A method and system for generating lightning protection detection tasks

Abstract

This invention provides a method and system for generating lightning protection detection tasks. The method includes: responding to a task generation command by activating a preset cloud server, which stores a personnel database, a detection point database, and a detection agency database; receiving a target detection location input by a user in real time, and extracting the corresponding detection features contained in the target detection location in real time based on preset rules; matching the corresponding target dataset in real time within the personnel database, the detection point database, and the detection agency database based on the detection features, and constructing a detection task pre-rehearsal environment adapted to the target detection location in real time based on a data twin program; generating a corresponding initial task plan in real time based on the target dataset, and adaptively adjusting the initial task plan through the detection task pre-rehearsal environment to generate lightning protection detection tasks in real time. This invention can generate lightning protection detection tasks quickly and effectively, improving task generation efficiency.

Description

Technical Field

[0001] This invention relates to the field of meteorological technology, and in particular to a method and system for generating lightning protection detection tasks. Background Technology

[0002] With the advancement of technology and the development of the times, people's awareness of disaster prevention is constantly increasing. Among them, lightning disasters are a common natural disaster, so corresponding early warning and protection are needed to eliminate safety hazards.

[0003] The sudden nature of lightning disasters requires that lightning protection testing not only be carried out regularly, but also have efficient emergency response capabilities. Specifically, when the meteorological department issues a lightning warning, key areas such as high-rise buildings, flammable and explosive sites, and power hubs must complete emergency testing of lightning protection devices in a short period of time.

[0004] Furthermore, in practical applications, because key data such as the qualifications of testing institutions, personnel files, and target locations are mostly stored in independent sub-modules or databases, it is impossible to integrate the above-mentioned key data in a timely and effective manner during the generation of lightning protection testing tasks. As a result, it is impossible to generate the required lightning protection testing tasks in a short time, which prolongs the generation cycle of testing tasks and reduces the generation efficiency of tasks. Summary of the Invention

[0005] Based on this, the purpose of the present invention is to provide a method and system for generating lightning protection detection tasks, so as to solve the problem that the existing technology cannot integrate key data in a timely and effective manner, resulting in the inability to generate the required lightning protection detection tasks in a short time, and thus extending the detection task cycle.

[0006] The first aspect of the present invention proposes:

[0007] A method for generating lightning protection detection tasks, wherein the method includes:

[0008] In response to the task generation command, a preset cloud server is activated, which stores a personnel database, a detection point database, and a detection agency database.

[0009] The system receives the target detection location input by the user in real time and extracts the corresponding detection features contained in the target detection location in real time based on preset rules.

[0010] Based on the detection features, the corresponding target dataset is matched in real time within the personnel database, the detection point database, and the detection agency database, and a detection task rehearsal environment adapted to the target detection location is constructed in real time based on the data twin program.

[0011] The initial task plan is generated in real time based on the target dataset, and the initial task plan is adaptively adjusted through the detection task pre-playing environment to generate lightning protection detection tasks in real time.

[0012] The beneficial effects of this invention are as follows: by activating the cloud server in real time, the required personnel database, detection point database, and detection agency database can be obtained. Based on this, a comprehensive analysis is performed to obtain the required target dataset. At the same time, the required detection task pre-rehearsal environment is constructed. Based on this, an initial task plan is generated according to the target dataset and adaptively adjusted to obtain the final lightning protection detection task. This enables the rapid and effective generation of the required lightning protection detection task, shortens the task cycle, and improves the task generation efficiency.

[0013] Furthermore, the step of extracting the corresponding detection features contained in the target detection location in real time based on preset rules includes:

[0014] Obtain location information corresponding to the target detection location, and perform attribute parsing processing on the location information through a preset semantic recognition model to separate static attribute information and dynamic attribute information accordingly;

[0015] The static attribute information is imported into a preset building lightning protection feature matrix to output the corresponding voltage detection feature, and the dynamic attribute information is matched with a preset risk coefficient lookup table to output the corresponding lightning strike risk coefficient.

[0016] Based on the voltage detection characteristics and the lightning strike risk coefficient, a corresponding feature association map is constructed in real time, and the detection characteristics are generated accordingly based on the feature association map.

[0017] Furthermore, the step of constructing a corresponding feature correlation map in real time based on the voltage detection characteristics and the lightning strike risk coefficient, and generating the detection characteristics based on the feature correlation map, includes:

[0018] The historical detection data generated by the voltage detection feature in a preset time period are detected in real time in a preset database, and the rate of change of the voltage detection feature in each detection cycle is calculated to construct the corresponding feature change trend vector.

[0019] The Pearson correlation coefficient that matches the voltage detection feature is calculated in real time based on the feature change trend vector, and the feature association map is constructed in real time with the voltage detection feature as the node and the Pearson correlation coefficient as the weight value.

[0020] The PageRank algorithm is used to calculate the influence value of each node in the feature association graph, and the influence value of each node is weighted by the lightning strike risk coefficient, so as to finally select the core feature node with the highest influence value as the detection feature.

[0021] Furthermore, the step of matching the corresponding target dataset in real time within the personnel database, the detection point database, and the detection agency database based on the detection features includes:

[0022] The detection features are decomposed into dimensions to generate corresponding personnel adaptation features, location matching features, and institutional collaboration features. The qualification files and historical detection records of all personnel are retrieved from the personnel database to select candidate personnel datasets based on the personnel adaptation features.

