Engineering construction quality analysis system and method based on data processing

Abstract

The application discloses an engineering construction quality analysis system and method based on data processing, and belongs to the technical field of business data processing and intelligent decision-making, which comprises a causality graph construction module used for fusing multi-source monitoring data to construct a causality graph; a risk profile construction module used for reverse deduction and forward simulation to construct a forward-looking quality risk profile; a multi-objective collaborative optimization module used for solving a Pareto optimal balance solution set; a quality pre-control instruction generation module used for instantiating a dynamic quality pre-control instruction; an efficiency evaluation and attribution correction module used for updating the causality graph; and an evolution audit and causality knowledge distillation module used for auditing previous updates of the graph and distilling a core causality rule set. The application adopts the dynamic causality graph construction to perform risk deduction and simulation, and combines multi-objective optimization and closed-loop feedback correction, so that the forward-looking identification and collaborative intelligent pre-control of engineering quality risks can be realized.

Description

Technical Field

[0001] This invention relates to the field of business data processing and intelligent decision-making technology, and in particular to an engineering construction quality analysis system and method based on data processing. Background Technology

[0002] Construction quality analysis is a core component of project management, directly impacting building safety, lifespan, and investment returns. In modern business practice, project management increasingly relies on data-driven decision support systems. These systems aim to maximize business value by processing and analyzing the vast amounts of data generated throughout the project lifecycle to optimize resource allocation, control costs, shorten construction periods, and ensure project quality.

[0003] In existing technologies, construction quality management typically employs a building information model-based digital management platform, combined with on-site sensor networks to collect various monitoring data. Managers use these platforms to monitor construction progress, material consumption, and certain quality inspection indicators. Some platforms utilize statistical methods to analyze the collected data, triggering alarms when certain indicators exceed thresholds to aid in quality control decisions.

[0004] However, existing technological solutions still have significant shortcomings in data processing and decision support. Most remain at the level of isolated monitoring and post-event response for single or a few data dimensions, lacking the ability to deeply mine the complex causal relationships between multi-source data. Data is often fragmented, making it difficult to form a complete chain of evidence to reveal the root cause of quality problems. Therefore, when quality defects occur, decisions often rely on the engineer's personal experience, lacking forward-looking risk assessment and integrated optimization decision-making capabilities, resulting in low quality management efficiency and difficulty in effectively avoiding potential major quality risks caused by the coupling of multiple factors. Summary of the Invention

[0005] To address the aforementioned issues, this invention provides a data-processing-based engineering construction quality analysis system and method. It employs the construction of a dynamic causal relationship graph for risk extrapolation and simulation, and combines multi-objective optimization and closed-loop feedback correction to achieve proactive identification and collaborative intelligent pre-control of engineering quality risks.

[0006] The above objectives can be achieved through the following approach: A data-processing-based engineering construction quality analysis system includes a causal relationship graph construction module, used to acquire and align the process flow network and multi-source monitoring data in the building information model. The multi-source monitoring data includes material parameters, process parameters, quality inspection indicators, and environmental parameters. Using process sequence dependence and specification constraints as causal direction priors, the system statistically analyzes and estimates the weight parameters of each side, dynamically updating them to construct a causal relationship graph. A risk profile construction module is used to perform causal path backward deduction on the causal relationship graph, identify critical parameter combinations, use these combinations as simulation inputs, and perform forward boundary condition simulations on the causal relationship graph to verify and quantify cascading failure effects and their impact range, constructing a forward-looking quality risk profile. A multi-objective collaborative optimization module is used to take the cascading failure effects in the forward-looking quality risk profile as the core optimization objective function and extract resources and processes from the causal relationship graph. The order dependency relationship is used as a constraint to obtain the Pareto optimal equilibrium solution set in the multidimensional decision space. The quality pre-control instruction generation module is used to select the target strategy from the Pareto optimal equilibrium solution set and, in combination with the real-time status of the nodes in the causal relationship graph, instantiate the target strategy into a dynamic quality pre-control instruction. The effectiveness evaluation and attribution correction module is used to execute the dynamic quality pre-control instruction, compare the on-site effect data with the prediction results of the forward-looking quality risk profile, perform contribution tracing analysis on the causal relationship graph, and update the corrected causal link weights to the causal relationship graph. The evolution audit and causal knowledge distillation module is used to perform version control and difference analysis on the weight updates of the causal relationship graph, distill the core causal rule set from the causal links of the causal relationship graph, and combine the core causal rule set with the attribution correction records of each version of the graph to generate an evolution audit report.

[0007] Optionally, the causal relationship graph construction module includes: a process data fusion unit, used to attach the multi-source monitoring data as attribute information to the process flow network in the building information model as a structured skeleton, based on timestamps and spatial coordinates, to generate a temporal attribute network; a causal structure learning unit, used to apply causal testing to the temporal attribute network with the process temporal dependencies and the specification constraints as hard constraints, to test and determine the directed causal relationships between material parameters, process parameters, quality inspection indicators, and environmental parameters, and generate an initial causal topology; and a dynamic edge weight estimation unit, used to establish a dynamic regression algorithm for the initial causal topology, with source node parameters as independent variables and target node parameters as dependent variables, and to perform online iterative updates based on the multi-source monitoring data to obtain the causal relationship graph.

[0008] Optionally, the risk profile construction module includes: a quality failure definition unit, used to parse the engineering acceptance specifications and material performance standards in the building information model, and convert the quality requirement text into a quality failure vector; a causal chain reverse solution unit, used to perform a reverse traversal of the causal path on the causal relationship graph with the quality failure vector as the deduction endpoint, and solve for the critical parameter combination; and a boundary forward simulation unit, used to perform a time-series forward propagation simulation on the causal relationship graph with the critical parameter combination as the initial perturbation condition, verify and quantify the cascade failure effect and the scope of influence, and aggregate all simulation results to construct a forward-looking quality risk profile.

