A safe production risk dynamic mapping method, system, medium and product

Abstract

The application discloses a kind of safe production risk dynamic mapping method, system, medium and product, it is related to data processing technical field.In the method, first, according to factory layout data, risk unit is divided, its basic risk grade and spatial topological relation are determined;Second, multi-source heterogeneous safety data is standardized as risk event, and time parameter and propagation radius are extracted;Then, the time contribution coefficient and spatial propagation attenuation coefficient of risk event are calculated respectively, and then the risk propagation intensity of risk event to each unit is obtained;Subsequently, based on the intensity, determine the dominant risk contribution and heterogeneous coupling coefficient, and calculate the dynamic comprehensive risk value in combination with the basic risk grade;Finally, according to this, the dynamic risk grade of each unit is determined and risk distribution visualization rendering is carried out.The technical scheme provided in the application can improve the accuracy of safety production risk assessment in complex dynamic scene.

Description

Technical Field

[0001] This application relates to the field of data processing technology, specifically to a method, system, medium, and product for dynamic mapping of safety production risks. Background Technology

[0002] With the continuous advancement of industrialization and urbanization, the production scale of high-risk industries such as petrochemicals, energy and power, and metallurgical manufacturing is constantly expanding, and production processes are becoming increasingly complex. These industries' production plants often contain a variety of hazardous sources, including storage facilities for flammable and explosive materials, high-temperature and high-pressure reaction equipment, and toxic and hazardous chemical processing units. Once a safety accident occurs, it can not only cause significant casualties and property losses but also trigger secondary disasters and environmental pollution, posing a serious threat to public safety. To adapt to the safety management needs of different production scenarios, safety production risk assessment technology is showing a trend towards refinement and intelligence. Its accuracy and real-time performance in complex production environments are of great significance for protecting people's lives and property and promoting sustainable economic and social development.

[0003] Currently, safety risk assessment methods in industrial production mainly rely on static evaluation techniques. These techniques involve collecting basic information such as plant layout, equipment types, and material characteristics to identify hazards and assess risk levels in various areas. This fixed-state analysis-based assessment method can identify the basic hazard attributes of each risk unit and has been widely used in the field of safety production risk management.

[0004] However, due to the dynamic nature of production processes and the variability of risk factors, safety risk assessment scenarios are becoming increasingly complex and varied. In practical applications, assessment methods based on fixed-state analysis struggle to account for the interference of dynamic factors on the assessment results, and the accuracy of risk status determination is difficult to guarantee. Especially when a risk event occurs in one area and spreads to surrounding areas, the impact of the risk exhibits dynamic evolution characteristics at different times and spatial locations. Existing methods, which employ simple fixed-level assessments, are prone to deviations in the determination of the actual risk level in different areas, or even delayed identification, thereby reducing the accuracy of safety production risk assessment in complex and dynamic scenarios. Summary of the Invention

[0005] This application provides a method, system, medium, and product for dynamic mapping of safety production risks, which can improve the accuracy of safety production risk assessment in complex dynamic scenarios.

[0006] The first aspect of this application provides a method for dynamic mapping of safety production risks, including: Obtain the plant layout data, divide the plant area into risk units based on the plant layout data, and determine the basic risk level and spatial topology of the risk units; Acquire multi-source heterogeneous security data, standardize the multi-source heterogeneous security data into risk events, and determine the time parameters and propagation radius of the risk events; Calculate the time contribution coefficient of the risk event at the current moment based on the time parameter; Based on the spatial topology and the propagation radius, determine the spatial propagation attenuation coefficient of the risk event for each risk unit; By combining the time contribution coefficient and the spatial propagation attenuation coefficient, the risk propagation intensity of the risk event on each of the risk units is calculated; The dominant risk contribution and heterogeneous coupling coefficient of each risk unit are determined based on the risk propagation intensity, and the dynamic comprehensive risk value of each risk unit is calculated in combination with the basic risk level. The dynamic risk level of each risk unit is determined based on the dynamic comprehensive risk value, and the risk distribution is visualized and rendered based on the dynamic risk level.

[0007] By adopting the above technical solution, and by acquiring plant layout data and dividing it into risk units, a static risk assessment foundation including basic risk levels and spatial topological relationships is established. Based on this, by acquiring multi-source heterogeneous safety data and standardizing it into risk events, dynamic factors such as equipment status fluctuations, changes in personnel operations, and alterations in environmental conditions can be incorporated into the assessment system, overcoming the problem that existing methods struggle to suppress the interference of dynamic factors on assessment results. Furthermore, by calculating the time contribution coefficient of a risk event at the current moment based on time parameters, the evolutionary characteristics of the risk event over time can be quantified. By determining the spatial propagation attenuation coefficient of the risk event on each risk unit based on spatial topological relationships and propagation radius, the diffusion and propagation patterns of the risk event at different spatial locations can be characterized, thus accurately describing the dynamic evolutionary characteristics of risk impact in both time and space dimensions. By combining the time contribution coefficient and the spatial propagation attenuation coefficient to calculate the risk propagation intensity, the degree of impact of a risk event on a specific area at a specific moment can be comprehensively reflected, avoiding the risk level judgment bias caused by the simple fixed-level assessments used in existing methods. By determining the dominant risk contribution and heterogeneous coupling coefficient based on the risk propagation intensity, and calculating the dynamic comprehensive risk value in combination with the basic risk level, the superposition and coupling effects of multiple risk events can be accurately assessed while considering the inherent hazard attributes of the risk unit. This makes the actual risk level of each region more accurate and effectively solves the problem of identification lag that existing methods tend to have when risk events occur and spread to the surrounding areas, thereby improving the accuracy of safety production risk assessment in complex dynamic scenarios.

[0008] Optionally, the physical connectivity and physical partition information are extracted from the plant area layout data; the horizontal and vertical adjacent edges between adjacent risk units are determined based on the physical connectivity; the physical barrier attenuation weight of the horizontal adjacent edge is determined based on the physical partition information; the floor penetration attenuation coefficient of the vertical adjacent edge is determined based on the closure level of the vertical connection opening; and the horizontal adjacent edge, the vertical adjacent edge, the physical barrier attenuation weight, and the floor penetration attenuation coefficient are combined to construct the spatial topology.

[0009] Optionally, spatial location features, timestamp features, and event description features are extracted from the multi-source heterogeneous security data; the spatial location features are spatially matched with the boundary range of each risk unit to determine the source risk unit corresponding to the multi-source heterogeneous security data; based on the attributes of the source risk unit and the event description features, the multi-source heterogeneous security data is transformed into a standardized risk event, and the initial impact range of the risk event is determined; the time parameter of the risk event is determined based on the timestamp feature, and the initial impact range is adjusted in conjunction with the basic risk level of the source risk unit to obtain the propagation radius of the risk event.

[0010] Optionally, starting from the source risk unit corresponding to the risk event, the spatial topology is traversed to obtain a set of reachable risk units whose topology path length is within the propagation radius; for each target risk unit in the reachable risk unit set, the shortest topology path from the source risk unit to the target risk unit is obtained; edge attributes on the shortest topology path are extracted; and the spatial propagation attenuation coefficient of the risk event to the target risk unit is calculated based on the edge attributes.

