Construction engineering management system

Abstract

The invention, which relates to the technical field of information management, discloses a construction engineering management system comprising a data integration module, an adaptive neural network module, a dynamic knowledge graph module, a probabilistic project simulation and optimization module, a multi-scale timeline analysis module, a transparent financial monitoring module, and a resource mobility optimization module. The self-adaptive neural network technology is adopted, the network structure and parameters can be automatically adjusted according to project characteristics, self-learning and optimization are achieved, uncertainty in project execution is simulated through a probability model, an optimization scheme of project execution is provided through an optimization algorithm, the project progress is analyzed on multiple time scales, and the project execution efficiency is improved. The system supports the adjustment of a project plan, optimizes the distribution and flow of resources according to the project progress and decision suggestions, reduces the resource waste, improves the resource utilization efficiency, each module has a clear function and responsibility, and forms a dynamic and adaptive project management cycle through the cooperative work of the modules.

Description

Technical Field

[0001] The present invention relates to the technical field of information management, in particular to a construction engineering management system. Background Art

[0002] Construction engineering refers to the construction of housing buildings and their ancillary facilities, as well as the installation of supporting lines, pipelines, and equipment. These activities together constitute an engineering entity. The scope of construction engineering is relatively narrow, focusing on housing buildings, their ancillary facilities, and related installation projects, so it is often referred to as housing construction engineering.

[0003] A construction project management system is a software tool specifically designed to manage and coordinate construction projects. It helps project teams plan, execute and control construction projects more effectively, thereby improving project efficiency, quality and cost control.

[0004] The workflow of existing construction project management systems is often preset and difficult to adapt to dynamic changes in projects. It requires frequent manual adjustments, and during the adjustment process, data between different departments and systems cannot be shared synchronously, which often leads to information islands and increases the difficulty of coordinating and integrating data. Especially in a remote working environment, it greatly challenges the communication and collaboration efficiency between project team members. Therefore, we proposed a construction project management system to solve the above problems. Summary of the invention

[0005] The purpose of the present invention is to provide a construction project management system to solve the problems in the current market raised by the above background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A construction project management system, including a data integration module, an adaptive neural network module, a dynamic knowledge graph module, a probabilistic project simulation and optimization module, a multi-scale timeline analysis module, a transparent financial monitoring module, and a resource liquidity optimization module;

[0008] Among them, the data integration module is used to collect project data from different sources. The adaptive neural network module uses adaptive neural network technology to automatically adjust the network structure, parameters and learning strategies according to the characteristics of the project data. The dynamic knowledge graph module stores and manages project-related expertise, historical data and industry practices. The probabilistic project simulation and optimization module simulates the uncertainty in project execution by building a probabilistic model and predicts possible results and risks. The multi-scale timeline analysis module analyzes the project progress at multiple time scales from the macro project progress to the micro daily task execution. The transparent financial monitoring module tracks the financial status of the project in real time and uses blockchain technology to ensure the transparency and immutability of financial data. The resource liquidity optimization module predicts resource shortages or surpluses by analyzing resource demand and usage patterns, and automatically adjusts resource allocation strategies.

[0009] As a further optimization scheme of the present invention, after the engineering project starts, the data integration module collects information from the project data source, and after the data is cleaned, formatted and standardized, it is passed to the adaptive neural network module;

[0010] Specifically, in the data integration module, the data are standardized and merged to form a comprehensive data set, the integrity and accuracy of the data are verified through cross-validation, and the processed data are passed to the adaptive neural network module using a queuing mechanism.

[0011] As a further optimization scheme of the present invention, the adaptive neural network module receives the pre-processed data from the data integration module, automatically adjusts the network structure according to the data characteristics, generates decision suggestions for project management through learning and simulation, and transmits the information to the dynamic knowledge graph module for knowledge update;

[0012] As a further optimization scheme of the present invention, after completing learning and simulation, the adaptive neural network module passes the output results to the dynamic knowledge graph module, identifies the risk prediction and cost optimization suggestion information in the output results, converts the information into project experience and professional knowledge nodes in the knowledge graph, establishes causal and dependency relationships between nodes, passes new knowledge nodes and relationships in the knowledge graph to the adaptive neural network module, updates the adaptive neural network module to add new knowledge nodes, update existing knowledge nodes and establish new relationship libraries, uses the updated knowledge graph information to perform more accurate data analysis and prediction, and generates decision recommendations for project management based on the information in the knowledge graph.

