Subway access control system multi-specialty collaborative construction monitoring method and system

Abstract

The invention relates to the technical field of construction monitoring, and discloses a multi-specialty cooperative construction monitoring method and system for a subway access control system. The method comprises the following steps: acquiring voltage, protocol and delay parameters between access control equipment, and calculating coupling strength to construct a matrix; dividing equipment installation units based on the coupling strength matrix; constructing an access control circuit knowledge enhancement graph neural network, and outputting an equipment installation priority score matrix; monitoring a multi-professional operation state, identifying construction conflicts and generating an early warning signal; and responding to the early warning signal to dynamically adjust an equipment installation time sequence, and obtaining a construction scheduling scheme. The technical problem that equipment electrical topology analysis, professional knowledge integrated application and real-time conflict detection are lacked in multi-professional construction of the subway access control system is solved. According to the invention, the intelligent monitoring level and the construction efficiency of multi-specialty collaborative construction are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of construction monitoring, in particular to a metro access control system multi-specialty collaborative construction monitoring method and system. BACKGROUND

[0002] The existing metro access control system construction monitoring technology mainly relies on traditional project management methods and independent professional operation modes, and supervises and manages the construction process through manual preparation of construction plans, on-site inspection and regular reporting. In the traditional method, the construction activities of different specialties such as civil engineering, electromechanical engineering, communication and debugging are relatively independent, and each specialty operates according to the predetermined time node and spatial distribution. The construction monitoring mainly focuses on the progress control and quality inspection of a single specialty, and lacks systematic monitoring and intelligent scheduling of multi-specialty collaborative operation.

[0003] However, the existing technology has significant deficiencies, mainly manifested as a lack of in-depth analysis and utilization of the electrical topological relationship between access control equipment, inability to scientifically group and plan based on the coupling strength of the equipment, and resulting in unreasonable construction arrangement. At the same time, the existing method lacks integrated application of professional knowledge in the access control field, and fails to convert knowledge in the fields of equipment installation specifications, electrical safety requirements, etc. into computable intelligent decision basis, resulting in subjectivity and randomness in determining construction priority. In addition, the traditional monitoring method lacks precise digital modeling and real-time detection capability for space occupation and time conflict of the construction site, making it difficult to identify and prevent potential conflicts in multi-specialty cross-operation in advance. SUMMARY

[0004] The present application provides a metro access control system multi-specialty collaborative construction monitoring method and system, which solves the technical problems of lack of equipment electrical topology analysis, integrated application of professional knowledge and real-time conflict detection in multi-specialty construction of metro access control systems. The present application improves the intelligent monitoring level and construction efficiency of multi-specialty collaborative construction.

[0005] In a first aspect, the present application provides a metro access control system multi-specialty collaborative construction monitoring method, which comprises: Step S1: Collecting the voltage level, communication protocol type and signal transmission delay parameters among the access controller, card reader and electromagnetic lock, calculating the coupling strength between the equipment, and constructing the equipment coupling strength matrix; Step S2: Based on the equipment coupling strength matrix, the access control equipment is divided into a plurality of equipment installation units; Step S3: Constructing a metro access circuit knowledge enhanced graph neural network, inputting the physical attribute features and electrical connection relationship of the equipment installation unit, and outputting an equipment installation priority score matrix; Step S4: Monitor the multi-specialty operation state of the access control system installation construction, identify the inter-professional construction conflict under the guidance of the equipment installation priority score matrix, and generate a multi-specialty construction conflict warning signal; Step S5: In response to the multi-specialty construction conflict warning signal, dynamically adjust the access control equipment installation timing, and obtain a construction scheduling scheme.

[0006] In a second aspect, the application provides a subway access control system multi-specialty collaborative construction monitoring system, which comprises: A construction module is configured to collect the voltage level, communication protocol type, and signal transmission delay parameters among the access controller, card reader, and electromagnetic lock, calculate the coupling strength between devices, and construct a device coupling strength matrix. A division module is configured to divide the access control equipment into multiple equipment installation units based on the device coupling strength matrix. An input module is configured to construct an access control circuit knowledge enhanced graph neural network, input the physical attribute features and electrical connection relationships of the equipment installation units, and output a device installation priority score matrix. An identification module is configured to monitor the multi-specialty operation state of the access control system installation construction, identify the inter-professional construction conflict under the guidance of the device installation priority score matrix, and generate a multi-specialty construction conflict warning signal. A response module is configured to respond to the multi-specialty construction conflict warning signal, dynamically adjust the access control equipment installation timing, and obtain a construction scheduling scheme.

[0007] In a third aspect, a subway access control system multi-specialty collaborative construction monitoring device is provided, which comprises a memory and at least one processor, the memory stores instructions, and the at least one processor invokes the instructions in the memory to enable the subway access control system multi-specialty collaborative construction monitoring device to perform the above-mentioned subway access control system multi-specialty collaborative construction monitoring method.

[0008] In a fourth aspect, a computer readable storage medium is provided, which stores instructions, and when it runs on a computer, it enables the computer to perform the above-mentioned subway access control system multi-specialty collaborative construction monitoring method.

[0009] The technical scheme provided in the application overcomes the defects in the prior art of ignoring the electrical correlation characteristics of access control devices, realizes scientific grouping based on the electrical topology relationship of the devices, and avoids the subjectivity and randomness of device grouping in the traditional method. The technical feature of dividing the access control devices into multiple device installation units based on the device coupling strength matrix considers the electrical dependency relationship and signal transmission characteristics between the devices, so that the devices in the same installation unit have stronger electrical correlation, reducing the complexity and coordination difficulty of cross-unit construction. The technical feature of constructing an access control circuit knowledge enhanced graph neural network and inputting the physical property characteristics and electrical connection relationship of the device installation unit to output a device installation priority score matrix combines the professional knowledge in the access control field with the physical characteristics of the devices, overcomes the limitations of the traditional method of relying on manual experience to determine the installation order, and improves the scientificity and accuracy of the construction priority decision. The technical feature of monitoring the multi-specialty operation state of the access control system installation and construction, and generating a multi-specialty construction conflict early warning signal by identifying the inter-professional construction conflict under the guidance of the device installation priority score matrix solves the problem that the prior art cannot detect and warn the multi-specialty cross-operation conflict in real time, and improves the safety and controllability of the construction process.

[0010] The technical feature of responding to the multi-specialty construction conflict early warning signal and dynamically adjusting the access control device installation time sequence to obtain a construction scheduling scheme realizes the change of the construction management mode from passive response to active prevention, and overcomes the deficiency of the traditional static scheduling method that cannot adapt to the dynamic changes on site. In this specific application field of the subway access control system, the electrical topology mapping algorithm fully considers the voltage compatibility, protocol consistency and signal transmission characteristics of the access control devices. Compared with the general device grouping method, this algorithm is specially optimized for the electrical characteristics of the access control system, so that the device grouping is more in line with the engineering practice of the access control system. The access control circuit knowledge enhanced graph neural network embeds the field-specific knowledge such as installation specifications and electrical safety distance requirements of the access control devices into the learning process of the neural network. Compared with the general graph neural network, this network is specially knowledge-enhanced for the technical characteristics of the access control system, improving the professionalism and practicality of the priority score. The particle swarm optimization algorithm fully considers the dependency constraints, spatial conflict penalties and other constraints specific to the access control system in the construction scheduling of the access control system. Compared with the general scheduling optimization algorithm, this algorithm is specially customized for the construction characteristics of the subway access control system, so that the optimization result is more in line with the construction requirements and safety standards of the access control system. BRIEF DESCRIPTION OF DRAWINGS

[0011] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the embodiment description will be briefly introduced as follows. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor based on these drawings.

