Monitoring, alarming and early warning method and system based on numerical analysis and coupling analysis

Abstract

The invention discloses a monitoring, alarming and early warning method and system based on numerical analysis and coupling analysis. The method comprises the following steps: acquiring monitoring data of each industry based on urban safety development evaluation from a plurality of data sources and preprocessing the monitoring data; calculating the preprocessed monitoring data by using an alarm logic formula based on static numerical analysis and dynamic numerical analysis, and determining whether to give an alarm or not according to a calculation result; according to an alarm logic formula, determining an association relationship and an interaction factor of multi-source alarm, and according to the association relationship and the interaction factor, performing association coupling early warning analysis and spatial coupling early warning analysis on each monitoring data; through the preset big data analysis model, urban safety event prediction and early warning prompt are carried out based on the coupling early warning analysis result, and through an alarm analysis mechanism and an early warning analysis mechanism which are widely applied and fully verified, the alarm accuracy and the early warning effectiveness in a cross-industry, cross-organization and cross-region monitoring scene are effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of urban safety development assessment, and in particular to a monitoring, alarm and early warning method and system based on numerical analysis and coupling analysis. Background Art

[0002] Currently, comprehensive urban safety and development assessments are used to evaluate and measure a city's overall safety status and the sustainability of its development. This assessment approach aims to comprehensively consider multiple key areas and factors to help urban planners, government decision-makers, and other relevant stakeholders better understand a city's strengths and weaknesses, enabling the formulation of effective policies and strategies to improve urban safety, sustainability, and the quality of life of its residents. The urban safety sector encompasses more than ten industries across four key areas: urban lifelines, public safety, natural disasters, and production safety. Each industry has its own unique monitoring, alarm, and warning generation processes and mechanisms. These processes vary in scope, principles, and data heterogeneity. Comprehensive urban safety and emergency management in cities requires adapting the data and process mechanisms for each industry, a significant and complex task. Furthermore, inconsistent data standards lead to low accuracy in cross-industry coupled warnings. Summary of the Invention

[0003] In response to the problems shown above, the present invention provides a monitoring, alarm, and early warning method and system based on numerical analysis and coupling analysis to solve the problem mentioned in the background technology that due to the different calibers, different principles, and heterogeneous data of the monitoring, alarm, and early warning generation process mechanisms in various industries, when conducting comprehensive urban safety emergency management in cities, it is necessary to adapt the data and process mechanisms of each industry, which is heavy and complicated. At the same time, the inconsistency of data standards leads to the problem of low accuracy of cross-industry coupling early warnings.

[0004] A monitoring, alarm, and early warning method based on numerical analysis and coupling analysis, characterized by comprising the following steps:

[0005] Collect and pre-process monitoring data from various industries based on urban safety development assessment from multiple data sources;

[0006] Use the alarm logic formula based on static numerical analysis and dynamic numerical analysis to calculate the pre-processed monitoring data, and determine whether to alarm based on the calculation results;

[0007] Determine the correlation and interaction factors of multi-source alarms based on the alarm logic formula, and conduct correlation coupling warning analysis and spatial coupling warning analysis on each monitoring data based on the correlation and interaction factors;

[0008] Urban security incident prediction and early warning prompts are carried out based on the coupled early warning analysis results through the preset big data analysis model.

[0009] Preferably, the monitoring data of various industries based on the urban safety development assessment are collected from multiple data sources and pre-processed, including:

[0010] Identify multiple special evaluation indicators based on urban safety development, obtain the mapping data source for each special evaluation indicator, and determine the subordinate data industry of the mapping data source;

[0011] Determine the data format of each subordinate data industry, select data extraction technology based on the data format, and use data extraction technology to collect monitoring data from multiple data sources;

[0012] Perform data cleaning on monitoring data, obtain cleaned data, detect the data form of the cleaned data, and determine the integrity of the cleaned data based on the data form;

[0013] Based on the integrity of the cleaned data, the cleaned data is preprocessed by deduplication, missing data supplementation and invalid data elimination.

[0014] Preferably, the method of calculating the pre-processed monitoring data using an alarm logic formula based on static numerical analysis and dynamic numerical analysis, and determining whether to issue an alarm based on the calculation result, includes:

[0015] Determine static data items and dynamic data items in the preprocessed monitoring data, and define formula variable value attributes based on the static data items and the dynamic data items, wherein the formula variable value attributes include: a determined value and an uncertain value;

[0016] Determine the monitoring indicators corresponding to the pre-processed monitoring data, determine the alarm logic based on the monitoring indicators, and define the alarm logic formula by adding variables and expressions according to the alarm logic;

[0017] Determine the monitoring object of each monitoring indicator, and define common alarm rules and individual alarm rules based on the consistency of the monitoring objects;

[0018] Based on the alarm common rules and alarm individual rules, the pre-processed monitoring data is calculated through the alarm logic formula, the abnormal data is determined according to the calculation results, and the alarm is determined based on the abnormal data.

