Building construction progress identification method and system based on Internet of Things data

Abstract

The invention discloses a building construction progress identification method and system based on Internet of Things data, and relates to the technical field of intelligent identification in a construction stage, and the method comprises the steps: collecting the operation state parameters of all resource devices, and determining the service range of all resource devices; extracting a BIM spatial position of the construction task, and constructing a task graph; identifying a controlled task based on a resource service range, combining a resource operation state and a task space relationship, and updating a task graph; and detecting the updated task graph, and outputting a construction progress stage identifier. The method achieves the automatic recognition of the construction progress stage, improves the real-time performance and accuracy of a recognition result, and supports the self-adaptive analysis of a structure in a complex construction scene.

Description

Technical Field

[0001] This invention relates to the field of intelligent identification technology during the construction phase, and in particular to a method and system for identifying building construction progress based on Internet of Things (IoT) data. Background Technology

[0002] In current construction sites, progress identification typically relies on construction plans and pre-set task flowcharts in BIM models, indirectly determining whether a certain stage is completed through sensor data. These methods often infer construction stages based on static rules, such as task completion rates and resource usage frequency. However, actual construction processes are far more complex than model specifications, especially in scenarios with multiple concurrent resources and dense spatial overlap. The relationships between tasks are not static, and stage evolution cannot be accurately depicted simply by thresholds or model classification. The operational status of construction resources (e.g., tower crane usage intensity, frequent elevator scheduling) does not truly participate in the structural judgment between tasks. Resources are treated as auxiliary references rather than dominant variables, failing to reflect the true impact of resource behavior on task progress. Furthermore, most task flowchart structures are static; once built, they no longer evolve with resource status, leading to lag in stage identification and limited accuracy.

[0003] In addition, although some studies have attempted to introduce machine learning models for construction phase classification, these methods rely on a large amount of training data, the results are difficult to interpret, and they lack a direct link with resource behavior, resulting in low feasibility in actual construction sites. Summary of the Invention

[0004] In view of the aforementioned existing problems, the present invention is proposed.

[0005] Therefore, this invention provides a construction progress identification method based on Internet of Things data to solve the problems of existing construction progress identification methods, such as the lack of a structural linkage mechanism between resources and tasks, static graph structure, delayed response, and inability of behavioral information to penetrate the graph topology, resulting in low accuracy, poor interpretability, and insufficient real-time performance in progress judgment.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0007] In a first aspect, the present invention provides a method for identifying building construction progress based on Internet of Things data, which includes collecting operating status parameters of various resource devices and determining the service range of each resource device;

[0008] Extract the BIM spatial location of the construction task and construct the task map;

[0009] Controlled tasks are identified based on the resource service scope, and the task graph is updated by combining the resource operation status with the task space relationship.

[0010] Detect the updated task map and output the construction progress stage identifier.

[0011] As a preferred embodiment of the construction progress identification method based on Internet of Things data according to the present invention, the operating status parameters include operating frequency, load intensity, status identifier and location information;

[0012] The process of determining the service range of each resource device includes constructing a corresponding spatial volume model in the BIM model based on the spatial coverage parameters, operation trajectory information or deployment location of the resource device, and uniformly discretizing the spatial volume model into a three-dimensional mesh representation aligned with the BIM model.

[0013] For each resource device, the operating frequency and load intensity of the resource device are collected and normalized by combining the historical maximum values ​​within a preset time period to obtain the behavioral tension representing the current capability of the resource. When the resource device is in a fault state, the behavioral tension of the resource device does not participate in the update calculation of the task edge weight of the task graph.

[0014] As a preferred embodiment of the construction progress identification method based on Internet of Things data described in this invention, the construction of the task map includes: obtaining the spatial regions corresponding to each construction task in the three-dimensional coordinate system from the BIM model, and uniformly discretizing the spatial regions of each task into a three-dimensional grid representation aligned with the BIM model;

[0015] Each construction task is used as a node, and task edges are established between any two nodes to construct a task graph; the weights of the task edges are initialized based on the volume overlap ratio between the corresponding 3D mesh representations of any two nodes.