[0012] Figure 1 An embodiment of the subway access control system multi-specialty collaborative construction monitoring method in the present application is shown in the figure. Figure 2 An embodiment of the subway access control system multi-specialty collaborative construction monitoring system in the present application is shown in the figure. Figure 3 An embodiment of the subway access control system multi-specialty collaborative construction monitoring method in the present application is shown in the figure. DETAILED DESCRIPTION

[0013] The present application provides a subway access control system multi-specialty collaborative construction monitoring method and system. The terms "first", "second", "third", "fourth" and the like (if any) in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the term "comprising" or "having" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device comprising a series of steps or units does not necessarily limit to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0014] For the sake of understanding, the specific process of the embodiments of the present application will be described below. Please refer to Figure 1 An embodiment of the subway access control system multi-specialty collaborative construction monitoring method in the present application includes: Step S1: Collecting the voltage level, communication protocol type and signal transmission delay parameters among the access controller, card reader and electromagnetic lock, calculating the coupling strength between devices, and constructing the device coupling strength matrix; Step S2: Based on the device coupling strength matrix, the access control devices are divided into a plurality of device installation units; Step S3: Constructing an access circuit knowledge enhanced graph neural network, inputting the physical attribute features and electrical connection relationship of the device installation unit, and outputting a device installation priority score matrix; Step S4: monitoring the multi-professional operation state of the access control system installation construction, identifying the professional construction conflict under the guidance of the equipment installation priority score matrix, and generating a multi-professional construction conflict warning signal; Step S5: in response to the multi-professional construction conflict warning signal, dynamically adjusting the access control equipment installation timing, and obtaining a construction scheduling scheme.

[0015] It can be understood that the execution subject of the present application can be a subway access control system multi-professional collaborative construction monitoring system, and can also be a terminal or a server, which is not limited here. The server is taken as an example for illustration in the embodiments of the present application.

[0016] Specifically, the equipment coupling strength matrix is constructed by collecting the voltage level, communication protocol type and signal transmission delay parameters between the access controller, card reader and electromagnetic lock. The voltage level reflects the electrical compatibility between devices, the communication protocol type embodies the compatibility of data transmission, and the signal transmission delay parameter represents the time characteristics of device response. The equipment coupling strength calculation adopts a weighted summation method, and the voltage matching degree, protocol compatibility and transmission delay reciprocal are respectively assigned weight coefficients for calculation. The voltage matching degree is determined by comparing the deviation degree of the rated voltage and the standard voltage of the equipment, the protocol compatibility is matched and evaluated based on the communication protocol standard supported by the equipment, and the transmission delay reciprocal is calculated by measuring the transmission time of the signal between the equipment. The calculated coupling strength value is filled in the corresponding position of the matrix according to the equipment number order, forming the coupling strength matrix reflecting the electrical correlation degree between the equipment, and then normalized to eliminate the dimension influence.

[0017] Based on the standardized equipment coupling strength matrix, the equipment is grouped. First, the degree matrix of the access control equipment is constructed, and each diagonal element of the degree matrix represents the connection number of the corresponding equipment with other equipment. The Laplacian matrix is calculated by the difference value of the degree matrix and the coupling strength matrix, which can reflect the connection structure characteristics between the equipment. The eigenvalue decomposition processing is performed on the Laplacian matrix, which decomposes the matrix into the product form of eigenvalue and eigenvector. The eigenvalues below the electrical coupling strength threshold and their corresponding eigenvectors are screened, and these eigenvectors contain the key information of equipment grouping. The screened eigenvectors and the installation space coordinates of the access control equipment are subjected to weighted summation operation, and the space coordinates include the three-dimensional position information of the equipment in the subway platform. The weighted summation operation combines the electrical characteristics and the spatial characteristics to form a comprehensive spatial constraint feature representation. The improved k-means clustering algorithm is executed based on the spatial constraint feature representation, and the number of devices in the same installation unit is limited to not more than the preset access control component capacity threshold in the clustering process, so as to ensure the balanced work load of each installation unit.

[0018] The access control circuit knowledge enhanced graph neural network is constructed to generate a device installation priority score matrix. The position coordinates, device type code, power level, installation height, and reserved space size parameters of each access control device in the device installation unit are extracted, and these parameters are combined to form a device physical attribute feature vector. The device type code is converted into a numerical vector by using one-hot encoding for different types of access control devices, the power level reflects the electrical power demand of the device, the installation height indicates the installation position of the device in the vertical direction, and the reserved space size describes the space range required for device installation. At the same time, the standard installation specification, electrical safety distance requirement, and debugging acceptance standard of the access control device are converted into a vector representation to construct the access control circuit knowledge graph embedding vector. The knowledge graph embedding vector contains the professional knowledge and installation specification of the access control system, and the professional knowledge can participate in the calculation process of the neural network through vector representation. The electrical connection weight is calculated according to the voltage difference, current capacity, and signal type parameters between the access control devices, the voltage difference reflects the voltage compatibility between the devices, the current capacity represents the current carrying capacity of the device, and the signal type describes the signal characteristics transmitted between the devices. The electrical connection weight is filled into the device adjacency matrix to construct the access control system device adjacency matrix. The access control circuit knowledge graph embedding vector and the device physical attribute feature vector are subjected to matrix splicing operation, and the splicing operation connects the two vectors in the feature dimension to form a comprehensive feature vector containing physical attributes and professional knowledge. The embedding layer parameters of the graph neural network are initialized based on the comprehensive feature vector and the device adjacency matrix, and the graph neural network learns the correlation features between the devices through multiple layers of graph convolution operation. The access control device installation dependency constraint weight and the space conflict penalty coefficient are set for the graph attention layer, the attention mechanism can automatically learn the importance weight between the devices, the dependency constraint weight ensures that the devices with dependency relationship are installed in the correct order, and the space conflict penalty coefficient avoids the simultaneous installation of multiple devices in the same space.

[0019] Monitor the multi-disciplinary work status of access control system installation and construction and identify construction conflicts. By collecting 3D spatial coordinate data from the subway platform construction area, the entire construction space is divided into regular grid cells, each with fixed dimensions of length, width, and height. A spatial occupancy matrix is ​​constructed to record the occupancy status of each grid cell at different times. Occupancy status is represented by a binary value: 1 when occupied and 0 when unoccupied. The installation time window and space requirement set for each access control device are determined based on the device installation priority scoring matrix. The time window defines the start and end time of device installation, and the space requirement set describes the range of grid cells required during device installation. A device installation space requirement database is established, storing the space requirement information and schedule for each device. Spatiotemporal conflict detection is performed based on the spatial occupancy matrix and the device installation space requirement database. Conflict detection identifies potential conflicts by comparing the overlap between the time windows and space requirements of different devices. A construction conflict is identified when two or more devices have overlapping time windows and overlapping space requirements. Identified conflicts are graded and handled according to the degree of impact. Minor conflicts refer to conflicts that affect construction efficiency but not safety. Moderate conflicts refer to conflicts that may lead to rework. Severe conflicts refer to conflicts that pose safety hazards.

[0020] Respond to multi-disciplinary construction conflict warning signals and dynamically adjust the access control equipment installation sequence. After receiving the conflict warning signal, the conflict type and impact scope are analyzed. Conflict types include spatial, temporal, and resource conflicts. The impact scope describes the number of devices involved and the affected construction area. Based on the conflict information, a set of conflict constraints is constructed. These constraints include time adjustment restrictions for conflicting devices, spatial reallocation requirements, and personnel rescheduling requirements. A multi-objective optimization function is developed based on the equipment installation priority scoring matrix. The optimization objectives include minimizing total construction time, maximizing installation quality scores, and minimizing inter-disciplinary waiting time. Weight coefficients are assigned to each optimization objective, reflecting their importance. The multi-objective optimization function is then fed into a particle swarm optimization algorithm for iterative solution. The particle swarm algorithm simulates the foraging behavior of a flock of birds to search for the optimal solution. Each particle represents a possible scheduling solution, and the particle moves through the solution space to find the optimal position. The algorithm continuously updates the particle position and velocity during the iteration process, guiding the particles to converge toward the optimal solution through individual and global optimal positions. The optimal adjustment plan for the access control equipment installation sequence is calculated, including the new installation time and spatial allocation for each device. Update the installation time window and professional operation sequence of the access control equipment according to the adjustment plan to form a construction scheduling plan.

[0021] In a specific embodiment, step S1 includes: Establish a set of access control device nodes and a set of electrical connection edges, and construct a directed graph of the electrical topology of the access control system; The device coupling strength values are filled in the matrix corresponding positions according to the device number sequence, and the device coupling strength matrix is constructed; The device coupling strength matrix is normalized to obtain the device coupling strength matrix. The device coupling strength matrix is normalized to obtain the device coupling strength matrix.

