Infectious disease monitoring method, device, equipment and readable medium based on fusion computing

Abstract

The present application discloses an infectious disease monitoring method, apparatus, device and readable medium based on fusion computing, the method comprising: the method comprising: obtaining time series data of medical consultations for a specified infectious disease within a specified range; extracting data from the time series data of medical consultations according to syndrome information corresponding to the specified infectious disease to determine the corresponding syndrome time series data; predicting the syndrome time series data through a time series model to determine the infectious disease prediction result; analyzing the syndrome time series data according to a control chart algorithm to determine the infectious disease analysis result; integrating the infectious disease prediction result and the infectious disease analysis result to determine the infectious disease warning result corresponding to the specified infectious disease.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to an infectious disease monitoring method, device, equipment and readable medium based on fusion computing. Background Art

[0002] Infectious diseases are important diseases that endanger human health. When infectious diseases occur, they usually show the characteristics of a syndrome, which is also called a syndrome. It is used to refer to the occurrence of one symptom in various pathological processes, accompanied by several other symptoms. This group of symptoms is very stereotyped and can be observed in a unified way, that is, the various symptoms of the syndrome can be regarded as caused by one basic cause, namely, infectious diseases.

[0003] By supplementing traditional disease monitoring with syndromic monitoring, we can continuously collect and analyze relevant epidemic information and signals of epidemics and syndromes hidden in clinical data, understand the epidemic characteristics and mutation patterns of syndromic pathogen spectra of infectious diseases, and use the monitoring of specific syndromes to conduct early warning detection of infectious disease outbreaks, which can effectively improve the ability to discover and diagnose new and emerging infectious diseases.

[0004] Usually, when there is no outbreak of infectious diseases, the prevalence level of syndromes generally fluctuates within a certain range. When the fluctuation exceeds the expected level and state for a certain period of time, it indicates a possible outbreak of infectious diseases. However, there are many factors affecting the fluctuation of syndrome data, resulting in low early warning accuracy of syndrome monitoring algorithms. Summary of the invention

[0005] In order to solve the above-mentioned problems existing in the background technology, the embodiments of the present application creatively provide an infectious disease monitoring method, device, equipment and readable medium based on fusion computing.

[0006] According to the first aspect of an embodiment of the present application, a method for early warning of an infectious disease based on fusion calculation is provided, the method comprising: obtaining time series data of medical consultations for a specified infectious disease within a specified range; extracting data from the time series data of medical consultations according to syndrome information corresponding to the specified infectious disease, and determining corresponding syndrome time series data; predicting the syndrome time series data through a time series model, and determining an infectious disease prediction result; analyzing the syndrome time series data according to a control chart algorithm, and determining an infectious disease analysis result; integrating the infectious disease prediction result and the infectious disease analysis result, and determining an infectious disease early warning result corresponding to the specified infectious disease.

[0007] According to one embodiment of the present application, the data is extracted from the time series data of medical consultations according to the syndrome information corresponding to the designated infectious disease to determine the corresponding syndrome time series data, including: extracting data from the time series data of medical consultations according to the syndrome information of the designated infectious disease to obtain the original syndrome data corresponding to the designated infectious disease; performing weighted smoothing processing on the syndrome data according to the time information corresponding to the original syndrome data to obtain the syndrome time series data.

[0008] According to one embodiment of the present application, predicting the syndrome time series data through a time series model to determine the infectious disease prediction result includes: predicting the syndrome time series data through a time series model to obtain model prediction data; accumulating residuals between actual observation data and the model prediction data to obtain residual accumulation data; determining the infectious disease prediction result by comparing the residual accumulation data with a specified residual threshold; wherein the infectious disease prediction result is a negative warning or a positive warning corresponding to the specified infectious disease.

[0009] According to one embodiment of the present application, the residual cumulative data is compared with a specified residual threshold to determine the infectious disease prediction result, including: if the residual cumulative data exceeds the specified residual threshold, determining that the infectious disease prediction result is a positive warning; if the residual cumulative data does not exceed the specified residual threshold, determining that the infectious disease prediction result is a negative warning.

[0010] According to one embodiment of the present application, the method also includes: determining a preset residual threshold based on residual data corresponding to the syndrome time series data; adjusting the preset residual threshold according to the infectious disease prediction results and the actual results of the infectious disease to obtain the specified residual threshold.

[0011] According to one embodiment of the present application, the preset residual threshold is adjusted according to the infectious disease prediction result and the actual result of the infectious disease to obtain the designated residual threshold, including: judging the infectious disease prediction result based on the actual result of the infectious disease to obtain a first judgment result; if the first judgment result is that the infectious disease prediction result of the current round is a warning false positive, the designated residual threshold of the current round and the residual accumulated data of the current round are integrated to determine the designated residual threshold of the next round; if the first judgment result is that the infectious disease prediction result of the current round is a warning false negative, the residual accumulated data of the current round is determined as the designated residual threshold of the next round.

[0012] According to one embodiment of the present application, the syndrome time series data is analyzed according to a control chart algorithm to determine the infectious disease analysis result, including: analyzing the syndrome time series data according to a control chart algorithm to determine the infectious disease analysis data; if the infectious disease analysis data exceeds a specified analysis threshold, determining that the infectious disease analysis result is a warning positive; if the infectious disease analysis data does not exceed the specified analysis threshold, determining that the infectious disease analysis result is a warning negative.

[0013] According to one embodiment of the present application, the method also includes: determining a preset analysis threshold based on historical analysis data corresponding to the syndrome time series data; the preset analysis threshold is a first-round designated analysis threshold; judging the infectious disease analysis result based on the actual result of the infectious disease to obtain a second judgment result; if the second judgment result is that the infectious disease analysis result of the current round is a warning false positive, integrating the infectious disease analysis data of the current round and the designated analysis threshold of the current round to determine the designated analysis threshold of the next round; if the second judgment result is that the infectious disease analysis result of the current round is a warning false negative, determining the infectious disease analysis data of the current round as the designated analysis threshold of the next round.

