Park Smart Security Business Operation and Management Methods, Systems, Equipment and Media

Abstract

This application provides a method, system, equipment, and medium for the operation and management of smart security business in a park, relating to the field of smart security technology. The method includes: acquiring real-time monitoring data of various areas within the park; generating a first security index for each area based on the real-time monitoring data; constructing a state correlation matrix between the areas; calculating correlation coefficients between the areas based on the state correlation matrix; adjusting the first and second security indices based on the correlation coefficients; generating a delay impact factor based on historical time-series correlated event data of each area; adjusting the second security index based on the delay impact factor to generate a target security index for each area; and identifying areas where the target security index is less than a preset index as target areas and generating early warning signals for these target areas. The technical effect of this application is to improve the accuracy of security early warnings.

Description

Technical Field

[0001] This application relates to the field of smart security technology, specifically to a method, system, equipment, and medium for the operation and management of smart security business in a park. Background Technology

[0002] With the rapid development of large-scale industrial parks such as modern industrial parks and chemical industrial parks, these parks encompass numerous functional areas and complex business processes. These areas are closely interconnected spatially and operationally, forming a highly integrated safety management system. The safety status of the park directly affects personnel safety, equipment integrity, and business continuity; therefore, continuous and effective safety monitoring and risk control are necessary for all areas within the park.

[0003] Currently, existing park safety management technologies mainly employ a method of directly generating safety indices based on real-time monitoring data from various areas. These indices are then compared to preset thresholds to trigger early warning signals, guiding personnel to conduct safety inspections and emergency responses in the corresponding areas. This approach can achieve a certain level of monitoring and early warning of park safety status. However, this method fails to fully consider the complex interrelationships between areas. This independent assessment method based on data from a single area cannot comprehensively reflect the true safety risk situation of the park, resulting in insufficient accuracy in safety warnings. Summary of the Invention

[0004] This application provides a method, system, and equipment for the intelligent security business operation and management of a park, which can improve the accuracy of security early warning.

[0005] Firstly, this application provides a method for the operation and management of smart security business in a park. The method includes: acquiring real-time monitoring data of each area within the park; generating a first security index for each area based on the real-time monitoring data; constructing a state correlation matrix between each area; calculating a correlation coefficient between each area based on the state correlation matrix; the correlation coefficient is used to characterize the degree of influence of the security status between each area; adjusting the first security index based on the correlation coefficient to generate a second security index for each area; acquiring historical time-series related event data for each area; generating a delayed impact factor based on the historical time-series related event data; the delayed impact factor is used to characterize the degree of delayed impact of historical security events on related areas in the time dimension; adjusting the second security index based on the delayed impact factor to generate a target security index for each area; and designating areas where the target security index is less than a preset index as target areas, generating an early warning signal for the target areas, so that operators can conduct safety inspections and risk management of the target areas based on the early warning signal.

[0006] By adopting the above technical solution, and through constructing a state correlation matrix and calculating correlation coefficients, the degree of safety status impact between different regions is accurately quantified and integrated into the adjustment process of the first safety index. The resulting second safety index is no longer an indicator that reflects the safety status of a single region in isolation, but rather a global safety assessment result that comprehensively considers the inter-regional correlation impact, thereby significantly improving the integrity and accuracy of the park's safety status assessment. Furthermore, by obtaining historical time-series correlation event data to generate a delayed impact factor, the degree of delayed impact of historical safety events on related regions in the time dimension is quantified and integrated into the adjustment of the second safety index. This ensures that the final target safety index not only reflects the current correlation impact but also fully considers the time-delay propagation effect of historical events, possessing forward-looking predictive capabilities and the ability to identify potential delayed risks in advance. The early warning signals generated based on the target safety index have higher accuracy and timeliness, providing operators with more scientific and reliable guidance for safety inspections and risk handling. This effectively avoids the problem of delayed or false alarms in safety warnings caused by ignoring regional correlation impacts and historical time-delay effects, significantly improving the accuracy of safety warnings in the park.

[0007] Secondly, this application provides a smart security business operation and management system for industrial parks, the system comprising: a first acquisition module, a construction module, a second acquisition module, a first adjustment module, and a second adjustment module; wherein, The first acquisition module is used to acquire real-time monitoring data of each area within the park, and generate a first safety index for each area based on the real-time monitoring data. The construction module is used to construct a state correlation matrix between each area, and calculate a correlation coefficient between each area based on the state correlation matrix. The correlation coefficient is used to characterize the degree of influence of the safety status between each area. Based on the correlation coefficient, the first safety index is adjusted to generate a second safety index for each area. The second acquisition module is used to acquire historical time-series related event data of each area, and generate a delayed impact factor based on the historical time-series related event data. The delayed impact factor is used to characterize the degree of lag impact of historical safety events on related areas in the time dimension. The first adjustment module is used to adjust the second safety index based on the delayed impact factor to generate a target safety index for each area. The second adjustment module is used to designate areas where the target safety index is less than a preset index as target areas, and generate an early warning signal for the target areas so that operators can conduct safety inspections and risk management of the target areas based on the early warning signal.

[0008] Thirdly, this application provides an electronic device that adopts the following technical solution: it includes a processor, a memory, a user interface, and a network interface. The memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes a computer program such as any of the above-mentioned smart security business operation and management methods for parks.

[0009] Fourthly, this application provides a computer-readable storage medium, which adopts the following technical solution: storing a computer program that can be loaded by a processor and executed by any of the above-mentioned smart security business operation and management methods for parks.

[0010] In summary, this application includes at least one of the following beneficial technical effects: By constructing a state correlation matrix and calculating correlation coefficients, the degree of safety status impact between different regions is precisely quantified and integrated into the adjustment process of the first safety index. The resulting second safety index is no longer an isolated indicator reflecting the safety status of a single region, but rather a comprehensive safety assessment result that considers the inter-regional correlation impact, thus significantly improving the integrity and accuracy of the park's safety status assessment. Furthermore, by acquiring historical time-series correlated event data to generate a delayed impact factor, the degree of delayed impact of historical safety events on related regions in the time dimension is quantified and integrated into the adjustment of the second safety index. This ensures that the final target safety index not only reflects the current correlation impact but also fully considers the time-delay propagation effect of historical events, possessing forward-looking predictive capabilities and the ability to identify potential delayed risks in advance. The early warning signals generated based on the target safety index have higher accuracy and timeliness, providing operators with more scientific and reliable guidance for safety inspections and risk management. This effectively avoids the problem of delayed or false alarms in safety warnings caused by ignoring regional correlation impacts and historical time-delay effects, significantly improving the accuracy of safety warnings in the park. Attached Figure Description

[0011] Figure 1 This is a flowchart illustrating a smart security business operation and management method for a park, as provided in an embodiment of this application. Figure 2 This is a schematic diagram of the structure of a smart security business operation and management system for a park, provided in an embodiment of this application; Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0012] Explanation of reference numerals in the attached figures: 1000, electronic device; 1001, processor; 1002, communication bus; 1003, user interface; 1004, network interface; 1005, memory. Detailed Implementation

[0013] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments.

[0014] In the description of the embodiments in this application, words such as "illustrative," "for example," or "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as "illustrative," "for example," or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or designs. Rather, the use of words such as "illustrative," "for example," or "for example" is intended to present the relevant concepts in a specific manner.

[0015] Figure 1 This is a flowchart illustrating a smart security business operation and management method for a park, as provided in an embodiment of this application. Figure 1 As shown, the method includes S101-S105: S101 acquires real-time monitoring data for each area within the park and generates a first safety index for each area based on the real-time monitoring data.