[0022] Specifically, the process of establishing the access control device node set and the electrical connection edge set to construct the electrical topology directed graph of the access control system needs to identify all access control devices in the subway station and assign them unique identifiers. The access control device node set includes the access control server of the control center, the gate controller of each entrance, the card reader device, the electromagnetic lock device, the door magnetic sensor, and the emergency door opening button, etc. Each device node has attributes such as device type, device number, installation location, and electrical parameters. The electrical connection edge set describes the physical connection relationship between devices, including power supply lines, signal transmission lines, and communication data lines. The construction of the directed graph determines the directionality of the edges by analyzing the signal flow between devices. The controller sends a query instruction to the card reader, forming a directed edge from the controller to the card reader. The card reader returns the card information to the controller, forming a directed edge from the card reader to the controller. The electrical topology directed graph uses an adjacency list data structure for storage. Each node maintains a list of connected devices, which includes the identifier of the target device and the connection type information. The construction process of the topology graph needs to traverse the electrical interface definition of all devices, determine the connection relationship between devices according to the input and output characteristics of the interface, and verify the validity of the connection considering the electrical compatibility requirements of the devices.

[0023] The process of calculating the coupling strength value of the device based on the voltage matching degree, protocol compatibility and transmission delay inverse of the electrical topology directed graph involves the quantitative calculation of three key parameters. The voltage matching degree is calculated by comparing the operating voltage range of two devices. When there is an overlapping interval between the output voltage range of device A and the input voltage range of device B, the matching degree is equal to the ratio of the overlapping interval length to the input voltage range length of device B. The protocol compatibility is evaluated based on the communication protocol standards supported by the device. The compatibility of the device supporting RS485 protocol is 1, the compatibility of the device supporting different protocols but having a conversion interface is 0.8, and the compatibility of the completely incompatible device is 0. The transmission delay inverse is calculated by measuring the propagation time of the signal between devices. The delay time includes the propagation time of the electrical signal in the wire and the processing time inside the device. The weighted calculation adopts linear weighted summation method. The voltage matching degree is multiplied by the voltage weight coefficient, the protocol compatibility is multiplied by the protocol weight coefficient, and the transmission delay inverse is multiplied by the delay weight coefficient. Then the three products are added to obtain the coupling strength value of the device. The determination of the weight coefficient is based on the evaluation of the importance of different parameters in the access control system. The voltage matching degree weight is usually set to 0.4, the protocol compatibility weight is set to 0.4, and the transmission delay weight is set to 0.2.

[0024] The process of constructing the device coupling strength matrix by filling the coupling strength value of the device into the corresponding position of the matrix needs to establish the mapping relationship between the device number and the matrix index. The device number adopts hierarchical coding method. The first layer represents the device type, the second layer represents the sequence number of the device in the same type, and the third layer represents the specific function module of the device. The row index and column index of the matrix correspond to the number of the source device and the target device respectively. The value of the matrix element represents the coupling strength between the corresponding device pair. The matrix filling process is in lexicographical order according to the device number. First, the coupling relationship between the device with the smallest number and all other devices is processed. Then the remaining coupling relationship of the device with the second smallest number is processed. And so on until all device pairs are calculated and filled into the matrix. For the device pairs that do not have direct electrical connection, the coupling strength value is set to 0. The diagonal elements of the matrix represent the coupling relationship of the device with itself, which is usually set to 1 indicating complete coupling. The asymmetry of the matrix reflects the directional characteristics of the connection between devices in the access control system. The coupling strength from the controller to the card reader is different from that from the card reader to the controller.

[0025] The process of normalizing the device coupling strength matrix to obtain the standardized device coupling strength matrix adopts the maximum-minimum normalization method to eliminate the influence of different parameter dimensions. The normalization process first calculates the maximum and minimum values of all non-zero elements in the matrix, and then divides each matrix element by the difference between the maximum and minimum values after subtracting the minimum value. The normalization formula is that the new value is equal to the result of the original value minus the minimum value divided by the result of the maximum value minus the minimum value, and the normalized value range is between 0 and 1. The zero elements in the matrix remain 0 in the normalization process, indicating that there is no coupling relationship between the corresponding devices. The normalization process makes the coupling strength of different types of parameters have the same numerical scale, which is convenient for subsequent clustering analysis and optimization calculation. The standardized matrix maintains the structural characteristics and relative size relationship of the original matrix, while eliminating the influence of absolute numerical difference on the calculation result.

[0026] In a specific embodiment, step S2 comprises: constructing an access control device degree matrix based on the device coupling strength matrix, and calculating an access control system Laplacian matrix; performing eigenvalue decomposition processing on the access control system Laplacian matrix, screening eigenvalues below an electrical coupling strength threshold, and obtaining an access control device grouping feature vector; performing weighted summation operation on the access control device grouping feature vector and the installation space coordinates of the access control devices, and obtaining a space constraint feature representation; performing improved k-means clustering calculation based on the space constraint feature representation, limiting the number of devices in the same device installation unit to be no more than a preset access control component capacity threshold, and obtaining the plurality of device installation units.

[0027] Specifically, the process of constructing the access device degree matrix based on the device coupling strength matrix and calculating the access system Laplacian matrix involves basic mathematical operations in graph theory. The access device degree matrix is a diagonal matrix, whose diagonal elements represent the sum of the connection strength of the corresponding device with other devices, and the non-diagonal elements are all zero. The calculation process of the degree matrix is to traverse each row of the device coupling strength matrix and add all the non-zero elements in the row to obtain the degree value of the corresponding device. The degree value reflects the connection density of the device in the electrical topology network of the access system, and the larger the degree value, the tighter the electrical association between the device and other devices. The access system Laplacian matrix is obtained by subtracting the device coupling strength matrix from the degree matrix, and the Laplacian matrix is an important tool for describing the network structure characteristics in graph theory. The diagonal elements of the Laplacian matrix are equal to the degree value of the corresponding device, and the non-diagonal elements are equal to the negative of the corresponding elements in the device coupling strength matrix. The Laplacian matrix has the property of semi-positivity, and its eigenvalues are all non-negative real numbers. The distribution of eigenvalues reflects the connectivity and clustering structure characteristics of the network. The matrix calculation process is carried out according to the standard matrix subtraction operation rules, and the difference between the corresponding elements of the degree matrix and the coupling strength matrix is calculated element by element.

[0028] The process of performing eigenvalue decomposition on the access system Laplacian matrix and selecting eigenvalues below the electrical coupling strength threshold to obtain the access device grouping feature vector uses the eigenvalue decomposition algorithm in linear algebra. Eigenvalue decomposition decomposes the Laplacian matrix into the product of eigenvalues and eigenvectors, where the eigenvalues represent the scaling ratio of the matrix in the corresponding eigenvector direction, and the eigenvectors represent the main direction of the matrix transformation. Eigenvalue decomposition uses the Jacobi iteration algorithm or the QR decomposition algorithm to calculate, which diagonalizes the Laplacian matrix through repeated matrix transformation. The electrical coupling strength threshold is a value set in advance according to the electrical characteristics and construction requirements of the access system, and the selection of the threshold is based on the minimum acceptable coupling strength level between devices. The selection process traverses all the calculated eigenvalues and selects the eigenvalues and their corresponding eigenvectors whose values are less than or equal to the electrical coupling strength threshold. The eigenvectors corresponding to small eigenvalues contain information about the weakly connected parts of the network, which helps to identify relatively independent device groups. The access device grouping feature vector is a set of selected eigenvectors, each with a dimension equal to the total number of access devices, and each element in the vector corresponds to the grouping weight of a specific device. The element value of the eigenvector reflects the inclination of the corresponding device to belong to that grouping, and the larger the value, the more the device tends to belong to that grouping.

