Intelligent risk early warning method and system for real-time monitoring of regional infection

Abstract

The invention discloses an intelligent risk early warning method and system for real-time monitoring of regional infection, and belongs to the field of infection early warning, and the method comprises the steps: obtaining a plurality of regional infection feature matrixes; performing infection index calculation to obtain a plurality of regional infection quality control index matrixes; performing infection abnormity identification on the plurality of regional infection quality control index matrixes by using the frequent quality control indexes to obtain a plurality of abnormal infection index matrixes; and positioning an abnormal area and abnormal infection characteristics, calling infection prevention and control execution record data, performing abnormal infection factor traceability analysis, obtaining a traceability result, and generating abnormal early warning information. The technical problem that infection hidden dangers cannot be found and early warned in time due to the fact that the infection dynamic state of each region cannot be reflected in real time in the prior art is solved, the infection data is analyzed and integrated by using a big data resource service technology, and the effects of analyzing and processing the infection data of each region through big data and improving the infection efficiency are achieved. The technical effects of timely response and early warning on various infections are achieved.

Description

Technical Field

[0001] The present invention relates to the field of infection early warning, and in particular to an intelligent risk early warning method and system for real-time monitoring of regional infection. Background Art

[0002] Nowadays, infection has become one of the important factors endangering health and safety. At present, the risk warning for real-time monitoring of infection generally relies on manual statistics and reporting, which is inefficient and cannot reflect the infection dynamics of various regions in real time. Various data collection and processing rely on regular manual statistics, resulting in the inability to respond and warn of infection risks in a timely manner. Therefore, how to use intelligent means to establish an intelligent risk warning system for real-time monitoring of infection and achieve accurate capture and active response to various types of infections is a technical problem that needs to be solved in current infection management. Summary of the invention

[0003] This application aims to solve the technical problem that the existing technology cannot reflect the infection dynamics of each region in real time, resulting in the inability to timely discover and warn of infection risks, by providing an intelligent risk warning method and system for real-time monitoring of regional infections.

[0004] In view of the above problems, the present application provides an intelligent risk warning method and system for real-time monitoring of regional infection.

[0005] The first aspect disclosed in the present application provides an intelligent risk warning method for real-time monitoring of regional infections, the method comprising: collecting infection data for multiple areas within a preset monitoring range to obtain multiple regional infection data sets, wherein the multiple regional infection data sets have infection feature identifiers; traversing multiple regional infection data according to the infection feature identifiers for classification and integration to obtain multiple regional infection feature matrices; calculating infection indicators based on the multiple regional infection feature matrices to obtain multiple regional infection quality control indicator matrices, wherein the regional infection quality control indicator matrix includes multiple indicator combinations, and any indicator combination includes an infection rate and an infection mortality rate corresponding to an infection feature; obtaining frequent quality control indicators corresponding to the infection feature identifiers; identifying infection anomalies on multiple regional infection quality control indicator matrices with frequent quality control indicators to obtain multiple abnormal infection indicator matrices; locating abnormal areas and abnormal infection features based on multiple abnormal infection indicator matrices, retrieving infection prevention and control execution record data, and tracing the source of abnormal infection factors with the infection prevention and control execution record data to obtain tracing results; and generating abnormal warning information with the tracing results.

[0006] Another aspect disclosed in this application provides an intelligent risk early warning system for real-time monitoring of regional infections. The system includes: a data collection module for collecting infection data from multiple regions within a preset monitoring range to obtain multiple regional infection data sets, where the multiple regional infection data sets have infection feature identifiers; a data classification and integration module for traversing and classifying and integrating the multiple regional infection data according to the infection feature identifiers to obtain multiple regional infection feature matrices; an infection index calculation module for calculating infection indexes based on the multiple regional infection feature matrices to obtain multiple regional infection quality control index matrices, where the regional infection quality control index matrix includes multiple index combinations, and any index combination includes an infection rate and an infection mortality rate corresponding to an infection feature; a frequent quality control index module for obtaining frequent quality control indexes corresponding to the infection feature identifiers; an infection anomaly recognition module for performing infection anomaly recognition on the multiple regional infection quality control index matrices with the frequent quality control indexes to obtain multiple abnormal infection index matrices; a traceability result acquisition module for positioning abnormal regions and abnormal infection features based on the multiple abnormal infection index matrices, retrieving infection prevention and control execution record data, and performing traceability analysis on the abnormal infection factors with the infection prevention and control execution record data to obtain a traceability result; an abnormal early warning generation module for generating an abnormal early warning message with the traceability result.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages: By collecting infection data from multiple regions to obtain multiple regional infection data sets containing infection feature identifiers, it realizes the acquisition of comprehensive and dynamic infection monitoring data; classifying and integrating the collected multiple regional infection data sets according to the infection feature identifiers to form multiple regional infection feature matrices containing infection indexes, which realizes targeted data preparation for different infection types; calculating various infection indexes based on the constructed multiple regional infection quality control index matrices to generate multiple regional infection quality control index matrices reflecting the severity of infections, laying a solid foundation for subsequent infection anomaly recognition and evaluation; obtaining frequent quality control indexes for infection anomaly recognition to actively discover infection risks and improve the sensitivity to abnormal infections; positioning abnormal regions and abnormal infection features in the multiple abnormal infection index matrices, retrieving infection prevention and control execution record data for traceability analysis to obtain a traceability result; and then generating timely and accurate abnormal early warning messages with the traceability result. This technical solution solves the technical problem in the prior art that the infection dynamics of each region cannot be reflected in real time, resulting in the inability to timely discover and warn of infection hazards. By using big data resource service technology for the analysis and integration of infection data, it achieves the technical effect of timely responding to and warning various infections through intelligent analysis and processing of regional infection data.

