Constructional engineering risk assessment method and system for multi-source anomaly monitoring

Abstract

The invention discloses a construction engineering risk assessment method and system for multi-source anomaly monitoring, and particularly relates to the field of construction engineering risk assessment, comprising the following steps: analyzing equipment-to-component node mapping and return delay characteristics based on multi-source monitoring data received in an idle task period; establishing a cross-device time alignment model and a pseudo-synchronization section time migration trajectory, identifying a potential abnormal path set through a time delay drift trend, and providing a time feature basis for subsequent structure anomaly reasoning and risk assessment; deducing a node triggering sequence and a time causal chain based on the final pseudo-synchronization segment index matrix and channel path mapping; multi-source monitoring data is received in an idle task period, and a cross-device time alignment model is established, so that the problem of time sequence dislocation caused by mechanisms such as cache delay and packet loss re-sending is effectively identified, and historical abnormal data is prevented from being misjudged as a future risk from the source.

Description

Technical Field

[0001] The present invention relates to the technical field of construction engineering risk assessment, and more specifically, to a construction engineering risk assessment method and system oriented to multi-source anomaly monitoring. Background Art

[0002] In construction project risk assessment for multi-source anomaly monitoring, the system often needs to integrate monitoring data from different types of sensors, such as structural displacement sensors, environmental image modules, and strain gauges, to make time-series risk judgments.

[0003] However, when the project is in a non-operating cycle or construction is suspended, due to the cache delay, intermittent return or packet loss retransmission mechanism of some equipment, its historical data may be delayed and incorrectly mapped to the current time period by the system, thereby causing time sequence misalignment with other real-time data; in this case, the system is very likely to misjudge "historical abnormal data" as "abnormal events that have occurred in the future", forming the so-called "abnormal advance retrospective illusion", thereby triggering erroneous structural warnings and affecting the correctness of the overall risk reasoning path. Summary of the Invention

[0004] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a construction project risk assessment method and system for multi-source abnormality monitoring, which synchronously verifies the cross-device time consistency of multi-source monitoring data during the idle task cycle, dynamically extracts pseudo-synchronous offset trajectories and performs structural causal chain reasoning and response time correction, eliminates abnormal misjudgments caused by historical data lags, and ensures the continuity and accuracy of the risk assessment reasoning chain, so as to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above objectives, the present invention provides the following technical solution: a construction project risk assessment method for multi-source anomaly monitoring, comprising:

[0006] Based on multi-source monitoring data received during the idle task cycle, the device-to-component node mapping and return delay characteristics are analyzed, and a cross-device time alignment model and pseudo-synchronization segment time offset trajectory are established. Potential abnormal path sets are identified through delay drift trends, providing a temporal feature basis for subsequent structural anomaly reasoning and risk assessment.

[0007] Based on the final pseudo-synchronization segment index matrix and channel path mapping, the node triggering sequence and time causal chain are derived. Combined with delay statistical analysis, time misalignment events are identified and structural sections with causal residual mismatches in the response chain are located. This provides support for pseudo-synchronization segment time correction and revised causal chain diagram reconstruction.

[0008] Based on the modified causal chain graph, the response time and order of pseudo-synchronous segment nodes are retrieved, the effective time correction function is derived and screened, the time label and node trigger order are corrected, the synchronization data set is reconstructed and the path index and delay characteristics are updated, and the structural response chain continuity closure and cross-cycle synchronization consistency are achieved;

[0009] Archive the synchronous instability indicators of each period and construct a time series risk indicator set. Predict the evolution of synchronous instability risk based on trend external driving dynamics. Adjust the detection parameters of high-risk path groups according to the prediction results. Continuously optimize the cross-period pseudo-synchronous segment screening and structural chain correction process to form an iterative risk feedback system.

[0010] In a preferred embodiment, the original monitoring records uploaded by various heterogeneous monitoring devices are collected when the risk assessment and monitoring platform is in an idle state, and the device identification, timestamp, and channel protocol fields of the records are extracted to form a set of original data tuples. Channel protocol classification and path identification grouping operations are performed on the original data tuples to generate a device channel table and record the return start time and periodic interval of each channel.

[0011] The start time and periodic interval data of each channel returned in the device channel table are aggregated according to the device ID and timestamp to generate a reporting period sequence. Based on this, the three statistical indicators of average delay, range, and frequency hopping rate are calculated to generate a delay statistical parameter group.

[0012] The delay statistical parameter group is projected onto the global time axis, the time alignment difference map between devices is solved, the response drift trend is recorded, and the path set that forms a stable offset trend is extracted.

[0013] In a preferred embodiment, a deviation trajectory map is constructed based on the delay statistical parameter group and the time alignment difference map between devices, and a set of paths whose continuous drift gradient exceeds a stability threshold is identified. This path set is defined as a statistically unstable path group, and a cross-analysis is performed on it with the alignment difference map to screen out paths that meet both trend anomaly and deviation amplitude exceeding the threshold to form a potential abnormal path set.

[0014] Extract the time period response records corresponding to each path in the potential abnormal path set, and aggregate them according to the time window to generate a pseudo-synchronization segment candidate set. Then, screen the pseudo-synchronization segment candidate set for drift trend consistency and output the final pseudo-synchronization segment index matrix. The final pseudo-synchronization segment index matrix records the device number, start timestamp, and path identification information corresponding to each pseudo-synchronization interval, which serves as the basic data for subsequent path structure mapping and causal reasoning.

