Intelligent construction collaborative operation platform integrating BIM and IoT

Abstract

The present invention discloses an intelligent construction collaborative operation platform integrating BIM and the Internet of Things, and relates to the field of intelligent construction technology. The platform includes: transmitting historical data collected by sensor deployment arrays and equipment deployment arrays to a BIM model for simulation to generate a historical construction model of a target area; obtaining a real-time sensor collection data set and a real-time equipment collection data set; performing collection data missing authentication to obtain multiple data missing points; determining multiple missing point fusion data; obtaining an updated historical construction model; performing construction collaborative operation plan analysis for the target area to obtain a target construction collaborative operation plan. The platform solves the technical problem that it is difficult to accurately monitor the construction data of a complex building site in real time in the existing intelligent construction, causing the BIM model data to be out of sync, and then resulting in insufficient accuracy of the construction collaborative operation plan and low operation efficiency, and achieves the technical effect of improving the accuracy of the collaborative operation plan and the operation collaborative efficiency.

Description

Technical Field

[0001] The present application relates to the technical field related to intelligent construction, and specifically to an intelligent construction collaborative operation platform integrating BIM and the Internet of Things. Background Art

[0002] With the rapid development of information technology, the construction industry is gradually moving towards intelligence and digitalization. The deep integration of Building Information Modeling (BIM) and the Internet of Things (IoT) provides a new solution for the field of intelligent construction. BIM technology manages the data of building design, construction and management in a unified way through digitalization, forming a three-dimensional visualization model, and providing full life cycle management of construction projects; IoT technology collects environmental data, equipment status and construction progress information of the construction site in real time through a large number of sensors and intelligent devices, providing real-time data support for the refined management and optimization of the construction site. However, the current intelligent construction platform faces some difficulties in practical application. Although the BIM model can present the overall information of the building, there is still a lag in the acquisition and feedback of real-time data during the actual construction process, resulting in poor synchronization between the BIM model and the actual construction scene, and unable to reflect the changes of the construction site in real time, which greatly limits the dynamic management ability of BIM in the construction stage; when IoT devices are deployed on large and complex construction sites, some data is often missing due to equipment failures, network problems, etc., which affects the integrity and accuracy of the on-site data, and thus affects the accuracy of construction decisions.

[0003] Therefore, in the current intelligent construction-related technologies, there is a technical problem that it is difficult to accurately monitor the construction data of complex construction sites in real time, which makes the BIM model data out of sync, and further leads to the lack of accuracy of construction collaborative work plans and low work efficiency. Summary of the invention

[0004] This application solves the technical problem that it is difficult to accurately monitor the construction data of complex construction sites in real time in existing intelligent construction, causing BIM model data to be out of sync, and further leading to insufficient accuracy of construction collaborative work plans and low work efficiency, by providing an intelligent construction collaborative work platform that integrates BIM and the Internet of Things. This application achieves the technical effect of improving the accuracy of collaborative work plans and the efficiency of collaborative work.

[0005] The present application provides an intelligent construction collaborative operation platform integrating BIM and the Internet of Things, the platform comprising: a target area historical construction model generation module, which is used to obtain a sensor layout array and a device layout array of the target area, and transmit the historical data collected by the sensor layout array and the device layout array to a BIM model in a preset historical window by using a communication component for simulation, so as to generate a historical construction model of the target area; a real-time data acquisition module, which is used to perform real-time data acquisition on the sensor layout array and the device layout array at a first moment, and obtain a real-time sensor collection data set and a real-time device collection data set; and a collection data missing authentication module, which is used to perform collection data missing authentication based on the real-time sensor collection data set, the real-time device collection data set and the historical construction model. A plurality of data missing points are obtained, wherein the plurality of data missing points include a plurality of missing position identifiers; a neighbor data fusion identification module is used to perform neighbor data fusion identification in the real-time sensor data collection set and the real-time device data collection set according to the plurality of data missing points and the plurality of missing position identifiers, and determine the fusion data of the plurality of missing points; an updated historical construction model acquisition module is used to update the historical construction model according to the plurality of missing point fusion data, the real-time sensor data collection set and the real-time device data collection set, and obtain an updated historical construction model; a target construction collaborative work plan acquisition module is used to obtain target construction task information, and perform construction collaborative work plan analysis on the target area in combination with the updated historical construction model to obtain a target construction collaborative work plan.