[0011] Optionally, extract each horizontal and vertical adjacent edge on the shortest topological path; obtain the physical barrier attenuation weight corresponding to each horizontal adjacent edge and the floor penetration attenuation coefficient corresponding to each vertical adjacent edge; calculate the product of the physical barrier transmittance corresponding to each horizontal adjacent edge based on the physical barrier attenuation weight, and calculate the total floor penetration attenuation according to the number of vertical adjacent edges and the floor penetration attenuation coefficient; multiply the product by the total floor penetration attenuation to obtain the spatial propagation attenuation coefficient.

[0012] Optionally, risk events propagating to the risk unit are divided into multiple category subsets according to event type; the maximum risk propagation intensity in each category subset is extracted as the representative contribution value of the corresponding category; the maximum representative contribution value in each category subset is selected as the dominant risk contribution; the heterogeneous coupling coefficient is calculated based on the non-empty state of each category subset and a preset heterogeneous coupling amplification coefficient; the product of the dominant risk contribution and the heterogeneous coupling coefficient is compared with the basic risk level, and the maximum value is taken as the dynamic comprehensive risk value.

[0013] Optionally, the dynamic comprehensive risk value is compared with a preset risk level threshold to determine the dynamic risk level of each risk unit; the preset rendering color and preset transparency corresponding to each dynamic risk level are obtained; the floor elevation information of each risk unit is extracted from the factory layout data; according to the floor elevation information, rendering layers corresponding to each floor are constructed in ascending order; the risk units in each rendering layer are filled with the preset rendering color and preset transparency, and the layer transparency is superimposed according to the construction order of the rendering layers to output the risk distribution visualization rendering result.

[0014] Secondly, embodiments of this application provide a dynamic mapping system for safety production risks. The dynamic mapping system for safety production risks includes: one or more processors and a memory; the memory is coupled to the one or more processors and is used to store computer program code, the computer program code including computer instructions, and the one or more processors call the computer instructions to cause the dynamic mapping system for safety production risks to perform the method described in the first aspect and any possible implementation thereof.

[0015] Thirdly, embodiments of this application provide a computer-readable storage medium including instructions that, when executed on a dynamic mapping system for safety production risks, cause the dynamic mapping system for safety production risks to perform the method described in the first aspect and any possible implementation thereof.

[0016] Fourthly, embodiments of this application provide a computer program product containing instructions that, when the computer program product is run on a dynamic mapping system for safety production risks, cause the dynamic mapping system for safety production risks to execute the method described in the first aspect and any possible implementation thereof.

[0017] In summary, one or more technical solutions provided in this application have at least the following technical effects or advantages: By adopting the above technical solution, and by acquiring plant layout data and dividing it into risk units, a static risk assessment foundation including basic risk levels and spatial topological relationships is established. Based on this, by acquiring multi-source heterogeneous safety data and standardizing it into risk events, dynamic factors such as equipment status fluctuations, changes in personnel operations, and alterations in environmental conditions can be incorporated into the assessment system, overcoming the problem that existing methods struggle to suppress the interference of dynamic factors on assessment results. Furthermore, by calculating the time contribution coefficient of a risk event at the current moment based on time parameters, the evolutionary characteristics of the risk event over time can be quantified. By determining the spatial propagation attenuation coefficient of the risk event on each risk unit based on spatial topological relationships and propagation radius, the diffusion and propagation patterns of the risk event at different spatial locations can be characterized, thus accurately describing the dynamic evolutionary characteristics of risk impact in both time and space dimensions. By combining the time contribution coefficient and the spatial propagation attenuation coefficient to calculate the risk propagation intensity, the degree of impact of a risk event on a specific area at a specific moment can be comprehensively reflected, avoiding the risk level judgment bias caused by the simple fixed-level assessments used in existing methods. By determining the dominant risk contribution and heterogeneous coupling coefficient based on the risk propagation intensity, and calculating the dynamic comprehensive risk value in combination with the basic risk level, the superposition and coupling effects of multiple risk events can be accurately assessed while considering the inherent hazard attributes of the risk unit. This makes the actual risk level of each region more accurate and effectively solves the problem of identification lag that existing methods tend to have when risk events occur and spread to the surrounding areas, thereby improving the accuracy of safety production risk assessment in complex dynamic scenarios. Attached Figure Description

[0018] Figure 1 This is a flowchart illustrating the dynamic mapping method for safety production risks disclosed in the embodiments of this application; Figure 2 This is another flowchart illustrating the dynamic mapping method for safety production risks disclosed in the embodiments of this application; Figure 3 This is a schematic diagram of the structure of a system provided in an embodiment of this application.

[0019] Explanation of reference numerals in the attached drawings: 301, Central Processing Unit; 302, Read-Only Memory; 303, Random Access Memory; 304, Bus; 305, Input / Output Interface; 306, Input Section; 307, Output Section; 308, Storage Section; 309, Communication Section; 310, Driver; 311, Removable Media. Detailed Implementation

[0020] 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.

[0021] In the description of the embodiments of this application, the words "for example" or "for instance" are used to indicate examples, illustrations, or explanations. Any embodiment or design that is described as "for example" or "for instance" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design options. Rather, the use of the words "for example" or "for instance" is intended to present the relevant concepts in a specific manner.

[0022] In the description of the embodiments of this application, the term "multiple" means two or more. For example, multiple systems means two or more systems, and multiple screen terminals means two or more screen terminals. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the indicated technical features. Thus, a feature defined with "first" or "second" may explicitly or implicitly include one or more of that feature. The terms "comprising," "including," "having," and variations thereof all mean "including but not limited to," unless otherwise specifically emphasized.

[0023] This application provides a method for dynamic mapping of safety production risks, referring to... Figure 1 , Figure 1 This is a flowchart illustrating a dynamic risk mapping method for safe production provided in an embodiment of this application. The method is applied to a system, which refers to a hardware and software integrated platform capable of executing a dynamic risk mapping program for safe production. The system can execute a dynamic risk mapping program for safe production. The method includes steps 101 to 107, as follows: Step 101: Obtain the plant layout data, divide the plant area into risk units based on the plant layout data, and determine the basic risk level and spatial topology of the risk units.

[0024] In this embodiment, the plant layout data refers to digital information reflecting the physical layout of an industrial plant, including spatial layout information such as building locations, equipment distribution, pipeline routes, and partition walls. A risk unit represents a basic spatial unit divided during risk assessment; it is a relatively independent area with relatively consistent risk characteristics, such as a production workshop, tank area, or substation. The basic risk level refers to the initial risk level predetermined based on static factors such as the functional attributes of the risk unit, the hazard of materials, and the complexity of equipment; it is typically divided into low risk, medium risk, high risk, and extremely high risk levels. Spatial topology is used to represent the physical connection methods and mutual influence between risk units, including information such as adjacency, connectivity, and physical barriers.