[0023] The geographic coordinates and attribute information of all points are extracted from the detection point database to filter candidate point datasets based on the point matching features. The service area maps and cooperation evaluation records of all institutions are obtained from the detection institution database to filter candidate institution datasets based on the institution collaboration features.

[0024] The candidate personnel dataset, the candidate location dataset, and the candidate institution dataset are linked and integrated to generate the target dataset.

[0025] Furthermore, the step of associating and integrating the candidate personnel dataset, the candidate location dataset, and the candidate institution dataset to generate the target dataset includes:

[0026] Obtain the detection timeliness parameters of each person in the candidate personnel dataset, the lightning protection level parameters of each point in the candidate point dataset, and the scheduling response parameters of each institution in the candidate institution dataset;

[0027] The detection timeliness parameter and the lightning protection level parameter are weighted and calculated to generate a first correlation value, and the scheduling response parameter and the geographical coordinates of the location are used to calculate the distance to generate a second correlation value.

[0028] A corresponding three-dimensional association array is constructed based on the first association value and the second association value, and the array elements in the three-dimensional association array are extracted so as to set the array elements as the target dataset.

[0029] Furthermore, the step of generating a corresponding initial task plan in real time based on the target dataset, and adaptively adjusting the initial task plan through the detection task rehearsal environment to generate a lightning protection detection task in real time includes:

[0030] Based on the distribution density of detection points in the target dataset, a corresponding standard detection grid is divided, and the detection personnel with corresponding qualifications in the personnel database are embedded into the standard detection grid to form the initial task plan.

[0031] The lightning activity frequency data of the target detection location is imported into the detection task simulation environment to simulate the lightning warning level at different time periods, and the detection route in the initial task plan is dynamically simulated and adjusted accordingly.

[0032] The corresponding round-trip travel time is calculated based on the adjusted detection route. Combined with the estimated detection time of the detection points, a three-dimensional task matrix including personnel configuration, route planning and time nodes is generated, and the three-dimensional task matrix is ​​converted into the lightning protection detection task in real time.

[0033] Furthermore, the step of converting the three-dimensional task matrix into the lightning protection detection task in real time includes:

[0034] Based on the coordinate parameters of each detection point in the three-dimensional task matrix, an electronic inspection map containing latitude and longitude information is generated, and the lightning risk level of each detection point is marked in the electronic inspection map.

[0035] The detection tasks in the three-dimensional task matrix are sorted according to the priority of the time nodes, and the sorted task sequence is bound with the biometric information of the detection personnel to generate a task execution list containing personnel-specific identifiers.

[0036] The route planning data in the three-dimensional task matrix is ​​extracted, and a dynamic navigation path is constructed by combining it with real-time meteorological data. The electronic inspection map, the task execution list, and the dynamic navigation path are then integrated to generate the lightning protection detection task.

[0037] The second aspect of the present invention proposes:

[0038] A lightning protection detection task generation system, wherein the system includes:

[0039] The response module is used to respond to the task generation command and activate the preset cloud server, which stores a personnel database, a detection point database, and a detection agency database.

[0040] The receiving module is used to receive the target detection location input by the user in real time, and extract the corresponding detection features contained in the target detection location in real time based on preset rules;

[0041] The matching module is used to match the corresponding target dataset in real time within the personnel database, the detection point database, and the detection agency database based on the detection features, and to build a detection task rehearsal environment adapted to the target detection location in real time based on the data twin program.

[0042] The adjustment module is used to generate a corresponding initial task plan in real time based on the target dataset, and to adaptively adjust the initial task plan through the detection task pre-playing environment to generate lightning protection detection tasks in real time.

[0043] Furthermore, the receiving module is specifically used for:

[0044] Obtain location information corresponding to the target detection location, and perform attribute parsing processing on the location information through a preset semantic recognition model to separate static attribute information and dynamic attribute information accordingly;

[0045] The static attribute information is imported into a preset building lightning protection feature matrix to output the corresponding voltage detection feature, and the dynamic attribute information is matched with a preset risk coefficient lookup table to output the corresponding lightning strike risk coefficient.

[0046] Based on the voltage detection characteristics and the lightning strike risk coefficient, a corresponding feature association map is constructed in real time, and the detection characteristics are generated accordingly based on the feature association map.

[0047] Furthermore, the receiving module is specifically used for:

[0048] The historical detection data generated by the voltage detection feature in a preset time period are detected in real time in a preset database, and the rate of change of the voltage detection feature in each detection cycle is calculated to construct the corresponding feature change trend vector.

[0049] The Pearson correlation coefficient that matches the voltage detection feature is calculated in real time based on the feature change trend vector, and the feature association map is constructed in real time with the voltage detection feature as the node and the Pearson correlation coefficient as the weight value.

[0050] The PageRank algorithm is used to calculate the influence value of each node in the feature association graph, and the influence value of each node is weighted by the lightning strike risk coefficient, so as to finally select the core feature node with the highest influence value as the detection feature.

[0051] Furthermore, the receiving module is specifically used for:

[0052] The detection features are decomposed into dimensions to generate corresponding personnel adaptation features, location matching features, and institutional collaboration features. The qualification files and historical detection records of all personnel are retrieved from the personnel database to select candidate personnel datasets based on the personnel adaptation features.