[0014] According to one embodiment of the present application, the syndrome time series data is analyzed according to a control chart algorithm to determine the infectious disease analysis result, including: determining a characteristic control chart corresponding to the syndrome time series data, analyzing the characteristic control chart, and determining a first analysis result; determining historical characteristic data corresponding to the syndrome time series data, and determining a second analysis result based on the syndrome time series data and the historical characteristic data; determining the infectious disease warning result based on the infectious disease prediction result, the first analysis result, and the second analysis result.

[0015] According to one embodiment of the present application, determining the second analysis result based on the syndrome time series data and the historical characteristic data includes: determining a moving percentile method early warning model based on the syndrome time series data and the historical characteristic data; determining the second analysis result based on the moving percentile method early warning model.

[0016] According to one embodiment of the present application, the integration of the infectious disease prediction results and the infectious disease analysis results to determine the infectious disease warning results corresponding to the designated infectious disease includes: voting on the infectious disease warning results based on the infectious disease prediction results and the infectious disease analysis results to determine the infectious disease warning results, wherein the infectious disease warning result is one of a positive warning or a negative warning.

[0017] According to the second aspect of the embodiment of the present application, an infectious disease warning device based on fusion computing is also provided, and the device includes: an acquisition module, which is used to acquire the time series data of medical consultations for a specified infectious disease within a specified range; an extraction module, which is used to extract data from the time series data of medical consultations according to the syndrome information corresponding to the specified infectious disease, and determine the corresponding syndrome time series data; a prediction module, which is used to predict the syndrome time series data through a time series model, and determine the infectious disease prediction result; an analysis module, which is used to analyze the syndrome time series data according to a control chart algorithm, and determine the infectious disease analysis result; an integration module, which is used to integrate the infectious disease prediction result and the infectious disease analysis result, and determine the infectious disease warning result corresponding to the specified infectious disease.

[0018] According to one embodiment of the present application, the extraction module includes: an extraction submodule, which is used to extract data from the medical consultation time series data according to the syndrome information of the specified infectious disease, and obtain the original syndrome data corresponding to the specified infectious disease; a smoothing submodule, which is used to perform weighted smoothing processing on the syndrome data according to the time information corresponding to the original syndrome data, and obtain the syndrome time series data.

[0019] According to one embodiment of the present application, the prediction module includes: a prediction submodule, which is used to predict the syndrome time series data through a time series model to obtain model prediction data; a residual accumulation submodule, which is used to accumulate residuals based on actual observation data and the model prediction data to obtain residual accumulation data; a comparison submodule, which is used to compare the residual accumulation data with a specified residual threshold to determine the infectious disease prediction result; wherein the infectious disease prediction result is a negative warning or a positive warning corresponding to the specified infectious disease.

[0020] According to one embodiment of the present application, the comparison submodule includes: if the cumulative residual data exceeds the specified residual threshold, determining that the infectious disease prediction result is a positive warning; if the cumulative residual data does not exceed the specified residual threshold, determining that the infectious disease prediction result is a negative warning.

[0021] According to one embodiment of the present application, the determination module is also used to determine a preset residual threshold based on the residual data corresponding to the syndrome time series data; the device also includes: an adjustment module, used to adjust the preset residual threshold according to the infectious disease prediction results and the actual results of the infectious disease to obtain the specified residual threshold.

[0022] According to one embodiment of the present application, the adjustment module includes: judging the infectious disease prediction result based on the actual result of the infectious disease to obtain a first judgment result; if the first judgment result is that the infectious disease prediction result of the current round is a warning false positive, integrating the specified residual threshold of the current round and the residual cumulative data of the current round to determine the specified residual threshold of the next round; if the first judgment result is that the infectious disease prediction result of the current round is a warning false negative, determining the residual cumulative data of the current round as the specified residual threshold of the next round.

[0023] According to one embodiment of the present application, the analysis module includes: analyzing the syndrome time series data according to a control chart algorithm to determine the infectious disease analysis data; if the infectious disease analysis data exceeds a specified analysis threshold, determining the infectious disease analysis result as a warning positive; if the infectious disease analysis data does not exceed the specified analysis threshold, determining the infectious disease analysis result as a warning negative.

[0024] According to one embodiment of the present application, the determination module is also used to determine a preset analysis threshold based on historical analysis data corresponding to the syndrome time series data; the preset analysis threshold is the first round designated analysis threshold; the adjustment module also includes: judging the infectious disease analysis result based on the actual result of the infectious disease to obtain a second judgment result; if the second judgment result is that the infectious disease analysis result of the current round is a warning false positive, the infectious disease analysis data of the current round and the designated analysis threshold of the current round are integrated to determine the designated analysis threshold for the next round; if the second judgment result is that the infectious disease analysis result of the current round is a warning false negative, the infectious disease analysis data of the current round is determined as the designated analysis threshold for the next round.

[0025] According to one embodiment of the present application, the analysis module includes: determining a characteristic control chart corresponding to the syndrome time series data, analyzing the characteristic control chart, and determining a first analysis result; determining historical characteristic data corresponding to the syndrome time series data, and determining a second analysis result based on the syndrome time series data and the historical characteristic data; the integration module is used to determine the infectious disease warning result based on the infectious disease prediction result, the first analysis result and the second analysis result.

[0026] According to one embodiment of the present application, the analysis module includes: determining a moving percentile method early warning model based on the syndrome time series data and the historical characteristic data; and determining a second analysis result based on the moving percentile method early warning model.

[0027] According to one embodiment of the present application, the integration module includes: voting on the infectious disease warning results based on the infectious disease prediction results and the infectious disease analysis results to determine the infectious disease warning results, and the infectious disease warning results are one of a positive warning or a negative warning.

[0028] According to the third aspect of the embodiments of the present application, an electronic device is provided, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, a method as described in any one of the above-mentioned possible implementation modes is implemented.

[0029] According to a fourth aspect of the embodiments of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the program is executed by a processor, a method as described in any one of the above-mentioned possible implementation modes is implemented.