[0025] Specifically, acquiring factory layout data includes importing factory CAD drawings, BIM models, or GIS data, and extracting spatial layout information. When dividing risk units based on this data, the physical boundaries within the factory area are first identified, such as walls, partitions, and fire compartments. Then, the space is divided into several relatively independent areas, each constituting a risk unit. Next, each risk unit is coded and its attributes are labeled, recording its spatial coordinates, area, functional type, and other basic information. When determining the basic risk level of each risk unit, factors such as the functional attributes (e.g., production area, storage area, office area), type and quantity of hazardous substances, complexity of process equipment, and historical accident records are analyzed. The initial risk level of each risk unit is quantitatively assessed by referring to safety production risk assessment standards. When establishing spatial topology relationships, the physical connectivity between adjacent risk units is first identified, marking horizontal and vertical adjacent edges. Then, information on physical partition components, such as firewalls and explosion-proof walls, is extracted. Next, the physical barrier attenuation weight of each adjacent edge is calculated to reflect the degree of influence of physical barriers on risk propagation. Finally, all edges and their weight information are integrated to construct a complete spatial topology network model.

[0026] In one possible implementation, risk units are divided based on the plant layout data, and the basic risk level and spatial topology of each risk unit are determined. This specifically includes steps 1011-1013, as follows: Step 1011: Extract the physical connectivity and physical partition information from the plant layout data; determine the horizontal and vertical adjacent edges between adjacent risk units based on the physical connectivity.

[0027] Specifically, when extracting physical connectivity and physical partition information from the factory layout data, the process begins by parsing the spatial layout layer in the CAD drawings or BIM model to identify the boundary lines and spatial partitions of each area. Then, the geometric data of physical components such as walls and partitions is extracted, including location coordinates, length, width, and height. Next, the location and dimensions of connecting components such as doors, windows, and passageways are identified. Finally, a data structure is established to store this information for subsequent analysis. When determining the horizontal and vertical adjacency edges between adjacent risk units based on physical connectivity, each risk unit is first considered a node in the topology diagram. Then, it is checked whether there are connecting facilities such as doors or passageways between adjacent risk units on the same floor. If so, a horizontal adjacency edge is established between the two risk unit nodes. Next, it is checked whether risk units on different floors are connected by vertical connecting facilities such as stairs, elevators, or pipe shafts. If so, a vertical adjacency edge is established. Finally, all horizontal and vertical adjacency edge information is integrated to form a preliminary spatial topology network structure.

[0028] Step 1012: Determine the physical barrier attenuation weight of the horizontal adjacent edges based on the information of the physical partition components.

[0029] Specifically, when determining the physical barrier attenuation weight of horizontal adjacent edges based on the information of physical partition components, the following steps are taken: First, the type of partition component between adjacent risk units is extracted from the building data, such as ordinary walls, firewalls, and explosion-proof walls. Then, the material information and thickness parameters of the partition components are obtained. Next, a preset benchmark barrier attenuation coefficient table is queried according to the partition component type to obtain the benchmark barrier attenuation coefficient for that type of partition. Then, the benchmark barrier attenuation coefficient is adjusted according to the ratio of the actual thickness of the component to the standard thickness. If there are multiple partition components between adjacent risk units (such as both walls and doors), a comprehensive barrier attenuation weight needs to be calculated. An area-weighted average method can be used to weight the barrier attenuation coefficients of each partition component according to their area ratio on the partition surface. Finally, the calculated physical barrier attenuation weight is assigned to the corresponding horizontal adjacent edge and stored as the attribute value of the edge in the spatial topology data structure.

[0030] Step 1013: Determine the floor penetration attenuation coefficient of the vertical adjacent edge based on the closure level of the vertical connected opening; combine the horizontal adjacent edge, vertical adjacent edge, physical barrier attenuation weight and floor penetration attenuation coefficient to construct the spatial topology relationship.

[0031] Specifically, when determining the floor penetration attenuation coefficient of vertical adjacent edges based on the closure level of vertical connecting openings, the type of each vertical connecting opening is first identified, such as stairwells, elevator shafts, and pipe shafts. Then, the closure status of the vertical connecting openings is checked to determine whether they are equipped with fire doors, sealed partitions, or other barrier facilities. Next, according to the closure level of the connecting openings, the corresponding benchmark floor penetration attenuation coefficient is looked up from a preset attenuation coefficient reference table. Then, the benchmark coefficient is adjusted according to factors such as the size and number of connecting openings. If there are multiple connecting openings between two vertically adjacent risk units, the overall penetration attenuation coefficient needs to be calculated comprehensively, and the minimum attenuation coefficient can be selected as the final value using a conservative principle. When constructing spatial topology relationships by combining horizontal adjacent edges, vertical adjacent edges, physical barrier attenuation weights, and floor penetration attenuation coefficients, a graph structure consisting of risk unit nodes and adjacent edges is first constructed. Then, a physical barrier attenuation weight attribute is added to each horizontal adjacent edge. Next, a floor penetration attenuation coefficient attribute is added to each vertical adjacent edge. Finally, this information is integrated into a complete spatial topology relationship data structure, which can be represented in the form of an adjacency matrix or adjacency list. The element values ​​in the matrix or table are the attenuation coefficients of the corresponding edges. If there are no edges, the values ​​are infinity or special marker values.

[0032] Step 102: Acquire multi-source heterogeneous security data, standardize the multi-source heterogeneous security data into risk events, and determine the time parameters and propagation radius of the risk events.

[0033] In this embodiment, multi-source heterogeneous security data refers to security-related information from different systems and in different formats, including but not limited to security monitoring system data, equipment fault records, security inspection records, alarm information, etc. A risk event represents a standardized security data unit, a structured expression of the original security data, containing core attributes such as event type, location, and time information. Time parameters are numerical values ​​used to quantify the temporal characteristics of a risk event, including event occurrence time, duration, and detection time, used to calculate the attenuation characteristics of risk over time. The propagation radius represents the maximum spatial impact range of a risk event, determining the farthest distance the risk impact can spread.

[0034] Specifically, acquiring multi-source heterogeneous safety data involves extracting safety-related data from different data sources such as safety production monitoring systems, equipment monitoring systems, and inspection record systems. When standardizing multi-source heterogeneous safety data into risk events, the process first involves extracting spatial location features, timestamp features, and event description features from the raw data. Then, the spatial location features are spatially matched with the boundary range of risk units within the plant area to determine the corresponding source risk unit. Next, based on the event description features and pre-defined event classification rules, the heterogeneous data is categorized into specific types of risk events, such as leakage events, abnormal temperature events, and equipment failure events. Finally, a standardized risk event structure is constructed, including attributes such as event ID, type, source risk unit, and occurrence time. When determining the time parameters of a risk event, the timestamp information of the event occurrence is extracted, and the event duration and the time difference between the current moment and the event occurrence time are calculated. When determining the propagation radius, the initial impact range is first set based on the event type and severity. Then, it is adjusted based on the basic risk level of the source risk unit; the higher the basic risk level, the larger the propagation radius. Finally, the propagation radius value is further optimized based on event characteristics (such as leakage amount, temperature exceedance degree, etc.).

[0035] In one possible implementation, connected component analysis is performed on the candidate mask to filter out the target candidate region, and the target candidate region is mapped onto the aerial image according to the scaling factor to extract a target resolution slice. Specifically, this includes steps 1021-1023, as follows: Step 1021: Extract spatial location features, timestamp features, and event description features from multi-source heterogeneous security data; spatially match the spatial location features with the boundary range of each risk unit to determine the source risk unit corresponding to the multi-source heterogeneous security data.

