Engineering construction whole process digital management method and system

Abstract

The invention relates to the technical field of data processing, and discloses an engineering construction whole process digital management method and system. The method comprises the following steps: collecting and standardizing engineering construction full-period multi-source data; constructing a stacked integrated prediction system by using the standardized data to obtain a three-dimensional index prediction value; allocating resources based on the predicted value in combination with the ergonomics risk index to obtain a configuration scheme; uncertainty factors are quantified for the configuration scheme, an optimal scheme set is calculated through a multi-target symbiotic algorithm, and a management strategy is formed. According to the method, high-precision prediction of the engineering three-dimensional indexes is realized through the stacking integration algorithm, ergonomics risk assessment and resource allocation optimization are combined, and the technical defect that human factor engineering is neglected in a traditional method is overcome.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, in particular to an engineering construction whole-process digital management method and system. BACKGROUND

[0002] With the development of the construction industry, engineering construction management has gradually transformed from traditional paper document management to digitalization. Currently, most engineering construction projects have adopted partial digital management tools, such as CAD design software, BIM model technology, project management systems, etc., to realize the digital processing of individual links such as design, construction, supervision, etc. The application of these technologies has improved the efficiency of engineering construction to a certain extent, reduced human errors, and promoted information sharing and collaboration.

[0003] However, the existing engineering construction digital management has obvious limitations. First, most digital tools only target a specific stage or link of engineering construction, leading to a serious information island phenomenon, and data cannot be effectively circulated and shared between systems; second, there is a lack of unified data standards and management platforms throughout the engineering life cycle, making it difficult to manage and trace data from planning and design to completion and acceptance; third, the real-time response capability of existing systems for engineering changes, cost control, and progress monitoring is limited, and cannot meet the needs of rapid decision-making during construction; in addition, traditional digital tools usually focus on static data management, and lack real-time monitoring and early warning mechanisms in dynamic construction processes.

[0004] In view of the information fragmentation problem in the engineering construction process, especially in terms of engineering data collection standardization, real-time interaction of multiple parties, data security and integrity protection, intelligent decision support in complex scenarios, there is a lack of systematic technical path and effective tools. In addition, there is a lack of an adaptive framework that can integrate and stack prediction algorithms, ergonomic risk assessment, and multi-objective symbiotic optimization algorithms in real time, resulting in the inability to automatically adjust decision parameters and re-optimize subsequent construction stages when project deviations occur. SUMMARY

[0005] The present application provides an engineering construction whole-process digital management method and system, which realizes high-precision prediction of engineering three-dimensional indicators by stacking integrated algorithms, combines ergonomic risk assessment with resource allocation optimization, and solves the technical defects of traditional methods that ignore human factors engineering. Through a multi-objective symbiotic biological search algorithm, engineering uncertainty is processed, overcoming the difficulty of existing technologies in providing optimal decision-making solutions under multi-level uncertainty.

[0006] In a first aspect, the application provides a whole-process digital management method for engineering construction, comprising: collecting multi-source heterogeneous data of the whole life cycle of engineering construction and performing standardized processing to obtain a standardized engineering data set; constructing a stacked integrated prediction system using the standardized engineering data set, integrating output results of linear regression, support vector machines and neural networks through gradient boosting decision trees to obtain three-dimensional index prediction values of engineering time-cost-quality; according to the three-dimensional index prediction values, combining an engineering task ergonomics risk index calculated by a professional repetitive action method and allocating engineering resources to obtain a resource allocation scheme; quantifying engineering uncertainty factors based on the resource allocation scheme, calculating a scheme set under multi-level uncertainty through a multi-objective symbiotic organism search algorithm to obtain an engineering construction management strategy.

[0007] In a second aspect, the application provides a whole-process digital management system for engineering construction, comprising: a processing module configured to collect multi-source heterogeneous data of the whole life cycle of engineering construction and perform standardized processing to obtain a standardized engineering data set; an integration module configured to construct a stacked integrated prediction system using the standardized engineering data set, integrate output results of linear regression, support vector machines and neural networks through gradient boosting decision trees to obtain three-dimensional index prediction values of engineering time-cost-quality; a distribution module configured to combine an engineering task ergonomics risk index calculated by a professional repetitive action method and allocate engineering resources according to the three-dimensional index prediction values to obtain a resource allocation scheme; a quantification module configured to quantify engineering uncertainty factors based on the resource allocation scheme, calculate a scheme set under multi-level uncertainty through a multi-objective symbiotic organism search algorithm to obtain an engineering construction management strategy.

[0008] In a third aspect, a whole-process digital management device for engineering construction is provided, comprising: a memory and at least one processor, the memory storing instructions; the at least one processor invokes the instructions in the memory to enable the whole-process digital management device for engineering construction to perform the whole-process digital management method for engineering construction described above.

[0009] In a fourth aspect, a computer readable storage medium is provided, the computer readable storage medium storing instructions, when executed on a computer, enabling the computer to perform the whole-process digital management method for engineering construction described above.

[0010] The technical scheme provided in the application solves the technical problems of data fragmentation and non-uniform format in traditional engineering management by collecting multi-source heterogeneous data of the whole life cycle of engineering construction and performing standardized processing, so that data from different sources such as BIM models, cost systems, progress monitoring and quality detection can be integrated and analyzed in a unified platform to provide a data basis for subsequent intelligent decision-making. The establishment of standardized engineering data sets realizes the spatiotemporal consistency and semantic interoperability of engineering information, significantly reducing information loss and errors in the data conversion and interfacing process. On this basis, the application integrates three basic models with complementary performance, namely linear regression, support vector machine and neural network, by using a stacked ensemble prediction system, and integrates the multi-model prediction results by using a gradient boosting decision tree algorithm as a meta-learner, effectively solving the limitations of a single prediction model in the prediction of three-dimensional indexes of engineering time, cost and quality. The stacked ensemble architecture makes full use of the advantages of the linear regression model in capturing linear relationships, the ability of the support vector machine in processing nonlinear data and the advantages of the neural network in extracting high-dimensional feature complex interactions, and the comprehensive prediction results of multiple models significantly improve the prediction accuracy and provide a reliable basis for engineering management decision-making. The application innovatively introduces the occupational repetitive action method into the engineering resource allocation process, systematically considers the influence of the ergonomics risk index on the engineering execution efficiency, calculates the ergonomics risk index matrix of the engineering task and combines the three-dimensional index prediction value to optimize the resource allocation, effectively solving the technical defects of traditional resource allocation methods that ignore human factors, and improving the health and safety level of workers and work efficiency.