[0029] The process of weighted summation operation of the access control equipment grouping feature vector and the installation space coordinates of the access control equipment combines electrical features and spatial position information. The installation space coordinates of the access control equipment include the X coordinate, Y coordinate and Z coordinate of the equipment in the three-dimensional space of the subway platform, and the coordinate values are calibrated by the platform building coordinate system. The spatial coordinates are obtained by building drawing analysis, field measurement or three-dimensional modeling software export, and the coordinate accuracy is required to reach the centimeter level to meet the construction positioning requirements. The weighted summation operation element-wise multiplies the grouping feature vector of each equipment with its space coordinate vector, and then adds the product results in sequence according to the equipment number. The weighting coefficient reflects the relative importance of electrical features and spatial features in equipment grouping, and the determination of the weighting coefficient is based on the actual needs of the construction of the access control system and expert experience. The space constraint feature representation is a multi-dimensional vector, and the dimension of the vector is equal to the number of grouping feature vectors. Each dimension corresponds to a potential equipment grouping direction. Each element in the vector considers the electrical correlation and spatial distribution characteristics of the equipment, and the numerical value reflects the comprehensive adaptation degree of the equipment in the corresponding grouping. The introduction of the space constraint solves the problem that the traditional electrical grouping method ignores the construction space limitation, and makes the grouping result more in line with the operability requirements of the actual construction.

[0030] The process of obtaining multiple device installation units based on improved k-means clustering calculation and limiting the number of devices in the same device installation unit to not exceed the preset access control component capacity threshold adopts a constraint optimization clustering algorithm. The improved k-means algorithm adds a capacity constraint mechanism based on the traditional k-means algorithm to ensure that the size of each cluster does not exceed the preset threshold limit. The preset access control component capacity threshold is determined according to the personnel configuration of the construction team, the tool device capacity and the construction time arrangement, and the threshold setting needs to balance the rationality of grouping and the operability of construction. The k-means clustering algorithm first randomly initializes k cluster centers, and the value of k is equal to the expected number of device installation units. The initial position of the cluster center is randomly distributed in the data space of the spatial constraint feature representation. The clustering process adopts an iterative optimization method, and each iteration includes two steps of device assignment and center update. The device assignment step calculates the Euclidean distance of each device to each cluster center, and assigns the device to the cluster center with the closest distance and not reaching the capacity threshold. The center update step calculates the arithmetic mean of the spatial constraint feature representation of all devices in each cluster, and takes the mean value as the new cluster center position. The capacity constraint mechanism plays a role in the device assignment process. When the number of devices in a certain cluster reaches the capacity threshold, the cluster can no longer accept new device assignments, and the remaining devices can only be assigned to other unfulfilled clusters. The iteration process continues until the position of the cluster center changes less than the preset convergence threshold or reaches the maximum number of iterations. The clustering result forms multiple device installation units, each unit containing a group of access control devices with high electrical correlation and relatively concentrated spatial position.

[0031] In a specific embodiment, step S3 comprises: extracting the position coordinates, device type code, power level, installation height and reserved space size parameters of each access control device in the multiple device installation units to construct a device physical attribute feature vector; convert the access control device standard installation specification, electrical safety distance requirement and commissioning acceptance standard into vector representation to construct an access control circuit knowledge graph embedding vector; construct an access control system device adjacency matrix based on the device physical attribute feature vector and electrical connection relationship, and construct an access control circuit knowledge enhanced graph neural network combined with the access control circuit knowledge graph embedding vector; input the device physical attribute feature vector into the access control circuit knowledge enhanced graph neural network for graph attention mechanism calculation to obtain a device node hidden state vector; perform full connection layer mapping processing on the device node hidden state vector to output the device installation priority score matrix.

[0032] Specifically, the process of constructing the device physical attribute feature vector by extracting the position coordinates, device type code, power level, installation height, and reserved space size parameters of each access control device in the multiple device installation units involves standardization processing of multidimensional data. The position coordinates include the X-axis, Y-axis, and Z-axis numerical values of the device in the coordinate system of the subway platform, with the coordinate origin set at the geometric center position of the platform, the X-axis along the direction of train travel, the Y-axis perpendicular to the X-axis pointing to the width direction of the platform, and the Z-axis representing the installation height of the device. The device type code adopts a hierarchical coding system, with the first digit representing the device category, such as controller 1, card reader 2, and electromagnetic lock 3, the second digit representing the device subcategory, such as in-station card reader 21 and out-station card reader 22, and the third digit representing the specific model and specifications of the device. The power level describes the electrical power consumption level of the device, with the power level of controller devices typically between 50 watts and 200 watts, the power level of card reader devices between 5 watts and 20 watts, and the power level of electromagnetic lock devices between 10 watts and 50 watts. The installation height represents the vertical distance of the device from the ground, with the standard installation height of card readers being 1.2 meters suitable for both adults and children, the installation height of controllers being 2.5 meters to avoid unauthorized access, and the installation height of electromagnetic locks matching the door frame structure. The reserved space size parameters include the length, width, and depth space required for device installation, as well as the necessary maintenance operation space and safety distance around the device. The construction of the feature vector arranges the above five types of parameters in a fixed order to form a multidimensional array, with the dimension of the array equal to the total number of parameters, and each parameter occupying a specific position index in the vector. The data standardization processing uses the maximum and minimum normalization method to eliminate the influence of different parameter dimensions, scaling all parameter values to the range of 0 to 1.

[0033] The process of converting the access control equipment standard installation specification, electrical safety distance requirement and commissioning acceptance standard into vector representation to construct the access control circuit knowledge graph embedding vector adopts the vector representation technology of knowledge graph. The access control equipment standard installation specification includes the installation position requirement, installation direction requirement, installation fixing method and wiring specification of the equipment, etc. The specification content is converted into a numerical rule set through text analysis and semantic analysis. The electrical safety distance requirement specifies the minimum distance that must be maintained between different types of equipment. The safety distance requirement between high-voltage equipment and low-voltage equipment is larger, and the electromagnetic isolation distance needs to be maintained between strong current equipment and weak current equipment. The commissioning acceptance standard defines the function test items, performance index requirements and acceptance process after the equipment installation is completed. The standard content includes communication connection test, electrical parameter test, mechanical action test and system integration test, etc. The construction of knowledge graph adopts the triple structure of entity-relation-entity. The entity represents the specific object in the access control system, such as equipment, specification, standard, etc. The relation represents the logical connection between entities, such as installation relation, test relation, constraint relation, etc. The vector representation converts the triple structure into a low-dimensional dense vector through the knowledge graph embedding algorithm. The embedding algorithm uses the TransE model to map entities and relations into the same vector space. The access control circuit knowledge graph embedding vector contains the prior knowledge in the professional field of access control system. Each dimension of the vector corresponds to a characteristic direction in the knowledge space, and the vector value reflects the importance of the corresponding knowledge characteristics.

[0034] The process of constructing the access control system device adjacency matrix based on the device physical attribute feature vector and the electrical connection relationship and constructing the access control circuit knowledge enhanced graph neural network in combination with the access control circuit knowledge graph embedding vector involves the neural network modeling of graph structure data. The access control system device adjacency matrix is a square matrix. The row index and column index of the matrix correspond to different access control devices, respectively. The matrix element represents whether there is an electrical connection relationship between the corresponding devices. The construction process of the adjacency matrix traverses the electrical connection information of all device pairs. When there is a direct electrical connection between device A and device B, the element at the corresponding position in the matrix is set to 1, otherwise it is set to 0. The electrical connection relationship includes power supply connection, signal transmission connection, data communication connection and control instruction connection, etc. Different types of connection relationships are represented by different numerical values in the adjacency matrix. The access control circuit knowledge enhanced graph neural network adopts the graph attention network architecture. The input layer of the network receives the device physical attribute feature vector and the adjacency matrix. The hidden layer learns the associated features between devices through graph convolution operation. The output layer generates the high-level representation vector of the device. The knowledge enhancement mechanism is realized by fusing the access control circuit knowledge graph embedding vector and the device feature vector. The fusion operation merges the two types of information by vector splicing or vector addition. The parameters of the graph neural network are trained through the back propagation algorithm. The training target is to minimize the loss function value between the predicted result and the true label.