[0016] In the park's smart security business operation and management system, the first step is to acquire real-time monitoring data through various types of sensors distributed throughout the park. This serves as the foundational data source for building the security assessment system. Real-time monitoring data includes information from multiple dimensions, such as personnel density data, equipment operating status data, environmental parameter data, and abnormal behavior data. Personnel density data is obtained by using personnel positioning systems and video surveillance equipment to statistically analyze the number and distribution density of personnel in each area in real time. Equipment operating status data is collected through industrial IoT sensors to gather operating parameters, fault status, and maintenance status of key equipment. Environmental parameter data includes real-time monitoring values ​​of environmental factors such as temperature, humidity, gas concentration, and noise. Abnormal behavior data is obtained by using intelligent video analytics systems to identify abnormal actions and violations by personnel.

[0017] Since the raw real-time monitoring data originates from different types of sensing devices, resulting in variations in data format, units, and precision, preprocessing is essential to ensure the accuracy of subsequent analysis. The data preprocessing process employs a standardization algorithm to normalize various types of monitoring data, converting data with different units to the 0-1 range while removing outliers and noise interference, generating standardized monitoring data. This standardized monitoring data provides a unified data foundation for subsequent safety feature extraction and quantitative scoring.

[0018] After obtaining standardized monitoring data, the system needs to extract key safety-related feature dimensions. These safety feature dimensions refer to key indicators that reflect the safety status of a region, including dimensions such as population density, equipment health, environmental risk level, and degree of behavioral abnormality. For each safety feature dimension, the system uses a specialized quantitative scoring algorithm for calculation. For example, population density is quantified by the ratio of population density to the area's safety capacity; equipment health is comprehensively scored using equipment failure rate and performance degradation indicators; and environmental risk level is calculated by the degree to which various environmental parameters deviate from normal ranges. Through this quantitative scoring mechanism, complex multidimensional monitoring data is transformed into comparable feature score values.

[0019] Different safety feature dimensions have varying degrees of impact on the overall safety status of a region. Therefore, it is necessary to determine the feature weight coefficients corresponding to each safety feature dimension based on a pre-defined feature weight configuration table. This table is a weight allocation table established based on the experience of safety management experts and the results of historical accident analysis. Feature dimensions related to personnel safety typically have higher weight coefficients, while environmental parameter features have relatively lower weight coefficients. By performing arithmetic multiplication of the feature score value of each safety feature dimension with its corresponding feature weight coefficient, and then summing all the weighted feature values, the first safety index for each region is finally generated.

[0020] Based on the above embodiments, as an optional implementation method, in S101, generating the first security index for each region according to real-time monitoring data specifically includes S11-S14: S11, perform data preprocessing on real-time monitoring data to generate standardized monitoring data; real-time monitoring data includes at least one of personnel density data, equipment operating status data, environmental parameter data, and abnormal behavior data.

[0021] Real-time monitoring data collected by various monitoring devices in the park typically exhibits characteristics such as inconsistent data formats, significant differences in units of measurement, and substantial noise interference. Directly using this data for safety assessments can lead to inaccurate and unstable results; therefore, standardized preprocessing is necessary. The system first cleanses personnel density data, equipment operating status data, environmental parameter data, and abnormal behavior data from different sensors, removing outliers and erroneous data. Then, normalization processing is used to convert data with different units of measurement into a unified numerical range, generating standardized monitoring data. Personnel density data reflects the concentration of people in the area; equipment operating status data includes operating parameters such as temperature, pressure, and rotational speed; environmental parameter data covers environmental indicators such as temperature, humidity, gas concentration, and noise; and abnormal behavior data uses video analysis to identify personnel violations or abnormal activities.

[0022] S12, extract multiple safety feature dimensions from the standardized monitoring data, quantify and score each safety feature dimension, and generate feature score values ​​for each safety feature dimension.

[0023] Based on standardized monitoring data, the system employs feature extraction algorithms to identify and extract multiple safety feature dimensions. These dimensions refer to key indicator categories that reflect the safety status of a region, including personnel safety features, equipment safety features, environmental safety features, and behavioral safety features. The system performs independent quantitative scoring for each safety feature dimension, using expert rules, statistical models, or machine learning algorithms to convert the monitoring data for each dimension into standardized score values, generating feature score values. Feature score values ​​typically range from 0 to 100; higher values ​​indicate a better safety status for that dimension, while lower values ​​indicate a higher safety risk.

[0024] S13. Determine the feature weight coefficients corresponding to each security feature dimension according to the preset feature weight configuration table.

[0025] Different safety feature dimensions have significantly different impacts on the overall safety status of a park, requiring the determination of the importance weight of each dimension based on the park's actual situation and safety management priorities. The system queries and determines the feature weight coefficients corresponding to each safety feature dimension based on a pre-set feature weight configuration table. This feature weight configuration table is a weight allocation scheme based on factors such as park safety management experience, historical accident statistics, and industry safety standards, used to characterize the relative importance of different safety feature dimensions in comprehensive safety assessments. For example, for chemical industrial parks, equipment safety features and environmental safety features have relatively high weight coefficients; while for logistics parks, personnel safety features and behavioral safety features may have more important weight coefficients.

[0026] S14, multiply the feature score and feature weight coefficient arithmetically to generate the first security index for each region.

[0027] The system performs arithmetic multiplication of the feature scores for each safety feature dimension with their corresponding feature weight coefficients to obtain a weighted score for each dimension. Then, all weighted scores are summed to generate a first safety index for each region. This calculation method, based on multi-dimensional feature weighted fusion, comprehensively considers safety status information from multiple aspects such as personnel, equipment, environment, and behavior, avoiding the one-sidedness of single-indicator assessments. It generates more comprehensive and accurate regional safety assessment results, providing reliable basic data for subsequent correlation analysis and risk warning.

[0028] S102, construct the state correlation matrix between each region, and calculate the correlation coefficient between each region based on the state correlation matrix; the correlation coefficient is used to characterize the degree of influence of the security status between each region; adjust the first security index based on the correlation coefficient to generate the second security index for each region.

[0029] In intelligent security management of the park, the security status of each area is not independent, but rather a complex system of interconnectedness and mutual influence. Therefore, the first security index calculated based solely on real-time monitoring data of a single area cannot fully reflect the interaction between the security statuses of different areas. To construct a more accurate security assessment model, the system needs to analyze and quantify the degree of correlation and influence between different areas, and describe this complex inter-area security relationship by constructing a state correlation matrix.

[0030] The process of constructing a state association matrix first requires acquiring spatial location information and business association information for each region as basic data. Spatial location information includes spatial dimension association elements such as distance between regions, connectivity paths, and physical isolation status. Among these, distance between regions reflects the geographical proximity of adjacent regions, connectivity paths describe the physical connections and accessibility between regions, and physical isolation status indicates whether physical barriers such as firewalls or isolation doors exist between regions. Business association information includes business dimension association elements such as personnel flow relationships, material flow relationships, and operational collaboration relationships. Personnel flow relationships record the frequency and paths of staff movement between different regions, material flow relationships reflect the transfer of raw materials, products, and other materials between regions, and operational collaboration relationships describe the degree of cooperation and coordination between different regions in production or management processes.

[0031] Based on the acquired spatial location information, the system uses a distance attenuation function to calculate the distance impact value between each area. Areas that are closer together are more likely to experience security incident propagation, and their distance impact value is correspondingly larger. Simultaneously, the system calculates the path connectivity coefficient based on the number and accessibility of connecting paths; multiple accessible connecting paths indicate a stronger correlation between areas. Furthermore, the system needs to consider the impact of physical isolation, calculating an isolation correction coefficient to characterize the attenuation effect of physical isolation facilities on the transmission of security impacts. Effective physical isolation can significantly reduce the probability of security incident propagation between adjacent areas. By weighted and fused calculations of the distance impact value, path connectivity coefficient, and isolation correction coefficient, a spatial correlation coefficient between each area is generated.

[0032] In processing business-related information, the system statistically analyzes historical data on personnel and material flow relationships to calculate the frequency of personnel and material flows between different regions. Higher frequencies indicate closer business connections between regions and a greater degree of mutual influence on safety status. Based on this frequency data, the system calculates a flow association strength value to quantify the contribution of personnel and material flows to safety connections between regions. Simultaneously, the system obtains operational collaboration frequency data between regions based on operational collaboration relationships. By analyzing the closeness of cooperation between different regions in operational processes, it calculates a collaboration association strength value. Finally, the system weights and calculates the flow association strength value and the collaboration association strength value to generate a business-related degree coefficient between each region.