[0030] The infectious disease early warning method, device, equipment and storage medium based on fusion calculation provided in the embodiments of the present application determine the syndrome time series data through the time series data of medical visits, predict the syndrome time series data through the time series model to determine the infectious disease prediction result, and analyze the syndrome time series data through the control chart algorithm to determine the infectious disease analysis result. This method combines multiple algorithms, integrates the infectious disease prediction results and the infectious disease analysis results, determines the infectious disease early warning results corresponding to the specified infectious disease, realizes the fusion early warning of infectious diseases, and improves the accuracy of infectious disease monitoring and early warning.

[0031] It should be understood that the teachings of the present application are not required to achieve all of the beneficial effects described above, but specific technical solutions can achieve specific technical effects, and other embodiments of the present application can also achieve beneficial effects not mentioned above. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] By reading the detailed description below with reference to the accompanying drawings, the above and other purposes, features and advantages of the exemplary embodiments of the present application will become readily understood. In the accompanying drawings, several embodiments of the present application are shown in an exemplary and non-limiting manner, wherein:

[0033] In the drawings, the same or corresponding reference numerals represent the same or corresponding parts.

[0034] Figure 1 A schematic diagram of the implementation process of an infectious disease early warning method based on fusion computing in an embodiment of the present application is shown;

[0035] Figure 2 A schematic diagram of an implementation scenario of an infectious disease early warning method based on fusion computing in an embodiment of the present application is shown;

[0036] Figure 3A time series schematic diagram of an infectious disease early warning method based on fusion computing in an embodiment of the present application is shown;

[0037] Figure 4 A differential sequence schematic diagram of an infectious disease early warning method based on fusion calculation in an embodiment of the present application is shown;

[0038] Figure 5 A schematic diagram of an implementation module of an infectious disease early warning device based on fusion computing according to an embodiment of the present application is shown;

[0039] Figure 6 A schematic diagram of the implementation structure of an electronic device according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0040] The principles and spirit of the present application will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are provided only to enable those skilled in the art to better understand and implement the present application, and are not intended to limit the scope of the present application in any way. On the contrary, these embodiments are provided to make the present application more thorough and complete, and to fully convey the scope of the present application to those skilled in the art.

[0041] The technical solution of the present application is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0042] Figure 1 A schematic diagram of the implementation process of an infectious disease early warning method based on fusion computing in an embodiment of the present application is shown. Figure 2 A schematic diagram of an implementation scenario of an infectious disease early warning method based on fusion computing in an embodiment of the present application is shown.

[0043] See also Figure 1 and Figure 2 According to the first aspect of the embodiment of the present application, a method for early warning of infectious diseases based on fusion computing is provided, and the method includes: operation 101, obtaining time series data of medical consultations for a specified infectious disease within a specified range; operation 102, extracting data from the time series data of medical consultations according to the syndrome information corresponding to the specified infectious disease, and determining the corresponding syndrome time series data; operation 103, predicting the syndrome time series data through a time series model, and determining the infectious disease prediction result; operation 104, analyzing the syndrome time series data according to a control chart algorithm, and determining the infectious disease analysis result; operation 105, integrating the infectious disease prediction result and the infectious disease analysis result, and determining the infectious disease early warning result corresponding to the specified infectious disease.

[0044] The infectious disease early warning method based on fusion calculation provided in the embodiment of the present application determines the syndrome time series data through the time series data of medical visits, predicts the syndrome time series data through the time series model to determine the infectious disease prediction result, and analyzes the syndrome time series data through the control chart algorithm to determine the infectious disease analysis result. This method combines multiple algorithms, integrates the infectious disease prediction results and the infectious disease analysis results, determines the infectious disease early warning results corresponding to the specified infectious disease, realizes the fusion early warning of infectious diseases, and improves the accuracy of infectious disease monitoring and early warning.

[0045] In operation 101 and operation 102 of the present method, the time series data of medical consultation in the specified range is the time series data of medical consultation in the specific area range and the specific time range. According to the actual situation, the specific area range can be a certain country, a certain province or city, a certain street, a certain hospital, a certain clinic, etc. The specific time range can be a week, a half month, a month, a quarter, etc. Among them, the time series data of medical consultation can be the electronic medical record information of a certain hospital. By screening the electronic medical record information with the syndrome information corresponding to the specified infectious disease, the electronic medical record information with the syndrome information corresponding to the specified infectious disease can be obtained, and then the syndrome time series data can be determined by the electronic medical record information with the syndrome information corresponding to the specified infectious disease. For example, by counting the electronic medical record information of the fever clinic of a certain hospital every day, the number of patients visiting the fever clinic every day can be determined; by analyzing the electronic medical record information of all hospitals in a certain city, the number of patients visiting the city with cough symptoms and the number of patients visiting the city with diarrhea symptoms can be determined. The specific syndrome time series data is determined according to the syndrome corresponding to the designated infectious disease that needs to be warned. For example, if the syndrome of the designated infectious disease that needs to be warned is related to fever, the syndrome time series data related to fever is counted. It is understandable that if the designated infectious disease that needs to be warned has multiple symptoms, the characteristic data corresponding to the multiple symptoms can be integrated and analyzed to obtain the iconic combined characteristic data that can correspond to the designated infectious disease, so as to more comprehensively characterize the syndrome time series data corresponding to the designated infectious disease. In this method, the syndrome time series data is specifically the syndrome time series data of each day in a specific area and a specific time interval.

[0046] In operation 103 of the method, the syndrome time series data is predicted by a time series model to determine the infectious disease prediction result. The method can use common time series models for prediction, including but not limited to autoregressive model (AR), moving average model (MA), autoregressive moving average model (ARMA), differential regression moving average model (ARIMA), vector autoregression model (VAR), structural autoregression model (SVAR) and other time series models. In a specific implementation scenario, the method uses the ARIMA model to predict the syndrome time series data to determine the infectious disease prediction result. The infectious disease prediction result is a negative warning or a positive warning corresponding to the specified infectious disease. The negative warning is used to characterize that the specified infectious disease will not break out in a specific area and within a specified time interval. The positive warning is used to characterize that the specified infectious disease will break out in a specific area and within a specified time interval. Among them, the specific area of ​​the warning is the same as the specific area corresponding to the syndrome time series data. The specified time interval may be a week, a month, or a quarter after the specific time interval in which the syndrome time series data is located. The specific specified time interval may be set according to actual conditions.