[0036] Specifically, when extracting spatial location features, timestamp features, and event description features from multi-source heterogeneous security data, the data structure of various data sources is first parsed to identify location information fields (such as coordinates, area names, device IDs, etc.), time information fields (such as occurrence time, recording time, duration, etc.), and event description fields (such as event type, level, cause, etc.). Then, the extracted location information is standardized, converting location information in different representations (such as text descriptions, relative coordinates, coordinates in different coordinate systems, etc.) into a unified spatial coordinate system. Next, the time information is standardized to unify time zones and time formats, resolving the issue of inconsistent timestamp precision. At the same time, the event description information is structured and standardized, converting unstructured text descriptions into structured feature vectors or standard event types. When spatially matching spatial location features with the boundary range of each risk unit, the boundary of the risk unit is first represented as a spatial geometric object (such as a polygon, polyhedron, etc.); then, the spatial location features of each safety data are used to determine whether the point is inside the polygon or to calculate spatial intersection; finally, based on the spatial matching results, each safety data is associated with its corresponding source risk unit, that is, the risk unit to which the initial location of the event occurred or was recorded belongs.

[0037] Step 1022: Based on the attributes and event description characteristics of the source risk units, transform the multi-source heterogeneous security data into standardized risk events and determine the initial impact range of the risk events.

[0038] Specifically, when transforming multi-source heterogeneous safety data into standardized risk events based on the attributes of the source risk units and the event description characteristics, the process begins by establishing a risk event type mapping rule base to map event description terms used by different sources to a predefined standard risk type system. Then, key attribute information of the source risk units is extracted, including unit type (e.g., production area, storage area, office area), contained hazards (e.g., hazardous chemicals, high-voltage equipment), and main functions. Next, combining keywords, severity indicators, and source risk unit attributes in the event description characteristics, rule matching or machine learning classification methods are used to determine the specific category and level of the event in the standardized classification system. Finally, a standardized risk event data structure is constructed, populated with fields such as event type, location, time, and severity, forming a risk event record with a unified structure and consistent semantics. When determining the initial impact range of a risk event, firstly, based on the standardized event type and severity, consult the preset impact range parameter table to obtain the baseline impact radius for that type of event; then, adjust the baseline impact radius according to the characteristics of the source risk unit (such as unit area, volume, and the quantity of hazardous substances contained therein); next, consider the amplification effect of specific risk factors within the source risk unit (such as flammable and explosive substances, hazardous processes, etc.) on the impact range; finally, calculate the numerical value or regional description representing the initial impact range of the risk event, which can be a circular area centered on the source risk unit or other shaped impact areas.

[0039] Step 1023: Determine the time parameters of the risk event based on the timestamp characteristics, and adjust the initial impact range in combination with the basic risk level of the source risk unit to obtain the propagation radius of the risk event.

[0040] Specifically, when determining the time parameters of a risk event based on timestamp features, the process begins by extracting key time points such as the event's occurrence, detection, and reporting times from the timestamp features. Then, the time delay from event occurrence to detection is calculated, reflecting the timeliness of risk discovery. Next, the duration of the event is estimated; if the original data includes an end time, the duration is directly calculated; otherwise, the possible duration is estimated from historical statistical data based on the event type and severity. Then, based on the event type and the characteristics of the source risk unit, a suitable time diffusion model, such as a linear diffusion model or an exponential diffusion model, is selected from a pre-defined time model library. Finally, by combining the above time information, the time parameters reflecting the risk's diffusion characteristics over time are calculated. When adjusting the initial impact range based on the basic risk level of the source risk unit, the following steps are taken: First, obtain the preset basic risk level of the source risk unit. This level is usually determined based on factors such as the functional type of the risk unit, the characteristics of the hazard source, and the frequency of historical risk events. Then, establish the correspondence between the basic risk level and the impact range adjustment coefficient. Generally, the higher the risk level, the larger the adjustment coefficient. Next, multiply the initial impact range by the adjustment coefficient to obtain the adjusted impact range after considering the risk level. Then, substitute the time parameter into the time diffusion model to calculate the distance that the risk may spread over the elapsed time. Finally, combine spatial diffusion and temporal diffusion to obtain the risk event propagation radius that comprehensively considers spatial characteristics, time characteristics, and the basic risk level. This radius defines the farthest distance or area that the risk may affect.

[0041] Step 103: Calculate the time contribution coefficient of the risk event at the current moment based on the time parameters.

[0042] In this embodiment, the time contribution coefficient represents the degree to which the intensity of a risk event's impact changes over time. It is a value between 0 and 1, reflecting the real-time impact of the risk event at the current moment. The closer the time contribution coefficient is to 1, the higher the intensity of the risk event's time impact; the closer it is to 0, the lower the intensity of the risk event's time impact. The calculation of the time contribution coefficient typically considers factors such as the event type, the difference between the occurrence time and the current time, and the event's duration. Different types of risk events may have different time decay characteristics.

[0043] Specifically, when calculating the time contribution coefficient of a risk event at the current moment based on time parameters, the occurrence time of the risk event and the current system time are first obtained, and the time difference between the two is calculated. Then, based on the type of risk event, the applicable time decay function is determined. Different types of risk events may use different decay modes (such as linear decay, exponential decay, step decay, etc.). Next, the time difference is substituted into the selected time decay function to calculate the time contribution coefficient. For transient events (such as sudden equipment failure), a fast decay function is usually used; for persistent events (such as continuous leakage), a slow decay function is used. When the calculated time contribution coefficient is less than a preset threshold, it can be determined that the impact of the risk event on the current risk status is negligible. The calculation result of the time contribution coefficient will serve as an important input parameter for subsequent risk propagation intensity calculations.

[0044] Step 104: Based on spatial topology and propagation radius, determine the spatial propagation attenuation coefficient of risk events for each risk unit.

[0045] In this embodiment, the spatial propagation attenuation coefficient refers to the degree of attenuation of the impact intensity of a risk as it propagates from a source risk unit to a target risk unit. It is a value between 0 and 1, reflecting the blocking effect of spatial distance and physical barriers on risk propagation. The closer the spatial propagation attenuation coefficient is to 1, the smaller the risk propagation attenuation; the closer it is to 0, the greater the risk propagation attenuation, meaning the risk is difficult to propagate to the target unit. The calculation of the spatial propagation attenuation coefficient needs to consider factors such as topological distance, physical barriers, and spatial structure.

[0046] Specifically, when determining the spatial propagation attenuation coefficient of a risk event for each risk unit based on spatial topology and propagation radius, the process begins by using the source risk unit corresponding to the risk event as the starting node. A breadth-first or depth-first traversal is performed within the established spatial topology network to identify all reachable risk units whose topological path length is within the propagation radius. Then, for each reachable risk unit, the shortest topological path from the source risk unit to that unit is calculated, and the attribute information of all edges on the path is extracted, including the physical barrier attenuation weight of horizontally adjacent edges and the floor penetration attenuation coefficient of vertically adjacent edges. Next, the attenuation effects of horizontal and vertical propagation are processed separately. For horizontally adjacent edges, the physical barrier transmittance of each edge is multiplied to obtain the total attenuation effect of horizontal propagation. For vertically adjacent edges, the total attenuation effect of vertical propagation is calculated based on the floor penetration attenuation coefficient and the number of layers of vertical propagation. Finally, the horizontal propagation attenuation and vertical propagation attenuation are multiplied to obtain the spatial propagation attenuation coefficient of the risk event from the source risk unit to the target risk unit. For risk units exceeding the propagation radius, their spatial propagation attenuation coefficient is directly set to 0, indicating that the risk impact cannot propagate to that area.