[0016] As a preferred embodiment of the construction progress identification method based on Internet of Things data described in this invention, the method for identifying controlled tasks based on resource service range includes: for each task edge, comparing the intersection volume and union volume of the three-dimensional mesh representation of the construction tasks at both ends of the task edge with the service range of each resource device in space, and setting the ratio of the intersection volume to the union volume as the projection factor; the projection factor ranges from zero to one; when the projection factor is zero, the resource device has no effect on the task edge, and when the projection factor is one, the resource device can fully affect the task edge.

[0017] As a preferred embodiment of the construction progress identification method based on Internet of Things data described in this invention, the updated task graph task edge weights include resource devices whose behavioral tension is not lower than a preset gate threshold selected from all resource devices, and the behavioral tension of the resource devices is exponentially enhanced.

[0018] For each task edge, the three-dimensional mesh representations of the construction tasks at both ends of the task edge are merged to obtain the task space region of the task edge. The three-dimensional volume intersection and union of the task space region and the service range of each resource device are calculated. The ratio of the intersection volume to the union volume is used as the spatial overlap coefficient of the resource device on the task edge.

[0019] Multiply the spatial overlap coefficient, the exponentially enhanced behavioral tension, and the projection factor, and set the product as the strength of the structural influence of the resource device on the task edge.

[0020] The structural influence intensity of all resource devices on the task edge is accumulated to obtain the weight decay of the task edge; the weight of the current edge of the task edge is corrected according to the weight decay.

[0021] As a preferred embodiment of the construction progress identification method based on Internet of Things data described in this invention, the updated task graph includes task edges whose weights are less than or equal to a preset fracture threshold selected from all task edges to form a fracture edge set.

[0022] Sort the task edges in descending order based on their structural influence intensity, and extract the top-ranked edges. The task edges form the projected main path set; the intersection-union ratio between the broken edge set and the projected main path set is calculated as the broken path matching degree; weak connectivity clustering of the task graph is performed, and the number of clusters and the edge density of each cluster are counted.

[0023] If the fracture path matching degree is not less than the matching threshold, the number of clusters is greater than or equal to two, the density of all cluster edges is not less than the structural density threshold, and the average structural influence intensity across cluster edges is not greater than the preset residual tension threshold, then the task graph is determined to have completed the structural transition.

[0024] As a preferred embodiment of the construction progress identification method based on Internet of Things data described in this invention, the output construction progress stage identifier includes: when it is determined that the task diagram has completed the structural transition, extracting the number of clusters, the distribution location of fracture edges, the density of edges within clusters and the remaining structural influence intensity index of the task diagram as structural state features.

[0025] The structural state characteristics are matched with a preset structural stage mapping table to obtain the corresponding construction stage identifier.

[0026] Secondly, the present invention provides a building construction progress identification system based on Internet of Things data, including a data module for collecting operating status parameters of various resource devices and determining the service range of each resource device.

[0027] The task map module extracts the BIM spatial location of construction tasks and constructs a task map;

[0028] The update module identifies controlled tasks based on the resource service scope, combines the resource operating status with the task space relationship, and updates the task graph.

[0029] The output module detects the updated task graph and outputs the construction progress stage identifier.

[0030] Thirdly, the present invention provides a computer device including a memory and a processor, wherein the memory stores a computer program, wherein when the computer program is executed by the processor, it implements any step of the construction progress identification method based on Internet of Things data as described in the first aspect of the present invention.

[0031] Fourthly, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the construction progress identification method based on Internet of Things data as described in the first aspect of the present invention.

[0032] The beneficial effects of this invention are as follows: By constructing a coupling mechanism between resource behavior tension and task space structure, real-time control of task graph edge weights by resource data is achieved, opening up a linkage path between IoT resource behavior and graph structure evolution. A structural influence intensity calculation model is adopted, fusing resource tension, spatial overlap coefficient, and projection factor to drive edge weight decay and structural fracture in the task graph. The rationality of fracture is judged by the matching degree between fractured edges and dominant paths, and stage transition determination is completed by combining multi-dimensional indicators such as cluster quantity, edge density, and residual structural tension. Finally, stage identifiers are directly generated using the graph structure state, achieving model-free, rule-free, and interpretable construction progress identification, improving the system's real-time performance, accuracy, and engineering adaptability. Attached Figure Description

[0033] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0034] Figure 1 This is a flowchart of a method for identifying building construction progress based on Internet of Things (IoT) data. Detailed Implementation

[0035] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0036] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0037] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0038] Example 1, referring to Figure 1 This is one embodiment of the present invention, which provides a method for identifying building construction progress based on Internet of Things (IoT) data, including the following steps:

[0039] S1: Collect the operating status parameters of each resource device to determine the service range of each resource device.

