Power transmission channel fire risk grade determination method and device and electronic equipment

Abstract

The invention discloses a power transmission channel fire risk grade determination method and apparatus, and an electronic device. The method comprises the steps that a target request is received, and the target request is used for determining a fire risk level corresponding to a power transmission channel; in response to the target request, determining topographic data, vegetation data and meteorological data corresponding to the power transmission channel; determining a dryness index corresponding to the power transmission channel according to the vegetation data and the meteorological data; according to the topographic data, determining a topographic complex index corresponding to the power transmission channel; and determining a fire risk level corresponding to the power transmission channel according to the terrain complexity index and the dryness index. The technical problem that when the fire risk level of the power transmission channel is determined, the fire risk level is determined inaccurately is solved.

Description

Technical Field

[0001] The present invention relates to the field of data, and in particular to a method, device and electronic equipment for determining the fire risk level of a power transmission channel. Background Art

[0002] In related technologies, fires in transmission channels may not only cause damage to power equipment and line interruption, but may also trigger large-scale power outages. Due to various uncertain factors such as the uncertainty of the time of fire occurrence and the uncertainty of the spread range, there is a technical problem of inaccurate determination of the fire risk level when determining the fire risk level of the transmission channel.

[0003] To address the above-mentioned problems, no effective solutions have been proposed so far. Summary of the Invention

[0004] Embodiments of the present invention provide a method, device, and electronic device for determining a fire risk level of a power transmission channel, to at least solve the technical problem of inaccurate determination of the fire risk level of a power transmission channel.

[0005] According to one aspect of an embodiment of the present invention, a method for determining a fire risk level of a transmission channel is provided, comprising: receiving a target request, wherein the target request is used to determine a fire risk level corresponding to the transmission channel; determining, in response to the target request, terrain data, vegetation data, and meteorological data corresponding to the transmission channel; determining a dryness index corresponding to the transmission channel based on the vegetation data and the meteorological data; determining a terrain complexity index corresponding to the transmission channel based on the terrain data; and determining a fire risk level corresponding to the transmission channel based on the terrain complexity index and the dryness index.

[0006] Optionally, determining the dryness index corresponding to the transmission channel based on the vegetation data and the meteorological data includes: when the vegetation data includes a vegetation cover index, determining the coverage change index corresponding to the transmission channel based on the vegetation cover index; determining the wind speed corresponding to the transmission channel based on the meteorological data; and determining the dryness index corresponding to the transmission channel based on the coverage change index and the wind speed.

[0007] Optionally, when the vegetation data includes a vegetation cover index, determining the coverage change index corresponding to the transmission channel based on the vegetation cover index includes: when the vegetation cover index includes multiple historical coverage indices and a current coverage index, determining the maximum coverage index and the minimum coverage index corresponding to the transmission channel from the multiple historical coverage indices; determining the current difference index based on the current coverage index and the minimum coverage index; determining the historical difference index based on the maximum coverage index and the minimum coverage index; and determining the coverage change index corresponding to the transmission channel based on the current difference index and the historical difference index.

[0008] Optionally, determining the terrain complexity index corresponding to the transmission channel based on the terrain data includes: determining a regional division scale corresponding to the terrain data; dividing the transmission channel based on the regional division scale to obtain multiple regions corresponding to the transmission channel; determining regional complexity indices corresponding to the multiple regions respectively based on the terrain data; and determining the terrain complexity index corresponding to the transmission channel based on the regional complexity indices corresponding to the multiple regions respectively.

[0009] Optionally, determining the regional complexity indexes corresponding to the multiple areas respectively based on the terrain data includes: when the terrain data includes height data and slope data, determining the undulation indexes corresponding to the multiple areas respectively based on the height data; determining the inclination indexes corresponding to the multiple areas respectively based on the slope data; determining the regional complexity indexes corresponding to the multiple areas respectively based on the undulation indexes and the inclination indexes corresponding to the multiple areas respectively.

[0010] Optionally, determining the fire risk level corresponding to the transmission channel based on the terrain complexity index and the dryness index includes: when the transmission channel is divided into multiple areas, determining the spatiotemporal characteristics corresponding to the multiple areas respectively based on the terrain complexity index and the dryness index; determining multiple spatiotemporal similarity indices corresponding to the multiple areas respectively based on the spatiotemporal characteristics corresponding to the multiple areas respectively; determining fusion characteristics corresponding to the multiple areas respectively based on the spatiotemporal characteristics corresponding to the multiple areas respectively and the multiple spatiotemporal similarity indices; and determining the fire risk level corresponding to the transmission channel based on the fusion characteristics corresponding to the multiple areas respectively.

[0011] Optionally, the fire risk level corresponding to the transmission channel is determined based on the terrain complexity index and the dryness index, including: when the risk level includes multiple levels, determining the level thresholds corresponding to the multiple levels respectively; determining the risk index corresponding to the transmission channel based on the terrain complexity index and the dryness index; determining the fire risk level corresponding to the transmission channel based on the risk index corresponding to the transmission channel and the level thresholds corresponding to the multiple levels respectively.

[0012] According to one aspect of an embodiment of the present invention, a device for determining a fire risk level of a transmission channel is provided, comprising: a receiving module for receiving a target request, wherein the target request is used to determine the fire risk level corresponding to the transmission channel; a response module for determining terrain data, vegetation data and meteorological data corresponding to the transmission channel in response to the target request; a first determination module for determining a dryness index corresponding to the transmission channel based on the vegetation data and the meteorological data; a second determination module for determining a terrain complexity index corresponding to the transmission channel based on the terrain data; and a third determination module for determining the fire risk level corresponding to the transmission channel based on the terrain complexity index and the dryness index.

[0013] According to one aspect of an embodiment of the present invention, an electronic device is provided, comprising: a processor; and a memory for storing instructions executable by the processor; wherein the processor is configured to execute the instructions to implement any of the above-mentioned methods for determining the fire risk level of a power transmission channel.

[0014] According to one aspect of an embodiment of the present invention, a computer-readable storage medium is provided. When the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device can execute any of the above-mentioned methods for determining the fire risk level of a power transmission channel.