[0011] The application quantitatively models the engineering uncertainty factors based on the resource allocation scheme, applies an alpha-cut fuzzy set method to process uncertainty, and finds an optimal solution under multi-level uncertainty conditions through a multi-objective symbiotic biological search algorithm. The algorithm simulates the evolution of solutions in symbiotic relationships in nature and can find the best balance point between the three contradictory objectives of schedule, cost and quality, providing multi-scheme decision support for project managers under different risk preferences. Overall, the application realizes intelligent management of the whole process from data collection, prediction analysis and resource allocation to uncertainty processing, changes the traditional experience-based decision-making of engineering construction management to data-driven scientific decision-making, significantly improves the precision, scientificity and adaptability of engineering project management, and is particularly suitable for whole-process digital management of complex large-scale engineering projects. BRIEF DESCRIPTION OF DRAWINGS

[0012] In order to more clearly illustrate the technical solutions of the embodiments of the application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are some embodiments of the application, and other drawings can be obtained by those skilled in the art without creative labor.

[0013] Figure 1 Fig. 1 is an embodiment of the engineering construction whole process digital management method in the present application; Figure 2 Fig. 2 is an embodiment of the engineering construction whole process digital management system in the present application; Figure 3 Fig. 3 is a structural schematic diagram of the engineering construction whole process digital management device in the embodiment of the present application. DETAILED DESCRIPTION

[0014] The embodiment of the present application provides an engineering construction whole process digital management method and system. The terms "first", "second", "third", "fourth" and the like (if any) in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not have to be used to describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the term "comprising" or "having" and any variation thereof is intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0015] For the convenience of understanding, the specific process of the embodiment of the present application is described below, please refer to Figure 1 An embodiment of the engineering construction whole process digital management method in the present application includes: Step S101, collecting multi-source heterogeneous data of the whole life cycle of engineering construction and performing standardized processing to obtain a standardized engineering data set; Step S102, constructing a stacked integrated prediction system by using the standardized engineering data set, integrating the output results of linear regression, support vector machine and neural network by gradient boosting decision tree to obtain three-dimensional index prediction values of engineering time-cost-quality; Step S103, according to the three-dimensional index prediction values, combining the engineering task ergonomics risk index calculated by the repetitive action method and allocating engineering resources to obtain a resource allocation scheme; Step S104, quantifying the engineering uncertainty factors based on the resource allocation scheme, calculating the scheme set under multi-level uncertainty by a multi-objective symbiotic organism search algorithm to obtain an engineering construction management strategy.

[0016] It can be understood that the execution subject of the present application can be an engineering construction whole-process digital management system, and can also be a terminal or a server, and the specific embodiments are not limited herein. The embodiments of the present application take the server as an execution subject for example.

[0017] Specifically, multi-source heterogeneous data is collected by a distributed Internet of Things system, including design parameters, cost, progress, quality, safety and human resource data, to form original multi-source heterogeneous data. Subsequently, the data is subjected to outlier detection marking, cleaning processing, format conversion and space-time alignment, and then subjected to semantic unification processing, and finally constructed in the form of a graph database, a multi-dimensional index structure is established, and a standardized engineering data set is generated. This step solves the problems of information fragmentation and non-uniform data standards in traditional engineering management. Based on the standardized engineering data set, the system performs feature engineering processing, obtains an optimized feature set through feature selection and dimension reduction, and divides it into training, validation and test data sets. The training data set is used to train a linear regression model, a support vector machine regression model and a deep neural network model, respectively, and the parameter optimization and performance evaluation are performed through the validation and test data sets, and the prediction results of each model are obtained. Then the prediction results of the three models and the key features are input into the gradient boosting decision tree algorithm for ensemble learning, and the engineering time-cost-quality three-dimensional index prediction values are obtained. This stacking ensemble method overcomes the shortcomings of single model prediction accuracy.

[0018] The action complexity, risk level and environmental load of the engineering task are quantified to form task feature quantization data. Based on this, the ergonomic risk index of the engineering task is calculated using the occupational repetitive action method, and the professional qualifications, work experience, physical fitness test and historical project score data of the workers are collected to establish a numerical archive of worker capabilities. The ergonomic risk index and the three-dimensional index prediction values are combined to calculate the time, cost and quality prediction values of each worker-task combination to form the basis data for task allocation calculation. Through constructive random search and simulated annealing optimization, an optimal resource allocation scheme is generated under the premise of meeting the ergonomic risk threshold constraint. The problem of not considering ergonomic risk in traditional resource allocation is solved. The system establishes an engineering uncertainty factor library, classifies and encodes external and internal uncertainty factors, and uses the alpha-cut fuzzy set method to establish a mathematical model, which is combined with the resource allocation scheme to construct a three-dimensional index fuzzy mathematical model. Through the multi-objective symbiotic biological search algorithm, the three symbiotic relationships of mutual benefit, one-sided benefit and parasitism are simulated for iterative optimization, and the Pareto non-dominated sorting and crowding degree calculation are applied to screen out the optimal scheme set under different uncertainty levels to form the engineering construction management strategy. This solves the problem that traditional decision-making methods cannot effectively handle uncertainty.

[0019] In a specific embodiment, the process of performing step S101 can specifically include the following steps: The design parameter data, cost data, progress data, quality data, safety data, and human resource data are collected by a distributed Internet of Things system to obtain original multi-source heterogeneous data; The original multi-source heterogeneous data is subjected to outlier detection to obtain an outlier marked data set; The outlier marked data set is subjected to data cleaning to obtain a cleaned data set; The cleaned data set is subjected to format conversion and space-time alignment to obtain a format standardized data set; The format standardized data set is subjected to semantic unification to obtain a semantic standardized data set; The semantic standardized data set is constructed into a graph database form, a multi-dimensional index structure is established, and a standardized engineering data set containing attribute characteristics, time sequence characteristics, spatial characteristics, and relationship characteristics is obtained.