[0006] In a possible implementation, the collected data missing authentication module also performs the following processing: mapping the real-time sensor collected data set and the real-time equipment collected data set to the historical construction model to obtain multiple initial data missing points and multiple initial data missing position identifiers; conditionally screening multiple central data missing points from the multiple initial data missing points, identifying the edges of missing areas among the multiple initial data missing points based on the multiple central data missing points, and determining multiple central data missing areas; performing missing authentication based on the multiple central data missing areas, and if the authentication passes, using the multiple initial data missing points as multiple data missing points, and using the multiple initial data missing position identifiers as multiple data missing position identifiers; if the authentication fails, obtaining a data collection early warning instruction, and performing troubleshooting on the sensor layout array and the equipment layout array based on the data collection early warning instruction.

[0007] In a possible implementation, the collected data missing authentication module also performs the following processing: randomly extracting a preset number of initial data missing points from the multiple initial data missing points to obtain a random central data missing point set; enumerating the random central data missing point set in pairs to obtain multiple enumeration combinations, and performing distance calculations on the multiple enumeration combinations in combination with the multiple initial data missing position identifiers to obtain multiple enumeration combination distance values; counting the number of multiple enumeration combination distance values ​​that are less than or equal to a preset distance threshold to obtain anomalies, and iteratively updating the random central data missing point set based on the size of the anomalies until the updated anomaly amount is less than or equal to the preset anomaly amount, and then using the data missing points in the updated random central data missing point set as multiple central data missing points.

[0008] In a possible implementation, the acquisition data missing authentication module also performs the following processing: constructing multiple first identification missing areas with the multiple central data missing points as multiple identification circle centers and a preset identification step as an identification radius; counting the number of missing points in the multiple first identification missing areas and calculating multiple first identification missing densities; performing area edge expansion on the multiple first identification missing areas according to the preset identification step to obtain multiple second identification missing areas, and calculating multiple second identification missing densities of the multiple second identification missing areas; when the multiple second identification missing densities are less than or equal to the multiple first identification missing densities, stopping the missing area edge identification and using the multiple first identification missing areas as the multiple central data missing areas; when the multiple second identification missing densities are greater than the multiple first identification missing densities, determining whether the density difference between the multiple second identification missing densities and the multiple first identification missing densities is less than or equal to a preset density difference threshold, and if so, stopping the missing area edge identification and using the multiple second identification missing areas as the multiple central data missing areas.

[0009] In a possible implementation, the collected data missing authentication module further performs the following processing: determining whether there is a missing point density greater than or equal to a preset density threshold among the multiple missing point densities of the multiple central data missing areas; if so, the authentication fails.

[0010] In a possible implementation, the neighbor data fusion identification module also performs the following processing: based on the multiple missing position identifiers, multiple first-level neighbor data sets of the multiple data missing points are retrieved in the real-time sensor collection data set and the real-time device collection data set, wherein the first-level neighbor data is the data of the data point directly associated with the data missing point; based on the multiple first-level neighbor data sets, the real-time sensor collection data set and the real-time device collection data set are searched to obtain multiple second-level neighbor data sets of the multiple data missing points, wherein the second-level neighbor data is the data of the data point directly associated with the data point corresponding to the first-level neighbor data; data prediction is performed on the multiple data missing points according to the multiple first-level neighbor data sets and the multiple second-level neighbor data sets to obtain multiple missing point fusion data.

[0011] In a possible implementation, the intelligent construction collaborative operation platform integrating BIM and the Internet of Things also performs the following processing: performing data transmission monitoring on the sensor deployment array and the equipment deployment array according to a preset monitoring indicator set to obtain multiple sensor transmission monitoring indicator sets and multiple equipment transmission monitoring indicator sets; performing communication reliability authentication based on the multiple sensor transmission monitoring indicator sets and the multiple equipment transmission monitoring indicator sets, and when the authentication is passed, using the communication component to perform data transmission of the sensor deployment array and the equipment deployment array.

[0012] In a possible implementation, the intelligent construction collaborative operation platform integrating BIM and the Internet of Things also performs the following processing: the preset monitoring indicator set includes data transmission speed, delay duration and data packet loss rate.

[0013] Through the intelligent construction collaborative operation platform that integrates BIM and the Internet of Things proposed in this application, the historical data collected by the sensor deployment array and the equipment deployment array are transmitted to the BIM model for simulation to generate a historical construction model of the target area; obtain a real-time sensor collection data set and a real-time equipment collection data set; perform collection data missing authentication to obtain multiple data missing points; determine the fusion data of multiple missing points; obtain an updated historical construction model; analyze the construction collaborative operation plan of the target area to obtain the target construction collaborative operation plan. It solves the technical problem that it is difficult to accurately monitor the construction data of complex building sites in real time in existing intelligent construction, which makes the BIM model data out of sync, and then leads to insufficient accuracy of the construction collaborative operation plan and low operation efficiency, and achieves the technical effect of improving the accuracy of the collaborative operation plan and the efficiency of the operation collaboration. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solution of the embodiment of the present disclosure, the accompanying drawings of the embodiment of the present disclosure are briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the platform according to the embodiment of the present application. It should be understood that the previous or following operations are not necessarily performed precisely in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0015] Figure 1 A schematic diagram of the structure of an intelligent construction collaborative operation platform integrating BIM and the Internet of Things provided in an embodiment of the present application;

[0016] Figure 2 A schematic diagram of the execution flow of the collection data missing authentication module in the intelligent construction collaborative operation platform integrating BIM and the Internet of Things provided in an embodiment of the present application.