[0015] In an embodiment of the present invention, a target request is received, wherein the target request is used to determine a fire risk level corresponding to a transmission channel; in response to the target request, terrain data, vegetation data, and meteorological data corresponding to the transmission channel are determined; a dryness index corresponding to the transmission channel is determined based on the vegetation data and meteorological data; a terrain complexity index corresponding to the transmission channel is determined based on the terrain data; and a fire risk level corresponding to the transmission channel is determined based on the terrain complexity index and the dryness index. By combining vegetation and meteorological data to determine the dryness index, the degree of vegetation dryness and fire susceptibility in the transmission channel can be accurately reflected. Determining the terrain complexity index using terrain data can accurately quantify the potential difficulty of fire propagation in space. By combining the terrain complexity index and the dryness index, the environmental conditions and fuel status of the transmission channel fire can be comprehensively analyzed, thereby significantly improving the accuracy of risk level judgment, thereby solving the technical problem of inaccurate fire risk level determination when determining the fire risk level of the transmission channel. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0017] Figure 1 is a flow chart of a method for determining a fire risk level of a power transmission channel according to an embodiment of the present invention;

[0018] Figure 2 This is a schematic diagram of a technology route for predicting the spatiotemporal distribution of fire points in power transmission channels in an optional embodiment of the present invention;

[0019] Figure 3 This is a structural block diagram of a device for determining a fire risk level of a power transmission channel according to an embodiment of the present invention. DETAILED DESCRIPTION

[0020] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0021] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0022] First, some nouns or terms that appear in the description of the embodiments of the present application are subject to the following interpretations:

[0023] CSV format: CSV (Comma-Separated Values) is a commonly used data file format for storing tabular data, including numbers and text.

[0024] GeoJSON format: GeoJSON is an open standard format for representing geospatial data and features.

[0025] WGS84 coordinate system: WGS84 coordinate system is a globally used geographic coordinate system.

[0026] Kriging: Kriging is a statistical interpolation method used to predict the value of an unknown point based on the values ​​of known points while providing a confidence level, or error estimate, for the prediction.

[0027] Stochastic Gradient Descent (SGD) Algorithm: Stochastic Gradient Descent (SGD) algorithm is an optimization algorithm used to minimize the loss function in machine learning.

[0028] DS Evidence Theory: DS (Dempster-Shafer) evidence theory is a mathematical framework for uncertain information processing, which provides a theoretical basis for decision-making under incomplete or uncertain information.

[0029] AUC value: AUC (Area Under the Curve) value is an indicator for evaluating the performance of classification models, especially binary classification models.

[0030] SVM: SVM is a supervised learning model used for classification and regression analysis.

[0031] Softmax function: The softmax function is a mathematical function used in machine learning and neural networks to convert a set of numerical values ​​into a probability distribution.

[0032] Example 1

[0033] According to an embodiment of the present invention, an embodiment of a method for determining the fire risk level of a power transmission channel is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0034] Figure 1 FIG. 1 is a flow chart of a method for determining a fire risk level of a power transmission channel according to an embodiment of the present invention. Figure 1 As shown, the method includes the following steps:

[0035] S102, receiving a target request, wherein the target request is used to determine a fire risk level corresponding to a power transmission channel;

[0036] In step S102 provided in the present application, a target request for determining a fire risk level corresponding to a power transmission channel is received.

[0037] This involves a target request, which is used to trigger the determination of the transmission channel risk level. The purpose is to initiate the process of fire risk assessment for the transmission channel. This target request can be issued by the power system monitoring center, automatic monitoring system, or monitoring object.

[0038] This involves transmission channels, which are pathways used for power transmission and include components such as high-voltage transmission lines, substations, towers, and cables. In other words, a transmission channel can also be an area where power transmission facilities are laid. Through this transmission channel, power can be transmitted from power plants to consumers or to the next-level power network. This transmission channel can also run through mountainous areas, forests, or arid regions.

[0039] Among them, the fire risk level is involved. This fire risk level is used to quantify the likelihood of fire and the potential threat level of the transmission corridor. The fire risk level can be qualitative (such as low, medium, and high risk) or quantitative (such as level 1 to level 5 risk).

[0040] By receiving the target request, the specific transmission channel for which the fire risk level needs to be determined can be clearly identified, providing an analysis object for the subsequent determination of the fire risk level, thereby facilitating subsequent targeted analysis based on the specific transmission channel.

[0041] S104, in response to the target request, determining terrain data, vegetation data, and meteorological data corresponding to the power transmission channel;

[0042] In step S104 provided in the present application, the target request is responded to, and the terrain data, vegetation data and meteorological data corresponding to the power transmission channel are determined.

[0043] Among them, terrain data is involved, which is data used to reflect the terrain characteristics of the transmission channel, such as altitude, slope, terrain type (such as plains, mountains, etc.), etc.

[0044] Among them, vegetation data is involved, which is data used to reflect the vegetation characteristics of the transmission channel, such as vegetation type, vegetation coverage, vegetation dryness, vegetation continuity, etc.

[0045] Among them, meteorological data is involved, which is data used to reflect the meteorological characteristics of the transmission channel, such as temperature, humidity, wind speed, wind direction, precipitation, etc.

[0046] By analyzing terrain data, we can reflect the physical obstacles and acceleration conditions for fire spread. By analyzing vegetation data, we can assess the fuel conditions and spread potential of the fire. Moreover, by analyzing meteorological data, we can understand the meteorological factors that affect the occurrence and spread rate of fire (such as the impact on the dryness of the transmission channel). By determining the terrain data, vegetation data and meteorological data corresponding to the transmission channel, we provide a reliable data basis for the subsequent comprehensive analysis of the fire risk level of the transmission channel.

[0047] S106, determining a dryness index corresponding to the power transmission channel based on vegetation data and meteorological data;

[0048] In step S106 provided in the present application, a dryness index corresponding to the power transmission channel is determined based on vegetation data and meteorological data.

[0049] This involves the aridity index, which quantifies the dryness of transmission corridors. This index is typically determined by combining vegetation data (which indicates the state of vegetation) with meteorological data (which indicates current weather conditions) to quantify the flammability of vegetation as fire fuel. For example, a high aridity index indicates dry and flammable vegetation, increasing the probability of fire and its spread.

[0050] S108, determining a terrain complexity index corresponding to the transmission channel based on the terrain data;

[0051] In step S108 provided in the present application, a terrain complexity index corresponding to the power transmission channel is determined based on the terrain data.

[0052] This involves the Terrain Complexity Index, which quantifies the impact of terrain on the complexity of fire spread. This index reflects the irregularity and complexity of the terrain, influencing the speed and direction of fire spread. For example, a higher terrain complexity index indicates that the fire encounters more natural obstacles during its spread, thus affecting the fire's path and speed.

[0053] Through terrain data, the irregularity and complexity of the terrain, such as slope changes and terrain undulations, can be captured, so that the terrain complexity index of the transmission channel can be accurately quantified, which will help to subsequently assess the fire risk level in combination with the terrain complexity index from a spatial perspective, so as to improve the comprehensiveness and accuracy of the assessment.

[0054] S110: Determine a fire risk level corresponding to the power transmission channel based on the terrain complexity index and the dryness index.

[0055] In step S110 provided in the present application, the fire risk level corresponding to the power transmission channel is determined based on the terrain complexity index and the dryness index.