[0009] Optionally, the critical parameter set includes a process parameter set and a material parameter set, wherein: the process parameter set is used to define quality defects that will be triggered under extremely non-standard operation, including construction time, maintenance conditions, equipment operating thresholds and personnel operation procedures; the material parameter set is used to define quality defects that will be triggered under substandard material conditions, including material ratio, batch strength, environmental adaptability and aging degree.

[0010] Optionally, the multi-objective collaborative optimization module includes: an objective and constraint definition unit, used to transform the cascading failure effects in the forward-looking quality risk profile into a risk cost function, extract process logical dependencies and resource spatiotemporal mutual exclusion relationships from the causal relationship graph, and formalize them into nonlinear inequality constraints, which together constitute a multi-objective optimization space; and a Pareto front solution unit, used to collaboratively optimize the risk cost function, project duration, and resource consumption within the feasible region of the multi-objective optimization space, iteratively search for and generate a Pareto optimal equilibrium solution set.

[0011] Optionally, the system further includes: performing correlation analysis on each equilibrium solution in the Pareto optimal equilibrium solution set with the critical parameter combination, simulating and verifying the intervention effectiveness of the equilibrium solution, and generating a strategy risk cause mapping matrix.

[0012] Optionally, the quality pre-control instruction generation module includes: a target strategy selection unit, used to calculate and select the optimal equilibrium solution from the Pareto optimal equilibrium solution set as the initial target strategy; an instruction refinement matching unit, used to match the refined target strategy with the highest intervention effectiveness from the strategy cluster of the initial target strategy based on the strategy risk cause mapping matrix; and an instruction instantiation generation unit, used to call the real-time state snapshot of the causal relationship graph, obtain the current parameter value in the refined target strategy, and fill the real-time parameter value into the refined target strategy to instantiate and generate dynamic quality pre-control instructions.

[0013] Optionally, the performance evaluation and attribution correction module includes: a performance deviation quantification unit, used to continuously track on-site performance data after the dynamic quality pre-control instruction is issued, and compare it with the prediction results in the forward-looking quality risk profile to quantify the performance deviation; a causal contribution attribution unit, used to take the performance deviation as the starting point of analysis, trace the contribution on the causal relationship graph, identify and calculate the corrected causal links; and a graph online correction unit, used to perform gradient correction on the corrected causal links according to the contribution size, and update the causal relationship graph.

[0014] Optionally, the evolution audit and causal knowledge distillation module includes: a graph evolution path audit unit, used to record and store the weight update events of the causal relationship graph in a versioned manner, and to compare the differences in graph structure and weight parameters of different versions to construct a causal evolution path; and a core causal rule distillation unit, used to perform convergence analysis on the causal evolution path, extract and generalize to form a core causal rule set, and generate an evolution audit report in combination with the attribution correction record.

[0015] Based on the same inventive concept, this invention also provides a data processing-based method for analyzing the construction quality of engineering buildings. The method includes: acquiring and aligning the process flow network and multi-source monitoring data in a building information model (BIM), wherein the multi-source monitoring data includes material parameters, process parameters, quality inspection indicators, and environmental parameters; using process sequence dependence and specification constraints as causal priors; statistically analyzing and estimating and dynamically updating the weight parameters of each side to construct a causal relationship graph; performing causal path backward deduction on the causal relationship graph to identify critical parameter combinations; using the critical parameter combinations as simulation inputs; performing forward boundary condition simulation on the causal relationship graph to verify and quantify the cascade failure effects and their impact range; and constructing a forward-looking quality risk profile; using the cascade failure effects in the forward-looking quality risk profile as the core optimization objective function, and... The resource and process dependencies are extracted from the causal relationship graph as constraints, and a Pareto optimal equilibrium solution set is obtained in the multidimensional decision space. A target strategy is selected from the Pareto optimal equilibrium solution set, and combined with the real-time status of nodes in the causal relationship graph, the target strategy is instantiated as a dynamic quality pre-control instruction. The dynamic quality pre-control instruction is executed, and the on-site effect data is compared with the prediction results of the forward-looking quality risk profile. A contribution tracing analysis is performed on the causal relationship graph, and the corrected causal link weights are updated to the causal relationship graph. Version control and difference analysis are performed on each weight update of the causal relationship graph, and a core causal rule set is distilled from the causal links of the causal relationship graph. The core causal rule set is combined with the attribution correction records of each version of the graph to generate an evolutionary audit report.

[0016] Compared with the prior art, the present invention has the following advantages: 1. This invention achieves deep fusion and internal logic mining of multi-source heterogeneous data during the construction process by constructing a dynamically evolving causal relationship map. Compared with traditional methods that rely on experience or isolated data analysis, this invention can reveal the quantitative causal relationship between materials, processes, environment, and quality results, providing a scientific basis for tracing the root causes and accurately locating quality problems, and greatly improving the data-driven level of decision-making and the precision of management. 2. This invention proposes a forward-looking risk assessment mechanism based on causal deduction and forward simulation. By retrospectively identifying critical risk sources and forward simulating their cascading failure effects, potential quality defects can be pre-simulated and quantified before they occur, achieving a fundamental shift from passive post-event inspection to proactive pre-event control. This forward-looking risk management model significantly enhances the project's ability to withstand uncertainties and effectively reduces rework costs and schedule delays caused by quality issues. 3. This invention establishes a complete intelligent management process, from risk identification and multi-objective optimization decision-making to closed-loop feedback correction. By incorporating quality risks, project schedules, and resource consumption into a unified optimization framework, a Pareto-optimal strategy set is generated, providing managers with scientific and multi-dimensional decision support. Simultaneously, the performance evaluation and attribution correction modules ensure continuous learning and self-evolution from actual execution results, guaranteeing the long-term effectiveness and adaptability of the model and decisions, forming a virtuous cycle of sustainable improvement.

