Construction project full life cycle management method and system, terminal and storage medium

Abstract

The invention relates to the technical field of building project management, and particularly provides a building project full life cycle management method and system, a terminal and a storage medium, and the method comprises the steps: obtaining project management data which comprises design parameters, construction progress data, material use data and environment monitoring data; corresponding management label types and contents are set for the historical project management data, a neural network model is trained based on the historical project management data and management labels, and the management labels comprise cost control management, progress management, quality management and risk management; inputting the current project management data into the neural network model, outputting the corresponding management label type and content by the model, and selecting a corresponding management decision mode; and calculating the cost, progress, quality and risk basis currently required to be managed by the project based on the corresponding management decision mode, and managing the project based on the basis currently required to be managed. And the flexibility and response speed of project management are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of construction project management, and particularly relates to a full life cycle management method, system, terminal and storage medium for construction projects. Background Art

[0002] With the booming development of the construction industry, the complexity of project management is also constantly increasing. In modern construction projects, from planning, design, construction to operation and maintenance, each link relies on a large amount of data support and accurate decision-making analysis. However, traditional management methods, relying on manual operations and paper documents, have become difficult to adapt to this challenge. These methods are not only inefficient but also error-prone and cannot meet the high efficiency and high precision requirements of modern construction project management.

[0003] In the traditional mode, construction project management often relies on the personal experience and intuition of project managers, who coordinate all parties through paper documents and face-to-face meetings.

[0004] This method is not only inefficient but also prone to lags and distortions in the information transmission process. This management mode with a linear process and hierarchical structure limits the flexibility and response speed of project management. Summary of the Invention

[0005] In view of the above deficiencies of the prior art, the present invention provides a full life cycle management method, system, terminal and storage medium for construction projects to solve the above technical problems.

[0006] In a first aspect, the present invention provides a full life cycle management method for construction projects, including: S1, obtaining project management data, where the project management data includes design parameters, construction progress data, material usage data and environmental monitoring data; S2, setting corresponding management label types and contents for historical project management data, and training a neural network model based on the historical project management data and management labels. The management labels include cost control management, schedule management, quality management and risk management; S3, inputting the current project management data into the neural network model, the model outputs the corresponding management label types and contents, and selects the corresponding management decision-making method based on the management label types and contents; S4, calculating the current management cost, schedule, quality and risk basis required for the project based on the corresponding management decision-making method, and managing the project based on the current management basis required.

[0007] In an optional implementation manner, before the model training in step S2, it includes: Constructing an objective function based on the management labels:

[0008] Among them, is the weight coefficient, is the cost efficiency, is the schedule accuracy rate, is the quality performance, is the degree of risk reduction;

[0009] Among them, T is the total project cycle, is the value actually completed by the project at time t, is the total cost invested at time t;

[0010] Among them, m is the number of tasks in the project, is the actual completion time of task i, is the planned completion time of task i;

[0011] Among them, k is the number of indicators of the project quality evaluation index, is the score of the j-th quality evaluation index, is the weight of the j-th quality evaluation index;

[0012] Among them, s is the number of identified risks, is the probability of occurrence of risk l, is the impact degree on the project after the risk occurs.

[0013] In an alternative implementation manner, in step S2, the training of the neural network model specifically includes: Initialize the neural network model. The model includes an input layer, a hidden layer, and an output layer. The input of the model is historical project management data, and the output of the model is the types and contents of cost control, schedule management, quality management, and risk management; Calculate the loss value of the model based on the objective function, calculate the gradients of the loss value with respect to the model weights and biases in combination with the backpropagation algorithm, and use the optimization algorithm to update the model weights and biases; Repeat the above steps. When the loss value is less than the preset loss threshold, stop training to obtain the trained neural network model.

[0014] In an alternative implementation manner, in step S3, the management decision-making method for cost management includes: In the early stage of the project, predict the project cost based on the linear regression algorithm and set an initial expectation for the project cost; During the project execution, calculate the project cost variance based on the earned value management algorithm; When the result of the project cost variance indicates cost overrun, reallocate the project resources.

[0015] In an alternative implementation, in step S3, the management decision-making methods for schedule management include: Calculate the earliest start time, earliest finish time, latest start time, and latest finish time of each task based on the critical path method to determine the shortest project duration and critical tasks; Judge whether the actual progress of each task lags behind based on the latest start time and latest end time, and judge whether the resources of each task are idle based on the earliest start time and earliest end time. When a critical task is determined to have a lag in actual progress, allocate the idle resources of non-critical tasks to critical tasks.