[0047] Step 105: Combine the time contribution coefficient and the spatial propagation attenuation coefficient to calculate the risk propagation intensity of the risk event to each risk unit.

[0048] In this embodiment, risk propagation intensity refers to the actual impact of a risk event on a specific risk unit after comprehensively considering time and space factors, and is a key indicator for assessing dynamic risk status. Risk propagation intensity is typically a function of the time contribution coefficient and the spatial propagation attenuation coefficient; a larger value indicates a more significant impact of the risk event on the target unit, making it an important input parameter for subsequent calculation of dynamic risk values. Risk propagation intensity integrates the time attenuation characteristics and spatial propagation characteristics of risk events, comprehensively reflecting the dynamic changes in risk impact.

[0049] Specifically, when calculating the risk propagation intensity of a risk event on each risk unit by combining the time contribution coefficient and the spatial propagation attenuation coefficient, the time contribution coefficient of the risk event is first obtained, reflecting its current timeliness. Then, for each target risk unit within the propagation radius, its corresponding spatial propagation attenuation coefficient is extracted. Next, the time contribution coefficient and the spatial propagation attenuation coefficient are multiplied to obtain the spatiotemporal comprehensive attenuation effect. Finally, the spatiotemporal comprehensive attenuation effect is multiplied by the initial intensity value of the risk event to calculate the risk propagation intensity of the risk event on that target risk unit. The initial intensity value of the risk event can be predetermined based on the event type and severity. For the source risk unit itself, its spatial propagation attenuation coefficient is usually set to 1; therefore, its risk propagation intensity is mainly determined by the time contribution coefficient and the initial intensity of the event. For each risk unit, the propagation intensity of all risk events affecting that unit needs to be calculated, and this information is stored as a risk propagation intensity list for that risk unit, providing a data foundation for subsequent comprehensive risk assessment.

[0050] Step 106: Determine the dominant risk contribution and heterogeneous coupling coefficient of each risk unit based on the risk propagation intensity, and calculate the dynamic comprehensive risk value of each risk unit in combination with the basic risk level.

[0051] In this embodiment, the dominant risk contribution represents the contribution value of the type of risk event that has the greatest impact on the risk unit, reflecting the main source of risk. The heterogeneous coupling coefficient refers to the amplification effect coefficient generated when multiple different types of risks coexist, used to quantify the interaction between different types of risks. The dynamic comprehensive risk value is a quantitative representation of the current actual risk level of the risk unit after comprehensively considering the basic risk level, the dominant risk contribution, and the heterogeneous coupling effect; it is the final calculation result of the dynamic risk assessment.

[0052] Specifically, when determining the dominant risk contribution and heterogeneous coupling coefficient of each risk unit based on the risk propagation intensity, all risk events propagating to the risk unit are first grouped by event type, forming multiple category subsets, such as equipment failure, leakage, and fire. Then, within each category subset, the event with the highest risk propagation intensity is selected as the representative contribution value for that category. Next, the maximum value among all representative contribution values ​​is selected as the dominant risk contribution of the risk unit. When calculating the heterogeneous coupling coefficient, the number of different types of risk events that have a substantial impact on the unit (i.e., the risk propagation intensity exceeds a specific threshold) is counted. Based on the number of affected risk types and a preset heterogeneous coupling amplification coefficient, the heterogeneous coupling effect is calculated. A specific calculation method could be a basic coefficient plus the increment corresponding to each additional risk type. When calculating the dynamic comprehensive risk value in conjunction with the basic risk level, the dominant risk contribution is multiplied by the heterogeneous coupling coefficient to obtain the dynamic risk factor. Then, the dynamic risk factor is compared with the value corresponding to the basic risk level, and the larger of the two is taken as the dynamic comprehensive risk value of the risk unit. This ensures that the risk assessment considers both the inherent hazards of the risk unit and the impact of current dynamic risk events.

[0053] In one possible implementation, the dominant risk contribution and heterogeneous coupling coefficient of each risk unit are determined based on the risk propagation intensity, and the dynamic comprehensive risk value of each risk unit is calculated in conjunction with the basic risk level. Specifically, this includes steps 1061-1062, as follows: Step 1061: Divide the risk events that propagate to the risk unit into multiple category subsets according to the event type; extract the maximum risk propagation intensity in each category subset as the representative contribution value of the corresponding category.

[0054] Specifically, when dividing risk events propagating to a risk unit into multiple category subsets based on event type, the process first involves obtaining a list of all risk events propagating to that risk unit. Then, based on the standardized type attributes of each risk event, these events are categorized into different category subsets, such as predefined risk categories like fire, explosion, leakage, and mechanical injury. Next, the risk events in each category subset are iterated through, and the propagation intensity value of each risk event on the current risk unit is extracted. This value is typically determined by factors such as the severity of the risk event, its distance from the current risk unit, and propagation attenuation. Finally, the largest propagation intensity value is identified from each non-empty category subset and set as the representative contribution value for that category, representing the maximum impact of that type of risk on the current risk unit.

[0055] Step 1062: Select the largest representative contribution value in each category subset as the dominant risk contribution; calculate the heterogeneous coupling coefficient based on the non-empty state of each category subset and the preset heterogeneous coupling amplification coefficient; compare the product of the dominant risk contribution and the heterogeneous coupling coefficient with the basic risk level, and take the maximum value as the dynamic comprehensive risk value.

[0056] Specifically, when selecting the largest representative contribution value from each category subset as the dominant risk contribution, the representative contribution values ​​of all non-empty category subsets are compared, and the maximum value is selected as the dominant risk contribution. This value represents the contribution of the risk type that has the greatest impact on the current risk unit. Then, the heterogeneous coupling coefficient is calculated based on the non-empty state of each category subset and the preset heterogeneous coupling amplification coefficient. The specific method is as follows: First, count the number n of non-empty category subsets, representing the number of risk types currently affecting the risk unit; then, look up the amplification coefficient corresponding to the simultaneous existence of n different types of risks from the preset heterogeneous coupling amplification coefficient table; if multiple types of risks exist simultaneously, this coefficient is usually greater than 1, reflecting the coupling amplification effect when multiple risks coexist. Multiply the dominant risk contribution by the heterogeneous coupling coefficient to obtain the risk value after considering the coupling effect; at the same time, obtain the basic risk level of the risk unit, which represents the inherent risk level of the risk unit itself; finally, compare the calculated product with the basic risk level, and take the larger of the two as the dynamic comprehensive risk value of the risk unit, ensuring that the dynamic comprehensive risk value is not lower than the basic risk level of the risk unit.

[0057] Step 107: Determine the dynamic risk level of each risk unit based on the dynamic comprehensive risk value, and perform risk distribution visualization rendering based on the dynamic risk level.

