Method and system for dynamically dividing line protection area based on neighborhood data analysis

Abstract

The invention relates to the technical field of data processing, and discloses a line protection area dynamic division method and system based on neighborhood data analysis, and the method comprises the steps: extracting line topology feature data and neighborhood dynamic feature data of a target line; by taking the line topology characteristic data as nodes, carrying out spatial topology association on the neighborhood dynamic characteristic data to obtain a dynamic neighborhood association map; dividing a preliminary protection area boundary of the target line according to association strength distribution of line topological feature data and neighborhood dynamic feature data in the dynamic neighborhood association map; generating a preliminary protection area boundary scheme according to the spatial topological structure compliance of the preliminary protection area boundary; and according to the dynamic environment monitoring data and the real-time operation state parameters, adjusting spatial topology parameters in the preliminary protection area boundary scheme to obtain a final protection area division scheme of the target line. According to the method, the accuracy of dynamic division of the line protection area based on neighborhood data analysis can be improved.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a method and system for dynamic division of line protection zones based on neighborhood data analysis. Background Technology

[0002] In the delineation of protection zones for power and telecommunications lines, existing technologies largely rely on static data and fixed rules, failing to fully integrate line topology characteristics with dynamic features of the surrounding environment. Traditional methods only analyze static information such as the line's basic orientation and node locations, neglecting the impact of dynamic data such as changes in the surrounding environment and fluctuations in equipment status. This results in protection zone boundaries that fail to reflect the real-time relationship between the line and its surrounding environment, making it difficult to accurately cover areas with potential risks and leading to insufficient protection effectiveness.

[0003] Existing technologies lack a systematic spatial topology association and dynamic adjustment mechanism. During the determination of protection zone boundaries, multi-level correlation strength analysis of line topology data and neighboring dynamic data is impossible. Determining the protection range solely through simple geometric division easily leads to problems such as non-compliant topology structures and poor boundary continuity. Furthermore, after the division scheme is generated, parameters cannot be adjusted based on dynamic environmental monitoring data and the real-time operating status of the line. This results in the protection zone being unable to adapt to dynamic changes in the environment and line operating requirements. When fluctuations occur in the external environment or line status, the protection zone struggles to respond and adjust quickly, further reducing the safety and stability of line operation. Summary of the Invention

[0004] This invention provides a method and system for dynamically dividing line protection zones based on neighborhood data analysis, in order to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides a method for dynamic division of line protection zones based on neighborhood data analysis, comprising: S1. Extract the topological feature data and neighborhood dynamic feature data of the target route; S2. Using the line topology feature data as nodes, perform spatial topology association on the neighborhood dynamic feature data to obtain the dynamic neighborhood association map of the target line; S3. Based on the distribution of the correlation strength between the line topology feature data and the neighborhood dynamic feature data in the dynamic neighborhood association map, delineate the preliminary protection zone boundary of the target line; S4. Based on the compliance of the spatial topology of the preliminary protection zone boundary, generate the preliminary protection zone boundary scheme for the target line; S5. Based on the dynamic environmental monitoring data and real-time operating status parameters of the target line, adjust the spatial topology parameters in the preliminary protection zone boundary scheme to obtain the final protection zone division scheme of the target line.

[0006] In a preferred embodiment, the extraction of the target line's topology feature data and neighborhood dynamic feature data includes: The route alignment and connection information of the target route are analyzed using topology analysis to obtain the route topology feature data of the target route. By fusing environmental change information and geospatial information of the area surrounding the target route with temporal features, the neighborhood dynamic feature data of the area surrounding the target route is obtained.

[0007] In a preferred embodiment, the step of using the line topology feature data as nodes to perform spatial topological association on the neighborhood dynamic feature data to obtain the dynamic neighborhood association map of the target line includes: The line segment identifiers and node location information in the line topology feature data are used as topology nodes; Based on the topological nodes, the environmental change information and device status information in the neighborhood dynamic feature data are mapped in multiple dimensions to obtain the association relationship of the topological nodes in the neighborhood dynamic feature data. Based on the aforementioned relationships, construct the topology of the target line; Based on the strength attributes of the connection points in the topology, a dynamic neighborhood association map of the target route is generated.

[0008] In a preferred embodiment, the step of performing multi-dimensional mapping between environmental change information and device status information in the neighborhood dynamic feature data based on the topological nodes to obtain the association relationship of the topological nodes in the neighborhood dynamic feature data includes: The environmental change information and equipment status information are standardized to obtain standardized feature data of the neighborhood dynamic feature data. The standardized feature data is matched one by one with the spatial attributes of the topology nodes to determine the dynamic feature vector of the topology nodes; The similarity measure between the dynamic feature vectors is fused in multiple dimensions to obtain the association strength of the topological nodes; Based on the association strength, the association relationship of topological nodes in the neighborhood dynamic feature data is determined.

[0009] In a preferred embodiment, the step of multi-dimensionally fusing the similarity measure between the dynamic feature vectors to obtain the association strength of the topological nodes includes: By analyzing the similarity characteristics of the dynamic feature vectors in the directional dimension, the degree of angular correlation of the dynamic feature vectors is obtained. The proximity characteristics of the dynamic feature vector in the time dimension are evaluated to obtain the temporal proximity measure of the dynamic feature vector; By examining the distribution characteristics of the dynamic feature vectors along the energy dimension, an energy similarity index of the dynamic feature vectors is obtained. The angular correlation degree, the temporal proximity metric, and the energy similarity index are fused in multiple dimensions to obtain the comprehensive correlation strength of the topological nodes. The formula for calculating the comprehensive correlation strength is as follows: In the formula, To summarize the aforementioned correlation strength, As an angle-related factor, The degree of correlation of the angle, As a time-sensitive factor, For the time proximity metric, As an energy regulator, The energy similarity index; The overall association strength is normalized to obtain the association strength of the topological node.

[0010] In a preferred embodiment, the step of delineating the preliminary protection zone boundary of the target line according to the correlation strength distribution between the line topology feature data and the neighborhood dynamic feature data in the dynamic neighborhood association map includes: Extract the multi-level association strength distribution pattern between the line topology feature data and the neighborhood dynamic feature data in the dynamic neighborhood association map; Based on the multi-level correlation strength distribution pattern, identify the backbone sections with stable strong correlation characteristics and the transition sections with dynamic changing characteristics in the target line; Using the backbone section as the core anchor point and combining the correlation intensity change gradient of the transition section, the initial contour of the target line is generated. The initial contour is optimized for topological continuity to obtain the preliminary protection zone boundary of the target line.

[0011] In a preferred embodiment, generating the initial contour of the target line by using the backbone section as the core anchor point and combining the correlation intensity change gradient of the transition section includes: Identify key topological nodes in the backbone segment and use these key topological nodes as the core reference points of the initial contour. Analyze the gradient of the correlation strength change in the transition section to determine the spatial distribution characteristics of the correlation strength in the transition section; Based on the spatial distribution characteristics of the correlation strength, the contour is extended from the core reference point to the transition section; Based on the rate of change of the associated intensity gradient, the expansion direction and expansion magnitude of the target line are dynamically adjusted. When the outline expands to cover the backbone section and the transition section, the initial outline of the target line is obtained.

[0012] In a preferred embodiment, generating the preliminary protection zone boundary scheme for the target line based on the spatial topology compliance of the preliminary protection zone boundary includes: Topology repair is performed on the topology anomaly segments in the boundary of the initial protection zone to obtain the topology optimization scheme of the boundary of the initial protection zone; Based on the compliance of spatial topology, a consistency assessment is performed on the topology optimization scheme to obtain a preliminary protection zone boundary scheme for the target line.

[0013] In a preferred embodiment, adjusting the spatial topology parameters in the preliminary protection zone boundary scheme based on the dynamic environmental monitoring data and real-time operating status parameters of the target line to obtain the final protection zone division scheme for the target line includes: Extract real-time change indicators of the impact of environmental factors on line operation from the dynamic environmental monitoring data; Assess the safety operation requirements of the line under the current operating state in the real-time operating status parameters; Based on the real-time change indicators and the safety operation requirements, an adjustment strategy for spatial topology parameters is generated; Based on the adjustment strategy, the spatial topology parameters in the preliminary protection zone boundary scheme are optimized and adjusted to obtain the final protection zone division scheme for the target line.

[0014] To address the aforementioned problems, this invention also provides a dynamic line protection zone partitioning system based on neighborhood data analysis, the system comprising: The feature extraction module is used to extract the topological feature data and neighborhood dynamic feature data of the target line. The spatial topology module is used to perform spatial topological association on the neighborhood dynamic feature data using the line topology feature data as nodes, so as to obtain the dynamic neighborhood association map of the target line. The region division module is used to divide the preliminary protection zone boundary of the target line according to the distribution of the correlation strength between the line topology feature data and the dynamic feature data of the neighborhood in the dynamic neighborhood association map. The scheme establishment module is used to generate a preliminary protection zone boundary scheme for the target line based on the spatial topology compliance of the preliminary protection zone boundary. The scheme optimization module is used to adjust the spatial topology parameters in the preliminary protection zone boundary scheme based on the dynamic environmental monitoring data and real-time operating status parameters of the target line, so as to obtain the final protection zone division scheme of the target line.

