Methods and related equipment for dynamic assessment and early warning of marine spatiotemporal risks
By constructing an adaptive spatiotemporal coupled grid and dynamic weight calculation, the problem of nonlinear coupling of multiple risk factors in traditional marine risk assessment is solved, achieving high accuracy and cross-sea area adaptability in marine risk assessment.
Patent Information
- Application Number
- CN202611250780.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-08-18
- Publication Date
- 2026-11-17
AI Technical Summary
In existing technologies, traditional marine risk assessment schemes use linear weighting and fixed expert scoring, which makes it difficult to characterize the nonlinear coupling of multiple risk factors. This leads to distorted assessments of scenarios with multiple high-risk factors overlapping, poor generalization ability, and a disconnect between the spatial radiation and temporal continuity of risk.
By constructing an adaptive spatiotemporal coupled grid, risk factor data is obtained. Normalization processing, dynamic weight calculation, and spatiotemporal nonlinear fusion are employed, combined with Kalman filtering and visualization rendering, to achieve dynamic assessment of maritime risks.
It significantly improves the authenticity and reference value of maritime risk assessment results, enhances the adaptability to cross-sea scenarios, and accurately depicts the evolutionary impact of risk spatial radiation and diffusion and temporal inertial continuation.
Smart Images

Figure CN123117776A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of marine assessment technology, and in particular to a method and related equipment for dynamic assessment and early warning of marine spatiotemporal risks. Background Technology
[0002] Currently, with the rapid development of intelligent shipping, unmanned maritime systems, and maritime digital communication technologies, modern maritime security threats are also showing new characteristics, posing new requirements for maritime risk assessment technologies.
[0003] In related technologies, static evaluation models based on expert scoring are commonly used for maritime risk assessment. However, in practical applications, it has been found that traditional maritime risk assessment schemes generally adopt linear weighting and fixed expert scoring frameworks, which are difficult to characterize the nonlinear coupling of multiple risk factors. Furthermore, they typically use single-grid, single-time-independent calculations, resulting in problems such as assessment distortion in scenarios with multiple high-risk factors overlapping, poor generalization ability, and disconnection between the spatial radiation and temporal continuity of risk.
[0004] In summary, the technical problems existing in the relevant technologies need to be improved. Summary of the Invention
[0005] This application provides a method and related equipment for dynamic assessment and early warning of maritime spatiotemporal risks, which can significantly improve the authenticity and reference value of maritime risk assessment results and enhance the adaptability to cross-sea scenarios.
[0006] On the one hand, embodiments of this application provide a method for dynamic assessment and early warning of maritime spatiotemporal risks, the method comprising the following steps: The target sea area is determined, and an adaptive spatiotemporal coupled grid and risk factor dataset for the target sea area are constructed; wherein, the risk factor dataset includes physical threat factor data, unmanned system threat factor data, digital domain interference factor data, marine environmental risk factor data, and waterway vulnerability factor data; Using each grid in the adaptive spatiotemporal coupling grid as a unit, the risk factor dataset is normalized based on a preset normalization processing algorithm; Based on the normalized risk factor dataset, the assigned weight of each risk factor is dynamically calculated, thereby obtaining the original risk value in each grid of the adaptive spatiotemporal coupled grid. Spatiotemporal nonlinear fusion and saturation suppression correction are performed on the original risk value of each grid to obtain the risk correction value of each grid. The risk correction value of each grid is filtered and combined with the preset risk assessment and grading rules to determine the risk assessment level of each grid. The result is then output through visualization rendering to obtain the dynamic assessment and early warning result of the marine spatiotemporal risk of the target sea area.
[0007] Optionally, determining the target sea area and constructing an adaptive spatiotemporally coupled grid and risk factor dataset for the target sea area includes: Determine the target sea area and, based on the extreme latitude and longitude values of the target sea area, trim the grid according to the preset spatial resolution; The longitude step size is dynamically adjusted based on the latitude of each grid, and time-series slicing is performed according to a preset time interval to complete the construction of an adaptive spatiotemporal coupled grid for the target sea area. According to the preset time interval, multi-source heterogeneous data are synchronously collected for each grid, including physical threat factor data, unmanned system threat factor data, digital domain interference factor data, marine environmental risk factor data, and waterway vulnerability factor data, thereby completing the construction of the risk factor dataset for the target sea area.
[0008] Optionally, the step of performing normalization processing on the risk factor dataset based on a preset normalization processing algorithm, using each grid in the adaptive spatiotemporal coupled grid as a unit, includes: Using each grid in the adaptive spatiotemporal coupling grid as a unit, the preset sliding window dynamic extreme value and the global steady-state extreme value are obtained, and the weighted calculation is used to obtain the mixed extreme value; Based on the mixed extreme values and the risk factor dataset, normalization is performed using an extreme value standardization algorithm.
[0009] Optionally, the step of dynamically calculating the assigned weight of each risk factor based on the normalized risk factor dataset, thereby calculating the original risk value on a per-grid basis in the adaptive spatiotemporal coupled grid, includes: Based on the normalized risk factor dataset, the mean and standard deviation of each risk factor in each grid under each time slice are obtained, and then the coefficient of variation of each risk factor is calculated. Based on the coefficient of variation of each risk factor, the objective weight of each risk factor is calculated. Combined with the preset prior weight, the assigned weight of each risk factor is dynamically calculated. The original risk value for each grid is calculated by weighting the assigned weight of each risk factor and the normalized observation values of the risk factors in each grid of the adaptive spatiotemporal coupled grid.
[0010] Optionally, the process of performing spatiotemporal nonlinear fusion and saturation suppression correction on the original risk value of each grid to obtain the corrected risk value for each grid includes: The original risk value of each grid is spatially smoothed using a Gaussian kernel, and time fusion is performed using an exponential decay function to complete the spatiotemporal nonlinear fusion. By combining the preset suppression threshold gradient gradation range, a matching saturation suppression correction is performed on each grid to obtain the risk correction value for each grid.