[0019] Preferably, determining the correlation relationship and interaction factor of the multi-source alarms according to the alarm logic formula, and performing correlation coupling warning analysis and spatial coupling warning analysis on each monitoring data according to the correlation relationship and interaction factor, includes:

[0020] Determine the common cause of multiple alarm sources based on the alarm logic formula, determine the risk factors based on the common cause of the alarm, and determine the correlation and interaction factors of multiple alarm sources based on the risk factors;

[0021] Performing correlation coupling early warning analysis on each monitoring data based on the correlation relationship and mutual factors of multi-source alarms to obtain a first analysis result;

[0022] Determine the dynamic spatial range of multi-source alarms based on the alarm logic formula, determine the idle constraint factors based on the dynamic spatial range, and determine the interaction and influencing factors of multi-source alarms in the spatial dimension based on the spatial constraint factors;

[0023] According to the interaction and influencing factors of multi-source alarms in the spatial dimension, spatial coupling early warning analysis is performed on each monitoring data to obtain the second analysis result.

[0024] Preferably, the method of predicting urban security incidents and providing early warning prompts based on coupled early warning analysis results using a preset big data analysis model includes:

[0025] Determine abnormal monitoring data based on the coupled early warning analysis results and determine the target monitoring nodes corresponding to the abnormal monitoring data;

[0026] Obtain historical data of target monitoring nodes and use the preset big data analysis model to predict urban security events based on historical data through linear regression algorithm;

[0027] Determine potential safety hazard events based on the prediction results, determine the event attributes of potential safety hazard events, and determine the early warning mechanism based on the event attributes;

[0028] Determine the warning level and warning signal type according to the warning mechanism, and provide warning prompts based on the warning level and warning signal type.

[0029] A monitoring, alarm, and early warning system based on numerical analysis and coupling analysis, the system comprising:

[0030] The acquisition module is used to collect monitoring data of various industries based on urban safety development assessment from multiple data sources and pre-process them;

[0031] An alarm module is used to calculate the pre-processed monitoring data using an alarm logic formula based on static numerical analysis and dynamic numerical analysis, and determine whether to issue an alarm based on the calculation results;

[0032] The analysis module is used to determine the correlation and interaction factors of multi-source alarms according to the alarm logic formula, and perform correlation coupling warning analysis and spatial coupling warning analysis on each monitoring data based on the correlation and interaction factors;

[0033] The early warning module is used to predict urban safety incidents and provide early warning prompts based on the coupled early warning analysis results through a preset big data analysis model.

[0034] Preferably, the acquisition module includes:

[0035] The first determination submodule is used to determine multiple evaluation special indicators based on urban safety development, obtain the mapping data source of each evaluation special indicator, and determine the subordinate data industry of the mapping data source;

[0036] The collection submodule is used to determine the data format of each subordinate data industry, select data extraction technology based on the data format, and collect monitoring data from multiple data sources through data extraction technology;

[0037] The cleaning submodule is used to clean the monitoring data, obtain the cleaned data, detect the data form of the cleaned data, and determine the integrity of the cleaned data based on the data form;

[0038] The preprocessing submodule is used to perform data deduplication, missing data supplementation and invalid data removal preprocessing on the cleaned data based on the integrity of the cleaned data.

[0039] Preferably, the alarm module includes:

[0040] A second determining submodule is configured to determine static data items and dynamic data items in the preprocessed monitoring data, and define formula variable value attributes based on the static data items and the dynamic data items, wherein the formula variable value attributes include: a determined value and an uncertain value;

[0041] The first definition submodule is used to determine the monitoring indicators corresponding to the pre-processed monitoring data, determine the alarm logic based on the monitoring indicators, and define the alarm logic formula by adding variables and expressions according to the alarm logic;

[0042] The second definition submodule is used to determine the monitoring object of each monitoring indicator and define the alarm common rules and alarm individual rules based on the consistency of the monitoring object;

[0043] The alarm determination submodule is used to calculate the pre-processed monitoring data through the alarm logic formula based on the alarm common rules and alarm individual rules, determine the abnormal data according to the calculation results, and make alarm determination based on the abnormal data.

[0044] Preferably, the analysis module includes:

[0045] A third determination submodule is configured to determine a common cause of alarms from multiple sources according to an alarm logic formula, determine risk factors based on the common cause of the alarms, and determine correlations and interaction factors of the alarms from multiple sources based on the risk factors;

[0046] The first analysis submodule is used to perform correlation coupling early warning analysis on each monitoring data according to the correlation relationship and mutual factors of the multi-source alarms to obtain a first analysis result;

[0047] a fourth determination submodule, configured to determine a dynamic spatial range of multi-source alarms according to an alarm logic formula, determine an idle constraint factor according to the dynamic spatial range, and determine interactions and influencing factors of the multi-source alarms in a spatial dimension based on the spatial constraint factor;

[0048] The second analysis submodule is used to perform spatial coupling early warning analysis on each monitoring data according to the interaction and influencing factors of multi-source alarms in the spatial dimension to obtain a second analysis result.