[0058] In this embodiment, the dynamic risk level represents the result of discretizing and classifying the dynamic comprehensive risk value according to a preset grading standard, typically divided into low risk, medium risk, high risk, and extremely high risk levels, facilitating risk management and decision-making. Risk distribution visualization rendering refers to the process of visually displaying the dynamic risk level graphically, including techniques such as color coding, transparency settings, and layered display. The aim is to intuitively present the risk distribution in various areas of the plant, supporting safety management decisions.

[0059] Specifically, when determining the dynamic risk level of each risk unit based on the dynamic comprehensive risk value, a preset risk level classification threshold is first obtained. These thresholds divide the continuous risk value space into several discrete level intervals. Then, the dynamic comprehensive risk value of each risk unit is compared with these thresholds to determine its dynamic risk level. When performing risk distribution visualization rendering based on dynamic risk levels, a mapping relationship between risk levels and rendering parameters is first established, including color codes corresponding to different risk levels (e.g., green for low risk, yellow for medium risk, orange for high risk, and red for extremely high risk) and transparency parameters. Then, the geometric shape and floor elevation information of each risk unit are extracted from the plant layout data. Next, rendering layers corresponding to each floor are constructed sequentially according to the floor elevation from low to high. Then, for each risk unit in the rendering layer, the corresponding rendering color and transparency are applied to fill it according to its dynamic risk level. Finally, all rendering layers are superimposed and displayed in elevation order to achieve a three-dimensional visualization effect of multi-floor risk distribution. In addition, a timeline control can be added to support the dynamic display of risk status changes over time, or an interactive query function can be provided, allowing users to select a specific risk unit to view detailed risk information.

[0060] In one possible implementation, the dynamic risk level of each risk unit is determined based on the dynamic comprehensive risk value, and the risk distribution is visualized and rendered based on the dynamic risk level. Specifically, this includes steps 1071-1073, as follows: Step 1071: Compare the dynamic comprehensive risk value with the preset risk level threshold to determine the dynamic risk level of each risk unit; obtain the preset rendering color and preset transparency corresponding to each dynamic risk level.

[0061] Specifically, when comparing the dynamic comprehensive risk value with preset risk level thresholds, a pre-defined set of risk level thresholds is first obtained. This set contains multiple threshold points, such as [T0, T1, T2, T3], used to divide the risk value range into multiple level intervals. Then, the dynamic comprehensive risk value V of each risk unit is compared. If V is less than T1, it is determined to be a low-risk level; if V is greater than or equal to T1 and less than T2, it is determined to be a medium-risk level; if V is greater than or equal to T2 and less than T3, it is determined to be a high-risk level; and if V is greater than or equal to T3, it is determined to be an extremely high-risk level. In this way, each risk unit is assigned a corresponding dynamic risk level. Next, based on the determined dynamic risk level, the corresponding preset rendering color and preset transparency parameters are looked up and obtained from a pre-configured mapping table. For example, low risk might correspond to green and high transparency, while extremely high risk might correspond to red and low transparency. These rendering parameters will be used in subsequent risk distribution visualization rendering processing.

[0062] Step 1072: Extract the floor elevation information of each risk unit from the factory layout data; based on the floor elevation information, construct the corresponding rendering layers for each floor in ascending order.

[0063] Specifically, when extracting floor elevation information for each risk unit from the factory layout data, all risk unit data recorded in the system is traversed, and the floor attribute or elevation value attribute of each risk unit is read. If the risk unit data does not directly contain floor information, the floor elevation is obtained indirectly based on its spatial coordinate height value or through associated building information. Then, all risk units are grouped according to their floor elevation values, forming multiple floor groups, each containing all risk units on the same floor. Next, based on this floor elevation information, all floors in the entire factory area are determined and sorted in ascending order of elevation. Finally, according to the sorted floor order, a corresponding rendering layer is constructed for each floor, and each rendering layer contains the geometric shape and location data of all risk units on that floor, preparing for subsequent risk rendering.

[0064] Step 1073: Fill the risk units in each rendering layer with preset rendering colors and preset transparency, and calculate the layer transparency overlay according to the construction order of the rendering layers to output the risk distribution visualization rendering result.

[0065] Specifically, when filling risk units in each rendering layer with preset rendering colors and preset transparency, all risk units in each rendering layer are traversed, and the preset rendering colors and preset transparency parameters corresponding to the dynamic risk level of that risk unit are applied to the geometric area of ​​that risk unit. Specific operations include setting the fill color of the risk unit area to the preset rendering color and setting the transparency of the area to the preset transparency. After filling all risk units, layers are overlaid according to the construction order of the rendering layers (i.e., from low to high floors). During the overlay process, for areas with spatial overlap, the display effect after overlay needs to be calculated. The calculation method is as follows: for each pixel in the overlapping area, the final display color is calculated using a transparency blending algorithm based on the color and transparency values ​​of the upper and lower layers. A typical blending algorithm considers the color and transparency of each layer, allowing the upper layer content to partially show through the lower layer content, creating a three-dimensional effect. After completing the overlay calculation of all layers, the final comprehensive rendering image is generated. This image contains the risk status information of all floor risk units, as well as the three-dimensional layered representation achieved through transparency processing, constituting a complete risk distribution visualization rendering result, which is then output for display or further processing.

[0066] In the above embodiments, the risk status quantification and hierarchical assessment of risk units are achieved through dynamic comprehensive risk value calculation and risk level classification. To further enhance the intuitive presentation of risk distribution and improve the spatial perception ability of risk management personnel regarding the risk situation in multi-story factory areas, this application also provides a dynamic mapping method for safety production risks. This method establishes a color model for risk representation through the mapping relationship between risk level and visual coding, constructs a three-dimensional rendering layer system by combining floor elevation information, and uses a transparency overlay algorithm to achieve synchronous display of risk distribution on different floors, enabling the system to comprehensively present the overall situation and local details of risk distribution within the factory area while maintaining spatial hierarchy. The following section will combine... Figure 2 The method for dynamic mapping of safety production risks in the embodiments of this application is described as follows: Please see Figure 2 This is another flowchart illustrating a different dynamic mapping method for safety production risks in this application.

[0067] Step 201: Starting from the source risk unit corresponding to the risk event, traverse the spatial topology to obtain the set of reachable risk units whose topological path length is within the propagation radius.

[0068] Specifically, taking the source risk unit corresponding to the risk event as the starting node, when traversing the spatial topology, the source risk unit where the risk event occurred is first determined as the starting point of the traversal, and the propagation radius is set as a constraint condition for the traversal. Then, a breadth-first search algorithm is used to traverse the spatial topology network outward from the source risk unit, recording the topological path length from each visited node (risk unit) to the source node. During the traversal, a queue and a set of visited nodes are maintained. Initially, the source risk unit is added to the queue and marked as visited; then, the following operations are repeated: a node is taken from the queue, and all adjacent nodes directly connected to that node are obtained; for each unvisited adjacent node, its topological path length to the source node is calculated; if this length does not exceed the set propagation radius, the adjacent node is added to the queue and marked as visited. When the queue is empty, the traversal ends. At this time, all nodes in the set of visited nodes, except for the source risk unit, constitute the set of reachable risk units, which are all units that the risk event may affect.

[0069] Step 202: For each target risk unit in the set of reachable risk units, obtain the shortest topological path from the source risk unit to the target risk unit.

