Scheduling optimization method and device of infrastructure project, computer equipment, storage medium and program product

Abstract

The invention relates to an infrastructure project scheduling optimization method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the steps of obtaining initial current data and initial historical data of a to-be-optimized project, and performing data preprocessing on the initial current data and the initial historical data to obtain current data and historical data; determining a key index based on the current data, analyzing a current scheduling mode of the to-be-optimized project through the key index, and determining a scheduling analysis result; performing time sequence analysis and machine learning model prediction on the current data and the historical data to obtain a predicted resource demand and a predicted project progress; and constructing a scheduling optimization model through the scheduling analysis result, the predicted resource demand and the predicted project progress, and performing scheduling optimization on the current scheduling mode through the scheduling optimization model. By adopting the method, the rationality of resource allocation of the capital construction project and the progress reliability of the capital construction project can be improved.

Description

Technical Field

[0001] The present application belongs to the field of power grid technology, and in particular, relates to a method, device, computer equipment, storage medium and program product for scheduling optimization of infrastructure projects. Background Art

[0002] As electricity demand continues to grow, the scale and complexity of distribution network infrastructure projects are also increasing. In this context, how to effectively dispatch resources and optimize project schedules has become an important challenge facing power companies and construction units. Traditional dispatching methods usually rely on manual experience and simple rules, and it is difficult to cope with the dynamic changes of multiple complex factors, such as the real-time supply of resources, the variability of the construction environment, and the volatility of project schedules. In this case, inefficient resource allocation and project schedule delays not only increase project costs, but may also affect the stability and reliability of the entire power system.

[0003] The current scheduling system cannot fully utilize the engineering progress data, resource data, and environmental data accumulated during the project process. This leads to the lack of scientific basis for scheduling decisions when responding to emergencies or predicting future resource needs, which is prone to problems such as uneven resource allocation, task conflicts, and project progress delays. Therefore, how to optimize the scheduling of infrastructure projects to ensure the rationality of resource allocation and the reliability of the progress of infrastructure projects is an urgent problem to be solved. Summary of the invention

[0004] Based on this, it is necessary to provide a scheduling optimization method, device, computer equipment, storage medium and program product for infrastructure projects that can optimize the scheduling of infrastructure projects to improve the rationality of resource allocation and the progress reliability of infrastructure projects in response to the above technical problems.

[0005] In a first aspect, the present application provides a method for optimizing the scheduling of an infrastructure project, comprising:

[0006] Obtaining initial current data and initial historical data of the project to be optimized, and performing data preprocessing on the initial current data and initial historical data to obtain current data and historical data;

[0007] Determine key indicators based on current data, and analyze the current scheduling mode of the project to be optimized through the key indicators to determine the scheduling analysis results for the current scheduling mode;

[0008] Perform time series analysis and machine learning model prediction on current and historical data to obtain predicted resource requirements and project progress;

[0009] A scheduling optimization model is constructed through scheduling analysis results, predicted resource requirements and predicted project progress, and the current scheduling mode is optimized through the scheduling optimization model.

[0010] In one embodiment, the key indicator includes a project progress deviation; the project progress deviation is used to measure the deviation of the current project progress compared to the project planned progress;

[0011] Determine key indicators based on current data, including:

[0012] Extract the engineering progress data from the current data; the engineering progress data includes the current project progress and the project plan progress;

[0013] Determine the progress difference between the current project progress and the project planned progress, calculate the ratio of the progress difference to the project planned progress, and determine the obtained ratio result as the project progress deviation;

[0014] Analyze the current scheduling mode of the project to be optimized through key indicators, and determine the scheduling analysis results for the current scheduling mode, including:

[0015] The progress deviation of the current scheduling mode of the project to be optimized is analyzed through the engineering progress deviation to determine the engineering progress deviation result of the current scheduling mode; the scheduling analysis result includes the engineering progress deviation result.

[0016] In one embodiment, the key indicator includes resource utilization rate; the resource utilization rate is used to describe the utilization rates of different types of resources in the project to be optimized;

[0017] Determine key indicators based on current data, including:

[0018] Extract resource data from the current data; the resource data includes actual usage corresponding to different types of resources and available capacity corresponding to different types of resources;

[0019] For each type of resource, the ratio of the actual usage of the resource to the available capacity of the resource is calculated, and the obtained ratio result is determined as the resource utilization rate of the resource;

[0020] Analyze the current scheduling mode of the project to be optimized through key indicators, and determine the scheduling analysis results for the current scheduling mode, including:

[0021] The resource utilization analysis is performed on the current scheduling mode of the project to be optimized through the resource utilization to determine the resource utilization result of the current scheduling mode; the scheduling analysis result includes the resource utilization result.

[0022] In one embodiment, the key indicator includes a resource balance rate; the resource balance rate is used to describe the degree of balance in the use of various resources in the project to be optimized;

[0023] Determine key indicators based on current data, including:

[0024] Extract resource data from the current data; the resource data includes actual usage corresponding to different types of resources and available capacity corresponding to different types of resources;

[0025] For each type of resource, obtain the resource's timeliness factor and resource's substitutability factor;

[0026] Determine the resource balance rate of resources through actual usage, available capacity, timeliness factor and substitutability factor;

[0027] Analyze the current scheduling mode of the project to be optimized through key indicators, and determine the scheduling analysis results for the current scheduling mode, including:

[0028] The resource balance rate is used to analyze the current scheduling mode of the project to be optimized, and the resource balance rate result of the current scheduling mode is determined; the scheduling analysis result includes the resource balance rate result.

[0029] In one embodiment, for each type of resource, obtaining the timeliness factor of the resource and the substitutability factor of the resource includes:

[0030] Use the critical path method to determine the critical tasks and non-critical tasks in the project to be optimized, and determine the critical task urgency of the critical tasks by the remaining time and total time of the critical tasks, and determine the non-critical task urgency of the non-critical tasks by the remaining time and total time of the non-critical tasks;

[0031] For each type of resource, determine the task urgency of the task associated with the resource, and determine the timeliness factor of the resource based on the task urgency and the task type of the task associated with the resource;

[0032] For each type of resource, determine the scarcity and market availability of the resource, and determine the substitutability factor of the resource through scarcity and market availability.

[0033] In one embodiment, the scheduling analysis results include: project progress deviation results, resource utilization results, and resource balance rate results; the project progress deviation results are used to describe the difference between the actual completion time and the planned completion time; the resource utilization results are used to describe the usage of resources; and the resource balance rate results are used to describe the unit cost of resources;

[0034] Forecast resource requirements include the number of resources required for each task in the project to be optimized;

[0035] The project progress forecast includes: the total construction period of the project to be optimized, the start time, duration and end time of each task in the project to be optimized, the progress deviation, actual completion time and planned completion time of each task;

[0036] Build a scheduling optimization model through scheduling analysis results, predicting resource requirements and predicting project progress, including:

[0037] The objective function of the scheduling optimization model is constructed through the project progress deviation results, resource utilization results and resource balance rate results;

[0038] Construct resource constraints based on resource utilization results and predicted resource requirements, and construct time constraints and schedule deviation constraints based on predicted project progress;

[0039] The objective function is constrained by resource constraints, time constraints and progress deviation constraints, and the total cost of the project to be optimized and the total duration of the project to be optimized are minimized as the goals of the objective function to build a scheduling optimization model.