[0013] As a further optimization scheme of the present invention, the probabilistic project simulation and optimization module uses the information in the dynamic knowledge graph and the decision suggestions of the adaptive neural network module to construct a probabilistic model to simulate the uncertainty in project execution, provides an optimization scheme for project execution through the optimization algorithm, and feeds the results back to the adaptive neural network module to improve the learning process.

[0014] As a further optimization scheme of the present invention, the probabilistic project simulation and optimization module passes the simulated and optimized project progress data to the multi-scale timeline analysis module, identifies the key milestones and time nodes of the project, analyzes the progress of the project in different years, quarters, months, weeks and days, compares the progress on different time scales, finds out the bottlenecks and potential problems in project execution, optimizes resource allocation, adjusts the schedule, solves bottlenecks and potential problems, re-evaluates the critical path, determines the focus and priority of project execution, and passes the adjusted project plan and optimization suggestions to the adaptive neural network module, which uses the feedback results to adjust the network parameters and structure.

[0015] As a further optimization scheme of the present invention, the transparent financial monitoring module monitors the financial status of the project in real time, ensures the rational use of budgets and costs, receives data from other modules, and at the same time, uses blockchain technology to ensure the transparency and immutability of the data.

[0016] As a further optimization scheme of the present invention, the multi-scale timeline analysis module transmits the project schedule data to the resource mobility optimization module, and the adaptive neural network module transmits the decision suggestions to the resource mobility optimization module, identifies the critical path and bottleneck activities in the project schedule, analyzes resource requirements, evaluates resource utilization efficiency, identifies the situation of excess or insufficient resources, adjusts the resource allocation plan, ensures the effective utilization of resources, optimizes the resource flow path, reduces the loss of resources in circulation, balances resource use, avoids excessive concentration or dispersion of resources, and transmits the optimized resource allocation plan to the adaptive neural network module. The adaptive neural network module uses the feedback results to adjust the network parameters and structure.

[0017] As a further optimization scheme of the present invention, in the data integration module, the project data sources include project plans, budgets, design drawings, contract documents, historical data, progress reports, quality control records, safety records, risk management documents, and environmental management documents.

[0018] As a further optimization scheme of the present invention, the dynamic knowledge graph module and the adaptive neural network module pass information to the probabilistic project simulation and optimization module, analyze the project experience and expertise in the dynamic knowledge graph, and identify the uncertainty factors in project execution. According to the uncertainty factors, a Bayesian network is constructed, and the initial state and decision variables of the project execution are input. The probability model is run to simulate the process of project execution, and the results and risk distribution of project execution are generated. The results of the project execution simulation are analyzed by genetic algorithms, the cost minimization and risk minimization goals are identified, the optimization goals and constraints are input, the genetic algorithm is run, and the optimization scheme for project execution is generated. The results of the optimization scheme are passed to the adaptive neural network module, and the adaptive neural network module uses the feedback results to adjust the network parameters and structure.

[0019] Compared with the prior art, the present invention has the following beneficial effects:

[0020] The present invention adopts adaptive neural network technology, which can automatically adjust the network structure and parameters according to the characteristics of the project, realize self-learning and optimization, use probability models to simulate the uncertainty in project execution, provide optimization solutions for project execution through optimization algorithms, analyze project progress on multiple time scales, support the adjustment of project plans, optimize the allocation and flow of resources according to project progress and decision-making suggestions, reduce resource waste, and improve resource utilization efficiency. Each module has clear functions and responsibilities, and through the collaborative work between modules, a dynamic and adaptive project management cycle is formed.

[0021] The above summary is for illustrative purposes only and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments and features described above, further aspects, embodiments and features of the present invention will be readily apparent by reference to the accompanying drawings and the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 This is a module block diagram of a construction project management system of the present invention. DETAILED DESCRIPTION

[0023] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0024] Embodiment 1

[0025] See also Figure 1, a construction project management system, including a data integration module, an adaptive neural network module, a dynamic knowledge graph module, a probabilistic project simulation and optimization module, a multi-scale timeline analysis module, a transparent financial monitoring module, and a resource liquidity optimization module;

[0026] Among them, the data integration module is used to collect project data from different sources. The adaptive neural network module uses adaptive neural network technology to automatically adjust the network structure, parameters and learning strategies according to the characteristics of the project data. The dynamic knowledge graph module stores and manages project-related expertise, historical data and industry practices. The probabilistic project simulation and optimization module simulates the uncertainty in project execution by building a probabilistic model and predicts possible results and risks. The multi-scale timeline analysis module analyzes the project progress at multiple time scales from the macro project progress to the micro daily task execution. The transparent financial monitoring module tracks the financial status of the project in real time and uses blockchain technology to ensure the transparency and immutability of financial data. The resource liquidity optimization module predicts resource shortages or surpluses by analyzing resource demand and usage patterns, and automatically adjusts resource allocation strategies.