[0016] In an alternative implementation, in step S3, the management decision-making methods for quality management include: Perform statistical analysis on process data based on the statistical process control algorithm in Six Sigma management, draw control charts, monitor the stability of the process and quality fluctuations. When data points exceed the control limits, start the troubleshooting process and issue an exception warning.

[0017] In an alternative implementation, in step S3, the management decision-making methods for risk management include: Perform multiple simulations on the uncertain factors in the project based on the Monte Carlo simulation algorithm, evaluate the risk distribution and overall risk level of the project to determine high-probability and high-impact risks, and formulate response strategies according to the risk types; Decompose risks into multiple levels based on the analytic hierarchy process, construct a judgment matrix by comparing the relative importance of factors in each level, calculate the weights of each factor, thereby determine the risk priorities, determine the risk types to be prioritized for handling based on the risk priorities, and execute the response strategies.

[0018] In a second aspect, the present invention provides a building project full life cycle management system. When the system is implemented, it executes the above-mentioned building project full life cycle management method. The system includes: A data acquisition module that acquires project management data, where the project management data includes design parameters, construction progress data, material usage data, and environmental monitoring data; A model training module that sets corresponding management label types and contents for historical project management data, and trains a neural network model based on the historical project management data and management labels. The management labels include cost control management, schedule management, quality management, and risk management; A decision-making and selection module inputs the current project management data into a neural network model. The model outputs the corresponding management label types and contents, and based on the management label types and contents, selects the corresponding management decision-making methods. A decision-making and execution module calculates the basis for the cost, schedule, quality, and risks that need to be managed for the project based on the corresponding management decision-making methods, and manages the project based on the basis that needs to be managed currently.

[0019] Thirdly, a terminal is provided, including: A processor and a memory, wherein, The memory is used to store a computer program, The processor is used to call and run the computer program from the memory, so that the terminal executes the method of the above-mentioned terminal.

[0020] Fourthly, a computer-readable storage medium is provided. Instructions are stored in the computer-readable storage medium, and when it runs on a computer, it enables the computer to execute the methods described in the above aspects.

[0021] The beneficial effects of the present invention are as follows. The whole-life cycle management method, system, terminal, and storage medium for construction projects provided by the present invention obtain multi-faceted management data of the project, train a neural network model to output management labels, select decision-making methods and calculate management bases accordingly, and then realize the effective management of the project cost, schedule, quality, and risks. It can improve the decision-making accuracy, optimize resource allocation, enhance the risk prevention and control ability, ensure the construction quality, improve the project management efficiency and overall benefits, and promote the smooth progress of the construction project.

[0022] In addition, the design principle of the present invention is reliable and the structure is simple, having a very wide application prospect. Description of the Drawings

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required to be used in the description of the embodiments or the prior art. Obviously, for those of ordinary skill in the art, other drawings can also be obtained according to these drawings without creative efforts.

[0024] Figure 1 It is a schematic flowchart of the whole-life cycle management method for construction projects in an embodiment of the present invention.

[0025] Figure 2 It is a schematic block diagram of the whole-life cycle management system for construction projects in an embodiment of the present invention.

[0026] Figure 3 It is a schematic structural diagram of a terminal provided in an embodiment of the present invention. Detailed Embodiments

[0027] In order to enable those skilled in the art of the present technology to better understand the technical solutions in the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0028] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs. The terms used in the description of the present invention in this specification are only for the purpose of describing specific embodiments, and are not intended to limit the present invention.

[0029] The method for managing the entire life cycle of a construction project provided by the embodiments of the present invention is executed by a computer device. Correspondingly, the system for managing the entire life cycle of a construction project runs on the computer device.

[0030] Figure 1 It is a schematic flowchart of the method for managing the entire life cycle of a construction project according to an embodiment of the present invention. Among them, Figure 1 The execution subject can be a system for managing the entire life cycle of a construction project. According to different requirements, the order of the steps in this flowchart can be changed, and some can be omitted.