[0033] By weighted and fused spatial correlation coefficients and business correlation coefficients, the system generates a comprehensive correlation coefficient between each region. The comprehensive correlation coefficient is a quantitative indicator that comprehensively reflects the strength of correlation between spatial and business dimensions, and can fully describe the degree of mutual influence on the security status between regions. Based on the comprehensive correlation coefficients between all regions, the system constructs a state correlation matrix, which is an n×n square matrix (n being the total number of regions in the park). The element value in the i-th row and j-th column of the matrix represents the strength of the security status influence of the i-th region on the j-th region; the larger the matrix element value, the stronger the correlation between the corresponding regions.

[0034] After the state correlation matrix is ​​constructed, the system extracts the correlation coefficients between each region as the basis for subsequent security index adjustments. The correlation coefficients directly correspond to the element values ​​in the state correlation matrix and are used to characterize the degree of security state influence between regions. When adjusting the first security index, the system first obtains the first security index of all neighboring regions associated with each region, and then extracts the correlation coefficients between each region and its neighboring regions based on the state correlation matrix.

[0035] During the adjustment calculation process, the system multiplies the first security index of each neighboring region with its corresponding correlation coefficient to obtain the weighted security value of each neighboring region. The weighted security value reflects the contribution of the security status of neighboring regions to the target region after being weighted by correlation strength. The system sums the weighted security values ​​of all neighboring regions to generate the correlation impact value for each region. The correlation impact value is a comprehensive indicator used to characterize the overall influence of the security status of neighboring regions on each region. A larger value indicates a stronger positive impact of the good security status of neighboring regions on the target region, and vice versa.

[0036] Finally, the system integrates the first security index of each region with the corresponding associated impact value and generates the second security index of each region by weighted average or linear combination.

[0037] Based on the above embodiments, as an optional implementation method, in S102, constructing the state association matrix between each region specifically includes S21-S24: S21, Obtain spatial location information and business association information for each region; spatial location information includes at least one of the following: distance between regions, connection path, and physical isolation status; business association information includes at least one of the following: personnel flow relationship, material flow relationship, and operational collaboration relationship.

[0038] The system first needs to comprehensively acquire basic data describing the relationships between various regions. This data is mainly divided into two categories: spatial location information and business-related information. Spatial location information is the basic data describing the physical spatial relationships between regions, including key elements such as distance between regions, connectivity paths, and physical isolation status. The distance between regions is measured through the park's geographic information system and represents the physical distance between the center point or boundary of each region. Regions that are closer together are more likely to influence each other in the propagation of security incidents. Connectivity paths reflect the physical connectivity between regions, including the number, accessibility, and connection methods of connecting channels such as roads, pipelines, and ventilation systems. The more and smoother the connectivity paths, the easier it is for security impacts to be transmitted between regions. Physical isolation status describes whether there are physical isolation facilities such as firewalls, isolation doors, and security barriers between regions, as well as the isolation effect and integrity of these facilities. Effective physical isolation can effectively block or mitigate the propagation of security impacts.

[0039] Business-related information reflects the logical connections formed between regions during production and operation, mainly including dimensions such as personnel flow relationships, material flow relationships, and operational collaboration relationships. Personnel flow relationships are obtained through data sources such as personnel positioning systems, access control records, and shift schedules, and the frequency, patterns, and paths of personnel flow between regions are statistically analyzed. Regions with frequent personnel flow are more likely to spread safety risks through personnel behavior. Material flow relationships are built based on information such as material management systems, transportation records, and supply chain data, analyzing the flow of raw materials, semi-finished products, and finished products between regions. Regions with close material flow may have related impacts due to material quality issues or risks during transportation. Operational collaboration relationships are identified through production planning systems, process flow data, and collaboration records, reflecting the degree of cooperation between different regions in production processes, management processes, and emergency response. Regions with close collaboration relationships have a stronger interdependence in safety status.

[0040] S22, Calculate the spatial correlation coefficient between each region based on spatial location information; calculate the business correlation coefficient between each region based on business correlation information.

[0041] Based on acquired spatial location and business association information, the system calculates the spatial association coefficient and business association coefficient between each region. The spatial association coefficient is calculated using a multi-factor weighted model. First, a distance influence factor is calculated using a distance decay function based on inter-regional distance data. This typically employs an inverse proportional function or an exponential decay function, ensuring that regions closer to each other receive higher association scores. Next, a path connectivity factor is calculated based on connectivity path data, comprehensively considering the number, type, and accessibility of connectivity paths; regions with more and smoother paths have higher connectivity factors. Finally, an isolation decay factor is calculated based on physical isolation status; robust physical isolation facilities significantly reduce the spatial association strength between regions. By weighting the distance influence factor, path connectivity factor, and isolation decay factor, the spatial association coefficient between each region is generated.

[0042] The calculation of the business correlation coefficient focuses on analyzing the closeness and dependence of business interactions between regions. The system statistically analyzes personnel flow data to calculate the frequency and intensity of personnel flow between regions, and generates personnel correlation factors by combining information such as personnel type, responsibilities, and authority. Based on material flow data, it analyzes the frequency, quantity, and importance of material flow between regions, calculating material correlation factors. Based on operational collaboration data, it assesses the degree of collaboration and dependence between regions in production processes, management systems, and emergency plans, generating collaboration correlation factors. By comprehensively weighting the personnel correlation factor, material correlation factor, and collaboration correlation factor, the business correlation coefficient between each region is obtained.

[0043] Based on the above embodiments, as an optional implementation, in S22, the spatial correlation coefficient between each region is calculated according to the spatial location information; the calculation of the business correlation coefficient between each region according to the business correlation information specifically includes S221-S227: S221, Calculate the distance influence value between regions based on the distance between regions.

[0044] The system calculates distance impact values ​​based on physical distance data between areas. These distance impact values ​​reflect the constraining effect of physical distance on the propagation of security impacts, and are typically calculated using an inverse proportional attenuation function, meaning the distance impact value is inversely proportional to the distance between areas. The system selects appropriate attenuation model parameters based on the actual size of the park and the characteristics of security propagation, ensuring that areas with closer proximity receive higher distance impact values, while areas with greater distance receive lower values, thus accurately reflecting the fundamental role of distance factors in security correlations.

[0045] S222, Determine the path connectivity coefficient between each region based on the connected paths; the path connectivity coefficient is quantitatively calculated based on the number of paths and the path smoothness.

[0046] The system determines the path connectivity coefficient based on connectivity path information. The path connectivity coefficient is a quantitative indicator that comprehensively reflects the convenience of physical connections between areas. Its calculation requires consideration of two key factors: the number of paths and path accessibility. The number of paths is calculated as the total number of direct connections between areas, including various connection methods such as roads, pipelines, and ventilation systems. Path accessibility assesses the actual availability and transmission efficiency of these connection channels, considering factors such as channel width, capacity limitations, and the impact of obstacles. The system uses a weighted calculation to combine the number of paths and accessibility into a path connectivity coefficient; areas with more and more accessible connections receive a higher connectivity coefficient value.

[0047] S223, Based on the physical isolation status, determine the isolation correction coefficient between each area; the isolation correction coefficient is used to characterize the degree of attenuation of the security impact of physical isolation between areas.

[0048] The system determines the isolation correction coefficient based on the physical isolation status. The isolation correction coefficient quantifies the degree to which physical isolation facilities attenuate the transmission of security impacts between areas, and is a crucial parameter for correcting spatial correlation. The system analyzes the type, specifications, integrity, and effectiveness of isolation facilities such as firewalls, isolation doors, and security barriers between areas, calculating the blocking effect of these facilities on the propagation of security impacts. Effective physical isolation corresponds to a smaller isolation correction coefficient, indicating a significant attenuation of security impact transmission; while areas lacking isolation or with poor isolation effectiveness correspond to a larger correction coefficient.