[0035] The process of inputting the device physical property feature vector into the access control circuit knowledge enhanced graph neural network to perform graph attention mechanism calculation to obtain the device node hidden state vector adopts attention mechanism to learn the importance weight between devices. The graph attention mechanism calculates the attention weight of each device node to its neighbor nodes, and the attention weight reflects the contribution degree of the neighbor nodes to the current node feature learning. The calculation process of the attention weight first splices the feature vector of the current node with the feature vector of the neighbor nodes, then inputs the spliced result into a single perceptron for nonlinear transformation, and finally normalizes the attention weight value through a softmax function. The hidden state vector of the device node is obtained by weighting and summing the feature vectors of the neighbor nodes according to the corresponding attention weights. The weighting and summing operation makes the important neighbor nodes have a greater impact on the current node. The multi-head design of the graph attention mechanism captures different types of node relationships by parallel computing multiple sets of attention weights, and the results of the multi-head attention are merged through splicing or averaging operations. The hidden state vector contains the physical property information of the device itself, the association information of the neighbor devices and the professional knowledge information in the access control field, and the dimension of the vector is determined by the hidden layer size of the graph neural network.

[0036] The process of performing full connection layer mapping on the device node hidden state vector to output the device installation priority score matrix generates the score result through linear transformation and nonlinear activation. The full connection layer adopts linear transformation to map the hidden state vector to the output space, and the linear transformation is realized through matrix multiplication operation of the weight matrix and the hidden state vector. The parameters of the weight matrix are learned through the network training process. The nonlinear activation function processes the result of the linear transformation. The activation function adopts a sigmoid function to limit the output value in the range of 0 to 1, and the output value represents the installation priority score of the corresponding device. The device installation priority score matrix is a two-dimensional matrix, the row index of the matrix corresponds to different device installation units, the column index corresponds to specific devices in the unit, and the matrix element represents the installation priority score of the corresponding device in the corresponding unit. The higher the score value, the higher the installation priority of the device. The calculation of the score considers factors such as electrical dependency relationship, spatial position constraint and construction difficulty. The output format of the matrix is convenient for subsequent construction scheduling algorithm, and the scheduling algorithm determines the installation order and time arrangement of the devices according to the score matrix.

[0037] In a specific embodiment, the process of constructing an access control system device adjacency matrix based on the device physical property feature vector and the electrical connection relationship can specifically include the following steps: According to the voltage difference, current capacity and signal type parameters between the access control devices, the electrical connection weight is calculated, and the access control system device adjacency matrix is constructed; The access control circuit knowledge graph embedding vector and the device physical attribute feature vector are subjected to a matrix splicing operation to obtain a knowledge enhanced node feature vector; An embedding layer parameter of a graph neural network is initialized based on the knowledge enhanced node feature vector and an access control system device adjacency matrix to construct a graph attention layer and a fully connected output layer. A door access device installation dependency constraint weight and a spatial conflict penalty coefficient are set for the graph attention layer to obtain a parameter configured access control circuit knowledge enhanced graph neural network.

[0038] Specifically, the process of calculating the electrical connection weight based on the voltage difference, current capacity and signal type parameters between access control devices to construct the access control system device adjacency matrix adopts a multi-parameter weighted fusion data processing method. The voltage difference parameter is calculated by comparing the working voltage values of two access control devices, and the voltage difference is equal to the absolute value of the output voltage of device A minus the input voltage of device B. The smaller the voltage difference, the better the electrical compatibility of the two devices. The current capacity parameter reflects the matching degree of the current carrying capacity of the device, which is calculated by comparing the output current capacity of device A with the input current demand of device B. When the output current capacity is greater than or equal to the input current demand, the matching degree is 1, otherwise the matching degree is equal to the ratio of the output current capacity to the input current demand. The signal type parameter describes the signal feature compatibility between devices, and the compatibility of digital signals and digital signals is 1, the compatibility of analog signals and analog signals is 1, and the compatibility of digital signals and analog signals is 0.5, indicating that an interface needs to be converted. The electrical connection weight is calculated by using a weighted summation method, which multiplies the reciprocal of the voltage difference by the voltage weight coefficient, multiplies the current capacity matching degree by the current weight coefficient, and multiplies the signal type compatibility by the signal weight coefficient. The sum of the three products is the electrical connection weight value. The weight coefficients are set based on the importance evaluation of the electrical design of the access control system. The weight coefficient of voltage matching is set to 0.5 because voltage mismatch directly affects device operation. The weight coefficient of current capacity is set to 0.3 because insufficient current affects device performance. The weight coefficient of signal type is set to 0.2 because signal incompatibility affects communication quality. The access control system device adjacency matrix uses these electrical connection weight values as matrix elements. The row index and column index of the matrix correspond to the source device and the target device, respectively, and the value of the matrix element represents the electrical connection strength between the corresponding device pair.

[0039] The process of embedding the access control circuit knowledge graph vector and the device physical attribute feature vector into a matrix to obtain a knowledge-enhanced node feature vector involves the fusion of different types of information. The access control circuit knowledge graph embedding vector contains professional knowledge information of the access control system, such as device installation specification requirements, electrical safety distance standards, and system debugging processes. The device physical attribute feature vector contains objective physical information of the device, such as location coordinates, device type, power level, installation height, and space size, which are measurable parameters. The matrix concatenation operation combines the two vectors into a longer vector through vector connection. The concatenation process arranges the elements in a fixed order, placing all elements of the device physical attribute feature vector first, and then placing all elements of the access control circuit knowledge graph embedding vector. The dimension of the knowledge-enhanced node feature vector after concatenation is equal to the sum of the dimensions of the two original vectors. The first half of the vector retains the physical feature information of the device, and the second half introduces professional knowledge information in the access control field. The knowledge enhancement mechanism uses this information fusion method to make the neural network learning process consider both the objective attributes of the device and the prior knowledge in the professional field, improving the richness and accuracy of the feature representation. The execution of the concatenation operation uses an array concatenation function to ensure that the order and numerical accuracy of the vector elements remain unchanged during the concatenation process.

[0040] The process of initializing the embedding layer parameters of the graph neural network based on the knowledge-enhanced node feature vector and the access control system device adjacency matrix, and constructing the graph attention layer and the fully connected output layer uses a hierarchical network architecture design. The embedding layer of the graph neural network is responsible for converting the knowledge-enhanced node feature vector into an internal representation form. The parameter initialization of the embedding layer uses the Xavier initialization method, which sets the initial value range of the parameters based on the size of the input and output dimensions to ensure stable gradient propagation during network training. The weight matrix dimension of the embedding layer is determined by the dimension of the knowledge-enhanced node feature vector and the dimension of the hidden layer, and the bias vector dimension is equal to the dimension of the hidden layer. The graph attention layer uses a multi-head attention mechanism to learn the correlation weights between devices. The construction of the attention layer includes the parameter initialization of the query matrix, key matrix, and value matrix. The dimensions of these matrices are determined by the hidden layer dimension and the number of attention heads. The attention weight is calculated by performing a dot product operation between the query vector and the key vector, and then normalized by the softmax function. The normalized weight is used to perform weighted summation on the value vector. The fully connected output layer maps the output of the graph attention layer to the prediction result. The weight matrix of the output layer maps the feature vector of the hidden layer to the output space, and the output dimension is set to the number of device installation priority scores according to task requirements. The connection between network layers uses residual connection and layer normalization techniques to improve training results. Residual connection adds the input directly to the output to avoid gradient vanishing problems, and layer normalization normalizes the output of each layer to accelerate the convergence process.

[0041] The graph attention layer is configured with access control device installation dependency constraint weights and spatial conflict penalty coefficients to obtain parameterized access control circuit knowledge-enhanced graph neural networks, which improve network performance through constrained optimization. The access control device installation dependency constraint weights reflect the installation order dependencies between devices. When device A must be installed before device B, the corresponding constraint weight is set to a large positive value. When there is no dependency between the devices, the constraint weight is set to zero. The dependency constraint weights are determined based on the access control system's electrical connection logic and construction process requirements. Controller devices typically have the highest dependency constraint weights because other devices require connection to the controller for proper operation. Power supply devices also have high dependency constraint weights because they require power. The spatial conflict penalty coefficient is used to avoid conflicts when multiple devices are installed simultaneously in the same space. The penalty coefficient is calculated based on the spatial footprint of the devices and the degree of overlap in their installation time. When two devices overlap in both installation space and time, the corresponding penalty coefficient is set to a large negative value. The penalty coefficient is proportional to the spatial overlap area and the length of the temporal overlap. Constraint weights and penalty coefficients influence the network training process by modifying the loss function. The modified loss function consists of three components: the original prediction loss, the dependency constraint loss, and the spatial conflict penalty loss. During network training, the backpropagation algorithm updates the network parameters based on this modified loss function, ensuring that the network's predictions meet both accuracy requirements and the practical constraints of the access control system.