[0049] Preferably, the early warning module includes:

[0050] A fifth determination submodule is configured to determine abnormal monitoring data based on the coupled early warning analysis result and determine a target monitoring node corresponding to the abnormal monitoring data;

[0051] The prediction submodule is used to obtain historical data of target monitoring nodes and use the preset big data analysis model to predict urban security events based on historical data through a linear regression algorithm;

[0052] a sixth determination submodule, configured to determine a potential safety hazard event according to the prediction result, determine event attributes of the potential safety hazard event, and determine an early warning mechanism based on the event attributes;

[0053] The early warning prompt submodule is used to determine the early warning level and early warning signal type according to the early warning mechanism, and to provide early warning prompts based on the early warning level and early warning signal type.

[0054] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or will be understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0055] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention.

[0057] Figure 1 This is a workflow diagram of a monitoring, alarm, and early warning method based on numerical analysis and coupling analysis provided by the present invention;

[0058] Figure 2This is a workflow diagram of a monitoring, alarm, and early warning method based on numerical analysis and coupling analysis provided by the present invention;

[0059] Figure 3 This is a structural diagram of a monitoring, alarm, and early warning system based on numerical analysis and coupling analysis provided by the present invention;

[0060] Figure 4 This is a structural diagram of an acquisition module in a monitoring, alarm, and early warning system based on numerical analysis and coupling analysis provided by the present invention. DETAILED DESCRIPTION

[0061] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all possible embodiments consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.

[0062] At present, the comprehensive evaluation of urban safety development is used to assess and measure the overall safety status of a city and the sustainability of its development. This evaluation method aims to comprehensively consider multiple key areas and factors to help urban planners, government decision-makers and other relevant stakeholders better understand the strengths and weaknesses of the city, so as to formulate effective policies and strategies to improve the safety, sustainability and quality of life of residents in the city. The field of urban safety includes more than ten industries in four major areas: urban lifeline, public safety, natural disasters, and safe production. Each industry has its own unique monitoring, alarm and early warning generation process mechanism. The monitoring, alarm and early warning generation process mechanisms of various industries have different calibers, different principles and heterogeneous data. When conducting comprehensive urban safety emergency management in the city, it is necessary to adapt the data and process mechanisms of each industry. The workload is large and complex. At the same time, the inconsistency of data standards leads to low accuracy of cross-industry coupled early warning. In order to solve the above problems, this embodiment discloses a monitoring, alarm and early warning method based on numerical analysis and coupling analysis.

[0063] A monitoring, alarm and early warning method based on numerical analysis and coupling analysis, such as Figure 1 As shown, the following steps are included:

[0064] Step S101: collecting monitoring data of various industries based on urban safety development assessment from multiple data sources and pre-processing the data;

[0065] Step S102: Calculate the pre-processed monitoring data using an alarm logic formula based on static numerical analysis and dynamic numerical analysis, and determine whether to issue an alarm based on the calculation result;

[0066] Step S103: determining the correlation relationship and interaction factor of the multi-source alarms according to the alarm logic formula, and performing correlation coupling warning analysis and spatial coupling warning analysis on each monitoring data according to the correlation relationship and interaction factor;

[0067] Step S104: Predict urban safety events and provide early warning prompts based on the coupled early warning analysis results using a preset big data analysis model.

[0068] The working principle of the above technical solution is as follows: monitoring data of various industries based on urban safety development assessment are collected from multiple data sources and preprocessed; the preprocessed monitoring data are calculated using alarm logic formulas based on static numerical analysis and dynamic numerical analysis, and whether to alarm is determined based on the calculation results; the correlation relationship and interaction factors of multi-source alarms are determined according to the alarm logic formula, and correlation coupling warning analysis and spatial coupling warning analysis are performed on each monitoring data based on the correlation relationship and interaction factors; urban safety incidents are predicted and warning prompts are issued based on the coupled warning analysis results through a preset big data analysis model.

[0069] The beneficial effects of the above technical solution are: by conducting associative coupling warning analysis and spatial coupling warning analysis, a widely applicable and fully verified alarm analysis mechanism and warning analysis mechanism can be implemented, thereby effectively improving the accuracy of alarms and the effectiveness of warnings in cross-industry, cross-organizational, and cross-regional monitoring scenarios. This solves the problem mentioned in the existing technology that due to the different calibers, different principles, and heterogeneous data of the monitoring, alarm, and warning generation process mechanisms of various industries, when conducting comprehensive urban safety emergency management in cities, it is necessary to adapt the data and process mechanisms for each industry, which is a large and complex workload. At the same time, the inconsistent data standards lead to low accuracy of cross-industry coupling warnings.