[0027] After the engineering project starts, the data integration module collects information from the project data source, and after the data is cleaned, formatted and standardized, it is passed to the adaptive neural network module;

[0028] Specifically, in the data integration module, the data are standardized and merged to form a comprehensive data set, the integrity and accuracy of the data are verified through cross-validation, and the processed data are passed to the adaptive neural network module using a queuing mechanism.

[0029] Furthermore, through the queue management function, a queue instance is created and a unique identifier is assigned to it. When the data processing is completed, the data will be written to the queue. This process can be performed automatically by the data integration module or manually. The system continuously monitors the data in the queue and starts the processing flow when there is data in the queue. When the adaptive neural network module is ready to process the data, it takes the data out of the queue. This process can be selected synchronously. The adaptive neural network module analyzes and processes the data, automatically adjusts the network structure according to the characteristics of the data, and generates decision recommendations for project management through learning and simulation. The processed data is passed to the dynamic knowledge graph module to update the project experience and expertise in the knowledge graph.

[0030] The adaptive neural network module receives pre-processed data from the data integration module, automatically adjusts the network structure according to the data characteristics, generates decision suggestions for project management through learning and simulation, and passes the information to the dynamic knowledge graph module for knowledge update;

[0031] Among them, the data integration module sends the processed data to the adaptive neural network module. First, determine the number of layers of the neural network, the number of neurons in each layer, and the activation function, adjust the hyperparameters of the network, perform forward propagation, and calculate the output of the neural network. Perform backpropagation and adjust the network weights according to the prediction error. Repeat the forward propagation and backpropagation processes until the network converges or reaches a predetermined number of iterations. Analyze the output of the neural network and identify key patterns and relationships in the data. Based on the key patterns and relationships, generate decision recommendations for project management and convert the decision recommendations into knowledge nodes and relationships in the knowledge graph. Update the knowledge graph in the dynamic knowledge graph module, including adding new knowledge nodes, updating existing knowledge nodes, and establishing new relationships.

[0032] Specifically, during the forward propagation process, the formula used by the activation function is:

[0033]

[0034] ReLU: ReLU(x) = max(0, x)

[0035]

[0036] Multi-layer forward propagation: O = f(W·X+b)

[0037] During the back propagation process, the error calculation formula is:

[0038] Weight update: ΔW = α·(OT)·X

[0039] Bias update: Δb = α (OT)

[0040] Formula used for batch gradient descent: W new =W old -α·▽J(W)

[0041] L1 Regularization:

[0042] L2 Regularization:

[0043] The dynamic knowledge graph module receives the output of the adaptive neural network module and updates the project experience and expertise in the knowledge graph. At the same time, the information in the knowledge graph is synchronized with the adaptive neural network module for further learning and decision support.

[0044] Among them, after completing learning and simulation, the adaptive neural network module passes the output results to the dynamic knowledge graph module, identifies the risk prediction and cost optimization suggestion information in the output results, converts the information into project experience and professional knowledge nodes in the knowledge graph, establishes causal and dependency relationships between nodes, passes new knowledge nodes and relationships in the knowledge graph to the adaptive neural network module, updates the adaptive neural network module to add new knowledge nodes, update existing knowledge nodes and establish new relationship libraries, uses the updated knowledge graph information to conduct more accurate data analysis and prediction, and generates decision recommendations for project management based on the information in the knowledge graph.

[0045] The probabilistic project simulation and optimization module uses the information in the dynamic knowledge graph and the decision suggestions of the adaptive neural network module to build a probabilistic model to simulate the uncertainty in project execution. Through the optimization algorithm, it provides an optimization plan for project execution and feeds the results back to the adaptive neural network module to improve the learning process.

[0046] The multi-scale timeline analysis module receives project progress data from the probabilistic project simulation and optimization module, analyzes the progress of the project on multiple time scales, and uses the analysis results to guide the adjustment of the project plan and feed back to the adaptive neural network module to optimize the decision;

[0047] Among them, the probabilistic project simulation and optimization module passes the simulated and optimized project progress data to the multi-scale timeline analysis module to identify the key milestones and time nodes of the project. Analyze the progress of the project in different years, quarters, months, weeks, and days. Compare the progress on different time scales, find out the bottlenecks and potential problems in project execution, optimize resource allocation, adjust the schedule, and solve bottlenecks and potential problems. Re-evaluate the critical path and determine the focus and priority of project execution. Pass the adjusted project plan and optimization suggestions to the adaptive neural network module. The adaptive neural network module uses the feedback results to adjust the network parameters and structure.