[0040] The operating status parameters collected for each resource device include: operating frequency (representing the number of actions per unit time); load intensity (representing the current workload); status indicator (representing whether the current device status is available); and location information (representing the current location of the device).

[0041] Fixed equipment (such as tower cranes and pumping stations): In the BIM model, a columnar volume model is constructed with the equipment base point as the center, the maximum operating radius as the bottom radius, and the given operating height as the height, which serves as the spatial service domain for the fixed equipment.

[0042] Mobile devices (such as construction elevators and transport vehicles): In the BIM model, a linear trajectory corridor model is constructed based on the historical scheduling trajectory point set of the device, and combined with a preset buffer radius to expand into a spatial corridor with volume, which serves as the spatial service domain of the mobile device.

[0043] The service domain volume models of all devices are spatially unified and discretized into a three-dimensional mesh representation (Voxel representation) aligned with the BIM model, which facilitates subsequent task graph matching and spatial overlap calculation.

[0044] Operating frequency of resource acquisition equipment With load strength Combined with the highest historical frequency With maximum load Calculate the normalized behavioral tension:

[0045]

[0046] If the status is fault, then set:

[0047]

[0048] Behavioral tension It will serve as one of the core weight parameters in the subsequent task graph edge weight update calculation.

[0049] in, Indicates resource equipment The behavioral tension, with a value range of [0, 1]; Indicates resource equipment Operating frequency; Indicates resource equipment Maximum operating frequency within a preset reference time period; Indicates resource equipment Current load intensity; Indicates resource equipment Maximum load intensity within a preset reference period; This represents an identifier for any construction resource device in the system.

[0050] Traditional construction scheduling schemes typically only collect data on the number of times resource equipment is used or simple task initiation status, making it difficult to comprehensively depict the actual participation of equipment and task execution load. By introducing multi-dimensional parameters such as operating frequency, load intensity, status indicators, and location information, a more representative resource status description system is constructed, which can simultaneously reflect the current operating frequency, execution load, and whether the equipment is in a normal and available state. Compared with single-variable or post-event statistical methods, this approach provides stronger task participation identification capabilities while maintaining the simplicity of the data collection method, providing a quantifiable input basis for subsequent graph-based control behavior.

[0051] Existing methods often use fixed areas or single locations to roughly estimate the construction impact range of resources, which is difficult to adapt to the actual needs of changing mobile device trajectories or diverse spatial coverage. This paper introduces a differentiated spatial modeling strategy for fixed and mobile devices. Fixed devices use column coverage areas to represent the maximum working space, while mobile devices generate dynamic corridor models based on historical trajectories. These volumetric representations are uniformly converted into a 3D mesh format and strictly aligned with the spatial granularity of the BIM model, solving the problem of spatial mapping distortion of the equipment service area in the graph structure.

[0052] Resource status varies significantly across different construction stages and equipment types, and directly using raw values ​​may lead to incomparable evaluation results. A normalization mechanism based on historical maximum values ​​is introduced to map frequency and load to a standardized scale, ensuring consistent weighting for different resources when participating in graph structure control. Simultaneously, fault status identification logic is implemented; when equipment is unavailable, its behavioral stress contribution is automatically removed, enhancing the stability and fault tolerance of the entire structural response model and preventing invalid equipment from interfering with subsequent structural evolution assessments.

[0053] S2: Extract the BIM spatial location of the construction task and construct the task map.

[0054] For each construction task Extract the spatial extent of the BIM model in the three-dimensional coordinate system, denoted as:

[0055]

[0056] The spatial extent of all tasks is uniformly discretized into a set of three-dimensional voxels aligned with the BIM model mesh, denoted as:

[0057]

[0058] The spatial resolution of the voxel grid is consistent with the discrete grid of the resource service domain, ensuring spatial alignment between the task graph and the resource graph.