[0070] Specifically, for each target risk unit in the reachable risk unit set, the shortest topological path from the source risk unit to the target risk unit is calculated using either Dijkstra's shortest path algorithm or the A* algorithm. For each target risk unit, starting from the source risk unit, the shortest path to that target risk unit is searched in the spatial topological network. During the algorithm, a priority queue is maintained to store nodes to be processed, and a distance mapping table records the current shortest distance from the source node to each node. Initially, the source node is added to the queue, and its distance is set to 0; the distances of other nodes are set to infinity. Then, the following operations are repeated: the node with the smallest distance is taken from the priority queue, and all its adjacent nodes are checked; for each adjacent node, the new distance to that adjacent node through the current node is calculated; if the new distance is less than the recorded distance, the distance of that adjacent node is updated, and the node is added to the priority queue, while the predecessor node is recorded. After the target risk unit has been processed, the shortest topological path from the source risk unit to the target risk unit can be constructed by backtracking from the predecessor node record. Repeat this process for each target risk unit in the set of reachable risk units to obtain all shortest topological paths.

[0071] Step 203: Extract the edge attributes on the shortest topological path; calculate the spatial propagation attenuation coefficient of the risk event to the target risk unit based on the edge attributes.

[0072] Specifically, when extracting edge attributes from the shortest topological path, the determined shortest topological path from the source risk unit to the target risk unit is traversed, visiting each edge on the path sequentially, and obtaining the attribute information of these edges from the spatial topological relationship data, including the edge's physical length, propagation impedance coefficient, and edge type. Then, the spatial propagation attenuation coefficient of the risk event to the target risk unit is calculated based on the extracted edge attributes. The calculation method is usually based on a propagation attenuation model, considering the cumulative effect of all edges on the path. First, the single-edge attenuation value is calculated for each edge on the path according to its attributes, considering the product of the edge's physical length and the standard attenuation rate, and then adjusted by the propagation impedance coefficient specific to the edge type. Then, the attenuation values ​​of all edges on the path are accumulated and calculated, using a product method or other composite methods, to obtain the overall spatial propagation attenuation coefficient from the source risk unit to the target risk unit. This coefficient reflects the degree of attenuation when a risk event propagates along the shortest topological path to the target risk unit; the smaller the value, the more severe the attenuation and the smaller the impact.

[0073] In one possible implementation, the spatial propagation attenuation coefficient of the risk event to the target risk unit is calculated based on the edge attributes, specifically including steps 2031-2033, as follows: Step 2031: Extract all horizontal and vertical adjacent edges on the shortest topological path.

[0074] Specifically, when extracting the horizontal and vertical adjacent edges on the shortest topological path, the calculated shortest topological path from the source risk unit to the target risk unit is first obtained. This path consists of a series of nodes (risk units) and edges connecting these nodes. Then, all edges on this path are traversed and classified according to the edge's attributes or the spatial relationship between the two risk units it connects. If the two risk units connected by an edge are located on the same floor (i.e., the two units have the same elevation attribute), the edge is classified as a horizontal adjacent edge; if the two risk units connected by an edge are located on different floors (i.e., the two units have different elevation attributes), the edge is classified as a vertical adjacent edge. After classifying each edge on the path, two sets are formed: a set of horizontal adjacent edges and a set of vertical adjacent edges. These two sets contain all edges on the risk propagation path, preparing for subsequent attenuation calculations.

[0075] Step 2032: Obtain the physical barrier attenuation weight corresponding to each horizontal adjacent edge, and the floor penetration attenuation coefficient corresponding to each vertical adjacent edge.

[0076] Specifically, to obtain the physical barrier attenuation weights corresponding to each horizontal adjacent edge and the floor penetration attenuation coefficients corresponding to each vertical adjacent edge, two query mapping tables are first established: one is a mapping table between physical barrier types and attenuation weights, and the other is a mapping table between vertical connection types and floor penetration attenuation coefficients. These tables are usually pre-defined and stored in the system. Then, each edge in the obtained set of horizontal adjacent edges is traversed, and the physical barrier type (such as ordinary wall, firewall, door, window, etc.) is extracted from the edge's attributes, and the corresponding attenuation weight value is looked up in the physical barrier type-attenuation weight mapping table. Similarly, each edge in the set of vertical adjacent edges is traversed, and the vertical connection type (such as stairs, elevator, pipe shaft, etc.) is extracted from the edge's attributes, and the corresponding attenuation coefficient value is looked up in the vertical connection type-floor penetration attenuation coefficient mapping table. If the physical barrier type or vertical connection type is not directly specified in the edge's attributes, it may be necessary to indirectly deduce it from other attributes of the edge or the relationship of the risk units connected. After the query is completed, each horizontal adjacent edge corresponds to a physical barrier attenuation weight, and each vertical adjacent edge corresponds to a floor penetration attenuation coefficient.

[0077] Step 2033: Based on the physical barrier attenuation weight, calculate the product of the physical barrier transmittance corresponding to the horizontal adjacent edges, and calculate the total floor penetration attenuation according to the number of vertical adjacent edges and the floor penetration attenuation coefficient; multiply the product by the total floor penetration attenuation to obtain the spatial propagation attenuation coefficient.

[0078] Specifically, based on the physical barrier attenuation weights, when calculating the product of the physical barrier transmittance corresponding to horizontal adjacent edges, the physical barrier attenuation weights of all horizontal adjacent edges on the shortest topological path are multiplied together. Assuming there are multiple horizontal adjacent edges on the path, the attenuation weight of each edge is extracted sequentially and multiplied together to obtain the final product. This product reflects the cumulative attenuation effect of risk when passing through multiple horizontal physical barriers. Next, based on the number of vertical adjacent edges and the floor penetration attenuation coefficient, the total floor penetration attenuation is calculated. Assuming there are multiple vertical adjacent edges on the path, the floor penetration attenuation coefficient of each edge is extracted sequentially and multiplied together to obtain the total floor penetration attenuation value. This calculation reflects the cumulative attenuation effect of risk when passing through multiple floors in the vertical direction. Finally, the product of the horizontal physical barrier transmittance is multiplied by the total floor penetration attenuation in the vertical direction to obtain the spatial propagation attenuation coefficient, which comprehensively considers the propagation characteristics in both horizontal and vertical directions. This coefficient will be used to subsequently calculate the actual impact intensity of the risk event on the target risk unit.

[0079] The following describes a dynamic risk mapping system for safe production according to an embodiment of the present invention from the perspective of hardware processing. Please refer to [link / reference needed]. Figure 3 This is a schematic diagram of the structure of a dynamic mapping system for safety production risks in an embodiment of this application.

[0080] It should be noted that, Figure 3 The structure of the safety production risk dynamic mapping system shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the present invention.

[0081] like Figure 3 As shown, a dynamic mapping system for safety production risks includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes based on programs stored in read-only memory (ROM) 302 or programs loaded from storage section 308 into random access memory (RAM) 303, such as executing the methods described in the above embodiments. The RAM 303 also stores various programs and data required for system operation. The CPU 301, ROM 302, and RAM 303 are interconnected via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0082] The following components are connected to I / O interface 305: input section 306 including audio input devices, push-button switches, etc.; output section 307 including a liquid crystal display (LCD) and audio output devices, indicator lights, etc.; storage section 308 including a hard disk, etc.; and communication section 309 including a network interface card such as a LAN (Local Area Network) card, modem, etc. Communication section 309 performs communication processing via a network such as the Internet. Drive 310 is also connected to I / O interface 305 as needed. Removable media 311, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., are installed on drive 310 as needed so that computer programs read from them can be installed into storage section 308 as needed.