[0040] In a second aspect, the present application also provides a scheduling optimization device for an infrastructure project, comprising:

[0041] The data acquisition and processing module is used to acquire the initial current data and initial historical data of the project to be optimized, and perform data preprocessing on the initial current data and initial historical data to obtain the current data and historical data;

[0042] The data analysis module is used to determine key indicators based on current data, and analyze the current scheduling mode of the project to be optimized through the key indicators to determine the scheduling analysis results for the current scheduling mode;

[0043] The data analysis and prediction module is used to perform time series analysis and machine learning model prediction on current and historical data to obtain predicted resource requirements and project progress;

[0044] The scheduling optimization module is used to build a scheduling optimization model through scheduling analysis results, predicted resource requirements and predicted project progress, and to optimize the current scheduling mode through the scheduling optimization model.

[0045] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0046] Obtaining initial current data and initial historical data of the project to be optimized, and performing data preprocessing on the initial current data and initial historical data to obtain current data and historical data;

[0047] Determine key indicators based on current data, and analyze the current scheduling mode of the project to be optimized through the key indicators to determine the scheduling analysis results for the current scheduling mode;

[0048] Perform time series analysis and machine learning model prediction on current and historical data to obtain predicted resource requirements and project progress;

[0049] A scheduling optimization model is constructed through scheduling analysis results, predicted resource requirements and predicted project progress, and the current scheduling mode is optimized through the scheduling optimization model.

[0050] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0051] Obtaining initial current data and initial historical data of the project to be optimized, and performing data preprocessing on the initial current data and initial historical data to obtain current data and historical data;

[0052] Determine key indicators based on current data, and analyze the current scheduling mode of the project to be optimized through the key indicators to determine the scheduling analysis results for the current scheduling mode;

[0053] Perform time series analysis and machine learning model prediction on current and historical data to obtain predicted resource requirements and project progress;

[0054] A scheduling optimization model is constructed through scheduling analysis results, predicted resource requirements and predicted project progress, and the current scheduling mode is optimized through the scheduling optimization model.

[0055] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0056] Obtaining initial current data and initial historical data of the project to be optimized, and performing data preprocessing on the initial current data and initial historical data to obtain current data and historical data;

[0057] Determine key indicators based on current data, and analyze the current scheduling mode of the project to be optimized through the key indicators to determine the scheduling analysis results for the current scheduling mode;

[0058] Perform time series analysis and machine learning model prediction on current and historical data to obtain predicted resource requirements and project progress;

[0059] A scheduling optimization model is constructed through scheduling analysis results, predicted resource requirements and predicted project progress, and the current scheduling mode is optimized through the scheduling optimization model.

[0060] The scheduling optimization method, device, computer equipment, computer-readable storage medium and computer program product of the above-mentioned infrastructure project obtains the initial current data and initial historical data of the project to be optimized, and performs data preprocessing on the initial current data and initial historical data to obtain current data and historical data, and ensures the integrity and accuracy of the data through data preprocessing. Secondly, key indicators are determined based on the current data, and the current scheduling mode of the project to be optimized is analyzed through the key indicators to determine the scheduling analysis results for the current scheduling mode, so that the scheduling analysis results are based on data analysis rather than relying on empirical judgment. Therefore, the current data and historical data are then subjected to time series analysis and machine learning model prediction to obtain predicted resource demand and predicted project progress. Predicted resource demand and predicted project progress help to make resource demand configuration and project progress time arrangements in advance to reduce unforeseen risks. Therefore, a scheduling optimization model is constructed through scheduling analysis results, predicted resource requirements and predicted project progress, and the current scheduling mode is optimized through the scheduling optimization model. Efficient allocation of resources and precise adjustment of task time under the current scheduling mode can be achieved from multiple dimensions, ensuring that the projects to be optimized are completed on time and resources are effectively utilized, thereby improving the rationality of resource allocation of infrastructure projects and the progress reliability of infrastructure projects. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0062] FIG1 is an application environment diagram of a method for optimizing scheduling of infrastructure projects in one embodiment;

[0063] Figure 2 A schematic diagram of a flow chart of a method for optimizing scheduling of infrastructure projects in one embodiment;

[0064] Figure 3 A schematic flow chart of a method for optimizing scheduling of infrastructure projects in another embodiment;

[0065] Figure 4 is an overall flow chart of a scheduling optimization method for infrastructure projects in one embodiment;

[0066] Figure 5It is a structural block diagram of a scheduling optimization device for a capital construction project in one embodiment;

[0067] Figure 6 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0068] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0069] With the continuous growth of electricity demand, the scale and complexity of distribution network infrastructure projects are also increasing. In this context, how to effectively dispatch resources and optimize project progress has become an important challenge faced by power companies and construction units. Traditional dispatching methods usually rely on manual experience and simple rules, which are difficult to cope with the dynamic changes of multiple complex factors, such as the real-time supply of resources, the variability of the construction environment, and the volatility of project progress. In this case, the inefficient allocation of resources and the delay of project progress not only increase the project cost, but also may affect the stability and reliability of the entire power system. The current dispatching system cannot make full use of the engineering progress data, resource data, and environmental data accumulated during the project process. As a result, when responding to emergencies or predicting future resource needs, dispatching decisions often lack scientific basis, and are prone to problems such as uneven resource allocation, task conflicts, and project progress delays. Therefore, how to optimize the dispatching of infrastructure projects to ensure the rationality of resource allocation for infrastructure projects and the reliability of the progress of infrastructure projects are urgent problems to be solved.

[0070] Therefore, in an embodiment of the present application, a scheduling optimization method for infrastructure projects is provided, which can optimize the scheduling of infrastructure projects to improve the rationality of resource allocation of infrastructure projects and the reliability of the progress of infrastructure projects. The scheduling optimization method for infrastructure projects provided in an embodiment of the present application can be applied in an application environment as shown in Figure 1. Among them, the terminal 102 communicates with the server 104 via a network. The data storage system can store data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers.