[0048] The transparent financial monitoring module monitors the financial status of the project in real time, ensures the reasonable use of budget and cost, receives data from other modules, and uses blockchain technology to ensure the transparency and immutability of data;

[0049] Receive financial data from other related modules, update budget balances, cost expenditures, and cash flows in real time, compare actual financial data with budgets and cost plans, and identify deviations and potential problems. Provide financial reports and suggestions based on deviations and potential problems to guide the project team to adjust budgets and cost usage. Receive project progress data and resource usage data from other modules. Combine the received data with financial data for comprehensive analysis. Encrypt the financial data and store it on the blockchain. Ensure data integrity and immutability through blockchain consensus mechanisms and distributed ledger technology, and allow project team members and other relevant parties to access and verify financial data in real time.

[0050] The resource mobility optimization module optimizes the allocation and flow of resources based on the progress data of the multi-scale timeline analysis module and the decision suggestions of the adaptive neural network module. The resource optimization results are fed back to the adaptive neural network module to improve the resource allocation strategy.

[0051] Specifically, the multi-scale timeline analysis module passes the project schedule data to the resource flow optimization module, and the adaptive neural network module passes the decision suggestions to the resource flow optimization module. Identify the critical path and bottleneck activities in the project schedule. Analyze resource requirements, evaluate resource utilization efficiency, and identify situations of excess or insufficient resources. Adjust the resource allocation plan to ensure the effective use of resources, optimize the resource flow path, and reduce the loss of resources in circulation. Balance resource use to avoid excessive concentration or dispersion of resources. Pass the optimized resource allocation plan to the adaptive neural network module. The adaptive neural network module uses the feedback results to adjust the network parameters and structure.

[0052] The formula used in linear programming is:

[0053] Minimize c T x

[0054] Subject to Ax≤b

[0055] Abd x≥0

[0056] Among them, c is the objective function coefficient vector, x is the decision variable vector, A is the constraint matrix, and b is the constraint vector.

[0057] In the data integration module, project data sources include project plans, budgets, design drawings, contract documents, historical data, progress reports, quality control records, safety records, risk management documents, and environmental management documents.

[0058] Furthermore, the project plan includes the project initiation document, project scope statement, project timeline, key task list, and resource allocation plan; the budget includes cost estimation, budget allocation, cash flow forecast, and financial statements;

[0059] Design drawings include architectural drawings, construction drawings, system design drawings, electrical and piping layout drawings; contract documents include main contracts, subcontracts, purchase orders, service agreements, insurance documents; historical data include cost records, progress reports, quality assessments, customer feedback, and risk records; progress reports include weekly reports, monthly reports, progress tracking sheets, and change requests; quality control records include quality inspection reports, lists of non-conformities, and corrective and preventive measures; safety records include safety checklists, accident reports, and safety training records; risk management documents include risk registers, risk response plans, and risk monitoring reports; environmental management documents include environmental impact assessments, environmental management plans, and waste disposal records.

[0060] The dynamic knowledge graph module and the adaptive neural network module pass information to the probabilistic project simulation and optimization module, analyze the project experience and expertise in the dynamic knowledge graph, and identify the uncertainties in project execution. Based on the uncertainties, a Bayesian network is constructed, and the initial state and decision variables of the project execution are input. The probabilistic model is run to simulate the process of project execution and generate the results and risk distribution of project execution. The results of the project execution simulation are analyzed through the genetic algorithm, the cost minimization and risk minimization goals are identified, the optimization goals and constraints are input, the genetic algorithm is run, the optimization plan for project execution is generated, and the results of the optimization plan are passed to the adaptive neural network module. The adaptive neural network module uses the feedback results to adjust the network parameters and structure.

[0061] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0062] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0063] In addition, each functional unit in each embodiment of the present invention may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0064] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A construction project management system, characterized in that: It includes data integration module, adaptive neural network module, dynamic knowledge graph module, probabilistic project simulation and optimization module, multi-scale timeline analysis module, transparent financial monitoring module, and resource liquidity optimization module; Among them, the data integration module is used to collect project data from different sources. The adaptive neural network module uses adaptive neural network technology to automatically adjust the network structure, parameters and learning strategies according to the characteristics of the project data. The dynamic knowledge graph module stores and manages project-related expertise, historical data and industry practices. The probabilistic project simulation and optimization module simulates the uncertainty in project execution by building a probabilistic model and predicts possible results and risks. The multi-scale timeline analysis module analyzes the project progress at multiple time scales from the macro project progress to the micro daily task execution. The transparent financial monitoring module tracks the financial status of the project in real time and uses blockchain technology to ensure the transparency and immutability of financial data. The resource liquidity optimization module predicts resource shortages or surpluses by analyzing resource demand and usage patterns, and automatically adjusts resource allocation strategies.