[0049] S224 calculates the spatial correlation coefficient between regions by weighting the distance influence value, path connectivity coefficient, and isolation correction coefficient.

[0050] The system calculates a spatial correlation coefficient between different areas by weighting the distance influence value, path connectivity coefficient, and isolation correction coefficient. During the weighted calculation, the system assigns appropriate weight ratios to the three factors based on the park's security management characteristics and risk propagation patterns. As a comprehensive indicator that considers distance, connectivity, and isolation, the spatial correlation coefficient accurately reflects the strength of security connections between different areas based on their physical spatial relationships.

[0051] S225. Based on the relationships between personnel flow and material flow, the frequency of personnel flow and material flow between different regions is statistically analyzed, and the flow correlation strength value is calculated based on the frequency of personnel flow and material flow.

[0052] The system uses historical data on personnel and material flows to statistically analyze the frequency of personnel and material movement between different areas. Personnel flow frequency is obtained by analyzing personnel location data, access control records, and other information, tracking the number and patterns of personnel exchanges between areas within a specific time period. Material flow frequency is based on data from the material management system and transportation records, tracking the frequency and quantity of material transfers between areas. The system calculates a flow association strength value based on these statistics, which comprehensively reflects the contribution of personnel and material flows to the security relationships between areas. The flow association strength value is an important indicator for measuring the closeness of dynamic business interactions between areas; areas with higher flow frequencies have stronger security relationships.

[0053] S226. Based on the operational collaboration relationship, obtain the operational collaboration frequency data between each region, and calculate the collaboration association strength value based on the operational collaboration frequency data.

[0054] The system acquires operational collaboration frequency data between different regions based on operational collaboration relationships and calculates the collaboration strength value. Operational collaboration frequency reflects the degree of cooperation between different regions in production processes, management activities, and emergency response, and is obtained by analyzing data such as production plans, process flows, and collaboration records. The collaboration strength value quantifies the impact of inter-regional business collaboration on safety correlation; a higher collaboration frequency indicates stronger business interdependence between regions and a more significant mutual influence on safety status.

[0055] S227, The flow association strength value and the collaborative association strength value are weighted and calculated to generate the business association coefficient between each region.

[0056] The system weights the calculated flow correlation strength value and collaboration correlation strength value to generate a business correlation coefficient between each region. This coefficient comprehensively reflects the combined impact of personnel and material flow and business collaboration on inter-regional security correlations. Reasonable weighting ensures that both types of correlation factors play their due role in the comprehensive assessment.

[0057] S23, weighted and fused the spatial correlation coefficient and the business correlation coefficient to generate a comprehensive correlation coefficient between regions.

[0058] The system weights and merges the calculated spatial correlation coefficient and business correlation coefficient to generate a more comprehensive and accurate overall correlation coefficient. During the fusion process, it is necessary to reasonably determine the weight ratio of spatial correlation and business correlation. This weighting is typically based on factors such as the specific characteristics of the park, safety management priorities, and historical accident analysis. For parks with high physical hazards, such as those in the chemical and energy industries, the weight of spatial correlation may be greater, as physical distance and isolation play a decisive role in the propagation of safety impacts. Conversely, for parks primarily engaged in personnel-intensive businesses, the weight of business correlation may be more important, as personnel and business activities are the main carriers of safety risk propagation. The overall correlation coefficient, as a correlation strength indicator that integrates both spatial and business dimensions, can more objectively and comprehensively reflect the true safety correlation relationships between different areas.

[0059] S24. Based on the comprehensive correlation coefficient, construct the state correlation matrix. The element values ​​in the state correlation matrix represent the correlation strength between the corresponding regions.

[0060] The system constructs a state correlation matrix based on the calculated comprehensive correlation coefficient. This is an n×n square matrix, where n represents the total number of areas within the park. The element in the i-th row and j-th column corresponds to the comprehensive correlation coefficient between the i-th and j-th areas. A larger value indicates a stronger correlation between the two areas and a more significant mutual influence on their safety status. The state correlation matrix has clear mathematical and physical meaning. The diagonal elements are usually set to 1 or the maximum value, representing a complete correlation between an area and itself. The off-diagonal elements reflect the correlation strength between different areas, and their values ​​are usually normalized to between 0 and 1 for ease of subsequent mathematical calculations and result interpretation.

[0061] Based on the above embodiments, as an optional implementation, in S102, adjusting the first security index according to the correlation coefficient to generate the second security index for each region specifically includes S25-S28: S25, obtain the first security index of all neighboring areas associated with each area.

[0062] The system first needs to identify and acquire all neighboring regions that are related to each target region, and extract the first security index data of these neighboring regions. Neighboring regions refer to other regions that are physically adjacent to the target region, related in business processes, or mutually influential in security management. Changes in the security status of these regions may have a ripple effect on the target region. The system identifies regions with a correlation coefficient greater than a preset threshold as valid neighboring regions by querying the status correlation matrix, avoiding including distant regions with extremely low correlation in the calculation scope, thus ensuring the relevance and computational efficiency of the correlation analysis. The acquired first security index serves as the security status assessment result of each neighboring region based on its own monitoring data, providing the foundational data for subsequent correlation impact calculations.

[0063] S26. Based on the state correlation matrix, extract the correlation coefficients between each region and its neighboring regions.

[0064] Based on the constructed state association matrix, the system accurately extracts the association coefficients between each region and its neighboring regions. The association coefficient is a numerical parameter that quantifies the strength of the security association between two regions; its magnitude directly determines the weight of the impact of the security status of neighboring regions on the target region. Through matrix indexing operations, the system quickly obtains the association values ​​corresponding to the target region and each neighboring region. These values ​​comprehensively consider multiple association factors such as spatial distance, connectivity paths, physical isolation, and business interactions, accurately reflecting the actual impact of each neighboring region on the target region.

[0065] S27, multiply the first security index of each neighboring region by the corresponding correlation coefficient to obtain the weighted security value of each neighboring region; sum up the weighted security values ​​of all neighboring regions to generate the correlation impact value of each region; the correlation impact value is used to characterize the comprehensive impact of the security status of neighboring regions on each region.

[0066] The system multiplies the first security index of each neighboring region with its corresponding correlation coefficient to generate a weighted security value for each neighboring region. The weighted security value is a numerical value obtained by weighting the security status of neighboring regions based on correlation strength. It retains the security status information of neighboring regions while also reflecting the actual influence of that region on the target region. Neighboring regions with higher correlation coefficients have a more significant impact on the target region, thus receiving a larger weighted security value; while regions with lower correlation coefficients, although still having some influence, have relatively smaller weighted security values.

[0067] The system then sums the weighted security values ​​of all neighboring areas to generate the correlation impact value for each area. The correlation impact value is an aggregated index that comprehensively reflects the degree to which the security status of all neighboring areas affects the security assessment of the target area. It unifies the dispersed influences of multiple neighboring areas into a single numerical representation. The magnitude of the correlation impact value directly reflects the comprehensive degree to which the target area is affected by the security status of neighboring areas. A larger value indicates a stronger positive or negative impact of the overall security status of neighboring areas on the target area, while a smaller value indicates a relatively limited impact from neighboring areas.

[0068] S28, the first security index of each region is integrated with the associated impact value to generate the second security index of each region.

[0069] The system integrates the primary safety index of each region with its associated impact values ​​to generate a more comprehensive secondary safety index. During this integration process, the system employs mathematical methods such as weighted averaging or linear combination to reasonably balance the weighting of a region's own safety status and the influence of neighboring regions. The primary safety index reflects a region's direct safety status based on its own monitoring data, while the associated impact values ​​reflect the indirect impact of the surrounding environment on the region's safety status. The organic combination of these two factors forms a comprehensive safety assessment result that considers both internal and external factors.

