Decision tree forest-based lightning protection design evaluation method and system, terminal and medium

Abstract

The invention discloses a lightning protection design evaluation method and system based on a decision tree forest, a terminal and a medium, and relates to the technical field of lightning protection design analysis, and the method is characterized in that data aggregation processing is carried out on multi-source lightning protection technical standard terms, and a structured lightning protection term data set of a dynamic hierarchical classification architecture is obtained; generating a special decision tree of each lightning protection measure type, and implanting an AHP weight engine and a conflict resolution engine into nodes of the decision tree; inputting lightning protection design parameters to be evaluated into the decision tree forest model to obtain a preliminary compliance identification result; performing dynamic branch adjustment processing on the decision tree forest model according to environmental condition parameters, and regenerating an environmental adaptation identification result; and generating and processing a visual report to obtain a lightning protection design evaluation report. According to the method, the standard dispersity is solved through a dynamic hierarchical classification architecture, the limitation of a static model is broken through through a double-engine decision tree forest, and precise protection of a complex scene is realized through environmental risk quantification.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of lightning protection design analysis, more specifically, it relates to a lightning protection design evaluation method, system, terminal and medium based on a decision tree forest. BACKGROUND

[0002] Lightning is a transient large current, high voltage and strong electromagnetic radiation weather phenomenon occurring in the atmosphere, and lightning disaster is listed as "one of the ten most serious natural disasters" by relevant departments. With the improvement of facility lightning protection safety requirements, the coexistence of multi-source lightning protection technical standards leads to redundant and conflicting clauses. The existing technology relies on manual analysis of scattered standard files, and it is difficult to realize dynamic environment adaptation and conflict resolution, such as different standards requiring different parameters, and traditional evaluation methods using fixed threshold judgment, which cannot respond to complex environment combinations.

[0003] Therefore, how to design a lightning protection design evaluation method, system, terminal and medium based on a decision tree forest which can overcome the above defects is a technical problem we need to solve at present. SUMMARY

[0004] To solve the problems in the prior art, the purpose of the present application is to provide a lightning protection design evaluation method, system, terminal and medium based on a decision tree forest. The present application solves the standard dispersion through a dynamic hierarchical classification architecture, breaks through the limitations of static models through a double-engine decision tree forest, and realizes precise protection in complex scenarios through environmental risk quantification.

[0005] The above technical purpose of the present application is realized by the following technical scheme: In a first aspect, a lightning protection design evaluation method based on a decision tree forest is provided, comprising the following steps: S1: performing data aggregation processing on multi-source lightning protection technical standard clauses to obtain a structured lightning protection clause dataset of a dynamic hierarchical classification architecture; S2: generating a special decision tree for each lightning protection measure type according to the structured lightning protection clause dataset, and implanting an AHP weight engine and a conflict resolution engine at the nodes of the decision tree to obtain a decision tree forest model with weighted branches; S3: inputting the lightning protection design parameters to be evaluated into the decision tree forest model for dynamic weight integration and conflict resolution processing to obtain a preliminary compliance identification result; S4: performing dynamic branch adjustment processing on the decision tree forest model according to the environmental condition parameters, and regenerating an environment-adaptive identification result based on the preliminary compliance identification result; S5: inputting the environment-adaptive identification result into a meteorological disaster risk management system integration gateway for visual report generation processing to obtain a lightning protection design evaluation report.

[0006] Further, the dynamic hierarchical classification architecture of the structured lightning protection clause dataset comprises: a measure-oriented layer, configured to establish a plurality of main classes according to the lightning protection measure types; an object scenario layer, configured to establish sub-classes under each of the main classes according to applicable objects and application scenarios; a condition constraint layer, configured to construct a tree structure according to parameter logical relationships within the sub-classes; wherein the root node of the tree structure is a protection target, the branch node is a condition judgment item, and the leaf node is a specific measure requirement.

[0007] Further, the data aggregation processing of the multi-source lightning protection technical standard clauses comprises: adopting a hierarchical clustering algorithm based on Levenshtein distance and semantic similarity weighting to dynamically group atomic clause units according to similarity into the dynamic hierarchical classification architecture; extracting a keyword TF-IDF vector and a classification path code for each of the atomic clause units to generate a classification feature vector that can be recognized and dynamically matched by a machine.