[0017] Explanation of the reference numerals: target area historical construction model generation module 10, real-time data collection module 20, collection data missing authentication module 30, neighbor data fusion and identification module 40, updated historical construction model acquisition module 50, target construction collaborative work plan acquisition module 60. DETAILED DESCRIPTION

[0018] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0019] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0020] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, platform, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or components that are not clearly listed or inherent to these processes, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0021] The present application embodiment provides an intelligent construction collaborative operation platform integrating BIM and IoT, such as Figure 1 As shown, the intelligent construction collaborative operation platform integrating BIM and IoT includes: a target area historical construction model generation module 10, a real-time data collection module 20, a collection data missing authentication module 30, a neighbor data fusion and identification module 40, an updated historical construction model acquisition module 50, and a target construction collaborative operation plan acquisition module 60.

[0022] The target area historical construction model generation module 10 is used to obtain the sensor layout array and the equipment layout array of the target area, and use the communication component to transmit the historical data collected by the sensor layout array and the equipment layout array in a preset historical window to the BIM model for simulation, so as to generate the historical construction model of the target area.

[0023] Preferably, the sensor array and the equipment array of the target area are obtained, that is, a plurality of sensors and equipment are arranged in the target building area, and these sensors can be used to monitor various environmental parameters (such as temperature, humidity, pressure, etc.) or equipment operation status (such as equipment working condition, vibration, energy consumption, etc.). The equipment array refers to a specific set of equipment used to control or collect data, such as equipment used in the construction process of monitors and data collectors, etc. Specifically, the sensor historical data and equipment historical data collected in the preset historical window are transmitted to the BIM model for simulation, wherein the communication component is used to realize data transmission, and the communication component can be used to transmit The data collected by on-site sensors and equipment are transmitted to the BIM model for processing. The communication components may involve wireless networks, optical fibers, Bluetooth and other data transmission methods. The preset historical window refers to the collection scope of historical data, which usually sets a time range, such as the past few days, weeks or months. The data collected by the sensor and equipment array within the preset historical time period is transmitted to the BIM (Building Information Model) through the communication components. The BIM model will simulate and reproduce the construction process or construction status based on these historical data, and finally generate a historical construction model of the target area, which reflects the specific situation, progress and status of the past construction stages of the target building area.

[0024] The real-time data acquisition module 20 is used to perform real-time data acquisition on the sensor array and the device array at a first moment to obtain a real-time sensor acquisition data set and a real-time device acquisition data set.

[0025] Preferably, the sensor array and the equipment array are used to collect real-time data of the target building area at the first moment, wherein the first moment refers to any time period, and multiple sensors and equipment deployed in the target area are used to monitor various environmental parameters, construction status, equipment operation status, operation data, etc. of the area in real time, and obtain a real-time sensor collection data set and a real-time equipment collection data set. The real-time sensor collection data set includes data of all sensors in the target area, such as temperature, humidity, pressure and other monitoring index data, and the real-time equipment collection data set includes information such as the operation status, operation process and performance indicators of all relevant equipment in the target area. Through real-time data collection, two types of data are obtained, namely, the environment and status data collected by the sensor and the data of the equipment operation status, which are used for subsequent model update analysis.

[0026] The collected data missing authentication module 30 is used to perform collected data missing authentication based on the real-time sensor collected data set, the real-time equipment collected data set and the historical construction model to obtain multiple data missing points, wherein the multiple data missing points include multiple missing position identifiers.

[0027] Preferably, the acquisition data missing authentication refers to the verification of the collected real-time data. Specifically, based on the generated historical construction model, the real-time sensor data and equipment data are compared with the data in the historical construction model to identify which data is missing or abnormal. The missing data is usually due to the failure of the sensor or device to successfully obtain the data during the acquisition process, or due to the interruption of data transmission, etc., thereby obtaining multiple data missing points, wherein the data missing point refers to the missing data found through authentication in the real-time collected data. These data points should have been collected, but due to various reasons (such as equipment failure, sensor failure, network interruption, etc.), they were not successfully collected. Each data missing point represents a data missing location and has a missing location identifier, that is, the specific location or source of each data missing point is marked. For example, a sensor is located in a certain area of ​​the building, and the data missing in this area is determined by the identifier, or the data of a certain device is not successfully collected. This information accurately points out the source of the data missing through the location identifier. The integrity of the real-time data is verified by collecting real-time sensor data and equipment data and comparing them with the data in the historical construction model.