[0020] Specifically, multi-source heterogeneous data is collected by a distributed Internet of Things system. The system collects three-dimensional design parameter data by a BIM data collection module, collects cost data such as material cost and labor cost by a cost data collection module, collects progress data in real time by RFID technology and video recognition technology, collects quality data such as structural quality and material quality by non-destructive testing equipment and sensor networks, collects safety status data on site by infrared cameras and gas detectors, and collects human resource data such as worker position and working state by intelligent positioning systems and biometric technology, forming original multi-source heterogeneous data. The original multi-source heterogeneous data is subjected to outlier detection, and the data is marked by a density clustering algorithm (DBSCAN). The algorithm divides data points by density, automatically identifies whether a data point is a core point, a boundary point, or a noise point by setting two parameters of neighborhood radius and minimum point number. For example, when detecting cost data, data that exceeds a preset range (such as a sudden large fluctuation in the cost of a certain material) is marked as an outlier, and an outlier marked data set is obtained.

[0021] Subsequently, the outlier marked data set is subjected to data cleaning, and a moving average filtering algorithm is used to remove noise. The algorithm replaces the original value with the average of several points before and after the data point to smooth the data fluctuation. For the marked abnormal data, correction (such as replacing with the average) or rejection processing is performed, and a cleaned data set is obtained. The cleaned data set is subjected to format conversion and space-time alignment, and different source data is uniformly converted to JSON format and aligned to a unified coordinate system through timestamps and spatial reference points. For example, IFC format design data exported by BIM software and Excel format cost data are both converted to JSON format, and are associated according to engineering component ID and time point, and a format standardized data set is obtained.

[0022] Then the format standardized dataset is semantically unified, and the semantic interoperability of data in different fields is realized by establishing a unified ontology model. The ontology model defines the core concepts in the engineering field and their relationships, such as the association between components and materials, cost, construction period, etc. This enables data from different sources to be semantically interoperable, resulting in a semantically standardized dataset. The semantically standardized dataset is constructed as a graph database, and a multi-dimensional index structure is established. The graph database uses nodes and relationships to form a network structure, with engineering components as nodes, spatial relationships and time sequence relationships between components as edges, forming a network structure. At the same time, attribute feature indexes (by material type, cost interval, etc.), time sequence feature indexes (by planned construction period, actual progress, etc.), spatial feature indexes (by location coordinates, spatial relationships, etc.), and relationship feature indexes (by dependency relationships, influence relationships, etc.) are established, resulting in a standardized engineering dataset that solves the problem of information fragmentation and data fragmentation in traditional engineering management.

[0023] In a specific embodiment, the process of performing step S102 can specifically include the following steps: Feature engineering is performed on the standardized engineering dataset to obtain an optimized feature set through feature selection and feature dimensionality reduction; The optimized feature set is divided into a training set, a validation set, and a test set to obtain a model training dataset, a model validation dataset, and a model test dataset; A linear regression model is trained using the model training dataset, and a regularization method is used to process the feature weights to obtain a linear prediction model; The linear prediction model is parameterized using the model validation dataset, and the model performance is evaluated using the model test dataset to obtain a linear prediction result; Support vector machine regression and deep neural network models are trained on the model training dataset, and the parameters are optimized using the model validation dataset to obtain support vector machine prediction results and neural network prediction results; The linear prediction result, support vector machine prediction result, and neural network prediction result are used as input features, combined with key features in the optimized feature set, and integrated learning is performed through a gradient boosting decision tree algorithm to obtain engineering time-cost-quality three-dimensional index prediction values.

[0024] Specifically, the feature selection technique is used to identify the features most strongly related to the three-dimensional indicators of engineering time, cost, and quality. By calculating the Pearson correlation coefficient of each feature and the target variable, features with an absolute correlation coefficient greater than 0.3 are selected, and the variance inflation factor is used to remove features with multicollinearity, such as merging design parameter features and cost features with a similarity of more than 80%. Then, principal component analysis is used for feature dimension reduction, projecting high-dimensional features into a low-dimensional space, retaining principal components with a cumulative contribution rate of 95%, and obtaining an optimized feature set. The optimized feature set is divided according to time sequence, with the first 70% of the data selected as the model training data set, the middle 10% as the model validation data set, and the last 20% as the model test data set. This time sequence division method ensures that the model can learn the time evolution law in the engineering construction process and avoids data leakage.

[0025] The linear regression model is trained using the model training data set, and the ridge regression form of regularization method is used to process the feature weights, introducing a penalty term for each feature to control the model complexity. The objective function of the linear regression model includes the mean square error term and the L2 regularization term, and the feature weight value is obtained by minimizing the objective function to form a linear prediction model.

[0026] The linear prediction model is parameterized using the model validation data set, mainly adjusting the regularization strength parameter λ, setting a series of candidate values on a logarithmic scale from 0.001 to 100, and selecting the λ value with the smallest root mean square error on the validation set as the optimal parameter. Then, the model performance is evaluated using the model test data set, calculating the root mean square error, mean absolute error, and determination coefficient of the predicted value and the actual value to obtain the linear prediction result. The support vector machine regression model and the deep neural network model are trained in parallel using the model training data set. The support vector machine regression model uses a radial basis kernel function to handle nonlinear relationships, and the optimal combination of the penalty factor C and the kernel function parameter γ is determined by grid search. The deep neural network model constructs a four-layer network structure, with the input layer corresponding to the feature dimension, two hidden layers with different node numbers, and the output layer corresponding to the three-dimensional indicators. The LeakyReLU activation function and the AdamW optimizer are used, with a learning rate of 0.001. The learning rate, batch size, and hidden layer node number are adjusted using the model validation data set, and the support vector machine prediction result and the neural network prediction result are obtained. The linear prediction result, the support vector machine prediction result, and the neural network prediction result are used as first-order features, combined with key features in the optimized feature set (such as engineering volume, construction process complexity, and material supply stability), and input into the gradient boosting decision tree meta-learner. The meta-learner iteratively trains multiple decision trees, with each tree learning the residual error of the previous round of prediction, and finally combines the prediction results of all trees with weighted combination to obtain more accurate engineering time-cost-quality three-dimensional indicator prediction values.