[0071] Specifically, taking the application to server 104 as an example, the initial current data and initial historical data of the project to be optimized are obtained, and the initial current data and initial historical data are preprocessed to obtain the current data and historical data; the key indicators are determined based on the current data, and the current scheduling mode of the project to be optimized is analyzed through the key indicators to determine the scheduling analysis results for the current scheduling mode; the current data and historical data are subjected to time series analysis and machine learning model prediction to obtain predicted resource demand and predicted project progress; the scheduling optimization model is constructed through the scheduling analysis results, predicted resource demand and predicted project progress, and the current scheduling mode is optimized through the scheduling optimization model. The integrity and accuracy of the data are ensured through data preprocessing, and the obtained scheduling analysis results are based on data analysis rather than relying on empirical judgment, and the obtained predicted resource demand and predicted project progress are helpful to make resource demand configuration and project progress time arrangement in advance to reduce unforeseen risks. Therefore, from the aforementioned multiple dimensions, efficient allocation of resources and precise adjustment of task time under the current scheduling mode are achieved to ensure that the project to be optimized is completed on time and resources are effectively utilized, thereby improving the rationality of resource allocation of infrastructure projects and the reliability of the progress of infrastructure projects.

[0072] The terminal 102 may be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, IoT devices, and portable wearable devices. The IoT devices may be smart speakers, smart TVs, smart air conditioners, smart car devices, projection devices, etc. Portable wearable devices may be smart watches, smart bracelets, head-mounted devices, etc. Head-mounted devices may be virtual reality (VR) devices, augmented reality (AR) devices, smart glasses, etc. The server 104 may be an independent physical server, a server cluster or distributed system consisting of multiple physical servers, or a cloud server that provides cloud computing services.

[0073] In an exemplary embodiment, Figure 2 As shown, a method for optimizing the scheduling of infrastructure projects is provided. This embodiment uses the method applied to the server 104 shown in FIG. 1 as an example for illustration. It can be understood that the method can also be applied to the terminal 102 shown in FIG. 1 , and can also be applied to a system including the terminal 102 and the server 104, and is implemented through the interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0074] Step 202: Acquire initial current data and initial historical data of the project to be optimized, and perform data preprocessing on the initial current data and initial historical data to obtain current data and historical data.

[0075] Among them, the initial current data includes project progress data, resource data and environmental data, while the initial historical data includes resource allocation records, progress records and environmental impact data. First, the initial current data is introduced. The aforementioned project progress data at least includes the current project progress and the project plan progress. The project progress data is used to measure the progress of the project to be optimized. The project progress data at least includes the following specific items: the percentage of completed tasks in the project to be optimized, the comparison between the tasks in the project plan and the tasks actually completed in the project to be optimized, the execution status of the currently executed tasks in the project to be optimized, the start date of the currently executed tasks in the project to be optimized, and the expected end date of the currently executed tasks in the project to be optimized.

[0076] Secondly, resource data refers to various types of data related to the actual usage of different types of resources and the available capacity of different types of resources. That is, resource data at least includes the actual usage corresponding to different types of resources, the available capacity corresponding to different types of resources, and resource utilization. The actual usage corresponding to the above-mentioned different types of resources can be the actual usage of labor, the actual usage of equipment, the actual usage of materials, etc. The available capacity corresponding to different types of resources can be the number of available labor, the number of available equipment, the available material inventory, etc. The resource utilization rate is used to reflect the efficiency of the use of different types of resources.

[0077] Environmental data is used to describe the external condition data of the construction site of the project to be optimized, that is, environmental data at least includes meteorological data, geological data, external event data and other external condition data of the construction site. The aforementioned meteorological data at least includes temperature, humidity, rainfall, wind speed, etc., geological data at least includes soil type, surface water conditions, etc., and external event data at least includes traffic conditions, changes in laws and regulations, etc.

[0078] The following is an introduction to the initial historical data. Resource allocation records are historical data on resource allocation in historical projects related to the project to be optimized. Resource allocation records are used to analyze resource utilization and allocation efficiency. Resource allocation records include at least: historical use records of resources in different tasks; records of resource scheduling and reallocation; historical situations of resource overload or idleness. Secondly, progress records are data that reflect the historical progress of the project, that is, progress records include at least historical progress deviations, timelines and node events for task completion, and records of historical delays or early completion. Environmental impact data is used to record the impact of environmental factors on historical projects related to the project to be optimized. Environmental impact data include at least: the impact of specific weather conditions on progress, the impact of geological events (such as earthquakes and landslides) on project progress, and the impact of external policy or legal changes on construction.

[0079] Similarly, current data is the initial current data after data preprocessing, and historical data is the initial historical data after data preprocessing. That is, current data and historical data are complete and more accurate data. Therefore, current data includes complete and more accurate project progress data, resource data, and environmental data, while historical data includes complete and more accurate resource allocation records, progress records, and environmental impact data. I will not go into details here.

[0080] Specifically, the server obtains the initial current data and initial historical data of the project to be optimized. The server can obtain the initial current data and initial historical data by actively transmitting data through the project person in charge of the project to be optimized. Alternatively, the server obtains the stored data from the data storage system to obtain the initial current data and initial historical data. The method of obtaining data is not limited here.

[0081] Furthermore, considering that the data may be incomplete, the server may also perform data preprocessing on the acquired initial current data and initial historical data to obtain current data and historical data. The aforementioned data preprocessing includes data cleaning, data standardization and normalization, and time series reconstruction.

[0082] The following is an introduction to data preprocessing:

[0083] 1. Data cleaning: Data cleaning includes missing value processing, outlier detection, and duplicate data removal.

[0084] Missing value processing is used to check the initial current data and initial historical data obtained, identify missing values ​​in the initial current data and initial historical data, and process the missing values ​​in the initial current data and initial historical data. The methods for processing missing values ​​can be interpolation, filling the mean, filling the median, deleting values ​​containing too many missing values, etc., which are not limited here.

[0085] Outlier detection usually requires the use of statistical analysis methods (such as standard deviation, box plot method, etc.) to identify abnormal data in the initial current data and initial historical data, and delete the abnormal data in the initial current data and initial historical data to ensure the validity of the current data and historical data obtained.

[0086] Deduplication is used to remove duplicate records in the initial current data and the initial historical data to avoid redundancy and errors in the obtained current data and historical data.

[0087] 2. Data standardization and normalization. Specifically, standardize the data of different dimensions in the initial current data and the initial historical data, and convert them into the same dimension for subsequent calculation and analysis. Commonly used methods include Z-score standardization and Min-Max normalization.

[0088] 3. Time series reconstruction. Specifically, based on the time series corresponding to the initial current data and the initial historical data, the initial current data and the initial historical data are reorganized according to the time sequence described by the time series to ensure that the temporal relationship between the data in the current data and the historical data is clear. Missing time points can be supplemented by interpolation methods. Secondly, the periodic data or seasonal data in the initial current data and the initial historical data can be processed to ensure that the impact of periodic fluctuations can be correctly identified and eliminated in subsequent data analysis.

[0089] Step 204, determining key indicators based on current data, and analyzing the current scheduling mode of the project to be optimized through the key indicators to determine a scheduling analysis result for the current scheduling mode.