[0031] As Figure 1 shown, the method includes: S1. Obtain project management data, where the project management data includes design parameters, construction progress data, material usage data, and environmental monitoring data; Automatically record design parameters such as the dimensions, shape, and structural type of the building with the help of professional design software, and manually review and mark key parameters at the same time. Deploy progress monitoring cameras at the construction site, and use image recognition technology combined with the task time and human and equipment input recorded by construction workers on mobile devices in real time to collect construction progress data; Install electronic tag recognition devices in the material warehouse to record material in and out information, and construction workers manually supplement special situations; Arrange sensors for temperature, humidity, noise, air quality, etc. at the construction site to automatically collect environmental monitoring data and wirelessly transmit it to the data acquisition server.

[0032] Comprehensively collect data in all aspects of the project to provide an accurate and rich information basis for subsequent analysis and management.

[0033] S2. Set corresponding management label types and contents for historical project management data, and train a neural network model based on the historical project management data and management labels. The management labels include cost control management, schedule management, quality management, and risk management; According to the actual cost, schedule, quality, and risk status of historical projects, label the corresponding project management data with cost control management, schedule management, quality management, and risk management labels. Select a suitable neural network architecture, use the historical project management data and their corresponding labels as training data, set reasonable training parameters, and use a deep learning framework to train the model. Continuously adjust the weights and biases of the model until the model achieves good prediction performance.

[0034] S3. Input the current project management data into the neural network model. The model outputs the corresponding management label types and contents, and select the corresponding management decision-making method based on the management label types and contents; Input the preprocessed current project management data into the trained neural network model to obtain the management label types and contents output by the model. According to different management labels, for example, when encountering a cost control management label, if it is in the early stage of the project, select the linear regression algorithm; if it is during the project execution process, then select the earned value management algorithm; for the schedule management label, select the corresponding algorithms such as the critical path method or the program evaluation and review technique according to the task time certainty.

[0035] Realize the automated and intelligent selection of management decisions, improve decision-making efficiency. According to the actual stage and characteristics of the project, match the most suitable management decision-making method to ensure the pertinence and effectiveness of the management strategy, and avoid management problems caused by inappropriate decision-making methods.

[0036] S4. Calculate the cost, schedule, quality, and risk bases that need to be managed for the project based on the corresponding management decision-making method, and manage the project based on the bases that need to be managed currently.

[0037] Use the selected management decision-making method to calculate the management bases such as the current cost deviation, schedule deviation, quality index score, and risk priority of the project. Based on these bases, manage the project, such as adjusting the procurement plan and optimizing the construction process when the cost is overrun; deploying resources and adjusting the construction sequence when the schedule is delayed; inspecting raw materials and construction techniques when the quality is abnormal; formulating response plans for high-risk events and handling them preferentially.

[0038] Provide clear directions and key points for project management by scientifically calculating management bases. Can promptly discover problems in the project and take targeted measures to effectively control project costs, ensure schedules, improve quality, and reduce risks, ultimately achieving the smooth delivery and efficient management of the project and improving the overall efficiency of the project.

[0039] Optionally, as an embodiment of the present invention, step S1 specifically includes: Design parameter collection: During the design phase, architects and engineers conduct building design through professional design software, which automatically records design parameters such as the size, shape, and structural type of the building. At the same time, the design drawings are manually reviewed to mark key parameters to ensure data accuracy. For material specifications, when the procurement department selects materials, it details and records information such as the model, performance indicators, and manufacturer of the materials. This information can be obtained from the product manuals provided by material suppliers and manually verified before being entered into the system.

[0040] Construction progress collection: Progress monitoring cameras are deployed at the construction site. Using image recognition technology, photos of the construction area are taken regularly. Through image analysis algorithms, by comparing photos at different times, the completed parts of the construction are identified to estimate the construction progress. At the same time, construction workers use the project management application on mobile devices to record the start time, completion time, labor and equipment input of construction tasks in real time. These data are automatically uploaded to the data acquisition server.

[0041] Material usage collection: Electronic tag identification devices are installed in the material warehouse. When materials enter and leave the warehouse, the devices automatically read the electronic tag information of the materials and record data such as the issuing time, quantity, and usage location of the materials. During the process of using materials, if construction workers find quality problems or special usage situations of the materials, they manually enter the relevant information through mobile devices to supplement the integrity of the material usage data.