[0053] The geographic coordinates and attribute information of all points are extracted from the detection point database to filter candidate point datasets based on the point matching features. The service area maps and cooperation evaluation records of all institutions are obtained from the detection institution database to filter candidate institution datasets based on the institution collaboration features.

[0054] The candidate personnel dataset, the candidate location dataset, and the candidate institution dataset are linked and integrated to generate the target dataset.

[0055] Furthermore, the receiving module is specifically used for:

[0056] Obtain the detection timeliness parameters of each person in the candidate personnel dataset, the lightning protection level parameters of each point in the candidate point dataset, and the scheduling response parameters of each institution in the candidate institution dataset;

[0057] The detection timeliness parameter and the lightning protection level parameter are weighted and calculated to generate a first correlation value, and the scheduling response parameter and the geographical coordinates of the location are used to calculate the distance to generate a second correlation value.

[0058] A corresponding three-dimensional association array is constructed based on the first association value and the second association value, and the array elements in the three-dimensional association array are extracted so as to set the array elements as the target dataset.

[0059] Furthermore, the receiving module is specifically used for:

[0060] Based on the distribution density of detection points in the target dataset, a corresponding standard detection grid is divided, and the detection personnel with corresponding qualifications in the personnel database are embedded into the standard detection grid to form the initial task plan.

[0061] The lightning activity frequency data of the target detection location is imported into the detection task simulation environment to simulate the lightning warning level at different time periods, and the detection route in the initial task plan is dynamically simulated and adjusted accordingly.

[0062] The corresponding round-trip travel time is calculated based on the adjusted detection route. Combined with the estimated detection time of the detection points, a three-dimensional task matrix including personnel configuration, route planning and time nodes is generated, and the three-dimensional task matrix is ​​converted into the lightning protection detection task in real time.

[0063] Furthermore, the receiving module is specifically used for:

[0064] Based on the coordinate parameters of each detection point in the three-dimensional task matrix, an electronic inspection map containing latitude and longitude information is generated, and the lightning risk level of each detection point is marked in the electronic inspection map.

[0065] The detection tasks in the three-dimensional task matrix are sorted according to the priority of the time nodes, and the sorted task sequence is bound with the biometric information of the detection personnel to generate a task execution list containing personnel-specific identifiers.

[0066] The route planning data in the three-dimensional task matrix is ​​extracted, and a dynamic navigation path is constructed by combining it with real-time meteorological data. The electronic inspection map, the task execution list, and the dynamic navigation path are then integrated to generate the lightning protection detection task.

[0067] The third aspect of the present invention proposes:

[0068] A computer includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the lightning protection detection task generation method as described above.

[0069] The fourth aspect of the present invention proposes:

[0070] A readable storage medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the lightning protection detection task generation method as described above.

[0071] Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0072] Figure 1 A flowchart of the lightning protection detection task generation method provided in the first embodiment of the present invention;

[0073] Figure 2 This is a structural block diagram of the lightning protection detection task generation system provided in the third embodiment of the present invention.

[0074] The following detailed description, in conjunction with the accompanying drawings, will further illustrate the present invention. Detailed Implementation

[0075] To facilitate understanding of the present invention, a more complete description will be given below with reference to the accompanying drawings. Several embodiments of the invention are illustrated in the drawings. However, the invention can be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.

[0076] It should be noted that when a component is said to be "fixed to" another component, it can be directly on the other component or there may be an intervening component. When a component is said to be "connected to" another component, it can be directly connected to the other component or there may be an intervening component. The terms "vertical," "horizontal," "left," "right," and similar expressions used in this document are for illustrative purposes only.

[0077] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0078] Please see Figure 1 The image shows a lightning protection detection task generation method provided in the first embodiment of the present invention. The lightning protection detection task generation method provided in this embodiment can quickly and effectively generate the required lightning protection detection tasks, thereby improving the task generation efficiency.

[0079] Specifically, this embodiment provides:

[0080] A method for generating lightning protection detection tasks specifically includes the following steps:

[0081] Step S10: In response to the task generation command, a preset cloud server is activated, which stores a personnel database, a detection point database, and a detection agency database.

[0082] It's important to note that when the system receives a task generation instruction, it first activates a pre-set cloud server. This server is the core data support platform for the entire process, integrating and storing three key databases: a personnel database, a testing site database, and a testing agency database. Specifically, the personnel database contains information such as the testing personnel's qualification certificates, skill levels, and historical task records. The testing site database stores the geographical location, facility type, and historical testing data of each testing site. Correspondingly, the testing agency database records information such as the service scope, qualification level, and cooperation evaluations of testing agencies. This step provides basic data support for subsequent data processing and task generation, ensuring that all operations are based on a complete and accurate data source, facilitating subsequent processing.

[0083] Step S20: Receive the target detection location input by the user in real time, and extract the corresponding detection features contained in the target detection location in real time based on preset rules;

[0084] It's important to note that the system receives user-inputted target detection locations (e.g., "XX Industrial Park, Area A") in real time and extracts key detection features from the location information using preset rules. These features are the core basis for subsequent matching data and task generation; for example, the location's building type, historical lightning strike history, and surrounding environment. The core function of this step is to transform the abstract concept of "location" into quantifiable and analyzable feature parameters, laying the foundation for accurate data matching and facilitating subsequent processing.

