Intelligent engineering progress tracking method and system based on Internet of Things

Abstract

The invention provides an intelligent engineering progress tracking method and system based on the Internet of Things, and relates to the technical field of engineering progress tracking, and the method comprises the steps: binding digital identities to construction members and construction equipment; executing multi-source data acquisition on an Internet of Things sensing layer based on the digital identity label; the construction activity is recognized through multi-source data semantics, and the execution state corresponding to the construction activity is judged; performing progress deviation calculation according to the execution state and the project progress; according to the deviation magnitude of the progress deviation and the job category, generating a scheduling suggestion; and outputting the scheduling suggestion to the construction equipment to dynamically adjust the project progress. According to the invention, the technical problem of poor engineering progress tracking efficiency in the prior art can be solved, and the technical effect of improving the engineering progress tracking efficiency is achieved.

Description

Technical Field

[0001] This application relates to the field of engineering progress tracking technology, and in particular to an intelligent engineering progress tracking method and system based on the Internet of Things. Background Technology

[0002] As the scale of construction projects continues to expand and the working environment at construction sites becomes increasingly complex, the demand for real-time, refined, and intelligent progress management in engineering projects continues to rise. Traditional progress management methods that rely on manual recording, manual inspection, and static planning are no longer sufficient to meet the requirements of modern construction management.

[0003] Currently, most existing project schedule management technologies employ localized monitoring or single-source data-driven approaches, lacking the systematic and semantic integration capabilities to integrate multi-source data from construction sites. This makes it difficult to construct dynamic schedule models that accurately reflect the actual work process. In practical applications, data acquisition typically relies on locally deployed sensing devices, such as monitoring only equipment power or only construction environment parameters, which fails to provide a comprehensive description of project activities. Regarding schedule assessment, some systems only compare planned time with manually entered completion rates, neglecting key indicators such as equipment load changes, component movement trajectories, and personnel work behaviors, leading to significant errors in schedule assessment.

[0004] In summary, existing technologies suffer from technical problems such as the inability to perform real-time fusion analysis of multi-source data from the construction site, the inability to accurately identify the execution status of engineering activities, the inability to make comprehensive judgments on schedule deviations from multiple dimensions, and the inability to form a closed-loop linkage between scheduling decisions and on-site execution. These problems lead to inaccurate tracking of project progress, lagging and untargeted scheduling strategies, and further affect the reliability of overall project schedule control and construction organization efficiency. Summary of the Invention

[0005] The purpose of this application is to provide an intelligent engineering progress tracking method and system based on the Internet of Things, in order to solve the technical problems in the existing technology that are due to the inability to perform real-time fusion analysis of multi-source data at the construction site, the inability to accurately identify the execution status of engineering activities, the inability to make multi-dimensional comprehensive judgments on progress deviations, and the inability to form a closed-loop linkage between scheduling decisions and on-site execution. These problems lead to inaccurate engineering progress tracking, lagging and untargeted scheduling strategies, and further affect the reliability of the overall project schedule control and the efficiency of construction organization.

[0006] In view of the above problems, this application provides a smart engineering progress tracking method and system based on the Internet of Things.

[0007] Firstly, this application provides an intelligent engineering progress tracking method based on the Internet of Things (IoT), implemented through an IoT-based intelligent engineering progress tracking system, comprising: binding digital identity identifiers to construction components and construction equipment; performing multi-source data acquisition at the IoT sensing layer based on the digital identity identifiers; semantically identifying construction activities through the multi-source data and determining the execution status corresponding to the construction activities; calculating the progress deviation based on the execution status and the project progress; generating scheduling suggestions based on the magnitude of the progress deviation and the work category; and outputting the scheduling suggestions to the construction equipment for dynamic adjustment of the project progress.

[0008] Preferably, the IoT-based intelligent engineering progress tracking method further includes: constructing a distributed IoT sensing network at the engineering site to collect component installation locations and movement paths; collecting personnel work behavior and positions through axial accelerometers; collecting equipment operating status through vibration sensors, power sensors, current sensors, voltage sensors, and speed sensors; collecting construction environment data, including temperature, humidity, dust, and noise; collecting construction images using fixed and mobile cameras; and combining the component installation locations, movement paths, personnel work behavior, personnel positions, equipment operating status, construction environment, and construction images to obtain multi-source data.

[0009] Preferably, the IoT-based intelligent engineering progress tracking method further includes: constructing an engineering activity identification model based on time-series features, performing fusion analysis on the multi-source data, obtaining fusion analysis results, and using these results to identify the execution status of different construction stages, wherein the execution status includes not started, in progress, completed, paused, and abnormal.

[0010] Preferably, the IoT-based intelligent engineering progress tracking method further includes: identifying whether the machinery is in an effective operating state based on the equipment power curve in the fusion analysis results, and obtaining a first identification result; identifying whether the installation is completed based on the component position changes in the fusion analysis results, and obtaining a second identification result; identifying whether key processes have started based on the personnel trajectory and behavior actions in the fusion analysis results, and obtaining a third identification result; identifying the component shape based on the image in the fusion analysis results, and obtaining a fourth identification result; and combining the first identification result, the second identification result, the third identification result, and the fourth identification result to identify the execution status of different construction stages.

[0011] Preferably, the IoT-based intelligent engineering progress tracking method further includes: calculating the time offset between the planned start and planned completion based on the execution status and the engineering progress to obtain the offset time; calculating the deviation between the task progress completion rate and the actual completion rate based on the execution status and the engineering progress to obtain the completion rate deviation; calculating the impact of critical path task delays on the overall project duration based on the execution status and the engineering progress to obtain the delay impact coefficient; identifying violations of logical relationship constraints between tasks based on the execution status and the engineering progress to obtain the violation coefficient; and combining the offset time, completion rate deviation, delay impact coefficient, and violation coefficient to obtain the progress deviation.