[0042] Environmental monitoring data collection: Temperature and humidity sensors, noise monitors, air quality monitoring equipment, etc. are arranged at the construction site. These sensors automatically collect environmental data at set time intervals and send the data to the data acquisition server through a wireless transmission module. The data acquisition server conducts preliminary verification on the received data, such as checking whether the data is within a reasonable range. If it exceeds the range, it is marked as abnormal data and awaits subsequent processing.

[0043] Optionally, as an embodiment of the present invention, after step S1, it includes preprocessing the project management data, specifically including: For duplicate data, calculate the feature values of each data record. For example, use a hash function to calculate the key information (such as time, construction location, data type, etc.) in the record to generate a unique hash value. By comparing the hash values, determine whether the data is duplicate. If the hash values are the same, it is considered duplicate data and is deleted. For incorrect data, make a judgment based on the logical relationship of the data. For example, in construction progress data, if the completion time of a certain process is earlier than the start time, it is determined as incorrect data. For incomplete data, check whether the required fields in the data record are empty. If they are empty, mark it as incomplete data, which can be supplemented manually or filled reasonably based on historical data.

[0044] Determine a unified data format standard. For example, the date is unified in the format of "YYYY - MM - DD", and numbers are represented with specific decimal places, etc. For data from different sources, write data conversion rules. For example, for temperature data obtained from sensors, if its original format is a string with a unit (such as "25℃"), the numerical part needs to be extracted and converted into a numerical type, and at the same time, a unified temperature unit identifier is added.

[0045] Adopt the min - max normalization method to map data with different dimensions and magnitudes to the interval [0, 1], eliminating the influence of dimensions and magnitudes.

[0046] Optionally, as an embodiment of the present invention, before model training in step S2, it includes: Construct an objective function based on management tags:

[0047] where is the weight coefficient, is the cost efficiency, is the progress accuracy rate, is the quality performance, is the degree of risk reduction;

[0048] where T is the total project cycle, is the value actually completed by the project at time t (calculated by multiplying the completed project quantity by the corresponding unit price), is the total cost invested at time t (including labor, materials, equipment costs, etc.), reflecting the proportional relationship between the project cost input and the actual output value. The larger the value, the higher the cost utilization efficiency;

[0049] where m is the number of tasks in the project, is the actual completion time of task i, is the planned completion time of task i, measuring the deviation degree between the actual progress and the planned progress of the project. The closer the value is to 1, the better the progress control, and the more accurate the model's prediction and management of the progress;

[0050] where k is the number of indicators of the project quality evaluation index, is the score of the j - th quality evaluation index, is the weight of the j - th quality evaluation index, comprehensively reflecting the quality performance of the project. The higher the score, the better the quality;

[0051] where s is the number of identified risks, is the probability of risk l occurring, is the impact degree on the project after the risk occurs (measured by a quantified loss index, such as the increased cost amount, the number of days of construction period delay, etc.), reflecting the effect of the model in risk identification and response measure formulation. The larger the value, the better the model manages risks and the lower the overall risk of the project.

[0052] Optionally, as an embodiment of the present invention, in step S2, the training of the neural network model specifically includes: Initialize the neural network model. The model includes an input layer, a hidden layer, and an output layer. The input of the model is historical project management data, and the output of the model is the types and contents of cost control, schedule management, quality management, and risk management; Calculate the loss value of the model based on the objective function, calculate the gradients of the loss value with respect to the model weights and biases in combination with the backpropagation algorithm, and use the optimization algorithm to update the model weights and biases; Repeat the above steps. When the loss value is less than the preset loss threshold, stop training to obtain the trained neural network model.

[0053] Optionally, as an embodiment of the present invention, in step S3, the management decision-making methods for cost management include: In the early stage of the project, obtain cost-related factors, such as building area, building type, geographical location, etc. as independent variables, establish a mathematical model between cost and these factors based on the linear regression algorithm, predict the project cost, and set an initial expectation for the project cost to help the project team plan funds and resources in advance; During the project execution process, record data such as the actual workload completed, actual cost, and planned cost of the project in real time. Calculate the project cost deviation based on the earned value management algorithm, and calculate the earned value (EV, the budgeted value of the completed work), planned value (PV, the budgeted value of the planned work), and actual cost (AC, the actual cost of the completed work). Calculate the cost deviation through the formula (CV = EV - AC) to determine whether the project cost is overspent; When the project cost deviation result indicates that the cost is overspent, reallocate the project resources, analyze the usage efficiency and necessity of each resource, such as reducing unnecessary material waste, optimizing personnel allocation, etc. Reallocate resources from non-critical tasks or tasks with low efficiency to critical tasks or tasks in urgent need of resources to control costs and ensure that the overall project schedule is not affected too much.