[0028] Furthermore, the specific configuration of the data collection missing authentication module 30 also includes: mapping the real-time sensor data collection set and the real-time equipment data collection set to the historical construction model to obtain multiple initial data missing points and multiple initial data missing position identifiers; conditionally screening multiple central data missing points from the multiple initial data missing points, and identifying the edges of missing areas in the multiple initial data missing points based on the multiple central data missing points to determine multiple central data missing areas; performing missing authentication based on the multiple central data missing areas, and if the authentication is passed, using the multiple initial data missing points as multiple data missing points, and using the multiple initial data missing position identifiers as multiple data missing position identifiers; if the authentication fails, obtaining a data collection early warning instruction, and performing troubleshooting on the sensor layout array and the equipment layout array based on the data collection early warning instruction.

[0029] Preferably, the data collected from sensors and devices in real time are compared and mapped with the historical data in the generated historical construction model to find out the data points in the current data that are inconsistent with or missing from the historical model. Specifically, through the mapping of real-time data and historical construction models, multiple initial data missing points are identified. These points represent the parts of the current collected data that are missing or cannot be matched to the historical model. The initial data missing position identifier is the specific location of these missing data points in the building model or construction site. For example, the data that a sensor or device should collect is missing, and its position identifier will indicate the specific location or area of ​​the sensor or device; then, among the initial data missing points, multiple central data missing points are screened out through certain conditions (such as the severity of data missing, the concentration of the location, etc.). These central points are areas or locations where the missing problem is more obvious. Further based on these central points, the edge area of ​​the missing data is identified, that is, the range or regional boundary of the data missing is determined, which areas are the central areas of the data missing, and finally multiple central data missing areas are determined. These areas represent relatively concentrated data missing problems in the current collected data. By demarcating these areas, it is possible to more accurately know which areas have data collection problems that need further processing.

[0030] Preferably, the identified data missing points and missing areas are further authenticated to verify whether these missing points actually exist, for example, by analyzing other relevant data, historical models or surrounding sensor data to ensure the accuracy and reliability of the missing points. If the authentication is passed, these initial data missing points are officially confirmed as the final data missing points, and the initial position identifier is used as the final data missing position identifier, that is, it is confirmed that there are indeed missing points in the data collection process, and these missing points can be considered in the subsequent model update or decision-making process; if the authentication fails, it means that there may be a problem with the sensor or device itself, and there is an anomaly or equipment failure in the data collection process, and then a data collection early warning instruction is generated. This warning instruction will prompt the need for further troubleshooting of the sensor or device. Specifically, based on the data collection early warning instruction, the relevant sensor or device array is checked to check for possible faults or problems in the data collection process to ensure the normal operation of data collection and the integrity and reliability of subsequent collected data.

[0031] Further, such as Figure 2As shown, the specific configuration of the collected data missing authentication module 30 also includes: randomly extracting a preset number of initial data missing points from the multiple initial data missing points to obtain a random central data missing point set; enumerating the random central data missing point set in pairs to obtain multiple enumeration combinations, and performing distance calculations on the multiple enumeration combinations in combination with the multiple initial data missing position identifiers to obtain multiple enumeration combination distance values; counting the number of multiple enumeration combination distance values ​​that are less than or equal to a preset distance threshold to obtain anomalies, and iteratively updating the random central data missing point set based on the size of the anomalies until the updated anomaly amount is less than or equal to the preset anomaly amount, and using the data missing points in the updated random central data missing point set as multiple central data missing points.

[0032] Preferably, a preset number of missing points are randomly selected from multiple initial data missing points to form a random central data missing point set, where the preset number refers to a pre-set number of extractions, which can be determined according to a specific application scenario to ensure that the selected missing points are representative as much as possible, and then the data points in the randomly selected central data missing point set are enumerated in pairs, that is, all the data missing points in the set are paired in pairs to form multiple combinations. For example, if there are 3 data missing points A, B, and C in the set, the possible combinations are (A, B), (A, C), and (B, C), which can form multiple enumeration combinations to facilitate subsequent distance calculations; then, for each enumeration combination, the distance between these missing points is calculated in combination with their location information (initial data missing location identifiers), and based on multiple initial data missing location identifiers, multiple enumeration combination distance values ​​are obtained through distance calculations to determine the correlation between the missing points.