[0012] Preferably, the IoT-based intelligent engineering progress tracking method further includes: obtaining the deviation level based on the degree of deviation between the execution status and the engineering progress; when the deviation level is within a preset tolerance range, a slight deviation is obtained; when the deviation level exceeds the preset tolerance range but can still be compensated for through resource fine-tuning, a moderate deviation is obtained; when the deviation level exceeds the preset tolerance range and will affect the engineering progress if not intervened immediately, a severe deviation is obtained; when the deviation level exhibits an abnormal pattern, a major abnormal deviation is obtained.

[0013] Preferably, the IoT-based intelligent engineering progress tracking method further includes: matching corresponding scheduling rules according to the task's job category, wherein the job categories include structural construction, electromechanical installation, decoration and renovation, equipment commissioning, and site preparation; combining and selecting a scheduling strategy based on the urgency level of the deviation magnitude and the scheduling rules of the job category, wherein the scheduling strategies include resource replenishment strategies, construction sequence adjustment strategies, and process parallelization strategies; determining the urgency level of the scheduling strategy according to the severity corresponding to the deviation magnitude; generating a corresponding scheduling suggestion template and execution priority according to the scheduling strategy and urgency level, and outputting the scheduling suggestion.

[0014] Preferably, the IoT-based intelligent engineering progress tracking method further includes: the deviation magnitude includes the time deviation magnitude, the progress completion rate deviation magnitude, the critical path impact magnitude, and the resource usage deviation magnitude.

[0015] Preferably, the IoT-based intelligent engineering progress tracking method further includes: distributing the scheduling suggestions to the construction equipment through the construction management platform; collecting feedback data on the scheduling execution results in the construction equipment, including equipment response status, personnel execution status, and process progress status; updating the execution status based on the feedback data, and performing secondary scheduling for tasks that do not meet the scheduling objectives.

[0016] Secondly, this application also provides an IoT-based intelligent engineering progress tracking system for executing the IoT-based intelligent engineering progress tracking method described in the first aspect, comprising: a digital identity binding module for binding digital identity identifiers to construction components and construction equipment; a multi-source data acquisition module for performing multi-source data acquisition at the IoT sensing layer based on the digital identity identifiers; an execution status determination module for identifying construction activities through the semantics of the multi-source data and determining the execution status corresponding to the construction activities; a progress deviation calculation module for calculating the progress deviation based on the execution status and the project progress; a scheduling suggestion generation module for generating scheduling suggestions based on the magnitude of the progress deviation and the job category; and a dynamic adjustment module for outputting the scheduling suggestions to the construction equipment for dynamic adjustment of the project progress.

[0017] The technical solution provided in this application has at least the following technical effects or advantages: by realizing the technical goal of unified modeling, semantic recognition and dynamic progress deviation analysis of multi-source data at the construction site, and generating intelligent scheduling strategies based on deviation levels, the technical effect of comprehensively improving the accuracy of project progress tracking, enhancing the real-time performance of scheduling response and improving the overall construction organization efficiency is achieved.

[0018] The above description is merely an overview of the technical solution of this application. To better understand the technical means of this application and to facilitate its implementation according to the description, and to make the above and other objects, features, and advantages of this application more apparent, specific embodiments of this application are described below. It should be understood that the content described in this section is not intended to identify key or important features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent through the following description. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely exemplary. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0020] Figure 1 This is a flowchart illustrating the IoT-based intelligent engineering progress tracking method of this application.

[0021] Figure 2 This is a schematic diagram of the structure of the IoT-based intelligent engineering progress tracking system of this application.

[0022] Figure labeling: 1. Digital identity binding module; 2. Multi-source data acquisition module; 3. Execution status determination module; 4. Progress deviation calculation module; 5. Scheduling suggestion generation module; 6. Dynamic adjustment module. Detailed Implementation

[0023] This application provides an IoT-based intelligent engineering progress tracking method and system, addressing the technical problems in existing technologies. These problems stem from the inability to perform real-time fusion analysis of multi-source data from the construction site, the inability to accurately identify the execution status of engineering activities, the inability to comprehensively assess progress deviations from multiple dimensions, and the inability to establish a closed-loop linkage between scheduling decisions and on-site execution. These issues lead to inaccurate progress tracking, lagging and untargeted scheduling strategies, and ultimately affect the reliability of overall project schedule control and construction organization efficiency. The application achieves the technical objectives of unified modeling, semantic recognition, and dynamic progress deviation analysis of multi-source data from the construction site, and generates intelligent scheduling strategies based on deviation levels. This results in a comprehensive improvement in the accuracy of engineering progress tracking, enhanced real-time scheduling response, and improved overall construction organization efficiency.

[0024] The technical solutions of this application will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. It should be understood that this application is not limited to the exemplary embodiments described herein. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application. It should also be noted that, for ease of description, only the parts related to this application are shown in the accompanying drawings, not all of them.

[0025] Example 1, please refer to the appendix. Figure 1 This application provides an IoT-based intelligent engineering progress tracking method, which is applied to an IoT-based intelligent engineering progress tracking system, and specifically includes the following steps: S1: Bind digital identity tokens to construction components and construction equipment.