[0015] A response sequence distribution consistency check is performed on the time period corresponding to each pseudo-synchronization interval in the final pseudo-synchronization segment index matrix, and the amplification characteristics of the drift residual change trend within the time period are evaluated. The candidate synchronization instability sections whose drift amplitude exceeds the set threshold are screened out, and the candidate synchronization instability sections that pass the drift residual screening are further calibrated as key drift sections, and the corresponding time offset gradient and sensor node mapping relationship is recorded.

[0016] In a preferred embodiment, the device number recorded in the final pseudo-synchronization segment index matrix is ​​used as the index entry of the potential abnormal path response record, and is mapped to the corresponding component node through the path rules defined by the channel protocol classification and path identification grouping, thereby constructing a component-level node sequence under the device channel path mapping;

[0017] The original timestamps of each node in the component-level node sequence are sorted sequentially to calibrate the triggering order of each node in the device path structure, which serves as the basis for constructing the timeline of the structural response chain. The device path mapping relationship is derived based on the path rules, the connection mode between component nodes is analyzed, the ordered structure of node connections is extracted, and a directional time-driven edge set is constructed.

[0018] Calculate the trigger interval for each node pair in the time-driven edge set, combine the device channel mapped by the node pair, the average delay and range parameters defined in the delay statistics parameter group, call the propagation delay fitting model of the corresponding channel, and generate a time residual vector;

[0019] The time residual vector is segmented according to a fixed time window, and the slope change value is continuously calculated based on the sliding window within each segment to form a slope change data sequence; the slope mutation points and slope reversal points are identified in the data sequence, and a set of landmark points with abnormal change trends is extracted; the time segments covered between adjacent landmark points are extracted to form a preliminary set of fluctuation candidate segments.

[0020] In a preferred embodiment, the fluctuation amplitude and slope change rate are calculated for each time segment in the preliminary fluctuation candidate segment set to construct a joint fluctuation evaluation index set; the index vector corresponding to each time segment in the joint fluctuation evaluation index set is compared with the set evaluation threshold segment by segment to screen out time segments that meet the fracture drift triggering characteristics and mark them as candidate drift fracture segments;

[0021] The time segment covered by the candidate drift fault segment is used as the index window, and the edge segments whose triggering time falls into this segment in the time-driven edge set are filtered and aggregated into a causal mismatch path set;

[0022] The response path elimination operation is performed on the edge segments in the causal mismatch path set to remove the logical conflict relationship, reconstruct a revised causal chain graph that satisfies the structural temporal consistency, and synchronously update the path index mapping table corresponding to the response path structure; the revised causal chain graph is fed back to the drift segment data correction process.

[0023] In a preferred embodiment, a modified causal chain graph structure is retrieved, a set of edge segments corresponding to key drift segments is extracted, and the original timestamps, component node numbers, and response timing traces within the path structure contained in each pseudo-synchronization segment are parsed; the parsed response timing traces are combined with the original timestamps to construct a node response residual table, and a node lag probability assessment model is introduced as a constraint term for time offset correction;

[0024] A recursive error inversion algorithm is executed based on the node response residual table to derive the time correction function node by node. The time correction functions derived from all nodes are aggregated into a time correction function group to generate a path consistency index.

[0025] A topological logic consistency check is performed on the time correction function group to eliminate illegal function subsets with time reversal and path crossing, and retain the valid time adjustment function set under topological constraints.

[0026] In a preferred embodiment, a valid time adjustment function set selected by topological logic consistency check is applied to the pseudo-synchronization segment record, and the response time label of the node in the structural path is updated according to the time correction function corresponding to each node in the node response residual table; a new node triggering order is synchronously derived based on the updated response time label, and a node sequence mapping record is generated to reconstruct the temporal causal chain relationship between the nodes, forming a synchronously reconstructed data set that conforms to the coherence of the corrected structural path;

[0027] Insert the synchronously reconstructed data set into the time segment position of the corresponding pseudo-synchronization segment in the original monitoring data stream, and synchronously update the response path index mapping table to form a new structural response timing link;

[0028] The corrected response time labels and node sequence mapping records in the synchronously reconstructed data set are returned to the delay statistical parameter group. The delay characteristic records between devices are dynamically updated according to the time adjustment amplitude of each node and the change in the continuity of the trigger sequence. The overall timing consistency baseline is further superimposed and corrected to form the basis for cross-cycle time synchronization evaluation.

[0029] In a preferred embodiment, after each idle task execution cycle ends, based on the pseudo-synchronization segment screening results and the structural path reconstruction data recorded in the modified causal chain diagram generation process, statistics are collected on the triggering frequency of the synchronization instability segments that occurred in this cycle, the number of associated abnormal paths, and the stability change index of the modified structural response chain;

[0030] The synchronization instability segment triggering frequency, the number of associated abnormal paths, and the stability change indicators of the corrected structural chain obtained during each idle period are archived and organized to form a time series risk indicator set, which is used to record the cumulative number of synchronization instabilities, the correction success rate, and the trend of path stability changes;

[0031] Based on the archived time series risk indicator set, trend extrapolation analysis is performed. By fitting the evolution curves of the cumulative number of synchronous instabilities, the correction success rate, and the changing trend of path stability, the changing trajectory of synchronous instability risks in future cycles is predicted, and high-risk path groups are dynamically marked in advance according to the risk threshold.