[0056] The terrain complexity index quantifies the potential impact of terrain undulations and slope changes on the path and speed of fire spread, while the dryness index directly reflects the burning tendency of vegetation. By combining the terrain complexity index and the dryness index, we can comprehensively analyze the environmental conditions and fuel status of transmission channel fires, thereby significantly improving the accuracy of risk level judgments and reducing misjudgments.

[0057] Furthermore, determining the fire risk level corresponding to the transmission corridor based on the terrain complexity index and the dryness index may further include determining historical risk characteristics corresponding to the transmission corridor, and determining the fire risk level corresponding to the transmission corridor based on the historical fire risk characteristics, the terrain complexity index, and the dryness index. The historical risk characteristics are fire risk characteristics exhibited by the transmission corridor over a historical period, such as the analyzed annual or monthly cycle characteristics of fire risk for the transmission corridor.

[0058] Through the above steps S102-S110, a target request is received, wherein the target request is used to determine the fire risk level corresponding to the transmission channel; in response to the target request, terrain data, vegetation data, and meteorological data corresponding to the transmission channel are determined; based on the vegetation data and meteorological data, a dryness index corresponding to the transmission channel is determined; based on the terrain data, a terrain complexity index corresponding to the transmission channel is determined; and based on the terrain complexity index and the dryness index, a fire risk level corresponding to the transmission channel is determined. By combining vegetation and meteorological data to determine the dryness index, the degree of vegetation dryness and fire susceptibility in the transmission channel can be accurately reflected. Determining the terrain complexity index using terrain data can accurately quantify the potential difficulty of fire propagation in space. By combining the terrain complexity index and the dryness index, the environmental conditions and fuel status of the transmission channel fire can be comprehensively analyzed, thereby significantly improving the accuracy of risk level judgment, thereby solving the technical problem of inaccurate fire risk level determination when determining the fire risk level of the transmission channel.

[0059] As an optional embodiment, the dryness index corresponding to the transmission channel is determined based on vegetation data and meteorological data, including: when the vegetation data includes a vegetation cover index, determining the coverage change index corresponding to the transmission channel based on the vegetation cover index; determining the wind speed corresponding to the transmission channel based on the meteorological data; and determining the dryness index corresponding to the transmission channel based on the cover change index and the wind speed.

[0060] In this embodiment, specific steps of determining the dryness index corresponding to the power transmission channel based on vegetation data and meteorological data are described.

[0061] Among them, the vegetation cover index is involved. The vegetation cover index is a quantitative indicator to measure the degree of vegetation coverage. It is used to reflect the growth status and coverage density of vegetation. It can be expressed by the Normalized Difference Vegetation Index (NDVI). The NDVI value range is between -1 and 1. The larger the value, the denser the vegetation coverage.

[0062] Among them, the Cover Change Index is involved. This Cover Change Index is used to quantify the degree of change in vegetation cover over time. The Cover Change Index can reflect seasonal or long-term changes in vegetation growth status and the impact of disturbances (such as drought, fire, disease, etc.) through the changing characteristics (such as the rate of change or the magnitude of change) of vegetation cover indices (such as NDVI values).

[0063] Wind speed is a measure of wind speed in meteorological data, representing the speed of air relative to the ground. The magnitude and direction of wind speed directly influence the speed and direction of fire spread. For example, in the fire risk assessment of power transmission corridors, high wind speeds accelerate fire spread and increase the difficulty of extinguishing the fire; conversely, low wind speeds facilitate fire control.

[0064] In the steps involved in this embodiment, if the vegetation data includes a vegetation cover index, first, a cover variation index corresponding to the transmission channel is determined based on the vegetation cover index. Then, the wind speed corresponding to the transmission channel is determined based on the meteorological data. Finally, a dryness index corresponding to the transmission channel is determined based on the cover variation index and the wind speed.

[0065] The cover change index can accurately reflect the changing state of vegetation in the transmission channel, while the wind speed can quantify the meteorological conditions for fire spread. Therefore, by combining the cover change index and wind speed, the dryness index of the transmission channel can be determined. This achieves a comprehensive consideration of the flammability of vegetation as fire fuel and the role of wind speed as a fire accelerator, which helps to more accurately determine the fire risk level of the transmission channel.

[0066] As an optional embodiment, when the vegetation data includes a vegetation cover index, the coverage change index corresponding to the transmission channel is determined based on the vegetation cover index, including: when the vegetation cover index includes multiple historical coverage indices and a current coverage index, determining the maximum coverage index and the minimum coverage index corresponding to the transmission channel from the multiple historical coverage indices; determining the current difference index based on the current coverage index and the minimum coverage index; determining the historical difference index based on the maximum coverage index and the minimum coverage index; and determining the coverage change index corresponding to the transmission channel based on the current difference index and the historical difference index.

[0067] In this embodiment, specific steps of determining a coverage change index corresponding to a power transmission channel according to the vegetation coverage index are described when the vegetation data includes the vegetation coverage index.

[0068] This involves multiple historical cover indices, which are quantitative indices representing vegetation cover over a historical time period (such as the past season, year, or a predetermined historical period). These indices can reflect cyclical changes or long-term trends in vegetation cover, providing a time-series reference for assessing the fire risk level of transmission corridors.

[0069] This involves the current cover index, which represents the degree of vegetation cover in the current state of the transmission corridor. This index reflects the current state of vegetation cover in the transmission corridor and provides direct information on whether there is sufficient dry vegetation to serve as fire fuel.

[0070] The maximum coverage index is the maximum value of the vegetation coverage index of the transmission corridor during the historical period. The maximum coverage index reflects the most lush and dense vegetation growth and coverage of the transmission corridor during the historical period.

[0071] The minimum coverage index is the minimum value of the vegetation coverage index of the transmission corridor during the historical period. The minimum coverage index reflects the state of the least lush vegetation growth and the most sparse coverage during the historical period.

[0072] The current difference index is used to represent the difference between the current coverage index and the minimum coverage index. This index reflects the difference between the current vegetation coverage of the transmission corridor and the driest or sparsest vegetation coverage in the transmission corridor during a historical period, and can be used to quantify the dryness of the current vegetation.

[0073] Among them, the historical difference index is involved, which is used to express the degree of difference between the maximum coverage index and the minimum coverage index, reflecting the changing characteristics of vegetation coverage of the transmission channel in historical records.

[0074] In the steps involved in this embodiment, when the vegetation cover index includes multiple historical cover indices and a current cover index, first, the maximum cover index and the minimum cover index corresponding to the transmission channel are determined from the multiple historical cover indices. Then, based on the current cover index and the minimum cover index, the current difference index of the vegetation cover of the transmission channel is determined. Next, based on the maximum cover index and the minimum cover index, the historical difference index of the vegetation cover of the transmission channel is determined. Finally, based on the current difference index and the historical difference index, the coverage change index corresponding to the transmission channel is determined.