[0026] Specifically, binding digital identities to construction components and equipment refers to uniquely associating physical components and individual pieces of equipment used for processing, transportation, and installation on the construction site with pre-set electronic identifiers. This gives each component and piece of equipment a traceable, indexable, and manageable digital identity within the Internet of Things (IoT) system. Digital identities consist of encoded sequences, identity indexes, or information tags, ensuring accurate differentiation of attribute information, spatial location, and operational participation of different components or equipment during subsequent data collection, status identification, job association, and scheduling management. Digital identities can be implemented using QR code tags, RFID tags, or electronic nameplates, with binding methods including physical adhesion, embedded installation, or writing to airborne modules, establishing a correspondence between construction components and equipment at both the physical and data levels. Furthermore, binding digital identities to construction components and equipment enables mapping between multi-source sensor data and specific physical objects, allowing data from different sources, such as location data, acceleration data, power data, or image data, to be categorized according to digital identities.

[0027] S2: Based on the digital identity identifier, perform multi-source data acquisition at the IoT sensing layer.

[0028] Furthermore, this application also includes: constructing a distributed Internet of Things (IoT) sensing network at the engineering site to collect the installation location and movement path of components; collecting personnel work behavior and personnel work positions through axial accelerometers; collecting equipment operating status through vibration sensors, power sensors, current sensors, voltage sensors, and speed sensors; collecting construction environment data, including temperature, humidity, dust, and noise; collecting construction images based on fixed and mobile camera equipment; and combining the component installation location, movement path, personnel work behavior, personnel work positions, equipment operating status, construction environment, and construction images to obtain multi-source data.

[0029] Specifically, constructing a distributed IoT sensing network on an engineering site refers to deploying a sensing structure composed of multiple types of sensor nodes within the construction area. This structure features wide coverage, strong node autonomy, and high data collaborative transmission capabilities, enabling continuous monitoring of the location status of on-site components, construction processes, and related dynamic changes. The distributed IoT sensing network connects nodes through wireless communication protocols, allowing positioning tags installed on components to output the component's installation location and movement path in real time. This allows the location information of components throughout the entire process from transportation and hoisting to installation to be recorded in the form of a continuous trajectory.

[0030] Collecting personnel work behavior and location data via axial accelerometers involves equipping mobile terminals or safety gear worn by construction workers with sensor units capable of detecting acceleration changes. These sensors collect acceleration patterns generated by personnel during different construction actions and, combined with a location identification module, determine the worker's work area. The acceleration sequences collected by the axial accelerometers can be used to distinguish different behavioral characteristics such as walking, carrying, and operating machinery, thereby enabling the identification and statistical analysis of construction activities at the personnel level.

[0031] Collecting equipment operating status through vibration sensors, power sensors, current sensors, voltage sensors, and speed sensors refers to installing multiple types of monitors on key components of construction equipment. By measuring the vibration intensity, output power, current changes, voltage levels, and speed changes during equipment operation, information such as the equipment's workload, operational stability, and whether it is in an effective operating state can be obtained.

[0032] Construction environment data collection, including temperature, humidity, dust, and noise, refers to the deployment of environmental sensing devices in the construction area to acquire parameters such as air temperature, humidity, dust concentration, and noise levels in decibels. These parameters are used to characterize changes in the construction site's environment. Environmental parameters can help determine the impact of external conditions on construction progress or operational safety.

[0033] The acquisition of construction images using fixed and mobile camera equipment refers to the use of fixed cameras installed in designated locations and mobile cameras mounted on drones or mobile robots to record images of component changes, personnel activities, and equipment operation during the construction process. Fixed camera equipment provides a continuous monitoring perspective, while mobile camera equipment compensates for blind spots by changing the shooting position, making the construction images more comprehensive.

[0034] By combining component installation location, movement path, personnel operation behavior, personnel operation location, equipment operating status, construction environment and construction images, multi-source data is obtained. This means that the structured and unstructured data output by each sensor module are aggregated to form a unified data set based on spatial information, behavioral information, working condition information and visual information.

[0035] S3: Semantically identify construction activities through the multi-source data and determine the execution status corresponding to the construction activities.

[0036] Furthermore, this application also includes: constructing an engineering activity identification model based on time-series features, performing fusion analysis on the multi-source data, obtaining fusion analysis results, and using them to identify the execution status of different construction stages, wherein the execution status includes not started, in progress, completed, paused, and abnormal.

[0037] Furthermore, this application also includes: identifying whether the machinery is in an effective operating state based on the equipment power curve in the fusion analysis results, and obtaining a first identification result; identifying whether the installation is completed based on the component position changes in the fusion analysis results, and obtaining a second identification result; identifying whether key processes have been started based on the personnel trajectory and behavioral actions in the fusion analysis results, and obtaining a third identification result; identifying the component shape based on the image in the fusion analysis results, and obtaining a fourth identification result; and combining the first identification result, the second identification result, the third identification result, and the fourth identification result to identify the execution status of different construction stages.

[0038] Specifically, constructing an engineering activity identification model based on time-series features refers to using an algorithmic structure capable of analyzing the changing patterns of time series data to encode data from different sensor sources in chronological order, capturing features such as the continuity of actions, process dependencies, and cyclical changes in equipment operation during construction. The engineering activity identification model learns from the trends, fluctuations, cycles, and abrupt changes in sensor data over time, enabling it to identify the evolutionary stages of construction activities.

[0039] Multi-source data fusion analysis refers to the correlation and processing of data from different modalities, such as component location data, equipment operating condition data, personnel behavior data, environmental parameter data, and image data. By merging spatial features, temporal features, and semantic features through a unified feature representation method, the engineering activity identification model can judge the true state of construction activities from multiple perspectives.

[0040] Obtaining the fusion analysis results refers to the analytical results output by the engineering activity identification model after processing multi-source data, which describe the characteristics of the construction process. The analysis results may include information such as the probability of process initiation, the determination of effective equipment operation, and component status labels, and provide a basis for judgment in subsequent status identification stages in a structured form. The fusion analysis results can eliminate noise from the original data and extract key behavioral features, making the judgment more accurate.