[0033] Preferably, the number of enumeration combinations whose enumeration combination distance values ​​are less than or equal to a preset distance threshold is counted, wherein the preset distance threshold is a critical value set in advance to determine whether two missing points are close to each other. If the enumeration combination distance is less than or equal to the preset distance threshold, it means that the two missing points may belong to the same area or have a stronger correlation, and then the anomaly is obtained, which represents how many missing points are close to each other or the number is inconsistent with the expected situation; then based on the size of the obtained anomaly, the random central data missing point set is iteratively updated. If the anomaly is large, it means that there may be more anomalies between the missing points, and the central data missing point set is reselected or adjusted until the anomaly is reduced to a reasonable range, that is, the updated anomaly is less than or equal to the preset anomaly, wherein the preset anomaly indicates that the anomaly is controlled within an acceptable range; finally, after the anomaly is controlled within the preset anomaly range, the points in the updated random central data missing point set are used as the final central data missing points, representing the data missing points after screening and optimization, and are the areas with the most concentrated or representative data missing.

[0034] Furthermore, the specific configuration of the collected data missing authentication module 30 also includes: constructing multiple first identification missing areas with the multiple central data missing points as multiple identification circle centers and a preset identification step as an identification radius; counting the number of missing points in the multiple first identification missing areas and calculating multiple first identification missing densities; performing area edge expansion on the multiple first identification missing areas according to the preset identification step to obtain multiple second identification missing areas, and calculating multiple second identification missing densities of the multiple second identification missing areas; when the multiple second identification missing densities are less than or equal to the multiple first identification missing densities, stopping the missing area edge identification and using the multiple first identification missing areas as the multiple central data missing areas; when the multiple second identification missing densities are greater than the multiple first identification missing densities, determining whether the density difference between the multiple second identification missing densities and the multiple first identification missing densities is less than or equal to a preset density difference threshold, and if so, stopping the missing area edge identification and using the multiple second identification missing areas as the multiple central data missing areas.

[0035] Preferably, multiple first identification missing areas are constructed with the determined multiple central data missing points as the identification center and a preset identification step (the step indicates the radius length) as the identification radius. Specifically, these first identification missing areas are circular areas surrounding each central missing point, similar to drawing a circle with a specific radius. Then, the number of missing points in each first identification missing area is counted, and then the ratio of the number of missing points to the area of ​​the corresponding first missing area is calculated, which is used as the corresponding first identification missing density to obtain multiple first identification missing densities; then the radius of each first identification missing area is expanded to twice the preset identification step, that is, it is further expanded outward on the basis of the original area to form a second identification missing area. After the expansion, the number of missing points in multiple new missing areas is counted, and the missing densities corresponding to these areas are calculated to obtain multiple second identification missing densities.

[0036] Preferably, if the missing density of the second identified missing area (region density after expansion) is less than or equal to the density of the first identified missing area, it means that as the area expands, the missing points do not increase significantly, or even decrease, and the expanded area is considered invalid or unnecessary, and the missing area edge identification is stopped (continued expansion), and the first identified missing area is finally used as the final central data missing area; if the density of the second identified missing area after expansion is greater than the first identified area, it means that as the area expands, the number of missing points is increasing. At this time, the missing density difference between the first identified missing area and the second identified missing area is calculated and compared with the preset density difference threshold. If the density difference between the two identified missing areas is less than or equal to the preset density difference threshold, it means that although the expanded area has more missing points, the density difference is within an acceptable range, and the expanded area is considered reasonable, and further expansion is stopped, and the second identified missing area is used as the final central data missing area. Through the analysis of missing density, the data missing area can be accurately identified to ensure the integrity of data collection.

[0037] Furthermore, the specific configuration of the collected data missing authentication module 30 also includes determining whether there is a missing point density greater than or equal to a preset density threshold among the multiple missing point densities of the multiple central data missing areas. If so, the authentication fails.

[0038] Preferably, the missing point density of each central data missing area is checked to determine whether there is any area with a density greater than or equal to a preset density threshold. If it is detected that the density of one or more missing points exceeds or equals the preset density threshold, it means that the data missing degree of the area is too serious and cannot pass the authentication. Further troubleshooting, data supplementation, etc. are required to ensure the integrity and accuracy of the data.

[0039] The neighbor data fusion identification module 40 is used to perform neighbor data fusion identification in the real-time sensor collection data set and the real-time device collection data set according to the multiple data missing points and the multiple missing position identifiers to determine multiple missing point fusion data.