[0090] Among them, the aforementioned key indicators at least include project progress deviation, resource utilization rate and resource balance rate. The aforementioned project progress deviation is used to measure the deviation of the current project progress compared with the project planned progress, the aforementioned resource utilization rate is used to describe the utilization rate of different types of resources in the project to be optimized, and the aforementioned resource balance rate is used to describe the balanced degree of utilization of various types of resources in the project to be optimized.

[0091] Secondly, the analysis of the current scheduling mode needs to be based on the similarity of key indicators, that is, a corresponding analysis is performed based on the key indicators introduced above. For example, when the key indicator is the project progress deviation, it is necessary to perform a progress deviation analysis on the current scheduling mode. Similarly, when the key indicator is the resource utilization rate, it is necessary to perform a resource utilization analysis on the current scheduling mode. When the key indicator is the resource balance rate, it is necessary to perform a resource balance rate analysis on the current scheduling mode. Therefore, in this embodiment, the scheduling analysis results include at least one of the following: project progress deviation results, resource utilization results, and resource balance rate results.

[0092] Specifically, the server first determines the key indicators based on the current data, that is, different key indicators are determined based on different types of data in the current data. Based on this, the current scheduling mode of the project to be optimized is analyzed through the key indicators to determine the scheduling analysis results for the current scheduling mode, that is, corresponding types of analysis are performed on different key indicators to determine the corresponding scheduling analysis results. Since the key indicators include at least project progress deviation, resource utilization rate and resource balance rate, the corresponding project progress deviation results, resource utilization rate results and resource balance rate results can be obtained by performing progress deviation diagnosis, resource utilization rate diagnosis and resource balance rate diagnosis based on the calculated project progress deviation, resource utilization rate and resource balance rate. The following is a corresponding introduction to the determination and corresponding analysis of different key indicators:

[0093] In a specific embodiment, the key indicator includes a project progress deviation; the project progress deviation is used to measure the deviation of the current project progress compared to the project planned progress. Determining the key indicator based on the current data includes: extracting the project progress data in the current data; the project progress data includes the current project progress and the project planned progress; determining the progress difference between the current project progress and the project planned progress, and calculating the ratio of the progress difference to the project planned progress, and determining the obtained ratio result as the project progress deviation.

[0094] Specifically, it can be known from the above introduction that the initial current data includes the engineering progress data, so more complete and accurate current data can be obtained after preprocessing the initial current data. Therefore, the server extracts the engineering progress data for the current data to extract the engineering progress data in the current data, and the engineering progress data includes the current project progress and the project plan progress. Based on this, the server calculates the difference between the current project progress and the project plan progress in the engineering progress data, that is, the progress difference between the current project progress and the project plan progress is obtained by subtracting the current project progress from the project plan progress, and then the ratio of the progress difference to the project plan progress is calculated, that is, the progress difference is used as the numerator and the project plan progress is used as the denominator to calculate the ratio result, and then the obtained ratio result is determined as the engineering progress deviation.

[0095] To facilitate understanding of the calculation method of project progress deviation, as shown in formula (1):

[0096] ; (1)

[0097] in, Indicates the deviation of project progress. Indicates the current project progress. Indicates the project plan progress. And A positive value indicates that the progress is ahead of schedule. A negative value indicates that progress is lagging behind.

[0098] Based on this, the current scheduling mode of the project to be optimized is analyzed through key indicators to determine the scheduling analysis results for the current scheduling mode, including: performing progress deviation analysis on the current scheduling mode of the project to be optimized through the engineering progress deviation to determine the engineering progress deviation result of the current scheduling mode; the scheduling analysis results include the engineering progress deviation result.

[0099] From this, we can see that the progress deviation analysis is to determine whether the project progress deviation is positive or negative. If the project progress deviation is positive, it means that the current project progress is ahead of schedule, and if the project progress deviation is negative, it means that the current project progress is lagging behind. In the subsequent optimization process, the progress should be adjusted according to the lagging progress of the current project progress.

[0100] In a specific embodiment, the key indicator includes resource utilization; resource utilization is used to describe the utilization rates of different types of resources in the project to be optimized. Determining the key indicator based on the current data includes: extracting resource data in the current data; the resource data includes actual usage corresponding to different types of resources, and available capacity corresponding to different types of resources; for each type of resource, calculating the ratio of the actual usage of the resource to the available capacity of the resource, and determining the obtained ratio result as the resource utilization rate of the resource.

[0101] Specifically, from the above introduction, it can be known that the initial current data includes resource data, so more complete and accurate current data can be obtained after preprocessing the initial current data. Therefore, the server extracts resource data for the current data to extract the resource data in the current data, and the resource data includes the actual usage corresponding to different types of resources, and the available capacity corresponding to different types of resources. Based on this, since there are actual usage and available capacity corresponding to different types of resources, the server needs to calculate the ratio of the actual usage of the resource to the available capacity of the resource for each type of resource, that is, the actual usage of the resource is used as the numerator, and the available capacity of the resource is used as the denominator to calculate the ratio to obtain the ratio result, and then the obtained ratio result is determined as the resource utilization rate of the resource.

[0102] To facilitate understanding of the calculation method of project progress deviation, take the case where there are n types of resources as an example, that is, there are n types of resources, as shown in formula (2):

[0103] ; (2)

[0104] in, represents the resource utilization of resource i, represents the actual usage of resource i, represents the available capacity of resource i, and n is the number of resources included in the resource data. And If the utilization rate is greater than the maximum threshold, it means that resource i is in a resource overload state. If the utilization rate is less than the minimum threshold, it means that resource i is in an idle state.

[0105] Based on this, the current scheduling mode of the project to be optimized is analyzed through key indicators to determine the scheduling analysis results for the current scheduling mode, including: performing resource utilization analysis on the current scheduling mode of the project to be optimized through resource utilization to determine the resource utilization results of the current scheduling mode; the scheduling analysis results include resource utilization results.

[0106] From this, we can see that resource utilization analysis is to compare the resource utilization of each resource with the maximum utilization threshold and the minimum utilization threshold to determine whether the project progress deviation is positive or negative. If the resource utilization of a resource is greater than the maximum utilization threshold, it means that the resource is in a state of resource overload, and if the resource utilization of a resource is less than the minimum utilization threshold, it means that the resource is in a state of resource idleness. In the subsequent optimization process, less scheduling optimization should be performed on resources that are in a state of resource overload in the current project progress, and more resource allocation optimization should be performed on resources that are in a state of resource idleness.

[0107] In a specific embodiment, the key indicator includes a resource balance rate; the resource balance rate is used to describe the degree of balance in the use of various types of resources in the project to be optimized. Determining the key indicator based on the current data includes: extracting resource data in the current data; the resource data includes the actual usage corresponding to different types of resources, and the available capacity corresponding to different types of resources; for each type of resource, obtaining the timeliness factor and the substitutability factor of the resource; determining the resource balance rate of the resource through the actual usage, available capacity, timeliness factor and substitutability factor.