[0070] In this embodiment, after predicting urban security incidents and providing early warning prompts based on the coupled early warning analysis results using a preset big data analysis model, the following steps are also included:

[0071] Identify the correlation factors between multiple urban safety public events and construct an urban safety public event chain based on the correlation factors;

[0072] Based on the urban safety public event chain and the feedback data of each urban safety event, the random feedback consistency parameters of the pairwise related urban safety public events are determined;

[0073] A two-way feedback mechanism for pairwise related urban safety public events is formulated based on the random feedback consistency parameter, and the co-evolution state of pairwise related urban safety events is determined based on the two-way feedback mechanism.

[0074] Determine the regional common features of any city security incident in the pairwise related city security incidents based on the co-evolutionary state;

[0075] According to the regional common characteristics and the dynamic dispatch resources of any of the two-way related urban security events, the basic diffusion model of each of the two-way related urban security events is constructed;

[0076] Determine the potential probability of simultaneous occurrence of two related urban security incidents based on the basic expansion model, and confirm whether the potential probability of simultaneous occurrence is greater than or equal to the preset probability;

[0077] If so, obtain the event process parameters and event result parameters of the pairwise related city security events, and perform vulnerability correlation analysis, consequence correlation analysis, and loss correlation analysis on the pairwise related city security events based on the event process parameters and event result parameters;

[0078] Determine the event sequence correlation between two related urban security events based on the analysis results, and determine the correlation coefficient between two related urban security events based on the event sequence correlation;

[0079] Determine, based on the correlation coefficient, the correlation attributes between the two correlated urban security events, wherein the correlation attributes include: slight correlation, moderate correlation, and high correlation;

[0080] The target associated safe city event of the predicted security event is determined according to the associated attributes, the warning information of the target associated safe city event is obtained, and a synchronous warning prompt is issued.

[0081] The beneficial effects of the above technical solution are: by evaluating the event sequence correlation between pairwise related urban security events, the synchronous correlation effect can be intuitively evaluated based on the symbiotic development and evolution status between pairwise related urban security events, and then the target-related security city events that are highly correlated with the predicted security events can be objectively evaluated for early warning, so as to prevent problems before they occur and improve stability and reliability.

[0082] In one embodiment, the monitoring data of various industries based on the urban safety development assessment is collected from multiple data sources and pre-processed, including:

[0083] Identify multiple special evaluation indicators based on urban safety development, obtain the mapping data source for each special evaluation indicator, and determine the subordinate data industry of the mapping data source;

[0084] Determine the data format of each subordinate data industry, select data extraction technology based on the data format, and use data extraction technology to collect monitoring data from multiple data sources;

[0085] Perform data cleaning on monitoring data, obtain cleaned data, detect the data form of the cleaned data, and determine the integrity of the cleaned data based on the data form;

[0086] Based on the integrity of the cleaned data, the cleaned data is preprocessed by deduplication, missing data supplementation and invalid data elimination.

[0087] The beneficial effects of the above technical solution are: by collecting monitoring data through intelligent selection data extraction technology, monitoring data from various industries can be collected in an all-round way, ensuring data integrity and comprehensiveness. Furthermore, data quality can be further guaranteed by performing data preprocessing.

[0088] In one embodiment, Figure 2 As shown, the alarm logic formula based on static numerical analysis and dynamic numerical analysis is used to calculate the pre-processed monitoring data, and whether to alarm is determined according to the calculation results, including:

[0089] Step S201: determining static data items and dynamic data items in the pre-processed monitoring data, and defining formula variable value attributes based on the static data items and the dynamic data items, wherein the formula variable value attributes include: a determined value and an uncertain value;

[0090] Step S202: determining monitoring indicators corresponding to the pre-processed monitoring data, determining alarm logic based on the monitoring indicators, and defining an alarm logic formula by adding variables and expressions according to the alarm logic;

[0091] Step S203: Determine the monitoring object of each monitoring indicator, and define common alarm rules and individual alarm rules based on the consistency of the monitoring objects;

[0092] Step S204: Calculate the pre-processed monitoring data using an alarm logic formula based on the alarm common rules and the alarm individual rules, determine abnormal data based on the calculation results, and make an alarm decision based on the abnormal data.

[0093] The beneficial effects of the above technical solution are: by defining the alarm logic formula, data source anomaly judgment and alarm can be performed according to the abnormal logic of each monitoring data, thereby improving the judgment accuracy and efficiency and realizing efficient and high-precision data anomaly alarm.