[0027] In a specific embodiment, the process of performing step S103 can specifically include the following steps: The action complexity, risk level and environmental load of each engineering task are quantified, and the specific numerical scores are calculated and weighted to obtain the task characteristic quantification data table; Based on the task characteristic quantification data table, the actual frequency, strength factor, posture factor, additional factor and recovery factor of technical action are calculated using the occupational repetitive action method, and a comprehensive operation is performed to obtain the engineering task ergonomics risk index matrix; Collect the professional qualification certificate level, work experience data, physical test results and historical project completion quality scores of each worker to form a structured data record and obtain the worker capability numerical profile; The engineering task ergonomics risk index matrix is associated with the three-dimensional index prediction value to generate the completion time value, cost consumption value and quality score prediction value of each worker-task combination to obtain the task allocation calculation basis data set; Perform a constructive random search operation on the task allocation calculation basis data set, and arrange and combine the workers and tasks through iterative calculation to minimize the total duration value, total cost value and maximize the total quality score, with the boundary condition that the total ergonomics risk score does not exceed the safety threshold, to obtain the initial digital resource allocation table; Perform a local search optimization calculation on the initial digital resource allocation table, adjust the solution set through a simulated annealing calculation process with gradually decreasing temperature parameters, and retain the optimal solution in each iteration to obtain the resource allocation scheme.

[0028] Specifically, the action complexity is scored in two dimensions of action number and body load. The action number is counted according to the total number of standard actions required to complete each task, such as bending, lifting, twisting, etc. in the steel bar binding task, each action is valued according to its frequency; the body load is divided into mild (1 point), moderate (3 points) and severe (5 points) according to the physical strength consumed by the action. The risk level is determined by the product of the probability of safety accidents and the degree of loss, both of which adopt 1-5 point system, such as the probability score of high-altitude operation is 4, and the loss degree score is 5. The environmental load considers the influence of environmental factors such as noise, temperature and humidity on workers, which is quantified by 1-5 point system. The scores of the three dimensions are weighted and summarized according to the proportion of 4:4:2 to form the comprehensive score, and the task characteristic quantization data table is obtained. Based on the task characteristic quantization data table, the engineering task ergonomics risk index is calculated by using the occupational repetitive action method (OCRA). First, the actual frequency of technical action is calculated, that is, the number of actions completed per unit time; then the strength factor is determined, which is scored according to the percentage of the required strength in the maximum autonomous strength; then the posture factor is evaluated, which is valued according to the degree of deviation of the working posture from the ideal position of ergonomics; then the additional factor is determined, considering vibration, accuracy requirements, etc.; finally, the recovery factor is calculated, which is determined according to the ratio of work and rest. The five factors are comprehensively calculated, the actual frequency of technical action is multiplied by the strength factor, posture factor and additional factor, and then divided by the recovery factor to obtain the OCRA index, and an engineering task ergonomics risk index matrix is constructed. The professional qualification certificate level, work experience data, physical test results and historical project completion quality scores of each worker are collected to form a worker's ability numerical file. The professional qualification certificate level is divided into primary (1 point), intermediate (3 points) and advanced (5 points) according to the national occupation qualification standard; the work experience data is recorded according to the actual years of experience, and is converted to ability score according to the experience curve; the physical test results include the comprehensive score of strength, endurance and flexibility; the historical project completion quality score is calculated by averaging the quality acceptance data of the worker's past projects.

[0029] The ergonomic risk index matrix for engineering tasks is correlated with the predicted values ​​of three-dimensional indicators to generate a basic dataset for task allocation calculations. The specific process involves matching each worker's capability data with the risk index of each task, determining the worker's efficiency coefficient for performing a specific task. This efficiency coefficient is then applied to standard duration, standard cost, and standard quality indicators to generate personalized time, cost, and quality predictions. For example, a highly skilled worker performing a high-risk task may achieve shorter time, slightly higher cost, and better quality, while a novice worker performing the same task may experience longer time, slightly lower cost, and lower quality. A constructive random search operation is performed on the basic dataset for task allocation calculations, iteratively permuting workers and tasks. The algorithm first generates an initial solution using a greedy strategy, prioritizing workers to their most skilled tasks. It then randomly replaces some worker-task assignments and checks whether they meet the multi-objective optimization criteria of minimizing total duration, minimizing total cost, and maximizing quality, while ensuring that the total ergonomic risk score does not exceed a safety threshold. The optimal solution is retained after each iteration, and after multiple rounds of iterations, an initial digital resource allocation table is obtained. Local search optimization is performed on this initial digital resource allocation table, and a simulated annealing algorithm is used to adjust the solution set. The algorithm sets an initial temperature parameter and, during the high-temperature phase, accepts a wide range of suboptimal solutions to escape the local optimum. As the temperature gradually decreases, the adjustment strategy becomes more conservative, ultimately accepting only the more optimal solutions during the low-temperature phase. Throughout this process, the optimal solution from each iteration is retained to form the final resource allocation plan.

[0030] In a specific embodiment, the process of executing step S104 may specifically include the following steps: Establish an engineering construction uncertainty factor library, identify external and internal uncertainty factors, and classify and code them to obtain a structured dataset of uncertainty factors; The α-cut fuzzy set method is used to mathematically model each factor in the structured data set of uncertainty factors, and each uncertainty factor is converted into a fuzzy numerical value with a membership function to obtain a fuzzy mathematical model of uncertainty factors. Combining the fuzzy mathematical model of uncertainty factors with the resource allocation plan, the fuzzy duration calculation matrix, fuzzy cost calculation matrix and fuzzy quality calculation matrix are constructed to obtain the fuzzy mathematical model of the three-dimensional engineering indicators taking into account uncertainty. Initialize the ecosystem of the multi-objective symbiotic search algorithm, create multiple candidate solutions and assign fitness values ​​to each solution to obtain an initial solution set; The initial solution set is iterated by simulating three symbiotic mechanisms: mutual benefit, unilateral benefit, and parasitic relationship. Mutual benefit generates a new solution by combining the advantages of two solutions, unilateral benefit generates an improved solution by influencing one solution on another, and parasitic relationship replaces the existing solution through random mutation to obtain the evolved solution set. The Pareto non-dominated sorting and crowding degree calculation are applied to the evolved solution set to screen out the non-dominated optimal solutions with the shortest duration, the lowest cost and the highest quality under different α levels, form multiple groups of optimal schemes, and obtain the construction management strategies.

