Building intelligent actual measurement and quantity management method and system

Abstract

The invention provides an intelligent actual measurement and quantity management method and system for a building. The method comprises the following steps: capturing environmental parameters, material circulation paths and spatial geometric information of key parts of a building in a construction process in real time to obtain a measurement data set; a distributed ledger technology is combined with a homomorphic encryption algorithm, a graph theory analysis technology is applied to evaluate a dependency relationship among operation points of a construction site, and a data log is generated; according to the data log, using an augmented reality technology to superpose a BIM model, introducing a support vector machine algorithm to carry out automatic classification and risk assessment processing on deviation data between measured data and preset standard data, and generating a rectification suggestion report; and a closed-loop quality management process is formed by continuously collecting rectification effect feedback. According to the technical scheme, high transparency and efficient quality control in the construction process are ensured.

Description

Technical Field

[0001] The embodiments of the present application relate to the technical field of intelligent actual measurement and quantity, and in particular to a method and system for managing intelligent actual measurement and quantity of buildings. Background Art

[0002] In the process of modern building construction, it is crucial to capture in real time the environmental parameters of the building, the material flow path, and the spatial geometric information of key parts. The project team needs to accurately record the operation details, timestamps, and operator identity identifiers of each operation point at the construction site to ensure the transparency and traceability of the construction process. In addition, it is necessary to perform accurate mapping processing on the measured data, identify quality risk areas, and generate rectification suggestion reports to achieve efficient construction management and quality control.

[0003] Currently, most building projects rely on traditional paper records or simple spreadsheets to track construction progress and manage quality control. Some more advanced projects may use BIM (Building Information Modeling) technology for 3D modeling and visualization, but these systems usually lack the ability to synchronize with actual construction data in real time and fail to fully integrate distributed ledger technology and encryption algorithms to protect data security and privacy.

[0004] Existing solutions have several deficiencies: First, traditional recording methods are prone to data loss or tampering, making it difficult to ensure the authenticity and integrity of data; second, there is a lack of effective automated tools to process and analyze a large amount of measured data, resulting in low efficiency in deviation detection and risk assessment; finally, the existing quality management process is often an open-loop system, and the implementation and effect feedback of rectification measures cannot form a closed loop, affecting the speed and effectiveness of problem-solving. Summary of the Invention

[0005] The embodiments of the present application provide a method and system for managing intelligent actual measurement and quantity of buildings to solve the problem of easy loss or tampering of data in the prior art.

[0006] In a first aspect, the embodiments of the present application provide a method for managing intelligent actual measurement and quantity of buildings, including: Capturing in real time the environmental parameters of the building, the material flow path, and the spatial geometric information of key parts of the building during the construction process to obtain a measurement data set; Using distributed ledger technology combined with homomorphic encryption algorithm to encrypt the measurement data set, recording the operation details, timestamps, and operator identity identifiers of all actual measurement activities carried out at each operation point at the construction site in the encrypted state, and applying graph theory analysis technology to evaluate the dependency relationship between each operation point at the construction site to generate a data log; Overlay the BIM model using augmented reality technology, perform precise mapping processing on the measured data in the data log, introduce the support vector machine algorithm to automatically classify and risk-assess the deviation data between the measured data and the preset standard data, identify the quality risk areas, generate a rectification suggestion report, and the rectification suggestion report contains specific rectification measures for the quality risk areas; Automatically match and assign the specific rectification measures formulated for the quality risk areas according to the preset rules and the weight scoring model, adjust the rules and methods for guiding the allocation of specific rectification measures by collecting the rectification effect feedback, and form a closed-loop quality management process.

[0007] Optionally, use the distributed ledger technology combined with the homomorphic encryption algorithm to encrypt the measurement data set, record the operation details, timestamps, and operator identity identifiers of all measured activities at each construction site operation point in the encrypted state, and apply graph theory analysis technology to evaluate the dependency relationships between the operation points at the construction site, generate a data log, including: Use the distributed ledger technology combined with the homomorphic encryption algorithm to encrypt the operation details, timestamps, and operator identity identifiers of all measured activities at each construction site operation point to obtain the encrypted operation records; According to the encrypted operation records, adopt the Byzantine fault-tolerant consensus mechanism to verify and reach a consensus among multiple system nodes in the distributed ledger technology, and add the encrypted operation records to the blockchain to generate a preliminary data log; Use the preliminary data log and apply graph theory analysis technology to model and analyze the dependency relationships between the operation points at the construction site to obtain a dependency relationship model; Based on the dependency relationship model, combined with the construction schedule plan formulated in advance according to the specific requirements and design requirements of the project, optimize and adjust the on-site operation process, and encrypt and record the optimized on-site operation process again using the distributed ledger technology and the homomorphic encryption algorithm to generate a data log.

[0008] Optionally, the step of adopting the Byzantine fault-tolerant consensus mechanism to verify and reach a consensus among multiple system nodes in the distributed ledger technology and adding the encrypted operation records to the blockchain to generate a preliminary data log includes: Adopt the Byzantine fault-tolerant consensus mechanism to perform validity verification processing on the encrypted operation records corresponding to each measured activity to obtain the verification results; Based on the verification results, perform consistency confirmation processing among multiple system nodes in the distributed ledger technology to generate a consensus decision; Using the consensus decision, add the encrypted operation records to the blockchain to form a block structure, and synchronize them to all system nodes in the distributed ledger technology to obtain block-based operation records; Apply graph theory analysis technology to evaluate the dependency relationships between various operation points at the construction site, and at the same time integrate all block-based operation records to generate a preliminary data log.