[0015] Compared with the prior art, the present invention has the following beneficial effects: 1. This invention provides a method and system for dynamically dividing line protection zones based on neighborhood data analysis, which significantly improves the efficiency and accuracy of line protection zone division. This technology extracts line topology feature data and neighborhood dynamic feature data, constructs a dynamic neighborhood association graph using the line topology feature data as nodes, and accurately captures the relationship between the line and its surrounding environment. Then, it divides the initial protection zone boundaries based on the association strength distribution, generates a preliminary scheme based on the compliance of the spatial topology structure, and finally adjusts the spatial topology parameters according to dynamic environmental monitoring data and real-time operating status parameters. The entire process is data-driven to achieve dynamic protection zone division, making the division process more efficient and the results more closely aligned with the actual protection needs of the line.

[0016] 2. This invention offers significant advantages in the scientific rigor and adaptability of protection zone delineation through its technical solution. The construction of the dynamic neighborhood association map incorporates multi-dimensional feature data, accurately identifying backbone and transitional sections of the line through comprehensive association strength calculation, ensuring the rationality of the initial protection zone boundary. Topology anomaly section repair and compliance assessment further optimize the boundary scheme, ensuring the integrity and continuity of the protection zone's topology. Furthermore, the parameter adjustment mechanism based on dynamic data allows the protection zone to be optimized in real time according to environmental changes and line operating status, effectively improving the targeting and timeliness of line protection and providing strong support for the safe and stable operation of the line. Attached Figure Description

[0017] Figure 1 This is a flowchart illustrating a method for dynamically dividing line protection zones based on neighborhood data analysis, provided in an embodiment of the present invention. Figure 2 This is a functional block diagram of a line protection zone dynamic division system based on neighborhood data analysis provided in an embodiment of the present invention; The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0018] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0019] This application provides a method for dynamically dividing line protection zones based on neighborhood data analysis. The executing entity of this method includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the method provided in this application: a server, a terminal, etc. In other words, the method for dynamically dividing line protection zones based on neighborhood data analysis can be executed by software or hardware installed on a terminal device or a server device. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster. The server can be an independent server 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, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0020] Reference Figure 1 The diagram shown is a flowchart illustrating a method for dynamically dividing line protection zones based on neighborhood data analysis according to an embodiment of the present invention. In this embodiment, the method for dynamically dividing line protection zones based on neighborhood data analysis includes: S1. Extract the topological feature data and neighborhood dynamic feature data of the target route; In this embodiment of the invention, the extraction of the target line's topology feature data and neighborhood dynamic feature data includes: The route alignment and connection information of the target route are analyzed using topology analysis to obtain the route topology feature data of the target route. By fusing environmental change information and geospatial information of the area surrounding the target route with temporal features, the neighborhood dynamic feature data of the area surrounding the target route is obtained.

[0021] Specifically, the route information and connection information of the target route are analyzed using topological structure analysis to obtain the route topology feature data of the target route. This involves collecting actual route data of the target route, including the starting point, ending point, key node locations along the route, and the bending and turning of the route in space. At the same time, the connection methods of the route with other routes or facilities are organized, such as intersections, parallels, access point locations, and connection types. By drawing a route topology map, this route information and connection information are presented intuitively in the form of nodes and line segments. Nodes represent the starting point, ending point, turning point, and connection point of the route, while line segments represent the specific route and connection path of the route. Information such as the number and distribution of nodes, the length and direction angle of line segments, and the type and number of connection points are extracted from the topology map. The collection of this information is the route topology feature data.

[0022] Furthermore, the environmental change information and geospatial information of the area surrounding the target route are fused with temporal features to obtain the neighborhood dynamic feature data of the area surrounding the target route. Specifically, this involves collecting geospatial information within a certain range around the target route, including static information such as topography, land use type, and building distribution, while continuously recording environmental change information that occurs in the area over time, such as vegetation changes caused by seasonal changes, weather changes, changes in construction areas caused by human activities, or changes in traffic flow. The environmental change information of the same spatial location is matched with the corresponding geospatial information in chronological order. For example, the vegetation cover around a certain section of the route in different seasons is matched with the topographic information of the area. This data set is integrated to form a data set that reflects the relationship between the surrounding environment and spatial features at different points in time. This data set is the neighborhood dynamic feature data.

[0023] In summary, topological analysis of the target route's alignment and connectivity information to obtain topological feature data can accurately capture the spatial distribution and connection logic of the target route. It clearly presents key information such as the route's starting point, ending point, turning points, and connection types and locations with other routes or facilities. This provides a precise structural foundation for the subsequent construction of a dynamic neighborhood association map, avoiding deviations in subsequent association analysis due to fuzzy route topological information. It ensures that the subsequent protection zone division conforms to the actual spatial layout of the route, fundamentally improving the spatial accuracy of protection zone division.

[0024] In summary, by fusing environmental change information and geospatial information around the target route with temporal features to obtain neighborhood dynamic feature data, static geospatial information can be deeply bound with dynamic environmental change information. This fully records the correlation between spatial features such as topography and land use types around the route and environmental dynamics such as vegetation changes, weather changes, and human activities at different time points. This breaks through the limitations of traditional methods that rely solely on static data, allowing the acquired neighborhood data to reflect the dynamic interaction between the route and its surrounding environment in real time. This provides dynamic data support for subsequent analysis of the correlation strength between the route and its surrounding environment and the delineation of protection zone boundaries. It also enables the delineation of protection zones to fully consider the impact of environmental changes on the route and improves the adaptability of protection zones to dynamic environments.

[0025] In summary, by extracting line topology feature data and neighborhood dynamic feature data through these two methods respectively, comprehensive and accurate acquisition of line structure data and surrounding dynamic environment data can be achieved. This provides a complete data foundation for subsequent steps such as constructing dynamic neighborhood association maps and delineating protection zone boundaries. It effectively solves the problems of low accuracy and inability to adapt to dynamic environments caused by single and static data in traditional protection zone delineation. From a data perspective, it lays the foundation for improving the efficiency and rationality of dynamic delineation of line protection zones.

[0026] S2. Using the line topology feature data as nodes, perform spatial topology association on the neighborhood dynamic feature data to obtain the dynamic neighborhood association map of the target line; In this embodiment of the invention, the step of using the line topology feature data as nodes to perform spatial topological association on the neighborhood dynamic feature data to obtain the dynamic neighborhood association map of the target line includes: The line segment identifiers and node location information in the line topology feature data are used as topology nodes; Based on the topological nodes, the environmental change information and device status information in the neighborhood dynamic feature data are mapped in multiple dimensions to obtain the association relationship of the topological nodes in the neighborhood dynamic feature data. Based on the aforementioned relationships, construct the topology of the target line; Based on the strength attributes of the connection points in the topology, a dynamic neighborhood association map of the target route is generated.

[0027] The step of performing a multi-dimensional mapping between environmental change information and device status information in the neighborhood dynamic feature data based on the topological nodes to obtain the association relationship of the topological nodes in the neighborhood dynamic feature data includes: The environmental change information and equipment status information are standardized to obtain standardized feature data of the neighborhood dynamic feature data. The standardized feature data is matched one by one with the spatial attributes of the topology nodes to determine the dynamic feature vector of the topology nodes; The similarity measure between the dynamic feature vectors is fused in multiple dimensions to obtain the association strength of the topological nodes; Based on the association strength, the association relationship of topological nodes in the neighborhood dynamic feature data is determined.

[0028] The step of performing multi-dimensional fusion of the similarity measure between the dynamic feature vectors to obtain the association strength of the topological nodes includes: By analyzing the similarity characteristics of the dynamic feature vectors in the directional dimension, the degree of angular correlation of the dynamic feature vectors is obtained. The proximity characteristics of the dynamic feature vector in the time dimension are evaluated to obtain the temporal proximity measure of the dynamic feature vector; By examining the distribution characteristics of the dynamic feature vectors along the energy dimension, an energy similarity index of the dynamic feature vectors is obtained. The angular correlation degree, the temporal proximity metric, and the energy similarity index are fused in multiple dimensions to obtain the comprehensive correlation strength of the topological nodes. The formula for calculating the comprehensive correlation strength is as follows: In the formula, To summarize the aforementioned correlation strength, As an angle-related factor, The degree of correlation of the angle, As a time-sensitive factor, For the time proximity metric, As an energy regulator, The energy similarity index; The overall association strength is normalized to obtain the association strength of the topological node.

[0029] Specifically, the line segment identifiers and node location information in the line topology feature data are used as topology nodes. Specifically, this means selecting unique identifiers from the line topology feature data to distinguish different line segments. These identifiers can clearly correspond to each independent segment of the target line. At the same time, all node location information recorded in the line topology feature data is extracted, including the starting point, ending point, turning point, and connection point with other lines or facilities of the line. Each line segment identifier is bound to the corresponding node location information to form an independent information unit, and each information unit is a topology node.