[0008] The above description is only an overview of the technical solution of the present application. In order to better understand the technical means of the present application, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of the present application more obvious and understandable, the specific embodiments of the present application are hereinafter specifically exemplified. Brief Description of the Drawings

[0009] Figure 1 FIG. is a schematic flowchart of an intelligent risk early warning method for real-time monitoring of regional infections provided by an embodiment of the present application.

[0010] Figure 2 FIG. is a schematic flowchart of obtaining frequent quality control indicators in the intelligent risk early warning method for real-time monitoring of regional infections provided by an embodiment of the present application.

[0011] Figure 3 FIG. is a schematic structural diagram of an intelligent risk early warning system for real-time monitoring of regional infections provided by an embodiment of the present application.

[0012] Description of the reference numerals: data acquisition module 11, data classification and integration module 12, infection index calculation module 13, frequent quality control index module 14, infection abnormality identification module 15, traceability result acquisition module 16, abnormality early warning generation module 17. Detailed Embodiments

[0013] The overall idea of the technical solution provided by the present application is as follows: The embodiments of the present application provide an intelligent risk early warning method and system for real-time monitoring of regional infections, and by constructing a closed-loop real-time monitoring and management system, the overall controllability and risk containment of regional infections are realized.

[0014] Specifically, first, the infection data of each region within the preset monitoring range is collected and classified and integrated to form a plurality of regional infection feature matrices. Then, the infection indexes in the plurality of regional infection feature matrices are calculated to generate a plurality of regional infection quality control index matrices describing the severity of the infection. Subsequently, frequent quality control indexes are used to identify infection abnormalities in the plurality of regional infection quality control index matrices to obtain a plurality of abnormal infection index matrices, and the abnormal regions and abnormal infection features are located in the plurality of abnormal infection index matrices. Thereafter, the source tracing analysis of the abnormal infection factors is carried out with the infection prevention and control execution record data to obtain the source tracing result, and the abnormal early warning information is generated based on this.

[0015] In summary, the present application realizes the accurate capture and rapid early warning of the regional infection situation by intelligently analyzing and processing the infection data of each region, and uses the big data resource service technology to analyze and integrate the infection data, achieving the basic effect of timely response and early warning to various infections, and providing support for containing the infection risk.

[0016] After introducing the basic principle of the present application, various non-limiting implementation manners of the present application will be specifically introduced below in conjunction with the accompanying drawings of the specification.

[0017] Embodiment 1 As Figure 1 shown, the embodiment of the present application provides an intelligent risk warning method for real-time monitoring of regional infections, and the method includes: Collecting infection data for a plurality of regions within a preset monitoring range to obtain a plurality of regional infection data sets, wherein the plurality of regional infection data sets have infection characteristic identifiers.

[0018] In the embodiment of the present application, first, for a plurality of regions within a preset monitoring range, the infection data of each region is obtained through the API interface of the regional information management system. The clinical diagnosis data includes various infection test reports of the personnel in the region, etc., and characteristic parameters related to various infections are extracted, such as whether the patient has respiratory infection symptoms such as fever, cough, and dyspnea, whether the respiratory secretion culture is positive, whether there is a test report of bile or blood infection, etc.

[0019] Then, the clinical diagnosis data extracted from the plurality of regions is statistically sorted to form a data set representing the infection conditions of different regions and different time periods, that is, a plurality of regional infection data sets. At the same time, the plurality of regional infection data sets are labeled to indicate the corresponding infection types, such as respiratory infection, bacterial infection, various virus infections, etc., as infection characteristic identifiers.

[0020] By obtaining a plurality of regional infection data sets with infection characteristic identifiers for different regions, a data basis is provided for the subsequent construction of the regional infection characteristic matrix and infection analysis.

[0021] Traverse the plurality of regional infection data sets according to the infection characteristic identifiers for classification and integration to obtain a plurality of regional infection characteristic matrices.