[0009] Optionally, based on the dependency relationship model, combined with the construction progress plan formulated in advance according to the specific requirements and design requirements of the project, optimize and adjust the on-site operation process, and use the distributed ledger technology and homomorphic encryption algorithm again to encrypt and record the optimized on-site operation process to generate a data log, including: Use the dependency relationship model to model and analyze the dependency relationships between various operation points at the construction site to obtain the dependency relationship analysis results; According to the dependency relationship analysis results, combined with specific requirements and the construction progress plan, optimize and adjust the on-site operation process to generate an optimized on-site operation process plan; Based on the optimized on-site operation process plan, apply the distributed ledger technology and homomorphic encryption algorithm to encrypt the details of each activity operation, timestamp, and operator identity identifier in the on-site operation process plan to obtain encrypted optimized operation process records; According to the encrypted optimized operation process records, use the Byzantine fault-tolerant consensus mechanism to verify and reach a consensus among multiple system nodes in the distributed ledger technology, add the encrypted optimized operation process records to the blockchain to form a block structure, and synchronize them to all system nodes to obtain block-based optimized operation process records; Use the block-based optimized operation process records to integrate all block-based information related to the optimized on-site operation process to generate a data log.

[0010] Optionally, use augmented reality technology to overlay the BIM model, perform precise mapping processing on the measured data in the data log, introduce the support vector machine algorithm to automatically classify and risk assess the deviation data between the measured data and the preset standard data to identify the quality risk areas, and generate a rectification suggestion report. The rectification suggestion report contains specific rectification measures for the quality risk areas, including: Use augmented reality technology to overlay the BIM model and perform precise mapping processing on the measured data of each operation point at the construction site in the data log to obtain a three-dimensional visualization interface; Based on the three-dimensional visualization interface, combined with spatial analysis technology, compare the measured data with the preset standard data to generate deviation data; Introduce the support vector machine algorithm to automatically classify and perform risk assessment on deviation data, identify quality risk areas, and generate a quality risk assessment report; According to the quality risk assessment report, comprehensively consider construction progress and resource allocation factors, formulate targeted rectification measures, and generate a rectification suggestion report.

[0011] Optionally, the introducing the support vector machine algorithm to automatically classify and perform risk assessment on deviation data, identify quality risk areas, and generate a quality risk assessment report includes: Introduce the support vector machine algorithm to automatically classify the deviation data and generate a classification result; According to the classification result, based on the support vector machine algorithm, perform risk assessment on the classified deviation data, identify quality risk areas, and generate a risk assessment conclusion; Based on the risk assessment conclusion, comprehensively organize all identified quality risk information and generate a quality risk assessment report.

[0012] Optionally, the automatically matching and assigning the specific rectification measures formulated for the identified quality risk areas according to preset rules and a weight scoring model, and adjusting the rules and methods for guiding the distribution of specific rectification measures by collecting rectification effect feedback to form a closed-loop quality management process includes: Perform intelligent matching and automated assignment on the specific rectification measures formulated according to the rectification suggestion report to generate a task assignment list; Based on the task assignment list, utilize intelligent contract technology and record the execution status of each task through a blockchain system built in the entire construction project management to obtain a task execution progress record; By collecting the rectification effect feedback in the task execution progress record, combining real-time data analysis technology and machine learning algorithms, establish a dynamic performance evaluation system and generate a preliminary performance evaluation result reflecting the actual rectification effect; Utilize the preliminary performance evaluation result, introduce historical data mining and expert system optimization mechanisms, adjust the task assignment strategy, and update the weight scoring model to form a closed-loop quality management process.

[0013] In a second aspect, an embodiment of the present application provides a building intelligent actual measurement and quality management system, including: A capture module for capturing in real time the environmental parameters, material flow paths during the construction process of the building, and the spatial geometric information of key parts of the building to obtain a measurement data set; A recording module, configured to encrypt the measurement data set by using distributed ledger technology in combination with a homomorphic encryption algorithm, record the operation details, timestamps, and operator identity identifiers of all actual measurement activities carried out at each construction site operation point in the encrypted state, and apply graph theory analysis technology to evaluate the dependency relationships between the operation points at the construction site, and generate a data log; A mapping module, configured to use augmented reality technology to overlay a BIM model, perform precise mapping processing on the actual measurement data in the data log, introduce a support vector machine algorithm to automatically classify and risk-assess the deviation data between the actual measurement data and the preset standard data, identify quality risk areas, and generate a rectification suggestion report, where the rectification suggestion report includes specific rectification measures for the quality risk areas; An adjustment module, configured to automatically match and assign the specific rectification measures formulated for the quality risk areas according to a preset rule and a weight scoring model, and adjust the rules and methods for guiding the distribution of specific rectification measures by collecting rectification effect feedback, so as to form a closed-loop quality management process.

[0014] In a third aspect, an embodiment of the present application provides a computing device, including a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a method for intelligent actual measurement and quality control management of a building as described in the first aspect.

[0015] In a fourth aspect, an embodiment of the present application provides a computer storage medium, characterized in that it stores a computer program, and when the computer program is executed by a computer, it implements a method for intelligent actual measurement and quality control management of a building as described in the first aspect.

