A highway engineering special construction scheme intelligent approval system

Abstract

This invention belongs to the field of highway engineering technology, specifically an intelligent approval system for highway engineering construction plans. It includes a network construction module, an instantiation processing module, a forward calculation module, a reverse derivation module, and an approval generation module. First, it matches standard verification indicators with the target component types in the plan to be approved, constructing a constraint network. Then, it obtains geological attributes based on component location information and retrieves the instantiated network for the target component from the constraint network. On one hand, it substitutes design parameters into the instantiated network to calculate the estimated values ​​of the standard verification indicators; on the other hand, it uses the qualified values ​​of the standard verification indicators as constraints to deduce the range of design parameter values. Finally, it generates an approval conclusion for the design parameters of the target component based on the results of the dual comparison. This system achieves consistency verification of highway construction plans from overall safety effect to local design logic, helping to improve the accuracy and interpretability of the approval process.

Description

Technical Field

[0001] This invention belongs to the field of highway engineering technology, specifically an intelligent approval system for highway engineering construction plans. Background Technology

[0002] The special construction plan for highway engineering is a technical document that guides on-site construction and ensures the quality and safety of the project. Its contents cover the design parameters of many key parts such as support system and temporary structure. One of the tasks of the plan approval is to check the design parameters item by item according to the standard provisions. However, the existing technical approval logic is still at the level of simple comparison of parameters and thresholds, which has the following defects: (1) It does not distinguish between location and geological conditions. The existing technology uses a uniform threshold to review the design parameters. The same qualification judgment standard is applied to the same type of component in different engineering locations and under different geological conditions, ignoring the impact of geological conditions on the safety performance of components, resulting in the review results being out of touch with the actual project.

[0003] (2) Failure to verify the mandatory correlation between parameters. Existing technology only reviews individual parameters independently, and cannot identify whether the combination of parameters meets the inherent mechanical logic of the specification. This leads to the false impression of compliance where the parameters appear to be qualified individually, but the whole has safety hazards, and thus the approval is granted. Summary of the Invention

[0004] To overcome the shortcomings of the prior art, this invention provides an intelligent approval system for highway engineering construction plans, which can effectively solve the problems mentioned in the prior art.

[0005] The objective of this invention can be achieved through the following technical solution: an intelligent approval system for highway engineering construction plans, comprising: a network construction module, an instance processing module, a forward calculation module, a reverse derivation module, and an approval generation module.

[0006] The network construction module is connected to the instance processing module, which is connected to the forward calculation module and the reverse derivation module respectively. Both the forward calculation module and the reverse derivation module are connected to the approval generation module.

[0007] The network construction module matches the specification verification indicators from the pre-stored technical standard library according to the target component type in the scheme to be approved, and constructs a constraint network with specification verification indicators as output, connecting intermediate state variables and design parameters at all levels through specification mandatory relationships.

[0008] The instance processing module performs spatial overlay analysis on the engineering location information of the target component and the digital geological layer to obtain the geological attribute data of the target component. Based on this, it determines the qualified value of the specification verification index from the pre-stored technical standard library and generates an instanced network for the target component.

[0009] The forward calculation module substitutes the design parameter values ​​into the instantiated network to perform forward calculations and obtain the estimated values ​​of the standard verification indicators.

[0010] The reverse derivation module uses the qualified values ​​of the standard verification indicators as constraints and performs reverse derivation in the instantiated network to solve for the range of values ​​that the design parameters must satisfy.

[0011] The approval generation module generates an approval conclusion for the target component based on the comparison results of the estimated and qualified values ​​of the standard verification indicators and the design parameter values ​​and value ranges of the target component.

[0012] Compared with the prior art, the embodiments of the present invention have at least the following advantages or beneficial effects: (1) The present invention uses the instance processing module to perform spatial overlay analysis on the component engineering location information and the digital geological layer, obtains the geological attribute data of the target component location and generates an engineering condition label set accordingly, determines the qualified value of the specification verification index from the qualified value rule set, so that the review standard can accurately match the geological conditions of the component location, and avoids the disconnect between the actual project and the unified threshold review.