[0022] In the embodiment of the present application, after obtaining a plurality of regional infection data sets, for the regional infection data sets of the same region, traversal classification is performed according to their infection characteristic identifiers. For example, for the regional infection data sets of the respiratory department, the respiratory infection group, the bloodstream infection group, etc. are sorted out according to the infection characteristic identifiers, so as to form the regional infection characteristic matrix of the respiratory department. Each element in the regional infection characteristic matrix represents an infection data group corresponding to a type of infection characteristic in the region. In this way, the corresponding regional infection data sets of each region are traversed and classified in turn, and finally a plurality of regional infection characteristic matrices are formed.

[0023] By converting multiple regional infection datasets into multiple regional infection feature matrices, a dataset foundation is established for obtaining a regional infection quality control index matrix in subsequent calculations. Meanwhile, the matrix form is also conducive to intuitively reflecting the associations between different regions and different infection types.

[0024] Based on the multiple regional infection feature matrices, infection index calculations are performed to obtain multiple regional infection quality control index matrices. Among them, the regional infection quality control index matrix includes multiple index combinations, and any index combination includes the infection rate and infection mortality rate corresponding to one infection feature.

[0025] In the embodiments of the present application, after obtaining the multiple regional infection feature matrices, for each regional infection feature matrix, each element of the regional infection feature matrix is traversed, that is, the infection data group corresponding to a specific infection feature in each region. Then, based on the infection data group corresponding to this element, the infection incidence rate of this infection feature in this region is calculated, such as the incidence rate of respiratory tract infections in the respiratory department, and the case fatality rate is calculated, such as the mortality rate of respiratory tract infections in the respiratory department. Repeat the above calculation process, and finally form multiple regional infection quality control index matrices, where the matrix elements reflect the infection rate and infection mortality rate indicators corresponding to different infection features in each region within the preset monitoring range.

[0026] By obtaining multiple regional infection quality control index matrices, the infection degrees of different regions and different infection types within the preset monitoring range can be intuitively reflected, providing a basis for identifying abnormal infections and issuing early warnings.

[0027] Obtain the frequent quality control indicators corresponding to the infection feature identifiers.

[0028] Furthermore, the embodiments of the present application also include: Establish a reference threshold for the data mining scale.

[0029] Based on the infection feature identifiers and the data mining scale reference threshold, a multi-feature infection quality control index sample set is collected.

[0030] Perform discrete value elimination on the multi-feature infection quality control index sample set, and calculate the frequent quality control indicators based on the discrete value elimination results.

[0031] Furthermore, as Figure 2 shown, the embodiments of the present application also include: Based on a predetermined distance threshold, the multi-feature infection quality control index sample set is divided into distribution regions to obtain multiple regional distribution probabilities.

[0032] Perform neighborhood probability deviation calculations on the multiple regional distribution probabilities to obtain multiple neighborhood probability deviation values.

[0033] Extract multiple target regions where the neighborhood probability deviation value is less than a predetermined deviation threshold and perform regional interval difference analysis. If the regional interval extreme value meets the preset interval threshold, extract the data distribution range of the quality control index samples within the multiple target regions to obtain the frequent quality control index.

[0034] In a feasible implementation manner, to obtain the frequent quality control index, first, establish a reference threshold for the data mining scale to set a limiting condition for the subsequent collection of the multi-feature infection quality control index sample set. Specifically, investigate information such as the number of beds and the number of patients admitted annually in each region within the preset monitoring range, and combine data such as the regional population distribution to generate the minimum sample size for calculating the frequent quality control index in the preset monitoring range, that is, the reference threshold for the data mining scale. In this way, when collecting the multi-feature infection quality control index sample set, it is required that the collected sample size is not less than this reference threshold for the data mining scale, to avoid affecting the statistical significance of the multi-feature infection quality control index sample set due to the too small data volume of the region itself, and at the same time, the differences in the actual business volumes of regions of different scales are also considered. Then, based on the actual business scale of the preset monitoring range and on the basis of the reference threshold for the data mining scale, extract a sufficient number of sample sets containing the infection feature identifiers possessed by multiple regional infection data sets to form a multi-feature infection quality control index sample set. For example, for the preset monitoring range, according to information such as the number of beds in its infection wards, collect nearly 1-year, more than 3000 cases of respiratory infection samples, 2000 cases of bloodstream infection samples, etc. with reference to the reference threshold for the data mining scale.