[0008] Further, the decision tree nodes implanted by the AHP weight engine are root nodes and branch nodes, and the functional time sequence position of the AHP weight engine is after condition judgment and before branch selection. wherein the input of the AHP weight engine is a set of technical elements, a judgment matrix, and a consistency threshold, and the output is an element weight vector and a consistency check state.

[0009] Further, the conflict resolution engine is configured to: read the element weight vector output by the AHP weight engine and the satisfaction degree of a single parameter; determine the conflict mark between two parameters; retrieve the corresponding priority from the rule base according to the conflict mark to obtain a rule weight; obtain the priority value of the corresponding parameter by multiplying the AHP weight in the element weight vector, the satisfaction degree, and the rule weight; rule the clause corresponding to the parameter with a larger priority value.

[0010] Further, the process of dynamic branch adjustment processing is specifically: obtain an environmental condition parameter including at least one of a geographical parameter, a meteorological parameter, and a geological parameter; determine an environmental risk value according to the absolute value of the difference between the parameter value in the environmental condition parameter and the corresponding parameter threshold, wherein the larger the absolute value of the difference, the larger the corresponding environmental risk value; selecting a maximum value among all the environmental risk values as an execution risk value; when the execution risk value is greater than a first threshold value: retrieving a substitute branch library matching the current environmental parameter from the decision tree forest model; and selecting an optimal branch using a satisfaction degree weighted voting mechanism to replace the original decision tree corresponding branch; when the execution risk value is greater than a second threshold value and less than or equal to the first threshold value: proportionally increasing the AHP weight of the corresponding node according to the execution risk value.

[0011] Further, the proportionally increasing the AHP weight of the corresponding node according to the execution risk value specifically includes: calculating the increased AHP weight increment by multiplying the industry risk coefficient and the execution risk value; if the sum of the AHP weight increment and the original AHP weight is less than 1, then using the sum as the updated AHP weight; if the updated AHP weight is equal to 1, then re-normalizing the AHP weight.

[0012] In a second aspect, a lightning protection design evaluation system based on a decision tree forest is provided, including: a data processing module configured to perform data aggregation processing on multiple-source lightning protection technical standard clauses to obtain a structured lightning protection clause dataset of a dynamic hierarchical classification architecture; a model construction module configured to generate a special decision tree for each lightning protection measure type according to the structured lightning protection clause dataset, and implant an AHP weight engine and a conflict resolution engine at a decision tree node to obtain a decision tree forest model with weighted branches; a preliminary identification module configured to input a lightning protection design parameter to be evaluated into the decision tree forest model for dynamic weight integration and conflict resolution processing to obtain a preliminary compliance identification result; an optimization identification module configured to perform dynamic branch adjustment processing on the decision tree forest model according to environmental condition parameters, and regenerate an environment-adapted identification result based on the preliminary compliance identification result; a report generation module configured to input the environment-adapted identification result into a meteorological disaster risk management system integration gateway for visual report generation processing to obtain a lightning protection design evaluation report.

[0013] In a third aspect, a computer terminal is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the lightning protection design evaluation method based on the decision tree forest as described in any one of the first aspect.

[0014] In a fourth aspect, a computer readable medium is provided, and a computer program is stored on the computer readable medium, and the computer program is executable by a processor to implement the lightning protection design evaluation method based on the decision tree forest according to any one of the first aspect.