[0032] In a preferred embodiment, for each device involved in a high-risk path group, the corresponding device item is located in the delay statistical parameter group, and its delay detection threshold and drift detection sensitivity configuration are dynamically adjusted to improve the ability to capture abnormal drift and the accuracy of identifying timing instability in high-risk path segments.

[0033] The dynamically adjusted delay detection parameters and drift detection sensitivity configuration of the high-risk path group are synchronously applied to the pseudo-synchronization segment screening, structure chain reconstruction and causal mismatch test process steps performed during the idle period of the next cycle, forming a continuous iterative cross-cycle risk accumulation detection and response calibration feedback mechanism.

[0034] In a preferred embodiment, a construction engineering risk assessment system for multi-source anomaly monitoring includes: an offset extraction module, a mismatch inference module, a synchronization correction module, and an early warning iteration module;

[0035] The offset extraction module analyzes the device-to-component node mapping and return delay characteristics based on multi-source monitoring data received during the idle task cycle. It then establishes a cross-device time alignment model and pseudo-synchronization segment time offset trajectory. It identifies potential abnormal path sets based on delay drift trends, providing a temporal feature foundation for subsequent structural anomaly reasoning and risk assessment.

[0036] The mismatch inference module derives the node triggering sequence and temporal causal chain based on the final pseudo-synchronization segment index matrix and channel path mapping. It then uses delay statistical analysis to identify time misalignment events and locate structural segments in the response chain with causal residual mismatches, providing support for pseudo-synchronization segment time correction and revised causal chain graph reconstruction.

[0037] The correction synchronization module is based on the correction causal chain graph, retrieves the response time and order of pseudo-synchronization segment nodes, derives and selects effective time correction functions, completes the correction of time tags and node triggering order, reconstructs the synchronization data set and updates the path index and delay characteristics, and achieves the continuity closure of the structural response chain and cross-cycle synchronization consistency;

[0038] The early warning iteration module archives the synchronization instability indicators of each period and constructs a time series risk indicator set. It predicts the evolution of synchronization instability risk based on the trend external driving dynamics, adjusts the high-risk path group detection parameters according to the prediction results, and continuously optimizes the cross-period pseudo-synchronization segment screening and structure chain correction process to form an iterative risk feedback system.

[0039] The technical effects and advantages of the present invention are as follows:

[0040] 1. By receiving multi-source monitoring data during idle task cycles and establishing a cross-device time alignment model, the present invention can effectively identify timing misalignment issues caused by mechanisms such as cache delays and packet loss retransmission. This prevents historical abnormal data from being misjudged as future risks, corrects the illusion of anomaly advance and retrospective tracing, and ensures the timeliness of structural warnings.

[0041] 2. This invention constructs pseudo-synchronization segment time offset trajectories, extracts potential abnormal paths based on drift trends, and combines node-level causal chain reasoning with time residual analysis to locate structural segments with timing breaks or causal mismatches in the response chain, thereby improving the integrity and continuity of the structural abnormality reasoning chain.

[0042] 3. By constructing pseudo-synchronization segment time offset trajectories, the present invention extracts potential abnormal paths based on drift trends. Combining node-level causal chain reasoning with time residual analysis, this method can locate structural segments with timing breaks or causal mismatches in the response chain, thereby improving the integrity and continuity of the structural abnormality reasoning chain.

[0043] 4. By archiving the synchronous instability indicators of each period, establishing a time series risk indicator set and performing trend extrapolation prediction, the present invention can dynamically adjust the detection parameters of the high-risk path group, and build an adaptive, iteratively optimized cross-period risk accumulation detection and feedback calibration system, thereby continuously improving the foresight of overall risk identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 The figure is a flow chart of the method steps of the present invention.

[0045] Figure 2 Schematic diagram of the system module of the present invention.

[0046] Figure 3 This is a flowchart of the multi-source data timing offset extraction method of the present invention.

[0047] Figure 4 This is a flowchart of the pseudo-synchronization segment causal chain mismatch inference of the present invention.

[0048] Figure 5 This is a flow chart of pseudo-synchronization segment time correction and synchronization reconstruction of the present invention.

[0049] Figure 6This is a flow chart of the cross-cycle synchronous instability risk prediction and feedback of the present invention. DETAILED DESCRIPTION

[0050] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0051] Refer to the instruction manual Figure 1-6 A construction project risk assessment method for multi-source anomaly monitoring according to an embodiment of the present invention includes:

[0052] Based on multi-source monitoring data received during the idle task cycle, the device-to-component node mapping and return delay characteristics are analyzed, and a cross-device time alignment model and pseudo-synchronization segment time offset trajectory are established. Potential abnormal path sets are identified through delay drift trends, providing a temporal feature basis for subsequent structural anomaly reasoning and risk assessment.

[0053] Based on the final pseudo-synchronization segment index matrix and channel path mapping, the node triggering sequence and time causal chain are derived. Combined with delay statistical analysis, time misalignment events are identified and structural sections with causal residual mismatches in the response chain are located. This provides support for pseudo-synchronization segment time correction and revised causal chain diagram reconstruction.