[0085] Step S30: Based on the detection features, the corresponding target dataset is matched in real time within the personnel database, the detection point database, and the detection agency database, and a detection task rehearsal environment adapted to the target detection location is constructed in real time based on the data twin program.

[0086] It's important to note that, based on the extracted detection features, the system performs real-time matching across three types of databases to filter out personnel, locations, and institutions highly relevant to the target location, forming a target dataset. Simultaneously, data twin technology is used to construct a virtual pre-simulation environment that mirrors the physical attributes of the target location. Specifically, this environment can simulate the geographical layout, facility distribution, and even weather conditions of a real-world scenario, providing a virtual testing space for verifying and optimizing the task plan. This step integrates data with the scenario, ensuring the task plan adapts to the actual environment, facilitating subsequent processing.

[0087] Step S40: Generate a corresponding initial task plan in real time based on the target dataset, and adaptively adjust the initial task plan through the detection task pre-playing environment to generate lightning protection detection tasks in real time.

[0088] It's important to note that the system first generates an initial task plan (such as personnel allocation and location sequence) based on the target dataset. This plan is then imported into a simulation environment for testing. Through adaptive adjustments to the simulation environment (such as avoiding route conflicts and excessive personnel load issues discovered during the simulation), a directly executable lightning protection detection task is finally generated. This step, through a "generate-verify-optimize" cycle, ensures the feasibility and efficiency of the task plan, facilitating subsequent processing.

[0089] Second Embodiment

[0090] Furthermore, the step of extracting the corresponding detection features contained in the target detection location in real time based on preset rules includes:

[0091] Obtain location information corresponding to the target detection location, and perform attribute parsing processing on the location information through a preset semantic recognition model to separate static attribute information and dynamic attribute information accordingly;

[0092] The static attribute information is imported into a preset building lightning protection feature matrix to output the corresponding voltage detection feature, and the dynamic attribute information is matched with a preset risk coefficient lookup table to output the corresponding lightning strike risk coefficient.

[0093] Based on the voltage detection characteristics and the lightning strike risk coefficient, a corresponding feature association map is constructed in real time, and the detection characteristics are generated accordingly based on the feature association map.

[0094] It should be noted that, firstly, complete information about the target detection location (such as address, building structure, usage function, historical lightning records, etc.) is obtained. Then, the information is parsed using a preset semantic recognition model (such as an attribute classification model based on NLP) to separate two types of attributes: static attribute information and dynamic attribute information. Specifically, static attribute information includes long-term stable features, such as building height, material, and type of lightning protection facilities. Correspondingly, dynamic attribute information includes features that change dynamically over time, such as seasonal lightning frequency, changes in surrounding vegetation, and recent construction status. Based on this, the static attribute information is imported into a preset "building lightning protection feature matrix" (this matrix is ​​built based on industry standards and includes the correspondence between different building parameters and lightning protection requirements), and outputs voltage detection features suitable for the location (such as grounding resistance detection threshold, surge protector testing standards, etc.). Correspondingly, the dynamic attribute information is matched with a preset "risk coefficient comparison table" (this table integrates meteorological data, historical accident statistics, etc.), and outputs a "lightning strike risk coefficient" reflecting the current probability of lightning strikes (such as high / medium / low risk levels and specific values). Finally, based on voltage detection characteristics and lightning strike risk coefficients, the system constructs a feature correlation map. Specifically, this map visualizes the dependencies between features (such as the positive correlation between "building height" and "voltage detection threshold"). Ultimately, the most critical core features for the detection task are extracted from the map to form "detection features." This step ensures that the extracted features are not only comprehensive but also reflect the inherent relationships between various factors, improving the accuracy of subsequent data matching and facilitating subsequent processing.

[0095] Furthermore, the step of constructing a corresponding feature correlation map in real time based on the voltage detection characteristics and the lightning strike risk coefficient, and generating the detection characteristics based on the feature correlation map, includes:

[0096] The historical detection data generated by the voltage detection feature in a preset time period are detected in real time in a preset database, and the rate of change of the voltage detection feature in each detection cycle is calculated to construct the corresponding feature change trend vector.

[0097] The Pearson correlation coefficient that matches the voltage detection feature is calculated in real time based on the feature change trend vector, and the feature association map is constructed in real time with the voltage detection feature as the node and the Pearson correlation coefficient as the weight value.

[0098] The PageRank algorithm is used to calculate the influence value of each node in the feature association graph, and the influence value of each node is weighted by the lightning strike risk coefficient, so as to finally select the core feature node with the highest influence value as the detection feature.