[0011] Optionally, the risk correction value of each grid is filtered and combined with a preset risk assessment grading rule to determine the risk assessment level of each grid, and then output through visualization rendering to obtain the dynamic assessment and early warning results of the marine spatiotemporal risks of the target sea area, including: The risk correction value of each grid is filtered by the Kalman time-series filtering algorithm, and the risk assessment level of each grid is determined by combining it with the preset risk assessment classification rules. The risk assessment level of each grid is smoothly calculated using a bilinear interpolation algorithm. Different colors are used to visualize and render the data according to different risk assessment levels, and the final rendered image is output to obtain the dynamic assessment and early warning results of the marine spatiotemporal risks of the target sea area.
[0012] On the other hand, embodiments of this application provide a dynamic assessment and early warning device for maritime spatiotemporal risks, the device comprising: The data acquisition module is used to determine the target sea area and construct an adaptive spatiotemporal coupled grid and risk factor dataset for the target sea area; wherein, the risk factor dataset includes physical threat factor data, unmanned system threat factor data, digital domain interference factor data, marine environmental risk factor data, and waterway vulnerability factor data; The data processing module is used to perform normalization processing on the risk factor dataset based on a preset normalization processing algorithm, taking each grid in the adaptive spatiotemporal coupling grid as a unit. The data calculation module is used to dynamically calculate the assigned weight of each risk factor based on the normalized risk factor dataset, thereby calculating the original risk value in each grid of the adaptive spatiotemporal coupled grid. The data correction module is used to perform spatiotemporal nonlinear fusion and saturation suppression correction on the original risk value of each grid to obtain the risk correction value of each grid. The data output module is used to filter the risk correction value of each grid, and in combination with the preset risk assessment and grading rules, determine the risk assessment level of each grid, and output it through visualization rendering to obtain the dynamic assessment and early warning results of the marine spatiotemporal risks of the target sea area.
[0013] On the other hand, embodiments of this application provide an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the above-described method.
[0014] On the other hand, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method.
[0015] On the other hand, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the above-described method.
[0016] This application embodiment constructs an adaptive spatiotemporal coupled grid and obtains risk factor data for each grid, accurately depicting the evolutionary impact of the spatial radiation and diffusion of maritime risks and the temporal inertial continuation, significantly improving the authenticity and reference value of maritime risk assessment results, and enhancing the adaptability to cross-sea scenarios through adaptive dynamic weighting. Attached Figure Description
[0017] Figure 1 This is a schematic diagram of the implementation environment of a dynamic assessment and early warning method for maritime spatiotemporal risks provided in an embodiment of this application; Figure 2 This is a flowchart illustrating a method for dynamic assessment and early warning of maritime spatiotemporal risks provided in an embodiment of this application; Figure 3 This is a schematic diagram of an architecture for dynamic assessment of maritime spatiotemporal risks provided in an embodiment of this application; Figure 4 This is a schematic diagram of an adaptive correction marine grid provided in an embodiment of this application; Figure 5 This is a schematic diagram of a process for dynamically calculating and assigning weights to risk factors, provided in an embodiment of this application. Figure 6 This is a schematic diagram of a saturation suppression correction and risk assessment classification process provided in an embodiment of this application; Figure 7 This is a schematic diagram of the structure of a marine spatiotemporal risk dynamic assessment and early warning device provided in an embodiment of this application; Figure 8 This is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of this application. Detailed Implementation
[0018] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit it. In the following description, when referring to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with those of this application; they are merely examples of apparatuses and methods consistent with some aspects of the embodiments of this application as detailed in the appended claims.
[0019] It is understood that the terms “first,” “second,” etc., used in this application may be used herein to describe various concepts, but unless otherwise stated, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another. For example, without departing from the scope of the embodiments of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the words “if,” “when,” or “in response to a determination” as used herein may be interpreted as “when…” or “when…” or “in response to a determination.”
[0020] As used in this application, the terms "at least one", "multiple", "each", "any", etc., "at least one" includes one, two or more, "multiple" includes two or more, "each" refers to each of the corresponding multiples, and "any" refers to any one of the multiples.
[0021] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.
[0022] Currently, with the rapid development of intelligent shipping, unmanned maritime systems, and maritime digital communication technologies, modern maritime security threats are also showing new characteristics, posing new requirements for maritime risk assessment technologies.
[0023] In related technologies, static evaluation models based on expert scoring are commonly used for maritime risk assessment. However, in practical applications, it has been found that traditional maritime risk assessment schemes generally adopt linear weighting and fixed expert scoring frameworks, which are difficult to characterize the nonlinear coupling of multiple risk factors. Furthermore, they typically use single-grid, single-time-independent calculations, resulting in problems such as assessment distortion in scenarios with multiple high-risk factors overlapping, poor generalization ability, and disconnection between the spatial radiation and temporal continuity of risk.
[0024] In view of this, this application provides a method and related equipment for dynamic assessment and early warning of marine spatiotemporal risks. By constructing an adaptive spatiotemporal coupled grid and acquiring risk factor data for each grid, it accurately depicts the evolutionary impact of the spatial radiation and diffusion of marine risks and the temporal inertial continuation, significantly improving the authenticity and reference value of maritime risk assessment results. Furthermore, through adaptive dynamic weighting, it enhances the adaptability to cross-sea scenarios.
[0025] It should be noted that in all specific embodiments of this application, when processing data related to user identity or characteristics, such as user information, user behavior data, user historical data, and user location information, user permission or consent is obtained first. Furthermore, the collection, use, and processing of this data comply with relevant laws, regulations, and standards. In addition, when embodiments of this application require access to sensitive personal information of users, separate permission or consent from the user is obtained through pop-ups or redirection to confirmation pages. Only after obtaining the user's separate permission or consent is the necessary user-related data required for the proper functioning of these embodiments acquired.
[0026] The specific implementation methods of the embodiments of this application will be described in detail below with reference to the accompanying drawings. First, a method for dynamic assessment and early warning of maritime spatiotemporal risks provided in the embodiments of this application will be described with reference to the accompanying drawings.
[0027] Please refer to Figure 1 , Figure 1 This is a schematic diagram of the implementation environment for a dynamic assessment and early warning method for maritime spatiotemporal risks provided in this application embodiment. In this implementation environment, the main hardware and software components involved include a terminal processor 110 and a server 120.
[0028] Specifically, the terminal processor 110 may be equipped with a control program for a dynamic assessment and early warning method for maritime spatiotemporal risks, and the server 120 serves as the backend server for this control program. The terminal processor 110 and the backend server 120 are connected. The dynamic assessment and early warning method for maritime spatiotemporal risks provided in this embodiment can be executed on the terminal processor 110 side.