[0059] For each construction task As graph nodes, construct the task graph:

[0060]

[0061] Among them, node set ; Indicates the first Each construction task corresponds to a construction entity in the BIM model (such as pouring a second-floor beam). Indicates task The original three-dimensional spatial region in a BIM model is usually composed of a set of geometric voxels or a component space; Indicates task The three-dimensional voxel set obtained after discretizing the spatial region; The set of edges representing the task graph; This represents the initial set of edges in the task graph. Includes all task pairs that satisfy the spatial overlap condition. .

[0062] For any two task nodes Calculate the spatial overlap volume and union volume of its voxel mesh representation:

[0063]

[0064] in, This represents the initial edge weight of the task edges. A larger value indicates a higher degree of overlap between the two task space regions, and a greater likelihood of resource conflicts or construction interference. If so, then there are no initial edges connecting the tasks; Indicates task and The spatial intersection between sets of voxel meshes; Indicates task and The spatial union of voxel mesh sets; Vol( Volume calculation function.

[0065] Traditional task mapping methods often simplify construction tasks into logical nodes or two-dimensional area markers, failing to accurately reflect the true interference relationships between tasks in three-dimensional space. Extracting the spatial regions of task components in the BIM model into three-dimensional coordinate ranges and further unifying them into a voxel mesh format consistent with resource modeling ensures complete spatial alignment between the task map and the resource map. This representation effectively avoids spatial misjudgments caused by inconsistent model resolution or irregular geometric shapes, improving the rigor and stability of identifying spatial relationships between tasks.

[0066] In the graph construction process, predefined task flow sequences or static dependencies are no longer used. Instead, task edge connections are established based on the actual overlapping areas between tasks in the BIM space. This approach more realistically reflects the physical proximity of tasks in space and potential resource conflict paths, especially in high-density, multi-layered structures, where it possesses a stronger ability to express inter-task connectivity. Simultaneously, this mapping method naturally supports the dynamic intervention of subsequent resource behaviors on structural relationships, contributing to the formation of the evolutionary foundation for the graph structure.

[0067] Compared to methods that construct edge weights based on task phases or categories, using the voxel overlap ratio of the task space region as the edge weight initialization index can form a continuous and quantifiable expression of connection strength in the graph structure. The edge weights not only reflect the degree of coupling in the task space but also provide a superimposed structural basis for subsequent behavioral factors such as resource pull and projection increment. This edge weight initialization mechanism also has the natural advantage of edge value normalization, which is beneficial for controlling the robustness of fracture judgment and ensuring that the structural change process is interpretable and asymptotic at the numerical level.

[0068] S3: Identify controlled tasks based on the resource service range, combine the resource operation status with the task space relationship, and update the task graph.

[0069] For each task edge Take the three-dimensional voxel sets corresponding to the two end nodes respectively. , The spatial regions that constitute the edge of this task are merged:

[0070]

[0071] in, Indicates construction task A three-dimensional voxel mesh set; Indicates construction task A three-dimensional voxel mesh set; Indicates task edge The corresponding task space region is equal to the union of the two endpoint task regions.

[0072] For each resource device Its spatial service range is expressed as Calculate the spatial intersection degree between the task edge and the resource device, and define the projection factor as:

[0073]

[0074] in, Represents the projection factor. A larger value indicates a stronger coverage of resources for that task edge; if Then resources Does not affect the edge ; Indicates resource equipment Spatial service domain; This represents the intersection area between the task edge and the resource service domain; This represents the union region of the task edge and the resource service domain.

[0075] Behavioral tension was filtered from all resource devices. Not less than the preset threshold resource collection Perform exponential enhancement operations on each of these resource devices:

[0076]

[0077] Based on this, computing resource devices With the task edge Spatial overlap coefficient:

[0078]

[0079] in, Indicates resource equipment Behavioral tension; Indicates the tension enhancement index; Indicates resource equipment The increased behavioral tension following the exponential growth; Indicates resource equipment With the task edge Spatial overlap coefficient; This represents the set of elements at the intersection of the task's edge space region and the resource service domain.

[0080] For each resource With the task edge The combination of these factors defines the structural influence strength as follows:

[0081]

[0082] For all resource devices on the edge The weight decay of an edge is obtained by summing the structural influence strengths:

[0083]

[0084] Adjust the current weight of the edge based on the decay amount:

[0085]

[0086] like Then set , indicating that the edge is completely broken.