[0030] Furthermore, based on the topology nodes, a multi-dimensional mapping is performed on the environmental change information and equipment status information in the neighborhood dynamic feature data to obtain the association relationship of the topology nodes in the neighborhood dynamic feature data. Specifically, for each topology node, the corresponding line segment and the specific spatial range around the node's location are determined. Environmental change information within this spatial range is searched in the neighborhood dynamic feature data, such as vegetation changes, weather changes, and the operating status information of line-related equipment in the area, such as whether the equipment is operating normally or whether there are potential faults. This environmental change information and equipment status information are bound to the corresponding topology nodes, clarifying which environmental change information and equipment status information are associated with each topology node. This correspondence between nodes and information is the association relationship of the topology nodes.

[0031] Furthermore, based on the aforementioned relationships, the topology of the target line is constructed. Specifically, this involves arranging all topology nodes in an orderly manner according to their actual spatial distribution on the target line. Then, based on the relationships between each topology node, the environmental change information and equipment status information associated with each node are labeled next to the corresponding node as supplementary explanations. At the same time, adjacent topology nodes are connected by line segments, with the direction of the line segments consistent with the actual direction of the target line. This visually presents the connection order of each segment of the target line and the information associated with each node. The resulting overall structure, which includes node arrangement, node association information, and node connection relationships, is the topology of the target line.

[0032] Furthermore, based on the strength attributes of the connection points in the topology, a dynamic neighborhood association map of the target line is generated. Specifically, the strength attributes of each connection point in the topology are first determined. These attributes are determined based on the operational stability, carrying capacity, and importance of associated equipment at the connection point. Connection points with high operational stability, strong carrying capacity, and high importance of associated equipment have higher strength attribute levels. Then, based on the topology, different visual identifiers are used to distinguish connection points with different strength attribute levels. For example, connection points with higher strength attribute levels are marked with thicker lines or eye-catching colors. At the same time, environmental change information and equipment status information associated with each topology node are attached to the corresponding node in the form of dynamic labels. The label content can be adjusted in real time as the information is updated. The final graphic that combines topology, connection point strength differentiation, and dynamic information display is the dynamic neighborhood association map of the target line.

[0033] Specifically, the environmental change information and equipment status information are standardized to obtain standardized feature data of the neighborhood dynamic feature data. This involves first determining a unified descriptive scale for environmental change information, such as classifying vegetation changes into three fixed levels: "no change," "slight change," and "significant change," and categorizing weather changes into fixed types such as "sunny," "rainy," and "snowy." Then, a unified descriptive standard for equipment status information is determined, such as defining equipment operating status as three fixed states: "normal operation," "minor anomaly," and "serious anomaly." Finally, all collected environmental change information and equipment status information are converted according to the aforementioned unified scale and standard, transforming environmental change information and equipment status information from different sources and in different formats into descriptive content conforming to fixed specifications. These converted, standardized descriptive contents constitute the standardized feature data of the neighborhood dynamic feature data.

[0034] Furthermore, the standardized feature data is matched one by one with the spatial attributes of the topology nodes to determine the dynamic feature vector of the topology nodes. Specifically, this involves first extracting the spatial attributes of each topology node, including fixed information such as the specific geographical location of the line segment corresponding to the topology node and the spatial range it covers. Then, for each topology node, the standardized feature data corresponding to the spatial attributes of the node in the neighborhood dynamic feature data is searched one by one. This includes standardized environmental change data and standardized equipment status data belonging to the spatial range of the node. These found standardized feature data are arranged in a fixed order of "environmental change - equipment status" to form an ordered data combination that can reflect the dynamic characteristics of the surrounding area of ​​the topology node. This ordered data combination is the dynamic feature vector of the topology node.

[0035] Furthermore, the similarity measurement between the dynamic feature vectors is fused in multiple dimensions to obtain the association strength of the topological nodes. Specifically, this involves first measuring the similarity between the dynamic feature vectors of any two topological nodes from both the environmental change dimension and the device state dimension. In the environmental change dimension, the consistency of the standardized environmental change data in the two vectors is compared; the higher the consistency, the higher the similarity in that dimension. In the device state dimension, the consistency of the standardized device state data in the two vectors is compared; the higher the consistency, the higher the similarity in that dimension. Then, the similarity measurement results of the two dimensions are integrated by merging the similarity descriptions of the two dimensions according to equal importance, forming a comprehensive description that can reflect the similarity between the two topological nodes in terms of both environment and device. This comprehensive description is the association strength of the topological nodes.

[0036] Furthermore, based on the association strength, the association relationships of topological nodes in the neighborhood dynamic feature data are determined. Specifically, a judgment standard for association strength is set, such as three levels: "high similarity," "moderate similarity," and "low similarity." "High similarity" indicates the highest association strength between two topological nodes, while "low similarity" indicates the lowest. Then, the association strength of any two topological nodes is compared with the set judgment standard. If the association strength reaches the "high similarity" level, a strong association relationship is determined between the two topological nodes; if it reaches the "moderate similarity" level, a moderate association relationship is determined; and if it reaches the "low similarity" level, a weak association relationship is determined. In this way, the association status between all topological nodes based on the neighborhood dynamic feature data is clarified, and these clarified association statuses constitute the association relationships of topological nodes in the neighborhood dynamic feature data.

[0037] Specifically, the similarity characteristics of the dynamic feature vectors in the directional dimension are analyzed to obtain the degree of angular correlation of the dynamic feature vectors. Specifically, each dynamic feature vector is regarded as a directional marker with a specific direction. The similarity characteristics are judged by comparing whether the directions of two dynamic feature vectors are the same or close. If the directions of the two vectors are completely consistent, the degree of angular correlation is the highest; if there is a certain deviation in direction but the deviation range is within a preset small range, the degree of angular correlation is medium; if the direction deviation exceeds the preset range, the degree of angular correlation is the lowest. The description determined based on this comparison result is the degree of angular correlation.

[0038] Furthermore, the proximity characteristics of the dynamic feature vectors in the time dimension are evaluated to obtain the temporal proximity measure of the dynamic feature vectors. Specifically, this involves recording the time information corresponding to each dynamic feature vector, comparing the length of the interval between the time points corresponding to two dynamic feature vectors, and determining the highest level of temporal proximity measure if the time interval is within a preset minimum range, a medium level if the time interval is within a preset medium range, and a lowest level if the time interval exceeds a preset maximum range. This level description based on time interval is the temporal proximity measure.

[0039] Furthermore, by examining the distribution characteristics of the dynamic feature vector along the energy dimension, an energy similarity index is obtained. Specifically, this involves extracting energy-related feature data from the dynamic feature vector and comparing the distribution of these energy feature data in two vectors. If the distribution trends are completely consistent and the numerical differences are within a preset minimum range, the energy similarity index is the highest; if the distribution trends are basically consistent and the numerical differences are within a preset medium range, the energy similarity index is medium; if the distribution trends are significantly different or the numerical differences exceed a preset maximum range, the energy similarity index is the lowest. This index description, determined based on energy distribution comparison, is the energy similarity index.

[0040] Furthermore, the angular correlation degree, the temporal proximity measure, and the energy similarity index are fused in multiple dimensions to obtain the comprehensive correlation strength of the topological node. Specifically, the angular correlation degree, temporal proximity measure, and energy similarity index are merged according to the same importance. First, the description of each dimension is converted into a unified level label, such as "high," "medium," and "low." Then, the number of times the "high" level appears in the three dimensions is counted. If all three are "high," the comprehensive correlation strength is the highest; if two are "high" and one is "medium," the comprehensive correlation strength is the second highest. The comprehensive level description is determined sequentially according to this combination rule, and this comprehensive level description is the comprehensive correlation strength of the topological node.

[0041] Furthermore, the comprehensive association strength is normalized to obtain the association strength of the topological node. Specifically, each level of comprehensive association strength is assigned a fixed descriptive identifier in ascending order, such as "Level 1" for the lowest level, "Level 2" for the middle level, and "Level 3" for the highest level. This converts different comprehensive association strength levels into specific identifiers in a unified sequence. The identifier obtained after this conversion is the association strength of the topological node.

[0042] Specifically, the sources of each parameter in the comprehensive association strength calculation formula are as follows: the angle influence factor is determined based on the actual influence of the dynamic feature vector on the association strength in the directional dimension. The degree of influence is derived from the analysis of the effect of directional similarity on node association in historical data. The greater the influence of directional similarity on association, the greater the value of the angle influence factor.

[0043] Furthermore, the degree of angular correlation is derived from the analysis of the similarity characteristics of dynamic feature vectors in the directional dimension, that is, the numerical value corresponding to the descriptive level obtained by comparing the consistency of the vector directions. The time sensitivity factor is set based on the importance of proximity characteristics in the time dimension to the strength of the correlation. The more important the time proximity is to the correlation, the larger the value of the time sensitivity factor. Its magnitude is determined based on the influence weight of the time factor in practical applications.