[0075] The current difference index can directly reflect the degree of difference between the current vegetation state and the driest state in history. The historical difference index can reflect the historical change characteristics of vegetation coverage in the transmission channel. Therefore, the coverage change index is determined by combining the current difference index and the historical difference index. It can not only reflect the degree of change of the quantitative vegetation coverage state over time, but also help to analyze whether the current vegetation condition deviates from the historical characteristics, which in turn helps to accurately determine the dryness index of the transmission channel in the future.

[0076] As an optional embodiment, determining a terrain complexity index corresponding to a transmission channel based on terrain data includes: determining a regional division scale corresponding to the terrain data; dividing the transmission channel based on the regional division scale to obtain multiple regions corresponding to the transmission channel; determining regional complexity indices corresponding to the multiple regions based on the terrain data; and determining a terrain complexity index corresponding to the transmission channel based on the regional complexity indices corresponding to the multiple regions.

[0077] In this embodiment, specific steps of determining a terrain complexity index corresponding to a power transmission channel based on terrain data are described.

[0078] This involves the regional division scale, which is the scale used to divide transmission channels or the regions corresponding to transmission channels. For example, the regional division scale can be the geographic spatial resolution used when analyzing terrain data. Determining the regional division scale requires balancing the level of analysis detail with the complexity of data processing. A scale that is too fine may increase the computational burden, while a scale that is too coarse may lose important terrain details. A reasonable regional division scale can not only capture changes in terrain characteristics but also maintain the efficiency of analysis.

[0079] Wherein, multiple regions are involved, and the multiple regions are a number of geographical units into which the transmission channel, or the transmission channel and its surrounding environment, is divided according to a selected regional division scale. For example, multiple grids corresponding to a predetermined geographic spatial resolution can be considered as the multiple regions.

[0080] This involves the regional complexity index, which is a quantitative indicator calculated based on terrain data for each divided region. The regional complexity index reflects the terrain characteristics of the region, such as irregularity and complexity.

[0081] This involves the terrain complexity index, which is a quantitative indicator of the complexity of the terrain of the transmission corridor (such as the transmission corridor and the area surrounding it) calculated based on the regional complexity index of the divided areas. The terrain complexity index comprehensively reflects the topographic characteristics of the transmission corridor and its surrounding environment.

[0082] In the steps involved in this embodiment, first, a regional division scale corresponding to the terrain data is determined. The transmission channel is then divided according to the regional division scale to obtain multiple regions corresponding to the transmission channel. Then, regional complexity indices corresponding to each of the multiple regions are determined based on the terrain data. Finally, a terrain complexity index corresponding to the transmission channel is determined based on the regional complexity indices corresponding to each of the multiple regions.

[0083] By rationally defining the regional division scale, we ensure comprehensive terrain feature analysis and achieve a reasonable geographic granularity for fire risk assessment. By dividing transmission corridors according to the regional division scale and determining the regional complexity index corresponding to each region based on terrain data, we can more meticulously capture and quantify the potential impact of terrain on fire propagation, providing reliable data for accurately assessing fire risk along transmission corridors over time.

[0084] As an optional embodiment, regional complexity indexes corresponding to multiple regions are determined based on terrain data, including: when the terrain data includes height data and slope data, determining the undulation indexes corresponding to the multiple regions based on the height data; determining the inclination indexes corresponding to the multiple regions based on the slope data; and determining the regional complexity indexes corresponding to the multiple regions based on the undulation indices and inclination indices corresponding to the multiple regions.

[0085] In this embodiment, specific steps of determining regional complexity indices corresponding to a plurality of regions respectively based on terrain data are described.

[0086] Herein, altitude data is involved, and the altitude data is the geographical altitude of the corresponding area. The geographical altitude may be the height of the ground surface of a certain area relative to a certain reference plane (such as sea level).

[0087] This involves slope data, which is the angle of inclination of the ground surface relative to the horizontal plane and is used to quantify the slope of the terrain. This slope data can be obtained by calculating the height difference (e.g., elevation difference) and distance between adjacent points.

[0088] The undulation index is a quantitative indicator used to reflect the degree of terrain undulation. The undulation index can be used to measure the complexity and ruggedness of the terrain by statistically analyzing the amplitude and frequency of height changes (such as elevation changes) within an area.

[0089] Among them, the tilt index is involved. The tilt index is a quantitative indicator to measure the degree of terrain tilt, which reflects the degree of terrain tilt, that is, the size of the slope.

[0090] In the steps of this embodiment, when the terrain data includes altitude data and slope data, first, the relief index corresponding to each of the multiple regions is determined based on the altitude data, and the slope index corresponding to each of the multiple regions is determined based on the slope data. Then, the regional complexity index corresponding to each of the multiple regions is determined based on the relief index and slope index corresponding to each of the multiple regions.

[0091] The undulation index reflects the irregularity and complexity of the terrain, while the tilt index quantifies the slope of the terrain. The combined use of the two can fully capture the characteristics of the terrain and help accurately identify areas with complex terrain and steep slopes, thereby facilitating the subsequent accurate analysis of the fire risk level of the transmission channel from a spatial perspective.

[0092] As an optional embodiment, the fire risk level corresponding to the transmission channel is determined based on the terrain complexity index and the dryness index, including: when the transmission channel is divided into multiple areas, based on the terrain complexity index and the dryness index, determining the spatiotemporal characteristics corresponding to the multiple areas respectively; determining multiple spatiotemporal similarity indices corresponding to the multiple areas respectively based on the spatiotemporal characteristics corresponding to the multiple areas respectively; determining fusion characteristics corresponding to the multiple areas respectively based on the spatiotemporal characteristics corresponding to the multiple areas respectively and the multiple spatiotemporal similarity indices; and determining the fire risk level corresponding to the transmission channel based on the fusion characteristics corresponding to the multiple areas respectively.

[0093] In this embodiment, specific steps for determining the fire risk level corresponding to the power transmission channel based on the terrain complexity index and the dryness index are described.

[0094] Among them, the spatiotemporal characteristics are involved, which are determined based on the terrain complexity index and dryness index, and are used to comprehensively reflect the characteristic information related to fire risk assessment of the transmission channel at the temporal and spatial levels.

[0095] Among them, multiple spatiotemporal similarity indices are involved, which are used to evaluate the similarity between regions in terrain complexity index and dryness index, that is, to quantify the neighborhood effect between regions.

[0096] This involves fusion features, which combine the spatiotemporal characteristics of multiple regions with corresponding spatiotemporal similarity indices. This fusion feature helps comprehensively capture and quantify the impact of terrain, vegetation status, and interactions between regions on fire risk.

[0097] In the steps involved in this embodiment, when the power transmission corridor is divided into multiple regions, the following steps are performed: first, the spatiotemporal features corresponding to each of the multiple regions are determined based on the terrain complexity index and the dryness index. Then, the multiple regions are fused. Finally, the fire risk level corresponding to the power transmission corridor is determined based on the fused features corresponding to the multiple regions.