[0070] S103, Obtain historical time-series related event data for each region, and generate a delayed impact factor based on the historical time-series related event data; the delayed impact factor is used to characterize the degree of delayed impact of historical security events on related regions in the time dimension.

[0071] In the practice of smart safety management in industrial parks, the impact of safety incidents is often not instantaneous but exhibits a significant time lag. That is, a safety incident occurring in one area may only have a significant impact on related areas hours or even days later. For example, equipment failure in a production area may lead to a disruption in raw material supply, which in turn affects the safety status of downstream processing areas several hours later; or inadequate safety training for personnel in one area may spread to other areas over time through personnel movement. While the second safety index considers the immediate correlation between areas, it cannot capture this time-lag pattern of safety incident propagation. Therefore, it is necessary to construct a delayed impact factor by analyzing historical time-series related event data to comprehensively assess the delayed impact of historical safety incidents on the current safety status over time.

[0072] The system first needs to acquire historical security incident records for each area as the basis for analysis. These records are event archives accumulated over time by the park's security management system, including key information dimensions such as incident occurrence time, incident type, incident severity, and scope of impact. The incident occurrence time accurately records the exact moment each security incident occurred, providing a time benchmark for time-series analysis. Incident types are categorized and labeled according to categories such as equipment failure, personnel violations, environmental anomalies, and management deficiencies; different types of incidents have different propagation characteristics and impact patterns. Incident severity is quantified using a standardized grading system, generally divided into minor, moderate, severe, and major levels, with severity directly affecting the incident's propagation range and duration. The scope of impact records the direct and indirect affected areas of each security incident, providing important evidence for identifying inter-regional relationships.

[0073] Based on historical security incident records, the system employs time-series data mining algorithms to identify historically correlated event sequences between different regions. A historically correlated event sequence refers to a causally related combination of security events occurring sequentially within a preset time window. These events typically involve a security incident in the source region triggering or influencing subsequent security incidents in related regions. The system searches historical data for event sequences that meet both temporal and spatial correlation conditions by setting reasonable time window parameters (e.g., 24 hours, 72 hours, etc.). During the identification process, the system considers not only the chronological order of events but also analyzes the logical correlation between event types and the rationality of spatial propagation to ensure that the identified correlated event sequences have a genuine causal relationship rather than being mere coincidences.

[0074] Through in-depth analysis of historical related event sequences, the system calculates time delay parameters between different regions. Time delay parameters characterize the typical time interval between the propagation of a security incident from its source region to related regions, and are a key indicator for quantifying the timeliness of event propagation. During the calculation process, the system statistically analyzes the time intervals between source and related events in similar related event sequences, and determines representative delay values ​​using statistical analysis methods (such as median and weighted average). Different types of security incidents have different propagation speeds; for example, environmental pollution incidents propagate relatively slowly, while abnormal human behavior can spread rapidly. Therefore, the system needs to calculate time delay parameters for different event types separately to improve the accuracy of delay impact assessment.

[0075] In addition to time delay characteristics, the system also needs to analyze the changing patterns of the impact intensity of security incidents during their propagation. Based on the severity and frequency data of events in historical related event sequences, the system calculates the impact attenuation coefficient between different regions. The impact attenuation coefficient characterizes the natural attenuation of the impact intensity of a security incident during its propagation over time, reflecting the objective law that the impact of an event gradually weakens over time. During the calculation, the system analyzes the comparison between the severity of the source event and related events in the related event sequence, and establishes a mathematical model of impact attenuation by statistically analyzing attenuation patterns in a large amount of historical data. Generally speaking, the longer the time interval, the greater the physical distance, and the more comprehensive the isolation measures between regions, the larger the impact attenuation coefficient, indicating a lower degree of delayed impact from historical events.

[0076] After obtaining the time delay parameter and the impact attenuation coefficient, the system comprehensively calculates these two key parameters to generate a delay impact factor for each region. The delay impact factor is a comprehensive weighting coefficient used to quantify the time-lag impact weight of historical security events on the current security assessment. The calculation formula typically uses an exponential decay function, treating the time delay parameter as the time variable, the impact attenuation coefficient as the attenuation constant, and the difference between the current time and the time of the historical event as the independent variable, to calculate the residual impact intensity of the historical event at the current moment. The larger the value of the delay impact factor, the more significant the lagging impact of the corresponding historical security event on the current security status, and the higher its weight should be given in subsequent security index adjustments.

[0077] Based on the above embodiments, as an optional implementation method, in S103, generating the delay impact factor according to historical time-series related event data specifically includes S31-S35: S31, Obtain historical security incident record data for each region; the historical security incident record data includes at least one of the following: incident occurrence time, incident type, incident severity, and incident impact range.

[0078] The system retrieves historical security incident records from the security management database for each region. This data forms the foundational information source for time-series correlation analysis. The historical security incident records include key elements such as incident occurrence time, incident type, incident severity, and incident impact scope. The incident occurrence time provides precise timestamp information for time-series analysis; the incident type reflects the nature and characteristics of the security incident; the incident severity quantifies the degree of harm and impact intensity; and the incident impact scope defines the spatial boundaries of the incident's spread. Through data cleaning and standardization, the system ensures the integrity and consistency of the historical incident data, providing a reliable data foundation for subsequent correlation analysis.

[0079] S32, based on the historical security event record data, identify the historical related event sequence between each region; the historical related event sequence includes related security events that occurred successively within a preset time window.

[0080] Based on historical security incident records, the system uses time-series mining algorithms to identify historically correlated event sequences between different regions. A historically correlated event sequence refers to a combination of security events that occur sequentially within a preset time window and have a causal relationship. These events typically demonstrate that an event in the source region triggers or influences subsequent events in the related regions. The system sets reasonable time window parameters to ensure that it can capture genuine correlations while avoiding misjudging accidental coincidences as causal relationships. By analyzing factors such as the chronological order of events, spatial distribution characteristics, and correlation of event types, the system identifies statistically significant correlated event sequences. These sequences reveal the historical patterns of security risk propagation across different regions.

[0081] S33, based on the historical sequence of related events, calculate the time delay parameter between each region; the time delay parameter represents the time interval between the propagation of a security event from the source region to the related region.

[0082] Based on the identified historical sequence of related events, the system calculates time delay parameters between different regions. These time delay parameters characterize the typical time interval between the propagation of a security event from its source region to related regions. By statistically analyzing the time difference between the source event and subsequent events in the sequence, representative delay times are determined using statistical methods such as mean, median, or probability distribution. Different types of security events and different regional relationships may correspond to different time delay characteristics. The system needs to calculate and record these differentiated delay parameters separately to provide fine-grained time characteristic data for accurate modeling.

[0083] S34. Calculate the impact attenuation coefficient between regions based on the severity and frequency of events in the historical associated event sequence. The impact attenuation coefficient is used to characterize the degree of attenuation of the impact intensity of a security event during its propagation over time.

[0084] The system calculates the impact attenuation coefficient between regions based on the severity and frequency of events in a historical sequence of related events. The impact attenuation coefficient quantifies the degree to which the intensity of a safety event's impact diminishes over time, reflecting the objective law that safety impacts gradually weaken over time. The system calculates the average impact attenuation rate by analyzing the changes in the severity of subsequent events relative to the source event in a sequence of related events, combined with statistical analysis of event frequency. The calculation of the attenuation coefficient also needs to consider the differences in attenuation characteristics between different event types; for example, environmental pollution events may have a long duration of impact, while the impact of equipment failure events may be relatively short-lived.

[0085] S35 combines the time delay parameter and the impact attenuation coefficient to generate the delay impact factor between regions; the delay impact factor is used to quantify the time delay impact weight of historical security events on the current security assessment.