[0016] In the embodiments of the present application, Capture the environmental parameters, material flow paths, and spatial geometric information of key parts of the building during the construction process in real time to obtain a measurement dataset; use distributed ledger technology combined with homomorphic encryption algorithms to encrypt the measurement dataset, record the operation details, timestamps, and operator identity identifiers of all actual measurement activities at each construction site operation point in the encrypted state, and apply graph theory analysis technology to evaluate the dependencies between operation points at the construction site to generate a data log; use augmented reality technology to overlay the BIM model, perform precise mapping processing on the measured data in the data log, introduce a support vector machine algorithm to automatically classify and risk-assess the deviation data between the measured data and the preset standard data to identify quality risk areas, generate a rectification recommendation report, and the rectification recommendation report includes specific rectification measures for the quality risk areas; automatically match and assign the specific rectification measures formulated for the quality risk areas according to preset rules and a weight scoring model, and adjust the rules and methods for guiding the distribution of specific rectification measures by collecting rectification effect feedback to form a closed-loop quality management process.

[0017] The technical solution of this application has the following beneficial effects: By leveraging distributed ledger technology and homomorphic encryption algorithms, ensure that the operation details, timestamps, and operator identity identifiers of all on-site measurement activities during construction are recorded and processed in an encrypted state. This not only protects the security of sensitive information but also allows certain types of calculations to be performed without decryption, thereby enhancing the level of data privacy protection; Real-time capture of environmental parameters, material flow paths, and spatial geometric information of key parts during the building construction process, and generate detailed measurement data sets. Combining graph theory analysis techniques to evaluate the dependencies between operation points, the generated data logs have anti-tampering characteristics, ensuring that every step of the construction process can be traced throughout, enhancing the transparency of the project; Use augmented reality (AR) technology to overlay the BIM model for precise mapping of the measured data, enabling deviation data to be visually displayed. Introduce the support vector machine (SVM) algorithm to automatically classify and risk-assess the deviation data, identify quality risk areas, and generate a rectification suggestion report. This method not only improves the efficiency of quality management but also can detect and solve potential problems in advance, reducing the possibility of rework in the later stage; According to the rectification suggestion report, automatically match and assign specific rectification measures according to preset rules and weight scoring models. By continuously collecting feedback on the rectification effect, establish a performance evaluation system, and continuously adjust the task assignment strategy to form a closed-loop quality management process. This mechanism promotes efficient collaboration among multiple parties such as the construction team, supervision party, and design party, ensuring that each rectification task can be executed promptly and accurately; The entire system is built based on blockchain technology, realizing full-process automated management and intelligent decision support from data collection to problem identification and then to the implementation of rectification measures. By continuously optimizing and improving the task assignment strategy, ensure that the construction process is more scientific and reasonable, promote the development of building engineering towards intelligence and refinement, and ultimately improve the overall construction quality and efficiency.

[0018] Furthermore, by using distributed ledger technology in combination with homomorphic encryption algorithms based on the measurement dataset, the operation details, timestamps, and operator identity identifiers of all the actual measurement activities at each operation point on the construction site are encrypted to obtain encrypted operation records. The Byzantine fault-tolerant consensus mechanism is used to verify and reach a consensus among multiple system nodes, and the encrypted operation records are added to the blockchain to generate preliminary data logs. Further, graph theory analysis technology is applied to evaluate the dependency relationships between the operation points on the construction site, forming a dependency relationship model. Combining with the pre-established construction schedule, the on-site operation process is optimized and adjusted, and the distributed ledger technology and homomorphic encryption algorithms are used again for encrypted recording, finally generating data logs with anti-tampering characteristics. This method not only ensures the security and privacy protection of data, preventing the leakage of sensitive information, but also realizes the full transparency and traceability of the construction process through blockchain technology, enhancing the trust foundation for multi-party collaboration. At the same time, the application of graph theory analysis technology makes the dependency relationships between operation points clearly visible, helping to identify potential conflicts in advance and optimize the construction process, improving the construction efficiency and quality control level. In addition, the closed-loop quality management process promotes the effective implementation and continuous improvement of rectification measures, significantly enhancing the overall construction project management level and execution efficiency. In summary, this method effectively improves the data security, transparency, intelligence, and refinement degree of the building construction process, providing a solid guarantee for the smooth progress of the project.

[0019] Furthermore, by using augmented reality (AR) technology to overlay the BIM model according to the immutable data logs, the actual measurement data is accurately mapped to obtain a three-dimensional visualization interface. Based on this interface and combined with spatial analysis technology, the actual measurement data and preset standard data at each operation point on the construction site are compared to generate a deviation comparison result. Further, the support vector machine (SVM) algorithm is used to automatically classify and risk-assess the deviation data, identify the quality risk areas, generate a quality risk assessment report, and finally formulate targeted rectification measures by comprehensively considering the construction schedule and resource allocation factors to generate a rectification suggestion report. This method not only realizes the intuitive display and accurate mapping of the actual measurement data during the construction process, improving the visualization and understanding degree of the data, but also significantly enhances the efficiency and accuracy of quality management through automated deviation classification and risk assessment, ensuring that problems can be discovered and solved in a timely manner. In addition, the rectification measures formulated based on the quality risk assessment report are more scientific and reasonable, helping to optimize resource allocation and construction schedule arrangements, reducing the possibility of rework and delays. Overall, this method effectively enhances the quality control level during the construction process, promotes the scientific nature of multi-party collaboration and decision-making, and drives the development of building engineering management towards intelligence and refinement, providing a solid guarantee for the high-quality completion of the project.