[0035] After obtaining the multi-feature infection quality control index sample set, analyze the statistical distribution of the multi-feature infection quality control index sample set. First, set a predetermined distance threshold for the index values. For example, when the index ranges from 0 to 100, the predetermined distance threshold can be set to 10. Then, divide the value range in the multi-feature infection quality control index sample set into multiple intervals according to the predetermined distance threshold. For example, with a predetermined distance threshold of 10, the range from 0 to 10 in the 0 - 100 range of the index is divided into Region 1, the range from 10 to 20 is Region 2, and so on, to obtain multiple regions. Subsequently, count the number of samples in each interval range of the multiple regions, calculate the proportion of the total number of samples, that is, obtain the distribution probabilities of multiple regions, which reflects the concentration degree of samples in each section and lays a foundation for calculating the neighborhood probability deviation. Then, for the distribution probabilities of multiple regions, select two adjacent regions in sequence, extract the distribution probabilities of these two regions, and subtract the distribution probability of the latter region from the distribution probability of the former region to obtain the difference between the two region distribution probabilities, that is, the probability deviation value. For example, subtract the distribution probability of Region 2 from the distribution probability difference of Region 1 to obtain the first neighborhood probability deviation value, and then subtract the distribution probability of Region 3 from the distribution probability difference of Region 2 to obtain the second neighborhood probability deviation value, and so on, finally obtaining multiple neighborhood probability deviation values, which reflect the change in the dispersion degree of the index samples between adjacent regions.

[0036] Set a predetermined deviation threshold in advance. After obtaining multiple neighborhood probability deviation values, compare the multiple neighborhood probability deviation values with the predetermined deviation threshold in sequence, calibrate the neighborhood probability deviation values less than the predetermined deviation threshold, and extract the regions corresponding to these calibrated neighborhood probability deviation values to obtain multiple target regions. For example, compare the neighborhood probability deviation values of Region 1 and Region 2 with the predetermined deviation threshold. If the neighborhood probability deviation values of Region 1 and Region 2 are less than the predetermined deviation threshold, then include Region 1 and Region 2 in the multiple target regions, and compare the relationship between the remaining neighborhood probability deviation values in the multiple neighborhood probability deviation values with the predetermined deviation threshold in sequence, finally determining multiple target regions. Subsequently, under normal circumstances, for data with a relatively concentrated distribution, it generally exists in several consecutive regions, and the difference between the two region numbers is not too large. Therefore, for the multiple selected target regions, calculate the maximum difference in region numbers, that is, the extreme value of the region interval. For example, the largest region number in the multiple target regions is Region 5, and the smallest region number is Region 1. At this time, subtract the number of Region 1 from the number of Region 5 to get 4, which is the extreme value of the region interval. Then, determine whether the extreme value of the region interval is less than or equal to the preset interval threshold set according to experience. If the extreme value of the region interval is less than or equal to the preset interval threshold, then extract the multi-feature infection quality control index samples within the data distribution range corresponding to the multiple target regions, which represents the main interval range with a concentrated distribution in the multi-feature infection quality control index sample set and serves as the frequent quality control index.

[0037] In the above - mentioned manner, both the smoothness of the sample distribution is considered and the span of the continuous region is controlled, thereby locking the high - frequency distribution interval of the index and realizing the extraction of frequently - quality - controlled indexes.

[0038] Use the frequently - quality - controlled indexes to identify abnormal infections in the matrix of regional infection quality - control indexes for multiple regions, and obtain multiple abnormal infection index matrices.

[0039] In the embodiment of the present application, after obtaining the frequently - quality - controlled indexes that describe the central tendency of the multi - feature infection quality - control index sample set, use the frequently - quality - controlled indexes to identify abnormalities in the obtained matrix of regional infection quality - control indexes for multiple regions.

[0040] Specifically, traverse the matrix of regional infection quality - control indexes for multiple regions, and compare each element in the matrix, that is, the infection rate and infection mortality rate of each specific infection type in each region, with the range of the frequently - quality - controlled indexes to determine whether it is outside the range of the frequently - quality - controlled indexes. If it exceeds the range of the frequently - quality - controlled indexes, mark the matrix element as an abnormal infection. Repeat the above comparison and marking process to obtain multiple abnormal infection index matrices reflecting the abnormal infection conditions in each region.

[0041] By identifying abnormal infections to obtain multiple abnormal infection index matrices, it can intuitively reflect the abnormal infection conditions in each region within the preset monitoring range, providing a basis for subsequent traceability and early warning.

[0042] Locate the abnormal regions and abnormal infection characteristics based on the multiple abnormal infection index matrices, retrieve the infection prevention and control execution record data, and conduct a traceability analysis of abnormal infection factors with the infection prevention and control execution record data to obtain a traceability result.

[0043] Furthermore, the embodiment of the present application further includes: Establish a multi - feature abnormal infection index distribution according to the multiple abnormal infection index matrices.

[0044] Retrieve the infection prevention and control execution record data of the associated regions for the abnormal index - associated regions based on the multi - feature abnormal infection index distribution, where the infection prevention and control execution record data includes the set of infection prevention and control execution record data of the associated regions.

[0045] Identify the infection prevention and control execution rate of the set of infection prevention and control execution record data through the infection prevention and control analysis network layer.