[0044] Furthermore, the temporal proximity metric is derived from the evaluation of the proximity characteristics of dynamic feature vectors in the time dimension, i.e., the numerical value corresponding to the level obtained based on the length of the time interval. The energy adjustment factor is determined based on the weight of the energy dimension distribution characteristics in the association strength; the greater the influence of energy distribution similarity, the larger the value of the energy adjustment factor, and its value is derived by referring to the actual effect of energy factors on node association. The energy similarity index is derived from the examination of the distribution characteristics of dynamic feature vectors in the energy dimension, i.e., the numerical value corresponding to the index obtained based on the consistency of the energy feature data distribution.

[0045] Furthermore, the significance of the formula lies in the fact that by multiplying the degree of angular correlation, the measure of temporal proximity, and the energy similarity index by the corresponding angular influence factor, time sensitivity factor, and energy adjustment factor, respectively, and then summing them, and then dividing by the sum of the three factors, the influence of the three dimensions on the correlation strength is comprehensively calculated, resulting in a comprehensive correlation strength that can fully reflect the degree of correlation between topological nodes. This strength integrates information from the three dimensions of direction, time, and energy, providing a unified quantitative basis for determining the correlation relationship of topological nodes.

[0046] Furthermore, the formula shows that when the degree of angular correlation increases, the value of the numerator will increase accordingly under the influence of the angular influence factor, and the overall correlation strength will increase accordingly. When the temporal proximity measure increases, the value of the numerator will increase under the influence of the time-sensitive factor, and the overall correlation strength will also increase. When the energy similarity index increases, the value of the numerator will also increase under the influence of the energy adjustment factor, and the overall correlation strength will increase accordingly. Conversely, if any of the three dimensions of indicators decreases, the overall correlation strength will show a decreasing trend under the influence of the corresponding factor. That is, the overall correlation strength and the degree of angular correlation, temporal proximity measure, and energy similarity index all show the same trend.

[0047] In summary, using the line segment identifiers and node location information in the line topology feature data as topology nodes can accurately anchor the core structural units of the target line, so that each topology node corresponds to the actual segment and key location of the line, avoiding the problem of ambiguous node positioning in subsequent association analysis. This provides a clear and explicit association benchmark for spatial topology association, ensuring that subsequent neighborhood dynamic feature data can accurately correspond to the specific section of the line, and guaranteeing the accuracy of association analysis at the node level.

[0048] In summary, by using topological nodes to perform multidimensional mapping of environmental change information and equipment status information in the dynamic feature data of the neighborhood to obtain correlations, the structural nodes of the line can be deeply bound to the surrounding dynamic environment and equipment status. This clarifies which environmental changes and equipment statuses each line node is associated with, breaking the limitation of the separation between line and neighborhood data in traditional methods. It fully presents the correspondence between the line and the surrounding dynamic elements, providing a basis for subsequent topology construction, and enabling the topology to reflect the interaction between the line and the neighborhood.

[0049] In summary, constructing the topology of the target route based on the relationships can transform abstract relationships into intuitive structured graphics. This not only presents the connection order of each segment and node of the route, but also displays the environmental and equipment information associated with each node through additional annotations. This visualizes the relationship between the route's own structure and surrounding dynamic elements, making it easier to clearly identify the relationship characteristics of different sections of the route. This lays a structured foundation for analyzing the strength attributes of connection points and generating dynamic neighborhood relationship maps, thus improving the operability of subsequent steps.

[0050] In summary, a dynamic neighborhood association map is generated based on the strength attributes of the connection points in the topology. This allows for the visual differentiation of the importance of different connection points. Simultaneously, it presents the environmental changes and equipment status information associated with each node in the form of dynamic labels. This enables the map to reflect both the stability of the line topology and the real-time display of neighborhood dynamics. Compared to traditional static maps, this dynamic map intuitively presents the dynamic association strength distribution between the line and its neighborhood environment. It provides an intuitive and accurate graphical reference for subsequent preliminary protection zone boundary delineation based on association strength, avoiding the subjectivity of traditional delineation based on experience and improving the scientific and rational nature of protection zone boundary delineation.

[0051] In summary, by implementing spatial topological association between line topological feature data and neighborhood dynamic feature data through these four steps and generating a dynamic neighborhood association map, the static structural data of the line and the dynamic data of the neighborhood can be deeply integrated to form an association map that is structured, visualized, and dynamic. This effectively solves the problems of weak association between line and neighborhood data and unintuitive information presentation in traditional protection zone delineation. It provides core support for the subsequent accurate delineation of protection zone boundaries and generation of protection zone schemes, and improves the efficiency and accuracy of dynamic delineation of line protection zones from the perspective of association analysis.

[0052] In summary, standardizing environmental change information and equipment status information to obtain standardized feature data can transform environmental and equipment data from different sources and in different formats into unified and standardized descriptive content, eliminate analytical biases caused by differences in data formats, ensure data comparability when matching with topology nodes, avoid confusion in correlation analysis due to inconsistent data standards, and lay a consistent data foundation for accurately establishing the correspondence between topology nodes and neighboring data.

[0053] In summary, by matching standardized feature data with the spatial attributes of topology nodes one by one to determine dynamic feature vectors, the spatial range corresponding to each topology node can be accurately bound to the standardized environmental and equipment data within that range. This forms an ordered data combination that specifically reflects the dynamic characteristics of the surrounding area of ​​each node, ensuring that each topology node has corresponding dynamic feature support. This avoids misalignment between neighborhood data and line nodes, ensuring that subsequent similarity measurements can be accurately carried out based on the actual neighborhood situation of the node, and improving the targeting of association strength calculation.

[0054] In summary, multi-dimensional fusion of similarity measures between dynamic feature vectors to obtain association strength can comprehensively measure the similarity between different topological nodes from multiple dimensions such as environment and equipment, rather than judging from a single dimension. For example, the consistency of environmental changes between nodes and the matching of equipment status are considered at the same time, so that the obtained association strength can fully reflect the closeness of association between nodes, avoid the one-sided judgment of association strength caused by single-dimensional analysis, and provide a more scientific and comprehensive quantitative basis for subsequent determination of association relationships.

[0055] In summary, determining the association relationships of topological nodes in the neighborhood dynamic feature data based on association strength can clarify the tightness of the association between nodes by preset association strength levels, clearly distinguishing strong, medium, and weak association relationships. This makes the association situation between each node of the line and the neighborhood dynamic data more concrete, providing a clear association basis for the subsequent construction of the topology structure of the target line, ensuring that the topology structure can accurately reflect the interaction relationship between nodes, and thus providing precise association logic support for generating dynamic neighborhood association maps and delineating protection zone boundaries.

[0056] In summary, by implementing multi-dimensional mapping of neighborhood dynamic feature data based on topological nodes and determining the correlation relationships through these four steps, scattered neighborhood data can be gradually transformed into structured information that is accurately associated with line nodes, standardized and unified, and with a clear degree of association. This effectively solves the problems of loose association between lines and neighborhood data and ambiguous judgment of the degree of association in traditional methods. It provides accurate association data and logical foundation for subsequent construction of topological structures and generation of dynamic neighborhood association maps, and ensures the accuracy and scientific nature of dynamic division of line protection zones from the association mapping level.

[0057] In summary, analyzing the similarity of dynamic feature vectors in the directional dimension to obtain the degree of angular correlation can accurately capture the consistency of the direction of dynamic feature vectors corresponding to different topological nodes, such as the matching of the changing trends of the surrounding environment of the line and the changing direction of equipment status. This avoids the deviation in the judgment of correlation strength due to neglecting the similarity of the directional dimension, making the correlation strength analysis more in line with the actual directional characteristics of the interaction between the line and the surrounding environment, providing accurate data support in the directional dimension for subsequent comprehensive correlation strength calculation, and improving the comprehensiveness of correlation strength.

[0058] In summary, evaluating the proximity characteristics of dynamic feature vectors in the time dimension to obtain a measure of temporal proximity can clarify the degree of synchronization of dynamic feature vectors of different topological nodes in time. This includes the length of time intervals between changes in the surrounding environment and fluctuations in equipment status of different nodes within the same time period. This breaks the limitation of neglecting the time dimension in traditional analysis, enabling the correlation strength to reflect the temporal correlation of dynamic features between nodes. It ensures that the subsequent comprehensive correlation strength can reflect the impact of time factors on the correlation between lines and neighborhoods, and improves the adaptability of correlation strength to actual dynamic changes.

[0059] In summary, examining the distribution characteristics of dynamic feature vectors along the energy dimension to obtain energy similarity indices allows for in-depth analysis of the distribution patterns of energy-related data in the dynamic feature vectors corresponding to different topological nodes, such as the similarity of energy consumption distribution of line equipment and energy changes in the surrounding environment. This fills the gap in the energy dimension in traditional analysis, enabling the correlation strength to not only cover the directional and temporal dimensions but also reflect the closeness of the correlation at the energy level, further enriching the analytical dimensions of correlation strength and enhancing its comprehensiveness and scientific rigor.

[0060] In summary, by integrating angle correlation, temporal proximity, and energy similarity indices into a multidimensional framework and combining them with formulas to calculate the overall correlation strength, reasonable weights can be assigned to the three dimensions by angle influence factors, time sensitivity factors, and energy adjustment factors. This accurately quantifies the influence of each dimension on the correlation strength, avoiding bias in the overall correlation strength caused by a single dimension dominating or an imbalance in the weights of each dimension. The calculation results can objectively and comprehensively reflect the overall correlation between topological nodes, providing accurate comprehensive correlation data for subsequent normalization processing.