[0047] It should be added that the infectious disease prediction results of this method may include prediction results obtained by one or more time series models. That is, if this method has multiple time series models to predict the syndrome time series data respectively, the infectious disease prediction results of this method can be multiple; if this method uses one time series model to predict the syndrome time series data, the infectious disease prediction result of this method can be one.

[0048] In operation 104 of the method, the control chart algorithm includes but is not limited to one or more of the cusum control chart algorithm and the moving percentile method. Similarly, the method can use different control chart algorithms to analyze the syndrome time series data respectively to determine multiple infectious disease analysis results; the method can also use only one control chart algorithm to analyze the syndrome time series data to determine one infectious disease analysis result. Similarly, the infectious disease analysis result is a warning negative or a warning positive corresponding to the specified infectious disease.

[0049] In operation 105 of the method, the infectious disease prediction result and the infectious disease analysis result are integrated to determine an infectious disease warning result corresponding to the designated infectious disease.

[0050] Specifically, operation 105 integrates the infectious disease prediction results and the infectious disease analysis results to determine the infectious disease warning results corresponding to the designated infectious disease, including: voting on the infectious disease warning results according to the infectious disease prediction results and the infectious disease analysis results to determine the infectious disease warning results, where the infectious disease warning results are either positive warning or negative warning.

[0051] The infectious disease warning result is a negative warning or a positive warning corresponding to the specified infectious disease. The integration operation of this method can be to integrate the infectious disease prediction results and the infectious disease analysis results by voting to determine the infectious disease warning result. For example, if this method uses two time series models to predict the syndrome time series data, the prediction results of the two models are both negative warnings; this method analyzes the syndrome time series data through three control chart algorithms to obtain three infectious disease analysis results, namely negative warning, positive warning and negative warning. According to the five results, the negative warning has 4 votes and the positive warning has 1 vote. The corresponding infectious disease warning result is negative warning.

[0052] In addition to the voting method, this method can also process the infectious disease prediction results and infectious disease analysis results through one or more of the integration methods such as addition, weighting, multiplication, and subtraction to determine the corresponding infectious disease warning results. For example, when integrating, judgments can be made based on the prior knowledge of different algorithms to set the credibility of different algorithms, and after weighting the results corresponding to different algorithms by credibility, the corresponding infectious disease warning results are determined by voting to avoid tie votes.

[0053] According to one embodiment of the present application, operation 102 extracts data from the time series data of medical consultations according to the syndrome information corresponding to the specified infectious disease to determine the corresponding syndrome time series data, including: first, extracts data from the time series data of medical consultations according to the syndrome information of the specified infectious disease to obtain the original syndrome data corresponding to the specified infectious disease; then, performs weighted smoothing processing on the syndrome data according to the time information corresponding to the original syndrome data to obtain the syndrome time series data.

[0054] In the process of determining the syndrome time series data, this method needs to first extract the data and then perform weighted smoothing on the data to eliminate the data fluctuation noise to a certain extent, further improve the accuracy of the infectious disease prediction results and infectious disease analysis results, and thus ensure the accuracy of the final infectious disease warning results.

[0055] Specifically, the method first counts medical records with designated infectious disease syndromes through electronic medical records, and determines syndrome data corresponding to the infectious disease syndromes of daily visits, such as counting the number of people with fever every day through electronic medical records.

[0056] Taking the number of patients with fever who visit the hospital every day as an example, the data of the number of patients with fever who visit the hospital every day is weighted and smoothed by taking the weighted average of the data of the N days before and after the number of patients with fever who visit the hospital that day to determine the syndrome time series data.

[0057] When N is 3, the specific calculation formula is as follows:

[0058]

[0059] Among them, x′ i Refers to the time series data of the syndrome on day i; x i Refers to the number of patients with fever who visited the hospital on day i; x i-1 、x i-2 、x i-3 , respectively, refer to the number of patients with fever who visited the hospital on the i-1 day, the i-2 day, and the i-3 day; x i+1 、x i+2 、x i+3 , respectively, refer to the number of people with fever who visited the hospital on the i+1 day, the i+2 day, and the i+3 day; 0.25, 0.15, and 0.1 are the corresponding weights, and the denominator 2 is the sum of the weights. It should be added that if the weights are not 2 after integration, the denominator is also not 2. The distribution of weights is determined based on time information. The closer the date is to the i-th day, the greater the corresponding weight. That is, in the above formula, the i-th day has the largest weight, followed by the i-1 day and the i1 day, and so on.

[0060] According to an embodiment of the present application, operation 103 predicts the syndrome time series data through the time series model to determine the infectious disease prediction result, including: first, predicting the syndrome time series data through the time series model to obtain model prediction data; then, accumulating residuals based on the actual observation data and the model prediction data to obtain residual accumulation data; and then, comparing the residual accumulation data with a specified residual threshold to determine the infectious disease prediction result;

[0061] Taking the ARIMA model as an example, this method predicts the syndrome time series data through the ARIMA model. Specifically, this method first constructs the ARIMA (p, d, q) model. Set p as the lag number of the time series data autoregression, d as the order of difference, and q as the lag number of the error weighted average.

[0062] Specifically, this method first determines the corresponding time series through the daily syndrome time series data. The stationarity of the time series is tested by ADF. If the time series is stationary, then d=0 is determined. If the time series is not stationary, the time series is differentiated at least once until the differentiated series passes the ADF test and is a stationary series. Furthermore, the number of differences of the time series is limited to no more than two times. The number of differences is the value of d, that is, if the time series is a stationary series after two differences, then d is 2.

[0063] To facilitate understanding of the above implementation, a smoothing operation scenario is provided below.