[0046] Locate the abnormal infection factors with the infection prevention and control execution rate to obtain the traceability result.

[0047] Furthermore, the embodiment of the present application further includes: Obtain the calibrated prevention and control period.

[0048] Perform periodic data partitioning on the infection prevention and control execution record data set according to the calibrated prevention and control period, and judge the infection prevention and control execution behavior according to the partitioning result through the infection prevention and control analysis network layer to obtain a judgment result.

[0049] Calculate the infection prevention and control execution rate based on the judgment result.

[0050] In a feasible implementation manner, after obtaining multiple abnormal infection index matrices reflecting abnormal infection situations, for each abnormal infection index matrix, extract each area and each infection index marked as infection abnormality in the matrix, perform summary statistics, and obtain the proportion of the number of occurrences of abnormal indicators of each infection type in each area, that is, the distribution ratio. At the same time, considering the connection between areas and the factors of pathogen transmission, evaluate the possibility of migration and diffusion of abnormal indicators between associated areas to form a supplementary distribution ratio factor. Then, pre-construct a multi-feature abnormal infection index distribution by combining the distribution ratio and the supplementary distribution ratio factor, reflecting the distribution and transmission of a certain abnormal infection in each area and between associated areas, laying a foundation for subsequent traceability and early warning. Subsequently, based on the multi-feature abnormal infection index distribution, determine the associated areas, and through the regional information management system, retrieve the infection prevention and control execution record data of these areas during the abnormal infection occurrence period to construct an infection prevention and control execution record data set. Among them, the infection prevention and control execution record data set includes infection prevention and control execution record data such as regional environmental disinfection records and personnel hand hygiene execution data sets.

[0051] Subsequently, obtain the calibrated prevention and control cycle, which is the average infection occurrence cycle of abnormal infections obtained through statistical analysis of historical data, such as the average onset cycle of common respiratory tract infections in the respiratory department, or parameters such as the average incubation period and treatment cycle of virus infections. Then, according to the obtained calibrated prevention and control cycle, the set of infection prevention and control execution record data is segmented into multiple cycle data sets along the time axis, that is, each cycle corresponds to a cycle data set, and the segmentation result is obtained. After that, use the preset infection prevention and control analysis network layer to analyze and judge each cycle data set. For each prevention and control execution record in the cycle data set, judge whether it is completed or complies with the standard procedures, and obtain the judgment result of whether each cycle data set is compliant with prevention and control. Among them, the infection prevention and control analysis network layer is a preset analysis model used to judge whether the set of infection prevention and control execution record data complies with the standard procedures. The infection prevention and control analysis network layer is composed of multiple neural network modules, and each module is used to judge the execution status of a type of prevention and control measure. For example, the environmental cleaning and disinfection module, the patient isolation module, etc. And each module learns the standard procedure characteristics of different prevention and control measures through model training, such as rules for the usage amount of disinfectant, the number of disinfections, and the qualifications of disinfection personnel for environmental disinfection. When analyzing the prevention and control record data in the actual cycle data set, different modules in the network layer will be started in sequence, extract the characteristic data in the cycle data set, and give a judgment result by comparing with the standard procedures. After that, traverse the judgment results of each cycle data set, and count the proportion of the infection prevention and control execution records judged to comply with the standard procedures in the total infection prevention and control execution records in each cycle data set, as the infection prevention and control execution rate of the abnormal index associated area.

[0052] Pre-set an execution rate threshold, such as 80%, and then compare it with the calculated infection prevention and control execution rate. If the infection prevention and control execution rate is lower than or equal to the execution rate threshold, it indicates that there are defects or omissions in the daily prevention and control of this abnormal associated area, and then determine the prevention and control measures or processes with defects or omissions as abnormal infection factors. If the infection prevention and control execution rate is higher than the execution rate threshold, it indicates that the daily prevention and control work in the abnormal associated area is acceptable, and then locate the abnormal infection factors in other areas. After that, summarize the located abnormal infection factors to obtain the traceability result.

[0053] Generate an abnormal warning message based on the traceability result.

[0054] In the embodiments of the present application, first, for various traceability results, such as various identified prevention and control defects or detailed loopholes, and other factors causing abnormal infections, corresponding early warning information templates are preset. The content of the early warning information template includes information such as improvement suggestions for relevant prevention and control measures, monitoring details of abnormal factors, and subsequent risk assessments. After obtaining the traceability results, the early warning information template is matched according to the traceability results, and the template details are filled, such as information on the area where the identified prevention and control loopholes are located, the wards involved, the time interval for subsequent self-checks, etc., to form abnormal early warning information for abnormal areas and abnormal infections, so as to achieve timely response and early warning of infections and reduce the risk of infection spread.

[0055] Further, the embodiments of the present application further include: Based on the multi-feature abnormal infection index distribution, locate the multi-region concurrent infection characteristics where the number of associated regions is greater than or equal to a predetermined number threshold.

