a decentralized database, is a series of data blocks associated with cryptographic methods. Each data block contains a batch of network transaction information for verification. The validity of the information (anti-counterfeiting) and the generation of the next block. The blockchain can include the underlying platform of the blockchain, the platform product service layer, and the application service layer.

The above-disclosed are only part of the embodiments of the application. Of course, it cannot be used to limit the scope of rights of the application. Those of ordinary skill in the art can understand all or part of the process of implementing the above-mentioned embodiments and follow the claims of this application. The equivalent changes made are still within the scope of this application.

Claims (20)

1. A server, the server includes a communication interface, a processor, and a memory, wherein:

   The memory is used to store a computer program, and the computer program includes program instructions;

   The processor is configured to call the program instructions for receiving, through the communication interface, a first infection prediction request associated with the area to be predicted and the target infectious disease, and the first infection prediction request is used to instruct to predict the Predict the first cumulative diagnosis data associated with the target infectious disease at the predicted time in the predicted area; obtain the infection statistics data associated with the target infectious disease at the target time in the to-be-predicted area and the implementation status of the first control measures, and Calling a target prediction model to perform data analysis on the infection statistics and the implementation status of the first control measures, the target time is determined based on the predicted time; determined based on the first data analysis result output by the target prediction model The first cumulative diagnosis data;

   Wherein, the target prediction model is obtained by revising the prediction model according to the historical infection statistics of the target infectious disease and the implementation status of historical control measures in the area to be predicted. The historical infection statistics of the target infectious disease and the implementation status of historical management and control measures are determined; the occurrence time of the target infectious disease in the predicted reference area is earlier than the occurrence time of the target infectious disease in the area to be predicted.
2. 4. The server according to claim 1, wherein the processor is configured to call a target prediction model to perform data analysis on the infection statistics and the implementation status of the first control measure, the processor is further configured to:

   Obtain historical infection statistics and historical control measures implementation status of the target infectious disease in the area to be predicted, and obtain a prediction model determined based on the historical infection statistics and historical control measures implementation status of the target infectious disease in the predicted reference area;

   The prediction model is revised according to the historical infection statistics of the target infectious disease and the implementation status of historical management and control measures in the region to be predicted to obtain a target prediction model corresponding to the region to be predicted.
3. The server according to claim 2, wherein the processor is specifically configured to:

   Acquiring historical consulting information about the target infectious disease in the region to be predicted, where the historical consulting information includes historical infection statistical data consulting information and historical management and control measures implementation status consulting information;

   Calling a text recognition algorithm model to obtain historical infection statistics of the target infectious disease in the region to be predicted from the historical infection statistics consulting information;

   The text recognition algorithm model is invoked to obtain the historical control measure implementation status of the target infectious disease in the region to be predicted from the historical control measure implementation status consultation information.
4. The server according to claim 2, wherein after the processor is configured to obtain historical infection statistics and historical control measures implementation status of the target infectious disease in the area to be predicted, the processor is further configured to:

   Preprocess the historical infection statistics and historical control measures implementation status of the target infectious disease in the area to be predicted according to a preset sliding window to obtain at least one piece of sequence data about the target infectious disease in the area to be predicted ；

   Correcting the prediction model according to at least one sequence data of the target infectious disease in the region to be predicted to obtain a target prediction model corresponding to the region to be predicted.
5. The server according to claim 4, wherein the processor is specifically configured to:

   Dividing at least one piece of sequence data about the target infectious disease in the area to be predicted into a training sequence data set and a test sequence data set;

   Correcting the prediction model according to the training sequence data set to obtain a candidate prediction model corresponding to the region to be predicted;

   Verifying the candidate prediction model according to the test sequence data set and preset evaluation rules;

   If the verification is passed, it is determined that the candidate prediction model is the target prediction model corresponding to the region to be predicted.
6. The server according to claim 5, wherein the preset evaluation rule is an evaluation rule corresponding to a predictive evaluation index, wherein the predictive evaluation index includes: root mean square error, mean square error, mean absolute error, and symmetric mean absolute Any of the percentage errors.
7. The server according to any one of claims 1 to 6, wherein the processor is configured to determine the first cumulative diagnosis data based on the first data analysis result output by the target prediction model, the processor further uses At:

   Receive a second infection prediction request associated with the area to be predicted and the target infectious disease, where the second infection prediction request is used to instruct to predict that the area to be predicted is associated with the target infectious disease at the predicted time The second cumulative diagnosis data;

   Change the implementation state of the first control measure associated with the target infectious disease at the target time in the area to be predicted to the implementation state of the second control measure, and call the target prediction model to analyze the infection statistics Perform data analysis with the implementation status of the second control measure, and the target time is determined based on the predicted time;