[0013] (2) This invention takes the standard verification index as the output, establishes a constraint network that connects intermediate state variables and design parameters at all levels by the standard mandatory relationship, transforms the discrete standard clauses into computable directed dependencies, and then uses the qualified value as a constraint to solve the value range of each design parameter in reverse, so as to realize the judgment of whether the parameter combination meets the inherent mechanical logic of the standard.

[0014] (3) This invention constructs a dual verification system of forward calculation and reverse derivation. By comparing the calculated value and qualified value of the standard verification index and the design parameters with their value range, the approval conclusion for the design parameters of the target component is generated, realizing the comprehensive verification of compliance of single parameters and parameter combination, and avoiding compliance falsehoods. Attached Figure Description

[0015] The present invention will be further described with reference to the accompanying drawings, but the embodiments in the drawings do not constitute any limitation on the present invention. For those skilled in the art, other drawings can be obtained based on the following drawings without creative effort.

[0016] Figure 1 This is a schematic diagram of the module connection of the present invention;

[0017] Figure 2 This is a schematic diagram illustrating the construction logic of the constraint network of the present invention;

[0018] Figure 3 This is a schematic diagram illustrating the logic for determining the pass value of the verification indicators in this invention. Detailed Implementation

[0019] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0020] Reference Figure 1 As shown, the present invention provides an intelligent approval system for special construction plans of highway engineering, including: a network construction module, an instance processing module, a forward calculation module, a reverse derivation module, and an approval generation module.

[0021] The network construction module is connected to the instance processing module, which is connected to the forward calculation module and the reverse derivation module respectively. Both the forward calculation module and the reverse derivation module are connected to the approval generation module.

[0022] To achieve automated and intelligent approval of specialized construction plans for highway engineering, the primary engineering objective is to construct a constraint network that reflects the logic of the specifications. This constraint network is a structured data model designed to link the final specification verification indicators used for evaluation with the design parameters in the plan through a series of calculation relationships, providing a computational basis for subsequent forward calculations and reverse derivations.

[0023] The network construction module matches the specification verification indicators from the pre-stored technical standard library according to the target component type in the scheme to be approved, and constructs a constraint network with specification verification indicators as output, connecting intermediate state variables and design parameters at all levels through specification mandatory relationships.

[0024] In this embodiment, the implementation and construction process of the constraint network strictly follows the inherent logic of the specification provisions and is completed through a step-by-step decomposition method, referring to... Figure 2 As shown, the specific construction steps are as follows: A1: Query the set of standard clauses involved in the target component type from the pre-stored technical standard library, and read the preset attribute tags of each standard clause. The preset attribute tags include at least clause type tags and level tags. The clause type tags are used to identify whether the standard clause belongs to the verification category, construction category or material category, and the level tags are used to identify the position of the standard clause in the verification calculation chain.

[0025] Standard clauses that simultaneously meet the criteria of having a clause type label of "verification type" and a hierarchy label of "end" are identified as standard clauses with final verification attributes, and their verification formulas are extracted as the calculation formulas for standard verification indicators.

[0026] A2: Decompose the verification formula layer by layer, take each parameter in the formula as a first-level intermediate state variable, and record the calculation relationship between each first-level intermediate state variable.

[0027] A3: Continue to decompose each intermediate state variable downwards. If an intermediate state variable is derived from a lower-level parameter through a calculation formula, then decompose it into a second-level intermediate state variable, until it can no longer be decomposed and directly corresponds to the design parameters of the target component.

[0028] A4: Using the standard verification index as the root node, the intermediate state variables at each level as intermediate nodes, and the design parameters as leaf nodes, establish the directed computational dependencies between the nodes to form a constraint network.

[0029] It should be noted that the pre-stored technical standards library is a structured knowledge base, which includes: a library of standard clauses, storing standard clauses extracted from current highway engineering-related standards in a structured manner, as well as type and level tags pre-set for each clause.

[0030] The verification formula library stores the calculation formulas and their variable dependencies parsed from the standard provisions.