[0099] It should be noted that the system retrieves historical detection data for the voltage detection feature within a preset time period (e.g., the past 3 years) from a pre-set database, calculates its rate of change (e.g., annual increase in grounding resistance) for each detection cycle (e.g., each quarter), and constructs a "feature change trend vector." This vector visually reflects the long-term change pattern of the feature, such as "the grounding resistance value in a certain area increases by an average of 5% annually," providing a basis for judging the stability of the feature. Based on this, and using the feature change trend vector, the system calculates the Pearson correlation coefficient (a statistic measuring the degree of linear correlation between variables) between the voltage detection feature and other related features (e.g., building height, surrounding terrain). Subsequently, using the voltage detection feature as the core node and the Pearson correlation coefficient as the weight value (the higher the coefficient, the thicker the connection), a feature association graph is constructed. For example, if the correlation coefficient between "building height" and "voltage detection threshold" is 0.8, then the two are connected with high weight in the graph, visually reflecting the strength of the correlation. Finally, the system uses the PageRank algorithm (originally used for webpage ranking, but here it's used to assess feature importance) to calculate the influence value of each node in the graph. This influence value is then weighted by combining the lightning strike risk coefficient (e.g., increasing the weight of the "surge protector" feature in high-risk areas). Ultimately, the top N (e.g., top 5) core feature nodes with the highest influence values ​​are selected as "detection features." This step quantifies feature importance through an algorithm, ensuring that the selected features best reflect the lightning protection detection needs of the target location, facilitating subsequent processing.

[0100] Furthermore, the step of matching the corresponding target dataset in real time within the personnel database, the detection point database, and the detection agency database based on the detection features includes:

[0101] The detection features are decomposed into dimensions to generate corresponding personnel adaptation features, location matching features, and institutional collaboration features. The qualification files and historical detection records of all personnel are retrieved from the personnel database to select candidate personnel datasets based on the personnel adaptation features.

[0102] The geographic coordinates and attribute information of all points are extracted from the detection point database to filter candidate point datasets based on the point matching features. The service area maps and cooperation evaluation records of all institutions are obtained from the detection institution database to filter candidate institution datasets based on the institution collaboration features.

[0103] The candidate personnel dataset, the candidate location dataset, and the candidate institution dataset are linked and integrated to generate the target dataset.

[0104] It's important to note that the detection features are first decomposed into three sub-features: personnel suitability features (e.g., high-voltage electrician's certificate) and skill requirements (e.g., drone operation ability); location matching features (e.g., lightning protection level of the location (Level 1 and Level 2, etc.) and facility type (e.g., substation or communication tower); and institutional collaboration features (e.g., service coverage and emergency response speed requirements). Based on this, candidate personnel datasets meeting the qualification and skill requirements are selected from the personnel database; candidate location datasets meeting the lightning protection level and facility type are selected from the detection location database; and candidate institutional datasets meeting the service coverage and response requirements are selected from the detection institution database. The system then integrates these candidate personnel, location, and institutional datasets: for example, ensuring that a detection personnel's service area covers their assigned detection locations and that their affiliated institution can provide the necessary equipment support. Through this multi-dimensional association, a "target dataset" containing personnel, location, and institutional collaboration information is ultimately formed. This step breaks down data silos, ensuring that the three types of data can collaboratively support task generation for subsequent processing.

[0105] Furthermore, the step of associating and integrating the candidate personnel dataset, the candidate location dataset, and the candidate institution dataset to generate the target dataset includes:

[0106] Obtain the detection timeliness parameters of each person in the candidate personnel dataset, the lightning protection level parameters of each point in the candidate point dataset, and the scheduling response parameters of each institution in the candidate institution dataset;

[0107] The detection timeliness parameter and the lightning protection level parameter are weighted and calculated to generate a first correlation value, and the scheduling response parameter and the geographical coordinates of the location are used to calculate the distance to generate a second correlation value.

[0108] A corresponding three-dimensional association array is constructed based on the first association value and the second association value, and the array elements in the three-dimensional association array are extracted so as to set the array elements as the target dataset.

[0109] It should be noted that three core parameters are extracted from the three datasets. Specifically, the detection timeliness parameter includes the average time for personnel to complete a single detection and the historical on-time rate of tasks; the lightning protection level parameter includes the lightning protection importance level of the detection point (e.g., special level / level 1) and the required detection accuracy; and the scheduling response parameter includes the organization's equipment scheduling speed and emergency support time. Based on this, the first correlation value is calculated: the detection timeliness parameter and the lightning protection level parameter are weighted (e.g., higher-level points correspond to higher timeliness weights), reflecting the matching efficiency of "personnel-point". Correspondingly, the second correlation value is calculated: the distance between the scheduling response parameter and the geographical coordinates of the point is measured (e.g., the straight-line distance between the organization and the point / travel time), reflecting the collaborative convenience of "organization-point". Based on this, and combining the basic information of personnel, locations, and institutions, a three-dimensional associated data set (with dimensions of "personnel-location-institution") is constructed. Each element in the array represents the overall matching degree of the three. The system then extracts the elements with the highest matching degree from the three-dimensional associated array (e.g., the top 20% of combinations in terms of overall score), integrates the personnel, location, and institution information corresponding to these elements, and forms the final "target dataset." This step uses quantitative calculations to ensure the objectivity and optimality of the data association, facilitating subsequent processing.

[0110] Furthermore, the step of generating a corresponding initial task plan in real time based on the target dataset, and adaptively adjusting the initial task plan through the detection task rehearsal environment to generate a lightning protection detection task in real time includes:

[0111] Based on the distribution density of detection points in the target dataset, a corresponding standard detection grid is divided, and the detection personnel with corresponding qualifications in the personnel database are embedded into the standard detection grid to form the initial task plan.

[0112] The lightning activity frequency data of the target detection location is imported into the detection task simulation environment to simulate the lightning warning level at different time periods, and the detection route in the initial task plan is dynamically simulated and adjusted accordingly.