[0086] The system integrates the calculated time delay parameters and impact attenuation coefficients to generate a delay impact factor for each region. The delay impact factor is a composite index that considers both time delay and impact attenuation characteristics, used to quantify the time-delayed impact weight of historical security events on the current security assessment. This factor uses mathematical modeling to unify delay time and attenuation degree into a single weight parameter, enabling the system to dynamically adjust the weight ratio of historical impacts in the current security assessment based on the time interval between the current moment and related historical events.

[0087] S104. Based on the delay impact factor, adjust the second security index to generate the target security index for each region.

[0088] While the aforementioned steps have incorporated the immediate inter-regional impacts of the second safety index, it still lacks consideration of the time-lag effects of historical safety events, failing to fully reflect the temporal continuity of safety status and the sustained influence of historical events. The actual situation of park safety management shows that the impact of certain historical safety events does not disappear immediately after the event ends, but rather has a potential impact on the safety status of related areas for a considerable period. For example, a major equipment failure that occurred in a production area three months ago, although the equipment has been repaired, may cause psychological safety concerns among workers in that area and related areas, leading to increased operational caution, or the management loopholes exposed by the accident may require a long time to fully improve. Therefore, it is necessary to further adjust the second safety index based on the delayed impact factor to generate a target safety index that can comprehensively reflect the impact of historical time lags.

[0089] The system first needs to obtain the second security index of all historically associated regions as the basis for calculation. Historically associated regions refer to areas identified in historical time-series correlation event data analysis that have a time-lag influence relationship with the target region. Security events that occurred in these regions within a certain period in the past still have a certain degree of impact on the current security status of the target region. The system determines the list of historically associated regions corresponding to each target region by querying the historical correlation event sequence database and obtains the current second security index values ​​for these historically associated regions. The second security index, as a security assessment result that already considers the immediate regional correlation impact, provides a more accurate and comprehensive basis for calculating the regional security status.

[0090] Based on the established delayed impact factor system, the system extracts the time-lag impact weights between each region and each historically related region. The time-lag impact weight is the specific value of the delayed impact factor at the current moment, reflecting the intensity of the impact of the security status of historically related regions on the current security assessment of the target region. During the extraction process, the system needs to consider the interval between the occurrence time of the historical event and the current assessment time, as well as factors such as the type and severity of the historical event, and calculates the precise time-lag impact weight through the mathematical model of the delayed impact factor. For historical associations with short time intervals and high event severity, the time-lag impact weight is relatively large; while for historical associations with long time intervals and whose event impact has largely dissipated, the time-lag impact weight approaches zero.

[0091] After obtaining the time-delayed impact weights, the system multiplies the second security index of each historically associated region with its corresponding time-delayed impact weight to obtain the time-delayed weighted security value for each historically associated region. The time-delayed weighted security value represents the actual contribution of the security status of the historically associated region to the target region after time decay and impact intensity adjustment. This weighting mechanism ensures that historically associated regions with stronger impacts receive greater weight in the final security assessment, while historical events with weaker impacts contribute less to the current assessment. During the calculation, the system also needs to consider the positive or negative nature of the security status of the historically associated regions, i.e., whether the historical security events had negative impacts or positive improvements, to ensure that the time-delayed weighted security value accurately reflects the directionality of the impact.

[0092] The system sums the time-lag weighted security values ​​of all historically related regions to generate the historical time-lag impact value for each region. This historical time-lag impact value is a comprehensive indicator used to characterize the degree of delayed impact of historical security events on the current security status of each region. The calculation of this value fully considers the combined impact of multiple historically related regions, avoiding the one-sidedness of assessing the impact of a single historical event. When the historical time-lag impact value is positive, it indicates that the combined impact of the historical event has an improving effect on the current security status; when it is negative, it indicates that the historical event still has an adverse impact on the current security status, which needs to be reflected in the final target security index.

[0093] To ensure a reasonable weighting of historical time-lag impact values ​​in the final safety index calculation, the system determines the corrective weight of these impact values ​​for the second safety index based on preset time-lag adjustment parameters. These preset time-lag adjustment parameters are weight control factors determined based on park safety management experience and historical data analysis, used to balance the importance ratio between the current safety status assessment and the impact of historical time lags. The setting of these parameters needs to consider factors such as the specific characteristics of the park, its safety management level, and the duration of the impact of historical events, ensuring that the impact of historical time lags is neither overemphasized nor ignored in the target safety index. Generally, for parks with a relatively sound safety management system and timely and effective handling of historical events, the time-lag adjustment parameters are relatively small; while for parks with a weak safety management foundation and incomplete rectification of historical problems, larger time-lag adjustment parameters are required.

[0094] Finally, the system integrates the second security index of each region with the historical time-lag impact value according to the adjusted weights to generate the target security index for each region. The integration calculation usually adopts a weighted linear combination method, that is, the target security index equals the second security index multiplied by its weight coefficient plus the historical time-lag impact value multiplied by the adjusted weight coefficient. This integration mechanism not only retains the real-time monitoring data and immediate correlation impact information contained in the second security index, but also fully incorporates the time-lag impact effect of historical security events, forming a continuous security assessment in the time dimension.

[0095] Based on the above embodiments, as an optional implementation method, in S104, adjusting the second security index according to the delay influence factor to generate the target security index for each region specifically includes S41-S45: S41, obtain the second security index of all historically associated regions related to each region.

[0096] The system first identifies and acquires all historically associated regions that have historical connections with each area, and then extracts the second security index data for these regions. Historically associated regions refer to other regions that have been associated with security incidents in the target region during a historical period. These past security incidents may have a delayed impact on the current security status of the target region. The system queries the historical associated event sequence database to identify all regions that have previously acted as sources of security incidents and affected the target region, and obtains the second security index of these historically associated regions as the basis for calculating the time-delay impact.

[0097] S42, based on the delayed impact factor, extract the time lag impact weight between each region and each historically related region.

[0098] The system extracts the time-lag impact weights between each region and each historically related region based on the delay impact factor. The time-lag impact weight is a weight parameter calculated based on the delay impact factor, used to quantify the degree of time-lag impact of the current security status of historically related regions on the target region. The system obtains the delay impact factor values ​​corresponding to the target region and each historically related region by querying the delay impact factor matrix, and dynamically calculates the time-lag impact weight based on the interval between the current time and the occurrence time of historical related events. The closer the time interval is to the typical propagation delay time of the historical event, the greater the corresponding time-lag impact weight; conversely, if the time interval deviates significantly from the delay time, the weight decreases accordingly.

[0099] S43, multiply the second security index of each historically associated region by the corresponding time-delay impact weight to obtain the time-delay weighted security value of each historically associated region; sum up the time-delay weighted security values ​​of all historically associated regions to generate the historical time-delay impact value of each region; the historical time-delay impact value is used to characterize the degree of lag impact of historical security events on the current security status of each region.

[0100] The system multiplies the second security index of each historically associated region with its corresponding time-delay influence weight to generate a time-delay-weighted security value for each region. This time-delay-weighted security value reflects the actual impact of the current security status of the historically associated region on the target region after adjustment by the time-delay influence weight. It retains the security status information of the associated regions while also reflecting the time-delay propagation characteristics under the historical association model. The system then sums the time-delay-weighted security values ​​of all historically associated regions to generate the historical time-delay influence value for each region. This historical time-delay influence value is an aggregated index that comprehensively reflects the degree to which all historically associated regions influence the current security status of the target region through the time-delay effect; it unifies multiple dispersed historical association influences into a single numerical representation.

[0101] S44, based on the preset time delay adjustment parameters, determine the correction weight of the historical time delay influence value on the second safety index.

[0102] The system determines the correction weight of historical time-lag impact values ​​on the second safety index based on preset time-lag adjustment parameters. These preset time-lag adjustment parameters are adjustment factors determined based on park safety management experience and historical data statistical analysis, used to control the weight ratio of historical time-lag impacts in the final safety assessment. The setting of the correction weights needs to balance the importance of historical impacts with the dominance of the current state, ensuring that historical time-lag impacts are reasonably reflected while avoiding over-reliance on historical data and neglecting the current actual state. The system determines the optimal correction weight configuration through parameter optimization and effect verification.