[0015] Compared with the prior art, the present application has the following beneficial effects: 1. The lightning protection design evaluation method based on the decision tree forest provided by the present application solves the standard dispersion through a dynamic hierarchical classification architecture, breaks through the limitations of static models through the decision tree forest of the double engine, and realizes precise protection in complex scenes through environmental risk quantification, thereby comprehensively overcoming the bottlenecks of the prior art. According to verification of 26 engineering projects, the identification accuracy is 96.3%, and the comprehensive efficiency is improved by 48 hours, thereby providing the first solution of "multi-source integration-dynamic adaptation-intelligent decision" for the field of lightning protection design evaluation. 2. The present application constructs a three-layer tree structure composed of a measure-oriented layer, an object scene layer and a condition constraint layer, forms a machine-resolvable hierarchical logic chain with a root node (protection target), a branch node (condition judgment item) and a leaf node (measure requirement), realizes the structured analysis and automatic matching of lightning protection clauses, solves the problem that the traditional text standard cannot be directly called by the algorithm, and effectively improves the matching efficiency of the atomic clause unit through tree path coding. 3. The present application adopts Levenshtein distance (character level similarity) and BERT semantic similarity weighted, controls the clustering direction through a dynamic weight coefficient, realizes accurate merging of cross-standard clauses by combining the hierarchical clustering method, breaks through the conflict of synonyms and numerical precision, and improves the clause merging accuracy. 4. The present application positions the AHP weight engine in time sequence after the condition judgment and before the branch selection of the decision tree node, inputs the technical element set / judgment matrix, and outputs the weight vector to drive the branch selection, and optimizes the judgment matrix by fusing the clustering distance, thereby effectively solving the problem that the analytic hierarchy process is separated from the actual data. 5. The present application triggers operation according to the risk value grading, can realize adaptive protection in complex scenes such as high corrosion and high altitude, and can overcome the problem of inaccurate judgment of environmental parameter dispersion by quantifying the environmental risk value through the relative deviation method. BRIEF DESCRIPTION OF DRAWINGS

[0016] The drawings described herein are used to provide further understanding of the embodiments of the present application, constitute a part of the present application, and do not constitute a limitation on the embodiments of the present application. In the drawings: Figure 1 is a flowchart in embodiment 1 of the present application; Figure 2 is a schematic diagram of the lightning arrester spacing distance decision tree in embodiment 1 of the present application; Figure 3 is a system block diagram in embodiment 2 of the present application. DETAILED DESCRIPTION

[0017] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with examples and drawings. The exemplary embodiments of the present invention and their descriptions are only used to explain the present invention and are not intended to limit the present invention.

[0018] Example 1: A lightning protection design evaluation method based on a decision tree forest comprises the following steps: S1: Aggregate data from multiple sources of lightning protection technical standard clauses to obtain a structured lightning protection clause dataset with a dynamic hierarchical classification architecture; S2: Generate a dedicated decision tree for each type of lightning protection measure based on the structured lightning protection clause dataset, and implant the AHP weight engine and conflict resolution engine into the decision tree nodes to obtain a decision tree forest model with weighted branches; S3: Input the lightning protection design parameters to be evaluated into the decision tree forest model for dynamic weight integration and conflict resolution to obtain preliminary compliance identification results; S4: Dynamically adjust the branches of the decision tree forest model according to the environmental condition parameters, and regenerate the environmental adaptation identification results based on the preliminary compliance identification results; S5: Input the environmental adaptability identification results into the meteorological disaster risk management system integrated gateway for visualization report generation and processing to obtain a lightning protection design evaluation report.

[0019] In step S1, a multi-source standard library needs to be established first to support multi-source data collection and preprocessing.

[0020] The process of establishing a multi-source standards library can involve collecting complete text data on lightning protection technical clauses from international standards, national standards, industry standards, local specifications, and specialized technical guidelines through API interfaces, document parsing tools, or manual entry. For example, international standards use the IEC 62305 series, national standards use GB 50057, and industry standards use QX / T 106. Document parsing tools can use PDF text extraction or OCR (Optical Character Recognition) recognition methods.

[0021] Then, using natural language processing (NLP) technology based on syntactic dependency analysis and semantic role labeling, complex clauses are broken down into indivisible atomic units. For example, the clause "When a building's height exceeds 60 meters, a lightning grid must be installed on the roof" is broken down into two atomic units: "Height > 60 meters" and "Install a rooftop lightning grid."

[0022] Then, the following attributes are labeled for each atomic clause unit: source standard, clause original number, validity type, applicable object, lightning protection measure type, and associated parameter. Specifically, the source standard includes the name and version number. The validity type is divided into mandatory and recommended. The applicable object can be divided into lightning protection building categories and types, etc. The building lightning protection categories are, for example, class 1 lightning protection building, class 2 lightning protection building, and class 3 lightning protection building. The system types are, for example, power supply system and signal system. The lightning protection measure types are, for example, lightning rod, current diversion, grounding, shielding, equipotential bonding, and SPD configuration. The associated parameters are, for example, height, thunderstorm day, soil resistivity, and equipment voltage withstand level.

[0023] The dynamic hierarchical classification architecture of the structured lightning protection clause dataset in the application includes a measure-oriented layer, an object scenario layer, and a condition constraint layer.