[0113] The corresponding round-trip travel time is calculated based on the adjusted detection route. Combined with the estimated detection time of the detection points, a three-dimensional task matrix including personnel configuration, route planning and time nodes is generated, and the three-dimensional task matrix is ​​converted into the lightning protection detection task in real time.

[0114] It's important to note that, based on the distribution density of detection points in the target dataset, the system divides the target area into several "standard detection grids" (e.g., 1km x 1km square areas) to ensure a balanced number of detection points within each grid. Subsequently, based on personnel qualifications and geographical location, candidates are embedded into corresponding grids (e.g., assigning personnel skilled in high-voltage equipment inspection to grids with dense substation activity), forming an "initial task plan" that includes personnel allocation and a list of detection points. This step ensures the basic rationality of task allocation. Based on this, the system imports historical lightning activity frequency data (e.g., monthly lightning strike counts, peak periods) of the target location into the detection task simulation environment, simulating different lightning warning levels for different time periods (e.g., red warnings during heavy rain). Based on the simulation results, the detection routes in the initial plan are dynamically extrapolated: for example, outdoor detection during peak lightning periods is avoided, and routes are adjusted to reduce cross-regional travel time, ultimately forming an optimized detection route. This step mitigates potential risks in actual execution through virtual simulation. Finally, the system calculates the round-trip travel time based on the adjusted route and combines this with the estimated detection time for each location (e.g., 30 minutes for primary locations and 15 minutes for secondary locations) to generate a three-dimensional task matrix containing "personnel allocation - route planning - time nodes". For example, a row in the matrix might be "Inspector A - Route B - 9:00 AM - 11:30 AM". Finally, this matrix is ​​converted into executable lightning protection detection tasks (e.g., electronic work orders, paper task sheets, etc.). This step transforms the task plan from abstract data into specific operational instructions, facilitating subsequent processing.

[0115] Furthermore, the step of converting the three-dimensional task matrix into the lightning protection detection task in real time includes:

[0116] Based on the coordinate parameters of each detection point in the three-dimensional task matrix, an electronic inspection map containing latitude and longitude information is generated, and the lightning risk level of each detection point is marked in the electronic inspection map.

[0117] The detection tasks in the three-dimensional task matrix are sorted according to the priority of the time nodes, and the sorted task sequence is bound with the biometric information of the detection personnel to generate a task execution list containing personnel-specific identifiers.

[0118] The route planning data in the three-dimensional task matrix is ​​extracted, and a dynamic navigation path is constructed by combining it with real-time meteorological data. The electronic inspection map, the task execution list, and the dynamic navigation path are then integrated to generate the lightning protection detection task.

[0119] It's important to note that, based on the coordinate parameters (latitude and longitude) of each detection point in the 3D task matrix, the system generates an electronic inspection map and marks the lightning risk level of each point on the map (e.g., red for high risk, yellow for medium risk). The map supports zooming and navigation functions, providing intuitive spatial guidance for inspection personnel. Based on this, the system prioritizes tasks according to time nodes (e.g., high-risk points are inspected first), forming a task sequence. Simultaneously, the sequence is linked to the biometric information of the inspection personnel (e.g., fingerprints, employee ID), generating a task execution list containing unique personnel identifiers (e.g., "Inspector A's Tasks Today") to ensure accountability. Finally, the system extracts route planning data and combines it with real-time meteorological data (e.g., the probability of rainfall in the next 2 hours) to construct a dynamic navigation path (allowing real-time avoidance of thunderstorm areas). Finally, the electronic inspection map, task execution list, and dynamic navigation path are integrated into a complete lightning protection inspection task, delivered to the personnel via app push notifications, printed documents, etc. This step, through the integration of multi-dimensional information, ensures the convenience and safety of task execution, facilitating subsequent processing.

[0120] Please see Figure 2 The third embodiment of the present invention provides:

[0121] A lightning protection detection task generation system, wherein the system includes:

[0122] The response module is used to respond to the task generation command and activate the preset cloud server, which stores a personnel database, a detection point database, and a detection agency database.

[0123] The receiving module is used to receive the target detection location input by the user in real time, and extract the corresponding detection features contained in the target detection location in real time based on preset rules;

[0124] The matching module is used to match the corresponding target dataset in real time within the personnel database, the detection point database, and the detection agency database based on the detection features, and to build a detection task rehearsal environment adapted to the target detection location in real time based on the data twin program.

[0125] The adjustment module is used to generate a corresponding initial task plan in real time based on the target dataset, and to adaptively adjust the initial task plan through the detection task pre-playing environment to generate lightning protection detection tasks in real time.

[0126] Furthermore, the receiving module is specifically used for:

[0127] Obtain location information corresponding to the target detection location, and perform attribute parsing processing on the location information through a preset semantic recognition model to separate static attribute information and dynamic attribute information accordingly;

[0128] The static attribute information is imported into a preset building lightning protection feature matrix to output the corresponding voltage detection feature, and the dynamic attribute information is matched with a preset risk coefficient lookup table to output the corresponding lightning strike risk coefficient.

[0129] Based on the voltage detection characteristics and the lightning strike risk coefficient, a corresponding feature association map is constructed in real time, and the detection characteristics are generated accordingly based on the feature association map.