[0040] Preferably, neighbor data fusion identification refers to inferring and filling missing data by analyzing the surrounding data of the missing point (i.e., neighboring data). Neighboring data refers to data collected by other sensors or devices that are close to the physical position of the missing point. Specifically, the data collected by sensors and devices that are close in space usually have a certain correlation, so the neighboring data is used to estimate the data of the missing point, that is, according to multiple data missing points and multiple missing position identifiers, the data of the missing point is estimated by the neighboring real-time data in the real-time sensor collection data set and the real-time device collection data set. For example, the missing point data is estimated by using a graph neural network. Specifically, the data of the sensor and the device is regarded as a graph structure, each sensor or device is a network node, and the edge of the network is represented by the neighboring relationship between the sensors and the devices. The graph neural network identifies the neighboring data around each missing point by learning the relationship between the sensor and device data (such as distance, historical correlation, etc.), and then gradually fuses the neighbor information of each node to obtain the predicted value of the missing point, and finally determines multiple missing point fusion data. These missing point fusion data are the results of inference based on the data of the neighboring sensors and devices, which are used to fill the missing data that could not be obtained before, thereby improving the data integrity and reliability.

[0041] Furthermore, the specific configuration of the neighbor data fusion identification module 40 also includes: retrieving multiple first-level neighbor data sets of the multiple data missing points in the real-time sensor collection data set and the real-time device collection data set based on the multiple missing position identifiers, wherein the first-level neighbor data is the data of the data points directly associated with the data missing points; based on the multiple first-level neighbor data sets, searching in the real-time sensor collection data set and the real-time device collection data set to obtain multiple second-level neighbor data sets of the multiple data missing points, wherein the second-level neighbor data is the data of the data points directly associated with the data points corresponding to the first-level neighbor data; performing data prediction on the multiple data missing points according to the multiple first-level neighbor data sets and the multiple second-level neighbor data sets to obtain multiple missing point fusion data.

[0042] Preferably, in the real-time sensor collection data set and the real-time device collection data set, multiple missing position identifiers are used to find the first-level neighbor data directly associated with the missing point, and then based on the first-level neighbor data, the second-level neighbor data associated with it is further retrieved to expand the data association range. Through two-step retrieval, multi-level data related to the missing point can be collected to enhance the accuracy of data prediction. Specifically, the first-level neighbor data refers to the data point directly associated with the data missing point. The association can be spatial proximity or physical connection, reflecting the data correlation between adjacent sensors or devices. For example, assuming that a sensor is missing data, the data of other sensors that are closer to this sensor will be regarded as first-level neighbor data. The first-level neighbor data set is all of these A collection of adjacent data; secondary neighbor data refers to other retrieved data points that are directly associated with the primary neighbor data, that is, secondary neighbor data are data points that are indirectly associated with data missing points, which can help capture a wider range of data patterns and trends, and provide more information to predict the data of missing points; then, based on the collected primary neighbor data set and secondary neighbor data set, data prediction is performed for each missing point. Specifically, by analyzing these neighboring data, the data pattern of the missing point is identified, and the reasonable value of the missing point is inferred, that is, the value of the missing point is derived based on the neighboring data, and finally, through the fusion and analysis of the primary and secondary neighbor data, predicted fused data is generated for each missing point, that is, multiple missing points are fused data, which effectively supplements the data missing and ensures the integrity of the data.

[0043] The updated historical construction model obtaining module 50 is used to update the historical construction model according to the multiple missing point fusion data, the real-time sensor collection data set and the real-time device collection data set to obtain an updated historical construction model.

[0044] Preferably, the historical construction model generated by historical data is updated according to the acquired multiple missing point fusion data, the real-time sensor collection data set and the real-time equipment collection data set. Specifically, the existing historical construction model is updated according to these new data, including fusion data update, integrating the missing point data obtained by prediction and neighbor data fusion into the model to make up for the previous blank data; real-time data update, in addition to fusion data, also uses the latest real-time sensor and equipment data to replace or supplement the original historical data to ensure that the model can accurately reflect the actual situation of the current building or construction site; finally, an updated historical construction model is generated, that is, an updated historical construction model is obtained, which not only includes historical data but also adds real-time data of the current time, so that the construction model can more accurately reflect the current construction status of the target area, thereby providing reliable construction guidance and support for subsequent analysis and construction management.

[0045] The target construction collaborative work plan acquisition module 60 is used to obtain target construction task information, analyze the construction collaborative work plan of the target area in combination with the updated historical construction model, and obtain the target construction collaborative work plan.