   The second cumulative diagnosis data is determined based on the second data analysis result output by the target prediction model.
8. A data processing method, the data processing method is executed by a server, and the data processing method includes:

   Receive a first infection prediction request associated with the area to be predicted and the target infectious disease, where the first infection prediction request is used to instruct to predict the first cumulative confirmed data associated with the target infectious disease in the area to be predicted at the predicted time ；

   Acquire the infection statistics data and the implementation status of the first control measures associated with the target infectious disease at the target time in the region to be predicted, and call the target prediction model to perform the statistics on the infection statistics and the implementation status of the first control measures Data analysis, the target time is determined based on the predicted time;

   Determining the first cumulative diagnosis data based on the first data analysis result output by the target prediction model;

   Wherein, the target prediction model is obtained by revising the prediction model according to the historical infection statistics of the target infectious disease and the implementation status of historical control measures in the area to be predicted. The historical infection statistics of the target infectious disease and the implementation status of historical management and control measures are determined; the occurrence time of the target infectious disease in the predicted reference area is earlier than the occurrence time of the target infectious disease in the area to be predicted.
9. The method according to claim 8, wherein before the processor is configured to invoke a target prediction model to perform data analysis on the infection statistics and the implementation status of the first management and control measure, the method further comprises:

   Obtain historical infection statistics and historical control measures implementation status of the target infectious disease in the area to be predicted, and obtain a prediction model determined based on the historical infection statistics and historical control measures implementation status of the target infectious disease in the predicted reference area;

   The prediction model is revised according to the historical infection statistics of the target infectious disease and the implementation status of historical management and control measures in the region to be predicted to obtain a target prediction model corresponding to the region to be predicted.
10. The method according to claim 9, wherein the method further comprises:

    Acquiring historical consulting information about the target infectious disease in the region to be predicted, where the historical consulting information includes historical infection statistical data consulting information and historical management and control measures implementation status consulting information;

    Calling a text recognition algorithm model to obtain historical infection statistics of the target infectious disease in the region to be predicted from the historical infection statistics consulting information;

    The text recognition algorithm model is invoked to obtain the historical control measure implementation status of the target infectious disease in the region to be predicted from the historical control measure implementation status consultation information.
11. The method according to claim 9, wherein after said obtaining historical infection statistics and historical control measures implementation status of the target infectious disease in the area to be predicted, the method further comprises:

    Preprocess the historical infection statistics and historical control measures implementation status of the target infectious disease in the area to be predicted according to a preset sliding window to obtain at least one piece of sequence data about the target infectious disease in the area to be predicted ；

    Correcting the prediction model according to at least one sequence data of the target infectious disease in the region to be predicted to obtain a target prediction model corresponding to the region to be predicted.
12. 11. The method according to claim 11, wherein said correcting said prediction model according to at least one piece of sequence data of said target infectious disease in said region to be predicted to obtain a target prediction model corresponding to said region to be predicted, include:

    Dividing at least one piece of sequence data about the target infectious disease in the area to be predicted into a training sequence data set and a test sequence data set;

    Correcting the prediction model according to the training sequence data set to obtain a candidate prediction model corresponding to the region to be predicted;

    Verifying the candidate prediction model according to the test sequence data set and preset evaluation rules;

    If the verification is passed, it is determined that the candidate prediction model is the target prediction model corresponding to the region to be predicted.
13. The method according to any one of claims 8-12, wherein, after the first cumulative diagnosis data is determined based on the first data analysis result output by the target prediction model, the method further comprises:

    Receive a second infection prediction request associated with the area to be predicted and the target infectious disease, where the second infection prediction request is used to instruct to predict that the area to be predicted is associated with the target infectious disease at the predicted time The second cumulative diagnosis data;

    Change the implementation state of the first control measure associated with the target infectious disease at the target time in the area to be predicted to the implementation state of the second control measure, and call the target prediction model to analyze the infection statistics Perform data analysis with the implementation status of the second control measure, and the target time is determined based on the predicted time;

    The second cumulative diagnosis data is determined based on the second data analysis result output by the target prediction model.
14. A data processing device, the data processing device is deployed on a server, and the data processing device includes:

    The acquisition module is configured to receive a first infection prediction request associated with the area to be predicted and the target infectious disease, where the first infection prediction request is used to instruct to predict the area to be predicted that is associated with the target infectious disease at the predicted time The first cumulative confirmed data;

    The acquisition module is also used to acquire the infection statistics data associated with the target infectious disease at the target time in the area to be predicted and the implementation status of the first management and control measures, and call the target prediction model to analyze the infection statistics and the infection statistics. Perform data analysis on the implementation status of the first control measure, and the target time is determined based on the predicted time;