[0054] Based on the modified causal chain graph, the response time and order of pseudo-synchronous segment nodes are retrieved, the effective time correction function is derived and screened, the time label and node trigger order are corrected, the synchronization data set is reconstructed and the path index and delay characteristics are updated, and the structural response chain continuity closure and cross-cycle synchronization consistency are achieved;

[0055] Archive the synchronous instability indicators of each period and construct a time series risk indicator set. Predict the evolution of synchronous instability risk based on trend external driving dynamics. Adjust the detection parameters of high-risk path groups according to the prediction results. Continuously optimize the cross-period pseudo-synchronous segment screening and structural chain correction process to form an iterative risk feedback system.

[0056] The risk assessment monitoring platform collects raw monitoring records uploaded by heterogeneous monitoring devices when the platform is idle, extracts the device identification, timestamp, and channel protocol fields from the records, and forms a set of raw data tuples. Channel protocol classification and path identification grouping operations are performed on the raw data tuples to generate a device channel table and record the return start time and periodic interval of each channel.

[0057] The start time and periodic interval data of each channel returned in the device channel table are aggregated according to the device ID and timestamp to generate a reporting period sequence. Based on this, the three statistical indicators of average delay, range, and frequency hopping rate are calculated to generate a delay statistical parameter group.

[0058] The delay statistical parameter group is projected onto the global time axis, the time alignment difference map between devices is solved, the response drift trend is recorded, and the path set that forms a stable offset trend is extracted.

[0059] Based on the delay statistical parameter group and the time alignment difference map between devices, a deviation trajectory map is constructed. A set of paths whose continuous drift gradients exceed a stability threshold is identified. This set of paths is defined as a statistically unstable path group. This path group is then cross-analyzed with the alignment difference map to select paths that meet both trend anomaly and deviation amplitude exceeding a threshold, forming a potential abnormal path set.

[0060] Extract the time period response records corresponding to each path in the potential abnormal path set, and aggregate them according to the time window to generate a pseudo-synchronization segment candidate set. Then, screen the pseudo-synchronization segment candidate set for drift trend consistency and output the final pseudo-synchronization segment index matrix. The final pseudo-synchronization segment index matrix records the device number, start timestamp, and path identification information corresponding to each pseudo-synchronization interval, which serves as the basic data for subsequent path structure mapping and causal reasoning.

[0061] A response sequence distribution consistency check is performed on the time period corresponding to each pseudo-synchronization interval in the final pseudo-synchronization segment index matrix. The amplification characteristics of the drift residual change trend within the time period are evaluated, and candidate synchronization instability sections with drift amplitudes exceeding the set threshold are screened out. The candidate synchronization instability sections that pass the drift residual screening are further calibrated as key drift sections, and the corresponding time offset gradient and sensor node mapping relationship is recorded as the input basis for subsequent causal structure continuity verification.

[0062]

[0063] in:

[0064]

[0065] in represents the pseudo synchronization segment index matrix; τ i (t),τ j (t) represents the timestamp of the return of the i-th and j-th devices at time t; Δt i,j (t) represents the time offset between the i-th and j-th devices; Represents the channel connection relationship matrix between devices; Indicates the rate of change of the time offset; represents the acceleration of the time offset; λ and κ represent the first-order and second-order feature enhancement exponents, respectively; represents the dynamic modulation factor of the channel stability between device pair i, j; θ sync represents the pseudo-synchronous drift anomaly judgment threshold; Seg(·) represents the extraction of the time period set that meets the drift intensity judgment condition from the joint drift discrimination expression as the pseudo-synchronous offset segment extraction operation; Represents the operation of jointly traversing and extracting features from the sensor path combinations formed by all device pairs (i, j); Indicates the element-wise multiplication operation of two vectors of the same dimension or function results;

[0066] The above formula forms a comprehensive drift anomaly intensity index by jointly calculating the first-order derivative (drift rate) and second-order derivative (drift acceleration) characteristics of the time offset of the computing device and combining them with the channel stability weight. It can then identify the segments where the drift anomaly exceeds the set threshold on the continuous time axis and realize the extraction of pseudo-synchronous segments. The overall structure is designed to highlight the sudden change and aggravation characteristics in the drift evolution trend, supporting the subsequent pseudo-synchronous time window screening and abnormal path reasoning.

[0067] The device number recorded in the final pseudo-synchronization segment index matrix is ​​used as the index entry of the potential abnormal path response record. It is mapped to the corresponding component node through the path rules defined by the channel protocol classification and path identification grouping, and the component-level node sequence under the device channel path mapping is constructed.

[0068] The original timestamps of each node in the component-level node sequence are sorted sequentially to calibrate the triggering order of each node in the device path structure, which serves as the basis for constructing the timeline of the structural response chain. The device path mapping relationship is derived based on the path rules, the connection mode between component nodes is analyzed, the ordered structure of node connections is extracted, and a directional time-driven edge set is constructed as the basic edge set for causal reasoning.

[0069] Calculate the trigger interval for each node pair in the time-driven edge set, combine the device channel mapped by the node pair, the average delay and range parameters defined in the delay statistics parameter group, call the propagation delay fitting model of the corresponding channel, and generate a time residual vector;

[0070] The time residual vector is segmented according to a fixed time window, and the slope change value is continuously calculated based on the sliding window within each segment to form a slope change data sequence; the slope mutation points and slope reversal points are identified in the data sequence, and a set of landmark points with abnormal change trends is extracted; the time segments covered between adjacent landmark points are extracted to form a preliminary set of fluctuation candidate segments.