[0098] By dividing the transmission channel into multiple smaller areas and calculating the corresponding spatiotemporal characteristics of each area based on the terrain complexity index and dryness index, the environmental conditions of each area can be analyzed more carefully. On this basis, the impact of the neighborhood effect on the spatiotemporal characteristics of each area is further considered. By determining the spatiotemporal similarity index between each area, the realization of the neighborhood effect between multiple areas is accurately quantified. Therefore, by combining the spatiotemporal characteristics and the spatiotemporal similarity index, the possible propagation pattern of the fire point in each area can be captured more accurately.

[0099] As an optional embodiment, the fire risk level corresponding to the transmission channel is determined based on the terrain complexity index and the dryness index, including: when the risk level includes multiple levels, determining the level thresholds corresponding to the multiple levels respectively; determining the risk index corresponding to the transmission channel based on the terrain complexity index and the dryness index; determining the fire risk level corresponding to the transmission channel based on the risk index corresponding to the transmission channel and the level thresholds corresponding to the multiple levels respectively.

[0100] In this embodiment, specific steps for determining the fire risk level corresponding to the power transmission channel based on the terrain complexity index and the dryness index are described.

[0101] Multiple levels are involved, which divide fire risk into multiple risk levels based on the level of risk. For example, level 1 can be set as the lowest risk and level 5 as the highest risk. Each level corresponds to different risk status and early warning measures.

[0102] This involves level thresholds, which are used to distinguish different risk levels. For example, if a risk index between 0 and 0.3 is considered low risk, 0.3 to 0.6 is medium risk, and above 0.6 is high risk, then 0.3 and 0.6 are the level thresholds used to distinguish low-risk, medium-risk, and high-risk areas.

[0103] This involves a risk index, which is calculated based on the terrain complexity index and the dryness index to quantify the fire risk level of transmission corridors. For example, a higher risk index means a higher fire risk, while a lower risk index means a lower risk level.

[0104] In the steps involved in this embodiment, if the risk level includes multiple levels, first, level thresholds corresponding to each of the multiple levels are determined. Then, a risk index corresponding to the transmission corridor is determined based on the terrain complexity index and the dryness index. Finally, the fire risk level corresponding to the transmission corridor is determined based on the risk index corresponding to the transmission corridor and the level thresholds corresponding to the multiple levels.

[0105] In the case of multiple risk levels, the fire risk level corresponding to the transmission corridor is determined by defining thresholds corresponding to each level and calculating a risk index based on the terrain complexity index and dryness index. This enables refined management and early warning of fire risks, reducing the potential threat posed by fire to the safe operation of the transmission corridor and its power system. Furthermore, by setting multiple risk levels and thresholds, varying degrees of resource allocation and response level adjustment are supported, ensuring that high-risk areas are prioritized within limited emergency resources, achieving optimal resource utilization.

[0106] Based on the above embodiment and optional embodiment, an optional implementation manner is provided, which is described in detail below.

[0107] In related technologies, fires in transmission channels may not only cause damage to power equipment and line interruption, but may also trigger large-scale power outages. Due to various uncertain factors such as the uncertainty of the time of fire occurrence and the uncertainty of the spread of the fire, there is a technical problem of inaccurate determination of the fire risk level when determining the fire risk level of the transmission channel.

[0108] To address the above-mentioned problems, no effective solutions have been proposed so far.

[0109] In view of this, an optional embodiment of the present invention provides a method for determining the fire risk level of a transmission channel, which can also be called a method for predicting the spatiotemporal distribution of fire points in a transmission channel, which can effectively solve the technical problem of inaccurate determination of the fire risk level when determining the fire risk level of a transmission channel.

[0110] Figure 2 FIG. 1 is a schematic diagram of a technology route for predicting the spatiotemporal distribution of fire points in a transmission channel in an optional embodiment of the present invention. Figure 2 As shown, the following is described in detail.

[0111] S1, data acquisition and fusion;

[0112] S11, fire point data:

[0113] Satellite fire data is used. This data spans 2004-2024 and has a spatial resolution of 375 meters. Satellite fire data has high temporal resolution and good spatial coverage. Fire data is a core data source for model training and validation, providing the precise location and occurrence time of fires.

[0114] Fire point data is typically stored in CSV or GeoJSON format and contains information such as the fire point's longitude, latitude, occurrence time, and confidence level. After data collection is complete, the fire point data needs to be cleaned. Duplicate records, outliers, and low-confidence fire point data should be removed to improve data quality and reliability.

[0115] S12, Environmental data:

[0116] Environmental data include Digital Elevation Model (DEM) terrain data (spatial resolution of 30 meters), Normalized Difference Vegetation Index (NDVI) vegetation index (8-day composite), and meteorological raster data (wind speed, humidity, precipitation, with a time interval of 6 hours).

[0117] DEM data can provide information such as elevation, slope, and aspect of the terrain. Using 30-meter resolution DEM data, the elevation standard deviation and average slope within the grid (same as the above multiple areas) are calculated through the geographic information system to generate the terrain complexity index T. c .

[0118] NDVI is an important indicator reflecting the growth status and coverage of vegetation. The vegetation dryness index V is generated by using 8-day synthetic NDVI data and calculating the normalized difference between the current NDVI value and the historical minimum and maximum values. d .

[0119] Meteorological data include information such as wind speed, humidity, and precipitation. Meteorological raster data with a 6-hour time interval are used and aligned with DEM and NDVI data through interpolation and resampling.

[0120] S13, data alignment:

[0121] To ensure consistency among multi-source data, all data were resampled to a 1 km × 1 km grid using the WGS84 coordinate system. This process, implemented using geographic information system technology, ensures spatial and temporal alignment of the data. Data alignment is fundamental to multi-source data fusion; only within a unified coordinate system and spatial resolution can information from different data sources be effectively integrated.

[0122] S14, data preprocessing:

[0123] After data collection is completed, the data needs to be preprocessed to ensure the quality and consistency of the data, mainly including missing value filling and data standardization.

[0124] For missing value filling, Kriging interpolation is used to fill the missing values ​​in the data. Kriging interpolation is an interpolation method based on spatial autocorrelation, which can predict the value of unknown data points based on the value of known data points. Its formula is:

[0125]

[0126] in:

[0127] s0 represents an unknown data point;

[0128] s u represents the u-th known data point;

[0129] num represents the total number of known data points used to predict the value of s0;

[0130] Z(s0) represents the value of the point to be interpolated (i.e., the unknown data point);

[0131] λ u is the u-th weight coefficient, satisfying ∑λ u =1.

[0132] Kriging interpolation method can effectively fill missing values ​​in data and improve data integrity and reliability.