[0054] Optionally, as an embodiment of the present invention, in step S3, the management decision-making methods for schedule management include: Calculate the earliest start time, earliest finish time, latest start time, and latest finish time of each task based on the critical path method, and determine the critical path of the project, that is, the path composed of tasks with zero total float. The critical path determines the shortest duration of the project, and the progress of critical tasks directly affects the overall progress of the project; Judge whether the actual progress of each task lags behind based on the latest start time and latest end time, and judge whether the resources of each task are idle based on the earliest start time and earliest end time. When a critical task is determined to have a lag in actual progress, allocate the idle resources of non-critical tasks to critical tasks.

[0055] Optionally, as an embodiment of the present invention, in step S3, the management decision-making methods for quality management include: Collect various quality data during the construction process of the construction project, such as raw material quality data, construction process parameter data, finished product quality inspection data, etc. Based on the statistical process control algorithm in Six Sigma management, perform statistical analysis on the process data, calculate statistical quantities such as the mean and standard deviation of the data. According to the statistical analysis results, draw control charts, such as mean-range control charts, mean-standard deviation control charts, etc. There are center lines, upper control limits, and lower control limits on the control charts, which are used to monitor the stability of the process and quality fluctuations, and monitor the stability of the process and quality fluctuations; During the project construction process, continuously monitor the data points on the control chart. When the data points exceed the control limits, it indicates that the process may be abnormal. Immediately start the troubleshooting process to find the reasons for quality fluctuations, such as raw material quality problems, improper operation of construction personnel, etc., and issue an abnormal warning to take corrective measures in a timely manner to ensure the project quality.

[0056] Optionally, as an embodiment of the present invention, in step S3, the management decision-making methods for risk management include: Identify the potential uncertainty factors in the project, such as weather changes, policy adjustments, market fluctuations, etc. Based on the Monte Carlo simulation algorithm, perform multiple simulations on the uncertainty factors in the project to generate a large number of possible results. Through the analysis of these results, evaluate the risk distribution and overall risk level of the project to determine high-probability and high-impact risks, and formulate corresponding countermeasures according to the risk types, such as risk avoidance, risk mitigation, risk transfer, etc.; Decompose the risks into multiple levels based on the analytic hierarchy process. By comparing the relative importance of factors in each level, construct a judgment matrix, calculate the weights of each factor, so as to determine the priority of risks. Based on the priority of risks, determine the risk types to be processed first, and implement the countermeasures.

[0057] Optionally, as an embodiment of the present invention, for example, a real estate company plans to construct a high-rise residential project with a total construction area of 50,000 square meters, including 4 residential buildings with 25 floors each and supporting facilities, and the expected construction period is 24 months. The project aims to create high-quality residences to meet the housing needs of the surrounding residents.

[0058] Design parameter collection: The design team uses professional software to complete the design and automatically records parameters such as building structure, house type layout, and material specifications. For example, a reinforced concrete frame-shear wall structure is adopted, the house types on the standard floors vary from 80 to 120 square meters, and the main building materials are cement, steel bars, etc. of specific grades. The drawings are carefully reviewed manually, and the key parameters are marked. After the procurement department determines the material information, it is manually checked and entered into the system.

[0059] Construction progress collection: Multiple high-definition cameras are installed at the construction site, and image recognition technology is used to take pictures regularly and analyze the construction progress. Construction workers use a mobile application to record the task time, labor, and equipment input in real time. For example, during the foundation construction, the usage duration of excavators and tower cranes and the number of construction workers are recorded daily, and the data is automatically uploaded.

[0060] Material usage collection: The material warehouse is equipped with electronic tag recognition equipment to automatically record the material in and out information. When construction workers find material quality problems or special usage situations, they enter them in time through mobile devices. For example, when color difference problems are found during the paving of a certain batch of tiles, they are immediately recorded and reported.

[0061] Environmental monitoring data collection: Temperature, humidity, noise, and air quality sensors are arranged at the construction site to collect data regularly and wirelessly transmit it to the server. The server conducts preliminary verification of the data and marks the abnormal values. For example, during the concrete pouring period, if it is monitored that the environmental temperature is too high, which may affect the performance of the concrete, the data is marked in time for subsequent processing.