[0024] The measure-oriented layer mainly establishes multiple main classes according to lightning protection measure types. The main classes include, but are not limited to, lightning protection class LSP, current diversion protection class CB, grounding system class ES, electromagnetic shielding class EMS, equipotential bonding class BBN, and surge protection device class SPD.

[0025] The object scenario layer mainly establishes sub-classes under each main class according to applicable objects and application scenarios. The applicable objects are, for example, communication base station, chemical plant, and high-rise residential building. The application scenarios are, for example, new construction / reconstruction and indoor / outdoor.

[0026] The condition constraint layer mainly constructs a tree structure according to parameter logical relationships within the sub-classes. The root node of the tree structure is a protection target, such as "protecting building personnel safety". The branch nodes are condition judgment items, such as "building height H" and "annual average thunderstorm day Td". The leaf nodes are specific measure requirements, such as "lightning rod grid size ≤ 10m × 10m".

[0027] Traditional data clustering methods mainly include pure text clustering (TF-IDF), pure semantic clustering (BERT), and K-means static clustering. The pure text clustering method cannot handle synonyms, such as "grounding" and "bonding". The pure semantic clustering (BERT) easily ignores numerical precision, such as "10m" and "100m". The K-means static clustering cannot adapt to new standards.

[0028] The application takes into account that the same technical requirements have text differences in different standards, such as "lightning rod belt" and "lightning rod conductor". In addition, equivalent clauses may be described in different sentence patterns, such as "grid size ≤ 5m" and "distance between adjacent downlead ≤ 5m". In addition, there are some clauses that are similar on the surface but conflict in essence, such as "when soil resistivity > 500Ω·m, grounding resistance can be relaxed to 30Ω" and "must maintain 10Ω".

[0029] When performing data aggregation processing on multi-source lightning protection technical standard clauses, the present invention adopts a hierarchical clustering algorithm based on the weighting of Levenshtein distance (character-level similarity) and semantic similarity (such as BERT) to dynamically classify atomic clause units into a dynamic hierarchical classification architecture according to similarity; extracts the keyword TF-IDF vector and classification path encoding for each atomic clause unit to generate a classification feature vector that can be machine-recognized and dynamically matched.

[0030] First, the atomized set of lightning protection standard clauses undergoes text cleaning and terminology standardization. Text cleaning involves removing legal descriptions and reference marks from clauses, such as "shall" and "should," and reference marks like "see Article 4.2.3." It also removes all non-text symbols, such as brackets, punctuation, and serial numbers, and converts all characters to lowercase, such as "SPD" to "spd." Terminology standardization primarily involves establishing a synonym mapping dictionary, which replaces synonyms by traversing the clause text. For example, synonyms for "lightning network" include "lightning grid," "lightning arrester," and "lightning protection network," while synonyms for "SPD" include "surge protector" and "surge arrester."

[0031] Then for any two clause texts and Calculate Levenshtein distance and semantic similarity simultaneously.

[0032] The specific calculation process of Levenshtein distance is as follows: first calculate becomes The minimum number of single-character edits required, including insert, delete, and replace operations; then determine and The maximum character length in the text is determined by the ratio of the minimum number of single-character edits to the maximum character length. and Levenshtein distance between .

[0033] The specific calculation process of semantic similarity is as follows: first, the two clause texts and Input into the pre-trained multilingual BERT model to generate the dimensional semantic vector of the corresponding text and ; Then calculate the cosine similarity of the two clause texts: ; Finally, convert the cosine similarity into semantic distance to get the two clause texts and The semantic similarity between .

[0034] Different weight coefficients are configured for different clause types. For example, if the clause contains a numerical parameter, the weight coefficient is set to 0.2 by enhancing the accuracy of character comparison ; for example, if the clause contains a professional term, the weight coefficient is set to 0.6 by focusing on semantic understanding ; and when neither of the above conditions exists, the weight coefficient is set to 0.5 in the balanced mode.

[0035] The final distance between two clause texts is determined by combining the Levenshtein distance and the semantic similarity . .

[0036] When hierarchical clustering is performed, a distance matrix is first constructed according to the final distance. For example, N distance values are calculated for N clauses to generate a symmetric distance matrix , and the main diagonal is 0.