[0041] The execution status used to identify different construction stages refers to determining the current stage of a construction stage based on the performance of construction activities reflected in the fusion analysis results. The execution status is used to express the real-time progress of the construction process and is divided into five categories: not started, in progress, completed, paused, and abnormal, so as to provide a clear staged description of construction activities.

[0042] The execution status includes Not Started, In Progress, Completed, Paused, and Abnormal. This refers to the classification and expression of the construction process based on the results of the fusion analysis. Not Started means that the construction stage has not yet entered the execution phase. In Progress means that the construction is progressing normally. Completed means that the current stage has met the planned completion conditions. Paused means that the construction is temporarily interrupted due to resource scheduling, environmental restrictions, or other reasons. Abnormal means that there is a risk of deviating from the normal working conditions.

[0043] Identifying whether machinery is in an effective operating state based on the equipment power curve in the fusion analysis results refers to using the curve shape of the equipment power change over time to determine whether the machinery is currently under load. The equipment power curve can reflect the changes in equipment speed, output power, and energy consumption. When the power value shows a continuous increase or stabilizes in a range higher than the static level within a certain period of time, it can be determined that the equipment is operating effectively; conversely, when the power curve remains in a low-value fluctuation range for a long time, it indicates that the equipment is not truly participating in construction.

[0044] Identifying whether installation is complete based on component position changes in the fusion analysis results refers to judging the status based on the changes in the component's position in spatial coordinates. When a component gradually transitions from a moving state to a fixed state, and its position coordinates tend to stabilize and no longer change within a continuous monitoring period, the component installation can be determined to be complete; if the component's position is still changing significantly, it indicates that the installation process is in progress.

[0045] Identifying whether a key process has started based on personnel trajectories and behavioral actions from the fusion analysis results refers to determining whether a manually involved key process has entered the execution phase by analyzing the movement paths, stopping areas, and action characteristics of construction personnel. Personnel trajectories can be used to determine whether they have arrived at a specific work area, while behavioral actions such as lifting, welding, fixing, and carrying can be used to identify whether the process has actually started.

[0046] Image recognition of component morphology based on fusion analysis results refers to identifying whether a component has achieved the expected shape using image data acquired from fixed and mobile cameras. This includes assessing whether component positioning is aligned, whether parts are fully assembled, and whether abnormal surface deformations occur. Image recognition can utilize deep learning models to analyze the edge morphology, geometric features, and surface structure of components to determine the completeness of construction procedures. For example, if the component seams remain consistent and without shift across multiple video frames, the morphology can be considered stable. This process yields a fourth recognition result reflecting the visual state of the component.

[0047] Combining the first, second, third, and fourth identification results involves comprehensively judging status information from different sources such as equipment, components, personnel, and images to determine the execution status of the current construction phase. Cross-validating multiple identification results improves the accuracy of status identification. For example, if equipment is operating effectively, component displacement is decreasing, personnel are performing key actions, and image recognition shows the component is in the assembly stage, then the construction phase can be determined to be in progress. If all the above data indicate that the activity has ended, then it can be determined to be in a completed state.

[0048] S4: Calculate the schedule deviation based on the execution status and project progress.

[0049] Furthermore, this application also includes: calculating the time offset between the planned start and planned completion based on the execution status and project progress to obtain the offset time; calculating the deviation between the task progress completion rate and the actual completion rate based on the execution status and project progress to obtain the completion rate deviation; calculating the impact of critical path task delays on the overall project duration based on the execution status and project progress to obtain the delay impact coefficient; identifying violations of logical relationship constraints between tasks based on the execution status and project progress to obtain the violation coefficient; and combining the offset time, completion rate deviation, delay impact coefficient, and violation coefficient to obtain the schedule deviation.

[0050] Specifically, calculating the time offset between planned start and completion dates based on execution status and project progress involves comparing the actual start and completion times of construction activities with the pre-set time nodes in the project plan to identify actual time delays or advances. The time offset is typically calculated by subtracting the planned time from the actual time. For example, if the planned start date is day 10 and the actual start date is day 12, the time offset is 2 days; if the planned completion date is day 20 and the actual completion date is day 18, the completion time offset is -2 days. This comparison yields the offset time reflecting the differences in construction progress.

[0051] Calculating the deviation between the planned completion rate and the actual completion rate based on the execution status and project progress refers to identifying whether the task's progress is meeting targets by comparing the percentage of completion planned with the actual percentage of completion during construction. For example, if a task is planned to have a 70% completion rate on day 15, but the actual completion rate is only 50%, the deviation is 20%. Completion rate deviation can be used to determine if there is insufficient progress or uneven resource allocation in a task, and it increases linearly as the task size increases from 100 square meters to 200 square meters.

[0052] Calculating the impact of critical path task delays on the overall project duration based on execution status and project progress refers to identifying the amplification effect of delays on tasks along the critical path on the overall project duration. Even a delay of just one day in a critical path task can directly extend the overall project duration by more than one day. Therefore, by cumulatively analyzing the time lags of critical path tasks, a delay impact coefficient can be obtained. For example, if a critical task is delayed by two days and its impact coefficient on downstream processes is 1.5, the overall project duration may be extended by three days.

[0053] Identifying violations of logical constraints between tasks based on execution status and project progress involves analyzing the dependencies, sequence requirements, and resource consumption relationships between different tasks to determine whether violations of logical order occur during actual execution. For example, if task A must start after task B is completed, but task A starts earlier in the actual data, this can be identified as a violation, and a violation coefficient will be given. For example, the severity of the violation can be expressed as 0.3 or 0.7 to characterize its impact on the overall project.