[0031] Specifically, by collecting historical engineering project data, key events leading to delay, cost increase and quality decline are extracted. Events are extracted from project anomaly records, change application documents and engineering summary reports through text mining technology to form an uncertain original data set. Then hierarchical clustering analysis is performed on these data, and the similarity between different factors is calculated using the complete connection method. Factors with a similarity higher than a preset threshold are classified into a class to obtain the classification results of uncertain factors. Then the factors are divided into two categories: external uncertainty and internal uncertainty. External uncertainty includes extreme weather (such as the impact of heavy rain and high temperature on open-air construction), policy changes (such as adjustment of environmental protection standards) and market fluctuations (such as fluctuations in the prices of materials such as steel and cement); internal uncertainty includes resource supply fluctuations (such as delays in the arrival of key equipment), technical changes (such as design scheme adjustments) and personnel flow (such as the resignation of skilled workers). The influence degree of each type of uncertain factor is quantified. The numerical values of three dimensions, i.e. influence intensity, occurrence probability and duration, are calculated through expert scoring method and historical data statistical analysis, and each type of factor is assigned a unique identification code to establish the correlation diagram between factors, and finally a structured data set of uncertain factors is formed.

[0032] Each factor in the structured dataset of uncertainty factors is mathematically modeled using the α-cut fuzzy set method. This method represents each uncertainty factor as a fuzzy number with a membership function that describes the degree of membership of a value to the uncertainty factor, with the value ranging from 0 to 1. The minimum possible value, the most likely value, and the maximum possible value of each factor are determined through historical data analysis, and a triangular membership function is constructed. Then, the interval value of the fuzzy number is calculated at different α levels (α values range from 0 to 1). The larger the α value, the narrower the interval, indicating less uncertainty. For example, for the uncertainty factor "heavy rain weather," α = 0 can result in a delay of 0-7 days, α = 0.5 can result in a delay of 2-5 days, and α = 1 can result in a fixed delay of 3 days. In this way, all uncertainty factors are represented as fuzzy numerical values with multiple levels of uncertainty, forming a fuzzy mathematical model of uncertainty factors. The fuzzy mathematical model of uncertainty factors is combined with the resource allocation scheme to construct a fuzzy mathematical model of engineering three-dimensional indicators considering uncertainty. First, the fuzzy calculation is performed on the duration calculation in the resource allocation scheme, combining the deterministic duration with the duration delay value affected by the uncertainty factor through fuzzy addition operation to form a fuzzy duration calculation matrix. Similarly, fuzzy arithmetic operations are applied to cost and quality calculations to form fuzzy cost calculation matrix and fuzzy quality calculation matrix, respectively. For example, the deterministic duration of a certain construction task is 10 days, but affected by the uncertainty factor "technician resignation," the actual duration is a fuzzy number 10 + [2, 5] days, i.e. 12-15 days, at an uncertainty level of α = 0.3. Through similar calculations, a complete fuzzy mathematical model of engineering three-dimensional indicators is obtained, which reflects the possible value range of engineering time, cost, and quality at different uncertainty levels.

[0033] When initializing the multi-objective symbiotic organism search algorithm, first set the population size and iteration number parameters, then generate multiple initial candidate solutions in the solution space through Latin hypercube sampling. Each candidate solution represents a resource allocation and engineering implementation strategy, and its fitness is evaluated by calculating its duration, cost, and quality fuzzy indicator values at different α levels to form an initial solution set family. The multi-objective symbiotic organism search algorithm is an evolutionary algorithm that simulates the symbiotic relationship between organisms, and optimizes the solution set family through three types of symbiotic relationships. In the mutual benefit relationship, two solutions are randomly selected, and their midpoint is calculated as a new solution. If the new solution is better than the original solution, replace the original solution; in the one-sided benefit relationship, one solution learns from another, but only the beneficiary is updated; in the parasitic relationship, a solution is copied and randomly mutated in a dimension. If the mutated solution is better than the original solution, replace the original solution. Through the alternating action of these three mechanisms, the solution set family gradually evolves towards the optimal direction.

[0034] The Pareto non-dominated sorting and crowding distance calculation are applied to the evolved solution set. The Pareto non-dominated sorting ranks the solutions according to the dominance relationship. If one solution is not worse than another solution in all objectives and better in at least one objective, the first solution is said to dominate the second solution. A non-dominated solution is a solution that is not dominated by any other solution. The crowding distance calculation measures the distance between solutions to maintain the diversity of solutions. Through these two steps, the non-dominated optimal solutions with the shortest duration, the lowest cost and the highest quality under different alpha levels (such as alpha = 0.2, 0.5, 0.8) are screened out to form multiple groups of optimal schemes, and finally a complete set of engineering construction management strategies is obtained.

[0035] In a specific embodiment, the process of identifying external uncertainty and internal uncertainty factors can specifically include the following steps: Collecting abnormal event records and change application data of historical engineering projects, extracting key events that cause delay, cost increase and quality decline from the data to obtain an uncertainty original data set; Performing cluster analysis on the uncertainty original data set, using a hierarchical clustering algorithm to classify similar factors to obtain an uncertainty factor classification result; Dividing the uncertainty factor classification result into an external uncertainty category and an internal uncertainty category, wherein the external uncertainty includes extreme weather, policy changes and market fluctuations, and the internal uncertainty includes resource supply fluctuations, technical changes and personnel flow, to obtain a two-level classification system; Quantifying the influence degree of each type of uncertainty factor in the two-level classification system, calculating the influence strength value, occurrence probability value and duration value of each factor through expert scoring and historical data analysis to obtain an uncertainty factor feature vector; Based on the uncertainty factor feature vector, an encoding rule is established, a unique identification code is assigned to each type of uncertainty factor, and a correlation graph between factors is established to obtain an uncertainty factor network structure; Converting the uncertainty factor network structure into a structured data format, establishing a data table containing factor identification, classification information, influence characteristics and correlation relationships to obtain an uncertainty factor structured data set.