[0017] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures pointed out in the description, claims and drawings. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a framework diagram of the engineering construction quality analysis system based on data processing, according to an embodiment of the present invention.

[0020] Figure 2 This is a schematic diagram of the structure of the engineering construction quality analysis system based on data processing according to an embodiment of the present invention.

[0021] Figure 3 This is a schematic diagram of the causal relationship graph structure according to an embodiment of the present invention.

[0022] Figure 4 This is a time-series probability distribution cloud and rain diagram of risk evolution extrapolation in an embodiment of the present invention.

[0023] Figure 5 This is a schematic diagram of the multi-objective collaborative optimization decision space according to an embodiment of the present invention. Detailed Implementation

[0024] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0025] Reference Figure 1 One embodiment of the present invention proposes an engineering construction quality analysis system and method based on data processing. It adopts the construction of a dynamic causal relationship map for risk inference and simulation, and combines multi-objective optimization and closed-loop feedback correction to achieve forward-looking identification and collaborative intelligent pre-control of engineering quality risks.

[0026] like Figure 2 As shown, the system in this embodiment specifically includes: The causal relationship graph construction module is used to acquire and align the process flow network and multi-source monitoring data in the building information model. The multi-source monitoring data includes material parameters, process parameters, quality inspection indicators and environmental parameters. The module uses process sequence dependence and specification constraints as causal direction priors, statistically analyzes the weight parameters of each side for estimation and dynamic updating, and constructs the causal relationship graph. The risk profile construction module is used to perform causal path backward deduction on the causal relationship graph, identify critical parameter combinations, use the critical parameter combinations as simulation input, perform boundary condition forward simulation on the causal relationship graph, verify and quantify cascade failure effects and impact range, and construct a forward-looking quality risk profile. The multi-objective collaborative optimization module is used to take the cascading failure effect in the forward-looking quality risk profile as the core optimization objective function, and extract the resource and process dependency relationship from the causal relationship map as the constraint condition, and solve for the Pareto optimal equilibrium solution set in the multi-dimensional decision space. The quality pre-control instruction generation module is used to select a target strategy from the Pareto optimal equilibrium solution set and, in combination with the real-time status of the nodes in the causal relationship graph, instantiate the target strategy into a dynamic quality pre-control instruction. The performance evaluation and attribution correction module is used to execute the dynamic quality pre-control instructions, compare the on-site effect data with the prediction results of the prospective quality risk profile, perform contribution tracing analysis on the causal relationship graph, and update the corrected causal link weights to the causal relationship graph. The evolution audit and causal knowledge distillation module is used to perform version control and difference analysis on the weight updates of the causal relationship graph, distill the core causal rule set from the causal links of the causal relationship graph, and combine the core causal rule set with the attribution correction records of each version of the graph to generate an evolution audit report.

[0027] By constructing a dynamic causal relationship graph for risk extrapolation and simulation, and combining multi-objective optimization and closed-loop feedback correction, it is possible to achieve forward-looking identification and collaborative intelligent pre-control of engineering quality risks.

[0028] Optionally, the causal relationship graph construction module includes: The process data fusion unit is used to use the process flow network in the building information model as a structured skeleton, and to attach the multi-source monitoring data as attribute information to the process flow network according to timestamps and spatial coordinates to generate a time-series attribute network. Specifically, the data fusion unit first acquires the process flow network from the Building Information Modeling (BIM). This network, defined as a directed graph, outlines the sequence and logical dependencies of each construction process, serving as the structured framework for subsequent data fusion. Next, the unit collects multi-source monitoring data from the site in real time. This data covers material parameters, process parameters, quality inspection indicators, and environmental parameters, with each data point including a timestamp and spatial coordinates. The unit precisely attaches each monitoring data point to the corresponding process node in the process flow network, treating it as a dynamic attribute of that node. For example, concrete temperature data collected at a specific time and location will be associated with the concrete curing process node currently in progress. This process transforms the static process flow network into a temporal attribute network containing process and status information.

[0029] The causal structure learning unit is used to apply causal testing on the temporal attribute network with the process time dependence and the specification constraints as hard constraints, to test and determine the directed causal relationship between the material parameters, process parameters, quality inspection indicators and environmental parameters, and to generate an initial causal topology. Specifically, this causal structure learning unit performs causal discovery based on the temporal attribute network generated by the previous unit. This step uses recognized engineering process temporal dependencies and industry standard constraints as inviolable hard constraints, which predefine irreversible causal directions. For example, the quality of rebar tying inevitably affects the structural strength of subsequent concrete pouring, but the reverse is not true. Within this hard constraint framework, this unit applies causal testing algorithms, such as the Granger causality test, to analyze the attribute time series of each node in the temporal attribute network to test and determine whether there is a statistically significant directed causal relationship between the parameters. Through this testing process, the unit ultimately generates an initial causal topology in the form of a directed acyclic graph (DAG).

[0030] The dynamic edge weight estimation unit is used to establish a dynamic regression algorithm for the initial causal topology, with source node parameters as independent variables and target node parameters as dependent variables, and to perform online iterative updates based on the multi-source monitoring data to obtain a causal relationship map.

[0031] Specifically, the dynamic edge weight estimation unit establishes a dynamic regression algorithm for each directed edge in the initial causal topology to quantify its influence strength. In this embodiment, the algorithm is a Bayesian Dynamic Linear Model (BDLM). This model can not only estimate the magnitude of the causal effect but also quantify the uncertainty of the estimation results. For any target node, its state equation and observation equation can be expressed as: , In the formula, The value observed at the target node at time t is the quality inspection index. for The vector of source node parameter observations at time t, i.e., parameters such as materials, processes, and environment; for The state vector at time t is composed of the core element of the causal link weights to be estimated. To observe the noise, its variance Known; This is the state transition matrix, usually set as the identity matrix to represent the stationary evolution of the weights; The state evolution noise has a covariance matrix. The drastic change of weights over time is controlled, and these weights are preset based on historical data or expert experience. This unit utilizes the Kalman filter algorithm to adjust the state vector based on real-time multi-source monitoring data. The posterior distribution is updated online iteratively, and the updated posterior mean is used as the weight parameter of the corresponding edge in the causal relationship graph, such as... Figure 3 The diagram shown is a schematic of the causal relationship graph structure in this invention, illustrating the coupling between the physical layer, which serves as a spatial reference, and the causal layer, which represents the dependency relationship.