[0054] Combining offset time, completion rate deviation, delay impact coefficient, and violation coefficient refers to uniformly weighting or integrating various indicators reflecting time differences, schedule differences, path impact, and logical violations to obtain the overall deviation of the project schedule. Different indicators can be assigned different weights according to their importance. For example, the weight of time offset and critical path delay is higher than that of task completion rate deviation, thus outputting a schedule deviation result that can comprehensively reflect the degree of deviation from the project schedule.

[0055] S5: Generate scheduling suggestions based on the magnitude of the schedule deviation and the job category.

[0056] Furthermore, this application also includes: obtaining the deviation level based on the degree of deviation between the execution state and the project progress; when the deviation level is within a preset tolerance range, a slight deviation is obtained; when the deviation level exceeds the preset tolerance range, but can still be compensated for through resource fine-tuning, a moderate deviation is obtained; when the deviation level exceeds the preset tolerance range, and will affect the project progress if not intervened immediately, a severe deviation is obtained; when the deviation level exhibits an abnormal pattern, a major abnormal deviation is obtained.

[0057] Furthermore, this application also includes: matching corresponding scheduling rules according to the job category to which the task belongs, wherein the job categories include structural construction, electromechanical installation, decoration and renovation, equipment commissioning, and site preparation; combining and selecting a scheduling strategy based on the urgency level of the deviation magnitude and the scheduling rules of the job category, wherein the scheduling strategies include resource replenishment strategies, construction sequence adjustment strategies, and process parallelization strategies; determining the urgency level of the scheduling strategy according to the severity corresponding to the deviation magnitude; generating a corresponding scheduling suggestion template and execution priority according to the scheduling strategy and urgency level, and outputting the scheduling suggestion.

[0058] Furthermore, this application also includes: the deviation magnitude includes the time deviation magnitude, the schedule completion rate deviation magnitude, the critical path impact magnitude, and the resource usage deviation magnitude.

[0059] Specifically, based on the degree of deviation between the execution status and the project progress, a deviation magnitude is obtained, which represents a quantitative assessment of the difference between the planned value and the actual execution status of predefined task nodes in the project. The execution status includes the actual start time, actual completion time, resource input, and real-time feedback of the task. The project progress includes the planned progress curve, key node time, task dependency constraints, and resource allocation plan. By comparing the difference, ratio difference, and trend deviation between the actual execution data and the planned data, a quantitative index of the degree of deviation is constructed, and the severity of the deviation is graded accordingly.

[0060] Furthermore, when the deviation is within the preset tolerance range, a slight deviation is obtained. The preset tolerance range is set based on the minimum allowable offset threshold of the project. This threshold is used to reflect the situation where the project can still maintain stable progress within the normal construction fluctuation range. A slight deviation means that the current degree of deviation is small and will not have a significant impact on the overall progress of the project. For example, when the actual progress is no more than 5% behind the planned progress, it can be regarded as a slight deviation.

[0061] Furthermore, when the deviation exceeds the preset tolerance range, but can still be compensated for through resource fine-tuning, a moderate deviation can be obtained. Resource fine-tuning includes appropriately increasing the number of construction personnel, extending daily working hours, increasing the utilization rate of construction equipment, and adjusting the task scheduling order. A moderate deviation usually corresponds to a task delay that has exceeded the normal fluctuation range, but the progress can still be restored within the planned construction period by investing a small amount of additional resources.

[0062] Furthermore, if the deviation exceeds the preset tolerance range, it will affect the project progress if not intervened immediately, resulting in a severe deviation. A severe deviation indicates a significant delay in the task, which cannot be compensated for by resource fine-tuning and requires intervention through replanning, increasing resources by multiple times, or establishing a special construction plan.

[0063] At the same time, when the magnitude of the deviation exhibits an abnormal pattern, it results in a major abnormal deviation. Abnormal patterns include situations such as a rapid increase in schedule deviation within a short period of time, a sudden halt in critical path tasks, a large-scale failure of inter-task dependencies, and a mismatch between resource input and output. Major abnormal deviations usually indicate that the project has experienced abnormal disturbance events, such as sudden equipment failure, deterioration of engineering environmental conditions, or absence of key personnel, which makes the deviation no longer linear or recoverable. It may be necessary to take emergency plans or revise the construction plan to avoid systemic schedule risks.

[0064] Based on the task's job category, corresponding scheduling rules are matched. Job categories include structural construction, electromechanical installation, decoration and renovation, equipment commissioning, and site preparation. Job categories are used to classify tasks of different natures during the construction process, so that a scheduling mechanism adapted to its characteristics can be matched for each type of task. Structural construction includes heavy operations such as concrete pouring, rebar tying, and formwork installation; electromechanical installation includes processes requiring precise connection, such as cable laying, pipeline installation, and distribution cabinet installation; decoration and renovation includes processes such as wall cladding, floor leveling, and ceiling installation; equipment commissioning includes operations such as joint commissioning and trial operation of installed equipment; and site preparation includes preliminary activities such as material storage layout, passageway clearing, and temporary facility construction. Through this classification method, different types of tasks can be automatically matched with pre-set scheduling rules, including resource allocation rules, dependency restrictions, and allowed parallelization conditions.

[0065] Furthermore, based on the urgency level of the deviation magnitude and the scheduling rules of the aforementioned job category, a scheduling strategy is selected through combination. This strategy includes resource replenishment, construction sequence adjustment, and process parallelization. The urgency level of the deviation magnitude reflects the severity of the task's current deviation from the plan and works in conjunction with the specific scheduling rules of the job category to form a scheduling decision. The resource replenishment strategy refers to increasing construction speed by adding construction personnel, machinery, or extending work periods without changing the process logic. The construction sequence adjustment strategy refers to rearranging construction processes according to task dependencies and site conditions, such as postponing non-critical processes or advancing critical processes. The process parallelization strategy refers to changing processes originally executed sequentially to be executed partially or completely in parallel, provided that dependencies allow, to shorten the overall construction time.