[0031] The qualified value rule library stores a set of rules consisting of combinations of engineering conditions and value suggestions.

[0032] The conditional classification standard library stores the hierarchical mapping relationship that discretizes continuous geological parameters into engineering semantic tags.

[0033] Taking slope anchor support components as an example, their design parameters include at least the anchor diameter, anchorage length, and anchorage spacing. The corresponding standard verification index is the anti-sliding stability safety factor. Intermediate state variables can be referred to Table 1 below, which includes at least the pull-out force of a single anchor, anchorage resistance, soil shear force, total anti-sliding force, and total sliding force.

[0034] Table 1 Reference Table of Intermediate State Variables for Slope Anchor Support Components

[0035]

[0036] As shown in Table 1, the safety performance of slope anchor support components is ultimately evaluated using the standard verification indicators. The anti-sliding stability safety factor is determined by the ratio of total anti-sliding force to total sliding force. The total sliding force is calculated from the slip surface inclination angle and soil weight, reflecting the slope's sliding tendency under gravity. The total anti-sliding force is further decomposed into the shear force provided by the soil and rock mass itself and the anchoring resistance provided by the anchor system. The soil and rock shear force depends on geological parameters such as the slip surface inclination angle, slip surface length, cohesion, and internal friction angle. The anchoring resistance is obtained by summing the pull-out forces of individual anchors, which are determined by the anchor diameter, anchoring length, and bond strength. The number of anchors is determined by the anchor spacing and slope area. This layer-by-layer decomposition relationship presents a complete mechanical transmission path from design parameters and geological parameters to standard verification indicators, providing a clear computational dependency for subsequent forward calculations and reverse derivations.

[0037] Based on the completion of the general constraint network construction, the instance processing module aims to bind the constraint network with the specific engineering environment to generate an instanced network for the target component.

[0038] Therefore, the first step is to perform spatial overlay analysis between the engineering location information of the target component and the digital geological layer to obtain the geological attribute data of the target component. This process enables the constraint network to reflect the actual engineering environment of the target component's location, realizing the correlation between the standard verification indicators and specific geological conditions. Specifically, the engineering location information of the target component is converted into GIS query coordinates. Then, the polygons of each geological unit are traversed in the digital geological layer, and the ray casting method is used to retrieve the geological unit into which the query coordinates fall. The geological attribute data associated with this geological unit in the digital geological layer is then used as the geological attribute data of the target component.

[0039] The execution logic of the ray method is as follows: starting from the coordinates queried in GIS, a virtual ray is emitted along any predetermined direction, and the number of intersections between this virtual ray and the boundary of the currently traversed polygon is counted. If the number of intersections is odd, it is determined that the queried coordinate point is inside the polygon, otherwise it is outside.

[0040] Next, based on the acquired geological attribute data, the qualified values ​​of the specification verification indicators are matched and determined from the pre-stored technical standard library, with reference to... Figure 3 As shown, the specific process is as follows: B1: Compare each parameter in the geological attribute data of the target component with the preset condition classification standard to generate the engineering condition label set of the target component's location.

[0041] The conditional classification standard discretizes continuous geological parameters into several engineering semantic tags, which include at least rock mass integrity classification, bond strength classification, and groundwater environment classification.

[0042] B2: Query the set of qualified value rules corresponding to the specification verification indicators from the pre-stored technical standard library. Each qualified value rule consists of a combination of engineering conditions and corresponding value suggestions.

[0043] B3: Match the engineering condition label set with the rules in the qualified value rule set one by one, filter out the target rules that match the current engineering conditions, and determine the qualified value of the specification verification index according to the value suggestion of the target rule. Specifically: B31: Take the rule in the qualified value rule set that completely matches the current engineering conditions as the first candidate rule, and directly determine the qualified value of the specification verification index according to the value suggestion in the first candidate rule.

[0044] B32: If there is no first candidate rule, then, based on the premise that at least one condition label is consistent with the current project conditions, identify the rule that partially matches the conditions and use it as the second candidate rule.