[0037] Then, clustering and merging iterations are performed, and the loop is executed until the termination condition is met: the minimum distance value is located in the ; the clusters and the cluster are merged to form a new cluster ; by deleting the rows and columns of , and , and adding the rows and columns of , the distance between and other clusters is calculated according to the formula: , is the distance between and , is the distance between and , is the distance between and .

[0038] When large clusters (such as national standard clusters) and small clusters (such as local standard clusters) are merged, the weight is automatically balanced , which can effectively solve the clustering scale sensitivity problem; in addition, by correcting the similar clauses after merging, the distance between the new cluster and the external cluster accurately reflects the technical correlation degree.

[0039] ​​In the classification feature vector generation process, the scikit-learn library is used to calculate the TF-IDF vector of the clause text first, and the word frequency feature dimension is generated. For example, the clause is: "The SPD voltage protection level Up of the power inlet should be less than 80% of the equipment withstand voltage Uw", the generated keyword vector is: [Up: 0.32, Uw: 0.28, SPD: 0.25, power: 0.15], and 0.32, 0.28, 0.25 and 0.15 are the corresponding dimension weights. Then the pre-trained BERT model (such as bert-base-chinese) is used to generate sentence vectors to capture implicit semantics and output semantic vectors; then the dynamic hierarchical result is converted into digital code to obtain the classification path code; finally, the TF-IDF vector, the semantic vector and the classification path code are spliced to obtain the classification feature vector, and the BLOB type field of the MySQL database is used for storage.

[0040] The present application can obtain a structured input with clear logic and controllable conflict by intelligently processing the multi-source lightning protection clauses, so as to solve the problems of scattered standards and lagging updates in traditional lightning protection evaluation.

[0041] In step S2, the structured lightning protection clause data set obtained in step S1 can be used to construct different special decision trees, such as the inter lightning rod spacing decision tree shown in the figure. Figure 2

[0042] The decision tree nodes implanted by the AHP weight engine are root nodes and branch nodes, and the function time sequence position of the AHP weight engine is after the condition judgment and before the branch selection; wherein the input of the AHP weight engine is the technical element set, the judgment matrix and the consistency threshold, and the output is the element weight vector and the consistency test state. After the preliminary conclusion is obtained by the condition judgment, the decision value is dynamically corrected by the weight to ensure that the high importance parameter dominates the branch selection.

[0043] Specifically, the technical element set mainly includes the lightning protection parameters associated with the current decision node, which can be extracted from the node condition expression parsed from the structured lightning protection clause data set output in step S1.

[0044] The judgment matrix can be generated based on the expert knowledge base and historical data training, and is optimized by the clustering distance in step S1. First, the relative importance of the parameter pair (m, n) in the technical element set is judged, different relative importance levels are assigned different values, and the initial matrix value can be obtained; then the clustering distance between the m parameter class and the n parameter class is calculated by the clustering distance calculation method in S1 , and the initial value corresponding to the parameter pair (m, n) in the initial matrix value is fused to obtain the optimized element value :​ . The application considers the actual technical correlation between parameters, and corrects the judgment matrix based on clustering distance, thereby ensuring the reliability and accuracy of the judgment matrix.

[0045] The AHP weight engine decomposes the judgment matrix, normalizes the eigenvector corresponding to the maximum eigenvalue to obtain the element weight vector, and performs consistency check on the maximum eigenvalue; if the consistency ratio is less than the consistency threshold, the element weight vector takes effect, and if the consistency ratio is greater than or equal to the consistency threshold, the element weight vector is modified and adjusted.

[0046] Then, the Boolean value obtained by performing Boolean judgment on the parameters in the technical element set is converted into a continuous quantity, and the satisfaction degree of the corresponding parameter can be obtained, and the compliance degree can be accurately quantified. The element weight vector and the satisfaction degree corresponding to the parameter pair are weighted and calculated to obtain a weighted decision value. If the weighted decision value is greater than or equal to the decision threshold, high-risk protection is performed; if the weighted decision value is less than the decision threshold, normal protection is performed. For example, parameter m is the height of a building, the satisfaction degree is 0.9, parameter n is the annual average thunderstorm day, the satisfaction degree is 0.8, the element weight vector corresponding to the parameter pair (m, n) is ; the decision threshold s is 0.7. The weighted decision value is , which is greater than the decision threshold, so the high-risk protection branch is triggered.