[0066] Furthermore, the urgency level of the scheduling strategy is determined based on the severity corresponding to the magnitude of the deviation. The severity levels include mild, moderate, severe, and major anomaly levels, each corresponding to different response speed requirements. For example, a mild deviation may only require routine adjustments, a moderate deviation requires additional resources in the short term, a severe deviation requires immediate scheduling intervention, and a major anomaly deviation may require the highest priority emergency scheduling measures. By mapping the severity of the deviation to the urgency level of the scheduling strategy, it can be ensured that the scheduling plan can take effect within the appropriate time window, so that the intervention measures are neither excessive nor delayed.

[0067] Furthermore, based on the scheduling strategy and urgency level, corresponding scheduling suggestion templates and execution priorities are generated, and the scheduling suggestions are output. The scheduling suggestion template contains predefined text structures, execution steps, resource configuration suggestions, and possible risk warnings for different scheduling strategies. The execution priority is used to indicate the implementation order between different scheduling suggestions. For example, strategies affecting the critical path are set to high priority, and small-scale adjustments for general work areas are set to low priority. This ensures that the scheduling suggestions have the characteristics of standardization, strong executability, and rapid response.

[0068] Deviation magnitudes include time deviation magnitude, schedule completion rate deviation magnitude, critical path impact magnitude, and resource utilization deviation magnitude. Deviation magnitude quantifies the degree of deviation between the execution status and the project plan, providing a measurable description of project schedule risks. Time deviation magnitude indicates the degree of deviation between the actual start or finish time of a task and the planned time. For example, if a task is planned to start on the tenth day but actually starts on the twelfth day, a time deviation occurs; the larger the deviation period, the higher the deviation level. Schedule completion rate deviation magnitude measures the difference between the actual completion rate of a task or project as a whole and the planned completion rate. For example, when the planned completion rate is 100%, the deviation magnitude is 100%. When the actual completion rate is only 30% out of 50, a significant deviation can occur. Furthermore, the deviation level increases as the difference grows from 10% to 20%. The critical path impact magnitude measures the cascading effects of delays in critical path tasks on the overall project duration. For example, a one-day delay in a critical task may cause a one-day delay in the overall project duration. Its magnitude can be calculated based on the importance and dependencies of the critical task. The resource utilization deviation magnitude reflects the discrepancy between actual and planned resource input. For instance, if a piece of equipment is planned to be used for eight hours but is actually used for twelve hours, this constitutes a resource over-utilization deviation. The higher the over-utilization percentage, the higher the deviation level.

[0069] S6: Output the scheduling suggestions to the construction equipment for dynamic adjustment of the project progress.

[0070] Furthermore, this application also includes: distributing the scheduling suggestions to the construction equipment through the construction management platform; collecting feedback data on the scheduling execution results in the construction equipment, including equipment response status, personnel execution status, and process progress status; updating the execution status based on the feedback data, and performing secondary scheduling for tasks that do not meet the scheduling objectives.

[0071] Specifically, the scheduling suggestions are issued to the construction equipment through the construction management platform. This indicates that the digital construction management system deployed in the project transmits the scheduling suggestions generated by the scheduling algorithm to the corresponding construction equipment or operation terminal in the form of task instructions, control parameters, or resource adjustment plans. The construction management platform is a digital platform that realizes the interconnection between construction planning, resource scheduling, and on-site execution. It achieves data interaction with various equipment through a communication network. The construction equipment includes lifting machinery, construction robots, transportation equipment, processing equipment, and other equipment with monitoring and controllable functions. The scheduling suggestions are executed through the platform's instruction receiving mechanism, such as adjusting equipment start-up time, modifying equipment operating mode, or changing task priority, and the instructions are distributed in the form of data packets.

[0072] Furthermore, feedback data on the scheduling execution results of construction equipment is collected, including equipment response status, personnel execution status, and process progress status. This data is used to represent the objective feedback information obtained in real time from on-site execution after the scheduling instructions are issued, through IoT sensors, equipment communication interfaces, and mobile terminals of operators. The equipment response status includes whether the equipment starts on time, the equipment's operating load, and whether the equipment has entered the preset operation mode. The personnel execution status includes whether the personnel start work as required, whether the work actions conform to the task specifications, and whether the personnel have reached the designated work area. The process progress status describes the actual progress of the task, including the real-time timestamps of process start, intermediate nodes, and process completion. Continuous collection of feedback data can reflect the execution effect of the scheduling strategy.

[0073] Furthermore, the execution status is updated based on feedback data, and secondary scheduling is performed on tasks that do not meet the scheduling objectives. This illustrates that the system dynamically corrects the task execution status using real-time collected information on equipment status, operator behavior, and process progress. By comparing the actual execution process with the scheduling objectives, tasks that do not achieve the expected scheduling effect are identified. If there are situations such as equipment not responding normally, personnel execution lagging, or insufficient process progress, the secondary scheduling mechanism is automatically triggered. By recalculating scheduling rules, adjusting resource allocation, or replanning the work sequence, the normal progress of the project plan is restored.

[0074] In summary, the IoT-based intelligent engineering progress tracking method provided in this application has the following technical effects: by realizing unified modeling, semantic recognition, and dynamic progress deviation analysis of multi-source data at the construction site, and generating intelligent scheduling strategies based on deviation levels, it achieves the technical objectives of comprehensively improving the accuracy of engineering progress tracking, enhancing the real-time performance of scheduling response, and improving the overall construction organization efficiency.