[0108] Specifically, from the above introduction, it can be known that the initial current data includes resource data, so after preprocessing the initial current data, more complete and accurate current data can be obtained. Therefore, the server extracts resource data for the current data to extract the resource data in the current data, and the resource data includes the actual usage corresponding to different types of resources, and the available capacity corresponding to different types of resources. Based on this, since there are actual usage and available capacity corresponding to different types of resources, the server needs to obtain the timeliness factor and the substitutability factor of the resource for each type of resource, and then determine the resource balance rate of the resource through the actual usage, available capacity, timeliness factor and substitutability factor.

[0109] To facilitate understanding of the calculation method of resource balance rate, take the case where there are n types of resources as an example, that is, there are n types of resources, as shown in formula (3):

[0110] ; (3)

[0111] in, represents the resource balance rate of resource i, represents the actual usage of resource i, represents the available capacity of resource i, represents the actual usage of resource j, represents the available capacity of resource j, Does it represent the timeliness factor of resource i? represents the substitutability factor of resource i.

[0112] Based on this, the current scheduling mode of the project to be optimized is analyzed through key indicators to determine the scheduling analysis results for the current scheduling mode, including: performing a resource balance rate analysis on the current scheduling mode of the project to be optimized through the resource balance rate to determine the resource balance rate result of the current scheduling mode; the scheduling analysis results include the resource balance rate result.

[0113] It can be seen that since the resource balance rate is used to describe the degree of balance in the use of various resources in the project to be optimized, the resource balance rate analysis is to judge the difference between the resource balance rate of each resource and 1. The closer the value of the resource balance rate of a resource is to 1, the more balanced the resource allocation for the resource is, and the farther the value of the resource balance rate of a resource is from 1, the more unbalanced the resource allocation for the resource is. Therefore, in the subsequent optimization process, the resource allocation of resources with balanced resource allocation should be maintained according to the current project progress, but the resource allocation of resources with unbalanced resource allocation should be adjusted.

[0114] The following introduces a method for obtaining timeliness factors and substitutability factors. In a specific embodiment, for each type of resource, the timeliness factor and substitutability factor of the resource are obtained, including: using the critical path method to determine the critical tasks and non-critical tasks in the project to be optimized, and determining the critical task urgency of the critical tasks through the remaining time and total time of the critical tasks, and determining the non-critical task urgency of the non-critical tasks through the remaining time and total time of the non-critical tasks; for each type of resource, determining the task urgency of the task associated with the resource, and determining the timeliness factor of the resource through the task urgency and the task type of the task associated with the resource; for each type of resource, determining the scarcity and market supply of the resource, and determining the substitutability factor of the resource through the scarcity and market supply.

[0115] Specifically, the critical path method is first used to determine the critical tasks and non-critical tasks in the project to be optimized, and the critical task urgency of the critical task is determined by the remaining time and total time of the critical task, and the non-critical task urgency of the non-critical task is determined by the remaining time and total time of the non-critical task. The calculation method of task urgency is introduced below through formula (4):

[0116] ; (4)

[0117] in, represents the urgency of task i, represents the remaining time of task i, represents the total time of task i.

[0118] Furthermore, for each type of resource, the task urgency of the task associated with the resource is determined, and the timeliness factor of the resource is determined by the task urgency and the task type of the task associated with the resource. That is, the value of the binary variable is determined by determining the task type of each task associated with the resource. That is, when the task type of the task associated with the resource is a critical task, the value of the binary variable is 1, and when the task type of the task associated with the resource is a non-critical task, the value of the binary variable is 0. The calculation method of the timeliness factor is introduced below through formula (5):

[0119] ; (5)

[0120] in, represents the timeliness factor of resource i, represents a binary variable, and Indicates the weight coefficient, which can be preset. When the task type of the task associated with resource i is a critical task, the value of the binary variable is 1.

[0121] Furthermore, for each type of resource, the scarcity and market availability of the resource are determined, and the resource's substitutability factor is determined based on scarcity and market availability. The calculation method of the substitutability factor is introduced below through formula (6):

[0122] ; (6)

[0123] in, represents the substitutability factor, represents the scarcity of resource i, represents the market availability of resource i; Represents the adjustment coefficient. and Based on the quantitative evaluation of resource i. The value range is between 0 and 1. The smaller the value of the substitutability factor, the more difficult it is to replace the resource.

[0124] Therefore, by introducing the timeliness factor and the substitutability factor, it can adapt to different types of project and resource management needs. Since the timeliness factor combines the importance of resources with the criticality of project schedule by considering the time urgency of the task where the resource is located and whether it is on the critical path, it ensures that the resource allocation of critical tasks takes precedence over non-critical tasks. This can effectively reduce project delays caused by unreasonable resource allocation, thereby improving the progress control of the entire project. The substitutability factor reflects the scarcity and market availability of resources. Therefore, by introducing the substitutability factor, resources can be allocated more scientifically, avoiding the use of scarce resources that are difficult to replace, and giving priority to more easily available resources, thereby improving the flexibility and reliability of the scheduling plan.

[0125] The timeliness factor ensures the timely completion of key tasks and reduces the risk of overall project delays due to delays in key path tasks. By prioritizing the allocation of resources required for key tasks, project managers can better control progress and reduce the impact of uncertainty and emergencies. The substitutability factor helps managers identify high-risk resource scheduling and avoid over-reliance on resources that are difficult to replace, thereby reducing the negative impact of resource shortages or market supply fluctuations on projects. This risk prevention mechanism helps the smooth progress and on-time delivery of projects.

[0126] Step 206, perform time series analysis and machine learning model prediction on current data and historical data to obtain predicted resource requirements and predicted project progress.

[0127] Among them, time series analysis includes trend analysis, seasonal analysis and periodic analysis. The aforementioned trend analysis is based on the moving average method to smooth the data and is used to identify long-term trends. The aforementioned seasonal analysis uses the seasonal decomposition method to decompose the time series into trend, seasonal and residual parts, while the seasonal classification is calculated by calculating the mean of each cycle. The aforementioned periodic analysis identifies periodic patterns in time series based on autocorrelation functions and partial correlation functions.

[0128] Secondly, the machine learning model uses the Long Short-Term Memory (LSTM) model. The core of the aforementioned LSTM is the three gating mechanisms in its unit: input gate, forget gate, and output gate, which are used to control the writing, retention, and output of information respectively. Through these gating mechanisms, LSTM can dynamically adjust the flow of data during training, thereby capturing long-term dependencies in time series data.