[0020] These aspects or other aspects of the present application will be more clearly understood in the following description of the embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0022] Figure 1 It is a flowchart of a method for actual measurement and management of building intelligentization provided by an embodiment of the present application; Figure 2 It is a schematic structural diagram of a system for actual measurement and management of building intelligentization provided by an embodiment of the present application; Figure 3 It is a schematic structural diagram of a computing device provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0023] In order to enable those skilled in the art to better understand the solutions of the present application, the following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application.

[0024] In some processes described in the specification, claims and the above drawings of the present application, there are multiple operations that appear in a specific order. However, it should be clearly understood that these operations may not be executed in the order in which they appear herein or may be executed in parallel. The operation numbers such as 101, 102, etc. are only used to distinguish different operations, and the numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions such as "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., and do not represent a sequence, nor do they limit that "first" and "second" are of different types.

[0025] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, rather than all embodiments. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present application.

[0026] Figure 1 There is provided a flowchart of a method for actual measurement and management of building intelligentization for an embodiment of the present application, as Figure 1 shown. The method includes: 101. Capture the environmental parameters, material flow paths, and spatial geometric information of key parts of the building during the construction process in real time to obtain a measurement dataset; In this step, capture the environmental parameters (such as temperature, humidity, etc.), material flow paths (including the specific transportation routes of materials from the warehouse to the construction site), and spatial geometric information of key parts of the building (such as the key dimensions and positions of the building structure) during the construction process in real time. These data are used to construct a comprehensive measurement dataset to ensure the accuracy and reliability of the basic data for subsequent analysis.

[0027] In the embodiment of the present application, various sensors and monitoring devices installed at the construction site are used to collect the above-mentioned various types of data in real time and transmit them to the central database for preliminary processing and storage, providing solid data support for subsequent encrypted records and dependency evaluations.

[0028] Suppose in a high-rise building project, an Internet of Things (IoT) sensor network is used to monitor environmental parameters such as temperature, humidity, and air quality at the construction site in real time; at the same time, RFID tags are used to track the flow paths of building materials, and a laser scanner is used to obtain the three-dimensional spatial geometric information of key parts of the building. All these data are centrally collected and stored in a cloud database to form a complete measurement dataset.

[0029] 102. Use distributed ledger technology combined with homomorphic encryption algorithms to encrypt the measurement dataset, record the operation details, timestamps, and operator identity identifiers of all actual measurement activities carried out at each operation point at the construction site in the encrypted state, and apply graph theory analysis technology to evaluate the dependencies between operation points at the construction site to generate a data log; In this step, use distributed ledger technology combined with homomorphic encryption algorithms to encrypt the operation details (such as operation types, tool usage), timestamps, and operator identity identifiers (such as employee numbers, job information) of all actual measurement activities carried out at each operation point at the construction site to ensure data security and privacy protection; apply graph theory analysis technology to evaluate the dependencies between operation points to generate a tamper-proof data log.

[0030] In the embodiment of the present application, the encrypted operation records are added to the blockchain, and the Byzantine fault-tolerant consensus mechanism is used to ensure that multiple nodes reach a consensus, thereby ensuring the authenticity and immutability of the data. Then, use graph theory analysis technology to establish a dependency relationship model between operation points to optimize the construction process.

[0031] Suppose in a bridge construction project, all on-site operations are recorded by mobile devices and immediately uploaded to the blockchain platform. Before each upload, the data is homomorphically encrypted to protect sensitive information. Then, the system automatically analyzes the logical sequence and mutual influence between different operation points, generates a data log reflecting the dependency relationship between operation points, ensuring that every step of the operation is traceable and tamper-proof.

[0032] 103. Use augmented reality technology to overlay the BIM model, perform precise mapping processing on the measured data in the data log, introduce the support vector machine algorithm to automatically classify and perform risk assessment processing on the deviation data between the measured data and the preset standard data, identify the quality risk area, and generate a rectification suggestion report, where the rectification suggestion report contains specific rectification measures for the quality risk area; In this step, according to the data log, use augmented reality (AR) technology to overlay the BIM model, perform precise mapping processing on the measured data actually measured at the construction site, introduce the support vector machine (SVM) algorithm to automatically classify and perform risk assessment processing on the deviation data between the measured data and the preset standard data, identify the quality risk area, and generate a rectification suggestion report.

[0033] In the embodiment of this application, by combining the BIM model with the actual construction scenario through AR technology, engineers can intuitively see the difference between the measured data and the preset standard data. The system uses the SVM algorithm to automatically classify the deviation data and evaluate the risk level, and finally generates a detailed rectification suggestion report to guide the on-site rectification work.

[0034] Suppose in a residential building construction, engineers wear AR glasses to view the construction site and intuitively compare the actual measurement results through the BIM model on the glasses screen. The system automatically detects that the thickness of some walls does not meet the design requirements and immediately generates a report containing specific rectification measures, prompting relevant personnel to correct the problem in time to avoid subsequent rework.

[0035] 104. Automatically match and assign the specific rectification measures formulated for the quality risk area according to the preset rules and weight scoring model, and by collecting feedback on the rectification effect, adjust the rules and methods for guiding the distribution of specific rectification measures to form a closed-loop quality management process.