[0075] Example 2: Based on the same inventive concept as the IoT-based intelligent engineering progress tracking method in the foregoing examples, this application also provides an IoT-based intelligent engineering progress tracking system. Please refer to the appendix. Figure 2 The system includes: a digital identity binding module 1, used to bind digital identity identifiers to construction components and construction equipment; a multi-source data acquisition module 2, used to perform multi-source data acquisition at the IoT sensing layer based on the digital identity identifiers; an execution status determination module 3, used to identify construction activities through the semantics of the multi-source data and determine the execution status corresponding to the construction activities; a schedule deviation calculation module 4, used to calculate the schedule deviation based on the execution status and the project progress; a scheduling suggestion generation module 5, used to generate scheduling suggestions based on the magnitude of the schedule deviation and the job category; and a dynamic adjustment module 6, used to output the scheduling suggestions to the construction equipment for dynamic adjustment of the project progress.

[0076] Furthermore, the IoT-based intelligent engineering progress tracking system is also used to: construct a distributed IoT sensing network at the engineering site to collect component installation locations and movement paths; collect personnel work behavior and positions through axial accelerometers; collect equipment operating status through vibration sensors, power sensors, current sensors, voltage sensors, and speed sensors; collect construction environment data, including temperature, humidity, dust, and noise; collect construction images using fixed and mobile cameras; and combine the component installation locations, movement paths, personnel work behavior, personnel positions, equipment operating status, construction environment, and construction images to obtain multi-source data.

[0077] Furthermore, the IoT-based intelligent engineering progress tracking system is also used to: construct an engineering activity identification model based on time-series features, perform fusion analysis on the multi-source data, obtain fusion analysis results, and identify the execution status of different construction stages, including not started, in progress, completed, paused, and abnormal.

[0078] Furthermore, the IoT-based intelligent engineering progress tracking system is also used to: identify whether the machinery is in an effective operating state based on the equipment power curve in the fusion analysis results, and obtain a first identification result; identify whether the installation is completed based on the component position changes in the fusion analysis results, and obtain a second identification result; identify whether key processes have been started based on the personnel trajectory and behavior actions in the fusion analysis results, and obtain a third identification result; identify the component shape based on the image in the fusion analysis results, and obtain a fourth identification result; and combine the first identification result, the second identification result, the third identification result, and the fourth identification result to identify the execution status of different construction stages.

[0079] Furthermore, the IoT-based intelligent engineering progress tracking system is also used for: calculating the time offset between the planned start and planned completion based on the execution status and engineering progress to obtain the offset time; calculating the deviation between the task progress completion rate and the actual completion rate based on the execution status and engineering progress to obtain the completion rate deviation; calculating the impact of critical path task delays on the overall project duration based on the execution status and engineering progress to obtain the delay impact coefficient; identifying violations of logical relationship constraints between tasks based on the execution status and engineering progress to obtain the violation coefficient; and combining the offset time, completion rate deviation, delay impact coefficient, and violation coefficient to obtain the progress deviation.

[0080] Furthermore, the IoT-based intelligent engineering progress tracking system is also used to: obtain the deviation level based on the degree of deviation between the execution status and the engineering progress; when the deviation level is within a preset tolerance range, a slight deviation is obtained; when the deviation level exceeds the preset tolerance range but can still be compensated for through resource fine-tuning, a moderate deviation is obtained; when the deviation level exceeds the preset tolerance range and will affect the engineering progress if not intervened immediately, a severe deviation is obtained; when the deviation level exhibits an abnormal pattern, a major abnormal deviation is obtained.

[0081] Furthermore, the IoT-based intelligent engineering progress tracking system is also used for: matching corresponding scheduling rules according to the job category to which the task belongs, wherein the job categories include structural construction, electromechanical installation, decoration and renovation, equipment commissioning, and site preparation; combining and selecting scheduling strategies based on the urgency level of the deviation magnitude and the scheduling rules of the job category, wherein the scheduling strategies include resource replenishment strategies, construction sequence adjustment strategies, and process parallelization strategies; determining the urgency level of the scheduling strategy according to the severity corresponding to the deviation magnitude; generating corresponding scheduling suggestion templates and execution priorities according to the scheduling strategies and urgency levels, and outputting the scheduling suggestions.

[0082] Furthermore, the IoT-based intelligent engineering progress tracking system is also used to: include the deviation magnitude as well as the deviation magnitudes as well as the progress completion rate deviation magnitudes, the critical path impact magnitudes, and the resource usage deviation magnitudes.

[0083] Furthermore, the IoT-based intelligent engineering progress tracking system is also used to: distribute the scheduling suggestions to the construction equipment through the construction management platform; collect feedback data on the scheduling execution results in the construction equipment, including equipment response status, personnel execution status, and process progress status; update the execution status according to the feedback data, and perform secondary scheduling for tasks that do not meet the scheduling objectives.

[0084] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The IoT-based intelligent engineering progress tracking method and specific examples in the aforementioned Embodiment 1 are also applicable to the IoT-based intelligent engineering progress tracking system in this embodiment. Through the foregoing detailed description of the IoT-based intelligent engineering progress tracking method, those skilled in the art can clearly understand the IoT-based intelligent engineering progress tracking system in this embodiment. Therefore, for the sake of brevity, it will not be described in detail here.

[0085] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0086] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of this application and its equivalents, this application also intends to include such modifications and variations.