[0129] Specifically, the time series analysis of the current data and historical data is first performed to obtain the time feature data. The aforementioned time feature data includes timestamps, calendar information (such as day of the week, month, season), etc. These data can help the model identify periodic and seasonal patterns. Therefore, the input data of the machine learning model (i.e., LSTM model) comes from the current data, historical data, and time feature data obtained through time series analysis. From the above introduction, it can be seen that these data include: project progress data (including the actual progress and planned progress of the current project, which is used to measure the execution of the project. The project progress data is usually provided in the form of a time series to reflect the progress of the project), resource data (including the actual usage of various resources, available capacity, resource utilization, and resource balance rate. These data reflect the use and distribution balance of resources in the project) and environmental data (including environmental factors affecting the construction site, such as climate, geological conditions, weather forecasts, etc., which will affect the construction progress and resource requirements) and time feature data.

[0130] Furthermore, the input data of the machine learning model (i.e., LSTM model) is organized in the form of a two-dimensional tensor, which includes at least time steps and features. Time steps represent different time points in a time series. For example, if you want to predict resource demand for the next month, the input time step of the machine learning model (i.e., LSTM model) may be resource utilization data for the past few months. Features represent different features input in each time step. In this embodiment, the features include project progress data, resource utilization, environmental data, etc.

[0131] Step 208, constructing a scheduling optimization model through scheduling analysis results, predicted resource requirements and predicted project progress, and performing scheduling optimization on the current scheduling mode through the scheduling optimization model.

[0132] Specifically, the objective function of the scheduling optimization model is constructed through the project progress deviation results, resource utilization results, and resource balance rate results, and the scheduling optimization model is constructed based on the conditional constraints of the objective function, so as to optimize the current scheduling mode through the constructed scheduling optimization model.

[0133] It should be understood that the corresponding examples in the embodiments of the present application are used to understand the present solution, but should not be understood as specific limitations of the present solution.

[0134] In the above-mentioned scheduling optimization method for infrastructure projects, data preprocessing is performed on the initial current data and the initial historical data to obtain the current data and the historical data, that is, the integrity and accuracy of the data are ensured by data preprocessing. And based on the current data, key indicators are determined, and the current scheduling mode of the project to be optimized is analyzed through the key indicators to determine the scheduling analysis results for the current scheduling mode, so that the scheduling analysis results are based on data analysis rather than relying on empirical judgment. Therefore, the current data and historical data are then subjected to time series analysis and machine learning model prediction to obtain predicted resource demand and predicted project progress. Predicted resource demand and predicted project progress help to make resource demand configuration and project progress time arrangement in advance to reduce unforeseen risks. Therefore, a scheduling optimization model is constructed through scheduling analysis results, predicted resource demand and predicted project progress, and the current scheduling mode is optimized through the scheduling optimization model, so as to achieve efficient allocation of resources and precise adjustment of task time under the current scheduling mode from multiple dimensions, and ensure that the project to be optimized is completed on time and resources are effectively utilized, thereby improving the rationality of resource allocation of infrastructure projects and the reliability of the progress of infrastructure projects.

[0135] The following is an introduction to the method of constructing a scheduling optimization model: In an exemplary embodiment, Figure 3 As shown in the figure, a scheduling optimization model is constructed by scheduling analysis results, predicting resource requirements and predicting project progress, including:

[0136] Step 302, constructing the objective function of the scheduling optimization model through the project progress deviation results, resource utilization results and resource balance rate results.

[0137] Specifically, the server constructs the objective function of the scheduling optimization model through the project progress deviation results, resource utilization results, and resource balance rate results. The aforementioned objective function includes a cost function for the total cost of the project to be optimized and a duration function for the total duration of the project to be optimized. The following introduces the construction method of the objective function through formula (7) and formula (8):

[0138] ; (7)

[0139] Among them, Z represents the cost function of the total cost of the project to be optimized, represents the unit cost of resource i, represents the usage of resource i, represents the delay penalty of task j, It represents the difference between the actual completion time and the planned time, n represents the number of resource types, Indicates the number of tasks.

[0140] ; (8)

[0141] in: Represents the total duration function of the project to be optimized, represents the duration of task j, and m represents the number of tasks.

[0142] Step 304: construct resource constraints based on the resource utilization results and the predicted resource demand, and construct time constraints and schedule deviation constraints based on the predicted project progress.

[0143] Specifically, resource constraints are constructed based on resource utilization results and predicted resource requirements, and time constraints and schedule deviation constraints are constructed based on predicted project progress. The resource constraints, time constraints, and schedule deviation constraints are introduced below through formulas (9) to (11).

[0144] Resource constraints:

[0145] ; (9)

[0146] in, represents the amount of resource i required for task j, It represents the available capacity of resource i, n is the number of resource types, and m is the number of tasks.

[0147] Time constraints:

[0148] ; (10)

[0149] in, represents the start time of task j, represents the duration of task j, represents the completion time of task j, and m is the number of tasks;

[0150] Schedule deviation constraint:

[0151] ; (11)

[0152] in, represents the progress deviation of task j, represents the actual completion time of task j, represents the planned completion time of task j, Indicates the maximum allowed progress deviation rate;

[0153] Step 306, constraining the objective function with resource constraints, time constraints and schedule deviation constraints, and taking the total cost of the project to be optimized as the minimum value and the total duration of the project to be optimized as the minimum value as the goal of the objective function, constructing a scheduling optimization model.

[0154] Specifically, the objective function is constrained by resource constraints, time constraints and progress deviation constraints, and the total cost of the project to be optimized and the total construction period of the project to be optimized are minimized as the goals of the objective function. The mixed integer linear programming is used to solve the above formula to obtain the optimal solution, and the scheduling optimization model is constructed by taking the value of the optimal solution.

[0155] In this embodiment, the objective function is constrained by resource constraints, time constraints and progress deviation constraints, and the total cost of the project to be optimized and the total construction period of the project to be optimized are taken as the minimum as the goal of the objective function. Efficient allocation of resources and precise adjustment of task time under the current scheduling mode are achieved from multiple dimensions to ensure that the project to be optimized is completed on time and resources are effectively utilized, thereby improving the rationality of resource allocation of infrastructure projects and the progress reliability of infrastructure projects, thereby solving the problems of resource imbalance and progress delays in project scheduling.

[0156] The following is an introduction to the complete implementation of the scheduling optimization method based on infrastructure projects. In an exemplary embodiment, Figure 4 As shown, a scheduling optimization method based on infrastructure projects is provided. This embodiment uses the method applied to the server 104 shown in FIG. 1 as an example for illustration. It can be understood that the method can also be applied to the terminal 102 shown in FIG. 1 , and can also be applied to a system including the terminal 102 and the server 104, and is implemented through the interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0157] Step 401, obtaining initial current data and initial historical data of the project to be optimized, and performing data preprocessing on the initial current data and the initial historical data to obtain current data and historical data.

[0158] Step 402, extracting the engineering progress data from the current data; the engineering progress data includes the current project progress and the project planned progress; determining the progress difference between the current project progress and the project planned progress, and calculating the ratio of the progress difference to the project planned progress, and determining the obtained ratio result as the engineering progress deviation.