[0045] B33: Pair the rules that meet the complementary coverage requirement among multiple second candidate rules. The complementary coverage requirement means that the condition label sets of the two rules can jointly cover all condition dimensions of the current engineering conditions, and the unmatched condition dimensions of the two rules in the case of complementary coverage are exactly arbitrary in the other rule.

[0046] The suggested values ​​in the pairing rules are used to form closed intervals. If there are multiple pairs, the intersection of all closed intervals is taken as the suggested numerical interval. If the intersection is empty, the minimum lower limit and maximum upper limit of the union of all closed intervals are taken as the suggested numerical interval. The upper limit of the suggested numerical interval is taken as the qualified value of the standard verification index.

[0047] B4: Assign values ​​to the corresponding environmental parameter nodes in the constraint network from the geological attribute data, and set the qualified values ​​as the top-level output constraints of the instantiated network.

[0048] It should be noted that the above-mentioned complete match means that all condition tags in the engineering condition tag set are consistent with the condition tags of the corresponding dimension in a certain qualified value rule; the above-mentioned partial match means that at least one condition tag in the engineering condition tag set is consistent with the condition tag of the corresponding dimension in a certain qualified value rule, and the remaining condition tags are arbitrary in that rule.

[0049] For example, the set of rules for the qualified values ​​of the corresponding standard verification index (anti-slip stability safety factor) for slope anchor support components can be found in Table 2 below.

[0050] Table 2 Example Table of Qualified Value Rules

[0051]

[0052] Table 2 shows that the set of qualified value rules achieves a detailed correlation between the standard benchmark requirements and engineering geological conditions: First, the integrity of the rock mass is used as the primary grading criterion. When the rock mass is intact, the standard benchmark value is directly adopted, with an anti-sliding stability safety factor of 1.35. When the rock mass is relatively broken or fractured, the anti-sliding stability safety factor requirement is correspondingly increased. Second, under the condition of relatively broken rock mass, further subdivision is made. The lower the bond strength, the higher the requirement for the anti-sliding stability safety factor, reflecting the need for compensation for safety margin due to the deterioration of the anchoring effect. Third, the anti-sliding stability safety factor required in the water-immersed environment is higher than that in the dry environment, reflecting the weakening effect of groundwater on the rock mass strength and anchoring performance. Through the above rules, the system can match and determine the qualified value of the anti-sliding stability safety factor that matches the geological conditions based on the rock mass conditions, bond strength, and groundwater conditions at the location of the target component. This directly reflects the differences in engineering geology in the approval standards and avoids the disconnect between the actual project and the project caused by uniform threshold review.

[0053] After generating the instantiated network for the target component, the system performs the following operations: In order to evaluate the actual engineering performance of the design parameters in the scheme to be approved, the forward calculation module substitutes the design parameter values ​​into the instantiated network to perform forward calculation and obtain the estimated values ​​of the standard verification indicators. Specifically, the following steps are performed: C1: Substitute the design parameter values ​​into the design parameter node at the lowest level of the instantiated network as the initial input value.

[0054] C2: Following the computation path defined by the instantiated network, the computation formulas corresponding to each intermediate state node are called sequentially. The input parameters are substituted into the calculation to obtain the estimated value of the intermediate state node, and then used as the input of the subsequent computation nodes.

[0055] C3: Repeat step C2, propagating upwards level by level until the calculation reaches the top-level output node of the instantiated network, to obtain the estimated value of the standard verification index. The estimated value is used to characterize the theoretical performance of the current scheme to be approved under a specific geological environment.

[0056] To provide optimization direction and compliance boundaries for design parameters, the reverse derivation module uses the qualified value of the standard verification index as a constraint condition and performs reverse derivation in the instantiated network to solve the value range that the design parameters need to satisfy. The following steps are performed: D1: The qualified value of the standard verification index is used as a known condition and substituted into the top output node of the instantiated network.

[0057] D2: Following the computation path defined by the instantiated network, solve the problem in reverse order from the top-level node downwards, starting from the top-level node. For each intermediate state node, deduce the performance requirement value that the node must meet in reverse order, based on the performance requirement value passed down from its parent node, combined with the node's own calculation formula and known environmental parameter values.