[0061] In summary, normalizing the overall association strength to obtain the association strength of topological nodes can convert the overall association strength of different numerical ranges into a unified descriptive identifier, such as "Level 1", "Level 2", and "Level 3", eliminating the confusion in association strength comparison caused by numerical differences. This makes the association strength between different topological nodes directly comparable, facilitating the subsequent clear division of the degree of association between nodes and providing an intuitive and unified basis for determining the association relationship of topological nodes in the neighborhood dynamic feature data.

[0062] In summary, this series of steps achieves multi-dimensional fusion of dynamic feature vector similarity measurement and obtains the association strength. It can comprehensively analyze the association between topological nodes from three key dimensions: direction, time, and energy. Combined with formula and normalization processing, it ensures the accuracy, comparability, and comprehensiveness of association strength, effectively solving the problems of single dimension, unbalanced weights, and incomparable values ​​in traditional association strength analysis. It provides scientific association strength support for subsequent determination of topological node association relationships and construction of topological structure, and ensures the accuracy and rationality of dynamic division of line protection zones from the association strength calculation level.

[0063] S3. Based on the distribution of the correlation strength between the line topology feature data and the neighborhood dynamic feature data in the dynamic neighborhood association map, delineate the preliminary protection zone boundary of the target line; In this embodiment of the invention, the step of delineating the preliminary protection zone boundary of the target line according to the correlation strength distribution between the line topology feature data and the neighborhood dynamic feature data in the dynamic neighborhood association map includes: Extract the multi-level association strength distribution pattern between the line topology feature data and the neighborhood dynamic feature data in the dynamic neighborhood association map; Based on the multi-level correlation strength distribution pattern, identify the backbone sections with stable strong correlation characteristics and the transition sections with dynamic changing characteristics in the target line; Using the backbone section as the core anchor point and combining the correlation intensity change gradient of the transition section, the initial contour of the target line is generated. The initial contour is optimized for topological continuity to obtain the preliminary protection zone boundary of the target line.

[0064] The step of generating the initial contour of the target line by using the backbone section as the core anchor point and combining the correlation intensity change gradient of the transition section includes: Identify key topological nodes in the backbone segment and use these key topological nodes as the core reference points of the initial contour. Analyze the gradient of the correlation strength change in the transition section to determine the spatial distribution characteristics of the correlation strength in the transition section; Based on the spatial distribution characteristics of the correlation strength, the contour is extended from the core reference point to the transition section; Based on the rate of change of the associated intensity gradient, the expansion direction and expansion magnitude of the target line are dynamically adjusted. When the outline expands to cover the backbone section and the transition section, the initial outline of the target line is obtained.

[0065] Specifically, the multi-level association strength distribution pattern between the line topology feature data and the neighborhood dynamic feature data in the dynamic neighborhood association map is extracted. Specifically, this involves examining the visual identifiers of the connecting lines between the line topology feature data and the neighborhood dynamic feature data in the dynamic neighborhood association map, distinguishing different association strength levels based on line thickness, color intensity, etc., and dividing them into three levels from high to low association strength: strong association, medium association, and weak association. The number of association relationships, the corresponding line segment locations, and the neighborhood feature types under each level are counted. These statistical results are then organized into a regular distribution form according to the levels. This distribution form is the multi-level association strength distribution pattern.

[0066] Furthermore, based on the multi-level association strength distribution pattern, the backbone segments with stable strong association characteristics and the transition segments with dynamic changing characteristics in the target line are identified. Specifically, in the multi-level association strength distribution pattern, line segments that maintain a strong association level over a long period and whose associated neighborhood dynamic characteristic data changes frequently are selected. The association relationship of these segments is not affected by short-term environmental or equipment status fluctuations, and these are the backbone segments with stable strong association characteristics. At the same time, line segments whose association strength frequently switches between strong, medium, and weak association and whose associated neighborhood dynamic characteristic data is frequently updated are selected. The association relationship of these segments is dynamically adjusted with changes in external conditions, and these are the transition segments with dynamic changing characteristics.

[0067] Furthermore, using the backbone sections as core anchor points and combining the correlation strength change gradient of the transition sections, the initial outline of the target route is generated. Specifically, the starting and ending points of each backbone section are used as fixed core anchor points, and the specific locations of these anchor points are marked on the map. Then, the variation law of correlation strength as the transition section extends outward from the edge of the backbone section is analyzed, that is, the gradient of correlation strength from strong to medium to weak. According to this gradient, lines extending from the anchor points of the backbone sections to the outside of the transition sections are drawn on the map. The termination position of the lines is set at the boundary where the correlation strength drops to the weak correlation level. Connecting the extension lines corresponding to all backbone sections forms a closed shape, which is the initial outline of the target route.

[0068] Furthermore, the initial contour is optimized for topological continuity to obtain the preliminary protection zone boundary of the target line. Specifically, this involves checking whether the lines of the initial contour are broken, overlapping, or significantly deviate from the actual route. If broken lines are found, the missing lines are supplemented by drawing them according to the gradient of the correlation strength change between adjacent segments to ensure the continuity of the contour lines. If overlapping lines are found, the lines more closely associated with the line topological feature data are retained, and redundant overlapping parts are deleted. If there is a deviation from the actual route, the line positions are adjusted to be consistent with the actual distribution trend of the line by referring to the node positions and direction information of the line topological feature data in the dynamic neighborhood correlation map. The complete, continuous contour boundary formed after the above adjustments that fits the actual situation of the line is the preliminary protection zone boundary of the target line.

[0069] Specifically, key topological nodes in the backbone section are identified and used as the core reference points of the initial profile. Specifically, among all the topological nodes included in the backbone section, nodes located at line turning points, connection points with other lines, or densely populated areas of associated equipment are selected. These nodes play a decisive role in maintaining the structure and relationships of the backbone section. These selected nodes are marked as key topological nodes, and the specific location of each key topological node in space is the core reference point of the initial profile.

[0070] Furthermore, the gradient of the correlation strength change in the transition section is analyzed to determine the spatial distribution characteristics of the correlation strength in the transition section. Specifically, starting from the connection position between the transition section and the backbone section, the level change of the correlation strength is gradually measured towards the outside of the transition section. The sequence of change from strong correlation to medium correlation and then to weak correlation, as well as the spatial range corresponding to each level, are recorded. The extension distance and coverage of this level change in different directions of the transition section are observed. This clarifies the distribution law of the correlation strength gradually weakening from the inside to the outside in the space of the transition section. This law is the spatial distribution characteristics of the correlation strength in the transition section.

[0071] Furthermore, based on the spatial distribution characteristics of the correlation strength, the outline is extended from the core reference point to the transition section. Specifically, starting from the core reference point, extension lines are drawn in all directions of the transition section according to the pattern of gradually weakening correlation strength from the inside to the outside. The initial direction of the extension lines is consistent with the extension direction of the areas with higher correlation strength in the transition section, ensuring that the lines first cover the areas with strong and medium correlation strength. In this way, the outline gradually extends from the core reference point to the transition section.

[0072] Furthermore, based on the rate of change of the correlation intensity gradient, the expansion direction and expansion amplitude of the target line are dynamically adjusted. Specifically, this means calculating the spatial distance when the correlation intensity changes from one level to the next in the transition section. The shorter the distance, the greater the rate of change. When the rate of change is large, the expansion amplitude is reduced so that the expansion line completes the level transition within a shorter distance. When the rate of change is small, the expansion amplitude is increased so that the expansion line maintains the same level of coverage within a longer distance. At the same time, the expansion direction is adjusted according to the difference in the rate of change in different directions, prioritizing extension in the direction with the smaller rate of change to ensure that the expanded contour can accurately reflect the actual distribution of the correlation intensity.

[0073] Furthermore, when the outline expansion covers the backbone segment and the transition segment, the initial outline of the target line is obtained. Specifically, the outline expansion is continuously performed until the expanded lines completely surround all backbone segments and cover all areas of the transition segment with association strength from strong to weak. At this time, it is checked whether the expanded graphic completely contains all key topological nodes of the backbone segment and all association strength level areas of the transition segment. If it has been completely covered, the expansion is stopped, and the closed graphic formed is the initial outline of the target line.

[0074] In summary, extracting the multi-level correlation strength distribution pattern between line topology feature data and neighborhood dynamic feature data in the dynamic neighborhood correlation graph can systematically sort out the distribution patterns of different levels of correlation, such as strong correlation, medium correlation, and weak correlation, from the graph. It can clarify the location of line segments and neighborhood feature types corresponding to each correlation level, avoid the subjectivity and one-sidedness of the correlation strength distribution judgment in traditional segmentation methods, and provide structured and hierarchical correlation data support for subsequent accurate identification of backbone segments and transition segments. This ensures that segment identification can fit the actual correlation between lines and neighborhoods, and improves the accuracy of segment division from the data level.