[0042] In a specific embodiment, step S4 includes: Collect 3D spatial coordinate data of the subway platform construction area, divide the construction space into grid units, and construct a space occupancy matrix; Determine the installation operation time window and space requirement set of the access control equipment according to the equipment installation priority scoring matrix, and establish an equipment installation operation space requirement database; Based on the space occupancy matrix and the equipment installation operation space requirement database, spatiotemporal conflict detection calculation is performed to identify the spatial overlap areas and time conflict periods of multi-professional construction, and obtain construction conflict identification results; The construction conflict identification results are graded according to the degree of conflict impact to generate the multi-professional construction conflict warning signals of minor conflict, moderate conflict and severe conflict.

[0043] Specifically, the process of collecting three-dimensional spatial coordinate data of the construction area of the subway platform and dividing the construction space into grid units to construct the space occupancy matrix adopts a spatial discretization data processing method. The collection of three-dimensional spatial coordinate data is obtained through laser scanning equipment, total station measurement and building information model export, etc. The coordinate data includes spatial information such as the boundary contour of the subway platform, column position, wall distribution, equipment reserved position and passage area. The coordinate system adopts the platform building coordinate system, taking the geometric center of the platform as the origin, the X-axis along the train running direction, the Y-axis perpendicular to the train running direction pointing to the platform width, and the Z-axis vertically upward indicating the height direction. The division of the construction space adopts a regular gridding method, which divides the entire three-dimensional space into several cubic grid units according to fixed length, width and height intervals. The size of the grid unit is set based on the minimum installation space requirement of the access control equipment and the operation space requirement of the construction personnel, and is usually set as a cubic unit of 1 meter long, 1 meter wide and 1 meter high. Each grid unit is assigned a unique three-dimensional index, and the index is represented in the form of a triple as the serial number of the grid unit in the X, Y and Z directions. The space occupancy matrix stores the occupancy state of the grid unit in the form of a three-dimensional array structure, and the three dimensions of the array correspond to the grid index in the X, Y and Z directions, respectively. The numerical value of the array element represents the occupancy of the corresponding grid unit. The occupancy state adopts binary coding, 0 represents an idle grid unit, and 1 represents an occupied grid unit. The initial state of the occupancy matrix is set according to the positions of the fixed facilities such as columns, walls and existing equipment of the platform.

[0044] The process of determining the installation time window and spatial requirement set of access control devices according to the device installation priority scoring matrix and establishing the device installation job spatial requirement database involves the quantitative allocation of time and space resources. The scoring values in the device installation priority scoring matrix directly affect the installation timing arrangement of devices. The higher the score, the earlier the installation time window is obtained. Devices with the same score are arranged in the time window according to the device number sequence. The determination of the installation time window uses a sequential allocation algorithm. First, all devices are arranged in descending order according to the priority score. Then, a continuous time period is allocated to each device according to the arrangement order. The length of the time window is determined according to the device type and installation complexity. The installation time window of the controller device is usually 4 hours because complex wiring and debugging work is required. The installation time window of the card reader device is 2 hours because the installation is relatively simple. The installation time window of the electromagnetic lock device is 1 hour because it is mainly a mechanical fixing operation. The spatial requirement set describes the range of grid cells that need to be occupied during the installation process of the device. The calculation of the spatial requirement is based on parameters such as the physical size of the device, the operation space of the installation tool, and the safe operation distance. The physical size of the device includes the length, width, and height of the device body. The operation space of the installation tool includes the movement range required by the construction personnel and tool equipment. The safe operation distance includes the minimum isolation distance required to prevent accidental injury. The spatial requirement set is represented in the form of a grid cell index list. The list contains the three-dimensional index of all grid cells that need to be occupied during the installation process of the device. The device installation job spatial requirement database uses a relational database structure. The database table contains fields such as device number, installation time window, spatial requirement set, professional type, and dependency relationship. The database supports query and statistical operations based on multiple conditions.

[0045] The process of construction conflict identification based on space occupation matrix and equipment installation operation space requirement database is to calculate the space-time conflict detection and identify the space overlap area and time conflict period of multi-specialty construction to obtain the construction conflict identification result. The space-time overlap analysis algorithm is adopted. The space-time conflict detection algorithm traverses all combinations of equipment pairs in the database, and checks the overlap of the time window and space requirement of each equipment pair. The time conflict detection is to compare the installation time window of two equipment to determine whether there is time overlap. When the start time of equipment A is less than the end time of equipment B and the end time of equipment A is greater than the start time of equipment B, it is determined that there is time overlap between the two equipment. The space conflict detection is to compare the space requirement set of two equipment to determine whether there is space overlap. The identification of multi-specialty construction conflict focuses on the space-time overlap between equipment of different specialties, because equipment in the same specialty is usually responsible by the same construction team, and the coordination between them is relatively easy. The identification of space overlap area is realized by calculating the intersection of the space requirement set of two equipment. The grid cell index in the intersection constitutes the description of the space overlap area. The identification of time conflict period is realized by calculating the intersection of the time window of two equipment. The start time of the intersection is equal to the maximum of the two start times, and the end time of the intersection is equal to the minimum of the two end times. The construction conflict identification result is stored in the form of conflict record list. Each conflict record contains the number of conflict equipment pair, conflict type, overlap area, conflict period and involved specialty, etc.

[0046] The process of classifying the construction conflict identification results according to the impact degree of the conflict and generating multi-specialty construction conflict warning signals of slight conflict, medium conflict and serious conflict adopts an impact degree quantitative evaluation method. The evaluation of the impact degree of the conflict is based on the comprehensive consideration of multiple factors, including the number of devices involved in the conflict, the spatial overlap area, the time overlap length, the difference in professional types and the importance level of the devices, etc. The device number factor reflects the size of the conflict scale, the more the number of devices involved, the wider the impact range of the conflict, and the device number factor is equal to the total number of devices involved in the conflict. The spatial overlap area factor is quantified by calculating the number of overlapping grid cells, and the more the number of overlapping grid cells, the more serious the spatial conflict, and the area factor is equal to the product of the number of overlapping grid cells and the volume of a single grid cell. The time overlap length factor is quantified by calculating the duration of the overlapping time period, and the longer the overlapping time, the greater the impact of the conflict, and the time factor is equal to the number of hours of the overlapping time period. The difference in professional types factor reflects the difficulty of coordination between different specialties, and the coordination of conflicts within the same specialty is relatively easy, while the coordination of conflicts between different specialties is more difficult, and the difference factor is set according to the combination of professional types. The importance level of the device factor is set based on the criticality of the device in the access control system, and the importance level of the controller device is the highest, the importance level of the card reader device is in the middle, and the importance level of the electromagnetic lock device is lower. The conflict impact degree score is calculated by weighted summation, and the total score is obtained by multiplying each factor by the corresponding weight coefficient and then adding them together. The classification processing classifies according to the numerical range of the impact degree score, and the conflict with a score lower than the preset slight threshold is classified as a slight conflict, the conflict with a score between the slight threshold and the serious threshold is classified as a medium conflict, and the conflict with a score higher than the serious threshold is classified as a serious conflict. The multi-specialty construction conflict warning signal contains information such as conflict level, conflict description, impact assessment and recommended measures, and the warning signal is sent to relevant construction management personnel and professional leaders through a message queue or a notification interface.

[0047] In a specific embodiment, step S5 comprises: receiving the multi-specialty construction conflict warning signal, analyzing the conflict type and the conflict impact range, and constructing a conflict constraint condition set; establishing a multi-objective optimization function based on the conflict constraint condition set and the device installation priority score matrix, and setting the weight coefficients of construction time, installation quality and professional waiting time; inputting the multi-objective optimization function into a particle swarm optimization algorithm for iterative solution, calculating the optimal adjustment scheme of the access control device installation time sequence, and obtaining the time sequence adjustment parameters; updating the installation time window and the professional operation sequence of the access control device according to the time sequence adjustment parameters, and generating the construction scheduling scheme.