Claims

1. A method for tracking progress of a project based on Internet of Things, characterized in that, The method comprises the following steps: binding a digital identity for a construction component and a construction device; performing multi-source data collection at an Internet of Things sensing layer based on the digital identity; identifying a construction activity through semantics of the multi-source data and determining an execution state corresponding to the construction activity; calculating a progress deviation based on the execution state and an engineering progress; generating a scheduling suggestion based on a deviation level of the progress deviation and a work category; and outputting the scheduling suggestion to the construction device for dynamic adjustment of the engineering progress.

2. The Internet of Things based smart engineering progress tracking method as claimed in claim 1 wherein, Performing multi-source data collection at an Internet of Things sensing layer comprises the following steps: constructing a distributed Internet of Things sensing network at a construction site to collect component installation positions and movement paths; collecting personnel work behavior and personnel work positions through an axial accelerometer; collecting device operating states through a vibration sensor, a power sensor, a current sensor, a voltage sensor, and a rotation speed sensor; collecting construction environment, including temperature, humidity, dust, and noise; collecting construction images according to fixed camera equipment and mobile camera equipment; and obtaining multi-source data in combination with the component installation positions, the movement paths, the personnel work behavior, the personnel work positions, the device operating states, the construction environment, and the construction images.

3. The Internet of Things based smart engineering progress tracking method as claimed in claim 1 wherein, Identifying a construction activity through semantics of the multi-source data and determining an execution state corresponding to the construction activity comprises the following steps: constructing an engineering activity identification model based on time sequence characteristics to perform fusion analysis on the multi-source data and obtain a fusion analysis result, which is used to identify execution states of different construction links, the execution states including not started, in progress, completed, paused, and abnormal.

4. The Internet of Things based smart engineering progress tracking method as claimed in claim 3, wherein, Identifying execution states of different construction links comprises the following steps: identifying whether a machine is in an effective work state based on a device power curve in the fusion analysis result to obtain a first identification result; identifying whether installation is completed based on a component position change in the fusion analysis result to obtain a second identification result; identifying whether a key work procedure is started based on personnel trajectory and behavior action in the fusion analysis result to obtain a third identification result; identifying a component form based on an image in the fusion analysis result to obtain a fourth identification result; and identifying execution states of different construction links in combination with the first identification result, the second identification result, the third identification result, and the fourth identification result.

5. The IoT based smart engineering progress tracking method as claimed in claim 1 wherein, Calculating a progress deviation based on the execution state and the engineering progress comprises the following steps: calculating a time offset of a planned start and a planned completion based on the execution state and the engineering progress to obtain an offset time; calculating a deviation of a task progress completion rate and an actual completion rate based on the execution state and the engineering progress to obtain a completion rate deviation; calculating an influence of a key path task delay on an overall construction period based on the execution state and the engineering progress to obtain a delay influence coefficient; and identifying a violation of a logical relationship constraint between tasks based on the execution state and the engineering progress to obtain a violation coefficient. Combining the offset time, the completion rate deviation, the delay influence coefficient, and the violation coefficient to obtain the progress deviation.

6. The Internet of Things based smart engineering progress tracking method as claimed in claim 1 wherein, Dividing a deviation level comprises the following steps: obtaining the deviation level based on a deviation degree of the execution state and the engineering progress; and obtaining a slight deviation when the deviation level is within a preset tolerance range. When the deviation magnitude exceeds the preset tolerance range, but can be compensated by resource fine-tuning, a moderate deviation is obtained; When the deviation magnitude exceeds the preset tolerance range, and immediate intervention will affect the project progress, a severe deviation is obtained; When the deviation magnitude shows an abnormal pattern, a major abnormal deviation is obtained.

7. The Internet of Things based smart engineering progress tracking method as claimed in claim 1 wherein, According to the deviation magnitude of the progress deviation and the work category, a scheduling suggestion is generated, including: According to the work category to which the task belongs, the corresponding scheduling rule is matched, and the work category includes structural construction, mechanical and electrical installation, decoration, equipment commissioning, and site preparation; Based on the emergency level of the deviation magnitude and the scheduling rule of the work category, a scheduling strategy is selected, including resource supplement strategy, construction sequence adjustment strategy, and process parallelization strategy; According to the severity corresponding to the deviation magnitude, the emergency level of the scheduling strategy is determined; According to the scheduling strategy and the emergency level, the corresponding scheduling suggestion template and execution priority are generated, and the scheduling suggestion is output.

8. The Internet of Things based smart engineering progress tracking method as claimed in claim 1 wherein, The deviation magnitude includes time deviation magnitude, progress completion rate deviation magnitude, critical path influence magnitude, and resource occupation deviation magnitude.

9. The Internet of Things based smart engineering progress tracking method as claimed in claim 1 wherein, The scheduling suggestion is output to the construction equipment for dynamic adjustment of the project progress, including: The scheduling suggestion is issued to the construction equipment through the construction management platform; Feedback data of scheduling execution results in the construction equipment is collected, including equipment response state, personnel execution state, and process progress state; According to the feedback data, the execution state is updated, and secondary scheduling is performed for tasks that do not meet the scheduling target.

10. An intelligent engineering progress tracking system based on Internet of Things characterized in that, Steps for implementing the intelligent project progress tracking method based on Internet of Things according to any one of claims 1-9, including: A digital identity binding module is used to bind digital identity to construction components and construction equipment. A multi-source data acquisition module is used to perform multi-source data acquisition based on the digital identity in the Internet of Things sensing layer. An execution state determination module is used to identify construction activities through multi-source data semantics and determine the corresponding execution state of construction activities. A progress deviation calculation module is used to calculate the progress deviation according to the execution state and the project progress. A scheduling suggestion generation module is used to generate a scheduling suggestion according to the deviation magnitude of the progress deviation and the work category. A dynamic adjustment module is used to output the scheduling suggestion to the construction equipment for dynamic adjustment of the project progress.

Images