[0087] in, Indicates resource equipment For the task edge The structure affects the strength; Indicates resource equipment Enhanced behavioral tension; Indicates task edge The weight decay is obtained by summing the structural influence strength of all effective resources; This refers to the set of resource devices whose behavioral tension is not lower than the gating threshold. Indicates resource equipment The strength of the structural impact on the task edge; Indicates task edge The updated edge weights.

[0088] Traditional construction drawing schemes often rely on static task logic flows to determine task relevance, lacking a dynamic binding mechanism for the scope of resource behavior. Here, a projection factor is introduced by the intersection ratio of the resource service domain and the space covered by the task edge, establishing a clear spatial relationship between the task edge and resource equipment. Whether a resource affects a task edge is no longer determined by preset rules, but by whether its service range truly penetrates the task area. This approach avoids the problem of edge connection logic being disconnected from resource space, providing a judgment entry point for the evolution of the resource-dominated graph structure.

[0089] When unfiltered resource status information is directly used in graph edge structure control, it often leads to misinterpretation or ineffective disturbances. Setting a behavioral tension gating threshold effectively shields low-state or critically faulty resources, improving the effectiveness of structural evolution decisions. Based on this, an exponential enhancement mechanism is introduced to make the response to changes in resource behavior intensity more resolution-oriented, avoiding the contribution smoothing problem caused by linear growth. The combined use of spatial overlap ratio and projection factor not only reflects whether the position of the resource and task edge coincides, but also expresses the proportion of the service range in the edge space region, making the intensity of the effect closer to the actual physical influence path.

[0090] The edge weight update mechanism is no longer driven by a single behavioral factor, but instead integrates resource status, spatial service domain, and structural connection paths into a unified indicator framework. The impact of each resource on the task edge is calculated independently in the form of structural impact intensity and aggregated into a decay amount at the task edge dimension, thus introducing a multi-source driving logic of resource behavior into the edge structure. Through this mechanism, the task graph structure evolves controllably with resource changes, and the evolution process of each edge has a clear source explanation path, which helps in subsequent stage transition judgment and task graph stability detection.

[0091] S4: Detect the updated task graph and output the construction progress stage identifier.

[0092] For all edges in the task graph Perform a filter; if the updated edge weights satisfy:

[0093]

[0094] Then the task edge is added to the fracture edge set, denoted as:

[0095]

[0096] in, This represents the preset edge weight breakage threshold; This represents the set of broken edges, i.e., all edges whose weights are less than or equal to a preset breaking threshold. The task edge set.

[0097] Based on structural influence strength Sort all task edges in descending order and select the top ones. The task edges form the set of projected main paths:

[0098]

[0099] in, This represents the set of projection principal paths, ranked by the structural influence intensity. The task edge is composed of; This represents the threshold for the percentage of edges extracted from the main path, expressed as a percentage.

[0100] Let the intersection-union ratio of the set of fracture edges and the set of main paths be defined as the fracture path matching degree:

[0101]

[0102] Perform weak connectivity clustering analysis on the current task graph, and let the cluster set be:

[0103]

[0104] in, This indicates the fracture path matching degree, used to quantify whether the set of fracture edges is concentrated on the high-tension main path; This represents a cluster set of the task graph; Indicates the first A cluster; Indicates the number of clusters.

[0105] The following indicators will be statistically analyzed separately:

[0106] Number of clusters:

[0107]

[0108] Edge density of each cluster:

[0109]

[0110] The average structural influence strength across cluster edges:

[0111]

[0112] in, Represents the set of all edges connecting different clusters; Indicates clustering edge density; Indicates clustering The internal set of task edges; Indicates clustering An internal collection of task nodes; This represents the average structural influence strength across all cluster edges.

[0113] The task graph is considered to have completed a structural transition when all of the following conditions are met: That is, the fracture path matching degree is not less than the preset matching threshold. ; That is, at least two connected clusters are formed; all That is, the internal structure density of each cluster is not lower than a set structure density threshold. ; That is, the average residual tension across the cluster edges is not greater than the set residual tension threshold. .