[0064] like Figure 3 and Figure 4 As shown, Figure 3 The time series determined according to the daily syndrome time series data is shown, wherein the horizontal axis is time and the vertical axis is the syndrome time series data. Figure 4 Shows the Figure 3 The time series is the difference series after the difference, where the horizontal axis is time and the vertical axis is the differenced data. It can be seen that Figure 4 The difference sequence of Figure 3 The time series is smoother.

[0065] In obtaining Figure 4 Afterwards, the method uses the autocorrelation function (ACF) to determine the parameter value of p and the partial autocorrelation function (PACF) to determine the parameter value of q.

[0066] Among them, the autocorrelation function (ACF) is used to describe the linear correlation between the time series observations and their past observations, that is, it is used to describe the linear correlation between the current time series corresponding to the specified time window of the i-th day and the historical time series in the specified time window before the i-th day. According to the autocorrelation function (ACF), the corresponding ACF graph is determined to determine the parameter value of p through the ACF graph.

[0067] The partial autocorrelation function (PACF) is used to describe the linear correlation between the time series observations and their past observations under the condition of a given intermediate observation value. The intermediate observation value is determined according to the actual situation, and the corresponding PACF graph is determined according to the partial autocorrelation function (PACF) to determine the parameter value of q through the PACF graph.

[0068] After determining the parameters p, d, and q of the ARIMA model, the model is fitted based on the syndrome feature samples corresponding to the syndrome time series data. The fitted ARIMA model is used to predict the daily syndrome time series data to obtain the predicted result sequence data X pt, it can be understood that the result sequence contains the prediction results for each day corresponding to the syndrome time series data of each day. Compared with the sample sequence data X corresponding to the syndrome feature sample t , the residual data u of the sequence is obtained by calculation t .

[0069] The specific calculation formula is as follows:

[0070] u t =X pt -X t

[0071] with u t Based on the data, the residual sum of the 7 days before the ith day is accumulated, and the calculation formula is as follows:

[0072]

[0073] Among them, S i is the residual cumulative data of the i-th day calculated based on the time window. j is u in the time window from 7 days before the i-th day to 1 day before the i-th day t value, is the residual mean in the time window. The lengths of the above time windows are the same and are set according to actual conditions.

[0074] The residual cumulative data obtained from the above calculations are compared with the specified residual threshold to determine the infectious disease prediction results. Among them, the specified residual threshold is a variable threshold. Through the variable threshold, the size of the specified residual threshold can be dynamically adjusted according to the feedback of the monitoring and early warning effect, thereby improving the accuracy of the model prediction and further improving the performance.

[0075] Specifically, the residual cumulative data is compared with the specified residual threshold to determine the infectious disease prediction result, including: if the residual cumulative data exceeds the specified residual threshold, the infectious disease prediction result is determined to be a positive warning; if the residual cumulative data does not exceed the specified residual threshold, the infectious disease prediction result is determined to be a negative warning.

[0076] According to one embodiment of the present application, the method also includes: first, determining a preset residual threshold based on residual data corresponding to the syndrome time series data; then, adjusting the preset residual threshold according to the infectious disease prediction results and the actual results of the infectious disease to obtain a specified residual threshold.

[0077] The preset residual data of this method is the standard deviation of the residual data within the 3-fold time window, that is, the specified residual data of the first round of the model is the preset residual data. It should be supplemented that the preset residual data is set based on certain prior knowledge, and this method can also set the preset residual data to other data based on prior knowledge. After obtaining the corresponding actual results of infectious diseases in each round, it is determined whether the specified residual threshold needs to be adjusted according to whether the predicted results of infectious diseases are consistent with the actual results of infectious diseases. If the predicted results of infectious diseases are consistent with the actual results of infectious diseases, there is no need to adjust the specified residual threshold. If the predicted results of infectious diseases are inconsistent with the actual results of infectious diseases, the specified residual threshold needs to be adjusted. It should be supplemented that the situation where the predicted results of infectious diseases are inconsistent with the actual results of infectious diseases includes predicted false positives and predicted false negatives, where the predicted false positives refer to the predicted results as warning positives, and the actual results are that no infectious disease outbreaks occurred in the time interval corresponding to the predicted results, and the predicted false negatives refer to the predicted results as warning negatives, and the actual results are that an infectious disease outbreak occurred in the time interval corresponding to the predicted results. According to actual needs, the adjustment methods of the specified residual thresholds for predicted false positives and predicted false negatives can be different or the same.

[0078] According to one embodiment of the present application, the preset residual threshold is adjusted according to the infectious disease prediction result and the actual result of the infectious disease to obtain a specified residual threshold, including: first, judging the infectious disease prediction result based on the actual result of the infectious disease to obtain a first judgment result; then, if the first judgment result is that the infectious disease prediction result of the current round is a warning false positive, the specified residual threshold of the current round and the residual cumulative data of the current round are integrated to determine the specified residual threshold of the next round; if the first judgment result is that the infectious disease prediction result of the current round is a warning false negative, the residual cumulative data of the current round is determined as the specified residual threshold of the next round.

[0079] The following provides a specific adjustment method for specifying the residual threshold. The specific adjustment formula is as follows:

[0080]

[0081] Among them, thr new Used to refer to the specified residual threshold for the next round, yhr old Used to refer to the specified residual threshold of the current round, S iUsed to refer to the residual cumulative data of the current round. When a false positive warning occurs in the current round, the specified residual threshold of the next round is the average of the residual cumulative data of the current round and the specified residual threshold of the current round. In the case of a false negative warning, the residual cumulative data of the current round is directly used as the new threshold. Based on this method, the probability of a false positive warning signal can be gradually reduced, and there is a large penalty when a false negative warning occurs, and it can be gradually and quickly adjusted to a better state.

[0082] According to one embodiment of the present application, operation 104, analyzing the syndrome time series data according to the control chart algorithm to determine the infectious disease analysis result, includes: first, analyzing the syndrome time series data according to the control chart algorithm to determine the infectious disease analysis data; then, if the infectious disease analysis data exceeds the specified analysis threshold, determining the infectious disease analysis result as a warning positive; then, if the infectious disease analysis data does not exceed the specified analysis threshold, determining the infectious disease analysis result as a warning negative.