    A processing module, configured to determine the first cumulative diagnosis data based on the first data analysis result output by the target prediction model;

    Wherein, the target prediction model is obtained by revising the prediction model according to the historical infection statistics of the target infectious disease and the implementation status of historical control measures in the area to be predicted. The historical infection statistics of the target infectious disease and the implementation status of historical management and control measures are determined; the occurrence time of the target infectious disease in the predicted reference area is earlier than the occurrence time of the target infectious disease in the area to be predicted.
15. A computer-readable storage medium in which program instructions are stored, and when the program instructions are executed, they are used to implement the following methods:

    Receive a first infection prediction request associated with the area to be predicted and the target infectious disease, where the first infection prediction request is used to instruct to predict the first cumulative confirmed data associated with the target infectious disease in the area to be predicted at the predicted time ；

    Acquire the infection statistics data and the implementation status of the first control measures associated with the target infectious disease at the target time in the region to be predicted, and call the target prediction model to perform the statistics on the infection statistics and the implementation status of the first control measures Data analysis, the target time is determined based on the predicted time;

    Determining the first cumulative diagnosis data based on the first data analysis result output by the target prediction model;

    Wherein, the target prediction model is obtained by revising the prediction model according to the historical infection statistics of the target infectious disease and the implementation status of historical control measures in the area to be predicted. The historical infection statistics of the target infectious disease and the implementation status of historical management and control measures are determined; the occurrence time of the target infectious disease in the predicted reference area is earlier than the occurrence time of the target infectious disease in the area to be predicted.
16. The computer-readable storage medium according to claim 15, wherein the processor is configured to invoke a target prediction model to perform data analysis on the infection statistics and the implementation status of the first control measure before the program instructions are executed Time is also used to achieve:

    Obtain historical infection statistics and historical control measures implementation status of the target infectious disease in the area to be predicted, and obtain a prediction model determined based on the historical infection statistics and historical control measures implementation status of the target infectious disease in the predicted reference area;

    The prediction model is revised according to the historical infection statistics of the target infectious disease and the implementation status of historical management and control measures in the region to be predicted to obtain a target prediction model corresponding to the region to be predicted.
17. The computer-readable storage medium according to claim 16, wherein the program instructions are also used to implement:

    Acquiring historical consulting information about the target infectious disease in the region to be predicted, where the historical consulting information includes historical infection statistical data consulting information and historical management and control measures implementation status consulting information;

    Calling a text recognition algorithm model to obtain historical infection statistics of the target infectious disease in the region to be predicted from the historical infection statistics consulting information;

    The text recognition algorithm model is invoked to obtain the historical control measure implementation status of the target infectious disease in the region to be predicted from the historical control measure implementation status consultation information.
18. The computer-readable storage medium according to claim 16, wherein after the acquisition of historical infection statistics and historical control measures implementation status of the target infectious disease in the area to be predicted, the program instructions are also used when executed accomplish:

    Preprocess the historical infection statistics and historical control measures implementation status of the target infectious disease in the area to be predicted according to a preset sliding window to obtain at least one piece of sequence data about the target infectious disease in the area to be predicted ；

    Correcting the prediction model according to at least one sequence data of the target infectious disease in the region to be predicted to obtain a target prediction model corresponding to the region to be predicted.
19. The computer-readable storage medium according to claim 18, wherein the execution of the correction of the prediction model based on at least one piece of sequence data related to the target infectious disease in the area to be predicted is executed to obtain the area corresponding to the area to be predicted The target prediction model includes:

    Dividing at least one piece of sequence data about the target infectious disease in the area to be predicted into a training sequence data set and a test sequence data set;

    Correcting the prediction model according to the training sequence data set to obtain a candidate prediction model corresponding to the region to be predicted;

    Verifying the candidate prediction model according to the test sequence data set and preset evaluation rules;

    If the verification is passed, it is determined that the candidate prediction model is the target prediction model corresponding to the region to be predicted.
20. The computer-readable storage medium according to any one of claims 15-19, wherein, after the first cumulative diagnosis data is determined based on the first data analysis result output by the target prediction model, the program instructions are It is also used to achieve:

    Receive a second infection prediction request associated with the area to be predicted and the target infectious disease, where the second infection prediction request is used to instruct to predict that the area to be predicted is associated with the target infectious disease at the predicted time The second cumulative diagnosis data;

    Change the implementation state of the first control measure associated with the target infectious disease at the target time in the area to be predicted to the implementation state of the second control measure, and call the target prediction model to analyze the infection statistics Perform data analysis with the implementation status of the second control measure, and the target time is determined based on the predicted time;

    The second cumulative diagnosis data is determined based on the second data analysis result output by the target prediction model.

Images