[0130] Furthermore, the receiving module is specifically used for:

[0131] The historical detection data generated by the voltage detection feature in a preset time period are detected in real time in a preset database, and the rate of change of the voltage detection feature in each detection cycle is calculated to construct the corresponding feature change trend vector.

[0132] The Pearson correlation coefficient that matches the voltage detection feature is calculated in real time based on the feature change trend vector, and the feature association map is constructed in real time with the voltage detection feature as the node and the Pearson correlation coefficient as the weight value.

[0133] The PageRank algorithm is used to calculate the influence value of each node in the feature association graph, and the influence value of each node is weighted by the lightning strike risk coefficient, so as to finally select the core feature node with the highest influence value as the detection feature.

[0134] Furthermore, the receiving module is specifically used for:

[0135] The detection features are decomposed into dimensions to generate corresponding personnel adaptation features, location matching features, and institutional collaboration features. The qualification files and historical detection records of all personnel are retrieved from the personnel database to select candidate personnel datasets based on the personnel adaptation features.

[0136] The geographic coordinates and attribute information of all points are extracted from the detection point database to filter candidate point datasets based on the point matching features. The service area maps and cooperation evaluation records of all institutions are obtained from the detection institution database to filter candidate institution datasets based on the institution collaboration features.

[0137] The candidate personnel dataset, the candidate location dataset, and the candidate institution dataset are linked and integrated to generate the target dataset.

[0138] Furthermore, the receiving module is specifically used for:

[0139] Obtain the detection timeliness parameters of each person in the candidate personnel dataset, the lightning protection level parameters of each point in the candidate point dataset, and the scheduling response parameters of each institution in the candidate institution dataset;

[0140] The detection timeliness parameter and the lightning protection level parameter are weighted and calculated to generate a first correlation value, and the scheduling response parameter and the geographical coordinates of the location are used to calculate the distance to generate a second correlation value.

[0141] A corresponding three-dimensional association array is constructed based on the first association value and the second association value, and the array elements in the three-dimensional association array are extracted so as to set the array elements as the target dataset.

[0142] Furthermore, the receiving module is specifically used for:

[0143] Based on the distribution density of detection points in the target dataset, a corresponding standard detection grid is divided, and the detection personnel with corresponding qualifications in the personnel database are embedded into the standard detection grid to form the initial task plan.

[0144] The lightning activity frequency data of the target detection location is imported into the detection task simulation environment to simulate the lightning warning level at different time periods, and the detection route in the initial task plan is dynamically simulated and adjusted accordingly.

[0145] The corresponding round-trip travel time is calculated based on the adjusted detection route. Combined with the estimated detection time of the detection points, a three-dimensional task matrix including personnel configuration, route planning and time nodes is generated, and the three-dimensional task matrix is ​​converted into the lightning protection detection task in real time.

[0146] Furthermore, the receiving module is specifically used for:

[0147] Based on the coordinate parameters of each detection point in the three-dimensional task matrix, an electronic inspection map containing latitude and longitude information is generated, and the lightning risk level of each detection point is marked in the electronic inspection map.

[0148] The detection tasks in the three-dimensional task matrix are sorted according to the priority of the time nodes, and the sorted task sequence is bound with the biometric information of the detection personnel to generate a task execution list containing personnel-specific identifiers.

[0149] The route planning data in the three-dimensional task matrix is ​​extracted, and a dynamic navigation path is constructed by combining it with real-time meteorological data. The electronic inspection map, the task execution list, and the dynamic navigation path are then integrated to generate the lightning protection detection task.

[0150] The fourth embodiment of the present invention provides a computer, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the lightning protection detection task generation method described above.

[0151] The fifth embodiment of the present invention provides a readable storage medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the lightning protection detection task generation method as described above.

[0152] In summary, the lightning protection detection task generation method and system provided in the above embodiments of the present invention can quickly and effectively generate the required lightning protection detection tasks, thereby improving the task generation efficiency.

[0153] It should be noted that the above modules can be functional modules or program modules, and can be implemented through software or hardware. For modules implemented through hardware, the above modules can reside in the same processor; or the above modules can be located in different processors in any combination.

[0154] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-including system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0155] More specific examples of computer-readable media (a non-exhaustive list) include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0156] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0157] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0158] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the appended claims.