[0046] Preferably, the target construction task information is obtained from the project management system and the construction plan, that is, the current construction task information is obtained to guide the actual construction process, mainly including the specific tasks, progress requirements, resource allocation, construction steps and related task goals that need to be completed in the project at present, and then the obtained target construction task information is combined with the updated historical construction model and a collaborative work plan analysis is performed. Specifically, if the task requires the completion of specific construction steps in a certain building area, based on the real-time data and construction progress information in the updated historical construction model, it is judged whether the conditions for completing the task are currently met, and how to coordinate the work of various teams and equipment in the current state is analyzed to ensure that the construction task can be carried out efficiently and seamlessly, such as analyzing which group of workers needs to use certain equipment in which time period, or which task needs to be completed first to avoid resource conflicts, and finally generating a collaborative work plan to ensure the coordinated operation of various tasks, teams, equipment and resources in the construction process, which may include task scheduling, resource allocation, time planning and conflict prevention, etc., to ensure the efficient, coordinated and seamless progress of construction tasks, and avoid resource conflicts through real-time data and model support to improve the efficiency of construction collaborative work.

[0047] Furthermore, the specific configuration of the intelligent construction collaborative operation platform integrating BIM and the Internet of Things also includes: performing data transmission monitoring on the sensor deployment array and the equipment deployment array according to a preset monitoring indicator set to obtain multiple sensor transmission monitoring indicator sets and multiple equipment transmission monitoring indicator sets; performing communication reliability authentication based on the multiple sensor transmission monitoring indicator sets and the multiple equipment transmission monitoring indicator sets, and when the authentication is passed, using the communication component to perform data transmission on the sensor deployment array and the equipment deployment array.

[0048] Furthermore, the preset monitoring indicator set includes data transmission speed, delay duration and data packet loss rate.

[0049] Preferably, data transmission monitoring specifically refers to real-time monitoring and evaluation of the performance of sensor arrays and device arrays during data transmission according to preset monitoring indicators (transmission speed, delay time and packet loss rate), ensuring that sensors and devices perform well during data transmission and meet preset performance standards, thereby obtaining multiple sensor transmission monitoring indicator sets and multiple device transmission monitoring indicator sets. Each sensor and device will have a set of transmission monitoring indicators that record its current transmission speed, delay time, packet loss rate and other information. These sets summarize the transmission performance data of multiple sensors and devices, wherein the data transmission speed is used to measure the time required for data to be transmitted from a sensor or device to a receiving end, usually expressed in bits per second (bps). A higher transmission speed means that data can be transmitted from a sensor or device to a destination faster; the delay time is also called latency, which refers to the time spent in the transmission process of data from the source to the destination. A shorter delay time indicates that the data transmission is faster and more timely; the packet loss rate indicates the proportion of data packets lost during the transmission process. The lower the packet loss rate, the more reliable the transmission process and the less data loss.

[0050] Preferably, the communication reliability certification is based on the collection of transmission monitoring indicators of sensors and devices to evaluate whether their data transmission is reliable enough to ensure that the data transmission meets the preset standards and avoid errors or delays in the transmission process. If the transmission indicators of some sensors or devices (such as excessive packet loss rate or long delay) do not meet the standards, they will not pass the certification. If the communication reliability certification is passed, it means that the data transmission quality of the sensors and devices meets the requirements. At this time, formal data transmission is allowed through the communication component, and the collected sensor data and device data are transmitted to the BIM model, thereby ensuring the stability and reliability of the transmission.

[0051] Although the present application makes various references to certain components in the platform according to the embodiments of the present application, any number of different components may be used and run on the user terminal and / or server, and the various units and components included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be implemented; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0052] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.