[0071] The fluctuation amplitude and slope change rate are calculated for each time segment in the preliminary fluctuation candidate segment set to construct a joint fluctuation evaluation index set. The indicator vector corresponding to each time segment in the joint fluctuation evaluation index set is compared with the set evaluation threshold segment by segment to screen out time segments that meet the fault drift triggering characteristics and mark them as candidate drift fault segments.

[0072] The time segment covered by the candidate drift fracture segment is used as the index window. The edge segments whose triggering time falls within the segment are screened in the time-driven edge set, and the set is aggregated into a causal mismatch path set to identify the structural path fracture area caused by response misalignment.

[0073] Perform response path elimination operation on the edge segments in the causal mismatch path set, remove the logical conflict relationship, reconstruct the modified causal chain graph that satisfies the structural temporal consistency, and synchronously update the path index mapping table corresponding to the response path structure; feed the modified causal chain graph back to the drift segment data correction process to correct the response record time label and close the causal reasoning path. Based on this definition represents the set of causal mismatch node paths;

[0074]

[0075] in,

[0076] Ψ u,v (t)=(τ u (t)-τ v (t));

[0077] where τ u (t), τ v (t) represents the timestamp of nodes u and v at time t respectively; Ψ u,v (t) represents the triggering time difference between node u and node v; represents the rate of change of node u to time difference; ζ and η represent the drift rate feature enhancement index and drift amplitude feature enhancement index respectively; ω u,v (t) represents the dynamic weight function of the edge weight of the node pair (u, v) at time t, which is used to measure the significance or importance of the causal relationship of the edge segment in the structural response path at the current moment. The unit is "dimensionless coefficient" or "weight coefficient / time" according to the specific physical quantity; θ mismatch represents the comprehensive threshold for mismatch determination; It represents a structural segment extraction function, which is used to filter out substructures that meet the causal chain mismatch condition from the global residual indicator set; It represents a set and union operation on the causal connection edges between all node pairs (u, v). In the entire structural response graph, it traverses all node pairs (u, v) with time-driven relationships, and collects the judgment expressions on each node pair into a set, thereby constructing an overall causal mismatch index.

[0078] exist In the formula, by calculating the first-order change rate of the node trigger time difference (drift rate anomaly) and the absolute time offset amplitude, superimposing the connectivity weighting, the trigger chain misalignment area caused by drift instability is screened out; the formula design structure is intended to dynamically capture the potential causal relationship breakpoints within the pseudo-synchronization segment, ensure the sensitivity and accuracy of the causal chain integrity test, and provide basic support for subsequent response correction and causal chain modification.

[0079] The modified causal chain graph structure is retrieved, and the edge segment set corresponding to the key drift segment is extracted. The original timestamp, component node number, and response timing trajectory within the path structure contained in each pseudo-synchronization segment are parsed. The parsed response timing trajectory is combined with the original timestamp to construct a node response residual table, and a node lag probability assessment model is introduced as a constraint term for time offset correction.

[0080] A recursive error inversion algorithm is executed based on the node response residual table to derive the time correction function node by node. The time correction functions derived from all nodes are aggregated into a time correction function group to generate a path consistency index for verifying the integrity of the structural correction.

[0081] A topological logic consistency check is performed on the time correction function group to eliminate illegal function subsets with time reversal and path crossing, and retain the valid time adjustment function set under topological constraints.

[0082] The effective time adjustment function set selected by the topological logic consistency check is applied to the pseudo-synchronization segment record. The response time label of the node in the structural path is updated according to the time correction function corresponding to each node in the node response residual table. The new node triggering order is deduced based on the updated response time label, and the node sequence mapping record is generated to reconstruct the temporal causal chain relationship between the nodes, forming a synchronous reconstructed data set that conforms to the coherence of the corrected structural path.

[0083] Insert the synchronously reconstructed data set into the time segment position of the corresponding pseudo-synchronization segment in the original monitoring data stream, and synchronously update the response path index mapping table to form a new structural response timing link;

[0084] The corrected response time labels and node sequence mapping records in the synchronously reconstructed data set are returned to the delay statistics parameter group. The inter-device delay characteristic records are dynamically updated based on the time adjustment amplitude of each node and the change in the trigger sequence consistency. The overall timing consistency baseline is further superimposed and corrected, forming the basis for cross-cycle time synchronization evaluation.

[0085]

[0086] in,

[0087] Φ u,v (t)=(τ u (t)+δ u )-(τ v (t)+δ v );

[0088] represents the optimization objective of synchronous dataset correction; τ u (t), τ v (t) represents the original timestamp of node u and node v at time t; δ u , δ v They represent the time correction offset of node u and node v respectively; Φ u,v (t) represents the residual error between node u and node v after correction; κ u,v (t) represents the connectivity weighting factor, which is used to adjust the synchronization importance between nodes; t s , t e Respectively represent the start and end time of the correction time window; Indicates that among all the optional time correction offset sets {δ u}, find the set of δ that minimizes the sum of the weighted terms of the subsequent integrals u Value combination; In addition, the fourth power in the formula is used to amplify the difference of timing offset error, which means that Φ u,v (t) Perform high-order power processing so that the larger the offset value, the more significant its impact on the overall optimization objective function, thereby strengthening the penalty effect on large offset paths and improving the sensitivity and selectivity of synchronous adjustment;

[0089] This formula accumulates the corrected time residuals of node pairs in the form of a fourth-power penalty and integrates them weighted by connectivity to globally optimize the set of correction quantities within the entire time window, thereby minimizing the structural chain synchronization error. The formula structure is designed to enhance the strong inhibitory effect on nodes with large synchronization offsets, while ensuring the closed consistency of the causal chain logic, supporting the reconstruction of the synchronization data set and the update of the path index.