[0032] Optionally, the risk profile construction module includes: The quality failure definition unit is used to parse the engineering acceptance specifications and material performance standards in the building information model and convert the quality requirement text into a quality failure vector. Specifically, this quality failure definition unit aims to transform textual engineering specifications into machine-processable structured data. The unit automatically parses the engineering acceptance specifications and material performance standards documents contained in the BIM, extracting key quality requirements and their quantified thresholds, such as concrete compressive strength and rebar spacing error, using natural language processing technology. Subsequently, the unit organizes these key indicators into a multi-dimensional vector, namely the quality failure vector. Each dimension of this vector corresponds to a quality indicator, and its domain is the allowable deviation range between the actual measured value and the standard requirement value of that indicator. A quality failure is defined as when the quality inspection results of a certain process cause any one or more components of this vector to exceed the allowable range.

[0033] The causal chain reverse solution unit is used to perform a reverse traversal of the causal path on the causal relationship graph with the quality failure vector as the deduction endpoint, and solve for the critical parameter combination. Specifically, this causal chain reverse solving unit uses the final non-conforming result represented by the quality failure vector as the target endpoint for deduction. On the previously constructed causal relationship graph, starting from the result node representing the final quality inspection index, the unit traverses the path in the reverse direction along the directed edges. This traversal process traces back all its direct and indirect upstream influencing factor nodes, namely process parameters, material parameters, and environmental parameter nodes. By analyzing the weight parameters of each causal link in the graph, the unit can calculate the contribution of different upstream nodes to the final quality failure, thereby identifying the specific set of upstream input parameter values ​​that, when combined, are most likely to cause quality failure. These sets are defined as critical parameter combinations.

[0034] The boundary forward simulation unit is used to take the critical parameter combination as the initial perturbation condition, perform time-series forward propagation simulation on the causal relationship map, verify and quantify the cascade failure effect and the scope of influence, and aggregate all simulation results to construct a forward-looking quality risk profile.

[0035] Specifically, this boundary forward simulation unit uses the critical parameter combinations solved by the previous unit as the initial perturbation conditions for the simulation, inputting them into the corresponding source node of the causal relationship graph. Subsequently, the unit performs a time-series forward propagation simulation on the graph, that is, following the directed links of causal relationships, starting from the input end, progressively calculating and propagating the impact of parameter changes on downstream nodes. This process simulates how quality problems gradually evolve and amplify as construction procedures progress under critical conditions. Through this simulation, the unit can verify that the identified critical parameter combinations do indeed lead to the expected quality failures and accurately quantify the resulting cascading failure effects and their scope of influence. The unit simulates all identified critical parameter combinations and performs statistical aggregation analysis on all simulation results, ultimately constructing a comprehensive and forward-looking quality risk profile, such as... Figure 4 As shown, the time-series probability distribution cloud map of risk evolution in this invention demonstrates the dynamic evolution of the probability distribution of key risk indicators over time.

[0036] Optionally, the critical parameter combination includes: a set of process parameters and a set of material parameters, wherein: The set of process parameters is used to define quality defects that may be triggered under extremely non-standard operation, including construction time, maintenance conditions, equipment operating thresholds and personnel operation procedures; Specifically, the process parameter set aims to quantify the risks introduced during construction due to improper operational behavior or environmental control. The parameters in this set are derived from construction plans and operating procedures, defined by mapping standard requirements to boundary conditions of extreme non-standard operations. For example, construction time parameters are used to determine whether critical time interval requirements have been followed, such as the minimum curing period before formwork removal; curing conditions include a set of environmental monitoring values, such as temperature and humidity, with critical values ​​set within ranges that may lead to abnormal concrete hydration; equipment operating thresholds involve key operating parameters of construction machinery, such as the vibration frequency of a vibrator, with critical values ​​corresponding to operational settings that may cause insufficient structural compaction; and personnel operation procedures are represented by a series of quantifiable steps, with critical states corresponding to omissions or disordered sequences of key processes.

[0037] The set of material parameters is used to define quality defects that will be triggered under substandard material conditions, including material ratio, batch strength, environmental adaptability, and degree of aging.

[0038] Specifically, the material parameter set is used to quantify the potential risks arising from the fact that the properties of incoming raw materials or semi-finished products do not meet design requirements. The parameters in this set are derived from material performance standards and quality inspection reports. For example, the material proportioning parameter directly reflects the proportion of each component in the mixture, and its critical value is set within a non-standard proportion range that will significantly affect the performance of the final product; batch strength records the actual mechanical performance test results of a specific batch of materials, and its critical value is the value lower than the design strength requirement; environmental adaptability describes the performance stability of materials under specific field conditions, and its critical value corresponds to environmental conditions where performance declines sharply; aging degree quantifies the performance degradation of materials due to prolonged storage, and its critical value is defined as the state where the material performance is below the usable lower limit.

[0039] Optionally, the multi-objective collaborative optimization module includes: The objective and constraint definition unit is used to transform the cascading failure effect in the prospective quality risk profile into a risk cost function, extract the process logic dependency and resource spatiotemporal mutual exclusion relationship from the causal relationship graph, and formalize them into nonlinear inequality constraints, which together constitute a multi-objective optimization space. Specifically, the objective and constraint definition unit is responsible for mathematically formalizing the optimization problem. This unit first receives the cascading failure effects quantified in the forward-looking quality risk profile and transforms them into a computable risk cost function through a risk assessment function. This risk cost function maps the cascading failure effects to the expected value of economic losses. Simultaneously, this unit automatically extracts the logical dependencies between processes and the shared or exclusive use requirements of construction activities for resources from the previously constructed causal relationship graph. These relationships are formalized into a series of nonlinear inequality constraints. These constraints, together with the risk cost function, define the solution space of the multi-objective optimization problem.