[0029] Server 120 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms.
[0030] In addition, server 120 can also be a node server in a blockchain network.
[0031] The terminal processor 110 and the server 120 can establish a communication connection via a wireless network. This wireless network uses standard communication technologies and / or protocols. The network can be the Internet or any other network, including but not limited to a Local Area Network (LAN), Metropolitan Area Network (MAN), Wide Area Network (WAN), mobile, or any combination of wireless networks, private networks, or virtual private networks. Furthermore, these hardware and software components can use the same or different communication connection methods; this application does not impose specific limitations in this regard.
[0032] Of course, this is understandable. Figure 1 The implementation environment described in this application is only one of the optional application scenarios for the dynamic assessment and early warning method for maritime spatiotemporal risks provided in this embodiment. The actual application is not fixed. Figure 1 The software and hardware environment shown is not specifically limited in this application.
[0033] like Figure 2 As shown, Figure 2 This is a flowchart illustrating a method for dynamic assessment and early warning of maritime spatiotemporal risks provided in this application embodiment, specifically including but not limited to steps 100 to 500.
[0034] Step 100: Determine the target sea area and construct an adaptive spatiotemporal coupled grid and risk factor dataset for the target sea area; wherein, the risk factor dataset includes physical threat factor data, unmanned system threat factor data, digital domain interference factor data, marine environmental risk factor data, and waterway vulnerability factor data.
[0035] In this embodiment of the application, the target sea area to be evaluated is determined, specifically by determining the latitude and longitude range information of the target sea area, and further by cropping according to the geographical range of the target sea area through a preset reference resolution to complete the global grid subdivision of the target sea area and construct an adaptive spatiotemporal coupled grid of the target sea area.
[0036] Among them, the adaptive spatiotemporal coupled grid is a grid that couples the spatial and temporal dimensions and adaptively adjusts the longitude step size.
[0037] Furthermore, by synchronously collecting multi-source heterogeneous data from the target sea area and achieving unified temporal-spatial mapping and alignment through standardized spatiotemporal registration processing, a risk factor dataset for the target sea area is constructed. Specifically, the risk factor dataset consists of physical threat factor data, unmanned system threat factor data, digital domain interference factor data, marine environmental risk factor data, and waterway vulnerability factor data. Physical threat factors include data such as the probability of ship collisions and the frequency of attacks; unmanned system threat factor data includes the activity density of drones, unmanned surface vessels, and underwater vehicles; digital domain interference factor data includes the number of AIS spoofing, GPS deception, and abnormal communication messages; marine environmental risk factor data includes wind and wave levels, sea surface visibility, tidal complexity, and the probability of extreme weather occurrence; and waterway vulnerability factor data includes data such as average waterway width, ship traffic density, waterway narrowing coefficient, and waterway congestion index.
[0038] Therefore, by constructing an adaptive spatiotemporal coupled grid for the target sea area, a standardized coordinate system is provided for subsequent risk assessment modeling and analysis. Threat factors are constructed from multiple different perspectives, and corresponding risk data are obtained. The data types include statistical counting, environmental observation, emergency events, and spatial density, thus forming a multi-level, fully covered, and high-precision risk factor dataset for maritime composite risks.
[0039] Specifically, as an optional implementation, determining the target sea area and constructing an adaptive spatiotemporally coupled grid and risk factor dataset for the target sea area includes: Determine the target sea area and, based on the extreme latitude and longitude values of the target sea area, trim the grid according to the preset spatial resolution; The longitude step size is dynamically adjusted based on the latitude of each grid, and time-series slicing is performed according to a preset time interval to complete the construction of an adaptive spatiotemporal coupled grid for the target sea area. According to the preset time interval, multi-source heterogeneous data are synchronously collected for each grid, including physical threat factor data, unmanned system threat factor data, digital domain interference factor data, marine environmental risk factor data, and waterway vulnerability factor data, thereby completing the construction of the risk factor dataset for the target sea area.
[0040] In the embodiments of this application, please refer to Figure 3 , Figure 3 This is a schematic diagram of the architecture for dynamic assessment of marine spatiotemporal risks provided in an embodiment of this application. First, the latitude and longitude extreme values of the target sea area to be assessed are determined to determine the entire range. Then, based on a preset spatial resolution (e.g., it can be set to 0.01°), the grid is clipped starting from the latitude and longitude extreme values to obtain multiple sea area grids.
[0041] Furthermore, the longitude step size is dynamically adjusted based on the latitude of each grid. In traditional latitude and longitude grid clipping, the longitude lines converge as they approach higher latitudes, resulting in a shorter actual ground distance corresponding to the same longitude difference. This leads to uneven grid areas, causing the same grid to represent different actual sea areas at different latitudes, which can distort cross-regional comparisons.
[0042] Therefore, this application dynamically adjusts the longitude step size corresponding to grids at different latitudes using the following formula (1): (1) in, Compensation for baseline longitude below the equator; The latitude of the center point of each grid is not 90°; This is the dynamically corrected longitude step.
[0043] Therefore, by correcting the longitude step size of different grids at the equator, mid-latitude, and high latitude using formula (1), the longitude step size can be adaptively amplified as latitude increases, offsetting the meridian convergence effect, ensuring that the actual ground area of each grid unit is equal and uniform as much as possible, and overcoming the defects of inflated risk density at high latitudes and inconsistent assessment benchmarks in the north and south sea areas.
[0044] For example, please refer to Figure 4 , Figure 4 This is a schematic diagram of an adaptively corrected marine grid provided in an embodiment of this application. Figure 4 The images show examples of traditional mesh clipping and the adaptive longitude step size adjustment mesh of this application. Specifically, in the traditional mesh clipping example, the longitude step size is gradually reduced as the latitude increases, resulting in a mesh at higher latitudes (…). Figure 4 The area distortion of the shaded region in the previous application caused problems such as inconsistent spatial reference. However, the adaptive adjustment grid of this application gradually adjusts the longitude step size as the latitude increases, and dynamically corrects the longitude step size of each grid through latitude cosine correction.