[0047] To solve the conflict of multiple source standard clauses in lightning protection design, such as the decision scenario driven by the element weight vector, the problem that the national standard and the line standard have inconsistent requirements for the same parameter, the conflict resolution engine is used to resolve the conflict clauses.

[0048] Specifically, the conflict resolution engine is configured to read the element weight vector output by the AHP weight engine and the satisfaction degree of the single parameter; determine the conflict mark between the two parameters; retrieve the corresponding priority from the rule library according to the conflict mark to obtain the rule weight; multiply the AHP weight in the element weight vector, the satisfaction degree, and the rule weight to obtain the priority value of the corresponding parameter; and resolve the clauses corresponding to the parameter with a larger priority value.

[0049] In some examples, the rule library is designed as follows: if the conflict type is the national standard and the line standard, the line standard with stricter requirements is forced to be executed, and the rule weight of the corresponding priority is 0.9; if the conflict type is mandatory and recommended, the mandatory clause is preferred, and the rule weight of the corresponding priority is 0.85; if the conflict type is the conflict between new and old versions, the clause with the latest release date is adopted, and the rule weight of the corresponding priority is 0.8; if the conflict type is industry-specific conflict, the industry-specific clause is preferred, and the rule weight of the corresponding priority is 0.95, and so on.

[0050] In step S3, the dynamic weight integration is realized by the AHP weight engine, and the conflict resolution processing is realized by the conflict resolution engine. The lightning protection design parameters to be evaluated are output through the corresponding special decision tree to obtain a preliminary compliance identification result.

[0051] In step S4, since the traditional lightning protection evaluation generally uses fixed threshold judgment, such as "if the thunderstorm day is greater than 40 days, the protection level is improved", it cannot respond to complex and variable environmental combinations, such as coastal high corrosion, strong thunderstorm and mountain terrain conditions; in addition, when the environmental conditions exceed the conventional range, the conflict probability of different standard clauses will increase obviously, such as the requirement of GB that the grounding body in high corrosion area is greater than or equal to 100 , while the national standard is greater than or equal to 50 .

[0052] Therefore, the decision tree forest model is dynamically branched and adjusted according to the environmental condition parameters to adapt to complex and variable environmental combinations, and to reduce the conflict probability of clauses.

[0053] In the dynamic branching adjustment process, at least one of the environmental condition parameters including geographical parameters, meteorological parameters and geological parameters is acquired, the geographical parameters such as altitude and terrain, the meteorological parameters such as thunderstorm days, and the geological parameters such as soil resistivity.

[0054] Then, the environmental risk value is determined according to the absolute value of the difference between the parameter value in the environmental condition parameter and the corresponding parameter threshold value, and the greater the absolute value, the greater the corresponding environmental risk value. For example, the environmental risk value is obtained by dividing the absolute value of the difference between the parameter value in the environmental condition parameter and the corresponding parameter threshold value by the parameter value in the environmental condition parameter. For example, the same absolute height difference in a mountainous area can produce a higher risk value, while the same height difference in a plain area can automatically reduce the risk value, and the problem of inaccurate judgment of environmental parameters is overcome by the relative deviation method.

[0055] Then, the maximum value of all the environmental risk values is selected as the execution risk value. When the execution risk value is greater than the first threshold value: the alternative branch library matched with the current environmental parameter is retrieved from the decision tree forest model, the environmental parameter can be encoded by 8-bit binary, and the node to be replaced is located through the decision tree metadata index table; and the optimal branch is selected by using the satisfaction weighted voting mechanism, the original decision tree corresponding branch is replaced, the satisfaction weighted voting mechanism is obtained by combining the satisfaction, the complexity coefficient and the protection coefficient to obtain the voting value, and the maximum voting value is selected as the optimal branch. The complexity coefficient represents the complexity of the environment, the more complex, the greater the complexity coefficient, and the maximum value does not exceed 1. And the protection coefficient represents the protection strictness, the higher the protection requirement, the greater the protection coefficient.

[0056] When the execution risk value is greater than the second threshold value and less than or equal to the first threshold value, the AHP weight of the corresponding node is proportionally increased according to the execution risk value.

[0057] Specifically, the increased AHP weight increment is calculated by the product of the industry risk coefficient and the execution risk value; if the sum of the AHP weight increment and the original AHP weight is less than 1, the sum is taken as the updated AHP weight; if the updated AHP weight is greater than or equal to 1, the AHP weight is re-normalized. Part of the industry risk coefficients are shown in Table 1.