[0083] According to one embodiment of the present application, a second analysis result is determined based on syndrome time series data and historical characteristic data, including: first, determining a moving percentile method early warning model based on the syndrome time series data and historical characteristic data; then, determining the second analysis result based on the moving percentile method early warning model.

[0084] Specifically, the control chart algorithm of this method can be selected as the CUSUM control chart and the MPM moving percentile method early warning model. This method analyzes the syndrome time series data through the CUSUM control chart and the MPM moving percentile method early warning model to respectively determine the first analysis result and the second analysis result.

[0085] Similarly, this method requires setting a specified analysis threshold corresponding to the CUSUM control chart and the MPM moving percentile method early warning model to compare the analysis data and determine whether the final analysis result is a positive warning or a negative warning.

[0086] According to one embodiment of the present application, the method also includes: first, determining a preset analysis threshold based on historical analysis data corresponding to the syndrome time series data; the preset analysis threshold is a first-round designated analysis threshold; then, judging the infectious disease analysis result based on the actual result of the infectious disease to obtain a second judgment result; if the second judgment result is that the infectious disease analysis data of the current round is a warning false positive, the infectious disease analysis data of the current round and the designated analysis threshold of the current round are integrated to determine the designated analysis threshold of the next round; if the second judgment result is that the infectious disease analysis data of the current round is a warning false negative, the infectious disease analysis data of the current round is determined as the designated analysis threshold of the next round.

[0087] Similar to the specified residual threshold, the specified analysis threshold can also be a variable threshold. This method can first use prior information to set a preset analysis threshold as the specified analysis threshold used in the first round. Among them, the preset analysis threshold for the Cusum control chart can be the standard deviation of the analysis data within a 3-fold time window; the preset analysis threshold for the MPM moving percentile method early warning model can be the parameter value corresponding to P90 in the figure. Then, the actual results of the infectious disease are compared with the results of the infectious disease analysis to determine whether the specified analysis threshold needs to be adjusted. The adjustment of the specified analysis threshold for infectious diseases can also apply the formula for adjusting the specified residual threshold. The only difference is that when the above formula is applied to adjust the specified analysis threshold, the S in the formula i Replaced with the current round of infectious disease analysis data.

[0088] According to one embodiment of the present application, syndrome time series data are analyzed according to a control chart algorithm to determine an infectious disease analysis result, including: first, determining a characteristic control chart corresponding to the syndrome time series data, analyzing the characteristic control chart, and determining a first analysis result; then, determining historical characteristic data corresponding to the syndrome time series data, and determining a second analysis result based on the syndrome time series data and the historical characteristic data; and determining an infectious disease warning result based on the infectious disease prediction result, the first analysis result, and the second analysis result.

[0089] Specifically, the deviation values ​​from the day before to the day before the i-th day can be accumulated through the CUSUM control chart, and 3 times the standard deviation of the deviation value in the time window can be set as the preset analysis threshold. The first analysis result is determined by comparing the deviation value with the preset analysis threshold. If the specified analysis threshold of the current round needs to be adjusted, it is adjusted according to the deviation value and the specified analysis threshold of the current round.

[0090] Specifically, through the moving percentile warning model, we can first establish a percentile graph through the historical feature data and syndrome time series data corresponding to the syndrome time series data, and then use the previous day to the previous 7 days of the i-th day as the time window to calculate the mean. And use the 90% quantile of the mean of the same 3 years in the same period corresponding to the syndrome time series data, that is, P90 as the preset analysis threshold. In the first round, the second analysis result is determined by comparing the mean corresponding to the previous day to the previous 7 days of the i-th day with the preset analysis threshold. Similarly, if the specified analysis threshold of the current round needs to be adjusted, it is adjusted according to the mean and the specified analysis threshold of the current round. It should be added that the time windows set in the three algorithms can be consistent or inconsistent.

[0091] Figure 5 A schematic diagram of implementation modules of an infectious disease early warning device based on fusion computing according to an embodiment of the present application is shown.

[0092] See also Figure 5 According to the second aspect of the embodiment of the present application, an infectious disease early warning device based on fusion computing is also provided, wherein an acquisition module 501 is used to acquire the time series data of medical consultations for a specified infectious disease within a specified range; an extraction module 502 is used to extract data from the time series data of medical consultations according to the syndrome information corresponding to the specified infectious disease, and determine the corresponding syndrome time series data; a prediction module 503 is used to predict the syndrome time series data through a time series model, and determine the infectious disease prediction result; an analysis module 504 is used to analyze the syndrome time series data according to a control chart algorithm, and determine the infectious disease analysis result; an integration module 505 is used to integrate the infectious disease prediction result and the infectious disease analysis result, and determine the infectious disease early warning result corresponding to the specified infectious disease.

[0093] According to one embodiment of the present application, the extraction module 502 includes: an extraction sub-module 5021, which is used to extract data from the medical consultation time series data according to the syndrome information of the specified infectious disease, and obtain the original syndrome data corresponding to the specified infectious disease; a smoothing sub-module 5022, which is used to perform weighted smoothing processing on the syndrome data according to the time information corresponding to the original syndrome data, and obtain the syndrome time series data.

[0094] According to one embodiment of the present application, the prediction module 503 includes: a prediction submodule 5031, which is used to predict the syndrome time series data through a time series model to obtain model prediction data; a residual accumulation submodule 5032, which is used to accumulate residuals according to actual observation data and model prediction data to obtain residual accumulation data; a comparison submodule 5033, which is used to compare the residual accumulation data with a specified residual threshold to determine the infectious disease prediction result; wherein the infectious disease prediction result is a negative warning or a positive warning corresponding to the specified infectious disease.

[0095] According to one embodiment of the present application, the comparison submodule 5033 includes: if the cumulative residual data exceeds the specified residual threshold, determining that the infectious disease prediction result is a positive warning; if the cumulative residual data does not exceed the specified residual threshold, determining that the infectious disease prediction result is a negative warning.