[0045] Furthermore, time-series slicing is performed according to a preset time interval, such as setting a fixed time-series slice of 1 hour, which can match the regular evolution cycle of maritime risks. This avoids losing dynamic mutation features due to excessively large time-series steps, and also prevents computational redundancy caused by excessively small steps. In this way, the spatial grid and time-series slices are integrated to construct a three-dimensional spatiotemporal data matrix, forming an adaptive spatiotemporal coupled grid for the target sea area.
[0046] Furthermore, using the adaptive spatiotemporal coupled grid of the target sea area as the computing basis, data on five major categories of maritime comprehensive threats—physical threats, unmanned system threats, digital domain interference, marine environmental risks, and waterway vulnerability—can be collected. For example, multi-source heterogeneous data can be collected synchronously on a grid-by-grid basis and at preset time intervals to obtain the risk factor dataset of the target sea area.
[0047] In practical applications, physical threat master data can be obtained through publicly available maritime datasets, unmanned system threat factor data can be obtained through publicly available maritime UAV GPS datasets, digital domain interference factor data can be generated based on the noise samples inherent in the MTAD dataset, marine environmental risk factor data can be obtained using publicly available ocean reanalysis time series datasets, and sea area geometric static parameters can be obtained as channel vulnerability factor data by combining open-source vector electronic nautical charts.
[0048] Ultimately, all threat factor data are uniformly normalized to an hourly UTC time series reference according to timestamps. Time series resampling and linear interpolation are performed at preset time intervals to ensure the synchronization of risk factor time series nodes. At the spatial level, an adaptive spatiotemporal coupled grid is used as a unified spatial reference. Point-to-grid spatial statistical assignment is used for data such as ships, unmanned equipment, and interference events. Spatial resampling and interpolation are used to match the grid resolution for marine environmental fields and channel geometric parameters. In this way, all heterogeneous data are uniformly mapped to the same grid cell and the same time series slice, which can effectively overcome the defects of inconsistent dimensions, spatiotemporal misalignment, and inability to jointly model multi-source heterogeneous data in traditional technologies.
[0049] Step 200: Using each grid in the adaptive spatiotemporal coupling grid as a unit, perform normalization processing on the risk factor dataset based on a preset normalization processing algorithm.
[0050] In the embodiments of this application, please refer to Figure 3 This application takes into account the different data dimensions and numerical scales among multi-source heterogeneous data. Therefore, it uses each grid in the adaptive spatiotemporal coupling grid as a unit and performs normalization processing on the data in the risk factor dataset based on a preset normalization processing algorithm, so that data of different types, scales and sources can be normalized into standardized risk inputs that are comparable, fusionable and stably calculable.
[0051] For example, the step of performing normalization processing on the risk factor dataset based on a preset normalization processing algorithm, using each grid in the adaptive spatiotemporal coupled grid as a unit, includes: Using each grid in the adaptive spatiotemporal coupling grid as a unit, the preset sliding window dynamic extreme value and the global steady-state extreme value are obtained, and the weighted calculation is used to obtain the mixed extreme value; Based on the mixed extreme values and the risk factor dataset, normalization is performed using an extreme value standardization algorithm.
[0052] In this embodiment of the application, firstly, taking each grid in the adaptive spatiotemporal coupled grid as a unit, the preset sliding window dynamic extreme value and global steady-state extreme value of each threat factor are obtained. The preset sliding window dynamic extreme value can be obtained by using a pre-set sliding window time, such as a 24-hour sliding window extreme value, to reflect the short-term fluctuations of the threat factor and obtain the minimum and maximum values. Then, the global long-term steady-state extreme value in the target sea area is obtained to reflect the long-term benchmark, and then the mixed extreme value is obtained by weighted calculation.
[0053] Specifically, the calculation process of mixed extrema can be expressed as the following formulas (2) and (3), as follows: (2) (3) in, This refers to the mixed maxima obtained through weighted fusion calculation; This represents the dynamic maximum value of the sliding window; This represents the global steady-state maximum. This is the mixed minimum value obtained through weighted fusion calculation; This represents the dynamic minimum value of the sliding window. The value represents the global steady-state minimum; where n represents the nth type of threat factor, specifically referring to physical threat factor data, unmanned system threat factor data, digital domain interference factor data, marine environmental risk factor data, and waterway vulnerability factor data.
[0054] Therefore, by setting the weights of the preset sliding window dynamic extreme value and the global steady-state extreme value respectively, for example, setting them to 0.6 and 0.4 respectively, and of course, adjusting and updating them according to the specific needs of the scenario, this application does not impose specific restrictions on this. Then, by calculating the mixed extreme value through mixed weighting, both short-term sensitivity and long-term comparability can be preserved.
[0055] Furthermore, based on the mixed extreme values and the aforementioned risk factor dataset, normalization is performed using an extreme value standardization algorithm. The specific calculation process can be expressed as the following formula (4): (4) Where i and j are the horizontal and vertical indices of the grid cells in the adaptive spatiotemporal coupled grid, respectively; This represents the k-th time slice; The original observation values of the nth risk factor in the kth time slice of the grid cell with index (i, j); The values are after normalization.
[0056] Therefore, this application utilizes the mixed maximum and mixed minimum values obtained by weighted fusion calculation of the dynamic extreme values of a preset sliding window and the steady-state extreme values of the entire domain. It then normalizes the data of each threat factor type under each time slice in each grid cell using the Min-Max extreme value normalization algorithm, and adds a 10 to the denominator. -8 The constant is used to avoid the extreme case where the difference between mixed extrema is 0.
[0057] Furthermore, compared to the traditional single global normalization which suppresses short-term sudden risks and lacks dynamic response sensitivity, and the single sliding window normalization which lacks a globally unified evaluation benchmark, this application improves the hybrid fault tolerance capability through dynamic hybrid computation. It retains the sensitivity of short-term risk mutation identification while maintaining the uniformity of long-term global evaluation scale, making data of different types, scales, and sources into standardized risk inputs that are comparable, fusionable, and stably computeable.
[0058] Step 300: Based on the normalized risk factor dataset, dynamically calculate the assigned weight of each risk factor, thereby calculating the original risk value for each grid in the adaptive spatiotemporal coupled grid.