[0056] Based on the multi-region concurrent infection characteristics, conduct an infection concurrent early warning.

[0057] In a feasible implementation manner, in the multi-feature abnormal infection index distribution, count the associated regions spread by various abnormal infection indexes to obtain the number of associated regions. Set a predetermined number threshold in advance, for example, set it to 5 regions. Then, when the number of associated regions is greater than or equal to the predetermined number threshold, these multiple regions of the associated regions are identified as concurrent infections, and the infection characteristics of the concurrent infections are extracted as the concurrent infection characteristics. This concurrent infection characteristic has a certain infectious risk and may cause large-scale infections within the region. Subsequently, after determining that there are concurrent infection characteristics of multi-region wide spread, extract the located concurrent infection characteristics and query the associated regions; at the same time, organize a preset concurrent early warning information template to generate corresponding early warning content, which includes the name of the concurrent infection, the spread area, the possible transmission method, the recommended prevention and control measures, etc. Then, immediately push the concurrent early warning information to relevant regions and infection control personnel through text messages, emails, etc. to complete the infection concurrent early warning.

[0058] By conducting an infection concurrent early warning, improve the proactive response to potential concurrent infections, and take control measures such as strengthening the isolation of the source of infection and the protection of medical staff, so as to effectively prevent the further deterioration of concurrent infections.

[0059] Further, the embodiments of the present application further include: Obtain the first abnormal infection characteristic whose infection prevention and control execution rate meets the calibrated execution rate threshold.

[0060] Perform a seasonal concurrent characteristic discrimination on the first abnormal infection characteristic. If the discrimination result is yes, conduct a sudden early warning on the first abnormal infection characteristic.

[0061] In a feasible implementation, after obtaining the infection prevention and control execution rate, traverse the infection prevention and control execution rates corresponding to the regions associated with each abnormal infection feature. Then, determine whether the infection prevention and control execution rate is greater than or equal to the calibrated execution rate threshold formulated by experts based on historical data. If the infection prevention and control execution rate is greater than or equal to the calibrated execution rate threshold, extract the corresponding abnormal infection feature as the first abnormal infection feature. After that, query the first abnormal infection feature, determine whether it is in the category of virus infections, and confirm whether the current date is in the high-incidence period of relevant seasonal epidemics such as influenza. If all the above conditions are met and it is determined that the first abnormal infection feature belongs to the seasonal concurrent feature, immediately trigger the generation of a sudden warning message. In the sudden warning message, it is prompted that there is an abnormal expansion of seasonal infections in the relevant regions currently, and it is necessary to increase the prevention and control efforts to avoid possible seasonal infection outbreaks in each region.

[0062] In summary, the intelligent risk warning method for real-time regional infection monitoring provided by the embodiments of the present application has the following technical effects: Collect infection data for multiple regions within the preset monitoring scope to obtain multiple regional infection data sets, laying a data foundation for subsequent analysis. Traverse the multiple regional infection data according to the infection feature identifiers for classification and integration to obtain multiple regional infection feature matrices, preparing targeted data sources. Calculate infection indicators based on the multiple regional infection feature matrices to obtain multiple regional infection quality control index matrices, supporting the accurate identification of infection risks. Obtain the frequent quality control indicators corresponding to the infection feature identifiers to achieve the proactive discovery of infection risks. Use the frequent quality control indicators to identify infection abnormalities in the multiple regional infection quality control index matrices to obtain multiple abnormal infection index matrices, providing support for locating abnormal regions and abnormal infection features. Locate abnormal regions and abnormal infection features based on the multiple abnormal infection index matrices, retrieve the infection prevention and control execution record data, and conduct a traceability analysis of abnormal infection factors based on the infection prevention and control execution record data to obtain a traceability result, providing information for generating an abnormal warning message. Generate an abnormal warning message based on the traceability result to achieve timely response and warning for various infections.

[0063] Embodiment 2 Based on the same inventive concept as the intelligent risk warning method for real-time regional infection monitoring in the foregoing embodiments, as Figure 3 shown, the embodiments of the present application provide an intelligent risk warning system for real-time regional infection monitoring, and the system includes: A data collection module 11, configured to collect infection data for multiple regions within the preset monitoring scope to obtain multiple regional infection data sets, wherein the multiple regional infection data sets have infection feature identifiers.

[0064] The data classification and integration module 12 is used to traverse the multiple regional infection data sets according to the infection characteristic identifier for classification and integration, so as to obtain multiple regional infection characteristic matrices.

[0065] The infection index calculation module 13 is used to calculate infection indexes based on the multiple regional infection characteristic matrices, so as to obtain multiple regional infection quality control index matrices. Among them, the regional infection quality control index matrix includes multiple index combinations, and any index combination includes the infection rate and infection mortality rate corresponding to an infection characteristic.