[0040] The Pareto front solver unit is used to collaboratively optimize the risk cost function, project duration, and resource consumption within the feasible region of the multi-objective optimization space, and iteratively search and generate the Pareto optimal equilibrium solution set.

[0041] Specifically, this Pareto front solving unit iteratively searches within a multidimensional objective space comprised of the risk-cost function, total project duration, and total resource consumption, and within the constrained feasible region defined by the previous unit. Since these three objectives are typically conflicting, there is no single optimal solution. This unit employs a non-dominated sorting genetic algorithm (NSGA-II) to gradually approach and ultimately obtain a set of Pareto-optimal equilibrium solutions by continuously generating, evaluating, and selecting new candidate solutions. Each solution in this set is a Pareto optimal solution, meaning that without worsening any other objective, it is impossible to optimize any of these objectives further, such as... Figure 5The diagram shown is a schematic of the multi-objective collaborative optimization decision space in this invention, illustrating the trade-offs between the three optimization objectives of risk cost, project duration, and resource consumption, as well as the Pareto optimal frontier.

[0042] Optionally, the system further includes: Each equilibrium solution in the Pareto optimal equilibrium solution set is correlated with the critical parameter combination, and the intervention effectiveness of the equilibrium solution is verified by simulation, generating a strategy risk cause mapping matrix.

[0043] Specifically, to establish a clear correspondence between the optimal strategy and the specific risk sources it can intervene in, this process first performs a correlation analysis on each equilibrium solution in the Pareto optimal equilibrium solution set. This involves matching the process parameters and resource allocation adjustment suggestions included in each solution with the previously identified critical parameter combinations to identify the primary risk causes targeted by each equilibrium solution. Subsequently, for each associated "equilibrium solution-critical parameter combination" pair, the process executes a new forward simulation to verify the intervention effectiveness. That is, in a simulation with the critical parameter combination as the initial condition, the intervention measures defined by the equilibrium solution are simultaneously applied, and the simulation results before and after the intervention are compared to quantitatively evaluate the equilibrium solution's ability to suppress specific risks. Finally, the process integrates all simulation verification results to generate a strategy risk cause mapping matrix. The rows of this matrix represent each equilibrium solution, the columns represent all critical parameter combinations, and the element values ​​are the quantitative intervention effectiveness values ​​of the corresponding equilibrium solution for the corresponding critical parameter combination, thus clearly revealing the applicable scenarios and effectiveness of each alternative optimization strategy.

[0044] Optionally, the quality pre-control instruction generation module includes: The target strategy selection unit is used to calculate and select the optimal equilibrium solution from the Pareto optimal equilibrium solution set as the initial target strategy. Specifically, the target strategy selection unit receives a set of Pareto optimal equilibrium solutions generated by the multi-objective collaborative optimization module. To select an optimal equilibrium solution from this set, the unit employs a decision preference function. This function assigns different weights to the three optimization objectives—risk cost, project duration, and resource consumption—based on the core management objectives of the current project phase. By calculating the weighted composite score of each equilibrium solution, the unit selects the solution with the highest score as the initial target strategy. This strategy provides macro-level guidance for subsequent instruction generation.

[0045] The instruction refinement matching unit is used to match the refined target strategy with the highest intervention effectiveness from the strategy cluster of the initial target strategy based on the strategy risk cause mapping matrix. Specifically, the instruction refinement matching unit first obtains the root cause critical parameter combinations corresponding to the activated risks under the current operating conditions. Then, this unit queries the strategy risk cause mapping matrix generated in the previous step, analyzing the effectiveness of the initial target strategy on all critical parameter combinations it can intervene in. The unit identifies the specific adjustment measure with the highest intervention effectiveness for the currently activated critical parameter combinations within the strategy cluster corresponding to the initial target strategy, and determines this as the refinement target strategy. This step ensures that the finally generated instructions accurately target the root cause of the current quality risk.

[0046] The instruction instantiation generation unit is used to call the real-time state snapshot of the causal relationship graph, obtain the current parameter value in the refinement target strategy, and fill the real-time parameter value into the refinement target strategy to instantiate and generate dynamic quality pre-control instructions.

[0047] Specifically, the instruction instantiation generation unit receives the refined target strategy matched by the previous unit. To make it fully executable, this unit calls the causal relationship graph to obtain a real-time state snapshot of the nodes involved in the refined target strategy. For example, if the refined target strategy is "increase the curing temperature of concrete", this unit will query the temperature sensor readings at the corresponding locations in real time. Then, this unit fills these real-time parameter values ​​into the instruction template of the refined target strategy, and finally instantiates and generates a dynamic quality pre-control instruction that contains the specific execution object, quantification threshold, and operation sequence, and can be executed immediately.

[0048] Optionally, the performance evaluation and attribution correction module includes: The performance deviation quantification unit is used to continuously track the on-site performance data after the dynamic quality pre-control command is issued, and compare it with the prediction results in the forward-looking quality risk profile to quantify the performance deviation. Specifically, the performance deviation quantification unit is activated after the dynamic quality pre-control command is issued and executed. This unit continuously tracks the on-site effect data of various quality inspection indicators and process parameters related to the command. Subsequently, the unit accurately compares the collected on-site effect data with the simulation prediction results when constructing the forward-looking quality risk profile. By calculating the difference between the actual and predicted values, the unit quantifies a performance deviation, which truly reflects the gap between the actual and expected effects of the pre-control measures.