[0096] According to one embodiment of the present application, the device also includes: a determination module 506, which is also used to determine a preset residual threshold based on the residual data corresponding to the syndrome time series data; an adjustment module 507, which is used to adjust the preset residual threshold according to the infectious disease prediction results and the actual results of the infectious disease to obtain a specified residual threshold.

[0097] According to one embodiment of the present application, the adjustment module 507 includes: judging the infectious disease prediction result based on the actual result of the infectious disease to obtain a first judgment result; if the first judgment result is that the infectious disease prediction result of the current round is a warning false positive, integrating the specified residual threshold of the current round and the residual cumulative data of the current round to determine the specified residual threshold of the next round; if the first judgment result is that the infectious disease prediction result of the current round is a warning false negative, determining the residual cumulative data of the current round as the specified residual threshold of the next round.

[0098] According to one embodiment of the present application, the analysis module 504 includes: analyzing the syndrome time series data according to the control chart algorithm to determine the infectious disease analysis data; if the infectious disease analysis data exceeds the specified analysis threshold, determining the infectious disease analysis result as a warning positive; if the infectious disease analysis data does not exceed the specified analysis threshold, determining the infectious disease analysis result as a warning negative.

[0099] According to one embodiment of the present application, the determination module 506 is used to determine a preset analysis threshold based on historical analysis data corresponding to the syndrome time series data; the preset analysis threshold is the first round designated analysis threshold; the adjustment module 507 also includes: judging the infectious disease analysis result based on the actual result of the infectious disease to obtain a second judgment result; if the second judgment result is that the infectious disease analysis data of the current round is a warning false positive, the infectious disease analysis data of the current round and the designated analysis threshold of the current round are integrated to determine the designated analysis threshold of the next round; if the second judgment result is that the infectious disease analysis data of the current round is a warning false negative, the infectious disease analysis data of the current round is determined as the designated analysis threshold of the next round.

[0100] According to one embodiment of the present application, the analysis module 504 includes: determining a characteristic control chart corresponding to the syndrome time series data, analyzing the characteristic control chart, and determining a first analysis result; determining historical characteristic data corresponding to the syndrome time series data, and determining a second analysis result based on the syndrome time series data and the historical characteristic data; an integration module 505 is used to determine an infectious disease warning result based on the infectious disease prediction result, the first analysis result, and the second analysis result.

[0101] According to one embodiment of the present application, the analysis module 504 includes: determining a moving percentile method early warning model according to the syndrome time series data and the historical characteristic data; and determining a second analysis result according to the moving percentile method early warning model.

[0102] According to one embodiment of the present application, the integration module 505 includes: voting on the infectious disease warning results according to the infectious disease prediction results and the infectious disease analysis results to determine the infectious disease warning results, where the infectious disease warning results are either positive warning or negative warning.

[0103] It should be noted that the above description of an embodiment of an infectious disease early warning device based on fusion computing is different from the above description of Figures 1 to 3 The description of the method embodiment shown is similar, with the same Figures 1 to 3 The method embodiments shown in the figure have similar beneficial effects, so they will not be described in detail. For technical details not disclosed in the embodiment of the infectious disease early warning device based on fusion computing of this application, please refer to the aforementioned Figures 1 to 3 The description of the method embodiment shown in the figure can be understood, and in order to save space, it will not be repeated.

[0104] According to the third aspect of the embodiments of the present application, an electronic device is provided, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, a method as described in any one of the above-described executable modes is implemented.

[0105] According to a fourth aspect of the embodiments of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the program is executed by a processor, a method as described in any one of the above-mentioned embodiments is implemented.

[0106] According to an embodiment of the present application, the present application also provides an electronic device and a readable storage medium.

[0107] Figure 6 A schematic block diagram of an example electronic device 600 that can be used to implement an embodiment of the present application is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described and / or required herein.

[0108] like Figure 6 As shown, the electronic device 600 includes a computing unit 601, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 602 or a computer program loaded from a storage unit 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the device 600 can also be stored. The computing unit 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0109] A number of components in the device 600 are connected to the I / O interface 605, including: an input unit 606, such as a keyboard, a mouse, etc.; an output unit 607, such as various types of displays, speakers, etc.; a storage unit 608, such as a disk, an optical disk, etc.; and a communication unit 609, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 609 allows the device 600 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0110] The computing unit 601 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 601 performs the various methods and processes described above, such as an infectious disease early warning method based on fusion computing. For example, in some embodiments, an infectious disease early warning method based on fusion computing may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 608. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 600 via the ROM 602 and / or the communication unit 609. When the computer program is loaded into the RAM 603 and executed by the computing unit 601, one or more steps of an infectious disease early warning method based on fusion computing described above may be performed. Alternatively, in other embodiments, the computing unit 601 may be configured to execute an infectious disease early warning method based on fusion computing in any other appropriate manner (eg, by means of firmware).

[0111] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0112] The program code for implementing the method of the present application can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, implements the functions / operations specified in the flow chart and / or block diagram. The program code can be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0113] In the context of the present application, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0114] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0115] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0116] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0117] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution disclosed in this application can be achieved, and this document is not limited here.