[0066] The frequent quality control index module 14 is used to obtain the frequent quality control indexes corresponding to the infection characteristic identifier.

[0067] The infection anomaly identification module 15 is used to identify infection anomalies in the multiple regional infection quality control index matrices with the frequent quality control indexes, so as to obtain multiple anomaly infection index matrices.

[0068] The traceability result acquisition module 16 is used to locate the abnormal area and abnormal infection characteristics based on the multiple anomaly infection index matrices, retrieve the infection prevention and control execution record data, and perform traceability analysis of abnormal infection factors with the infection prevention and control execution record data to obtain the traceability result.

[0069] The abnormal warning generation module 17 is used to generate abnormal warning information with the traceability result.

[0070] Further, the frequent quality control index module 14 includes the following execution steps: Establish a reference threshold for the data mining scale.

[0071] Collect a multi-feature infection quality control index sample set based on the infection characteristic identifier and the data mining scale reference threshold.

[0072] Perform discrete value elimination on the multi-feature infection quality control index sample set, and calculate the frequent quality control indexes based on the discrete value elimination result.

[0073] Further, the frequent quality control index module 14 also includes the following execution steps: Divide the distribution area of the multi-feature infection quality control index sample set based on a predetermined distance threshold to obtain multiple regional distribution probabilities.

[0074] Perform neighborhood probability deviation calculation on the multiple regional distribution probabilities to obtain multiple neighborhood probability deviation values.

[0075] Extract multiple target regions with neighborhood probability deviation values less than a predetermined deviation threshold and perform regional interval difference analysis. If the regional interval extreme value meets the preset interval threshold, extract the data distribution range of the quality control index samples within the multiple target regions to obtain the frequent quality control indexes.

[0076] Further, the traceability result acquisition module 16 includes the following execution steps: Establish a multi-feature abnormal infection index distribution based on the multiple abnormal infection index matrices.

[0077] Retrieve the infection prevention and control execution record data of the abnormal index association area based on the multi-feature abnormal infection index distribution, where the infection prevention and control execution record data includes a set of infection prevention and control execution record data for the associated area.

[0078] Identify the infection prevention and control execution rate of the set of infection prevention and control execution record data through the infection prevention and control analysis network layer.

[0079] Locate the abnormal infection factors based on the infection prevention and control execution rate to obtain the traceability result.

[0080] Further, the traceability result acquisition module 16 further includes the following execution steps: Obtain the calibrated prevention and control period.

[0081] Perform periodic data division on the set of infection prevention and control execution record data according to the calibrated prevention and control period, and judge the infection prevention and control execution behavior through the infection prevention and control analysis network layer according to the division result to obtain a judgment result.

[0082] Calculate the infection prevention and control execution rate based on the judgment result.

[0083] Further, the embodiment of the present application further includes an infection complication warning module, which includes the following execution steps: Locate the multi-region concurrent infection characteristics with the number of associated regions greater than or equal to a predetermined number threshold based on the multi-feature abnormal infection index distribution.

[0084] Perform infection complication warning based on the multi-region concurrent infection characteristics.

[0085] Further, the embodiment of the present application further includes a sudden warning module, which includes the following execution steps: Obtain the first abnormal infection characteristics with the infection prevention and control execution rate meeting the calibrated execution rate threshold.

[0086] Discriminate the seasonal concurrent characteristics of the first abnormal infection characteristics. If the discrimination result is yes, give a sudden warning to the first abnormal infection characteristics.

[0087] Any step of the above-mentioned method can be stored as computer instructions or programs in an unrestricted computer memory and can be called and recognized by an unrestricted computer processor to implement any one of the methods in the embodiment of the present application, and no redundant limitation is made here.

[0088] Furthermore, the first or second as described above may not only represent an order relationship, but may also represent a specific concept, and / or refer to the selection of multiple elements either individually or in whole. Obviously, those skilled in the art can make various changes and modifications to this application without departing from the scope of this application. Thus, if these modifications and variations of this application fall within the scope of this application and its equivalent technologies, then this application is intended to include these changes and modifications.

Claims

1. An intelligent risk early warning method for real-time monitoring of regional infections, characterized in that, The method includes: Collecting infection data for multiple regions within a preset monitoring range to obtain multiple regional infection data sets, where the multiple regional infection data sets have infection characteristic identifiers; Traversing the multiple regional infection data sets according to the infection characteristic identifiers for classification and integration to obtain multiple regional infection characteristic matrices; Calculating infection indicators based on the multiple regional infection characteristic matrices to obtain multiple regional infection quality control index matrices, where a regional infection quality control index matrix includes multiple index combinations, and any index combination includes an infection rate and an infection mortality rate corresponding to an infection characteristic; Obtaining the frequent quality control indicators corresponding to the infection characteristic identifiers; Identifying abnormal infections in the multiple regional infection quality control index matrices with the frequent quality control indicators to obtain multiple abnormal infection index matrices; Locating abnormal regions and abnormal infection characteristics based on the multiple abnormal infection index matrices, retrieving infection prevention and control execution record data, and performing traceability analysis of abnormal infection factors with the infection prevention and control execution record data to obtain a traceability result; Generating an abnormal warning message with the traceability result.