[0048] Specifically, the process of receiving multi-disciplinary construction conflict warning signals and analyzing conflict types and conflict impact ranges to construct a conflict constraint set adopts structured data analysis and constraint modeling techniques. Multi-disciplinary construction conflict warning signals are transmitted in JSON format structured data, and the signal content includes key information such as conflict identifier, conflict level, involved equipment list, conflict time period, conflict space area, and conflict type code. Conflict type analysis identifies the specific nature of the conflict by interpreting the conflict type code, and the conflict type includes four categories: time conflict, space conflict, resource conflict, and dependency conflict. Time conflict indicates that the installation time window of multiple devices overlaps, space conflict indicates that the installation space demand of multiple devices intersects, resource conflict indicates that multiple devices compete for the same construction resources such as personnel or tools, and dependency conflict indicates that the installation dependency relationship between devices is violated. Conflict impact range analysis determines the impact range of the conflict by extracting the involved equipment list and conflict area information, and the impact range includes direct conflict devices and related devices that may be affected by the chain. The construction of the conflict constraint set converts the parsed conflict information into mathematical constraint expressions, and the constraint condition adopts the form of inequality or equality to describe the time and space relationship restrictions between devices. Time constraint conditions specify the installation time of conflict devices that must meet the order relationship, space constraint conditions specify the minimum distance requirement that must be maintained for the installation position of conflict devices, and resource constraint conditions specify the number of devices that use the same resource within the same time period. The constraint condition set adopts a list structure for storage, and each constraint condition contains attributes such as constraint type, involved variables, constraint expression, and constraint weight.

[0049] The process of establishing a multi-objective optimization function based on a set of conflicting constraints and an equipment installation priority matrix and assigning weights to construction time, installation quality, and professional waiting time involves mathematical modeling of the multi-objective optimization problem. This multi-objective optimization function comprises a linear combination of three optimization objectives: minimizing total construction time (expressed as the maximum installation completion time for all equipment); maximizing the average installation quality score (expressed as the arithmetic mean of all equipment installation quality scores); and minimizing the average waiting time among professionals (expressed as the arithmetic mean of all professional waiting times). The scores in the equipment installation priority matrix serve as weighting factors in the installation quality objective function; higher-scoring equipment receives a greater weight in the quality objective. The calculation of the construction time objective takes into account inter-equipment dependencies and resource constraints. The actual completion time of a piece of equipment is equal to its start time plus the installation duration, and the total construction time is equal to the maximum of all equipment completion times. The installation quality objective is calculated based on the degree of match between the equipment installation priority scores and the actual installation conditions. The highest quality score is achieved when equipment is installed according to priority order and meets all technical requirements. The calculation of the discipline waiting time objective is based on the coordination and waiting conditions between different disciplines. Waiting time occurs when one discipline is unable to begin work due to waiting for the completion of other disciplines. Weighting coefficients are set to reflect the relative importance of different objectives in construction management. Construction time is typically weighted higher because the construction period is critical to project success. Installation quality is weighted medium because quality affects the long-term stability of the system. Discipline waiting time is weighted lower because appropriate waiting time helps ensure construction quality.

[0050] The process of inputting the multi-objective optimization function into the particle swarm optimization algorithm for iterative solution and calculating the optimal adjustment scheme of the installation timing of the access control equipment to obtain the timing adjustment parameters adopts the numerical solution technology of swarm intelligence optimization algorithm. The particle swarm optimization algorithm searches for the optimal solution by simulating the foraging behavior of bird flocks. Each particle in the algorithm represents a possible equipment installation timing scheme, and the position vector of the particle encodes the installation start time of all equipment. The initialization of the particle swarm adopts a random generation method, and the position and velocity vectors of each particle are randomly set under the premise of meeting the basic constraint conditions. The iterative process of the algorithm includes four steps of fitness evaluation, individual optimal update, global optimal update, and particle position update. The fitness evaluation evaluates the pros and cons of the scheme represented by each particle by calculating the numerical value of the multi-objective optimization function. The smaller the fitness value, the better the scheme. The individual optimal update records the optimal position encountered by each particle in the search process. When the fitness value of the current position of the particle is better than the historical optimal value, the individual optimal position is updated. The global optimal update records the optimal position encountered in the entire particle swarm. When the individual optimal position of any particle is better than the current global optimal position, the global optimal position is updated. The particle position update adopts the speed-position update formula. The new speed of the particle is equal to the current speed multiplied by the inertia weight plus the acceleration term of the individual optimal direction plus the acceleration term of the global optimal direction. The new position of the particle is equal to the current position plus the new speed. The convergence judgment of the algorithm is based on the improvement degree of the global optimal position and the iteration limit. When the global optimal position has no significant improvement for several consecutive iterations or reaches the maximum iteration number, the algorithm terminates. The timing adjustment parameters are extracted from the global optimal position, including the adjusted start time, adjustment duration, and adjustment priority of each equipment, and other information.

[0051] The process of updating the installation time window of the access control device and generating the construction scheduling scheme based on the timing adjustment parameter adopts the scheduling scheme reconstruction and formatting output technology. The device start time in the timing adjustment parameter is directly used to update the installation time window of the device, and the new time window start time is equal to the start time in the adjustment parameter, and the time window length remains unchanged or is fine-tuned according to the adjustment duration parameter. The update of the professional operation sequence is based on the reordered time window of all devices in the same professional, and the operation sequence in the professional is determined according to the start time in chronological order. The construction scheduling scheme is generated by using the data structure of the Gantt chart to represent the construction scheduling scheme. The horizontal axis of the Gantt chart represents the time axis, and the vertical axis represents the device or the professional. The horizontal bar in the graph represents the installation time window of each device. The scheduling scheme includes global time arrangement, professional coordination plan, resource allocation table, and critical path analysis. The global time arrangement lists the installation time window and key time nodes of all devices, the professional coordination plan describes the handover time and coordination requirements between different professionals, the resource allocation table describes the use of various resources in each time period, and the critical path analysis identifies the key devices and key activities that affect the total duration. The output format of the scheduling scheme supports multiple representation methods, including table form, graphical form and text description form, which is convenient for users of different types to understand and use.

[0052] The above describes the metro access control system multi-professional collaborative construction monitoring method in the embodiments of the present application. The metro access control system multi-professional collaborative construction monitoring system in the embodiments of the present application is described below. Please refer to Figure 2 An embodiment of the metro access control system multi-professional collaborative construction monitoring system in the embodiments of the present application includes: A construction module is configured to collect voltage levels, communication protocol types and signal transmission delay parameters among the access controller, the card reader and the electromagnetic lock, calculate the coupling strength between devices, and construct a device coupling strength matrix. A division module is configured to divide the access control devices into a plurality of device installation units based on the device coupling strength matrix. An input module is configured to construct an access control circuit knowledge enhanced graph neural network, input physical attribute features and electrical connection relationships of the device installation units, and output a device installation priority score matrix. An identification module is configured to monitor the multi-professional operation state of the access control system installation construction, identify professional construction conflicts guided by the device installation priority score matrix, and generate a multi-professional construction conflict early warning signal. A response module is configured to respond to the multi-professional construction conflict early warning signal, dynamically adjust the installation timing of the access control device, and obtain a construction scheduling scheme.

[0053] The above Figure 2The subway access control system multi-professional collaborative construction monitoring system in the embodiment of the application is described in detail from the perspective of a modular functional entity. The subway access control system multi-professional collaborative construction monitoring device in the embodiment of the application is described in detail from the perspective of hardware processing.

[0054] With reference to Figure 3 The embodiment of the application also provides a subway access control system multi-professional collaborative construction monitoring device. The subway access control system multi-professional collaborative construction monitoring device can be a server, and the internal structure of the subway access control system multi-professional collaborative construction monitoring device can be as shown in Figure 3 The subway access control system multi-professional collaborative construction monitoring device includes a processor, a memory, a display screen, an input device, a network interface, and a database connected through a system bus. The processor of the computer is used to provide computing and control capabilities. The memory of the subway access control system multi-professional collaborative construction monitoring device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The database of the subway access control system multi-professional collaborative construction monitoring device is used to store corresponding data in the embodiment. The network interface of the subway access control system multi-professional collaborative construction monitoring device is used to communicate with an external terminal through a network connection. The computer program is executed by the processor to implement the above method.