[0049] The causal contribution attribution unit is used to take the performance deviation as the starting point of analysis, trace the contribution on the causal relationship map, and identify and calculate the corrected causal links. Specifically, this causal contribution attribution unit uses the performance bias calculated by the previous unit as the starting point for analysis. It traces the contribution of each causal link back along the causal graph to identify the root cause of the bias. This unit employs a contribution analysis algorithm, starting from the node where the performance bias occurs and propagating the bias signal backward along the causal graph. During propagation, the unit calculates the contribution of each causal link to the final bias based on its weight, thereby locating the causal links whose weight parameters are most inconsistent with reality and calculating the corrected causal link weights.

[0050] The online graph correction unit is used to perform gradient correction on the corrected causal links according to the contribution level and update the causal relationship graph.

[0051] Specifically, this online correction unit updates the causal relationship graph online based on the results of the attribution analysis in the previous unit. This unit determines the step size and direction of the weight update based on the contribution of each identified causal link to be corrected. This update process uses a gradient correction method, fine-tuning the weights along the direction that reduces prediction error. The corrected causal link weights are updated in real time to the causal relationship graph, replacing the original weight values, thus completing one iteration of learning based on actual feedback.

[0052] Optionally, the evolution audit and causal knowledge distillation module includes: The graph evolution path auditing unit is used to record and store the weight update events of the causal relationship graph in a versioned manner, and to compare the differences in graph structure and weight parameters of different versions to construct the causal evolution path. Specifically, the graph evolution path auditing unit records and stores versioned updates each time the weights of the causal relationship graph are updated due to performance evaluation and attribution correction. Each update generates a new graph version and records the update time, triggering event, and details of weight changes before and after the update. By comparing these chronologically arranged graph versions, the unit can clearly track the historical changes in the weights of any causal link. By linking these update events together, a complete causal evolution path is constructed, recording the entire process of model cognition evolving over time.

[0053] The core causal rule distillation unit is used to perform convergence analysis on the causal evolution path, extract and generalize to form a core causal rule set, and generate an evolution audit report in combination with the attribution correction record.

[0054] Specifically, this core causal rule distillation unit performs convergence analysis on the causal evolution paths constructed in the previous unit. Its aim is to extract causal relationships from the specific, noisy causal link weights that have stabilized and have a significant impact after multiple iterative corrections. To quantify this stability, this unit calculates a rule stability index for each causal link, using the following formula: , In the formula, For nodes To the node The stability of the causal link rules; For this link in the most recent observation period Average weight within; For this link in the cycle The weighted standard deviation within the range characterizes its volatility; It is a smoothing constant used to prevent the denominator from being zero; This represents the total number of times the link has been updated. A decay factor, derived from expert experience, is used to ensure that the rule undergoes a sufficient number of validations. This unit identifies causal links with rule stability exceeding a preset threshold as core causal links and generalizes them into a set of core causal rules that are understandable to humans. Finally, this unit combines the extracted set of core causal rules with detailed records of each attribution correction to generate a structured evolutionary audit report.

[0055] Based on the same inventive concept, the present invention also provides a method for analyzing the construction quality of engineering buildings based on data processing, the method comprising: Acquire and align the process flow network and multi-source monitoring data in the building information model. The multi-source monitoring data includes material parameters, process parameters, quality inspection indicators and environmental parameters. Using process sequence dependence and specification constraints as causal direction priors, statistically analyze the weight parameters of each side for estimation and dynamic updating, and construct a causal relationship graph. The causal path is reversed on the causal relationship graph to identify critical parameter combinations. The critical parameter combinations are used as simulation inputs to perform forward simulation of boundary conditions on the causal relationship graph to verify and quantify the cascade failure effects and their scope of influence, and to construct a forward-looking quality risk profile. The cascading failure effect in the forward-looking quality risk profile is used as the core optimization objective function, and the resource and process dependency relationship is extracted from the causal relationship graph as the constraint condition. The Pareto optimal equilibrium solution set is obtained by solving in the multi-dimensional decision space. The target strategy is selected from the Pareto optimal equilibrium solution set and, in combination with the real-time status of the nodes in the causal relationship graph, the target strategy is instantiated into a dynamic quality pre-control instruction. Execute the dynamic quality pre-control command, compare the on-site effect data with the prediction results of the forward-looking quality risk profile, perform contribution tracing analysis on the causal relationship graph, and update the corrected causal link weights to the causal relationship graph; Version control and difference analysis are performed on each weight update of the causal relationship graph. The core causal rule set is distilled from the causal links of the causal relationship graph. The core causal rule set is combined with the attribution correction records of each version of the graph to generate an evolution audit report.

[0056] To verify the feasibility and effectiveness of this invention, it was applied to the main structure construction phase of a large-scale complex project. This project had extremely high requirements for the construction quality of concrete structures and steel reinforcement, and traditional management methods struggled to analyze quality defects caused by the coupling of multiple factors.

[0057] In this embodiment, the causal relationship graph construction module is activated first. Its process data fusion unit uses the process flow network defined in the Building Information Model (BIM) such as "rebar tying → formwork support → concrete pouring → curing" as a structured framework, and spatiotemporally matches and mounts the multi-source monitoring data collected on-site, generating a temporal attribute network. Subsequently, the causal structure learning unit uses industry standards as hard constraints and applies causal testing algorithms to analyze the statistical causal relationships between various parameters, generating an initial causal topology. Finally, the dynamic edge weight estimation unit quantitatively estimates the edge weights of each causal link through online iterative updates, obtaining a complete causal relationship graph.

[0058] Based on this map, the risk profile construction module is activated. Its quality failure definition unit analyzes the engineering acceptance specifications, defining "insufficient concrete compressive strength" as a quality failure vector. The causal chain reverse solution unit uses this as the endpoint for backward traversal, identifying a high-risk critical parameter combination, which is divided into a material parameter set and a process parameter set. The boundary forward simulation unit uses this critical parameter combination as initial conditions for forward simulation. The results show that this combination will lead to a cascading failure effect, ultimately resulting in an 85% probability that the 28-day strength of the concrete in this area will be lower than the design standard, thus constructing a forward-looking quality risk profile.