[0090] After each idle task execution cycle ends, based on the pseudo-synchronization segment screening results and the structural path reconstruction data recorded in the modified causal chain diagram generation process, the triggering frequency of the synchronization instability segment that occurred in this cycle, the number of associated abnormal paths, and the stability change index of the modified structural response chain are counted;

[0091] The synchronization instability segment triggering frequency, the number of associated abnormal paths, and the stability change indicators of the corrected structural chain obtained during each idle period are archived and organized to form a time series risk indicator set, which is used to record the cumulative number of synchronization instabilities, the correction success rate, and the trend of path stability changes;

[0092] Based on the archived time series risk indicator set, trend extrapolation analysis is performed. By fitting the evolution curves of the cumulative number of synchronous instabilities, the correction success rate, and the changing trend of path stability, the changing trajectory of synchronous instability risks in future cycles is predicted, and high-risk path groups are dynamically marked in advance according to the risk threshold.

[0093] For each device involved in a high-risk path group, locate the corresponding device item in the delay statistics parameter group and dynamically adjust its delay detection threshold and drift detection sensitivity configuration to improve the ability to capture abnormal drift and the accuracy of identifying timing instability in high-risk path segments.

[0094] The dynamically adjusted delay detection parameters and drift detection sensitivity configuration of the high-risk path group are synchronously applied to the pseudo-synchronization segment screening, structure chain reconstruction, and causal mismatch detection process steps performed during the idle period of the next cycle, forming a continuous and iterative cross-cycle risk accumulation detection and response calibration feedback mechanism.

[0095]

[0096] represents the predicted value of synchronous instability risk trend; Σ instability (t) represents the curve of the cumulative number of synchronous instability up to time t; represents the third-order derivative of the synchronous instability trend, the acceleration change rate; χ(t) represents the synchronous instability sensitivity modulation function, which is used to adjust the risk response sensitivity; Υ(·) represents the high-order dynamic extrapolation function, which is used to estimate the synchronous instability trend in the future cycle;

[0097] This formula extracts the third-order derivative of the cumulative number of synchronous instability curves and, after weighted sensitivity adjustment, predicts the evolution trend of synchronous instability risks in future cycles. The purpose of designing the formula structure is to quickly respond to the acceleration and mutation characteristics of changes in instability trends, dynamically deduce the cross-cycle risk evolution situation, and guide the early warning and adaptive adjustment of detection strategies for synchronous instability risks.

[0098] A construction engineering risk assessment system for multi-source anomaly monitoring, comprising: an offset extraction module, a mismatch inference module, a synchronization correction module, and an early warning iteration module;

[0099] The offset extraction module analyzes the device-to-component node mapping and return delay characteristics based on multi-source monitoring data received during the idle task cycle. It then establishes a cross-device time alignment model and pseudo-synchronization segment time offset trajectory. It identifies potential abnormal path sets based on delay drift trends, providing a temporal feature foundation for subsequent structural anomaly reasoning and risk assessment.

[0100] The mismatch inference module derives the node triggering sequence and temporal causal chain based on the final pseudo-synchronization segment index matrix and channel path mapping. It then uses delay statistical analysis to identify time misalignment events and locate structural segments in the response chain with causal residual mismatches, providing support for pseudo-synchronization segment time correction and revised causal chain graph reconstruction.

[0101] The correction synchronization module is based on the correction causal chain graph, retrieves the response time and order of pseudo-synchronization segment nodes, derives and selects effective time correction functions, completes the correction of time tags and node triggering order, reconstructs the synchronization data set and updates the path index and delay characteristics, and achieves the continuity closure of the structural response chain and cross-cycle synchronization consistency;

[0102] The early warning iteration module archives the synchronization instability indicators of each period and constructs a time series risk indicator set. It predicts the evolution of synchronization instability risk based on the trend external driving dynamics, adjusts the high-risk path group detection parameters according to the prediction results, and continuously optimizes the cross-period pseudo-synchronization segment screening and structure chain correction process to form an iterative risk feedback system.

[0103] In the formula structure involved in this solution, dimensionless terms can serve as proportionality or structural adjustment factors. When combined with quantities with units, they only have a numerical scaling effect and do not introduce new physical dimensions. Therefore, they do not change or confuse the overall unit system of expression. This combination of "dimensionless terms and units" can be understood as a composite structural expression commonly used in mathematical and physical modeling, conforming to the principle of dimensional consistency and having a clear physical interpretation basis.

[0104] Secondly, in the formula structure of this scheme, if multiple variables with different physical units are involved, including but not limited to time, mass, or energy variables, their joint appearance is to express the collaborative modeling relationship of multiple physical mechanisms. Each variable is formed into a unified structure through function mapping, ratio combination, or normalization adjustment. The units and meanings are clear, and the overall expression conforms to the principle of dimensional consistency and the common formula of engineering modeling.