Claims

1. Intelligent construction collaborative operation platform integrating BIM and IoT, characterized by: The platform includes: A target area historical construction model generation module is used to obtain a sensor layout array and a device layout array of the target area, and use a communication component to transmit historical data collected by the sensor layout array and the device layout array in a preset historical window to a BIM model for simulation, so as to generate a historical construction model of the target area; A real-time data acquisition module, used to perform real-time data acquisition on the sensor array and the device array at a first moment to obtain a real-time sensor acquisition data set and a real-time device acquisition data set; A collection data missing authentication module, used to perform collection data missing authentication based on the real-time sensor collection data set, the real-time device collection data set and the historical construction model, and obtain a plurality of data missing points, wherein the plurality of data missing points include a plurality of missing position identifiers; A neighbor data fusion identification module is used to perform neighbor data fusion identification in the real-time sensor collection data set and the real-time device collection data set according to the multiple data missing points and the multiple missing position identifiers, and determine multiple missing point fusion data; An updated historical construction model acquisition module is used to update the historical construction model according to the multiple missing point fusion data, the real-time sensor collection data set and the real-time device collection data set to obtain an updated historical construction model; A target construction collaborative operation plan acquisition module is used to obtain target construction task information, analyze the construction collaborative operation plan of the target area in combination with the updated historical construction model, and obtain a target construction collaborative operation plan; Wherein, based on the real-time sensor collection data set, the real-time equipment collection data set and the historical construction model, collection data missing authentication is performed to obtain multiple data missing points, including: Mapping the real-time sensor collected data set and the real-time device collected data set to the historical construction model to obtain a plurality of initial data missing points and a plurality of initial data missing position identifiers; Conditionally selecting a plurality of central data missing points from the plurality of initial data missing points, identifying missing area edges in the plurality of initial data missing points based on the plurality of central data missing points, and determining a plurality of central data missing areas; Performing missing data authentication based on the multiple central data missing areas, and if the authentication is passed, using the multiple initial data missing points as multiple data missing points, and using the multiple initial data missing position identifiers as the multiple data missing position identifiers; If the authentication fails, a data acquisition warning instruction is obtained, and the sensor array and the device array are troubleshooted based on the data acquisition warning instruction; The method of conditionally selecting a plurality of central data missing points from the plurality of initial data missing points, identifying missing area edges among the plurality of initial data missing points based on the plurality of central data missing points, and determining a plurality of central data missing areas comprises: Randomly extracting a preset number of initial data missing points from the multiple initial data missing points to obtain a random central data missing point set; Enumerate the random central data missing point sets in pairs to obtain multiple enumeration combinations, and perform distance calculations on the multiple enumeration combinations in combination with the multiple initial data missing position identifiers to obtain multiple enumeration combination distance values; Counting the number of multiple enumeration combination distance values ​​that are less than or equal to a preset distance threshold to obtain anomaly quantity, iteratively updating the random central data missing point set based on the size of the anomaly quantity until the updated anomaly quantity is less than or equal to the preset anomaly quantity, and using the data missing points in the updated random central data missing point set as multiple central data missing points; The method of identifying the edges of missing regions among the multiple initial data missing points based on the multiple central data missing points to determine multiple central data missing regions includes: Constructing a plurality of first identification missing areas with the plurality of central data missing points as a plurality of identification circle centers and a preset identification step length as an identification radius; Counting the number of missing points in the plurality of first identified missing regions, and calculating a plurality of first identified missing densities; Expanding the region edges of the plurality of first identified missing regions according to a preset identification step length to obtain a plurality of second identified missing regions, and calculating a plurality of second identified missing densities of the plurality of second identified missing regions; When the plurality of second identified missing densities are less than or equal to the plurality of first identified missing densities, stopping the missing region edge identification, and using the plurality of first identified missing regions as the plurality of central data missing regions; When the multiple second identification missing densities are greater than the multiple first identification missing densities, determine whether the density difference between the multiple second identification missing densities and the multiple first identification missing densities is less than or equal to a preset density difference threshold. If so, stop identifying the missing area edges and use the multiple second identification missing areas as the multiple central data missing areas.

2. The intelligent construction collaborative operation platform integrating BIM and the Internet of Things as claimed in claim 1 is characterized in that: It is determined whether there is a missing point density greater than or equal to a preset density threshold among the multiple missing point densities of the multiple central data missing areas. If so, the authentication fails.

3. The intelligent construction collaborative operation platform integrating BIM and the Internet of Things as claimed in claim 1, characterized in that: According to the multiple data missing points and the multiple missing position identifiers, neighbor data fusion identification is performed in the real-time sensor collection data set and the real-time device collection data set to determine multiple missing point fusion data, including: Retrieving a plurality of first-order neighbor data sets of the plurality of data missing points in the real-time sensor collected data set and the real-time device collected data set based on the plurality of missing position identifiers, wherein the first-order neighbor data is data of data points directly associated with the data missing points; Based on the multiple first-level neighbor data sets, searching is performed in the real-time sensor collection data set and the real-time device collection data set to obtain multiple second-level neighbor data sets of the multiple data missing points, wherein the second-level neighbor data is data of data points directly associated with data points corresponding to the first-level neighbor data; Data prediction is performed on the multiple data missing points according to the multiple first-level neighbor data sets and the multiple second-level neighbor data sets to obtain multiple missing point fusion data.

4. The intelligent construction collaborative operation platform integrating BIM and the Internet of Things as claimed in claim 1, characterized in that: include: Performing data transmission monitoring on the sensor deployment array and the device deployment array according to a preset monitoring indicator set to obtain multiple sensor transmission monitoring indicator sets and multiple device transmission monitoring indicator sets; Communication reliability authentication is performed based on the multiple sensor transmission monitoring indicator sets and the multiple device transmission monitoring indicator sets. When the authentication is passed, the communication component is used to perform data transmission of the sensor array and the device array.

5. The intelligent construction collaborative operation platform integrating BIM and the Internet of Things as claimed in claim 4 is characterized in that: The preset monitoring indicator set includes data transmission speed, delay duration and data packet loss rate.

Images