[0036] Specifically, the key events that affect the duration, cost, and quality of a project are extracted by text analysis of the quality acceptance report, progress comparison table, cost settlement table, and change application form of completed projects. The data collection uses a structured template to mark the occurrence time, duration, impact range, cause description, and result description of each event. For example, the event "due to continuous heavy rain, the foundation pit water cannot be constructed, delaying the structure construction for 7 days" is extracted from the progress report, coded as "abnormal event-weather-001", and associated with the specific impact data on the duration. In this way, a large number of typical events are accumulated from multiple historical projects to form an uncertainty original dataset. When clustering the uncertainty original dataset, a hierarchical clustering algorithm is used to classify similar factors. First, the event feature vector is constructed, including the text features of event description (processed by TF-IDF vectorization) and impact features (duration delay days, cost increase ratio, quality deviation degree). Then, the similarity matrix between events is calculated, using cosine similarity to calculate the similarity of text features, Euclidean distance to calculate the similarity of impact features, and combining the two to get the comprehensive similarity. Based on the similarity matrix, the most similar event clusters are merged from bottom to top using the complete connection method to form a clustering tree diagram. By setting a similarity threshold (such as 0.7), the tree diagram is truncated to obtain several event clusters, forming the classification results of uncertainty factors.

[0037] The classification results of uncertainty factors are further divided into external uncertainty categories and internal uncertainty categories. External uncertainty includes factors that cannot be controlled by the project party, which is subdivided into extreme weather category (such as heavy rain, high temperature, typhoon), policy change category (such as environmental standard adjustment, specification update), and market fluctuation category (such as material price fluctuation, inflation). Internal uncertainty includes factors that can be partially controlled within the project, which is subdivided into resource supply fluctuation category (such as material supply not in time, equipment failure), technical change category (such as design scheme adjustment, construction process change), and personnel flow category (such as key personnel change, labor dispute). This classification method forms a two-level classification system, which facilitates the adoption of appropriate countermeasures for different categories of factors. The impact degree of each uncertainty factor in the two-level classification system is quantified using a double-track evaluation method: on the one hand, expert scores are collected through Delphi method, and multiple rounds of anonymous expert scoring are used to evaluate the impact degree of each factor in different project types; on the other hand, the average impact value and standard deviation of each factor in history are calculated through statistical analysis of historical data. By weighting and fusing the two evaluation results (historical data weight 0.7, expert score weight 0.3), the three-dimensional feature vector of each factor is obtained: impact intensity value (average deviation degree of three-dimensional indicators, 1-5 points), occurrence probability value (historical occurrence frequency, decimal between 0 and 1), and duration value (average number of days of impact duration). These three values together form the uncertainty factor feature vector.

[0038] Based on the uncertainty factor feature vector, an encoding rule is established, and a hierarchical encoding scheme is adopted, in the form of "A-BB-CCC", where A represents the first-level classification (E for external and I for internal), BB represents the second-level classification (such as WT for extreme weather and PC for policy change), and CCC represents the factor serial number. At the same time, according to the time sequence association, causal association and impact accumulation relationship between factors, a factor association matrix is established to record the association strength between each pair of factors (a value between 0 and 1). Based on the association matrix, an association relationship diagram is drawn, with nodes representing uncertainty factors and edges representing association relationships. The thickness of the edge represents the association strength, forming an uncertainty factor network structure. The uncertainty factor network structure is converted into a structured data format, and a relational data table set is created, including a factor basic information table (storing factor ID, name, description, classification information), a factor feature table (storing impact strength, occurrence probability, duration, etc. Characteristic value) and a factor association table (storing the association type and strength between factors). The three tables are associated through the factor ID to form a complete uncertainty factor structured data set, providing a data basis for subsequent α-cut fuzzy set modeling, and solving the problem of lack of systematic management of uncertainty factors in the engineering construction process.

[0039] In a specific embodiment, the process of performing the steps of creating a plurality of candidate solutions and assigning a fitness value to each solution can specifically include the following steps: Based on the engineering three-dimensional index fuzzy mathematical model, the solution space and constraint conditions of the multi-objective optimization problem are defined, the population size parameter and the iteration number parameter are set, and the algorithm control parameter set is obtained; According to the algorithm control parameter set and the resource allocation scheme, a plurality of initial candidate schemes are generated in the solution space through Latin hypercube sampling method, forming an initial population with diversity, and obtaining a candidate solution set; The duration target function value, cost target function value and quality target function value of each solution in the candidate solution set are calculated, and the comprehensive fitness value is synthesized by weighted summation method to obtain the initial solution set family.

[0040] Specifically, an optimization problem is defined based on a three-dimensional index fuzzy mathematics model. The solution space includes three types of decision variables, i.e., process sequencing, resource allocation and risk response. The constraint conditions include resource total quantity constraint, technical logic constraint and risk threshold constraint. Meanwhile, algorithm control parameters such as population quantity parameter (usually 30-50), iteration number parameter (100-300 times), mutation probability and crossover probability are set. According to these parameters and resource allocation schemes, Latin hypercube sampling is used to generate initial candidate schemes. The method equally divides the value range of each decision variable into N intervals (N is equal to the population quantity), randomly selects a value from each interval, and generates candidate solutions by randomly combining the values of different dimensions. For example, multiple sequencing schemes that meet the logical relationship are generated for the process sequencing variable, and multiple allocation schemes that meet the resource limit are generated for the resource allocation variable, so as to ensure the diversity of the initial population covering the entire solution space.

[0041] For each candidate solution, three objective function values are calculated: the duration objective function is calculated based on the critical path method; the cost objective function calculates the total cost including direct cost and indirect cost; and the quality objective function evaluates the quality level according to the worker-task matching degree and other factors. Fuzzy objective function values are calculated at multiple alpha levels (0.3, 0.5, 0.7), and finally the comprehensive fitness value is synthesized by weighted summation (for example, the weights of duration, cost and quality are 0.4, 0.4 and 0.2 respectively), forming an initial solution set family, providing a basis for multi-objective optimization, and effectively solving the problem that traditional methods cannot simultaneously optimize three-dimensional indexes and handle uncertainties.