[0058] Table 1 Industry risk coefficients Industry type Thunderstorm days (k1) Corrosion grade (k2) Altitude (k3) Petroleum and chemical 1.5 2.0 0.9 Power plant 1.8 1.5 1.0 Commercial residential 1.0 1.0 0.7 Communication base station 1.2 1.3 1.5 Agricultural facility 0.7 0.5 0.5 It should be noted that, in order to avoid damaging the overall reasoning chain of the decision tree forest, the environmental adaptation identification should be modified based on the preliminary results rather than being independently generated.

[0059] In step S5, the environmental adaptation identification result includes but is not limited to the clause compliance state, the key parameter satisfaction degree, the replaced branch ID, the AHP weight increased node, the real-time data driving adjustment, and the like.

[0060] Working principle: The application solves the standard dispersion through the dynamic hierarchical classification architecture, breaks through the limitation of the static model through the dual-engine decision tree forest, and realizes the accurate protection of complex scenes through the environmental risk quantification, thereby comprehensively overcoming the technical bottlenecks of the prior art. The application is verified by 26 engineering projects, and the identification accuracy reaches 96.3%, and the comprehensive efficiency is improved by 48 hours, thereby providing the first solution of "multi-source integration-dynamic adaptation-intelligent decision" for the lightning protection design evaluation field.

[0061] Those skilled in the art will understand that embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage, etc.) containing computer-usable program code.

[0062] The present application is described with reference to flowcharts and / or block diagrams according to the methods, devices (systems), and computer program products of the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of the flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to produce a machine, so that the instructions executed by the computer or other programmable data processing devices produce a device that implements the functions described in the flowcharts and / or block diagrams. These computer program instructions can also be stored in a computer-readable memory that can guide the computer or other programmable data processing devices to work in a specific manner, so that the instructions stored in the computer-readable memory produce a product including the functions described in the flowcharts and / or block diagrams. The computer-readable memory can be a volatile memory or a non-volatile memory, or a combination of the two.Figure 1 apparatuses that implement the functions specified in the flowchart Figure 1 block or blocks.

[0063] These computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture including instructions which implement the flowchart Figure 1 apparatuses that implement the functions specified in the flowchart Figure 1 block or blocks.

[0064] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the flowchart Figure 1 apparatuses that implement the functions specified in the flowchart Figure 1 block or blocks.

[0065] The above detailed description merely describes a specific implementation of the application, and the specific implementation does not limit the scope of the application. Any modification, equivalent replacement, or improvement made within the spirit and principle of the application shall be included in the scope of the application.

Claims

1. A lightning protection design evaluation method based on decision tree forest is characterized by: The following steps are involved: S1: Aggregate data from multiple sources of lightning protection technical standard clauses to obtain a structured lightning protection clause dataset with a dynamic hierarchical classification architecture; S2: Generate a dedicated decision tree for each type of lightning protection measure based on the structured lightning protection clause dataset, and implant an AHP weight engine and a conflict resolution engine into the decision tree nodes to obtain a decision tree forest model with weighted branches; S3: Inputting the lightning protection design parameters to be evaluated into the decision tree forest model for dynamic weight integration and conflict resolution to obtain preliminary compliance identification results; S4: Dynamically adjusting branches of the decision tree forest model according to environmental condition parameters, and regenerating an environmental adaptation identification result based on the preliminary compliance identification result; S5: Inputting the environmental adaptability identification result into the meteorological disaster risk management system integrated gateway for visualization report generation processing to obtain a lightning protection design evaluation report; The data aggregation processing of the multi-source lightning protection technical standard clauses includes: A hierarchical clustering algorithm based on Levenshtein distance and semantic similarity weighting is used to dynamically classify atomic clause units into the dynamic hierarchical classification framework according to similarity; The keyword TF-IDF vector and classification path code are extracted from each of the atomic clause units to generate a classification feature vector that is machine-recognizable and dynamically matched.