[0094] In one embodiment, determining the correlation relationship and interaction factor of the multi-source alarms according to the alarm logic formula, and performing correlation coupling warning analysis and spatial coupling warning analysis on each monitoring data according to the correlation relationship and interaction factor, includes:

[0095] Determine the common cause of multiple alarm sources based on the alarm logic formula, determine the risk factors based on the common cause of the alarm, and determine the correlation and interaction factors of multiple alarm sources based on the risk factors;

[0096] Performing correlation coupling early warning analysis on each monitoring data based on the correlation relationship and mutual factors of multi-source alarms to obtain a first analysis result;

[0097] Determine the dynamic spatial range of multi-source alarms based on the alarm logic formula, determine the idle constraint factors based on the dynamic spatial range, and determine the interaction and influencing factors of multi-source alarms in the spatial dimension based on the spatial constraint factors;

[0098] According to the interaction and influencing factors of multi-source alarms in the spatial dimension, spatial coupling early warning analysis is performed on each monitoring data to obtain the second analysis result.

[0099] The beneficial effects of the above technical solution are: by determining the correlation between multi-source alarms and the interaction factors in the spatial dimension, the abnormal status of various monitoring data in the same space and related attributes can be comprehensively evaluated, and then early warning analysis can be carried out, thereby achieving more comprehensive early warning work in cross-industry, cross-organization, and cross-regional monitoring scenarios.

[0100] In one embodiment, the method of predicting urban security incidents and providing early warning prompts based on coupled early warning analysis results using a preset big data analysis model includes:

[0101] Determine abnormal monitoring data based on the coupled early warning analysis results and determine the target monitoring nodes corresponding to the abnormal monitoring data;

[0102] Obtain historical data of target monitoring nodes and use the preset big data analysis model to predict urban security events based on historical data through linear regression algorithm;

[0103] Determine potential safety hazard events based on the prediction results, determine the event attributes of potential safety hazard events, and determine the early warning mechanism based on the event attributes;

[0104] Determine the warning level and warning signal type according to the warning mechanism, and provide warning prompts based on the warning level and warning signal type.

[0105] The beneficial effect of the above technical solution is: by determining the event attributes and then determining the early warning mechanism to select the early warning signal for early warning, the staff can know the warning content and warning time at the first time and take response measures quickly and timely, thereby improving practicality.

[0106] In one embodiment, this embodiment discloses a monitoring, alarm, and early warning process mechanism based on numerical analysis and coupling analysis, specifically including:

[0107] 1. Monitoring Data Access and Processing

[0108] 1. Monitoring data access: Connect with monitoring data sources through various technologies, including API interfaces (pull and push), message queues, files, sockets, database links, etc., and be compatible with various definable data formats;

[0109] 2. Monitoring data cleaning: Clean the collected multi-source heterogeneous monitoring data to remove duplicate, missing, or invalid data. Also, perform data format conversion and standardization.

[0110] 2. Alarm Analysis Mechanism

[0111] 1. Alarm Engine: A set of services that process monitoring data in real time and output alarm data in real time. The alarm calculation logic is based on various formulas and rule definitions;

[0112] 2. Alarm logic formula: Define the alarm logic of each monitoring indicator by combining variables and expressions. Substitute the indicator values ​​in the monitoring data into the formula for calculation, and determine whether to alarm based on the calculation results.

[0113] 3. Static numerical analysis: The variables in the formula use fixed values ​​to participate in the calculation. The value of the variable is determined at the same time when the formula is defined;

[0114] 4. Dynamic numerical analysis: The variables in the formula use dynamic numerical values ​​to participate in the calculation. The value of the variable is uncertain when the formula is defined. The value of the variable can be calculated in real time through its calculation logic during alarm calculation, such as the value of the monitoring indicator in the same period of the previous month, the average value of the previous month, etc.

[0115] 5. Common rule definition: The alarm formula is defined according to the type of monitoring object / equipment. All monitoring objects or monitoring equipment of the same type use the same alarm logic formula for alarm determination.

[0116] 6. Personalized rule definition: Define a unique alarm formula for a specific monitoring object / device. This is usually used when the alarm logic is different from the common rules for the monitoring object / device type.

[0117] 7. Alarm merging rule definition: Define the merging logic for repeated alarms of the same source and type to reduce the number of repeated alarms and avoid alarm storms in specific scenarios;

[0118] 8. Definition of alarm filtering rules: Define the alarms generated by specific monitoring objects / equipment to be filtered out. For example, if some monitoring objects / equipment are identified as abnormal, the alarms they generate are all false alarms and therefore need to be filtered out.