[0059] To address this risk, a multi-objective collaborative optimization module was activated. Its objective and constraint definition unit transformed the cascading failure effect into a risk cost function and defined optimization objectives and constraints such as project duration and resource consumption. The Pareto front solver iteratively searched and generated a set of Pareto optimal equilibrium solutions containing multiple strategies. Subsequently, simulations were performed to verify each equilibrium solution, generating a strategy risk cause mapping matrix.

[0060] The quality pre-control instruction generation module then starts. Its target strategy selection unit, based on the "quality first" principle, selects solution A, the lowest risk-cost option, from the Pareto optimal equilibrium solution set as the initial target strategy. The instruction refinement and matching unit queries the strategy risk cause mapping matrix and finds that the measure "replacing cement" in solution A has the highest intervention effectiveness against "insufficient cement stability," refining it into a refined target strategy. Finally, the instruction instantiation and generation unit calls the real-time state snapshot of the causal relationship graph to generate dynamic quality pre-control instructions.

[0061] After the command was executed, the performance deviation quantification unit of the performance evaluation and attribution correction module continuously tracked the data and found a 5% performance deviation between the actual intensity and the prediction. The causal contribution attribution unit traced the source and located a deviation in the causal link of "cement hydration rate". The online graph correction unit then performed gradient correction on the weight of this link and updated it to the causal relationship graph.

[0062] Finally, the evolution audit and causal knowledge distillation module performed version control and difference analysis on this and previous map updates, distilling the core causal rule set of "a certain brand of cement has an 8% faster hydration rate under specific temperature and humidity" from long-term stable causal links, and combined with attribution correction records to generate an evolution audit report, providing valuable knowledge assets for future projects.

[0063] Table 1. Examples of Construction Quality Risk Identification and Simulation Data Table 2. Examples of Data Representation for Multi-Objective Optimization and Pre-Control Command Generation Table 3. Examples of data representation for closed-loop feedback and causal relationship map updates As can be seen from the data in Tables 1-3 above, this invention demonstrates excellent analytical and pre-control capabilities in complex construction scenarios. Table 1 clearly shows that through causal inference and simulation, hidden risks such as "R002" caused by the coupling of multiple factors were successfully identified. Table 2 records the multi-objective optimization process, providing decision-makers with a scientific basis for trade-offs, and the final generated instructions are specific and executable. Table 3 verifies the closed-loop learning capability; by comparing the deviation between prediction and reality, the causal relationship map can be adaptively corrected, which allows the model accuracy to continuously improve with the increase of application time.

[0064] It should be noted that the formulas described above, through the principle of dimensional consistency and mathematical standardization methods (such as normalization, dimensionless parameter conversion, or unit system unification), can translate physical quantities with different properties into unitless standard values ​​or parameters that can be superimposed in the same dimension. This eliminates the interference of different dimensions on the computational logic, allowing the formulas to retain the original data distribution characteristics while possessing mathematical rationality and adaptability to objective laws. These are conventional technical methods and will not be elaborated further. The electrical connections between the various units described above do not necessarily represent direct or indirect connections; any indirect connection method is applicable to the embodiments of this invention as long as it achieves the purpose of this invention. The above descriptions are merely exemplary embodiments of this invention and should not be construed as limiting the scope of this invention.

[0065] All equivalent changes and modifications made in accordance with the teachings of this invention are still within the scope of this invention. Those skilled in the art will readily conceive of other embodiments of this invention upon considering the specification and the disclosure of practical truth. This application is intended to cover any variations, uses, or adaptations of this invention that follow the general principles of this invention and include common knowledge or conventional techniques in the art not described herein.

Claims

1. A construction quality analysis system based on data processing, characterized in that, The system includes: The causal relationship graph construction module is used to acquire and align the process flow network and multi-source monitoring data in the building information model. The multi-source monitoring data includes material parameters, process parameters, quality inspection indicators and environmental parameters. The module uses process sequence dependence and specification constraints as causal direction priors, statistically analyzes the weight parameters of each side for estimation and dynamic updating, and constructs the causal relationship graph. The risk profile construction module is used to perform causal path backward deduction on the causal relationship graph, identify critical parameter combinations, use the critical parameter combinations as simulation input, perform boundary condition forward simulation on the causal relationship graph, verify and quantify cascade failure effects and impact range, and construct a forward-looking quality risk profile. The multi-objective collaborative optimization module is used to take the cascading failure effect in the forward-looking quality risk profile as the core optimization objective function, and extract the resource and process dependency relationship from the causal relationship map as the constraint condition, and solve for the Pareto optimal equilibrium solution set in the multi-dimensional decision space. The quality pre-control instruction generation module is used to select a target strategy from the Pareto optimal equilibrium solution set and, in combination with the real-time status of the nodes in the causal relationship graph, instantiate the target strategy into a dynamic quality pre-control instruction. The performance evaluation and attribution correction module is used to execute the dynamic quality pre-control instructions, compare the on-site effect data with the prediction results of the prospective quality risk profile, perform contribution tracing analysis on the causal relationship graph, and update the corrected causal link weights to the causal relationship graph. The evolution audit and causal knowledge distillation module is used to perform version control and difference analysis on the weight updates of the causal relationship graph, distill the core causal rule set from the causal links of the causal relationship graph, and combine the core causal rule set with the attribution correction records of each version of the graph to generate an evolution audit report.