2. The lightning protection design evaluation method based on decision tree forest according to claim 1 is characterized in that: The dynamic hierarchical classification architecture of the structured lightning protection clause dataset includes: A measures-oriented layer, used to establish multiple main categories according to the types of lightning protection measures; The object scenario layer is used to establish subclasses under each main class according to applicable objects and application scenarios; The conditional constraint layer is used to construct a tree structure according to the logical relationship of parameters within the subclass; The root node of the tree structure is the protection target, the branch nodes are the conditional judgment items, and the leaf nodes are the specific measure requirements.

3. The lightning protection design evaluation method based on decision tree forest according to claim 1 is characterized in that: The decision tree nodes implanted by the AHP weight engine are root nodes and branch nodes, and the functional timing position of the AHP weight engine is located after condition judgment and before branch selection; The input of the AHP weight engine is the technical factor set, the judgment matrix and the consistency threshold, and the output is the factor weight vector and the consistency test status.

4. The lightning protection design evaluation method based on decision tree forest according to claim 1 is characterized in that: The conflict resolution engine is configured to: Read the factor weight vector and the satisfaction degree of a single parameter output by the AHP weight engine; Determines a conflict marker between two parameters; Retrieving the corresponding priority from the rule library according to the conflict mark to obtain the rule weight; The priority value of the corresponding parameter is obtained by multiplying the AHP weight, satisfaction and rule weight in the factor weight vector; The decision is to execute the clause corresponding to the parameter with the larger priority value.

5. The lightning protection design evaluation method based on decision tree forest according to claim 1 is characterized in that: The dynamic branch adjustment process is specifically as follows: Acquiring environmental condition parameters including at least one of geographical parameters, meteorological parameters, and geological parameters; Determine an environmental risk value according to the absolute value of the difference between the parameter value in the environmental condition parameter and the corresponding parameter threshold value, the larger the absolute value of the difference, the larger the corresponding environmental risk value; Select the maximum value of all the environmental risk values ​​as the execution risk value; When the execution risk value is greater than a first threshold: retrieving an alternative branch library matching current environment parameters from the decision tree forest model; And adopt the satisfaction weighted voting mechanism to select the optimal branch and replace the corresponding branch of the original decision tree; When the execution risk value is greater than the second threshold and less than or equal to the first threshold: the AHP weight of the corresponding node is increased in proportion according to the execution risk value.

6. The lightning protection design evaluation method based on decision tree forest according to claim 5 is characterized in that: The AHP weight of the corresponding node is increased proportionally according to the execution risk value, specifically: The increased AHP weight increment is calculated by multiplying the industry risk coefficient by the execution risk value; If the sum of the AHP weight increment and the original AHP weight is less than 1, the sum is used as the updated AHP weight; If the updated AHP weight is equal to 1, the AHP weight is renormalized.

7. A lightning protection design evaluation system based on decision tree forest is characterized by: include: The data processing module is used to aggregate data from multiple sources of lightning protection technical standard clauses to obtain a structured lightning protection clause dataset with a dynamic hierarchical classification architecture; A model building module is used to generate a dedicated decision tree for each type of lightning protection measure based on the structured lightning protection clause data set, and implant an AHP weight engine and a conflict resolution engine into the decision tree nodes to obtain a decision tree forest model with weighted branches; A preliminary identification module is used to input the lightning protection design parameters to be evaluated into the decision tree forest model for dynamic weight integration and conflict resolution processing to obtain preliminary compliance identification results; An optimization identification module, configured to dynamically adjust branches of the decision tree forest model according to environmental condition parameters, and regenerate an environmental adaptation identification result based on the preliminary compliance identification result; A report generation module is used to input the environmental adaptability identification result into the meteorological disaster risk management system integrated gateway for visual report generation processing to obtain a lightning protection design evaluation report; The data aggregation processing of the multi-source lightning protection technical standard clauses includes: A hierarchical clustering algorithm based on Levenshtein distance and semantic similarity weighting is used to dynamically classify atomic clause units into the dynamic hierarchical classification framework according to similarity; The keyword TF-IDF vector and classification path code are extracted from each of the atomic clause units to generate a classification feature vector that is machine-recognizable and dynamically matched.

8. A computer terminal comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the lightning protection design evaluation method based on the decision tree forest as described in any one of claims 1 to 6 is implemented.

9. A computer-readable medium having a computer program stored thereon, characterized in that: The computer program is executed by a processor to implement the lightning protection design evaluation method based on decision tree forest as described in any one of claims 1 to 6.

Images