[0062] Cost management decision-making: At the initial stage of the project, data such as construction area, building type, and local building material prices are collected, and a linear regression algorithm is used to predict the project cost and formulate a budget. During the project implementation, the earned value management algorithm is adopted to compare the planned value (PV), earned value (EV), and actual cost (AC). If a cost deviation (CV = EV - AC < 0) is found, the reasons are analyzed and resources are reallocated. For example, if it is found that the labor cost exceeds the budget in a certain stage, the construction process is optimized to reduce unnecessary labor input, and some workers are transferred to key construction tasks.

[0063] Schedule management decision: Use the critical path method to determine the project's critical path and the time parameters of each task, such as critical tasks like foundation construction and main structure construction. Judge the progress lag by comparing the actual time and the latest time of the task, and judge the resource idleness by comparing the actual time and the earliest time. If the progress of the critical task of main structure construction lags behind, allocate the idle equipment and personnel of non-critical tasks such as preliminary preparation for landscape greening to the main structure construction.

[0064] Quality management decision: Collect quality data during construction, such as the strength of concrete test blocks and the data of steel bar tensile tests. Use the statistical process control algorithm in Six Sigma management to draw control charts. When the data points of concrete strength exceed the control limit, start the investigation process, check the quality of raw materials, construction technology, etc. If it is found that the problem is with the quality of cement, immediately replace the supplier and issue a quality anomaly warning.

[0065] Risk management decision: Identify project risk factors, such as bad weather, policy changes, material price fluctuations, etc. Use the Monte Carlo simulation algorithm to simulate multiple times to evaluate the risk distribution and the overall risk level. For risks with high probability and high impact, such as the project duration delay caused by heavy rain, formulate coping strategies, such as preparing drainage equipment in advance and adjusting the construction plan. Use the analytic hierarchy process to rank the risks and prioritize the handling of important risks, such as the impact of policy changes on project approval, arrange special personnel to track policy dynamics and prepare coping plans in advance.

[0066] Based on the basis of various management decisions, manage the project comprehensively. When the cost overruns, in addition to resource allocation, renegotiate the price with the supplier and optimize the procurement plan. When the schedule is delayed, increase the number of construction shifts and reasonably adjust the construction sequence. When the quality is abnormal, strictly check and rectify, and train the relevant responsible persons. For high-risk events, such as heavy rain, start the emergency plan, drain water in time and adjust the subsequent construction arrangements to ensure the smooth progress of the project, and finally achieve the goals of delivering the project on time, controlling the cost within the budget, meeting the quality standards and controlling the risks.

[0067] In some embodiments, the building project full life cycle management system may include multiple functional modules composed of computer program segments. The computer programs of each program segment in the building project full life cycle management system can be stored in the memory of the computer device and executed by at least one processor to execute (see Figure 1 description) the functions of building project full life cycle management.

[0068] In this embodiment, the building project full life cycle management system can be divided into multiple functional modules according to the functions it performs, such as Figure 2As shown in the figure. The functional modules of the system may include: a data acquisition module, a model training module, a decision-making selection module, and a decision-making execution module. The modules referred to in the present invention refer to a series of computer program segments that can be executed by at least one processor and can complete fixed functions, and are stored in a memory. In this embodiment, the functions of each module will be described in detail in subsequent embodiments. The system includes: A data acquisition module that acquires project management data, where the project management data includes design parameters, construction progress data, material usage data, and environmental monitoring data; A model training module that sets corresponding management label types and contents for historical project management data, and trains a neural network model based on the historical project management data and management labels. The management labels include cost control management, progress management, quality management, and risk management; A decision-making selection module that inputs the current project management data into the neural network model, and the model outputs the corresponding management label types and contents, and selects the corresponding management decision-making method based on the management label types and contents; A decision-making execution module that calculates the basis for the cost, progress, quality, and risk that need to be managed for the project based on the corresponding management decision-making method, and manages the project based on the basis that needs to be managed currently.

[0069] The data acquisition, model training, decision-making selection, and decision-making execution modules cooperate with each other to comprehensively collect project management data and conduct in-depth analysis. By training the neural network model, it can accurately identify project management problems and match appropriate decision-making methods, and then effectively control the project cost, progress, quality, and risk based on the scientifically calculated management basis, improve the accuracy, timeliness, and scientific nature of project management, ensure the smooth progress of the project, improve the overall efficiency of the project, and enhance the project's ability to handle complex situations.