[0133] For data normalization, all input data are normalized so that their values ​​range from 0 to 1. The formula is as follows:

[0134]

[0135] in:

[0136] x ′ Represents the standardized data value;

[0137] x represents the original input data value;

[0138] min(x) represents the minimum value in the original data;

[0139] max(x) represents the maximum value in the original data.

[0140] S2, feature engineering;

[0141] S21, Terrain-derived features:

[0142] Determine a regional division scale (i.e., resolution) corresponding to the terrain data; divide the transmission channel based on the regional division scale to obtain multiple regions corresponding to the transmission channel (i.e., multiple grids at the corresponding resolution); determine regional complexity indices corresponding to the multiple regions (i.e., the terrain complexity index of each grid) based on the terrain data; and determine the terrain complexity index corresponding to the transmission channel based on the regional complexity indices corresponding to the multiple regions.

[0143] Terrain complexity is an important indicator to measure the impact of terrain on wildfire spread. The calculation formula of terrain complexity index is:

[0144]

[0145] in:

[0146] T c Represents the terrain complexity index (same as the regional complexity index above);

[0147] σ 高程 Indicates the standard deviation of elevation within the grid (same as the relief index above);

[0148] μ 坡度 Represents the average slope within the grid (same as the slope index above).

[0149] For the terrain complexity index (T c ), which can comprehensively reflect the undulations and slope changes of the terrain and provide the model with richer terrain information.

[0150] For the standard deviation of elevation (σ 高程 ), the standard deviation of elevation reflects the degree of terrain undulation. During wildfire spread, areas with greater terrain undulation are more likely to develop complex fire patterns. By calculating the standard deviation of elevation within a grid, we can quantify the complexity of the terrain.

[0151] For the average slope (μ 坡度 Slope is a key factor influencing the speed and direction of wildfire spread. Flames spread more quickly on steep slopes because gravity accelerates their spread. By calculating the average slope within a grid, we can quantify the slope of the terrain.

[0152] S22, vegetation-derived characteristics.

[0153] The dryness of vegetation directly affects the occurrence and spread of wildfires. The combination of Normalized Difference Vegetation Index (NDVI) and wind speed quantifies the impact of vegetation dryness and wind speed on wildfires. d The formula is:

[0154]

[0155] in:

[0156] V d Indicates the vegetation dryness index (same as the dryness index corresponding to the transmission channel above);

[0157] NDVI 当前 Indicates the current coverage index;

[0158] NDVI 历史最小 represents the minimum covering index;

[0159] NDVI 历史最大 represents the maximum covering index;

[0160] NDVI 当前 -NDVI 历史最小Indicates the current difference index;

[0161] NDVI 历史最大 -NDVI 历史最小 represents the historical difference index;

[0162] Represents the coverage change index.

[0163] NDVI is an important indicator of vegetation growth and coverage. Its value ranges from -1 to 1. Positive values ​​indicate vegetation cover, with larger values ​​indicating more lush vegetation. Negative values ​​indicate areas without vegetation. The dryness of vegetation can be quantified by calculating the normalized difference between the current NDVI value and its historical minimum and maximum values.

[0164] Wind speed is a key meteorological factor influencing the speed and direction of wildfire spread. The greater the wind speed, the faster the flames spread, and the more likely the fire is to get out of control. By multiplying the normalized NDVI value by wind speed, we can comprehensively reflect the impact of vegetation dryness and wind speed on wildfires.

[0165] S3, spatiotemporal prediction model construction;

[0166] S31, construct a spatiotemporal prediction model (hereinafter referred to as the ST-LSTM model).

[0167] The ST-LSTM model consists of a spatial convolution layer, a temporal LSTM layer, and a spatiotemporal attention module. The spatial convolution layer is used to extract spatial features, the temporal LSTM layer is used to capture time series features, and the spatiotemporal attention module is used to fuse temporal and spatial features. The details are as follows:

[0168] (1) Spatial convolution layer:

[0169] The spatial convolution layer extracts spatial features from the input data. Through convolution, the model captures local spatial information, such as terrain undulations and vegetation distribution. The convolution kernel size of the spatial convolution layer is 3×3, with a stride of 1. This setting effectively extracts local spatial features while maintaining the integrity of spatial information.

[0170] (2) Temporal LSTM layer:

[0171] LSTM (Long Short-Term Memory) is a neural network structure that can capture time series characteristics. The temporal LSTM layer is designed to capture temporal variations in fire data, such as changes in meteorological conditions and seasonal variations in vegetation dryness. The LSTM hidden layer has 64 units, which effectively captures long- and short-term dependencies in time series.

[0172] (3) Spatiotemporal Attention Module:

[0173] The spatiotemporal attention module is one of the key points of the model. By introducing the attention mechanism, the model can automatically learn the spatial correlations between different grids. The specific steps include: when the transmission channel is divided into multiple regions, the spatiotemporal characteristics corresponding to each of the multiple regions are determined based on the terrain complexity index and the dryness index; based on the spatiotemporal characteristics corresponding to each of the multiple regions, multiple spatiotemporal similarity indices corresponding to each of the multiple regions are determined; based on the spatiotemporal characteristics corresponding to each of the multiple regions and the multiple spatiotemporal similarity indices, fused features corresponding to each of the multiple regions are determined; and based on the fused features corresponding to each of the multiple regions, the fire risk level corresponding to the transmission channel is determined.

[0174] Spatiotemporal attention weight α ij Indicates the degree of attention of the i-th grid to the j-th grid. By calculating the similarity between hidden states, the model can automatically learn the spatial correlation between different grids. The specific formula is:

[0175]

[0176] in:

[0177] α ij represents the spatiotemporal attention weight (same as the spatiotemporal similarity index above);

[0178] N represents the total number of grids;

[0179] h i Represents the hidden state of the i-th grid (same as the above spatiotemporal features);

[0180] h kn Represents the hidden state of the kn-th grid (same as the above spatiotemporal features);

[0181] W represents the learnable weight matrix.

[0182] This mechanism allows us to dynamically adjust the attention weights between different grids, thereby better capturing the propagation patterns of hotspots. The above formula can be used to normalize similarities into probability values ​​using the softmax function to obtain the attention weights.

[0183] During wildfire spread, the spatial distribution and temporal variation of fire points are interrelated. For example, a fire point is affected by the surrounding terrain, vegetation, and meteorological conditions during its spread, exhibiting a significant neighborhood effect. Traditional time series models (such as LSTM) only capture temporal features while ignoring spatial correlations. By introducing the spatiotemporal attention mechanism, we achieve a deep fusion of temporal and spatial features.

[0184] The spatial and temporal features of different grids are fused by weighted summation. The specific formula is:

[0185]

[0186] in:

[0187] h ′ i is the fused spatiotemporal feature (same as the fused feature above);

[0188] h j is the hidden state of the j-th grid (same as the above spatiotemporal features).