[0075] In summary, by identifying the backbone sections with stable and strong correlation characteristics and the transition sections with dynamic and changing characteristics in the target line based on the multi-level correlation strength distribution pattern, it is possible to accurately locate the core sections with long-term stable and high-strength correlation relationships, as well as the transition sections with frequent fluctuations in correlation strength due to environmental changes. This breaks through the limitations of the vague segment division of the line in traditional methods, clarifies the functional attributes of different sections of the line, and provides a clear segment foundation for the subsequent generation of the initial outline with the backbone sections as the core anchor points. This ensures that the initial outline can preferentially cover key protection areas and improves the targeting of protection zone boundary division.

[0076] In summary, by using the backbone section as the core anchor point and combining the gradient of the correlation intensity change in the transition section, the initial contour of the target line can be generated. The core benchmark of the contour can be determined based on the stable position of the backbone section. Then, the contour range can be reasonably extended according to the variation law of the correlation intensity from strong to weak in the transition section. This avoids the range deviation of the initial contour due to the lack of a core benchmark or the neglect of the correlation intensity gradient. The initial contour can not only completely surround the core protection area of ​​the backbone section, but also accurately cover the areas with high correlation intensity in the transition section, laying a reasonable contour foundation for subsequent optimization of the initial protection zone boundary.

[0077] In summary, optimizing the topological continuity of the initial contour to obtain the preliminary protection zone boundary can correct problems such as broken lines, overlaps, or deviations from the actual route in the initial contour. By supplementing broken lines, deleting redundant overlapping parts, and adjusting the position of deviated lines, the boundary lines of the protection zone are ensured to be complete, continuous, and conform to the actual spatial layout of the route. This avoids protection loopholes or redundant coverage caused by incomplete boundary topology, ensuring the rationality and practicality of the preliminary protection zone boundary from a structural perspective, and providing a complete and compliant boundary foundation for the subsequent generation of preliminary protection zone boundary schemes.

[0078] In summary, by dividing the initial protection zone boundary according to the distribution of correlation strength in these four steps, a systematic process can be achieved from correlation data sorting, segment identification, contour generation to boundary optimization. Taking the correlation strength between the line topology and the dynamic neighborhood as the core basis, it effectively solves the problems of low boundary accuracy and poor adaptability caused by the traditional protection zone division relying on static rules and ignoring dynamic correlation. It improves the accuracy, completeness and rationality of the initial protection zone boundary from the perspective of division logic and process, and provides a reliable boundary foundation for the subsequent generation of initial protection zone boundary schemes and optimization of final protection zone division schemes, further ensuring the effectiveness of line protection.

[0079] In summary, identifying key topological nodes in the backbone section and using them as core reference points for the initial profile can accurately pinpoint the nodes within the backbone section that play a decisive role in the line structure and relationships. This provides a stable and clear spatial reference for the generation of the initial profile, avoids positional deviations of the initial profile due to fuzzy reference points, and ensures that subsequent profile expansion always revolves around the core protection area of ​​the line. From the reference level, this guarantees the fit between the initial profile and the actual key structure of the line, and prevents the omission of the core protection area.

[0080] In summary, analyzing the gradient of association strength changes in transition zones to determine their spatial distribution characteristics can clearly reveal the pattern of association strength changes from strong to weak within the transition zone. This breaks through the limitations of the vague understanding of association characteristics in transition zones in traditional classification, providing a clear direction and scope for subsequent contour expansion. This ensures that contour expansion accurately matches the association strength distribution of the transition zone, avoiding over-expansion or under-expansion.

[0081] In general, based on the spatial distribution characteristics of the correlation strength, the contour is extended from the core reference point to the transition section. Relying on the fixed position of the core reference point, the contour lines are gradually extended according to the spatial distribution law of "strong-medium-weak" correlation strength in the transition section. This ensures that the contour first covers the areas with higher correlation strength, while naturally connecting the areas with lower correlation strength. This avoids the contour extension from deviating from the actual correlation characteristics of the transition section, so that the initial contour can completely cover the areas in the transition section that have an important impact on the line, and improves the adaptability of the contour to the dynamic correlation characteristics of the transition section.

[0082] In summary, the expansion direction and amplitude are dynamically adjusted based on the rate of change of the correlation intensity gradient. This allows for flexible adjustments based on the spatial distance of the correlation intensity level changes in different directions of the transition section. For example, the expansion amplitude can be reduced in the direction with a large rate of change to quickly complete the level transition, while the expansion amplitude can be increased in the direction with a small rate of change to fully cover the correlation area of ​​the same level. At the same time, the expansion is prioritized in the direction with a small rate of change to avoid contour deviation caused by a fixed expansion direction and amplitude. This enables the contour to more accurately reflect the actual spatial differences in the correlation intensity of the transition section, further improving the accuracy of the initial contour.

[0083] In summary, when the initial profile is obtained by expanding to cover the backbone and transition sections, it ensures that the initial profile fully includes the core protection area of ​​the line and the transition area that needs to be dynamically adjusted, forming a complete coverage of the line's overall associated features. This avoids incomplete protection due to the omission of any section. At the same time, the "cover and stop" rule prevents the profile from being over-expanded to redundant areas with extremely low association strength. This ensures both comprehensive protection and economic efficiency, providing a reasonable and complete initial profile foundation for subsequent topology continuity optimization.

[0084] In summary, by generating the initial outline of the target line through these five steps, and based on the key nodes of the backbone section and the correlation strength characteristics of the transition section, the outline generation is made more accurate, dynamic and comprehensive. This effectively solves the problems of outline deviation caused by fuzzy benchmarks, neglect of correlation strength gradients and rigid expansion methods in traditional outline generation. It lays the foundation for obtaining reasonable preliminary protection zone boundaries from the outline generation level, and further ensures the accuracy and practicality of the dynamic division of the line protection zone.

[0085] S4. Based on the compliance of the spatial topology of the preliminary protection zone boundary, generate the preliminary protection zone boundary scheme for the target line; In this embodiment of the invention, generating the preliminary protection zone boundary scheme for the target line based on the spatial topology compliance of the preliminary protection zone boundary includes: Topology repair is performed on the topology anomaly segments in the boundary of the initial protection zone to obtain the topology optimization scheme of the boundary of the initial protection zone; Based on the compliance of spatial topology, a consistency assessment is performed on the topology optimization scheme to obtain a preliminary protection zone boundary scheme for the target line.

[0086] Specifically, topology repair is performed on the topology-abnormal sections in the initial protection zone boundary to obtain the topology optimization scheme for the initial protection zone boundary. This involves checking the line connections of the initial protection zone boundary to identify sections that do not conform to topology specifications, such as overlapping lines, breaks, discontinuities, or misaligned boundary nodes. These sections are considered topology-abnormal sections. For overlapping sections, redundant overlapping parts are deleted, leaving a continuous boundary line. For broken sections, connecting lines are drawn based on the direction and correlation strength distribution characteristics of adjacent normal sections to ensure boundary continuity. For misaligned boundary nodes, the node positions are adjusted to match the actual node positions in the line topology feature data. The resulting complete, continuous protection zone boundary scheme with accurate node positions after the above repairs is the topology optimization scheme for the initial protection zone boundary.

[0087] Furthermore, based on spatial topology compliance, a consistency assessment is performed on the topology optimization scheme to obtain a preliminary protection zone boundary scheme for the target line. Specifically, spatial topology compliance means that the line direction of the protection zone boundary should be consistent with the actual direction of the target line, the boundary should completely surround all areas with high correlation strength, and the boundary nodes should correspond to the spatial positions of the line topology nodes. Based on these compliance requirements, it is checked whether the boundary lines in the topology optimization scheme conform to the actual distribution trend of the target line, whether they completely cover the key areas of the backbone section and transition section, and whether there are any cases where the positions of the boundary nodes and the line topology nodes deviate too much. If all the check items meet the compliance requirements, the topology optimization scheme is the preliminary protection zone boundary scheme for the target line; if there are any non-compliance items, the topology repair is repeated until the requirements are met. The final scheme that meets the spatial topology compliance is the preliminary protection zone boundary scheme for the target line.

[0088] In summary, topology repair of topology-anomaly sections within the initial protection zone boundary to obtain optimized topology solutions can accurately locate and correct issues that violate topology specifications, such as overlapping lines, discontinuities, and misaligned boundary nodes. For overlapping lines, redundant overlapping portions are deleted, leaving continuous lines; for discontinuous sections, connecting lines are added based on the direction and correlation strength distribution of adjacent normal sections; for misaligned nodes, node positions are adjusted to match the actual node positions in the line topology feature data. Through these repair operations, protection vulnerabilities or redundancies caused by topology anomalies in the initial protection zone boundary can be eliminated, ensuring the integrity of boundary lines and the accuracy of node positions. This provides a structurally complete and logically sound optimization foundation for subsequently generating compliant initial protection zone boundary solutions, preventing topology anomalies from affecting the actual protection effect of the protection zone.