[0059] In the embodiments of this application, please refer to Figure 3 Based on the normalized risk factor dataset, the assigned weight of each risk factor in each grid cell is calculated. Then, based on the normalized risk factors and their corresponding assigned weights, the original risk value of each grid in the adaptive spatiotemporal coupled grid is obtained through weighted calculation.
[0060] Therefore, compared with the traditional fixed manual weight configuration, this application can dynamically adjust the weight of each risk factor according to the characteristics of data distribution and changes in marine scenarios, which greatly improves the model's data adaptability and risk level differentiation.
[0061] Specifically, as an optional implementation, the step of dynamically calculating the assigned weight of each risk factor based on the normalized risk factor dataset, thereby calculating the original risk value on a per-grid basis in the adaptive spatiotemporal coupled grid, includes: Based on the normalized risk factor dataset, the mean and standard deviation of each risk factor in each grid under each time slice are obtained, and then the coefficient of variation of each risk factor is calculated. Based on the coefficient of variation of each risk factor, the objective weight of each risk factor is calculated. Combined with the preset prior weight, the assigned weight of each risk factor is dynamically calculated. The original risk value for each grid is calculated by weighting the assigned weight of each risk factor and the normalized observation values of the risk factors in each grid of the adaptive spatiotemporal coupled grid.
[0062] In the embodiments of this application, please refer to Figure 5 , Figure 5 This is a flowchart illustrating the dynamic calculation and weighting process for risk factors provided in this application embodiment. After inputting the normalized risk factor dataset, the mean and standard deviation of the sea area grid are calculated time-series and factor-by-factor, and then the coefficient of variation is obtained. ,in, Let be the coefficient of variation of the nth type of threat factor. Let n be the standard deviation of the nth type of threat factor. Let be the mean of the nth type of threat factor.
[0063] Furthermore, based on the coefficient of variation of each threat factor, the coefficients of variation of all factors are normalized and summed to obtain the objective weights calculated based on objective data. The specific calculation process is as follows: ;in, denoted as the objective weight of the nth type of threat factor.
[0064] Therefore, the higher the coefficient of variation, the greater the global grid dispersion of the risk factor, the stronger its risk differentiation ability, and the higher the weight it is automatically assigned.
[0065] Furthermore, different prior weights can be pre-set for three typical maritime operation scenarios: nearshore, narrow waterways, and open sea. Then, based on the actual sea conditions of each grid cell, the corresponding prior weight is selected, and finally, the assigned weight of each risk factor is obtained by dynamically weighting and fusing the objective weight and the prior weight. For example, ;in, The final dynamic adaptive weights are for the nth type of risk factors.
[0066] It is understood that the weight coefficients of the objective weights and the weight coefficients of the prior weights mentioned above are just some optional settings provided in the embodiments of this application. This application does not impose specific restrictions on them and they can be preset according to the specific usage requirements of the scenario.
[0067] Therefore, this application can dynamically adjust the weight of each risk factor as data distribution and marine scene changes, thereby improving flexibility.
[0068] Furthermore, based on the assigned weight of each risk factor and the normalized risk factor observation values of each grid in the adaptive spatiotemporal coupled grid, the original risk value of each grid cell is obtained through weighted calculation.
[0069] Step 400: Perform spatiotemporal nonlinear fusion and saturation suppression correction on the original risk value of each grid to obtain the risk correction value of each grid.
[0070] In the embodiments of this application, compared with the problem that traditional risk assessment schemes use fixed linear weighting and manually preset weights, which make it difficult to represent the nonlinear coupling and superposition relationship of multiple risk factors, this application uses a spatial and temporal dual-dimensional nonlinear fusion computing architecture to fuse and calculate risk data under multiple factors, multiple grids, and multiple time periods to synthesize a risk field.
[0071] Specifically, as an optional implementation, the process of performing spatiotemporal nonlinear fusion and saturation suppression correction on the original risk value of each grid to obtain the risk correction value for each grid includes: The original risk value of each grid is spatially smoothed using a Gaussian kernel, and time fusion is performed using an exponential decay function to complete the spatiotemporal nonlinear fusion. By combining the preset suppression threshold gradient gradation range, a matching saturation suppression correction is performed on each grid to obtain the risk correction value for each grid.
[0072] In the embodiments of this application, please refer to Figure 6 , Figure 6 This is a flowchart illustrating a saturation suppression correction and risk assessment classification process provided in this application embodiment. First, the original risk values of each grid are fused in a spatiotemporal nonlinear manner. Specifically, spatial fusion can be achieved first, that is, by using a 3×3 Gaussian kernel smoothing filter to traverse the entire grid, the spatial correlation characteristics of the natural radiation diffusion of maritime risks from the high-risk center to the surrounding neighborhood are simulated. This avoids the "island-like grid" caused by independent calculation of single grids, making the risk field more continuous and more in line with the spatial propagation law.
[0073] Furthermore, by introducing an exponential decay function to achieve fusion in the time series dimension, the exponential decay function can be expressed as follows: λ is a configurable time-series decay coefficient, which can be set according to specific scenario requirements or adaptively adjusted according to the rate of marine risk evolution. A preset time interval (e.g., 1 hour) is set for adjacent time slices, thereby introducing an exponential decay function to represent that the risks of past historical moments will continue to the current moment at a certain speed and gradually decay over time.
[0074] Therefore, by integrating spatial and temporal dimensions, and achieving spatiotemporal nonlinear fusion, the complex evolutionary patterns of spatial radiation and diffusion, temporal inertial continuation, and multi-factor coupling and checks and balances of maritime risks can be accurately depicted, significantly improving the authenticity and scientific reference value of maritime risk assessment results.
[0075] Furthermore, such as Figure 6 As shown, this application considers that when multiple high-risk factors are superimposed, simple linear weighting will lead to abnormal amplification of the values, which may result in an artificially high risk. Therefore, by further pre-setting the suppression threshold gradient classification interval, a matching saturation suppression correction can be performed on each grid to obtain the final risk correction value for each grid cell.