Claims

1. A method for generating lightning protection detection tasks, characterized in that, The method includes: In response to the task generation command, a preset cloud server is activated, which stores a personnel database, a detection point database, and a detection agency database. The system receives the target detection location input by the user in real time and extracts the corresponding detection features contained in the target detection location in real time based on preset rules. Based on the detection features, the corresponding target dataset is matched in real time within the personnel database, the detection point database, and the detection agency database, and a detection task rehearsal environment adapted to the target detection location is constructed in real time based on the data twin program. The initial task plan is generated in real time based on the target dataset, and the initial task plan is adaptively adjusted through the detection task pre-playing environment to generate lightning protection detection tasks in real time. The steps of generating a corresponding initial task plan in real time based on the target dataset, and adaptively adjusting the initial task plan through the detection task pre-playing environment to generate lightning protection detection tasks in real time include: Based on the distribution density of detection points in the target dataset, a corresponding standard detection grid is divided, and the detection personnel with corresponding qualifications in the personnel database are embedded into the standard detection grid to form the initial task plan. The lightning activity frequency data of the target detection location is imported into the detection task simulation environment to simulate the lightning warning level at different time periods, and the detection route in the initial task plan is dynamically simulated and adjusted accordingly. The corresponding round-trip travel time is calculated based on the adjusted detection route. Combined with the expected detection time of the detection points, a three-dimensional task matrix including personnel configuration, route planning and time nodes is generated, and the three-dimensional task matrix is ​​converted into the lightning protection detection task in real time. The step of converting the three-dimensional task matrix into the lightning protection detection task in real time includes: Based on the coordinate parameters of each detection point in the three-dimensional task matrix, an electronic inspection map containing latitude and longitude information is generated, and the lightning risk level of each detection point is marked in the electronic inspection map. The detection tasks in the three-dimensional task matrix are sorted according to the priority of the time nodes, and the sorted task sequence is bound with the biometric information of the detection personnel to generate a task execution list containing personnel-specific identifiers. The route planning data in the three-dimensional task matrix is ​​extracted, and a dynamic navigation path is constructed by combining it with real-time meteorological data. The electronic inspection map, the task execution list, and the dynamic navigation path are then integrated to generate the lightning protection detection task.

2. The lightning protection detection task generation method according to claim 1, characterized in that, The step of extracting the corresponding detection features contained in the target detection location in real time based on preset rules includes: Obtain location information corresponding to the target detection location, and perform attribute parsing processing on the location information through a preset semantic recognition model to separate static attribute information and dynamic attribute information accordingly; The static attribute information is imported into a preset building lightning protection feature matrix to output the corresponding voltage detection feature, and the dynamic attribute information is matched with a preset risk coefficient lookup table to output the corresponding lightning strike risk coefficient. Based on the voltage detection characteristics and the lightning strike risk coefficient, a corresponding feature association map is constructed in real time, and the detection characteristics are generated accordingly based on the feature association map.

3. The lightning protection detection task generation method according to claim 2, characterized in that, The step of constructing a corresponding feature correlation map in real time based on the voltage detection characteristics and the lightning strike risk coefficient, and generating the detection characteristics based on the feature correlation map, includes: The historical detection data generated by the voltage detection feature in a preset time period are detected in real time in a preset database, and the rate of change of the voltage detection feature in each detection cycle is calculated to construct the corresponding feature change trend vector. The Pearson correlation coefficient that matches the voltage detection feature is calculated in real time based on the feature change trend vector, and the feature association map is constructed in real time with the voltage detection feature as the node and the Pearson correlation coefficient as the weight value. The PageRank algorithm is used to calculate the influence value of each node in the feature association graph, and the influence value of each node is weighted by the lightning strike risk coefficient, so as to finally select the core feature node with the highest influence value as the detection feature.

4. The lightning protection detection task generation method according to claim 1, characterized in that, The step of matching the corresponding target dataset in real time within the personnel database, the detection point database, and the detection institution database based on the detection features includes: The detection features are decomposed into dimensions to generate corresponding personnel adaptation features, location matching features, and institutional collaboration features. The qualification files and historical detection records of all personnel are retrieved from the personnel database to select candidate personnel datasets based on the personnel adaptation features. The geographic coordinates and attribute information of all points are extracted from the detection point database to filter candidate point datasets based on the point matching features. The service area maps and cooperation evaluation records of all institutions are obtained from the detection institution database to filter candidate institution datasets based on the institution collaboration features. The candidate personnel dataset, the candidate location dataset, and the candidate institution dataset are linked and integrated to generate the target dataset.

5. The lightning protection detection task generation method according to claim 4, characterized in that, The step of linking and integrating the candidate personnel dataset, the candidate location dataset, and the candidate institution dataset to generate the target dataset includes: Obtain the detection timeliness parameters of each person in the candidate personnel dataset, the lightning protection level parameters of each point in the candidate point dataset, and the scheduling response parameters of each institution in the candidate institution dataset; The detection timeliness parameter and the lightning protection level parameter are weighted and calculated to generate a first correlation value, and the scheduling response parameter and the geographical coordinates of the location are used to calculate the distance to generate a second correlation value. A corresponding three-dimensional association array is constructed based on the first association value and the second association value, and the array elements in the three-dimensional association array are extracted so as to set the array elements as the target dataset.

6. A lightning protection detection task generation system, characterized in that, The system for implementing the lightning protection detection task generation method as described in any one of claims 1 to 5 includes: The response module is used to respond to the task generation command and activate the preset cloud server, which stores a personnel database, a detection point database, and a detection agency database. The receiving module is used to receive the target detection location input by the user in real time, and extract the corresponding detection features contained in the target detection location in real time based on preset rules; The matching module is used to match the corresponding target dataset in real time within the personnel database, the detection point database, and the detection agency database based on the detection features, and to build a detection task rehearsal environment adapted to the target detection location in real time based on the data twin program. The adjustment module is used to generate a corresponding initial task plan in real time based on the target dataset, and to adaptively adjust the initial task plan through the detection task pre-playing environment to generate lightning protection detection tasks in real time.

7. A computer comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the lightning protection detection task generation method as described in any one of claims 1 to 5.

8. A readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the lightning protection detection task generation method as described in any one of claims 1 to 5.

Images