[0058] The reverse derivation specifically involves: obtaining the calculation formula for the current intermediate node in the instantiated network, where the performance requirement of the current node is the dependent variable and the performance requirement of its subordinate nodes are the independent variables. The performance requirement value passed down from the parent node is substituted into the left side of the calculation formula, and the known parameter values ​​are substituted into the independent variables on the right side of the formula, excluding the current subordinate node to be solved. An algebraic transformation is then performed on the calculation formula to obtain the performance requirement value that the current subordinate node to be solved must meet.

[0059] If the calculation formula is a nonlinear relationship, iterative calculations are performed within a reasonable range pre-calibrated by the lower-level nodes using existing numerical solution methods such as the bisection method or Newton's iteration method until the solution value meets the convergence condition.

[0060] D3: If an intermediate state node corresponds to multiple lower-level parameters, the priority order of each lower-level parameter is determined according to the preset allocation rules, and the value boundaries that each lower-level parameter must satisfy are solved respectively. Specifically, the preset allocation rules are as follows: the lower-level parameters are prioritized according to their adjustability during the construction phase. Parameters that cannot be adjusted after construction are set as the first priority, parameters that need to be re-approved after adjustment after being determined before construction are set as the second priority, and parameters that can be adjusted in real time during construction are set as the third priority.

[0061] The phrase "cannot be adjusted after construction" refers to the fact that once the parameter values ​​are implemented according to the plan, their physical form cannot be changed in subsequent construction. The phrase "adjustments after determination before construction require re-approval" refers to the fact that if the parameter values ​​are determined during the construction preparation stage, any adjustments must be submitted for re-approval. The phrase "can be adjusted in real time during construction" refers to the fact that parameter values ​​can be adjusted on-site according to actual conditions without requiring re-approval.

[0062] For the subordinate parameter with the highest priority (first priority), it is treated as the variable to be solved. The remaining subordinate parameters are temporarily fixed as the actual values ​​in the current scheme to be approved. They are substituted into the calculation formula of the intermediate state node, and the value boundary that this highest priority subordinate parameter must satisfy is solved in reverse.

[0063] The boundary values ​​obtained from the solution are used as constraints for this lower-level parameter and fixed as parameter values.

[0064] The same operation is performed on the next lower priority parameters in sequence until the boundary values ​​of all lower priority parameters have been solved.

[0065] D4: Repeat steps D2 to D3 until the design parameter node at the lowest level is derived, and the range of values ​​that the design parameters must meet to ensure that the standard verification indicators are met is obtained.

[0066] It should be noted that during the reverse derivation process, if, when solving for each lower-level parameter according to the established priority order, the current priority parameter, after fixing the value boundary of the higher-priority parameter, cannot obtain a real solution by substituting it into the calculation formula of the intermediate state node, or if the obtained value boundary exceeds the pre-defined reasonable range, then a no-solution backtracking mechanism is triggered: backtracking to the previous priority parameter, lowering the lower limit of the original value or raising the upper limit by one step to expand its acceptable range, and then resolving the value boundary of the current priority parameter on this basis. The step size is pre-set according to the type of design parameter and its adjustment granularity in engineering practice; different design parameters correspond to different step sizes. For example, the step size corresponding to the anchor diameter of a slope anchor support component is 2 millimeters.

[0067] Repeat the backtracking adjustment process until all lower-level parameter values ​​are successfully solved, or the preset maximum number of backtracking iterations is reached.

[0068] If a consistent boundary value cannot be obtained after reaching the maximum number of backtracking iterations, the reverse derivation will terminate, and the approval generation module will output an approval conclusion that the combination of design parameters cannot meet the safety requirements, while marking the constraints that lead to no solution.

[0069] The approval generation module generates an approval conclusion for the target component based on the comparison results of the estimated and qualified values ​​of the standard verification indicators and the design parameter values ​​and value ranges of the target component.

[0070] Specifically, when the estimated value of the standard verification index is greater than or equal to the qualified value, and the values ​​of each design parameter of the target component fall within their respective value ranges, the output approval conclusion for the target component is that the design parameters have been approved.