[0076] For example, a three-level threshold gradient interval can be pre-set, where the first-level threshold is 0.7, the second-level threshold is 0.85, and the third-level threshold is 0.95. When the risk value after spatiotemporal nonlinear fusion meets any of the thresholds, a matching saturation suppression correction is performed. For example, if the risk value after spatiotemporal nonlinear fusion is below 0.7, no attenuation is performed; if the risk value is in the range [0.7, 0.85), a slight attenuation is performed; if the risk value is in the range [0.85, 0.95), a moderate attenuation is performed; and if the risk value is greater than or equal to 0.95, a severe saturation attenuation is performed. The attenuation can be expressed as a percentage, and a step-by-step gradient attenuation can be performed on the high-risk range to prevent excessive numerical inflation.
[0077] Therefore, traditional single-point linear weighting completely severs the spatiotemporal coupling relationship, resulting in fragmented risk field distribution and frequent jumps in temporal evolution. In contrast, this application restores the risk radiation law through Gaussian space smoothing and retains the historical risk evolution inertia through exponential decay function, achieving continuous and smooth evolution of the risk field. Furthermore, it introduces a saturation suppression correction mechanism to address the problem of inflated risk values caused by the superposition of multiple high-risk factors, gradually weakening the superposition gain of ultra-high risks, making the output risk value distribution conform to the actual occurrence law of maritime accidents, while fully retaining the ability to finely distinguish between medium and low-risk areas, and improving the interpretability of dynamic assessment and early warning results.
[0078] Step 500: Filter the risk correction value of each grid and combine it with the preset risk assessment grading rules to determine the risk assessment level of each grid. Output the results through visualization rendering to obtain the dynamic assessment and early warning results of the marine spatiotemporal risks of the target sea area.
[0079] In the embodiments of this application, please refer to Figure 3 By filtering the risk correction value of each grid, noise reduction and smoothing are achieved to avoid drastic oscillations in the subsequent risk curve. After the filtering is completed, the risk assessment level of each grid is determined according to the preset risk assessment grading rules and output through visualization rendering. The risk assessment level is transformed into an intuitive and clear risk heat field. The output heat map serves as the dynamic assessment and early warning result of the marine spatiotemporal risk in the target sea area, thus completing a high-precision dynamic visualization representation of the maritime risk situation.
[0080] Therefore, this application constructs an adaptive spatiotemporal coupled grid and obtains risk factor data for each grid, accurately characterizing the evolutionary impact of the spatial radiation and diffusion of maritime risks and the temporal inertial continuation, significantly improving the authenticity and reference value of maritime risk assessment results, and enhancing the adaptability to cross-sea scenarios through adaptive dynamic weighting.
[0081] Specifically, as an optional implementation, the risk correction value of each grid is filtered and combined with preset risk assessment grading rules to determine the risk assessment level of each grid, and then output through visualization rendering to obtain the dynamic assessment and early warning results of the maritime spatiotemporal risks of the target sea area, including: The risk correction value of each grid is filtered by the Kalman time-series filtering algorithm, and the risk assessment level of each grid is determined by combining it with the preset risk assessment classification rules. The risk assessment level of each grid is smoothly calculated using a bilinear interpolation algorithm. Different colors are used to visualize and render the data according to different risk assessment levels, and the final rendered image is output to obtain the dynamic assessment and early warning results of the marine spatiotemporal risks of the target sea area.
[0082] In the embodiments of this application, such as Figure 6 As shown, after completing the spatiotemporal nonlinear fusion and saturation suppression correction, the grid-by-grid time-series risk sequence output by the spatiotemporal nonlinear fusion and the three-level gradient saturation suppression correction can be used as the observation input. The Kalman time-series filtering algorithm is introduced for noise reduction, smoothing, and trend fitting, so as to fully preserve the true risk evolution law and filter out invalid numerical fluctuations caused by equipment sampling errors and instantaneous environmental clutter.
[0083] Furthermore, the Kalman time-series filtering algorithm treats risk states as state variables that evolve over time. Through state observation and observation updates, it continuously iterates and smooths the data, thereby filtering out random noise, preserving the true trend, and outputting a more stable time-series risk value.
[0084] Furthermore, after completing the filtering process of the Kalman time-series filtering algorithm, the numerical difference between the observed and predicted values during the Kalman time-series filtering process can be compared as the residual. When the residual is greater than a preset threshold, it is regarded as a sudden high-risk event, and when the parameter is less than or equal to the preset threshold, it is regarded as a normal gradual change. This simultaneously takes into account the smoothness and stability of the time-series situation and the sensitivity of sudden high-risk risk perception, thereby reducing the probability of false alarms and missed alarms.
[0085] Therefore, this application not only achieves noise reduction and filtering by introducing the Kalman time-series filtering algorithm to smooth the fitting effect, but also solves the problem that traditional static linear models cannot identify sudden scenarios such as unmanned system attacks, maritime digital interference, and instantaneous channel congestion by combining the residuals between prediction and observation in the Kalman time-series filtering process.
[0086] Furthermore, such as Figure 6 As shown, by combining pre-set risk assessment and grading rules, such as different threshold ranges being considered as different risk levels, and matching different color gradient bands in sequence, the risk assessment level and corresponding rendering method of each grid can be determined.
[0087] Finally, by using bilinear interpolation algorithm to smoothly calculate the risk assessment level of each grid, and by using different colors corresponding to different risk assessment levels for visualization rendering, the final rendering effect map is output, and the dynamic assessment and early warning results of marine spatiotemporal risks in the target sea area are obtained.
[0088] Specifically, a bilinear interpolation algorithm is used to smooth the risk assessment level of each grid. That is, the risk value of the intermediate pixel is fitted by the numerical values of the four neighboring areas of the target grid. This can effectively overcome the defects of natural jaggedness, boundary discontinuity, and color block fragmentation in traditional discrete grid heatmaps. Finally, a dynamic risk heatmap of the whole area with continuous and smooth boundaries, clear risk levels, and spatial distribution that fits the real geographical features of the sea area is output, thus completing a high-precision, dynamic, and intuitive visualization of the maritime risk situation.