[0105] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A construction project risk assessment method for multi-source anomaly monitoring, characterized by: include: Based on multi-source monitoring data received during the idle task cycle, the device-to-component node mapping and return delay characteristics are analyzed, and a cross-device time alignment model and pseudo-synchronization segment time offset trajectory are established. Potential abnormal path sets are identified through delay drift trends, providing a temporal feature basis for subsequent structural anomaly reasoning and risk assessment. Based on the final pseudo-synchronization segment index matrix and channel path mapping, the node triggering sequence and time causal chain are derived. Combined with delay statistical analysis, time misalignment events are identified and structural sections with causal residual mismatches in the response chain are located. This provides support for pseudo-synchronization segment time correction and revised causal chain diagram reconstruction. Based on the modified causal chain graph, the response time and order of pseudo-synchronous segment nodes are retrieved, the effective time correction function is derived and screened, the time label and node trigger order are corrected, the synchronization data set is reconstructed and the path index and delay characteristics are updated, and the structural response chain continuity closure and cross-cycle synchronization consistency are achieved; Archive the synchronous instability indicators of each period and construct a time series risk indicator set. Predict the evolution of synchronous instability risk based on trend external driving dynamics. Adjust the detection parameters of high-risk path groups according to the prediction results. Continuously optimize the cross-period pseudo-synchronous segment screening and structural chain correction process to form an iterative risk feedback system.

2. The construction engineering risk assessment method for multi-source anomaly monitoring according to claim 1 is characterized by: The original monitoring records uploaded by various heterogeneous monitoring devices when the risk assessment monitoring platform is in idle state are collected, and the device identification, timestamp and channel protocol fields of the records are extracted to form a set of original data tuples. Channel protocol classification and path identification grouping operations are performed on the original data tuples respectively to generate a device channel table and record the return start time and periodic interval of each channel. The start time and periodic interval data of each channel returned in the device channel table are aggregated according to the device ID and timestamp to generate a reporting period sequence. Based on this, the three statistical indicators of average delay, range, and frequency hopping rate are calculated to generate a delay statistical parameter group. The delay statistical parameter group is projected onto the global time axis, the time alignment difference map between devices is solved, the response drift trend is recorded, and the path set that forms a stable offset trend is extracted.

3. The construction engineering risk assessment method for multi-source anomaly monitoring according to claim 2 is characterized by: Based on the delay statistical parameter group and the time alignment difference map between devices, a deviation trajectory map is constructed. A set of paths whose continuous drift gradients exceed a stability threshold is identified. This set of paths is defined as a statistically unstable path group. This path group is then cross-analyzed with the alignment difference map to select paths that meet both trend anomaly and deviation amplitude exceeding a threshold, forming a potential abnormal path set. Extract the time period response records corresponding to each path in the potential abnormal path set, and aggregate them according to the time window to generate a pseudo-synchronization segment candidate set. Then, screen the pseudo-synchronization segment candidate set for drift trend consistency and output the final pseudo-synchronization segment index matrix. The final pseudo-synchronization segment index matrix records the device number, start timestamp, and path identification information corresponding to each pseudo-synchronization interval, which serves as the basic data for subsequent path structure mapping and causal reasoning. A response sequence distribution consistency check is performed on the time period corresponding to each pseudo-synchronization interval in the final pseudo-synchronization segment index matrix, and the amplification characteristics of the drift residual change trend within the time period are evaluated. The candidate synchronization instability sections whose drift amplitude exceeds the set threshold are screened out, and the candidate synchronization instability sections that pass the drift residual screening are further calibrated as key drift sections, and the corresponding time offset gradient and sensor node mapping relationship is recorded.

4. The construction engineering risk assessment method for multi-source anomaly monitoring according to claim 3 is characterized by: The device number recorded in the final pseudo-synchronization segment index matrix is ​​used as the index entry of the potential abnormal path response record. It is mapped to the corresponding component node through the path rules defined by the channel protocol classification and path identification grouping, and the component-level node sequence under the device channel path mapping is constructed. The original timestamp of each node in the component-level node sequence is sorted sequentially to calibrate the triggering order of each node in the device path structure, which serves as the basis for constructing the timeline of the structural response chain; The device path mapping relationship is derived based on the path rules, the connection mode between component nodes is analyzed, the ordered structure of node connections is extracted, and a directional time-driven edge set is constructed; Calculate the trigger interval for each node pair in the time-driven edge set, combine the device channel mapped by the node pair, the average delay and range parameters defined in the delay statistics parameter group, call the propagation delay fitting model of the corresponding channel, and generate a time residual vector; The time residual vector is segmented according to a fixed time window, and the slope change value is continuously calculated based on the sliding window within each segment to form a slope change data sequence; the slope mutation points and slope reversal points are identified in the data sequence, and a set of landmark points with abnormal change trends is extracted; the time segments covered between adjacent landmark points are extracted to form a preliminary set of fluctuation candidate segments.

5. The construction engineering risk assessment method for multi-source anomaly monitoring according to claim 4 is characterized by: The fluctuation amplitude and slope change rate are calculated for each time segment in the preliminary fluctuation candidate segment set to construct a joint fluctuation evaluation index set. The indicator vector corresponding to each time segment in the joint fluctuation evaluation index set is compared with the set evaluation threshold segment by segment to screen out time segments that meet the fault drift triggering characteristics and mark them as candidate drift fault segments. The time segment covered by the candidate drift fault segment is used as the index window, and the edge segments whose triggering time falls into this segment in the time-driven edge set are filtered and aggregated into a causal mismatch path set; The response path elimination operation is performed on the edge segments in the causal mismatch path set to remove the logical conflict relationship, reconstruct a revised causal chain graph that satisfies the structural temporal consistency, and synchronously update the path index mapping table corresponding to the response path structure; the revised causal chain graph is fed back to the drift segment data correction process.