[0036] In this step, automatically match and assign the specific rectification measures formulated for the identified quality risk area according to the preset rules and weight scoring model, and by continuously collecting feedback on the rectification effect, establish a performance evaluation system, and continuously adjust the rules and methods for guiding the distribution of specific rectification measures to form a closed-loop quality management process.

[0037] In the embodiments of the present application, the system automatically generates a task list based on the rectification suggestion report and assigns it to the corresponding responsible party according to the priority. Subsequently, the system tracks the execution progress and effect feedback of each task, dynamically adjusts the task assignment strategy to ensure the effective implementation of the rectification measures, and continuously improves the quality control level through the performance evaluation system.

[0038] Suppose in the construction of a commercial complex, the system assigns specific rectification measures to each discovered problem according to the rectification suggestion report, designates the responsible personnel and completion time limit. The system monitors the rectification progress in real time, collects feedback information, and adjusts the task assignment according to the actual situation to ensure that each quality problem can be solved efficiently. At the same time, a perfect performance evaluation system is established to supervise the whole rectification process.

[0039] In summary, steps 101 to 104 cover the whole process from data collection, encrypted recording, dependency assessment to quality risk identification and implementation of rectification measures, aiming to provide a highly transparent, secure and reliable closed-loop building construction quality management solution to meet the requirements of modern construction projects for high efficiency, high quality and high safety.

[0040] To solve the problems of insufficient data security and dependency assessment in existing construction management, in some embodiments, in step 102, the measurement data set is encrypted by using the distributed ledger technology combined with the homomorphic encryption algorithm, and the operation details, timestamps and operator identity identifiers of all actual measurement activities carried out at each construction site operation point in the encrypted state are recorded, and the graph theory analysis technology is applied to evaluate the dependencies between the operation points at the construction site to generate a data log, including: Using the distributed ledger technology combined with the homomorphic encryption algorithm, encrypt the operation details, timestamps and operator identity identifiers of all actual measurement activities carried out at each construction site operation point to obtain the encrypted operation records; according to the encrypted operation records, adopt the Byzantine fault-tolerant consensus mechanism to verify and reach a consensus among multiple system nodes in the distributed ledger technology, and add the encrypted operation records to the blockchain to generate a preliminary data log; use the preliminary data log, apply the graph theory analysis technology to model and analyze the dependencies between the operation points at the construction site to obtain a dependency model; based on the dependency model, combined with the construction progress plan formulated in advance according to the specific requirements and design requirements of the project, optimize and adjust the on-site operation process, and encrypt and record the optimized on-site operation process again by using the distributed ledger technology and the homomorphic encryption algorithm to generate a data log.

[0041] Using distributed ledger technology combined with homomorphic encryption algorithms, encrypt the operation details, timestamps, and operator identity identifiers of all actual measurement activities at each operation point on the construction site to obtain encrypted operation records; according to the encrypted operation records, adopt the Byzantine fault-tolerant consensus mechanism to verify and reach a consensus among multiple system nodes in the distributed ledger technology, and add the encrypted operation records to the blockchain to generate preliminary data logs; use the preliminary data logs and apply graph theory analysis technology to model and analyze the dependency relationships between operation points on the construction site to obtain a dependency relationship model; based on the dependency relationship model, combined with the construction schedule pre-developed by the project management team according to the specific requirements and design requirements of the project, optimize and adjust the on-site operation process, and encrypt and record the optimized process again using distributed ledger technology and homomorphic encryption algorithms to generate data logs.

[0042] In this embodiment, first, the operation details include information such as the specific construction operation type and the tools used; the timestamp ensures the time accuracy of each record; the operator identity identifier is used to confirm the specific person who performs the operation. Second, through encryption processing, it is ensured that these sensitive information is not tampered with or leaked during transmission and storage. Third, the dependency relationship model reflects the logical sequence and mutual influence between operation points, helping to identify critical paths and potential bottlenecks. Finally, the optimized and adjusted process is encrypted and recorded again, ensuring data consistency and security, and at the same time providing a basis for continuous improvement.

[0043] In the embodiment of the present application, first, by encrypting the data of all actual measurement activities, its security and privacy protection are ensured; second, the Byzantine fault-tolerant consensus mechanism is used to ensure data consistency among multiple nodes, and the encrypted operation records are added to the blockchain to generate preliminary data logs; third, a dependency relationship model between operation points is established through graph theory analysis technology to optimize the construction process; finally, combined with the pre-developed construction schedule, the optimized process is encrypted and recorded again to form the final data logs, ensuring a high degree of transparency and efficient management of the entire construction process.

[0044] Among them, the specific process of "using the preliminary data logs and applying graph theory analysis technology to model and analyze the dependency relationships between operation points on the construction site to obtain a dependency relationship model" includes: First, parse the unique identifiers of each operation point at the construction site from the preliminary data log, and extract the operation time sequence (including start / end timestamps), resource interaction records (equipment numbers, material batches, personnel IDs), and spatial coordinate information of each operation point. Use each operation point as a node to construct an initial node set. Among them, each node is attached with an attribute table, including operation types (such as steel bar binding, formwork installation), standard operation cycles (extracted from the BIM model), associated bill of materials (material specifications and quantities), and spatial positioning codes. The relevant information in the attached attribute table is parsed from the data log.