[0071] Otherwise, the output will include an approval conclusion with abnormal information. The abnormal information will include at least the name of the failed design parameter, the deviation data between the actual value and the qualified or boundary value, and the specific specification clause that was violated.

[0072] The above description is merely an example and illustration of the structure of the present invention. Those skilled in the art can make various modifications or additions to the specific embodiments described, or use similar methods to replace them, as long as they do not deviate from the structure of the invention or exceed the scope defined by the present invention, and all such modifications and additions should fall within the protection scope of the present invention.

Claims

1. An intelligent approval system for highway engineering construction plans, characterized in that, include: The network construction module matches the specification verification indicators from the pre-stored technical standard library according to the target component type in the scheme to be approved, and constructs a constraint network with specification verification indicators as output, connecting intermediate state variables and design parameters at all levels through specification mandatory relationships; The instance processing module performs spatial overlay analysis on the engineering location information of the target component and the digital geological layer to obtain the geological attribute data of the target component. Based on this, it determines the qualified value of the specification verification index from the pre-stored technical standard library and generates an instanced network for the target component. The forward calculation module substitutes the design parameter values ​​into the instantiated network to perform forward calculations and obtain the estimated values ​​of the standard verification indicators. The step of substituting the design parameter values ​​into the instantiated network for forward calculation includes: C1: Substitute the design parameter values ​​into the lowest-level design parameter node of the instantiated network as the initial input values; C2: Following the computation path defined by the instantiated network, the computation formulas corresponding to each intermediate state node are called sequentially, the input parameters are substituted into the calculation to obtain the estimated value of the intermediate state node, and it is used as the input of the subsequent computation nodes. C3: Repeat step C2, propagating upwards level by level until the calculation reaches the top-level output node of the instantiated network, and obtain the estimated value of the canonical verification index; The reverse derivation module takes the qualified values ​​of the standard verification indicators as constraints and performs reverse derivation in the instantiated network to solve the range of values ​​that the design parameters need to satisfy. The range of values ​​that the design parameters must satisfy includes: D1: Take the pass value of the standard verification index as a known condition and substitute it into the top output node of the instantiated network; D2: Following the computation path defined by the instantiated network, solve the problem in reverse order from the top-level node downwards, starting from the top-level node. For each intermediate state node, deduce the performance requirement value that the node must meet in reverse order, based on the performance requirement value passed down from its parent node, combined with the node's own calculation formula and known environmental parameter values. D3: If an intermediate state node corresponds to multiple lower-level parameters, the priority order of the allocation of each lower-level parameter is determined according to the preset allocation rules, and the boundary values ​​that each lower-level parameter must satisfy are solved respectively. D4: Repeat steps D2 to D3 until the design parameter node at the lowest level is derived, and the range of values ​​that the design parameters must meet to ensure that the standard verification indicators are met. The approval generation module generates an approval conclusion for the target component based on the comparison results of the estimated and qualified values ​​of the standard verification indicators and the design parameter values ​​and value ranges of the target component.

2. The intelligent approval system for highway engineering special construction plans according to claim 1, characterized in that, The process of constructing the constraint network is as follows: A1: Query the set of standard clauses related to the target component type from the pre-stored technical standard library, identify the standard clauses with final verification attributes, and extract the verification formulas in the standard clauses as the calculation formulas for the standard verification index; A2: Decompose the verification formula layer by layer, take each parameter in the formula as a first-level intermediate state variable, and record the calculation relationship between each first-level intermediate state variable; A3: Continue to decompose each intermediate state variable downwards. If an intermediate state variable is derived from a lower-level parameter through a calculation formula, then decompose it into a second-level intermediate state variable, until it can no longer be decomposed and directly corresponds to the design parameters of the target component. A4: Using the standard verification index as the root node, the intermediate state variables at each level as intermediate nodes, and the design parameters as leaf nodes, establish the directed computational dependencies between the nodes to form a constraint network.