[0083] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing computer programs for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 309, and / or installed from removable medium 311. When the computer program is executed by central processing unit (CPU) 301, it performs the various functions defined in the present invention.

[0084] It should be noted that specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this invention, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0085] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. Each block in a flowchart or block diagram may represent a module, segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those shown in the drawings.

[0086] Specifically, a safety production risk dynamic mapping system according to this embodiment includes a processor and a memory. The memory stores a computer program. When the computer program is executed by the processor, it implements a safety production risk dynamic mapping method provided in the above embodiment.

[0087] In another aspect, the present invention also provides a computer-readable storage medium, which may be included in the safety production risk dynamic mapping system described in the above embodiments; or it may exist independently and not assembled into the safety production risk dynamic mapping system. The storage medium carries one or more computer programs, which, when executed by a processor of the safety production risk dynamic mapping system, enable the safety production risk dynamic mapping system to implement the safety production risk dynamic mapping method based on IoT data encryption transmission provided in the above embodiments.

Claims

1. A method for dynamic mapping of safety production risks, characterized in that, The method includes: Obtain the plant layout data, divide the plant area into risk units based on the plant layout data, and determine the basic risk level and spatial topology of the risk units; Acquire multi-source heterogeneous security data, standardize the multi-source heterogeneous security data into risk events, and determine the time parameters and propagation radius of the risk events; Calculate the time contribution coefficient of the risk event at the current moment based on the time parameter; Based on the spatial topology and the propagation radius, determine the spatial propagation attenuation coefficient of the risk event for each risk unit; By combining the time contribution coefficient and the spatial propagation attenuation coefficient, the risk propagation intensity of the risk event on each of the risk units is calculated; The dominant risk contribution and heterogeneous coupling coefficient of each risk unit are determined based on the risk propagation intensity, and the dynamic comprehensive risk value of each risk unit is calculated in combination with the basic risk level. The dynamic risk level of each risk unit is determined based on the dynamic comprehensive risk value, and the risk distribution is visualized and rendered based on the dynamic risk level.

2. The method according to claim 1, characterized in that, The step of dividing risk units based on the plant layout data and determining the basic risk level and spatial topology of the risk units includes: Extract the physical connectivity and solid partition information from the factory layout data; The horizontal and vertical adjacency edges between adjacent risk units are determined based on the physical connectivity relationship. The physical barrier attenuation weight of the horizontal adjacent edge is determined based on the information of the physical partition component. The floor penetration attenuation coefficient of the vertical adjacent edge is determined based on the closure level of the vertical connecting opening; The spatial topology is constructed by combining the horizontal adjacent edges, the vertical adjacent edges, the physical barrier attenuation weights, and the floor penetration attenuation coefficients.

3. The method according to claim 1, characterized in that, The process of acquiring multi-source heterogeneous security data, standardizing the multi-source heterogeneous security data into risk events, and determining the time parameters and propagation radius of the risk events includes: Spatial location features, timestamp features, and event description features are extracted from the multi-source heterogeneous security data; Spatial matching is performed between the spatial location features and the boundary range of each risk unit to determine the source risk unit corresponding to the multi-source heterogeneous security data; Based on the attributes of the source risk unit and the event description characteristics, the multi-source heterogeneous security data is transformed into standardized risk events, and the initial impact range of the risk events is determined. The time parameters of the risk event are determined based on the timestamp feature, and the initial impact range is adjusted in conjunction with the basic risk level of the source risk unit to obtain the propagation radius of the risk event.

4. The method according to claim 1, characterized in that, The determination of the spatial propagation attenuation coefficient of the risk event for each risk unit based on the spatial topology and the propagation radius includes: Starting with the source risk unit corresponding to the risk event as the starting node, the spatial topology is traversed to obtain the set of reachable risk units whose topology path length is within the propagation radius; For each target risk unit in the set of reachable risk units, obtain the shortest topological path from the source risk unit to the target risk unit; Extract the edge attributes on the shortest topological path; The spatial propagation attenuation coefficient of the risk event on the target risk unit is calculated based on the edge attribute.

5. The method according to claim 4, characterized in that, The step of calculating the spatial propagation attenuation coefficient of the risk event on the target risk unit based on the edge attribute includes: Extract each horizontal and vertical adjacent edge on the shortest topological path; Obtain the physical barrier attenuation weight corresponding to each of the horizontal adjacent edges, and the floor penetration attenuation coefficient corresponding to each of the vertical adjacent edges; Based on the physical barrier attenuation weight, calculate the product of the physical barrier transmittance corresponding to the horizontal adjacent edges, and calculate the total floor penetration attenuation based on the number of vertical adjacent edges and the floor penetration attenuation coefficient. Multiplying the product by the total floor penetration attenuation yields the spatial propagation attenuation coefficient.

6. The method according to claim 1, characterized in that, The process of determining the dominant risk contribution and heterogeneous coupling coefficient of each risk unit based on the risk propagation intensity, and calculating the dynamic comprehensive risk value of each risk unit in conjunction with the basic risk level, includes: Risk events propagating to the risk unit are categorized into multiple subsets based on event type; Extract the maximum risk propagation intensity from each of the aforementioned category subsets as the representative contribution value for the corresponding category; The largest representative contribution value in each of the aforementioned category subsets is selected as the dominant risk contribution. The heterogeneous coupling coefficient is calculated based on the non-empty state of each category subset and the preset heterogeneous coupling amplification coefficient; The product of the dominant risk contribution and the heterogeneous coupling coefficient is compared with the basic risk level, and the maximum value is taken as the dynamic comprehensive risk value.

7. The method according to claim 1, characterized in that, The step of determining the dynamic risk level of each risk unit based on the dynamic comprehensive risk value, and performing risk distribution visualization rendering based on the dynamic risk level, includes: The dynamic comprehensive risk value is compared with a preset risk level threshold to determine the dynamic risk level of each risk unit; Obtain the preset rendering color and preset transparency corresponding to each of the aforementioned dynamic risk levels; Extract the floor elevation information of each risk unit from the plant layout data; Based on the floor elevation information, construct the corresponding rendering layers for each floor in ascending order; The risk units in each rendering layer are filled with the preset rendering color and the preset transparency, and the layer transparency is superimposed according to the construction order of the rendering layers to output the visualization rendering result of the risk distribution.

8. A dynamic mapping system for safety production risks, characterized in that, The dynamic mapping system for safety production risks includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to cause the dynamic mapping system for safety production risks to perform the method as described in any one of claims 1-7.

9. A computer-readable storage medium comprising instructions, characterized in that, When the instruction is executed on the dynamic mapping system for safety production risks, the dynamic mapping system for safety production risks performs the method as described in any one of claims 1-7.

10. A computer program product, characterized in that, When the computer program product is run on the dynamic mapping system for safety production risks, the dynamic mapping system for safety production risks performs the method as described in any one of claims 1-7.

Images