[0159] Step 403, extracting resource data from the current data; the resource data includes actual usage corresponding to different types of resources, and available capacity corresponding to different types of resources; for each type of resource, a ratio of the actual usage of the resource to the available capacity of the resource is calculated, and the obtained ratio result is determined as the resource utilization rate of the resource.

[0160] Step 404, extracting resource data from the current data; the resource data includes actual usage corresponding to different types of resources, and available capacity corresponding to different types of resources; for each type of resource, obtaining the timeliness factor of the resource and the substitutability factor of the resource; determining the resource balance rate of the resource through the actual usage, available capacity, timeliness factor and substitutability factor.

[0161] Step 405, performing progress deviation analysis on the current scheduling mode of the project to be optimized through the project progress deviation to determine the project progress deviation result of the current scheduling mode; performing resource utilization analysis on the current scheduling mode of the project to be optimized through the resource utilization to determine the resource utilization result of the current scheduling mode; performing resource balance rate analysis on the current scheduling mode of the project to be optimized through the resource balance rate to determine the resource balance rate result of the current scheduling mode; wherein the scheduling analysis results include project progress deviation results, resource utilization results and resource balance rate results.

[0162] Step 406: Analyze the current scheduling mode of the project to be optimized through key indicators to determine the scheduling analysis result for the current scheduling mode.

[0163] Step 407, perform time series analysis and machine learning model prediction on current data and historical data to obtain predicted resource requirements and predicted project progress.

[0164] Step 408, construct the objective function of the scheduling optimization model through the project progress deviation results, resource utilization results and resource balance rate results; construct resource constraints based on the resource utilization results and the predicted resource demand, and construct time constraints and progress deviation constraints based on the predicted project progress; constrain the objective function with resource constraints, time constraints and progress deviation constraints, and take the total cost of the project to be optimized as the minimum value and the total construction period of the project to be optimized as the minimum value as the goal of the objective function to construct the scheduling optimization model.

[0165] Step 409: perform scheduling optimization on the current scheduling mode through a scheduling optimization model.

[0166] In the embodiment of the present application, the integrity and accuracy of the data are ensured through data preprocessing, and the obtained scheduling analysis results are based on data analysis rather than relying on empirical judgment, and the obtained predicted resource demand and predicted project progress are helpful to make resource demand configuration and project progress time arrangement in advance to reduce unforeseen risks. Therefore, from the aforementioned multiple dimensions, efficient allocation of resources and precise adjustment of task time under the current scheduling mode are achieved, ensuring that the projects to be optimized are completed on time and resources are effectively utilized, thereby improving the rationality of resource allocation of infrastructure projects and the reliability of the progress of infrastructure projects.

[0167] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0168] Based on the same inventive concept, the embodiment of the present application also provides a scheduling optimization device for infrastructure projects for implementing the scheduling optimization method for infrastructure projects involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the embodiments of the scheduling optimization device for one or more infrastructure projects provided below can refer to the limitations of the scheduling optimization method for infrastructure projects above, and will not be repeated here.

[0169] In an exemplary embodiment, Figure 5 As shown, a scheduling optimization device for infrastructure projects is provided, including: a data acquisition and processing module 502, a data analysis module 504, a data analysis and prediction module 506 and a scheduling optimization module 508, wherein:

[0170] The data acquisition and processing module is used to acquire the initial current data and initial historical data of the project to be optimized, and perform data preprocessing on the initial current data and initial historical data to obtain the current data and historical data;

[0171] The data analysis module is used to determine key indicators based on current data, and analyze the current scheduling mode of the project to be optimized through the key indicators to determine the scheduling analysis results for the current scheduling mode;

[0172] The data analysis and prediction module is used to perform time series analysis and machine learning model prediction on current and historical data to obtain predicted resource requirements and project progress;

[0173] The scheduling optimization module is used to build a scheduling optimization model through scheduling analysis results, predicted resource requirements and predicted project progress, and to optimize the current scheduling mode through the scheduling optimization model.

[0174] In an exemplary embodiment, the key indicator includes a project progress deviation; the project progress deviation is used to measure the deviation of the current project progress compared to the project planned progress;

[0175] The data analysis module is specifically used to extract the engineering progress data from the current data; the engineering progress data includes the current project progress and the project planned progress; determine the progress difference between the current project progress and the project planned progress, and calculate the ratio of the progress difference to the project planned progress, and determine the obtained ratio result as the engineering progress deviation; perform progress deviation analysis on the current scheduling mode of the project to be optimized through the engineering progress deviation, and determine the engineering progress deviation result of the current scheduling mode; the scheduling analysis result includes the engineering progress deviation result.

[0176] In an exemplary embodiment, the key indicator includes resource utilization rate; the resource utilization rate is used to describe the utilization rates of different types of resources in the project to be optimized;

[0177] The data analysis module is specifically used to extract resource data from the current data; the resource data includes the actual usage corresponding to different types of resources, and the available capacity corresponding to different types of resources; for each type of resource, the ratio of the actual usage of the resource to the available capacity of the resource is calculated, and the obtained ratio result is determined as the resource utilization rate of the resource; the resource utilization rate of the current scheduling mode of the project to be optimized is analyzed through the resource utilization rate to determine the resource utilization rate result of the current scheduling mode; the scheduling analysis result includes the resource utilization rate result.

[0178] In an exemplary embodiment, the key indicators include a resource balance rate; the resource balance rate is used to describe the degree of balance in the use of various resources in the project to be optimized;

[0179] The data analysis module is specifically used to extract resource data from the current data; the resource data includes the actual usage corresponding to different types of resources, and the available capacity corresponding to different types of resources; for each type of resource, the timeliness factor and the substitutability factor of the resource are obtained; the resource balance rate of the resource is determined through the actual usage, available capacity, timeliness factor and substitutability factor; the resource balance rate analysis is performed on the current scheduling mode of the project to be optimized through the resource balance rate to determine the resource balance rate result of the current scheduling mode; the scheduling analysis result includes the resource balance rate result.

[0180] In an exemplary embodiment, the data analysis module is specifically used to determine the critical tasks and non-critical tasks in the project to be optimized using the critical path method, and determine the critical task urgency of the critical tasks through the remaining time and total time of the critical tasks, and determine the non-critical task urgency of the non-critical tasks through the remaining time and total time of the non-critical tasks; for each type of resource, determine the task urgency of the tasks associated with the resource, and determine the timeliness factor of the resource through the task urgency and the task type of the tasks associated with the resource; for each type of resource, determine the scarcity and market supply of the resource, and determine the substitutability factor of the resource through the scarcity and market supply.