[0119] III. Early Warning Analysis Mechanism

[0120] 1. Correlation and Coupling Analysis: By analyzing the correlation between alarms from multiple sources, considering the interactions and impacts of multiple alarms, identifying deep coupling risk factors, and exploring common causes of alarms, effective risk coupling warnings can be formed, such as warning of urban waterlogging and traffic congestion caused by heavy rainfall;

[0121] 2. Spatial coupling analysis: By analyzing multi-source alarms within a dynamic spatial range, the spatial interactions and impacts of each alarm are identified to form effective spatial coupling warnings, such as warnings for the gathering of multiple hazardous chemical transport vehicles in a small area;

[0122] 3. Alarm high-frequency analysis mechanism: Through periodic and continuity judgment rules, the root causes of high-frequency alarms are identified to form effective high-frequency risk warnings;

[0123] 4. Mechanism model calculation: Through plug-in mechanism models, early warning services are provided for different scenarios. For example, early warnings of urban waterlogging risk points can be output through rainfall process models, runoff process models, surface runoff process models, and pipe network runoff process models.

[0124] 5. Data analysis model calculation: Through the built-in big data analysis model, based on the historical data of various monitoring points, through linear regression models, decision tree models, support vector machine models, grayscale models and other models and their coupling models, it predicts possible urban safety risk events in the future and issues early warnings.

[0125] A standardized data governance foundation is used to solve the problems of data multi-source, data quality, and data heterogeneity, ensuring the data foundation for alarm and early warning calculations. Through widely applicable and fully verified alarm analysis mechanisms and early warning analysis mechanisms, the accuracy of alarms and the effectiveness of early warnings in cross-industry, cross-organizational, and cross-regional monitoring scenarios are effectively improved.

[0126] In one embodiment, this embodiment also discloses a monitoring, alarm, and early warning system based on numerical analysis and coupling analysis, such as Figure 3 As shown, the system includes:

[0127] The collection module 301 is used to collect monitoring data of various industries based on urban safety development assessment from multiple data sources and pre-process the data;

[0128] An alarm module 302 is configured to calculate the pre-processed monitoring data using an alarm logic formula based on static numerical analysis and dynamic numerical analysis, and determine whether to issue an alarm based on the calculation result;

[0129] Analysis module 303, used to determine the correlation relationship and interaction factors of multi-source alarms according to the alarm logic formula, and perform correlation coupling warning analysis and spatial coupling warning analysis on each monitoring data according to the correlation relationship and interaction factors;

[0130] The early warning module 304 is used to predict urban safety events and provide early warning prompts based on the coupled early warning analysis results through a preset big data analysis model.

[0131] The working principle and beneficial effects of the above technical solution have been explained in the method embodiment and will not be repeated here.

[0132] In one embodiment, Figure 4 As shown, the acquisition module 301 includes:

[0133] The first determination submodule 3011 is used to determine multiple evaluation indicators based on urban safety development, obtain the mapping data source of each evaluation indicator, and determine the data industry under which the mapping data source belongs;

[0134] The collection submodule 3012 is used to determine the data format of each subordinate data industry, select a data extraction technology based on the data format, and collect monitoring data from multiple data sources using the data extraction technology;

[0135] The cleaning submodule 3013 is used to clean the monitoring data, obtain the cleaned data, detect the data form of the cleaned data, and determine the integrity of the cleaned data based on the data form;

[0136] The pre-processing sub-module 3014 is used to perform data deduplication, missing data supplementation, and invalid data removal pre-processing on the cleaned data based on the integrity of the cleaned data.

[0137] In one embodiment, the alarm module includes:

[0138] A second determining submodule is configured to determine static data items and dynamic data items in the preprocessed monitoring data, and define formula variable value attributes based on the static data items and the dynamic data items, wherein the formula variable value attributes include: a determined value and an uncertain value;

[0139] The first definition submodule is used to determine the monitoring indicators corresponding to the pre-processed monitoring data, determine the alarm logic based on the monitoring indicators, and define the alarm logic formula by adding variables and expressions according to the alarm logic;

[0140] The second definition submodule is used to determine the monitoring object of each monitoring indicator and define the alarm common rules and alarm individual rules based on the consistency of the monitoring object;

[0141] The alarm determination submodule is used to calculate the pre-processed monitoring data through the alarm logic formula based on the alarm common rules and alarm individual rules, determine the abnormal data according to the calculation results, and make alarm determination based on the abnormal data.

[0142] In one embodiment, the analysis module includes:

[0143] A third determination submodule is configured to determine a common cause of alarms from multiple sources according to an alarm logic formula, determine risk factors based on the common cause of the alarms, and determine correlations and interaction factors of the alarms from multiple sources based on the risk factors;

[0144] The first analysis submodule is used to perform correlation coupling early warning analysis on each monitoring data according to the correlation relationship and mutual factors of the multi-source alarms to obtain a first analysis result;

[0145] a fourth determination submodule, configured to determine a dynamic spatial range of multi-source alarms according to an alarm logic formula, determine an idle constraint factor according to the dynamic spatial range, and determine interactions and influencing factors of the multi-source alarms in a spatial dimension based on the spatial constraint factor;

[0146] The second analysis submodule is used to perform spatial coupling early warning analysis on each monitoring data according to the interaction and influencing factors of multi-source alarms in the spatial dimension to obtain a second analysis result.