[0055] Those skilled in the art can understand that Figure 3 The structure shown in the embodiment of the application is only a block diagram of part of the structure related to the scheme of the application, and does not constitute a limitation on the subway access control system multi-professional collaborative construction monitoring device to which the scheme of the application is applied.

[0056] The application also provides a computer readable storage medium. The computer readable storage medium can be a non-volatile computer readable storage medium or a volatile computer readable storage medium. The computer readable storage medium stores instructions. When the instructions are run on a computer, the computer executes the steps of the subway access control system multi-professional collaborative construction monitoring method.

[0057] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the system, the system, and the unit described above can refer to the corresponding processes in the foregoing method embodiments, which will not be described herein.

[0058] The integrated unit, if implemented in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application or the entire or part of the technical solutions that essentially contribute to the prior art can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a subway access control system multi-professional collaborative construction monitoring equipment (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0059] The above embodiments are only used to illustrate the technical solutions of the present application, but not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that the technical solutions recorded in the foregoing embodiments can be modified, or some technical features can be replaced by equivalents; and these modifications or replacements do not make the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A multi-professional collaborative construction monitoring method for a subway access control system, characterized in that: The method comprises: Step S1: Collect the voltage levels, communication protocol types, and signal transmission delay parameters between the access controller, card reader, and electromagnetic lock, calculate the coupling strength between devices, and construct a device coupling strength matrix; Step S2: Dividing the access control device into a plurality of device installation units based on the device coupling strength matrix; Step S3: Constructing a knowledge-enhanced graph neural network for access control circuits, inputting the physical property characteristics and electrical connection relationships of the equipment installation units, and outputting an equipment installation priority scoring matrix; Step S4: monitoring the multi-professional operation status of the access control system installation and construction, identifying the construction conflicts between the professions under the guidance of the equipment installation priority scoring matrix, and generating a multi-professional construction conflict warning signal; Step S5: responding to the multi-professional construction conflict warning signal, dynamically adjusting the installation sequence of the access control equipment, and obtaining a construction scheduling plan.

2. The multi-professional collaborative construction monitoring method for subway access control system according to claim 1 is characterized in that: The step S1 includes: Establish a set of access control device nodes and a set of electrical connection edges, and construct a directed graph of the electrical topology of the access control system; A device coupling strength value is obtained by performing a weighted calculation based on voltage matching, protocol compatibility, and the inverse of transmission delay between devices in the electrical topology directed graph; Fill the device coupling strength values ​​into the corresponding positions of the matrix according to the device number sequence to construct the device coupling strength matrix; The device coupling strength matrix is ​​normalized to obtain a device coupling strength matrix.

3. The multi-professional collaborative construction monitoring method for subway access control system according to claim 1 is characterized in that: The step S2 includes: Constructing an access control device degree matrix based on the device coupling strength matrix and calculating the access control system Laplace matrix; Performing eigenvalue decomposition on the Laplace matrix of the access control system, screening eigenvalues ​​below an electrical coupling strength threshold, and obtaining an access control device grouping eigenvector; Performing a weighted sum operation on the access control device grouping feature vector and the installation space coordinates of the access control device to obtain a spatial constraint feature representation; An improved k-means clustering calculation is performed based on the spatial constraint feature representation to limit the number of devices in the same device installation unit to not exceed a preset access control component capacity threshold, thereby obtaining the multiple device installation units.

4. The multi-professional collaborative construction monitoring method for subway access control system according to claim 1 is characterized in that: The step S3 comprises: Extracting the location coordinates, device type code, power level, installation height, and reserved space dimension parameters of each access control device in the multiple device installation units to construct a device physical property feature vector; Convert access control equipment standard installation specifications, electrical safety distance requirements, and commissioning acceptance criteria into vector representations to construct an embedding vector for the access control circuit knowledge graph. Constructing an access control system device adjacency matrix based on the device physical property feature vectors and electrical connection relationships, and constructing an access control circuit knowledge enhanced graph neural network based on the access control circuit knowledge graph embedding vectors; Input the physical property feature vector of the device into the access control circuit knowledge enhanced graph neural network to perform graph attention mechanism calculation to obtain the hidden state vector of the device node; Performing fully connected layer mapping processing on the hidden state vector of the device node and outputting the device installation priority scoring matrix.

5. The multi-professional collaborative construction monitoring method for subway access control system according to claim 4 is characterized in that: The method of constructing an access control system device adjacency matrix based on the device physical property feature vector and electrical connection relationship, and constructing an access control circuit knowledge enhanced graph neural network in combination with the access control circuit knowledge graph embedding vector, includes: Calculating electrical connection weights based on voltage differences, current capacities, and signal type parameters between access control devices to construct an access control system device adjacency matrix; Perform a matrix concatenation operation on the access control circuit knowledge graph embedding vector and the device physical property feature vector to obtain a knowledge enhancement node feature vector; Initialize the embedding layer parameters of the graph neural network based on the knowledge-enhanced node feature vector and the access control system device adjacency matrix, and construct the graph attention layer and the fully connected output layer; The access control equipment installation dependency constraint weight and the spatial conflict penalty coefficient are set for the graph attention layer to obtain the access control circuit knowledge enhanced graph neural network after parameter configuration.

6. The multi-professional collaborative construction monitoring method for subway access control system according to claim 1 is characterized in that: The step S4 comprises: Collect 3D spatial coordinate data of the subway platform construction area, divide the construction space into grid units, and construct a space occupancy matrix; Determine the installation operation time window and space requirement set of the access control equipment according to the equipment installation priority scoring matrix, and establish an equipment installation operation space requirement database; Based on the space occupancy matrix and the equipment installation operation space requirement database, spatiotemporal conflict detection calculation is performed to identify the spatial overlap areas and time conflict periods of multi-professional construction, and obtain construction conflict identification results; The construction conflict identification results are graded according to the degree of conflict impact to generate the multi-professional construction conflict warning signals of minor conflict, moderate conflict and severe conflict.

7. The multi-professional collaborative construction monitoring method for subway access control system according to claim 1 is characterized in that: The step S5 comprises: Receiving the multi-professional construction conflict warning signal, analyzing the conflict type and conflict impact range, and constructing a conflict constraint condition set; Establishing a multi-objective optimization function based on the conflict constraint condition set and the equipment installation priority scoring matrix, and setting weight coefficients for construction time, installation quality, and professional waiting time; Input the multi-objective optimization function into the particle swarm optimization algorithm for iterative solution, calculate the optimal adjustment scheme for the installation sequence of the access control equipment, and obtain the sequence adjustment parameters; The installation time window and professional operation sequence of the access control equipment are updated according to the timing adjustment parameters to generate the construction scheduling plan.

8. A multi-professional collaborative construction monitoring system for subway access control systems, characterized by: The method for implementing the multi-disciplinary collaborative construction monitoring method of a subway access control system according to any one of claims 1 to 7, wherein the multi-disciplinary collaborative construction monitoring system of the subway access control system comprises: A construction module is used to collect voltage levels, communication protocol types, and signal transmission delay parameters between access controllers, card readers, and electromagnetic locks, calculate the coupling strength between devices, and construct a device coupling strength matrix; a division module, configured to divide the access control device into a plurality of device installation units based on the device coupling strength matrix; An input module is used to construct a knowledge-enhanced graph neural network for access control circuits, input the physical property characteristics and electrical connection relationships of the equipment installation units, and output a equipment installation priority scoring matrix; An identification module is used to monitor the multi-disciplinary operation status of the access control system installation and construction, identify the construction conflicts between disciplines under the guidance of the equipment installation priority scoring matrix, and generate a multi-disciplinary construction conflict early warning signal; The response module is used to respond to the multi-professional construction conflict warning signal, dynamically adjust the installation sequence of the access control equipment, and obtain a construction scheduling plan.

9. A multi-professional collaborative construction monitoring device for a subway access control system, characterized in that: It includes a memory and a processor, the memory stores a computer program that can be run on the processor, and when the processor executes the computer program, it implements the multi-professional collaborative construction monitoring method of the subway access control system described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the processor executes the multi-professional collaborative construction monitoring method for a subway access control system as described in any one of claims 1 to 7.

Images