[0189] In this way, the model can dynamically adjust the attention weights between different grids to better capture the propagation patterns of fire points.

[0190] S4, model training and validation.

[0191] S41, hyperparameter settings:

[0192] According to the experimental results, the hyperparameters of the model are set as follows:

[0193] For LSTM hidden layer units: 64. It can effectively capture long-term and short-term dependencies in time series while avoiding overfitting problems caused by overly complex models.

[0194] For spatial convolution kernel: 3×3, stride 1. It can effectively extract local spatial features while maintaining the integrity of spatial information.

[0195] For the loss function: weighted cross entropy is used. The weighted cross entropy loss function can effectively solve the problem of data imbalance and improve the model's ability to identify fire points. The formula is as follows:

[0196] L=-w in y in log∑(p in ),

[0197] in:

[0198] L represents the value of the loss function;

[0199] y in Indicates the true label of the in-th sample;

[0200] p in Indicates the predicted probability of the in-th sample;

[0201] w in Represents the category weight, the fire point area w in =5, non-fire point w in =1.

[0202] S42, model training:

[0203] The model is trained using the Stochastic Gradient Descent (SGD) algorithm. During training, the model parameters are adjusted using the backpropagation algorithm to minimize the loss function. Training continues until the model's loss function converges or the preset number of training rounds is reached.

[0204] For data partitioning: the dataset is divided into training set, validation set and test set. The training set is used for model training, the validation set is used for hyperparameter adjustment and model selection, and the test set is used for final model performance evaluation.

[0205] For the number of training rounds: Based on the experimental results, the number of training rounds is set to 100. After each round of training, the loss function value on the validation set is calculated, and the model with the smallest loss function value is selected as the final model.

[0206] For learning rate adjustment: We use a learning rate decay strategy to gradually reduce the learning rate during training. The initial learning rate is set to 0.001, and it decays to 0.1 every 20 rounds. This learning rate decay strategy can effectively improve model training efficiency and prevent the model from falling into a local optimum during the initial training phase.

[0207] S43, Model Validation:

[0208] Cross-validation: The model is validated using the k-fold cross-validation method. The dataset is divided into k subsets, with k-1 subsets used for training and 1 subset used for validation. This process is repeated k times, and the average is taken as the final performance metric. Cross-validation effectively assesses the generalization ability and stability of the model.

[0209] Performance metrics: Model performance is evaluated using metrics such as AUC, precision, recall, and F1. The AUC is an important indicator for measuring a model's classification ability; higher values ​​indicate better performance. Precision and recall measure the model's ability to distinguish between positive and negative samples, respectively. The F1 value is the harmonic mean of these two metrics, providing a comprehensive reflection of model performance.

[0210] When the risk level includes multiple levels, the level thresholds corresponding to the multiple levels are determined; the risk index corresponding to the transmission channel is determined based on the terrain complexity index and the dryness index; the fire risk level corresponding to the transmission channel is determined based on the risk index corresponding to the transmission channel and the level thresholds corresponding to the multiple levels.

[0211] For example, based on the prediction results, the wildfire risk of the transmission channel is divided into 5 levels (the same as the multiple levels mentioned above). Table 1 is a wildfire risk level classification table. The specific classification standards are shown in Table 1:

[0212] Table 1

[0213] Risk Level Probability interval Early warning measures Level 1 <0.3 Daily inspections Level 2 0.3-0.5 Strengthen inspections Level 3 0.5-0.7 Early warning notification Level 4 0.7-0.8 Emergency Preparedness Level 5 ≥0.8 Emergency power off

[0214] Through the above steps, terrain, vegetation, and meteorological data are integrated using the DS evidence theory, achieving deep coupling of multi-source data. Compared with traditional weighted fusion methods, the conflict factor resolution rate is improved by 62%. This innovation effectively resolves conflicts between multi-source data and improves the quality of model input data.

[0215] Furthermore, the spatiotemporal prediction model achieved an AUC of 0.93, a 31% improvement over the traditional SVM (AUC = 0.71). The 72-hour warning accuracy reached ≥82%. This significant performance improvement can provide more accurate predictions for wildfire warnings in power systems.

[0216] Furthermore, the spatiotemporal prediction model supports dynamic rendering on the geographic information platform and generates optimized inspection routes. By optimizing inspection routes, emergency response times can be shortened by over 40%, improving power system operation and maintenance efficiency while also reducing the threat of wildfires to safe operation.

[0217] Through the above optional implementation, at least the following beneficial effects can be achieved:

[0218] (1) Compared with the related art, the present invention determines the dryness index by combining vegetation and meteorological data, which can accurately reflect the vegetation dryness and fire susceptibility of the transmission channel, and determines the terrain complexity index by terrain data, which can accurately quantify the potential difficulty of fire propagation in space. By combining the terrain complexity index and the dryness index, the environmental conditions and fuel status of the occurrence of fire in the transmission channel can be comprehensively analyzed, thereby significantly improving the accuracy of risk level judgment, and thus solving the technical problem of inaccurate determination of fire risk level when determining the fire risk level of the transmission channel.

[0219] (2) Compared with related technologies, the present invention determines the coverage change index by combining the current difference index and the historical difference index. It can not only reflect the degree of change of the quantitative vegetation coverage status over time, but also help to analyze whether the current vegetation status deviates from the historical characteristics, and thus help to accurately determine the dryness index of the transmission channel in the subsequent period.

[0220] (3) Compared with related technologies, the present invention ensures the comprehensiveness of terrain feature analysis and achieves a reasonable refinement of the geographical granularity of fire risk assessment by reasonably setting the regional division scale. By dividing the transmission channel according to the regional division scale and determining the regional complexity index corresponding to each region based on terrain data, it is possible to more carefully capture and quantify the potential impact of terrain on fire propagation, thereby providing reliable data for accurately assessing the fire risk of the transmission channel from a temporal perspective.

[0221] (4) Compared with related technologies, the present invention can fully capture the characteristics of the terrain by combining the undulation index and the tilt index, which helps to accurately identify areas with complex terrain and steep slopes, thereby facilitating the subsequent accurate analysis of the fire risk level of the transmission channel from a spatial perspective.

[0222] (5) Compared with related technologies, the present invention integrates multi-dimensional data such as terrain, vegetation, and meteorology to establish a spatiotemporal coupling model and explore the long-term laws of wildfires, thereby achieving accurate prediction of wildfire risks in transmission channels.

[0223] It should be noted that for the aforementioned method embodiments, for simplicity of description, they are all expressed as a series of action combinations. However, those skilled in the art should be aware that the present invention is not limited by the order of the actions described, because according to the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0224] Through the description of the above embodiments, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus the necessary general hardware platform, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods of various embodiments of the present invention.