[0045] Secondly, based on the timestamp sequence, conduct a statistical analysis of the operation intervals between adjacent operation points. The process of statistical analysis includes: calculating the time interval distribution of each pair of operation points, setting a dynamic threshold (such as 30% of the average operation cycle), and determining whether there is a mandatory sequence dependency based on whether the time interval distribution is greater than the dynamic threshold. For the operation point pairs with mandatory sequence dependencies (A→B), generate directed time sequence edges. The weight of the directed time sequence edge is the standard deviation of the time interval (reflecting the time sequence stability), and mark the mandatory sequence clause numbers in the construction specifications. Finally, output the directed graph skeleton with time sequence constraints (hereinafter referred to as: time sequence graph skeleton) as the baseline structure for subsequent analysis.

[0046] Then, on the basis of the time sequence graph skeleton, introduce resource interaction data and continue to optimize the time sequence graph skeleton to obtain a hybrid graph structure. Among them, resource interaction data refers to the data in which a certain interaction exists between this operation point and other operation points.

[0047] The specific process includes: counting the resource overlap times and durations of operation points with shared equipment (such as tower crane usage records) or cross personnel (records of the same work team across operation points), calculating the resource coupling coefficient (such as resource coupling coefficient = number of shared resources / total number of resources); for operation point pairs with a resource coupling coefficient exceeding the preset threshold (such as ≥0.6), add undirected resource edges. The weight of the undirected resource edge is the resource coupling coefficient, and record conflict events (such as the number of times of equipment waiting timeout); and superimpose the undirected resource edges on the time sequence graph skeleton to form a hybrid graph structure (that is, a hybrid graph structure refers to a graph structure that simultaneously includes directed time sequence edges and undirected resource edges).

[0048] Furthermore, a hybrid graph is used for topological feature analysis. The topological feature analysis process includes: applying the k-core decomposition algorithm to iteratively strip low-connectivity nodes, identifying high-density dependent subgraphs (core regions with k≥3), and labeling them as potential key job groups; screening key subgraphs in the potential key job groups (specifically set according to requirements), and running the weighted PageRank algorithm within the key subgraphs (using the weights of directed time-series edges and undirected resource edges as transition probability parameters) to calculate the node centrality scores, and screening the top 10% of the nodes as hub nodes (for example, the concrete pouring point has a significantly higher score due to its dependence on formwork acceptance and steel bar inspection); finally, based on the dynamic programming algorithm, calculate the longest path of the hub nodes under time-series constraints, mark it as the critical path chain, and associate the parallel job points affected by it.

[0049] For example, the specific process of calculating the critical path chain based on the dynamic programming algorithm under time-series constraints is as follows: First, based on the previously corrected acyclic hybrid graph, normalize the PageRank centrality scores of the hub nodes into priority weights, and combine the directional constraints of time-series edges (forcing the construction sequence) and the coupling strength of resource edges (shared resource stability) to construct a directed acyclic graph (DAG) with multiple weights. , where represents the longest weighted path value reaching node v. The weights incorporate the standard deviation of time-series edges (reflecting the stability of process connection) and the resource coupling coefficient (reflecting the collaborative efficiency). At the same time, a virtual node connection mechanism is introduced for parallel branch nodes to handle multi-predecessor dependencies. Then, starting from all starting points with an in-degree of 0, iteratively calculate the dp values of each node in topological sorting order and record the predecessor node chain. Finally, select the path with the largest dp value as the critical path chain. Finally, by traversing the nodes on the critical path chain in reverse, extract the directly associated parallel job points (non-critical path nodes that satisfy the spatial distance ≤5 meters and the resource coupling degree ≥0.4), establish an influence relationship matrix to label the dependence type (strong resource dependence / weak time-series dependence), and finally form a construction network topological structure including the main path and 23 associated parallel branches.

[0050] Even further, a deep verification of the hybrid graph is carried out. The deep verification process includes: executing the topological sorting algorithm to detect cyclic dependence chains (such as A→B→C→A), and combining the spatial topological relationship of the BIM model to locate the dead loops caused by design conflicts or process mismatches; applying the maximum flow-minimum cut theorem, using the production capacity of job points (quantity completed per unit time) as the capacity value, analyzing the flow bottlenecks on resource edges, and identifying the minimum production capacity improvement points corresponding to the cut sets (for example, adding a pump truck can increase the concrete supply flow by 50%).