2. The method according to claim 1, characterized in that, The obtaining the frequent quality control indicators corresponding to the infection characteristic identifiers includes: Establishing a reference threshold for the data mining scale; Collecting a multi-characteristic infection quality control index sample set based on the infection characteristic identifiers and the data mining scale reference threshold; Removing discrete values from the multi-characteristic infection quality control index sample set and calculating the frequent quality control indicators based on the discrete value removal result.

3. The method according to claim 2, wherein Removing discrete values from the multi-characteristic infection quality control index sample set and calculating the frequent quality control indicators based on the discrete value removal result includes: Dividing the distribution area of the multi-characteristic infection quality control index sample set based on a predetermined distance threshold to obtain multiple regional distribution probabilities; Performing neighborhood probability deviation calculation on the multiple regional distribution probabilities to obtain multiple neighborhood probability deviation values; Extracting multiple target regions with neighborhood probability deviation values less than a predetermined deviation threshold and performing regional interval difference analysis. If the regional interval extreme value meets the preset interval threshold, extracting the data distribution range of the quality control index samples within the multiple target regions to obtain the frequent quality control indicators.

4. The method according to claim 1, characterized in that, The locating abnormal regions and abnormal infection characteristics based on the multiple abnormal infection index matrices, retrieving infection prevention and control execution record data, and performing traceability analysis of abnormal infection factors with the infection prevention and control execution record data to obtain a traceability result includes: Establishing a multi-characteristic abnormal infection index distribution according to the multiple abnormal infection index matrices; Retrieving infection prevention and control execution record data of associated regions based on the multi-characteristic abnormal infection index distribution to generate a set of infection prevention and control execution record data for the associated regions; Identifying the infection prevention and control execution rate of the set of infection prevention and control execution record data through the infection prevention and control analysis network layer; Locating abnormal infection factors with the infection prevention and control execution rate to obtain the traceability result.

5. The method according to claim 4, wherein The identifying the infection prevention and control execution rate of the set of infection prevention and control execution record data through the infection prevention and control analysis network layer includes: Obtaining the calibrated prevention and control period; Perform periodic data partitioning on the infection prevention and control execution record data set according to the calibrated prevention and control period, and judge the infection prevention and control execution behavior according to the partitioning result through the infection prevention and control analysis network layer to obtain a judgment result; Calculate the infection prevention and control execution rate based on the judgment result.

6. The method according to claim 4, wherein The method further includes: Locate the multi-region concurrent infection characteristics with the number of associated regions greater than or equal to the predetermined quantity threshold based on the multi-feature abnormal infection index distribution; Generate an infection concurrent warning based on the multi-region concurrent infection characteristics.

7. The method according to claim 5, wherein The method further includes: Obtain the first abnormal infection characteristics with the infection prevention and control execution rate meeting the calibrated execution rate threshold; Discriminate the seasonal concurrent characteristics of the first abnormal infection characteristics. If the discrimination result is yes, issue a sudden warning for the first abnormal infection characteristics.

8. An intelligent risk early warning system for real-time monitoring of regional infections, characterized in that, A system for implementing the intelligent risk warning method for regional infection real-time monitoring according to any one of claims 1-7, the system includes: A data collection module, which is used to collect infection data for multiple regions within a preset monitoring range to obtain multiple regional infection data sets. Among them, the multiple regional infection data sets have infection feature identifiers; A data classification and integration module, which is used to traverse the multiple regional infection data sets according to the infection feature identifiers for classification and integration to obtain multiple regional infection feature matrices; An infection index calculation module, which is used to calculate infection indexes based on the multiple regional infection feature matrices to obtain multiple regional infection quality control index matrices. Among them, the regional infection quality control index matrix includes multiple index combinations, and any index combination includes the infection rate and infection mortality corresponding to one infection feature; A frequent quality control index module, which is used to obtain the frequent quality control index corresponding to the infection feature identifier; An infection anomaly recognition module, which is used to identify infection anomalies in the multiple regional infection quality control index matrices with the frequent quality control index to obtain multiple abnormal infection index matrices; A traceability result acquisition module, which is used to locate abnormal regions and abnormal infection characteristics based on the multiple abnormal infection index matrices, retrieve infection prevention and control execution record data, and perform traceability analysis of abnormal infection factors with the infection prevention and control execution record data to obtain a traceability result; An abnormal warning generation module, which is used to generate abnormal warning information based on the traceability result.

Images