2. A construction project management system according to claim 1, characterized in that: After the engineering project begins, the data integration module collects information from the project data source, and after the data is cleaned, formatted and standardized, it is passed to the adaptive neural network module; Specifically, in the data integration module, the data are standardized and merged to form a comprehensive data set, the integrity and accuracy of the data are verified through cross-validation, and the processed data are passed to the adaptive neural network module using a queuing mechanism.

3. A construction project management system according to claim 1, characterized in that: The adaptive neural network module receives preprocessed data from the data integration module, automatically adjusts the network structure according to the data characteristics, generates decision suggestions for project management through learning and simulation, and passes the information to the dynamic knowledge graph module for knowledge updating.

4. A construction project management system according to claim 1, characterized in that: After completing learning and simulation, the adaptive neural network module passes the output results to the dynamic knowledge graph module, identifies the risk prediction and cost optimization suggestion information in the output results, converts the information into project experience and professional knowledge nodes in the knowledge graph, establishes causal and dependency relationships between nodes, passes the new knowledge nodes and relationships in the knowledge graph to the adaptive neural network module, updates the adaptive neural network module to add new knowledge nodes, update existing knowledge nodes and establish new relationship libraries, uses the updated knowledge graph information to conduct more accurate data analysis and prediction, and generates decision recommendations for project management based on the information in the knowledge graph.

5. A construction project management system according to claim 1, characterized in that: The probabilistic project simulation and optimization module uses the information in the dynamic knowledge graph and the decision suggestions of the adaptive neural network module to build a probabilistic model to simulate the uncertainty in project execution. Through the optimization algorithm, it provides an optimization plan for project execution and feeds the results back to the adaptive neural network module to improve the learning process.

6. A construction project management system according to claim 1, characterized in that: in, The probabilistic project simulation and optimization module passes the simulated and optimized project progress data to the multi-scale timeline analysis module, identifies the key milestones and time nodes of the project, analyzes the progress of the project in different years, quarters, months, weeks and days, compares the progress on different time scales, finds out the bottlenecks and potential problems in project execution, optimizes resource allocation, adjusts the schedule, solves bottlenecks and potential problems, re-evaluates the critical path, determines the focus and priority of project execution, and passes the adjusted project plan and optimization suggestions to the adaptive neural network module. The adaptive neural network module uses the feedback results to adjust the network parameters and structure.

7. A construction project management system according to claim 1, characterized in that: The transparent financial monitoring module monitors the financial status of the project in real time, ensures the rational use of budgets and costs, receives data from other modules, and uses blockchain technology to ensure the transparency and immutability of data.

8. A construction project management system according to claim 1, characterized in that: The multi-scale timeline analysis module passes the project schedule data to the resource mobility optimization module, and the adaptive neural network module passes the decision suggestions to the resource mobility optimization module, identifies the critical paths and bottleneck activities in the project schedule, analyzes resource requirements, evaluates resource utilization efficiency, identifies situations of excess or insufficient resources, adjusts the resource allocation plan, ensures the effective use of resources, optimizes the resource flow path, reduces resource loss in circulation, balances resource use, avoids excessive concentration or dispersion of resources, and passes the optimized resource allocation plan to the adaptive neural network module. The adaptive neural network module uses the feedback results to adjust the network parameters and structure.

9. A construction project management system according to claim 1, characterized in that: In the data integration module, project data sources include project plans, budgets, design drawings, contract documents, historical data, progress reports, quality control records, safety records, risk management documents, and environmental management documents.

10. A construction project management system according to claim 5, characterized in that: The dynamic knowledge graph module and the adaptive neural network module pass information to the probabilistic project simulation and optimization module, analyze the project experience and expertise in the dynamic knowledge graph, and identify the uncertainty factors in project execution. According to the uncertainty factors, a Bayesian network is constructed, and the initial state and decision variables of the project execution are input. The probability model is run to simulate the process of project execution, and the results and risk distribution of project execution are generated. The results of the project execution simulation are analyzed by genetic algorithms, and the cost minimization and risk minimization goals are identified. The optimization goals and constraints are input, and the genetic algorithm is run to generate the optimization plan for project execution. The results of the optimization plan are passed to the adaptive neural network module, and the adaptive neural network module uses the feedback results to adjust the network parameters and structure.

Images