[0051] Furthermore, when constructing the dependency relationship model based on the comprehensive topological feature analysis and the deep verification results, the following integration process is specifically executed: First, based on the key subgraphs identified by k-core decomposition (k≥3 regions), construct an attribute adjacency matrix in the blocked compressed sparse row (BCSR) format. Encode the time-series edge direction, the standard deviation of the time interval, and the corresponding specification clauses as non-symmetric elements of the matrix, record the resource edge coupling coefficient and the number of conflicts as symmetric elements, and divide independent data blocks for the key subgraphs to accelerate high-frequency access; Secondly, integrate the PageRank hub node list and the critical path chain data to establish a multi-layer adjacency list structure: embed the PageRank value, the k-core level, and the critical path identifier (derived from the topological feature analysis) at the node layer, associate the time-series / resource weight parameters and the bottleneck level obtained from the maximum flow-minimum cut analysis (such as the "high-priority capacity expansion edge" mark) at the edge layer, and mount the loop dependency chain correction record (from the Tarjan algorithm detection result) and the BIM space collision verification log at the event layer; Then, map the visualization rules: drive the node radius scaling based on the normalized PageRank value (in the range of 0-1) of the hub node (basic radius 20px + score × 50px), distinguish the dependency types by the red transparency of the time-series edge (1 - time interval stability coefficient) and the blue saturation of the resource edge (coupling coefficient × 100%), use the pulse mutation light effect for the critical path chain (frequency = 1 / total path duration) and superimpose parallel branches connected by virtual nodes (filter nodes with a spatial distance ≤ 5 meters and a resource coupling degree ≥ 0.4); Finally, inject the deep verification results: mark the loop dependency correction status (such as "passed the BIM space topology verification") in the edge attributes of the adjacency list, bind the corresponding production capacity improvement plan for the cut set (such as the coordinate points for additional pump trucks) as metadata to the resource edge, and achieve spatial grid alignment with the BIM model (error ≤ 0.1 meters) through the 3D rendering engine of Cytoscape.js to form a dynamic iterable model that simultaneously includes construction logic dependencies, resource bottleneck warnings, and spatial conflict hotspots, that is, the dependency relationship model.

[0052] Finally, connect the dependency relationship model to the construction Internet of Things system: when new measured data triggers a change in the dependency relationship (such as a resource coupling break due to equipment failure), automatically recalculate the k-core subgraph and the critical path chain, and push warnings to the associated operation points; verify the prediction accuracy of the model through historical data playback (such as determining it is effective when the critical path delay and the actual progress deviation ≤ 5%), and dynamically adjust the threshold parameters (such as the resource coupling coefficient threshold adapting from 0.6 to 0.55).

[0053] Through progressive analysis of timing constraints → resource coupling → topological features → bottleneck diagnosis, this process transforms the original log into a quantifiable, traceable, and predictable dependency model, providing a decision-making basis at the topological level for construction scheduling optimization.

[0054] The following is a specific example: Suppose in a large industrial park construction project. First, all on-site operations (such as concrete pouring and steel structure installation) are recorded in real time through intelligent devices and immediately uploaded to the blockchain platform. Before each upload, the data is homomorphically encrypted to protect sensitive information. Second, the system automatically verifies the authenticity of each operation record and adds it to the blockchain to generate a preliminary data log. Third, engineers use graph theory analysis techniques to construct a dependency model between operation points, identifying which tasks are on the critical path and which tasks can be executed in parallel, thus optimizing the construction process. Finally, the records are re-encrypted according to the optimized process to ensure data consistency and security, and at the same time, a basis for continuous improvement is established. Through the above steps, the full process automation and intelligence from data collection to process optimization and then to security management are achieved, significantly improving construction quality and efficiency.

[0055] To address the problem of insufficient data verification and consistency confirmation in existing construction management, in some embodiments, based on the encrypted operation records, a Byzantine fault-tolerant consensus mechanism is used to verify and reach a consensus among multiple system nodes in distributed ledger technology, and the encrypted operation records are added to the blockchain to generate a preliminary data log, including: Using a Byzantine fault-tolerant consensus mechanism, perform validity verification processing on the encrypted operation records corresponding to each measured activity to obtain verification results; based on the verification results, perform consistency confirmation processing among multiple system nodes in distributed ledger technology to generate a consensus decision; use the consensus decision to add the encrypted operation records to the blockchain to form a block structure and synchronize it to all system nodes in distributed ledger technology to obtain block-structured operation records; apply graph theory analysis techniques to evaluate the dependencies between operation points at the construction site, and at the same time integrate all block-structured operation records to generate a preliminary data log.

[0056] In this embodiment, first, the verification results include whether the encrypted records of each measurement event meet the preset security standards and logical rules; second, the consensus decision refers to ensuring that multiple nodes reach a consensus on the same transaction or record through a Byzantine fault-tolerant consensus mechanism; third, the block structure is the basic unit of the blockchain, containing a series of verified operation records to ensure data immutability; finally, the dependency model reflects the logical order and mutual influence between operation points, helping to identify the critical path and potential bottlenecks. These concepts work together to ensure the security and reliability of construction data.

[0057] In the embodiments of the present application, first, the system uses the Byzantine fault-tolerant consensus mechanism to verify the validity of the encrypted records of each measurement event to ensure its authenticity and integrity; second, based on the verification results, consistency confirmation is carried out among multiple system nodes to generate a consensus decision to ensure data consistency; third, using the consensus decision, the encrypted operation records are added to the blockchain in the form of blocks and synchronized to all participating nodes to form block-based operation records; finally, the system applies graph theory analysis technology to evaluate the dependency relationships between work points, and at the same time integrates all block-based operation records to generate preliminary data logs to ensure the high transparency and efficient management of the entire construction process.

[0058] The following is a specific example: Suppose in a large bridge construction project, first, the system uses the Byzantine fault-tolerant consensus mechanism to verify the encrypted records of each operation such as concrete pouring and steel bar binding to ensure the authenticity and integrity of each record; second, multiple system nodes (such as the construction party, supervision party, and design party) carry out consistency confirmation based on the verification results to generate a consensus decision to ensure that all participating parties reach an agreement on the same record; third, the system adds these verified operation records to the blockchain in the form of blocks and synchronizes them to all participating nodes to form block-based operation records to ensure that the data is tamper-proof and traceable throughout the process; finally, engineers use graph theory analysis technology to evaluate the dependency relationships between different work points, and at the same time integrate all block-based operation records to generate detailed preliminary data logs to ensure the optimization of the construction process and the timely discovery and solution of quality problems. Through the above steps, the full process automation and intelligence from data verification to consistency confirmation and then to dependency relationship evaluation are realized, significantly improving the construction quality and efficiency.