[0089] In practical applications, after completing the visualization rendering, an incremental / full dual-mode time-series iterative simulation mechanism can be introduced. Under normal circumstances, incremental local updates are performed based on the preset time interval between adjacent time-series slices as the update frequency. Only grid areas where risk observation data has changed are recalculated and simulated, while grids without changes reuse historical calculation results. This can significantly reduce the overhead of repeated calculations across the entire domain. Furthermore, a full-domain calibration update is performed once at a preset time frequency (e.g., once every 24 hours), traversing all grid cells and uniformly correcting risk values, dynamic weights, and mixed extreme value benchmarks. This reduces the calculation deviations accumulated over long periods of continuous iteration, ensuring the stability of the global risk field assessment benchmark, the uniformity of cross-regional scales, and the reliability of long-term simulation results. This effectively balances the real-time response speed of dynamic simulation with the accuracy of the long-term global assessment benchmark, that is, effectively balancing real-time refresh speed with long-term stable accuracy.
[0090] The following section provides a detailed explanation and description of the maritime spatiotemporal risk dynamic assessment and early warning method provided in this invention, in conjunction with specific application implementation procedures: This application provides a method for dynamic assessment and early warning of marine spatiotemporal risks. This method can be applied to marine risk dynamic assessment scenarios. By constructing an adaptive spatiotemporal coupled grid and obtaining risk factor data for each grid, it accurately depicts the evolutionary impact of marine risk spatial radiation and diffusion and temporal inertial continuation, significantly improving the authenticity and reference value of marine risk assessment results. Furthermore, through adaptive dynamic weighting, it enhances the adaptability to cross-sea scenarios.
[0091] Specifically, by determining the extreme values of latitude and longitude of the target sea area to be evaluated, the entire area is determined. Then, based on the preset spatial resolution, the grid is clipped starting from the extreme values of latitude and longitude to obtain multiple sea area grids. By correcting the longitude step size of different grids at the equator, mid-latitude, and high latitude, the longitude step size can be adaptively increased as the latitude increases, offsetting the meridian convergence effect and ensuring that the actual ground area of each grid unit is as uniform as possible.
[0092] Furthermore, time-series slicing is performed according to preset time intervals. Using the adaptive spatiotemporal coupled grid of the target sea area as the computing basis, data on five major categories of maritime comprehensive threats—physical threats, unmanned system threats, digital domain interference, marine environmental risks, and waterway vulnerability—are collected. For example, multi-source heterogeneous data can be collected synchronously on a grid-by-grid basis and at preset time intervals to obtain the risk factor dataset of the target sea area.
[0093] Furthermore, taking each grid in the adaptive spatiotemporal coupled grid as a unit, the data in the risk factor dataset is normalized based on a preset normalization processing algorithm. Specifically, taking each grid in the adaptive spatiotemporal coupled grid as a unit, the preset sliding window dynamic extreme value and the global steady-state extreme value of each threat factor are obtained, and then a weighted calculation is performed to obtain a mixed extreme value. Based on the mixed extreme value and the risk factor dataset, a normalization processing is performed through an extreme value standardization algorithm to obtain the normalized risk factor dataset.
[0094] Furthermore, based on the normalized risk factor dataset, the assigned weight of each risk factor in each grid cell is calculated. Thus, based on the normalized risk factors and their corresponding assigned weights, the original risk value of each grid in the adaptive spatiotemporal coupled grid is obtained through weighted calculation.
[0095] In practical applications, a spatial and temporal dual-dimensional nonlinear fusion computing architecture is used to fuse and compute risk data from multiple factors, multiple grids, and multiple time points to synthesize a risk field. Furthermore, by using a pre-set suppression threshold gradient grading interval, a matching saturation suppression correction is performed on each grid to obtain the final risk correction value for each grid cell.
[0096] Finally, by filtering the risk correction value of each grid, noise reduction and smoothing are achieved to avoid drastic oscillations in the subsequent risk curve. After the filtering is completed, the risk assessment level of each grid is determined according to the preset risk assessment grading rules, and then output through visualization rendering. The risk assessment level is transformed into an intuitive and clear risk heat field. The output heat map serves as the dynamic assessment and early warning result of the spatiotemporal risk of the target sea area, thus completing a high-precision dynamic visualization representation of the maritime risk situation.
[0097] Please see Figure 7 , Figure 7 This is a schematic diagram of a marine spatiotemporal risk dynamic assessment and early warning device provided in an embodiment of this application. This application also provides a marine spatiotemporal risk dynamic assessment and early warning device that can implement the above-mentioned marine spatiotemporal risk dynamic assessment and early warning method. The device includes: The data acquisition module 710 is used to determine the target sea area and construct an adaptive spatiotemporal coupled grid and risk factor dataset for the target sea area; wherein, the risk factor dataset includes physical threat factor data, unmanned system threat factor data, digital domain interference factor data, marine environmental risk factor data, and waterway vulnerability factor data; The data processing module 720 is used to perform normalization processing on the risk factor dataset based on a preset normalization processing algorithm, taking each grid in the adaptive spatiotemporal coupling grid as a unit. The data calculation module 730 is used to dynamically calculate the assigned weight of each risk factor based on the normalized risk factor dataset, thereby calculating the original risk value in each grid of the adaptive spatiotemporal coupled grid. The data correction module 740 is used to perform spatiotemporal nonlinear fusion and saturation suppression correction on the original risk value of each grid to obtain the risk correction value of each grid. The data output module 750 is used to filter the risk correction value of each grid, and in combination with the preset risk assessment grading rules, determine the risk assessment level of each grid, and output it through visualization rendering to obtain the dynamic assessment and early warning results of the marine spatiotemporal risks of the target sea area.
[0098] It is understood that the content of the above method embodiments is applicable to the present device embodiments. The specific functions implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.
[0099] Please see Figure 8 , Figure 8 This is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of this application. The electronic device includes: The processor 801 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application. The memory 802 can be implemented as a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 802 can store the operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 802 and is called and executed by the processor 801 using the methods described in the embodiments of this application. The 803 input / output interface is used to implement information input and output. The communication interface 804 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.). Bus 805 transmits information between various components of the device (e.g., processor 801, memory 802, input / output interface 803, and communication interface 804); The processor 801, memory 802, input / output interface 803, and communication interface 804 are connected to each other within the device via bus 805.
[0100] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method.
[0101] It is understood that the content of the above method embodiments is applicable to this storage medium embodiment. The specific functions implemented in this storage medium embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.
[0102] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.
[0103] It is understood that the content of the above method embodiments is applicable to the embodiments of this program product. The specific functions implemented by the embodiments of this program product are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.
[0104] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.