2. The engineering construction quality analysis system based on data processing according to claim 1, characterized in that, The causal relationship mapping construction module includes: The process data fusion unit is used to use the process flow network in the building information model as a structured skeleton, and to attach the multi-source monitoring data as attribute information to the process flow network according to timestamps and spatial coordinates to generate a time-series attribute network. The causal structure learning unit is used to apply causal testing on the temporal attribute network with the process time dependence and the specification constraints as hard constraints, to test and determine the directed causal relationship between the material parameters, process parameters, quality inspection indicators and environmental parameters, and to generate an initial causal topology. The dynamic edge weight estimation unit is used to establish a dynamic regression algorithm for the initial causal topology, with source node parameters as independent variables and target node parameters as dependent variables, and to perform online iterative updates based on the multi-source monitoring data to obtain a causal relationship map.

3. The engineering construction quality analysis system based on data processing according to claim 1, characterized in that, The risk profile construction module includes: The quality failure definition unit is used to parse the engineering acceptance specifications and material performance standards in the building information model and convert the quality requirement text into a quality failure vector. The causal chain reverse solution unit is used to perform a reverse traversal of the causal path on the causal relationship graph with the quality failure vector as the deduction endpoint, and solve for the critical parameter combination. The boundary forward simulation unit is used to take the critical parameter combination as the initial perturbation condition, perform time-series forward propagation simulation on the causal relationship map, verify and quantify the cascade failure effect and the scope of influence, and aggregate all simulation results to construct a forward-looking quality risk profile.

4. The engineering construction quality analysis system based on data processing according to claim 3, characterized in that, The critical parameter combination includes: a set of process parameters and a set of material parameters, wherein: The set of process parameters is used to define quality defects that may be triggered under extremely non-standard operation, including construction time, maintenance conditions, equipment operating thresholds and personnel operation procedures; The set of material parameters is used to define quality defects that will be triggered under substandard material conditions, including material ratio, batch strength, environmental adaptability, and degree of aging.

5. The engineering construction quality analysis system based on data processing according to claim 1, characterized in that, The multi-objective collaborative optimization module includes: The objective and constraint definition unit is used to transform the cascading failure effect in the prospective quality risk profile into a risk cost function, extract the process logic dependency and resource spatiotemporal mutual exclusion relationship from the causal relationship graph, and formalize them into nonlinear inequality constraints, which together constitute a multi-objective optimization space. The Pareto front solver unit is used to collaboratively optimize the risk cost function, project duration, and resource consumption within the feasible region of the multi-objective optimization space, and iteratively search and generate the Pareto optimal equilibrium solution set.

6. The engineering construction quality analysis system based on data processing according to claim 5, characterized in that, The system also includes: Each equilibrium solution in the Pareto optimal equilibrium solution set is correlated with the critical parameter combination, and the intervention effectiveness of the equilibrium solution is verified by simulation, generating a strategy risk cause mapping matrix.

7. The engineering construction quality analysis system based on data processing according to claim 6, characterized in that, The quality pre-control instruction generation module includes: The target strategy selection unit is used to calculate and select the optimal equilibrium solution from the Pareto optimal equilibrium solution set as the initial target strategy. The instruction refinement matching unit is used to match the refined target strategy with the highest intervention effectiveness from the strategy cluster of the initial target strategy based on the strategy risk cause mapping matrix. The instruction instantiation generation unit is used to call the real-time state snapshot of the causal relationship graph, obtain the current parameter value in the refinement target strategy, and fill the real-time parameter value into the refinement target strategy to instantiate and generate dynamic quality pre-control instructions.

8. The engineering construction quality analysis system based on data processing according to claim 1, characterized in that, The performance evaluation and attribution correction module includes: The performance deviation quantification unit is used to continuously track the on-site performance data after the dynamic quality pre-control command is issued, and compare it with the prediction results in the forward-looking quality risk profile to quantify the performance deviation. The causal contribution attribution unit is used to take the performance deviation as the starting point of analysis, trace the contribution on the causal relationship map, and identify and calculate the corrected causal links. The online graph correction unit is used to perform gradient correction on the corrected causal links according to the contribution level and update the causal relationship graph.

9. The engineering construction quality analysis system based on data processing according to claim 1, characterized in that, The evolution audit and causal knowledge distillation module includes: The graph evolution path auditing unit is used to record and store the weight update events of the causal relationship graph in a versioned manner, and to compare the differences in graph structure and weight parameters of different versions to construct the causal evolution path. The core causal rule distillation unit is used to perform convergence analysis on the causal evolution path, extract and generalize to form a core causal rule set, and generate an evolution audit report in combination with the attribution correction record.

10. A method for analyzing the quality of engineering construction based on data processing, applied to the engineering construction quality analysis system based on data processing as described in any one of claims 1-9, characterized in that, The method includes: Acquire and align the process flow network and multi-source monitoring data in the building information model. The multi-source monitoring data includes material parameters, process parameters, quality inspection indicators and environmental parameters. Using process sequence dependence and specification constraints as causal direction priors, statistically analyze the weight parameters of each side for estimation and dynamic updating, and construct a causal relationship graph. The causal path is reversed on the causal relationship graph to identify critical parameter combinations. The critical parameter combinations are used as simulation inputs to perform forward simulation of boundary conditions on the causal relationship graph to verify and quantify the cascade failure effects and their scope of influence, and to construct a forward-looking quality risk profile. The cascading failure effect in the forward-looking quality risk profile is used as the core optimization objective function, and the resource and process dependency relationship is extracted from the causal relationship graph as the constraint condition. The Pareto optimal equilibrium solution set is obtained by solving in the multi-dimensional decision space. The target strategy is selected from the Pareto optimal equilibrium solution set and, in combination with the real-time status of the nodes in the causal relationship graph, the target strategy is instantiated into a dynamic quality pre-control instruction. Execute the dynamic quality pre-control command, compare the on-site effect data with the prediction results of the forward-looking quality risk profile, perform contribution tracing analysis on the causal relationship graph, and update the corrected causal link weights to the causal relationship graph; Version control and difference analysis are performed on each weight update of the causal relationship graph. The core causal rule set is distilled from the causal links of the causal relationship graph. The core causal rule set is combined with the attribution correction records of each version of the graph to generate an evolution audit report.

Images