[0089] In summary, a consistency assessment of topology optimization schemes based on spatial topology compliance is used to obtain preliminary protection zone boundary schemes. This assessment employs clear criteria such as "the protection zone boundary direction aligns with the actual route of the target line, completely encloses areas with high correlation strength, and the boundary nodes correspond spatially to the line's topology nodes." This comprehensive check ensures that the topology optimization schemes meet the requirements of the actual spatial layout and correlation characteristics of the line. If a scheme meets all compliance requirements, it can be directly identified as a preliminary protection zone boundary scheme; if any non-compliance exists, it is returned for revision until it meets the standards. This assessment process effectively filters out optimization schemes that do not meet actual needs, ensuring that the final preliminary protection zone boundary scheme not only conforms to the actual distribution trend of the line but also fully covers the key areas of the backbone and transition sections. It avoids a disconnect between the boundary and the actual line situation, guaranteeing the scientific validity and practicality of the preliminary protection zone boundary scheme from a compliance perspective. This provides a reliable foundation for subsequent adjustments based on dynamic data to obtain the final protection zone division scheme.

[0090] In summary, the two-step process of "topology repair - compliance assessment" to generate preliminary protection zone boundary schemes can systematically solve the structural defects and compliance issues of preliminary protection zone boundaries. It ensures both the integrity and accuracy of the boundary's own topology and the consistency between the boundary scheme and the actual spatial layout and associated characteristics of the line. This effectively compensates for the unreasonable boundary problems caused by neglecting topology compliance in traditional protection zone division, improves the reliability of line protection zone boundaries from the scheme generation level, provides a high-quality initial scheme for subsequent dynamic adjustment and optimization, and further promotes the accuracy and standardization of dynamic division of line protection zones.

[0091] S5. Based on the dynamic environmental monitoring data and real-time operating status parameters of the target line, adjust the spatial topology parameters in the preliminary protection zone boundary scheme to obtain the final protection zone division scheme of the target line.

[0092] In this embodiment of the invention, adjusting the spatial topology parameters in the preliminary protection zone boundary scheme based on the dynamic environmental monitoring data and real-time operating status parameters of the target line to obtain the final protection zone division scheme for the target line includes: Extract real-time change indicators of the impact of environmental factors on line operation from the dynamic environmental monitoring data; Assess the safety operation requirements of the line under the current operating state in the real-time operating status parameters; Based on the real-time change indicators and the safety operation requirements, an adjustment strategy for spatial topology parameters is generated; Based on the adjustment strategy, the spatial topology parameters in the preliminary protection zone boundary scheme are optimized and adjusted to obtain the final protection zone division scheme for the target line.

[0093] Specifically, the real-time change indicators of the impact of environmental factors on line operation are extracted from the dynamic environmental monitoring data. This means screening out environmental factors that may affect line operation from the dynamic environmental monitoring data, such as rainfall, wind force, vegetation growth rate, and intensity of surrounding construction activities, continuously recording the real-time values ​​of these environmental factors, comparing these values ​​with the normal range of the same period in history, calculating the degree of difference and classifying them into levels such as "no impact," "slight impact," and "significant impact." These levels are combined with the corresponding environmental factors to form specific indicators that can reflect the changes in the impact of environmental factors on line operation. These indicators are the real-time change indicators of the impact of environmental factors on line operation.

[0094] Furthermore, assessing the safety operation requirements of the line under the current operating state in the real-time operating status parameters specifically refers to collecting the line's real-time operating status parameters, including the line's load, equipment temperature, operational stability, and fault occurrence frequency. These parameters are then compared with the line's designed safety operation standards to determine the gap between the current operating state and the safety standards, such as whether the load is close to full load or whether the equipment temperature is close to the warning value. Based on the size of the gap, the strength and scope of the protective measures required to ensure the safe operation of the line are determined. For example, it may be necessary to expand the protection range to reduce external interference or strengthen the protection to cope with high loads. These clearly defined measures are the safety operation requirements of the line under the current operating state.

[0095] Furthermore, based on the real-time change indicators and the safety operation requirements, adjustment strategies for spatial topology parameters are generated. Specifically, this involves analyzing the correspondence between the impact level of environmental factors in the real-time change indicators and the protection requirements in the safety operation requirements. When the impact level of environmental factors is "significant" and the safety operation requirements require expanding the protection range, an adjustment strategy is formulated to expand the boundary of the initial protection zone. When the impact level of environmental factors is "minor" and the safety operation requirements do not have special requirements for the protection range, an adjustment strategy is formulated to maintain the original boundary or slightly shrink the boundary. At the same time, the specific sections and directions of adjustment are clearly defined to ensure that the adjustment strategies can both cope with the real-time impact of environmental factors and meet the safety operation requirements of the line. These strategies are the adjustment strategies for spatial topology parameters.

[0096] Furthermore, according to the adjustment strategy, the spatial topology parameters in the preliminary protection zone boundary scheme are optimized and adjusted to obtain the final protection zone division scheme of the target line. Specifically, this means modifying the spatial topology parameters in the preliminary protection zone boundary scheme according to the adjustment direction and sections specified in the adjustment strategy. For example, when expanding the boundary, the boundary extension length of a specific section is increased, and when shrinking the boundary, the boundary coverage of the corresponding section is reduced. During the adjustment process, the latest association strength distribution in the dynamic neighborhood association graph is referenced to ensure that the adjusted boundary can still cover areas with high association strength, while maintaining the topological continuity of the boundary. The complete, reasonable protection zone boundary scheme formed after optimization and adjustment that meets the requirements of the real-time environment and operating status is the final protection zone division scheme of the target line.

[0097] In summary, extracting real-time change indicators of environmental factors affecting line operation from dynamic environmental monitoring data can accurately screen key environmental factors such as rainfall, wind force, vegetation growth rate, and surrounding construction intensity from dynamic environmental data. By comparing real-time values ​​with historical normal ranges to classify the impact level, the real-time effect of environmental changes on line operation can be clearly quantified. This breaks through the limitation of traditional protection zone division ignoring dynamic environmental changes, and provides accurate environmental impact basis for subsequent adjustment of spatial topology parameters. This ensures that the final protection zone can adapt to real-time environmental changes and avoids protection failure due to sudden changes in environmental factors.

[0098] In summary, assessing the safety requirements of a line under its current operating state in real-time operational parameters can be achieved by comparing parameters such as real-time line load, equipment temperature, operational stability, and fault frequency with safety operation standards. This clarifies the gap between the current operating state and safety thresholds, thereby determining the strength and scope of the required protective measures. This concretizes safety requirements into actionable protective adjustment directions, avoiding over- or under-protection by traditional protection schemes that are out of touch with the line's real-time operating state. It provides operational-level support for generating adjustment strategies that align with the actual needs of the line.

[0099] In summary, the strategy for adjusting spatial topology parameters based on real-time changing indicators and safe operation requirements establishes a correspondence between dynamic environmental impacts and line safety needs: when the environmental impact is "significant" and safety requirements necessitate expanding the protection range, a strategy to expand the boundary is formulated; when the environmental impact is "minor" and safety requirements are not specific, a strategy to maintain or slightly shrink the boundary is formulated, while clearly defining the specific sections and directions of adjustment. This strategy generation method ensures that the adjustment direction can both address real-time environmental impacts and meet the line's safe operation requirements, avoiding the blindness of adjustment strategies and providing clear and feasible operational guidance for subsequent optimization of spatial topology parameters.

[0100] In summary, the spatial topology parameters in the initial protection zone boundary scheme are optimized and adjusted according to the adjustment strategy to obtain the final protection zone division scheme. Parameters such as boundary extension length and coverage area can be precisely modified according to the direction and segments specified in the strategy—increasing the extension length of specific segments when expanding the boundary, and reducing the coverage area of ​​corresponding segments when shrinking the boundary. Simultaneously, the latest correlation strength distribution of the dynamic neighborhood correlation map is referenced to ensure that the adjusted boundary still covers highly correlated areas and maintains topological continuity. This adjustment process allows the initial scheme to be dynamically optimized based on real-time data, avoiding the problem of traditional fixed schemes being unable to adapt to dynamic changes. The final scheme not only meets the real-time requirements of the environment and operating status but also possesses structural integrity, ensuring the targeted and timely nature of line protection from the perspective of scheme optimization.

[0101] In summary, these four steps enable dynamic adjustments from real-time data extraction to final scheme generation, deeply integrating environmental dynamic monitoring data and real-time line operating parameters into the protection zone delineation process. This effectively solves the core problem of traditional protection zone schemes being static and unable to adapt to dynamic changes, making the final protection zone delineation scheme both environmentally adaptable and operationally safe. From a dynamic adjustment perspective, it improves the accuracy and practical value of line protection zone delineation, providing more reliable protection for the safe and stable operation of the line.

[0102] like Figure 2 The diagram shown is a functional block diagram of a dynamic line protection zone division system based on neighborhood data analysis provided in an embodiment of the present invention.

[0103] The line protection zone dynamic division system 100 based on neighborhood data analysis described in this invention can be installed in an electronic device. Depending on the functions implemented, the line protection zone dynamic division system 100 may include a feature extraction module 101, a spatial topology module 102, a region division module 103, a scheme determination module 104, and a scheme optimization module 105. The module described in this invention can also be called a unit, which refers to a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, and are stored in the memory of the electronic device.