[0118] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0119] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. An infectious disease early warning method based on fusion computing, characterized in that: The method comprises: Obtain the time series data of medical consultations for a specified infectious disease within a specified range; the time series data of medical consultations within a specified range refers to the time series data of medical consultations within a specific area and a specific time range; Extracting data from the medical consultation time series data based on the syndrome information corresponding to the designated infectious disease to determine corresponding syndrome time series data; wherein the syndrome time series data is specifically the syndrome time series data for each day within a specific area and a specific time interval; Predicting the syndrome time series data using a time series model to determine infectious disease prediction results; Analyzing the syndrome time series data according to a control chart algorithm to determine the infectious disease analysis results; Integrating the infectious disease prediction results and the infectious disease analysis results to determine an infectious disease warning result corresponding to the designated infectious disease; The method of predicting the syndrome time series data using a time series model to determine the infectious disease prediction result includes: Predicting the syndrome time series data using a time series model to obtain model prediction data; Accumulate residuals based on actual observation data and model prediction data to obtain residual accumulation data; Determining an infectious disease prediction result based on the comparison of the residual accumulated data with a specified residual threshold; The infectious disease prediction result is a negative warning or a positive warning corresponding to the designated infectious disease; The method further comprises: Determining a preset residual threshold based on residual data corresponding to the syndrome time series data; Adjusting the preset residual threshold according to the infectious disease prediction result and the actual infectious disease result to obtain the specified residual threshold; Adjusting the preset residual threshold according to the infectious disease prediction result and the actual infectious disease result to obtain the specified residual threshold includes: Judging the predicted infectious disease result based on the actual infectious disease result to obtain a first judgment result; If the first judgment result is that the infectious disease prediction result of the current round is a warning false positive, integrating the specified residual threshold of the current round and the accumulated residual data of the current round to determine the specified residual threshold of the next round; If the first judgment result is that the infectious disease prediction result of the current round is a false negative warning, the accumulated residual data of the current round is determined as the specified residual threshold of the next round.

2. The method according to claim 1, characterized in that The step of extracting data from the time series data of medical consultations based on the syndrome information corresponding to the designated infectious disease to determine the corresponding syndrome time series data includes: Extracting data from the time series data of medical consultations according to the syndrome information of the designated infectious disease to obtain original syndrome data corresponding to the designated infectious disease; The syndrome data is weighted and smoothed according to time information corresponding to the original syndrome data to obtain syndrome time series data.

3. The method according to claim 1, characterized in that The step of comparing the accumulated residual data with a specified residual threshold to determine an infectious disease prediction result includes: If the accumulated residual data exceeds the specified residual threshold, the infectious disease prediction result is determined to be a positive warning; If the residual cumulative data does not exceed the specified residual threshold, the infectious disease prediction result is determined to be a negative warning.

4. The method according to claim 1, wherein Analyzing the syndrome time series data according to the control chart algorithm to determine the infectious disease analysis results includes: Analyzing the syndrome time series data according to a control chart algorithm to determine infectious disease analysis data; If the infectious disease analysis data exceeds a specified analysis threshold, determining that the infectious disease analysis result is a warning positive; If the infectious disease analysis data does not exceed the specified analysis threshold, the infectious disease analysis result is determined to be a warning negative.

5. The method according to claim 4, characterized in that The method further comprises: Determining a preset analysis threshold based on historical analysis data corresponding to the syndrome time series data; the preset analysis threshold is a first-round designated analysis threshold; Judging the infectious disease analysis result based on the actual infectious disease result to obtain a second judgment result; If the second judgment result is that the infectious disease analysis result of the current round is a warning false positive, integrating the infectious disease analysis data of the current round and the designated analysis threshold of the current round to determine the designated analysis threshold of the next round; If the second judgment result is that the infectious disease analysis result of the current round is a warning false negative, the infectious disease analysis data of the current round is determined as the designated analysis threshold for the next round.

6. The method according to claim 1, characterized in that Analyzing the syndrome time series data according to the control chart algorithm to determine the infectious disease analysis results includes: Determining a characteristic control chart corresponding to the syndrome time series data, analyzing the characteristic control chart, and determining a first analysis result; Determining historical feature data corresponding to the syndrome time series data, and determining a second analysis result based on the syndrome time series data and the historical feature data; The infectious disease early warning result is determined based on the infectious disease prediction result, the first analysis result and the second analysis result.

7. The method according to claim 6, characterized in that Determining the second analysis result based on the syndrome time series data and the historical feature data includes: Determine a moving percentile method early warning model based on the syndrome time series data and the historical characteristic data; The second analysis result is determined according to the moving percentile method early warning model.

8. The method according to claim 1, characterized in that The step of integrating the infectious disease prediction result and the infectious disease analysis result to determine an infectious disease warning result corresponding to the designated infectious disease includes: The infectious disease warning result is voted on based on the infectious disease prediction result and the infectious disease analysis result to determine the infectious disease warning result, which is either a positive warning or a negative warning.

9. An infectious disease early warning device based on fusion computing, characterized in that: The device comprises: An acquisition module is used to obtain time series data of medical consultations for a specified infectious disease within a specified range; An extraction module, configured to extract the time series data of the medical consultation according to the syndrome information corresponding to the designated infectious disease, and determine the corresponding syndrome time series data; A prediction module, configured to predict the syndrome time series data using a time series model to determine an infectious disease prediction result; an analysis module for analyzing the syndrome time series data according to a control chart algorithm to determine an infectious disease analysis result; an integration module, configured to integrate the infectious disease prediction result and the infectious disease analysis result to determine an infectious disease warning result corresponding to the designated infectious disease; The prediction module includes: a prediction submodule for predicting the syndrome time series data using a time series model to obtain model prediction data; a residual accumulation submodule for accumulating residuals based on actual observation data and model prediction data to obtain residual accumulation data; and a comparison submodule for comparing the residual accumulation data with a specified residual threshold to determine the infectious disease prediction result; wherein the infectious disease prediction result is a negative warning or a positive warning corresponding to the specified infectious disease; The apparatus further includes: a determination module, further configured to determine a preset residual threshold based on residual data corresponding to the syndrome time series data; an adjustment module, configured to adjust the preset residual threshold according to the infectious disease prediction result and the actual infectious disease result to obtain a specified residual threshold; The adjustment module includes: judging the infectious disease prediction results based on the actual results of the infectious disease to obtain a first judgment result; if the first judgment result is that the infectious disease prediction result of the current round is a false positive warning, integrating the specified residual threshold of the current round and the residual cumulative data of the current round to determine the specified residual threshold of the next round; if the first judgment result is that the infectious disease prediction result of the current round is a false negative warning, determining the residual cumulative data of the current round as the specified residual threshold of the next round.

10. An electronic device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method according to any one of claims 1 to 8 when executing the program.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images