[0042] The above describes the method for digital management of the whole process of engineering construction in the embodiments of the application, and the following describes the system for digital management of the whole process of engineering construction in the embodiments of the application. Please refer to Figure 2 An embodiment of the system for digital management of the whole process of engineering construction in the embodiments of the application includes: The processing module 201 is configured to collect multi-source heterogeneous data of the whole life cycle of engineering construction and perform standardized processing to obtain a standardized engineering data set; The integration module 202 is configured to construct a stacked integrated prediction system by using the standardized engineering data set, integrate the output results of linear regression, support vector machine and neural network through gradient boosting decision tree, and obtain three-dimensional index prediction values of engineering time, cost and quality; The allocation module 203 is configured to allocate engineering resources according to the three-dimensional index prediction values and the engineering task ergonomics risk index calculated by the repetitive action method, and obtain a resource allocation scheme; The quantification module 204 is configured to quantify engineering uncertainty factors based on the resource allocation scheme, calculate a scheme set under multi-level uncertainty by using a multi-objective symbiotic organism search algorithm, and obtain an engineering construction management strategy.

[0043] The above Figure 2 The engineering construction whole-process digital management system in the embodiment of the present application is described in detail from the perspective of the modular function entity, and the engineering construction whole-process digital management device in the embodiment of the present application is described in detail from the perspective of hardware processing.

[0044] Figure 3 is a structural schematic diagram of an engineering construction whole-process digital management device provided by the embodiment of the present application. The engineering construction whole-process digital management device 300 can be greatly different due to different configurations or performances, and can include one or more than one processor (central processing unit, CPU) 310 (for example, one or more than one processor) and a memory 320, one or more than one storage medium 330 (for example, one or more than one mass storage device end) storing an application program 333 or data 332. The memory 320 and the storage medium 330 can be temporary storage or persistent storage. The program stored in the storage medium 330 can include one or more than one module (not shown in the figure), and each module can include a series of instruction operations in the engineering construction whole-process digital management device 300. Further, the processor 310 can be configured to communicate with the storage medium 330, and execute a series of instruction operations in the storage medium 330 on the engineering construction whole-process digital management device 300, so as to realize the steps of the above engineering construction whole-process digital management method.

[0045] The engineering construction whole-process digital management device 300 can also include one or more than one power supply 340, one or more than one wired or wireless network interface 350, one or more than one input and output interface 360, and / or one or more than one operating system 331, such as Windows Serve, Mac OS X, Unix, Linux, FreeBSD, etc. Those skilled in the art can understand that, Figure 3 The engineering construction whole-process digital management device structure shown does not constitute a limitation on the engineering construction whole-process digital management device provided by the present application, and can include more or fewer components than shown, or combine certain components, or different component arrangements.

[0046] The present application also provides a computer readable storage medium, which can be a non-volatile computer readable storage medium, and can also be a volatile computer readable storage medium. The computer readable storage medium has instructions stored therein, and when the instructions run on a computer, the computer executes the steps of the engineering construction whole-process digital management method.

[0047] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described system, system and unit can refer to the corresponding processes in the foregoing method embodiments, and will not be described here.

[0048] The integrated unit, if implemented in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes a number of instructions for making an engineering construction whole process digital management device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the method described in each embodiment of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0049] The above embodiments are only used to illustrate the technical solutions of the present application, rather than limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A digital management method for the entire process of engineering construction, characterized in that: The method comprises: Collect multi-source heterogeneous data from the entire life cycle of engineering construction and perform standardization processing to obtain standardized engineering data sets; Using the standardized engineering data set to build a stacked integrated prediction system, the output results of linear regression, support vector machine and neural network are integrated through a gradient boosting decision tree to obtain the predicted values ​​of the three-dimensional indicators of engineering time-cost-quality; According to the predicted values ​​of the three-dimensional indicators, the engineering task ergonomic risk index calculated by the occupational repetitive action method is combined with engineering resources to obtain a resource allocation plan; Based on the resource allocation scheme, the engineering uncertainty factors are quantified, and a set of schemes under multi-level uncertainty is calculated through a multi-objective symbiotic search algorithm to obtain an engineering construction management strategy.

2. The digital management method for the entire construction process according to claim 1 is characterized in that: The multi-source heterogeneous data of the entire life cycle of the engineering construction is collected and standardized to obtain a standardized engineering data set, including: Collect design parameter data, cost data, schedule data, quality data, safety data, and human resource data through the distributed Internet of Things system to obtain original multi-source heterogeneous data; Performing outlier detection on the original multi-source heterogeneous data to obtain an outlier labeled data set; Performing data cleaning on the outlier labeled data set to obtain a cleaned data set; Performing format conversion and spatiotemporal alignment on the cleaned data set to obtain a format-standardized data set; Performing semantic unification on the format-standardized dataset to obtain a semantically standardized dataset; The semantic standardized dataset is constructed in the form of a graph database, and a multi-dimensional index structure is established to obtain a standardized engineering dataset containing attribute features, temporal features, spatial features and relationship features.

3. The digital management method for the entire construction process according to claim 1 is characterized in that: The stacked integrated prediction system is constructed using the standardized engineering data set, and the output results of linear regression, support vector machine and neural network are integrated through gradient boosting decision tree to obtain the predicted values ​​of the three-dimensional indicators of engineering time-cost-quality, including: Performing feature engineering on the standardized engineering data set to obtain an optimized feature set through feature selection and feature dimensionality reduction; Dividing the optimized feature set into a training set, a validation set, and a test set to obtain a model training data set, a model validation data set, and a model test data set; Using the model training data set to train a linear regression model, using a regularization method to process feature weights to obtain a linear prediction model; Optimizing the parameters of the linear prediction model using the model validation dataset, and evaluating the model performance using the model test dataset to obtain a linear prediction result; Training a support vector machine regression model and a deep neural network model on the model training data set, and optimizing parameters using the model verification data set to obtain support vector machine prediction results and neural network prediction results; The linear prediction results, the support vector machine prediction results and the neural network prediction results are used as input features, combined with the key features in the optimization feature set, and integrated learning is performed through the gradient boosting decision tree algorithm to obtain the prediction value of the three-dimensional indicators of engineering time, cost and quality.