[0105] This application provides a method and related equipment for dynamic assessment and early warning of maritime spatiotemporal risks. By constructing an adaptive spatiotemporal coupled grid and acquiring risk factor data for each grid, it accurately depicts the evolutionary impact of the spatial radiation and diffusion of maritime risks and the temporal inertial continuation, significantly improving the authenticity and reference value of maritime risk assessment results. Furthermore, through adaptive dynamic weighting, it enhances the adaptability to cross-sea scenarios.
[0106] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.
[0107] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.
[0108] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.
[0109] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.
[0110] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.
[0111] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.
[0112] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above 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 coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.
[0113] The units described above 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.
[0114] 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.
[0115] 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 medium. 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 storage medium and includes multiple 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 of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0116] The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.
Claims
1. A method for dynamic assessment and early warning of maritime spatiotemporal risks, characterized in that, The method includes the following steps: The target sea area is determined, and an adaptive spatiotemporal coupled grid and risk factor dataset for the target sea area are constructed; wherein, the risk factor dataset includes physical threat factor data, unmanned system threat factor data, digital domain interference factor data, marine environmental risk factor data, and waterway vulnerability factor data; Using each grid in the adaptive spatiotemporal coupling grid as a unit, the risk factor dataset is normalized based on a preset normalization processing algorithm; Based on the normalized risk factor dataset, the assigned weight of each risk factor is dynamically calculated, thereby obtaining the original risk value in each grid of the adaptive spatiotemporal coupled grid. Spatiotemporal nonlinear fusion and saturation suppression correction are performed on the original risk value of each grid to obtain the risk correction value of each grid; The risk correction value of each grid is filtered and combined with the preset risk assessment and grading rules to determine the risk assessment level of each grid. The result is then output through visualization rendering to obtain the dynamic assessment and early warning result of the marine spatiotemporal risk of the target sea area.
2. The method according to claim 1, characterized in that, The process of determining the target sea area and constructing an adaptive spatiotemporally coupled grid and risk factor dataset for the target sea area includes: Determine the target sea area and, based on the extreme latitude and longitude values of the target sea area, trim the grid according to the preset spatial resolution; The longitude step size is dynamically adjusted based on the latitude of each grid, and time-series slicing is performed according to a preset time interval to complete the construction of an adaptive spatiotemporal coupled grid for the target sea area. According to the preset time interval, multi-source heterogeneous data are synchronously collected for each grid, including physical threat factor data, unmanned system threat factor data, digital domain interference factor data, marine environmental risk factor data, and waterway vulnerability factor data, thereby completing the construction of the risk factor dataset for the target sea area.
3. The method according to claim 1, characterized in that, The step of performing normalization processing on the risk factor dataset based on a preset normalization processing algorithm, using each grid in the adaptive spatiotemporal coupled grid as a unit, includes: Using each grid in the adaptive spatiotemporal coupling grid as a unit, the preset sliding window dynamic extreme value and the global steady-state extreme value are obtained, and the weighted calculation is used to obtain the mixed extreme value; Based on the mixed extreme values and the risk factor dataset, normalization is performed using an extreme value standardization algorithm.
4. The method according to claim 1, characterized in that, The process of dynamically calculating the assigned weight of each risk factor based on the normalized risk factor dataset, thereby calculating the original risk value on a per-grid basis in the adaptive spatiotemporal coupled grid, includes: Based on the normalized risk factor dataset, the mean and standard deviation of each risk factor in each grid under each time slice are obtained, and then the coefficient of variation of each risk factor is calculated. Based on the coefficient of variation of each risk factor, the objective weight of each risk factor is calculated. Combined with the preset prior weight, the assigned weight of each risk factor is dynamically calculated. The original risk value for each grid is calculated by weighting the assigned weight of each risk factor with the normalized observation values of the risk factors in each grid of the adaptive spatiotemporal coupled grid.
5. The method according to claim 1, characterized in that, The process of performing spatiotemporal nonlinear fusion and saturation suppression correction on the original risk value of each grid to obtain the risk correction value for each grid includes: The original risk value of each grid is spatially smoothed using a Gaussian kernel, and time fusion is performed using an exponential decay function to complete the spatiotemporal nonlinear fusion. By combining the preset suppression threshold gradient gradation range, a matching saturation suppression correction is performed on each grid to obtain the risk correction value for each grid.
6. The method according to claim 1, characterized in that, The process involves filtering the risk correction value for each grid and combining it with preset risk assessment grading rules to determine the risk assessment level for each grid. This level is then output through visualization rendering to obtain the dynamic spatiotemporal risk assessment and early warning results for the target sea area, including: The risk correction value of each grid is filtered by the Kalman time-series filtering algorithm, and the risk assessment level of each grid is determined by combining it with the preset risk assessment classification rules. The risk assessment level of each grid is smoothly calculated using a bilinear interpolation algorithm. Different colors are used to visualize and render the data according to different risk assessment levels, and the final rendered image is output to obtain the dynamic assessment and early warning results of the marine spatiotemporal risks of the target sea area.
7. A dynamic assessment and early warning device for maritime spatiotemporal risks, characterized in that, The device includes: The data acquisition module is used to determine the target sea area and construct an adaptive spatiotemporal coupled grid and risk factor dataset for the target sea area; wherein, the risk factor dataset includes physical threat factor data, unmanned system threat factor data, digital domain interference factor data, marine environmental risk factor data, and waterway vulnerability factor data; The data processing module is used to perform normalization processing on the risk factor dataset based on a preset normalization processing algorithm, taking each grid in the adaptive spatiotemporal coupling grid as a unit. The data calculation module is used to dynamically calculate the assigned weight of each risk factor based on the normalized risk factor dataset, thereby calculating the original risk value in each grid of the adaptive spatiotemporal coupled grid. The data correction module is used to perform spatiotemporal nonlinear fusion and saturation suppression correction on the original risk value of each grid to obtain the risk correction value of each grid. The data output module is used to filter the risk correction value of each grid, and in combination with the preset risk assessment and grading rules, determine the risk assessment level of each grid, and output it through visualization rendering to obtain the dynamic assessment and early warning results of the marine spatiotemporal risks of the target sea area.
8. An electronic device, characterized in that, The electronic device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the method according to any one of claims 1 to 6.
9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 6.
10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 6.