[0103] S45, the second security index of each region and the historical time lag impact value are integrated and calculated according to the corrected weight to generate the target security index of each region.

[0104] The system integrates the secondary security index of each region with historical time-lag impact values ​​according to adjusted weights to generate a target security index for each region. The integration calculation process employs mathematical methods such as weighted averaging or linear combination to organically combine the secondary security index, reflecting the current security status and associated impacts, with the historical time-lag impact values, embodying the historical time-lag effect. As the final assessment result that comprehensively considers the current status, associated impacts, and historical time lags, the target security index can more comprehensively and accurately reflect the true security risk level of each region.

[0105] S105 identifies areas in each region where the target safety index is less than the preset index as target areas and generates early warning signals for these target areas, enabling workers to conduct safety inspections and risk management of the target areas based on the early warning signals.

[0106] After obtaining the target security index for each region, the system needs to translate the security assessment results into actual security management actions. This is a crucial step for the entire intelligent security business operation and control system to achieve its practical effectiveness. Since the target security index is a numerical assessment result, security managers find it difficult to quickly identify high-risk areas requiring special attention from a large number of values. Therefore, it is necessary to establish an automated early warning mechanism based on threshold judgment to transform the security assessment results into intuitive early warning information and specific management instructions.

[0107] The system pre-sets preset index thresholds for safety assessments based on park safety management standards and historical safety incident statistical analysis. These preset indices are critical values ​​that distinguish between a good safety status and a risky situation, typically determined by a combination of factors including park safety management requirements, historical accident probabilities, and industry safety standards. The system compares the target safety index for each area with the preset index, identifying areas where the target safety index is lower than the preset index, and defining these areas as target areas. Target areas are those where the current safety assessment indicates a high risk, requiring close monitoring and timely intervention. These areas may face various safety hazards such as equipment malfunctions, personnel violations, environmental anomalies, or the continued impact of historical issues.

[0108] For identified target areas, the system automatically generates corresponding early warning signals. These signals are structured alarm messages containing key information such as area location, risk level, main risk factors, and recommended handling measures. They are pushed to relevant operational and management personnel in real time through the safety management system's communication module. During the signal generation process, the system also incorporates specific risk management recommendations for each target area, based on the target safety index, influencing factor analysis results, and historical experience in handling similar incidents. These recommendations include key safety inspection areas, emergency material preparation, and personnel evacuation plans.

[0109] Upon receiving an early warning signal, operators can promptly proceed to the target area to conduct safety inspections and risk mitigation based on the risk information and handling suggestions provided by the system. During the safety inspection, operators follow the guidance information in the early warning signal, focusing on checking equipment, the environment, and personnel that may pose safety hazards, promptly identifying and eliminating safety risks. For any actual safety issues discovered, operators can immediately take corresponding risk mitigation measures, such as equipment shutdown and maintenance, personnel safety training, and improvement of environmental conditions, thereby eliminating potential safety risks at their inception.

[0110] Based on the above method, this application also discloses a smart security business operation and management system for industrial parks, such as... Figure 2 As shown, Figure 2 This is a schematic diagram of the structure of a smart security business operation and management system for a park, provided in an embodiment of this application. The system includes: a first acquisition module, a construction module, a second acquisition module, a first adjustment module, and a second adjustment module; wherein, The first acquisition module acquires real-time monitoring data of each area within the park and generates a first safety index for each area based on the real-time monitoring data. The second acquisition module constructs a state correlation matrix between each area and calculates the correlation coefficient between each area based on the state correlation matrix. The correlation coefficient characterizes the degree of impact of safety status between areas. Based on the correlation coefficient, the first safety index is adjusted to generate a second safety index for each area. The third acquisition module acquires historical time-series related event data of each area and generates a delayed impact factor based on the historical time-series related event data. The delayed impact factor characterizes the degree of lag in the impact of historical safety events on related areas over time. The fourth adjustment module adjusts the second safety index based on the delayed impact factor to generate a target safety index for each area. The fifth adjustment module identifies areas where the target safety index is less than a preset index as target areas and generates early warning signals for these target areas, enabling workers to conduct safety inspections and risk management of the target areas based on the early warning signals.

[0111] Please see Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 3 As shown, the electronic device 1000 may include: at least one processor 1001, at least one network interface 1004, a user interface 1003, a memory 1005, and at least one communication bus 1002.

[0112] The communication bus 1002 is used to realize the connection and communication between these components.

[0113] The user interface 1003 may include a display screen and a camera. Optionally, the user interface 1003 may also include a standard wired interface and a wireless interface.

[0114] The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface).

[0115] The processor 1001 may include one or more processing cores. The processor 1001 connects to various parts of the server using various interfaces and lines, and performs various server functions and processes data by running or executing instructions, programs, code sets, or instruction sets stored in the memory 1005, and by calling data stored in the memory 1005. Optionally, the processor 1001 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor 1001 may integrate one or a combination of several of the following: Central Processing Unit (CPU), Graphics Processing Unit (GPU), and modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the content to be displayed on the screen; and the modem handles wireless communication. It is understood that the modem may also not be integrated into the processor 1001 and may be implemented as a separate chip.

[0116] The memory 1005 may include random access memory (RAM) or read-only memory. Optionally, the memory 1005 may include a non-transitory computer-readable storage medium. The memory 1005 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 1005 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-described method embodiments, etc.; the data storage area may store data involved in the above-described method embodiments, etc. Optionally, the memory 1005 may also be at least one storage device located remotely from the aforementioned processor 1001. Figure 3 As shown, the memory 1005, which serves as a computer storage medium, may include an operating system, a network communication module, a user interface module, and an application program for a smart security business operation and management method for a park.

[0117] exist Figure 3 In the electronic device 1000 shown, the user interface 1003 is mainly used to provide an input interface for the user and obtain the user input data; while the processor 1001 can be used to call the application program of a smart security business operation and management method in the memory 1005. When executed by one or more processors, the electronic device executes one or more of the methods described in the above embodiments.

[0118] An electronic device readable storage medium stores instructions that, when executed by one or more processors, cause the electronic device to perform one or more of the methods described in the above embodiments.

[0119] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0120] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0121] In the several embodiments provided in this application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some service interfaces; indirect couplings or communication connections between devices or units may be electrical or other forms.

[0122] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0123] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0124] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as USB flash drives, portable hard drives, magnetic disks, or optical disks.

[0125] The foregoing description is merely an exemplary embodiment of this disclosure and should not be construed as limiting the scope of this disclosure. Any equivalent changes and modifications made in accordance with the teachings of this disclosure shall still fall within the scope of this disclosure. Other embodiments of this disclosure will be readily apparent to those skilled in the art upon consideration of the specification and practice of the disclosure herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not described herein. The specification and embodiments are to be considered exemplary only, and the scope and spirit of this disclosure are defined by the claims.