[0147] In one embodiment, the early warning module includes:

[0148] A fifth determination submodule is configured to determine abnormal monitoring data based on the coupled early warning analysis result and determine a target monitoring node corresponding to the abnormal monitoring data;

[0149] The prediction submodule is used to obtain historical data of target monitoring nodes and use the preset big data analysis model to predict urban security events based on historical data through a linear regression algorithm;

[0150] a sixth determination submodule, configured to determine a potential safety hazard event according to the prediction result, determine event attributes of the potential safety hazard event, and determine an early warning mechanism based on the event attributes;

[0151] The early warning prompt submodule is used to determine the early warning level and early warning signal type according to the early warning mechanism, and to provide early warning prompts based on the early warning level and early warning signal type.

[0152] Those skilled in the art should understand that the first and second in the present invention simply refer to different application stages.

[0153] Other embodiments of the present disclosure will readily occur to those skilled in the art after considering the specification and practicing the disclosure herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow from the general principles of the present disclosure and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, with the true scope and spirit of the present disclosure being indicated by the following claims.

[0154] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes can be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A monitoring, alarm and early warning method based on numerical analysis and coupling analysis, characterized in that: The following steps are involved: Collect and pre-process monitoring data from various industries based on urban safety development assessment from multiple data sources; Use the alarm logic formula based on static numerical analysis and dynamic numerical analysis to calculate the pre-processed monitoring data, and determine whether to alarm based on the calculation results; Determine the correlation and interaction factors of multi-source alarms based on the alarm logic formula, and conduct correlation coupling warning analysis and spatial coupling warning analysis on each monitoring data based on the correlation and interaction factors; Urban security incident prediction and early warning prompts are carried out based on the coupled early warning analysis results through the preset big data analysis model.

2. The monitoring, alarm and early warning method based on numerical analysis and coupling analysis according to claim 1 is characterized in that: The monitoring data of various industries based on the urban safety development assessment are collected from multiple data sources and pre-processed, including: Identify multiple special evaluation indicators based on urban safety development, obtain the mapping data source for each special evaluation indicator, and determine the subordinate data industry of the mapping data source; Determine the data format of each subordinate data industry, select data extraction technology based on the data format, and use data extraction technology to collect monitoring data from multiple data sources; Perform data cleaning on monitoring data, obtain cleaned data, detect the data form of the cleaned data, and determine the integrity of the cleaned data based on the data form; Based on the integrity of the cleaned data, the cleaned data is preprocessed by deduplication, missing data supplementation and invalid data elimination.

3. The monitoring, alarm and early warning method based on numerical analysis and coupling analysis according to claim 1 is characterized in that: The method of calculating the pre-processed monitoring data using an alarm logic formula based on static numerical analysis and dynamic numerical analysis and determining whether to issue an alarm based on the calculation result includes: Determine static data items and dynamic data items in the preprocessed monitoring data, and define formula variable value attributes based on the static data items and the dynamic data items, wherein the formula variable value attributes include: a determined value and an uncertain value; Determine the monitoring indicators corresponding to the pre-processed monitoring data, determine the alarm logic based on the monitoring indicators, and define the alarm logic formula by adding variables and expressions according to the alarm logic; Determine the monitoring object of each monitoring indicator, and define common alarm rules and individual alarm rules based on the consistency of the monitoring objects; Based on the alarm common rules and alarm individual rules, the pre-processed monitoring data is calculated through the alarm logic formula, the abnormal data is determined according to the calculation results, and the alarm is determined based on the abnormal data.

4. The monitoring, alarming and early warning method based on numerical analysis and coupling analysis according to claim 1 is characterized in that: The method of determining the correlation relationship and interaction factors of the multi-source alarms according to the alarm logic formula, and performing correlation coupling warning analysis and spatial coupling warning analysis on each monitoring data according to the correlation relationship and interaction factors, includes: Determine the common cause of multiple alarm sources based on the alarm logic formula, determine the risk factors based on the common cause of the alarm, and determine the correlation and interaction factors of multiple alarm sources based on the risk factors; Performing correlation coupling early warning analysis on each monitoring data based on the correlation relationship and mutual factors of multi-source alarms to obtain a first analysis result; Determine the dynamic spatial range of multi-source alarms based on the alarm logic formula, determine the idle constraint factors based on the dynamic spatial range, and determine the interaction and influencing factors of multi-source alarms in the spatial dimension based on the spatial constraint factors; According to the interaction and influencing factors of multi-source alarms in the spatial dimension, spatial coupling early warning analysis is performed on each monitoring data to obtain the second analysis result.