[0114] Once the structural transition conditions are met, the following indicators are extracted from the task graph structure as structural state features: number of clusters. The location and distribution of fracture edges in the task graph; edge density within each cluster. Intensity of cross-cluster residual structure influence .Constitutes the structural state description vector:

[0115]

[0116] Match the structural state vector with the preset structural stage mapping table and output the corresponding construction stage identifier:

[0117]

[0118] in, Represents the structural state feature vector; Pattern(ℰbreak) represents the spatial / structural distribution pattern of the fracture edge in the task graph; Stage represents the identifier of the current construction stage; Map( ) represents the stage mapping function.

[0119] The specific process of the stage mapping function is as follows: A manually defined stage structure template library is pre-established. Each template record includes the range of structural state characteristics and the corresponding construction stage number. After the structural transition in the task graph is completed, the system extracts the current structural state vector and matches it against the rules in the template library one by one, filtering out the stage numbers that meet all constraints. When multiple matches exist, the stage with the smaller number is selected as the current stage identifier; if no match exists, the system outputs "unidentified" or "to be labeled" status, waiting for subsequent updates.

[0120] The structural assessment is no longer limited to traditional edge weight threshold screening, but incorporates a mechanism for identifying resource-dominant paths. By sorting all task edges according to their structural influence intensity, path segments with highly concentrated resource intensity are extracted and subjected to intersection and union analysis with the set of fracture edges. This ensures that fracture assessment not only relies on the decrease in edge weight itself, but also focuses on whether fractures are concentrated on the main resource structural pathways. This mechanism effectively eliminates non-structural fracture assessments caused by noise disturbances or edge fluctuations, improving the interpretability of fracture results and the robustness of stage transition triggers.

[0121] Structural transitions are no longer determined by the number of fractures on a single edge. Instead, they are determined by a combined approach of connectivity decomposition of the task graph and structural density statistics within subgraphs. By detecting the number of clusters and the edge density of each cluster, and combining this with the influence intensity of residual structures across clusters, a multi-dimensional judgment logic based on "structural convergence + structural fragmentation + residual tension dissipation" is formed. Compared to methods that rely solely on the number of edges or changes in average edge weight, this judgment method more accurately reflects the actual structural stability and separability of the task graph, making it particularly suitable for improving the accuracy required in complex or dense task phases.

[0122] The phase output method introduces structural state feature vectors as the mapping basis. It utilizes a graph structure summary composed of multiple dimensions such as cluster size, edge density distribution, fracture edge spatial distribution, and residual tension to directly match a manually pre-defined phase template table and output phase labels. This method avoids the previous phase inference paths based on rule trees, manually labeled conditions, or classification models. Instead, it constructs a method where phase evolution is driven by the shape of the task graph itself, making phase identifiers traceable and the structural process fully verifiable.

[0123] This embodiment also provides a construction progress identification system based on Internet of Things (IoT) data, including:

[0124] The data module collects the operating status parameters of each resource device and determines the service range of each resource device.

[0125] The task map module extracts the BIM spatial location of construction tasks and constructs a task map.

[0126] The update module identifies controlled tasks based on the resource service scope, combines the resource operating status with the task space relationship, and updates the task graph.

[0127] The output module detects the updated task graph and outputs the construction progress stage identifier.

[0128] This embodiment also provides a computer device applicable to the construction progress identification method based on Internet of Things (IoT) data, comprising: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the construction progress identification method based on IoT data as proposed in the above embodiment.

[0129] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0130] This embodiment also provides a storage medium storing a computer program, which, when executed by a processor, implements the construction progress identification method based on Internet of Things data as proposed in the above embodiments. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0131] In summary, this invention achieves automatic identification of construction phases by constructing a resource service domain and a task space graph, using resource behavior tension to drive the dynamic evolution of task edge weights, and based on structural fracture characteristics, adaptive graph decomposition, and state mapping mechanisms. It features strong real-time performance and interpretable structure.

[0132] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for identifying building construction progress based on Internet of Things (IoT) data, characterized in that: include: Collect the operating status parameters of each resource device to determine the service range of each resource device; Extract the BIM spatial location of the construction task and construct the task map; Controlled tasks are identified based on the resource service scope, and the task graph is updated by combining the resource operation status with the task space relationship. Detect the updated task map and output the construction progress stage identifier.