[0225] Example 2

[0226] According to an embodiment of the present invention, there is also provided a device for implementing the above-mentioned method for determining the fire risk level of a power transmission channel. Figure 3 FIG. 1 is a structural block diagram of a device for determining a fire risk level of a power transmission channel according to an embodiment of the present invention. Figure 3As shown, the apparatus includes: a receiving module 302, a responding module 304, a first determining module 306, a second determining module 308 and a third determining module 310. The apparatus will be described in detail below.

[0227] A receiving module 302 is used to receive a target request, wherein the target request is used to determine the fire risk level corresponding to the transmission channel; a response module 304 is connected to the above-mentioned receiving module 302, and is used to determine the terrain data, vegetation data and meteorological data corresponding to the transmission channel in response to the target request; a first determination module 306 is connected to the above-mentioned response module 304, and is used to determine the dryness index corresponding to the transmission channel based on the vegetation data and meteorological data; a second determination module 308 is connected to the above-mentioned first determination module 306, and is used to determine the terrain complexity index corresponding to the transmission channel based on the terrain data; a third determination module 310 is connected to the above-mentioned second determination module 308, and is used to determine the fire risk level corresponding to the transmission channel based on the terrain complexity index and the dryness index.

[0228] It should be noted here that the above-mentioned receiving module 302, response module 304, first determination module 306, second determination module 308 and third determination module 310 correspond to steps S102 to S110 in the method for determining the fire risk level of a transmission channel. The examples and application scenarios implemented by multiple modules and corresponding steps are the same, but are not limited to the contents disclosed in the above-mentioned embodiment 1.

[0229] Example 3

[0230] According to another aspect of an embodiment of the present invention, an electronic device is provided, comprising: a processor; and a memory for storing processor-executable instructions, wherein the processor is configured to execute instructions to implement any of the above methods for determining the fire risk level of a power transmission channel.

[0231] Example 4

[0232] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is also provided. When the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device can execute any of the above-mentioned methods for determining the fire risk level of a power transmission channel.

[0233] The serial numbers of the above embodiments of the present invention are for description only and do not represent the advantages or disadvantages of the embodiments.

[0234] In the above embodiments of the present invention, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0235] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only exemplary. For example, the division of the units can be a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0236] The units described as separate components may or may not be physically separate, and 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 units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0237] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0238] If the integrated unit is implemented in the form of 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 the present invention, 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. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk, etc. Various media that can store program codes.

[0239] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as within the scope of protection of the present invention.

Claims

1. A method for determining the fire risk level of a power transmission channel, characterized in that: include: receiving a target request, wherein the target request is used to determine a fire risk level corresponding to a power transmission channel; In response to the target request, determining terrain data, vegetation data, and meteorological data corresponding to the power transmission channel; determining a dryness index corresponding to the power transmission channel based on the vegetation data and the meteorological data; determining a terrain complexity index corresponding to the power transmission channel based on the terrain data; A fire risk level corresponding to the power transmission channel is determined based on the terrain complexity index and the dryness index.

2. The method according to claim 1, characterized in that The determining, based on the vegetation data and the meteorological data, a dryness index corresponding to the power transmission channel includes: In a case where the vegetation data includes a vegetation cover index, determining a coverage change index corresponding to the power transmission channel according to the vegetation cover index; determining a wind speed corresponding to the power transmission channel based on the meteorological data; A dryness index corresponding to the power transmission channel is determined according to the coverage change index and the wind speed.

3. The method according to claim 2, characterized in that When the vegetation data includes a vegetation cover index, determining the coverage change index corresponding to the power transmission channel according to the vegetation cover index includes: In a case where the vegetation cover index includes a plurality of historical cover indices and a current cover index, determining a maximum cover index and a minimum cover index corresponding to the power transmission channel from the plurality of historical cover indices; Determining a current difference index based on the current coverage index and the minimum coverage index; Determining a historical difference index based on the maximum coverage index and the minimum coverage index; A coverage change index corresponding to the power transmission channel is determined according to the current difference index and the historical difference index.

4. The method according to claim 1, wherein Determining a terrain complexity index corresponding to the power transmission channel based on the terrain data includes: determining a regional division scale corresponding to the terrain data; Dividing the power transmission channel according to the area division scale to obtain a plurality of areas corresponding to the power transmission channel; Determining regional complexity indexes corresponding to the plurality of regions respectively based on the terrain data; The terrain complexity index corresponding to the power transmission channel is determined according to the regional complexity indexes corresponding to the multiple regions.

5. The method according to claim 4, characterized in that Determining, based on the terrain data, regional complexity indexes corresponding to the plurality of regions, respectively, includes: In a case where the terrain data includes height data and slope data, determining, based on the height data, relief indices corresponding to the plurality of regions respectively; Determining, based on the slope data, a slope index corresponding to each of the plurality of regions; The regional complexity indexes respectively corresponding to the plurality of regions are determined according to the undulation indices and the tilt indices respectively corresponding to the plurality of regions.

6. The method according to claim 1, wherein The determining, based on the terrain complexity index and the dryness index, a fire risk level corresponding to the power transmission channel includes: In the case where the power transmission channel is divided into a plurality of regions, determining the spatiotemporal characteristics corresponding to the plurality of regions respectively according to the terrain complexity index and the dryness index; Determining a plurality of spatiotemporal similarity indexes corresponding to the plurality of regions respectively based on the spatiotemporal features corresponding to the plurality of regions respectively; Determining fusion features corresponding to the plurality of regions respectively according to the spatiotemporal features corresponding to the plurality of regions and a plurality of spatiotemporal similarity indexes; The fire risk level corresponding to the power transmission channel is determined based on the fusion features corresponding to the multiple areas.

7. The method according to any one of claims 1 to 6, characterized in that Determining a fire risk level corresponding to the power transmission channel based on the terrain complexity index and the dryness index includes: In a case where the risk level includes multiple levels, determining level thresholds corresponding to the multiple levels respectively; determining a risk index corresponding to the power transmission channel according to the terrain complexity index and the dryness index; The fire risk level corresponding to the power transmission channel is determined based on the risk index corresponding to the power transmission channel and the level thresholds corresponding to the multiple levels.

8. A device for determining the fire risk level of a power transmission channel, characterized in that: include: A receiving module, configured to receive a target request, wherein the target request is used to determine a fire risk level corresponding to a power transmission channel; a response module, configured to determine terrain data, vegetation data, and meteorological data corresponding to the power transmission channel in response to the target request; A first determining module is configured to determine a dryness index corresponding to the power transmission channel based on the vegetation data and the meteorological data; A second determining module is configured to determine a terrain complexity index corresponding to the power transmission channel based on the terrain data; The third determination module is used to determine the fire risk level corresponding to the power transmission channel based on the terrain complexity index and the dryness index.

9. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the method for determining the fire risk level of a power transmission channel according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that When the instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the method for determining the fire risk level of a power transmission channel according to any one of claims 1 to 7.

Images