[0104] In this embodiment, the functions of each module / unit are as follows: The feature extraction module 101 is used to extract the line topology feature data and neighborhood dynamic feature data of the target line. The spatial topology module 102 is used to perform spatial topology association on the neighborhood dynamic feature data using the line topology feature data as nodes, so as to obtain the dynamic neighborhood association map of the target line. The region division module 103 is used to divide the preliminary protection zone boundary of the target line according to the correlation strength distribution between the line topology feature data and the neighborhood dynamic feature data in the dynamic neighborhood association map. The scheme establishment module 104 is used to generate a preliminary protection zone boundary scheme for the target line based on the spatial topology compliance of the preliminary protection zone boundary. The scheme optimization module 105 is used to adjust the spatial topology parameters in the preliminary protection zone boundary scheme according to the dynamic environmental monitoring data and real-time operating status parameters of the target line, so as to obtain the final protection zone division scheme of the target line.

[0105] In the several embodiments provided by this invention, it should be understood that the disclosed methods and systems can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.

[0106] The modules described as separate components may or may not be physically separate. The components shown as modules 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 modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0107] Furthermore, the functional modules in the various embodiments of the present invention 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 in the form of hardware plus software functional modules.

[0108] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0109] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0110] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for dynamic division of a protection zone of a line based on neighborhood data analysis, characterized in that, The method comprises: S1. extracting line topology feature data and neighborhood dynamic feature data of a target line; S2. taking the line topology feature data as nodes, performing spatial topology association on the neighborhood dynamic feature data to obtain a dynamic neighborhood correlation graph of the target line; S3. dividing a preliminary protection zone boundary of the target line according to the correlation strength distribution of the line topology feature data and the neighborhood dynamic feature data in the dynamic neighborhood correlation graph; S4. generating a preliminary protection zone boundary scheme of the target line according to the spatial topology structure compliance of the preliminary protection zone boundary; S5. adjusting the spatial topology parameters in the preliminary protection zone boundary scheme according to the dynamic environment monitoring data and real-time operation state parameters of the target line to obtain a final protection zone division scheme of the target line.

2. The method of claim 1, wherein the method further comprises: The extraction of the line topology feature data and the neighborhood dynamic feature data of the target line comprises: topology structure analysis on line direction information and connection relationship information of a target line to obtain line topology feature data of the target line; time feature fusion on environmental change information and geographic space information of a region around the target line to obtain neighborhood dynamic feature data of the region around the target line.

3. The method of claim 1, wherein the method further comprises: The spatial topology association of the neighborhood dynamic feature data with the line topology feature data as nodes to obtain a dynamic neighborhood correlation graph of the target line comprises: taking line section identifiers and node position information in the line topology feature data as topology nodes; based on the topology nodes, performing multidimensional mapping on environmental change information and device state information in the neighborhood dynamic feature data to obtain the correlation relationship of the topology nodes in the neighborhood dynamic feature data; constructing a topology structure of the target line according to the correlation relationship; generating a dynamic neighborhood correlation graph of the target line according to the strength attributes of the connection points in the topology structure.

4. The method of claim 3, wherein the method further comprises: The multidimensional mapping of the environmental change information and the device state information in the neighborhood dynamic feature data based on the topology nodes to obtain the correlation relationship of the topology nodes in the neighborhood dynamic feature data comprises: standardizing the environmental change information and the device state information to obtain standardized feature data of the neighborhood dynamic feature data; matching the standardized feature data with the spatial attributes of the topology nodes one by one to determine dynamic feature vectors of the topology nodes; performing multidimensional fusion on the similarity measurement between the dynamic feature vectors to obtain the correlation strength of the topology nodes; determining the correlation relationship of the topology nodes in the neighborhood dynamic feature data according to the correlation strength.

5. The method of claim 4, wherein the method further comprises: The multidimensional fusion on the similarity measurement between the dynamic feature vectors to obtain the correlation strength of the topology nodes comprises: analyzing the similarity characteristics of the dynamic feature vectors in the direction dimension to obtain the angle correlation degree of the dynamic feature vectors; evaluating the proximity characteristics of the dynamic feature vectors in the time dimension to obtain the time proximity measurement of the dynamic feature vectors; Obtaining an energy similarity index of the dynamic feature vector by investigating distribution characteristics of the dynamic feature vector in an energy dimension; Fusing the angle correlation degree, the time proximity measure and the energy similarity index in multiple dimensions to obtain a comprehensive correlation strength of the topology node, wherein a calculation formula of the comprehensive correlation strength is as follows: ； wherein, is the correlation strength, is the angle influence factor, is the angle correlation degree, is the time sensitivity factor, is the time proximity measure, is the energy adjustment factor, is the energy similarity index; Performing normalization processing on the comprehensive correlation strength to obtain a correlation strength of the topology node.

6. The method of claim 1, wherein the method further comprises: determining a number of neighbor data analysis-based line protection zones based on the number of line sections and the number of line sections per zone; and determining a number of line sections per zone based on the number of line sections and the number of neighbor data analysis-based line protection zones. The preliminary protection zone boundary of the target line is divided according to the correlation strength distribution of the line topology feature data and the neighborhood dynamic feature data in the dynamic neighborhood correlation graph, and the method comprises the following steps: Extracting a multi-level correlation strength distribution mode between the line topology feature data and the neighborhood dynamic feature data in the dynamic neighborhood correlation graph; According to the multi-level correlation strength distribution mode, identifying a backbone section with stable strong correlation characteristics and a transition section with dynamic change characteristics in the target line; Taking the backbone section as a core anchor point, and combining a correlation strength change gradient of the transition section, an initial contour of the target line is generated; Performing topology continuity optimization on the initial contour to obtain the preliminary protection zone boundary of the target line.

7. The method of claim 6, wherein the method further comprises: determining a number of neighbor data analysis-based line protection zones based on the number of line sections and the number of line sections per zone; and determining a number of line sections per zone based on the number of line sections and the number of neighbor data analysis-based line protection zones. The initial contour of the target line is generated by taking the backbone section as a core anchor point and combining a correlation strength change gradient of the transition section, and the method comprises the following steps: Identifying a key topology node in the backbone section, and taking the key topology node as a core reference point of the initial contour; Analyzing the correlation strength change gradient of the transition section to determine the spatial distribution characteristics of the correlation strength in the transition section; According to the spatial distribution characteristics of the correlation strength, the contour is expanded along the core reference point to the transition section; According to the change rate of the correlation strength gradient, the expansion direction and the expansion amplitude of the target line are dynamically adjusted; When the contour expansion covers the backbone section and the transition section, the initial contour of the target line is obtained.

8. The method of claim 1, wherein the method further comprises: determining a number of neighbor data analysis-based line protection zones based on the number of line sections and the number of line sections per zone; and determining a number of line sections per zone based on the number of line sections and the number of neighbor data analysis-based line protection zones. The preliminary protection zone boundary scheme of the target line is generated according to the spatial topology structure compliance of the preliminary protection zone boundary, and the method comprises the following steps: Performing topology repair on a topology abnormal section in the preliminary protection zone boundary to obtain a topology optimization scheme of the preliminary protection zone boundary; Based on the spatial topology structure compliance, the topology optimization scheme is evaluated for consistency to obtain the preliminary protection zone boundary scheme of the target line.

9. The method of claim 1, wherein the method further comprises: determining a number of neighbor data analysis-based line protection zones based on the number of line sections and the number of line sections per zone; and determining a number of line sections per zone based on the number of line sections and the number of neighbor data analysis-based line protection zones. According to the dynamic environment monitoring data and the real-time operation state parameters of the target line, the spatial topology parameters in the preliminary protection zone boundary scheme are adjusted to obtain the final protection zone division scheme of the target line, and the method comprises the following steps: Extracting a real-time change index of the influence of environmental factors on line operation in the dynamic environment monitoring data; Evaluating a safety operation demand of the line in the current operation state in the real-time operation state parameters; According to the real-time change index and the safety operation demand, an adjustment strategy of the spatial topology parameters is generated; According to the adjustment strategy, the spatial topology parameters in the preliminary protection zone boundary scheme are optimized and adjusted to obtain the final protection zone division scheme of the target line.

10. A system for dynamic division of a protection zone of a line based on neighborhood data analysis, characterized in that, The system comprises: The feature extraction module is configured to extract line topology feature data and neighborhood dynamic feature data of the target line; The spatial topology module is configured to take the line topology feature data as nodes, perform spatial topology correlation on the neighborhood dynamic feature data, and obtain a dynamic neighborhood correlation graph of the target line; The region division module is configured to divide a preliminary protection zone boundary of the target line according to an association strength distribution of the line topology feature data and the neighborhood dynamic feature data in the dynamic neighborhood correlation graph; The scheme establishment module is configured to generate a preliminary protection zone boundary scheme of the target line according to spatial topology structure compliance of the preliminary protection zone boundary; The scheme optimization module is configured to adjust spatial topology parameters in the preliminary protection zone boundary scheme according to dynamic environment monitoring data and real-time operation state parameters of the target line, and obtain a final protection zone division scheme of the target line.

Images