6. The construction engineering risk assessment method for multi-source anomaly monitoring according to claim 5 is characterized by: The modified causal chain graph structure is retrieved, and the edge segment set corresponding to the key drift segment is extracted. The original timestamp, component node number, and response timing trajectory within the path structure contained in each pseudo-synchronization segment are parsed. The parsed response timing trajectory is combined with the original timestamp to construct a node response residual table, and a node lag probability assessment model is introduced as a constraint term for time offset correction. A recursive error inversion algorithm is executed based on the node response residual table to derive the time correction function node by node. The time correction functions derived from all nodes are aggregated into a time correction function group to generate a path consistency index. A topological logic consistency check is performed on the time correction function group to eliminate illegal function subsets with time reversal and path crossing, and retain the valid time adjustment function set under topological constraints.

7. The construction engineering risk assessment method for multi-source anomaly monitoring according to claim 6 is characterized by: The effective time adjustment function set selected by the topological logic consistency check is applied to the pseudo-synchronization segment record. The response time label of the node in the structural path is updated according to the time correction function corresponding to each node in the node response residual table. The new node triggering order is deduced based on the updated response time label, and the node sequence mapping record is generated to reconstruct the temporal causal chain relationship between the nodes, forming a synchronous reconstructed data set that conforms to the coherence of the corrected structural path. Insert the synchronously reconstructed data set into the time segment position of the corresponding pseudo-synchronization segment in the original monitoring data stream, and synchronously update the response path index mapping table to form a new structural response timing link; The corrected response time labels and node sequence mapping records in the synchronously reconstructed data set are returned to the delay statistical parameter group. The delay characteristic records between devices are dynamically updated according to the time adjustment amplitude of each node and the change in the continuity of the trigger sequence. The overall timing consistency baseline is further superimposed and corrected to form the basis for cross-cycle time synchronization evaluation.

8. The construction engineering risk assessment method for multi-source anomaly monitoring according to claim 7 is characterized by: After each idle task execution cycle ends, based on the pseudo-synchronization segment screening results and the structural path reconstruction data recorded in the modified causal chain diagram generation process, the triggering frequency of the synchronization instability segment that occurred in this cycle, the number of associated abnormal paths, and the stability change index of the modified structural response chain are counted; The synchronization instability segment triggering frequency, the number of associated abnormal paths, and the stability change indicators of the corrected structural chain obtained during each idle period are archived and organized to form a time series risk indicator set, which is used to record the cumulative number of synchronization instabilities, the correction success rate, and the trend of path stability changes; Based on the archived time series risk indicator set, trend extrapolation analysis is performed. By fitting the evolution curves of the cumulative number of synchronous instabilities, the correction success rate, and the changing trend of path stability, the changing trajectory of synchronous instability risks in future cycles is predicted, and high-risk path groups are dynamically marked in advance according to the risk threshold.

9. The construction engineering risk assessment method for multi-source anomaly monitoring according to claim 8 is characterized by: For each device involved in a high-risk path group, locate the corresponding device item in the delay statistics parameter group and dynamically adjust its delay detection threshold and drift detection sensitivity configuration to improve the ability to capture abnormal drift and the accuracy of identifying timing instability in high-risk path segments. The dynamically adjusted delay detection parameters and drift detection sensitivity configuration of the high-risk path group are synchronously applied to the pseudo-synchronization segment screening, structure chain reconstruction and causal mismatch test process steps performed during the idle period of the next cycle, forming a continuous iterative cross-cycle risk accumulation detection and response calibration feedback mechanism.

10. A construction engineering risk assessment system for multi-source anomaly monitoring, comprising an offset extraction module, a mismatch inference module, a synchronization correction module, and an early warning iteration module, characterized in that: The offset extraction module analyzes the device-to-component node mapping and return delay characteristics based on multi-source monitoring data received during the idle task cycle. It then establishes a cross-device time alignment model and pseudo-synchronization segment time offset trajectory. It identifies potential abnormal path sets based on delay drift trends, providing a temporal feature foundation for subsequent structural anomaly reasoning and risk assessment. The mismatch inference module derives the node triggering sequence and temporal causal chain based on the final pseudo-synchronization segment index matrix and channel path mapping. It then uses delay statistical analysis to identify time misalignment events and locate structural segments in the response chain with causal residual mismatches, providing support for pseudo-synchronization segment time correction and revised causal chain graph reconstruction. The correction synchronization module is based on the correction causal chain graph, retrieves the response time and order of pseudo-synchronization segment nodes, derives and selects effective time correction functions, completes the correction of time tags and node triggering order, reconstructs the synchronization data set and updates the path index and delay characteristics, and achieves the continuity closure of the structural response chain and cross-cycle synchronization consistency; The early warning iteration module archives the synchronization instability indicators of each period and constructs a time series risk indicator set. It predicts the evolution of synchronization instability risk based on the trend external driving dynamics, adjusts the high-risk path group detection parameters according to the prediction results, and continuously optimizes the cross-period pseudo-synchronization segment screening and structure chain correction process to form an iterative risk feedback system.

Images