5. The monitoring, alarm and early warning method based on numerical analysis and coupling analysis according to claim 1 is characterized in that: The method of predicting urban safety incidents and providing early warning prompts based on the coupled early warning analysis results using a preset big data analysis model includes: Determine abnormal monitoring data based on the coupled early warning analysis results and determine the target monitoring nodes corresponding to the abnormal monitoring data; Obtain historical data of target monitoring nodes and use the preset big data analysis model to predict urban security events based on historical data through linear regression algorithm; Determine potential safety hazard events based on the prediction results, determine the event attributes of potential safety hazard events, and determine the early warning mechanism based on the event attributes; Determine the warning level and warning signal type according to the warning mechanism, and provide warning prompts based on the warning level and warning signal type.

6. A monitoring, alarm and early warning system based on numerical analysis and coupling analysis, characterized in that: The system includes: The acquisition module is used to collect monitoring data of various industries based on urban safety development assessment from multiple data sources and pre-process them; An alarm module is used to calculate the pre-processed monitoring data using an alarm logic formula based on static numerical analysis and dynamic numerical analysis, and determine whether to issue an alarm based on the calculation results; The analysis module is used to determine the correlation and interaction factors of multi-source alarms according to the alarm logic formula, and perform correlation coupling warning analysis and spatial coupling warning analysis on each monitoring data based on the correlation and interaction factors; The early warning module is used to predict urban safety incidents and provide early warning prompts based on the coupled early warning analysis results through a preset big data analysis model.

7. The monitoring, alarm, and early warning system based on numerical analysis and coupling analysis according to claim 6 is characterized in that: The acquisition module includes: The first determination submodule is used to determine multiple evaluation special indicators based on urban safety development, obtain the mapping data source of each evaluation special indicator, and determine the subordinate data industry of the mapping data source; The collection submodule is used to determine the data format of each subordinate data industry, select data extraction technology based on the data format, and collect monitoring data from multiple data sources through data extraction technology; The cleaning submodule is used to clean the monitoring data, obtain the cleaned data, detect the data form of the cleaned data, and determine the integrity of the cleaned data based on the data form; The preprocessing submodule is used to perform data deduplication, missing data supplementation and invalid data removal preprocessing on the cleaned data based on the integrity of the cleaned data.

8. The monitoring, alarm, and early warning system based on numerical analysis and coupling analysis according to claim 6 is characterized in that: The alarm module comprises: A second determining submodule is configured to determine static data items and dynamic data items in the preprocessed monitoring data, and define formula variable value attributes based on the static data items and the dynamic data items, wherein the formula variable value attributes include: a determined value and an uncertain value; The first definition submodule is used to determine the monitoring indicators corresponding to the pre-processed monitoring data, determine the alarm logic based on the monitoring indicators, and define the alarm logic formula by adding variables and expressions according to the alarm logic; The second definition submodule is used to determine the monitoring object of each monitoring indicator and define the alarm common rules and alarm individual rules based on the consistency of the monitoring object; The alarm determination submodule is used to calculate the pre-processed monitoring data through the alarm logic formula based on the alarm common rules and alarm individual rules, determine the abnormal data according to the calculation results, and make alarm determination based on the abnormal data.

9. The monitoring, alarm, and early warning system based on numerical analysis and coupling analysis according to claim 6 is characterized in that: The analysis module includes: A third determination submodule is configured to determine a common cause of alarms from multiple sources according to an alarm logic formula, determine risk factors based on the common cause of the alarms, and determine correlations and interaction factors of the alarms from multiple sources based on the risk factors; The first analysis submodule is used to perform correlation coupling early warning analysis on each monitoring data according to the correlation relationship and mutual factors of the multi-source alarms to obtain a first analysis result; a fourth determination submodule, configured to determine a dynamic spatial range of multi-source alarms according to an alarm logic formula, determine an idle constraint factor according to the dynamic spatial range, and determine interactions and influencing factors of the multi-source alarms in a spatial dimension based on the spatial constraint factor; The second analysis submodule is used to perform spatial coupling early warning analysis on each monitoring data according to the interaction and influencing factors of multi-source alarms in the spatial dimension to obtain a second analysis result.

10. The monitoring, alarm, and early warning system based on numerical analysis and coupling analysis according to claim 6, characterized in that: The early warning module includes: A fifth determination submodule is configured to determine abnormal monitoring data based on the coupled early warning analysis result and determine a target monitoring node corresponding to the abnormal monitoring data; The prediction submodule is used to obtain historical data of target monitoring nodes and use the preset big data analysis model to predict urban security events based on historical data through a linear regression algorithm; a sixth determination submodule, configured to determine a potential safety hazard event according to the prediction result, determine event attributes of the potential safety hazard event, and determine an early warning mechanism based on the event attributes; The early warning prompt submodule is used to determine the early warning level and early warning signal type according to the early warning mechanism, and to provide early warning prompts based on the early warning level and early warning signal type.

Images