2. The construction progress identification method based on Internet of Things data as described in claim 1, characterized in that: The operating status parameters include operating frequency, load intensity, status identifier, and location information; The process of determining the service range of each resource device includes constructing a corresponding spatial volume model in the BIM model based on the spatial coverage parameters, operation trajectory information or deployment location of the resource device, and uniformly discretizing the spatial volume model into a three-dimensional mesh representation aligned with the BIM model. For each resource device, the operating frequency and load intensity of the resource device are collected, and normalized calculations are performed in combination with the historical maximum values ​​within a preset time period to obtain the behavioral tension representing the current performance capability of the resource. When a resource device is in a faulty state, the behavioral tension of the resource device does not participate in the update calculation of the task edge weights of the task graph.

3. The construction progress identification method based on Internet of Things data as described in claim 2, characterized in that: The construction of the task map includes obtaining the spatial regions corresponding to each construction task in the three-dimensional coordinate system from the BIM model, and discretizing the spatial regions of each task into a three-dimensional mesh representation aligned with the BIM model. Each construction task is used as a node, and task edges are established between any two nodes to construct a task graph; the weights of the task edges are initialized based on the volume overlap ratio between the corresponding 3D mesh representations of any two nodes.

4. The construction progress identification method based on Internet of Things data as described in claim 3, characterized in that: The method of identifying controlled tasks based on resource service range includes, for each task edge, comparing the intersection volume and union volume of the 3D mesh representation of the construction tasks at both ends of the task edge with the service range of each resource device in space, and setting the ratio of the intersection volume to the union volume as the projection factor; the projection factor ranges from zero to one; when the projection factor is zero, the resource device has no effect on the task edge, and when the projection factor is one, the resource device can fully affect the task edge.

5. The construction progress identification method based on Internet of Things data as described in claim 4, characterized in that: The updated task graph task edge weights include selecting resource devices from all resource devices whose behavioral tension is not lower than a preset gating threshold, and exponentially enhancing the behavioral tension of the resource devices. For each task edge, the three-dimensional mesh representations of the construction tasks at both ends of the task edge are merged to obtain the task space region of the task edge. The three-dimensional volume intersection and union of the task space region and the service range of each resource device are calculated. The ratio of the intersection volume to the union volume is used as the spatial overlap coefficient of the resource device on the task edge. Multiply the spatial overlap coefficient, the exponentially enhanced behavioral tension, and the projection factor, and set the product as the strength of the structural influence of the resource device on the task edge. The structural influence intensity of all resource devices on the task edge is accumulated to obtain the weight decay of the task edge; the weight of the current edge of the task edge is corrected according to the weight decay.

6. The construction progress identification method based on Internet of Things data as described in claim 5, characterized in that: The updated task graph includes task edges whose weights are less than or equal to a preset fracture threshold, selected from all task edges, forming a fracture edge set. Sort the task edges in descending order based on their structural influence intensity, and extract the top-ranked edges. The task edges constitute the set of projected main paths; Calculate the intersection-union ratio between the set of broken edges and the set of projected main paths, as the broken path matching degree; perform weak connectivity clustering of the task graph, and count the number of clusters and the edge density of each cluster; If the fracture path matching degree is not less than the matching threshold, the number of clusters is greater than or equal to two, the density of all cluster edges is not less than the structural density threshold, and the average structural influence intensity across cluster edges is not greater than the preset residual tension threshold, then the task graph is determined to have completed the structural transition.

7. The construction progress identification method based on Internet of Things data as described in claim 6, characterized in that: The output construction progress stage identifiers include, when it is determined that the task diagram has completed the structural transition, extracting the number of clusters, the distribution location of fracture edges, the density of edges within clusters, and the remaining structural influence intensity index of the task diagram as structural state features. The structural state characteristics are matched with a preset structural stage mapping table to obtain the corresponding construction stage identifier.

8. A construction progress identification system based on Internet of Things (IoT) data, based on the construction progress identification method based on IoT data according to any one of claims 1 to 7, characterized in that: The data module collects the operating status parameters of each resource device to determine the service range of each resource device; The task map module extracts the BIM spatial location of construction tasks and constructs a task map; The update module identifies controlled tasks based on the resource service scope, combines the resource operating status with the task space relationship, and updates the task graph. The output module detects the updated task graph and outputs the construction progress stage identifier.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the construction progress identification method based on Internet of Things data as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the construction progress identification method based on Internet of Things data as described in any one of claims 1 to 7.

Images