[0181] In an exemplary embodiment, the scheduling analysis results include: project progress deviation results, resource utilization results, and resource balance rate results; the project progress deviation results are used to describe the difference between the actual completion time and the planned completion time; the resource utilization results are used to describe the usage of resources; the resource balance rate results are used to describe the unit cost of resources;

[0182] Forecast resource requirements include the number of resources required for each task in the project to be optimized;

[0183] The project progress forecast includes: the total construction period of the project to be optimized, the start time, duration and end time of each task in the project to be optimized, the progress deviation, actual completion time and planned completion time of each task;

[0184] The scheduling optimization module is specifically used to construct the objective function of the scheduling optimization model through the project progress deviation results, resource utilization results and resource balance rate results; construct resource constraints based on resource utilization results and predicted resource requirements, and construct time constraints and progress deviation constraints based on predicted project progress; constrain the objective function with resource constraints, time constraints and progress deviation constraints, and take the total cost of the project to be optimized as the minimum value and the total construction period of the project to be optimized as the minimum value as the goal of the objective function to construct a scheduling optimization model.

[0185] Each module in the above-mentioned scheduling optimization device for infrastructure projects can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each of the above modules.

[0186] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 6As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store current data and historical data and other data related to the embodiment of the present application. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a scheduling optimization method for an infrastructure project is implemented.

[0187] Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0188] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0189] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0190] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0191] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0192] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0193] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0194] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A scheduling optimization method for infrastructure projects, characterized in that: The method comprises: Acquire initial current data and initial historical data of the project to be optimized, and perform data preprocessing on the initial current data and the initial historical data to obtain current data and historical data; Determine key indicators based on the current data, and analyze the current scheduling mode of the project to be optimized through the key indicators to determine a scheduling analysis result for the current scheduling mode; Perform time series analysis and machine learning model prediction on the current data and the historical data to obtain predicted resource requirements and predicted project progress; A scheduling optimization model is constructed based on the scheduling analysis results, the predicted resource requirements and the predicted project progress, and the current scheduling mode is optimized through the scheduling optimization model.

2. The method according to claim 1, characterized in that The key indicators include engineering progress deviation; the engineering progress deviation is used to measure the deviation of the current project progress compared with the project planned progress; Determining key indicators based on the current data includes: Extracting engineering progress data from the current data; the engineering progress data includes the current project progress and the project planned progress; Determine the progress difference between the current project progress and the project planned progress, calculate the ratio of the progress difference to the project planned progress, and determine the obtained ratio result as the engineering progress deviation; The analyzing the current scheduling mode of the project to be optimized by using the key indicator to determine the scheduling analysis result for the current scheduling mode includes: The progress deviation of the current scheduling mode of the project to be optimized is analyzed through the engineering progress deviation to determine the engineering progress deviation result of the current scheduling mode; the scheduling analysis result includes the engineering progress deviation result.

3. The method according to claim 1, characterized in that The key indicator includes resource utilization rate; the resource utilization rate is used to describe the utilization rates of different types of resources in the project to be optimized; Determining key indicators based on the current data includes: Extracting resource data from the current data; the resource data includes actual usage corresponding to different types of resources, and available capacity corresponding to different types of resources; For each type of resource, a ratio of the actual usage of the resource to the available capacity of the resource is calculated, and the obtained ratio result is determined as the resource utilization rate of the resource; The analyzing the current scheduling mode of the project to be optimized by using the key indicator to determine the scheduling analysis result for the current scheduling mode includes: The resource utilization rate is used to analyze the current scheduling mode of the project to be optimized, and the resource utilization rate result of the current scheduling mode is determined; the scheduling analysis result includes the resource utilization rate result.

4. The method according to claim 1, characterized in that: The key indicators include resource balance rate; the resource balance rate is used to describe the degree of balance in the use of various resources in the project to be optimized; Determining key indicators based on the current data includes: Extracting resource data from the current data; the resource data includes actual usage corresponding to different types of resources, and available capacity corresponding to different types of resources; For each type of resource, obtain the timeliness factor of the resource and the substitutability factor of the resource; Determining a resource balance rate of the resource according to the actual usage, the available capacity, the timeliness factor, and the substitutability factor; The analyzing the current scheduling mode of the project to be optimized by using the key indicator to determine the scheduling analysis result for the current scheduling mode includes: The resource balancing rate is used to analyze the current scheduling mode of the project to be optimized, and the resource balancing rate result of the current scheduling mode is determined; the scheduling analysis result includes the resource balancing rate result.

5. The method according to claim 4, characterized in that The step of obtaining the timeliness factor and the substitutability factor of each type of resource includes: Using the critical path method to determine the key tasks and non-key tasks in the project to be optimized, and determining the key task urgency of the key task by the remaining time and total time of the key task, and determining the non-key task urgency of the non-key task by the remaining time and total time of the non-key task; For each type of resource, determine the task urgency of the task associated with the resource, and determine the timeliness factor of the resource according to the task urgency and the task type of the task associated with the resource; For each type of resource, the scarcity and market availability of the resource are determined, and the substitutability factor of the resource is determined by the scarcity and the market availability.

6. The method according to any one of claims 1 to 5, characterized in that The scheduling analysis results include: project progress deviation results, resource utilization results, and resource balance rate results; the project progress deviation results are used to describe the difference between the actual completion time and the planned completion time; the resource utilization results are used to describe the usage of resources; and the resource balance rate results are used to describe the unit cost of resources; The predicted resource requirements include the quantity of resources required for each task in the project to be optimized; The predicted project progress includes: the total construction period of the project to be optimized, the start time, duration and end time of each task in the project to be optimized, the progress deviation, actual completion time and planned completion time of each task; The constructing of a scheduling optimization model through the scheduling analysis results, the predicted resource demand and the predicted project progress includes: Constructing an objective function of a scheduling optimization model through the engineering progress deviation result, the resource utilization result and the resource balance rate result; Constructing resource constraints based on the resource utilization results and the predicted resource demand, and constructing time constraints and progress deviation constraints based on the predicted project progress; The objective function is functionally constrained by the resource constraint, the time constraint and the progress deviation constraint, and the total cost of the project to be optimized and the total duration of the project to be optimized are minimized as the goals of the objective function to construct the scheduling optimization model.

7. A scheduling optimization device for infrastructure projects, characterized in that: The device comprises: A data acquisition and processing module, used to acquire initial current data and initial historical data of the project to be optimized, and perform data preprocessing on the initial current data and the initial historical data to obtain current data and historical data; A data analysis module, used to determine key indicators based on the current data, and analyze the current scheduling mode of the project to be optimized through the key indicators to determine a scheduling analysis result for the current scheduling mode; A data analysis and prediction module is used to perform time series analysis and machine learning model prediction on the current data and the historical data to obtain predicted resource requirements and predicted project progress; The scheduling optimization module is used to construct a scheduling optimization model through the scheduling analysis results, the predicted resource requirements and the predicted project progress, and to perform scheduling optimization on the current scheduling mode through the scheduling optimization model.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images