[0070] Figure 3 It is a schematic structural diagram of a terminal provided by an embodiment of the present invention, and this terminal can be used to execute the method for the full life cycle management of construction projects provided by the embodiment of the present invention.

[0071] Among them, the terminal may include: a processor, a memory, and a communication unit. These components communicate through one or more buses. Those skilled in the art can understand that the structure of the server shown in the figure does not constitute a limitation to the present invention. It can be a bus structure, a star structure, and may also include more or fewer components than shown in the figure, or combine some components, or have different component arrangements.

[0072] Among them, the memory can be used to store the execution instructions of the processor. The memory can be implemented by any type of volatile or non-volatile storage terminal or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disc. When the execution instructions in the memory are executed by the processor, the terminal can execute some or all of the steps in the above method embodiments.

[0073] The processor is the control center of the storage terminal, connecting various parts of the entire electronic terminal through various interfaces and lines. By running or executing software programs and / or modules stored in the memory, and by calling data stored in the memory, it executes various functions of the electronic terminal and / or processes data. The processor can be composed of an integrated circuit (IC). For example, it can be composed of a single packaged IC, or can be composed of multiple packaged ICs with the same or different functions connected together. For example, the processor can include only a central processing unit (CPU). In the embodiment of the present invention, the CPU can be a single operation core or can include multiple operation cores.

[0074] The communication unit is used to establish a communication channel so that the storage terminal can communicate with other terminals. It receives user data sent by other terminals or sends user data to other terminals.

[0075] The present invention also provides a computer storage medium. Among them, the computer storage medium can store a program, and when the program is executed, it can include some or all of the steps in the embodiments provided by the present invention. The storage medium can be a magnetic disk, an optical disc, a read-only memory (ROM), a random access memory (RAM), etc.

[0076] Those skilled in the art can clearly understand that the technology in the embodiments of the present invention can be implemented by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solutions in the embodiments of the present invention, in essence, or the part that contributes to the prior art can be embodied in the form of a software product. This computer software product is stored in a storage medium such as a USB flash drive, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk, or an optical disc, etc., various media that can store program codes, including several instructions to enable a computer terminal (which can be a personal computer, a server, or a second terminal, a network terminal, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention.

[0077] For the same or similar parts among the various embodiments in this specification, reference can be made to each other. In particular, for the terminal embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the descriptions in the method embodiments.

[0078] In several embodiments provided by the present invention, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For example, the division of the modules is only a logical function division. In actual implementation, there can be other division methods. For example, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection to each other can be through some interfaces. The indirect coupling or communication connection of systems or modules can be in an electrical, mechanical, or other form.

[0079] The modules described as separate components may or may not be physically separated. The components shown as modules may or may not be physical modules, that is, they can be located in one place, or they can be distributed to multiple network modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0080] In addition, in each embodiment of the present invention, the various functional modules can be integrated in a processing module, or each module can exist physically alone, or two or more modules can be integrated in one module.

[0081] Although the present invention has been described in detail by reference to the accompanying drawings and in conjunction with the preferred embodiments, the present invention is not limited thereto. Without departing from the spirit and essence of the present invention, those of ordinary skill in the art can make various equivalent modifications or substitutions to the embodiments of the present invention, and all such modifications or substitutions should be within the scope of the present invention. / Any person skilled in the art within the technical scope disclosed by the present invention can easily conceive of changes or substitutions, which should all be covered within the protection scope of the present invention.

Claims

1. A construction project life cycle management method, characterized in that: The following steps are involved: S1, obtaining project management data, which includes design parameters, construction progress data, material usage data and environmental monitoring data; S2, setting corresponding management tag types and contents for historical project management data, and training the neural network model based on historical project management data and management tags. Management tags include cost control management, schedule management, quality management and risk management; S3, input the current project management data into the neural network model, the model outputs the corresponding management tag type and content, and selects the corresponding management decision method based on the management tag type and content; S4, calculates the cost, progress, quality and risk basis that the project currently needs to manage based on the corresponding management decision-making method, and manages the project based on the basis that currently needs to be managed.