3. The intelligent approval system for highway engineering special construction plans according to claim 2, characterized in that, The identification of the normative clauses with final verification attributes includes: Read the preset attribute tags of each standard clause. The preset attribute tags include at least a clause type tag and a level tag. The clause type tag is used to identify whether the standard clause belongs to the verification category, the construction category, or the material category. The level tag is used to identify the position of the standard clause in the verification calculation chain. A standard provision that simultaneously satisfies the condition that its type label is "verification type" and its level label is "end" is identified as a standard provision with final verification attribute.

4. The intelligent approval system for highway engineering special construction plans according to claim 1, characterized in that, The step of spatially overlaying the engineering location information of the target component with a digital geological layer includes: The engineering location information of the target component is converted into GIS query coordinates. The polygons of each geological unit are traversed in the digital geological layer. The ray method is used to retrieve the geological unit into which the query coordinates fall. The geological attribute data associated with this geological unit in the digital geological layer is used as the geological attribute data of the target component.

5. The intelligent approval system for highway engineering special construction plans according to claim 1, characterized in that, The determination of the pass value of the standard verification indicators includes: B1: Compare each parameter in the geological attribute data of the target component with the preset condition classification standard to generate a set of engineering condition labels for the location of the target component; The conditional classification standard discretizes continuous geological parameters into several engineering semantic tags, which include at least rock mass integrity classification, bond strength classification, and groundwater environment classification. B2: Query the set of qualified value rules corresponding to the specification verification indicators from the pre-stored technical standard library. Each qualified value rule consists of a combination of engineering conditions and corresponding value suggestions. B3: Match the engineering condition label set with the rules in the qualified value rule set one by one, filter out the target rules that match the current engineering conditions, and determine the qualified value of the specification verification index based on the value suggestions of the target rules; B4: Assign values ​​to the corresponding environmental parameter nodes in the constraint network from the geological attribute data, and set the qualified values ​​as the top-level output constraints of the instantiated network.

6. The intelligent approval system for highway engineering special construction plans according to claim 5, characterized in that, The process of determining the pass value of the specification verification indicator based on the value suggestion of the target rule includes: B31: The rule that perfectly matches the current project conditions in the set of qualified value rules is taken as the first candidate rule, and the qualified value of the specification verification index is directly determined based on the value suggestions in the first candidate rule; B32: If there is no first candidate rule, then, based on the premise that at least one condition label is consistent with the current project conditions, identify the rule that partially matches the conditions and use it as the second candidate rule; B33: Pair the rules that meet the complementary coverage requirement from multiple second candidate rules, and form a closed interval by the value suggestions in the paired rules. If there are multiple pairs, take the intersection of all closed intervals as the numerical suggestion interval. If the intersection is empty, take the minimum lower limit and maximum upper limit of the union of all closed intervals as the numerical suggestion interval. Take the upper limit value of the numerical suggestion interval as the qualified value of the specification verification index.

7. The intelligent approval system for highway engineering special construction plans according to claim 1, characterized in that, The boundary values ​​that must be satisfied when solving each lower-level parameter include: For the subordinate parameter with the highest priority, it is used as the variable to be solved. The remaining subordinate parameters are temporarily fixed as the actual values ​​in the current scheme to be approved. They are substituted into the calculation formula of the intermediate state node to solve the value boundary that the subordinate parameter with the highest priority must satisfy. The boundary values ​​obtained from the solution are used as constraints for this lower-level parameter and fixed as parameter values. The same operation is performed on the next lower priority parameters in sequence until the boundary values ​​of all lower priority parameters have been solved.

8. The intelligent approval system for highway engineering special construction plans according to claim 1, characterized in that, The approval conclusion for generating the target component includes: When the estimated value of the standard verification index is greater than or equal to the qualified value, and the values ​​of each design parameter of the target component fall within their respective value ranges, the output of the approval conclusion for the target component is that the design parameters have been approved. Otherwise, the output will include an approval conclusion containing abnormal information; the abnormal information will include at least the name of the design parameter that failed, the deviation data between the actual value and the qualified value or boundary value, and the specific specification clause that was violated.

Images