4. The digital management method for the entire construction process according to claim 1 is characterized in that: The resource allocation plan is obtained by allocating engineering resources based on the predicted values ​​of the three-dimensional indicators and the engineering task ergonomic risk index calculated using the occupational repetitive action method, including: The action complexity, risk level and environmental load of each engineering task are numerically quantified, and the specific numerical scores of each item are calculated and weighted and summarized to obtain a quantitative data table of task characteristics; Based on the quantitative data table of task characteristics, the actual frequency of technical movements, force factor, posture factor, additional factor and recovery factor are calculated using the occupational repetitive action method and comprehensive calculations are performed to obtain the engineering task ergonomic risk index matrix; Collect each worker's professional qualification certificate level, years of work experience, physical fitness test results, and historical project completion quality scores to form a structured data record and obtain a numerical file of the worker's ability; Correlating the engineering task ergonomic risk index matrix with the three-dimensional indicator prediction values ​​to generate completion time values, cost consumption values, and quality score prediction values ​​for each worker-task combination, thereby obtaining a basic dataset for task allocation calculation; Performing a constructive random search operation on the task allocation calculation basic data set, and permuting and combining workers and tasks through iterative calculations, with the goal of minimizing the total construction period value, the total cost value, and maximizing the total quality score, with the boundary condition that the total ergonomic risk score does not exceed the safety threshold, to obtain an initial digital resource allocation table; A local search optimization calculation is performed on the initial digital resource allocation table, and a solution set is adjusted through a simulated annealing calculation process with gradually decreasing temperature parameters, and the optimal solution in previous iterations is retained to obtain a resource allocation plan.

5. The digital management method for the entire construction process according to claim 1 is characterized in that: The project uncertainty factors are quantified based on the resource allocation plan, and a set of plans under multi-level uncertainty is calculated through a multi-objective symbiotic search algorithm to obtain a project construction management strategy, including: Establish an engineering construction uncertainty factor library, identify external and internal uncertainty factors, and classify and code them to obtain a structured dataset of uncertainty factors; Performing mathematical modeling on each factor in the structured data set of uncertainty factors using the α-cut fuzzy set method, converting each uncertainty factor into a fuzzy numerical value with a membership function, and obtaining a fuzzy mathematical model of the uncertainty factors; Combining the uncertainty factor fuzzy mathematical model with the resource allocation plan, constructing a fuzzy duration calculation matrix, a fuzzy cost calculation matrix, and a fuzzy quality calculation matrix, and obtaining a fuzzy mathematical model of three-dimensional engineering indicators taking uncertainty into account; Initialize the ecosystem of the multi-objective symbiotic search algorithm, create multiple candidate solutions and assign fitness values ​​to each solution to obtain an initial solution set; The initial solution set is iterated by simulating three symbiotic mechanisms: mutual benefit relationship, unilateral benefit relationship and parasitic relationship. Mutual benefit relationship generates a new solution by combining the advantages of two solutions, unilateral benefit relationship generates an improved solution by influencing one solution on another, and parasitic relationship replaces the existing solution by random mutation to obtain the evolved solution set. The Pareto non-dominated sorting and congestion calculation are applied to the evolved solution set to screen out the non-dominated optimal solutions with the shortest construction period, lowest cost and highest quality under different α levels, form multiple groups of optimal solutions, and obtain the engineering construction management strategy.

6. The digital management method for the entire construction process according to claim 5 is characterized in that: The engineering construction uncertainty factor library is established to identify external uncertainty and internal uncertainty factors, and classify and encode them to obtain a structured dataset of uncertainty factors, including: Collect abnormal event records and change application data from historical engineering projects, extract key events that lead to construction delays, cost increases, and quality decline, and obtain the uncertainty original data set; Performing cluster analysis on the uncertainty original data set, classifying similar factors using a hierarchical clustering algorithm, and obtaining uncertainty factor classification results; The uncertainty factors are classified into external uncertainty categories and internal uncertainty categories, where external uncertainty includes extreme weather, policy changes and market fluctuations, and internal uncertainty includes resource supply fluctuations, technological changes and personnel mobility, thus obtaining a two-level classification system; Quantify the impact of various uncertainty factors in the secondary classification system, calculate the impact intensity value, occurrence probability value and duration value of each factor through expert scoring and historical data analysis, and obtain the uncertainty factor characteristic vector; Establishing a coding rule based on the uncertainty factor feature vector, assigning a unique identification code to each type of uncertainty factor, and establishing a correlation relationship diagram between factors to obtain an uncertainty factor network structure; The uncertainty factor network structure is converted into a structured data format, and a data table including factor identification, classification information, influencing characteristics and association relationships is established to obtain an uncertainty factor structured data set.

7. The digital management method for the entire construction process according to claim 6 is characterized in that: The ecosystem of the multi-objective symbiotic biological search algorithm is initialized, multiple candidate solutions are created and a fitness value is assigned to each solution, and an initial solution set family is obtained, including: Based on the three-dimensional engineering index fuzzy mathematical model, the solution space and constraint conditions of the multi-objective optimization problem are defined, the population size parameter and the iteration number parameter are set, and the algorithm control parameter set is obtained; According to the algorithm control parameter set and the resource allocation plan, a plurality of initial candidate solutions are generated in the solution space by Latin hypercube sampling to form an initial population with diversity, thereby obtaining a candidate solution set; The duration objective function value, cost objective function value and quality objective function value are calculated for each solution in the candidate solution set, and the comprehensive fitness value is synthesized by weighted summation to obtain an initial solution set family.

8. A digital management system for the entire process of engineering construction, characterized in that: The method for digital management of the entire engineering construction process according to any one of claims 1 to 7 is used, wherein the digital management system for the entire engineering construction process comprises: The processing module is used to collect multi-source heterogeneous data from the entire life cycle of engineering construction and perform standardization processing to obtain a standardized engineering data set; An integration module is used to construct a stacked integrated prediction system using the standardized engineering data set, integrating the output results of linear regression, support vector machine and neural network through a gradient boosting decision tree to obtain the predicted values ​​of the three-dimensional indicators of engineering time, cost and quality; an allocation module for allocating engineering resources based on the predicted values ​​of the three-dimensional indicators and the engineering task ergonomic risk index calculated using the occupational repetitive action method, thereby obtaining a resource allocation plan; The quantification module is used to quantify the engineering uncertainty factors based on the resource allocation plan, calculate the solution set under multi-level uncertainty through the multi-objective symbiotic search algorithm, and obtain the engineering construction management strategy.

9. A digital management device for the entire process of engineering construction, characterized in that: It includes a memory and a processor, the memory stores a computer program that can be run on the processor, and when the processor executes the computer program, it implements the digital management method for the entire process of engineering construction as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the processor executes the method for digital management of the entire engineering construction process as described in any one of claims 1 to 7.

Images