2. The construction project life cycle management method according to claim 1, characterized in that: Before model training in step S2, the following steps are included: Construct the objective function based on the management tags: in, is the weight coefficient, is cost efficiency, is the progress accuracy, is quality performance, is the degree of risk reduction; Where T is the total project period, is the value of the project actually completed at time t, is the total cost invested at time t; Where m is the number of tasks in the project, is the actual completion time of task i, is the planned completion time of task i; Among them, k is the number of indicators of project quality assessment indicators, is the score of the jth quality assessment indicator, is the weight of the jth quality assessment indicator; Where s is the number of risks identified, is the probability of risk l occurring, It is the degree of impact on the project after the risk occurs.

3. The construction project life cycle management method according to claim 2 is characterized in that: In step S2, the training of the neural network model specifically includes: Initialize the neural network model, which includes an input layer, a hidden layer, and an output layer. The input of the model is historical project management data, and the output of the model is the type and content of cost control, schedule management, quality management, and risk management; Calculate the loss value of the model based on the objective function, calculate the gradient of the loss value to the model weights and biases based on the loss value combined with the back propagation algorithm, and use the optimization algorithm to update the model weights and biases; Repeat the above steps. When the loss value is less than the preset loss threshold, stop training and obtain a trained neural network model.

4. The construction project full life cycle management method according to claim 2 is characterized in that: In step S3, the management decision-making methods of cost management include: In the early stages of a project, project costs are predicted based on a linear regression algorithm to set initial expectations for project costs; During project execution, calculate project cost deviation based on earned value management algorithm; When the result of the project cost deviation is cost overrun, reallocate project resources.

5. The construction project full life cycle management method according to claim 2, characterized in that: In step S3, the management decision-making methods of progress management include: Calculate the earliest start time, earliest finish time, latest start time and latest finish time of each task based on the critical path method to determine the shortest duration and key tasks of the project; Based on the latest start time and the latest end time, determine whether the actual progress of each task is lagging behind. Based on the earliest start time and the earliest end time, determine whether the resources of each task are idle. When a critical task is determined to be lagging behind in actual progress, allocate idle resources of non-critical tasks to the critical task.

6. The construction project full life cycle management method according to claim 2 is characterized in that: In step S3, the management decision-making methods of quality management include: Based on the statistical process control algorithm in Six Sigma management, statistical analysis of process data is performed, control charts are drawn, and process stability and quality fluctuations are monitored. When data points exceed the control limits, the troubleshooting process is initiated and an abnormal warning is issued.

7. The construction project full life cycle management method according to claim 2, characterized in that: In step S3, the management decision-making methods of risk management include: Based on the Monte Carlo simulation algorithm, multiple simulations are conducted on the uncertainties in the project to evaluate the risk distribution and overall risk level of the project, so as to identify the risks with high probability and high impact, and formulate response strategies according to the risk types; Based on the hierarchical analysis method, risks are decomposed into multiple levels. By comparing the relative importance of factors in each level, a judgment matrix is ​​constructed and the weight of each factor is calculated to determine the priority of risks. Based on the priority of risks, the risk types that need to be prioritized are determined, and response strategies are implemented.

8. A construction project full life cycle management system, characterized in that: When the system is implemented, the construction project full life cycle management method according to any one of claims 1 to 7 is executed, and the system includes: Data acquisition module, which acquires project management data, including design parameters, construction progress data, material usage data and environmental monitoring data; Model training module, which sets corresponding management tag types and contents for historical project management data, and trains neural network models based on historical project management data and management tags. Management tags include cost control management, schedule management, quality management, and risk management. The decision selection module inputs the current project management data into the neural network model, and the model outputs the corresponding management tag type and content, and selects the corresponding management decision method based on the management tag type and content; The decision-making execution module calculates the cost, progress, quality and risk basis that the project currently needs to manage based on the corresponding management decision-making method, and manages the project based on the basis that currently needs to be managed.

9. A terminal, characterized in that: include: Storage device for storing the whole life cycle management program of the construction project; A processor is used to implement the steps of the construction project life cycle management method as described in any one of claims 1 to 7 when executing the construction project life cycle management program.

10. A computer-readable storage medium, characterized in that: The readable storage medium stores a construction project life cycle management program, and when the construction project life cycle management program is executed by the processor, the steps of the construction project life cycle management method as described in any one of claims 1-7 are implemented.

Images