Claims

1. A method for intelligent security business operation and management in a park, characterized in that, The method includes: acquiring real-time monitoring data of each area within the park, and generating a first safety index for each area based on the real-time monitoring data; A state correlation matrix is ​​constructed between each of the regions. Based on the state correlation matrix, correlation coefficients are calculated between each region. These correlation coefficients characterize the degree of security status impact between each region. Spatial correlation coefficients are calculated between each region based on spatial location information. Service correlation coefficients are calculated between each region based on service correlation information, including: calculating the distance impact value between regions based on inter-regional distance; determining the path connectivity coefficient between regions based on the connectivity path; the path connectivity coefficient is quantified based on the number of paths and path smoothness; path smoothness characterizes the availability and transmission efficiency of the connectivity path, and is quantified based on at least one of the following factors: channel width, capacity limitation, and obstacle impact factors of the connectivity path; and physical isolation... The system determines the isolation correction coefficient between each region; the isolation correction coefficient characterizes the attenuation degree of the security impact transmission between regions due to physical isolation; the spatial correlation coefficient between each region is generated by weighting the distance impact value, path connectivity coefficient, and isolation correction coefficient; the frequency of personnel flow and material flow between each region is statistically analyzed based on personnel flow and material flow relationships, and the flow correlation strength value is calculated based on these frequencies; the frequency of operational collaboration between each region is obtained based on operational collaboration relationships, and the collaboration correlation strength value is calculated based on this data; the business correlation coefficient between each region is generated by weighting the flow correlation strength value and the collaboration correlation strength value; and a state correlation matrix is ​​constructed based on the spatial correlation coefficient and the business correlation coefficient. Based on the correlation coefficient, the first security index is adjusted to generate a second security index for each of the regions; Historical time-series related event data for each region is acquired. Based on this data, a delay impact factor is generated. This delay impact factor characterizes the degree of delayed impact of historical security events on the related regions over time. A time delay parameter is calculated between regions based on the historical related event sequence. This time delay parameter characterizes the time interval between the propagation of a security event from the source region to the related region. An impact attenuation coefficient is calculated between regions based on the severity and frequency of events in the historical related event sequence. This impact attenuation coefficient characterizes the degree of attenuation of the impact intensity of a security event during its propagation over time. The time delay parameter and the impact attenuation coefficient are then combined to generate the delay impact factor between regions. Based on the delay impact factor, the second safety index is adjusted to generate a target safety index for each of the regions; regions where the target safety index is less than a preset index are designated as target regions, and an early warning signal for the target region is generated so that operators can conduct safety inspections and risk management of the target region based on the early warning signal.

2. The method for intelligent security business operation and management in a park according to claim 1, characterized in that, The step of generating a first safety index for each of the aforementioned regions based on the real-time monitoring data includes: preprocessing the real-time monitoring data to generate standardized monitoring data; the real-time monitoring data includes at least one of personnel density data, equipment operating status data, environmental parameter data, and abnormal behavior data; extracting multiple safety feature dimensions from the standardized monitoring data, quantifying and scoring each of the aforementioned safety feature dimensions to generate feature score values ​​for each of the aforementioned safety feature dimensions; determining the feature weight coefficients corresponding to each of the aforementioned safety feature dimensions according to a preset feature weight configuration table; and arithmetically multiplying the feature score values ​​and the feature weight coefficients to generate a first safety index for each of the aforementioned regions.

3. The method for intelligent security business operation and management in a park according to claim 1, characterized in that, The construction of the state association matrix between the regions includes: acquiring spatial location information and business association information of each region; the spatial location information includes at least one of inter-region distance, connectivity path, and physical isolation status; the business association information includes at least one of personnel flow relationship, material flow relationship, and operational collaboration relationship; calculating the spatial association coefficient between each region based on the spatial location information; calculating the business association coefficient between each region based on the business association information; weighting and fusing the spatial association coefficient and the business association coefficient to generate a comprehensive association coefficient between each region; and constructing a state association matrix based on the comprehensive association coefficient, wherein the element values ​​in the state association matrix represent the association strength between the corresponding regions.

4. The method for intelligent security business operation and management in a park according to claim 1, characterized in that, The step of adjusting the first security index according to the correlation coefficient to generate a second security index for each region includes: obtaining the first security index of all neighboring regions associated with each region; extracting the correlation coefficient between each region and each neighboring region according to the state correlation matrix; multiplying the first security index of each neighboring region by its corresponding correlation coefficient to obtain a weighted security value for each neighboring region; summing the weighted security values ​​of all neighboring regions to generate a correlation impact value for each region; the correlation impact value is used to characterize the comprehensive influence of the security status of neighboring regions on each region; and merging the first security index of each region with the correlation impact value to generate a second security index for each region.

5. The method for intelligent security business operation and management in a park according to claim 1, characterized in that, The step of generating a delay impact factor based on the historical time-series related event data includes: acquiring historical security event record data for each region; the historical security event record data includes at least one of event occurrence time, event type, event severity, and event impact range; identifying a historical related event sequence between each region based on the historical security event record data; the historical related event sequence includes related security events that occur sequentially within a preset time window.

6. The method for intelligent security business operation and management in a park according to claim 1, characterized in that, The step of adjusting the second security index according to the delay impact factor to generate a target security index for each region includes: obtaining the second security index of all historically associated regions related to each region; extracting the time-lag impact weight between each region and each historically associated region according to the delay impact factor; multiplying the second security index of each historically associated region by its corresponding time-lag impact weight to obtain a time-lag weighted security value for each historically associated region; summing the time-lag weighted security values ​​of all historically associated regions to generate a historical time-lag impact value for each region; the historical time-lag impact value is used to characterize the degree of delayed impact of historical security events on the current security status of each region; determining the correction weight of the historical time-lag impact value on the second security index according to a preset time-lag adjustment parameter; and merging the second security index of each region with the historical time-lag impact value according to the correction weight to generate a target security index for each region.

7. A smart security business operation and management system for industrial parks, characterized in that, The system includes: a first acquisition module, a construction module, a second acquisition module, a first adjustment module, and a second adjustment module; wherein, the first acquisition module is used to acquire real-time monitoring data of each area within the park, and generate a first security index for each area based on the real-time monitoring data; the construction module is used to construct a state correlation matrix between each area, and calculate the correlation coefficient between each area based on the state correlation matrix; the correlation coefficient is used to characterize the degree of influence of the security status between each area; calculate the spatial correlation coefficient between each area based on spatial location information; calculate the business correlation coefficient between each area based on business correlation information, including: calculating the business correlation coefficient between each area based on the distance between areas. The distance impact value between regions is determined; based on the connectivity path, the path connectivity coefficient between each region is determined; the path connectivity coefficient is quantified based on the number of paths and path smoothness; path smoothness is used to characterize the availability and transmission efficiency of the connectivity path, and is quantified based on at least one of the following factors: channel width, capacity limitation, and obstacle impact factor of the connectivity path; based on the physical isolation status, the isolation correction coefficient between each region is determined; the isolation correction coefficient is used to characterize the degree of attenuation of the security impact transmission between regions due to physical isolation; the distance impact value, path connectivity coefficient, and isolation correction coefficient are weighted and calculated to generate the spatial correlation coefficient between each region; based on the personnel flow relationship and material flow relationship, the spatial correlation coefficient between each region is statistically analyzed. The system calculates the flow correlation strength value based on the frequency of personnel movement and material flow; it acquires operational collaboration frequency data between regions based on operational collaboration relationships, and calculates the collaboration correlation strength value based on this data; it weights the flow correlation strength value and the collaboration correlation strength value to generate a business correlation coefficient between regions; it constructs a state correlation matrix based on the spatial correlation coefficient and the business correlation coefficient; it adjusts the first security index based on the correlation coefficient to generate a second security index for each region; the second acquisition module is used to acquire historical time-series correlation event data for each region, and generates a delay impact factor based on this data; the delay... The delayed impact factor is used to characterize the degree of delayed impact of historical security events on related regions in the time dimension; based on the historical related event sequence, the time delay parameter between each region is calculated; the time delay parameter characterizes the time interval between the propagation of a security event from the source region to the related region; according to the severity and frequency of events in the historical related event sequence, the impact attenuation coefficient between each region is calculated; the impact attenuation coefficient is used to characterize the degree of attenuation of the impact intensity of a security event during the time propagation process; the time delay parameter and the impact attenuation coefficient are comprehensively calculated to generate the delayed impact factor between each region; the first adjustment module is used to adjust the second security index according to the delayed impact factor to generate the target security index for each region;The second adjustment module is used to designate areas in each of the aforementioned regions where the target safety index is less than a preset index as target areas, and generate an early warning signal for the target areas, so that operators can conduct safety inspections and risk management in the target areas based on the early warning signal.

8. An electronic device, characterized in that, The device includes a processor, a memory, a user interface, and a network interface. The memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory to cause the electronic device to perform the method as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer program is stored that can be loaded by a processor and executed as described in any one of claims 1-6.

Images