[0059] To solve the problems of insufficient optimization of the operation process and inadequate data security protection in existing construction management, in some embodiments, based on the dependency relationship model, combined with the construction schedule plan formulated in advance according to the specific requirements and design requirements of the project, the on-site operation process is optimized and adjusted, and the optimized on-site operation process is encrypted and recorded again using distributed ledger technology and homomorphic encryption algorithm to generate data logs, including: Using the said dependency model, model and analyze the dependencies between various operation points at the construction site to obtain the dependency analysis result; according to the said dependency analysis result, combined with specific requirements and the construction schedule plan, optimize and adjust the on-site operation process to generate an optimized on-site operation process plan; based on the said optimized on-site operation process plan, apply distributed ledger technology and homomorphic encryption algorithm to encrypt the details of each activity operation, timestamp and operator identity identifier in the on-site operation process plan to obtain an encrypted optimized operation process record; according to the said encrypted optimized operation process record, adopt the Byzantine fault-tolerant consensus mechanism to verify and reach a consensus among multiple system nodes in the distributed ledger technology, add the said encrypted optimized operation process record to the blockchain to form a block structure, and synchronize it to all system nodes to obtain a block-structured optimized operation process record; use the said block-structured optimized operation process record to integrate all block-structured information related to the optimized on-site operation process to generate a data log.

[0060] In this embodiment, first, the dependency model includes the logical sequence, time dependency and resource dependency between each operation point, and is used to identify the critical path and potential bottlenecks; second, the construction schedule plan is a timetable pre-developed by the project management team, which clarifies the key milestones and time nodes of each construction stage to ensure the project is completed on time; third, the optimized on-site operation process refers to the new operation process optimized by the dependency model and the schedule plan, aiming to improve efficiency and quality; finally, the data log is the operation record encrypted by the distributed ledger technology and the homomorphic encryption algorithm to ensure the security and immutability of the data.

[0061] In the embodiment of the present application, first, the system uses the dependency model to analyze the dependencies between various operation points at the construction site, and combines the construction schedule plan pre-developed according to the specific requirements and design requirements set by the project to optimize and adjust the on-site operation process; second, the optimized operation process is re-evaluated to ensure that all critical paths and potential bottlenecks have been effectively handled; third, the system uses the distributed ledger technology and the homomorphic encryption algorithm again to encrypt and record the optimized on-site operation process to ensure that each step of the new process is securely recorded; finally, the generated data log not only contains the details of the optimized operation process, but also ensures the security and immutability of all data.

[0062] The following is a specific example: Suppose in a high-rise residential building construction project. First, the engineer uses the dependency relationship model to analyze the dependency relationships among various operation points at the construction site, and combines the construction schedule plan pre-established according to the specific requirements and design requirements set by the project to optimize and adjust the on-site operation process. For example, adjust the priorities of certain processes or reallocate resources. Second, the project manager combines the optimized operation process with the existing schedule plan to ensure that all critical paths and potential bottlenecks are effectively addressed. Third, the system uses distributed ledger technology and homomorphic encryption algorithms to encrypt and record the optimized on-site operation process again to ensure that every operation step in the new process is securely recorded, forming an updated data log. Finally, the generated data log not only contains the details of the optimized operation process but also ensures the security and immutability of all data. Through the above steps, the full process automation and intelligence from dependency relationship modeling to operation process optimization and then to data security processing are achieved, significantly improving the construction quality and efficiency.

[0063] This application takes into account that in order to solve the problems of insufficient data security and integrity in existing construction management, especially the risk that sensitive information is easily tampered with or leaked. This application further provides an alternative solution. In the prior art, due to problems such as insufficient data encryption strength, lax permission control, and improper time window management, the operation records during the construction process cannot be effectively protected, thus affecting the construction quality and safety. Therefore, the inventive embodiments propose this alternative solution. By introducing distributed ledger technology and homomorphic encryption algorithms in combination with multi-dimensional data analysis and role-based access control models, it is ensured that the operation details, timestamps, and operator identity identifiers of all measurement events are processed in an encrypted state, and the immutability and confidentiality of the data are enhanced through a series of complex security mechanisms to solve the above technical problems.

[0064] Optionally, using the distributed ledger technology in combination with the homomorphic encryption algorithm to encrypt the operation details, timestamps, and operator identity identifiers of all measurement events to obtain encrypted operation records, including: Clean, standardize, and perform multi-dimensional data analysis on the measurement data set, and prepare a secure environment through a role-based access control model and a time lock mechanism; ; Among them, represents the encrypted operation record; is the homomorphic encryption algorithm used to ensure that certain types of operations can still be performed on the data in the encrypted state; is the operation details including the operation content of the specific measurement event; is the timestamp indicating the exact time point of each operation; The operator identity identifier confirms the legitimacy of the operator by comparing with a pre-registered identity information database; The public key is used to encrypt sensitive information to ensure that only the recipient with the corresponding private key can decrypt it; After the calculation is completed, the hash function is used to enhance the immutability, the weight is adjusted in combination with the permission level, the influence of the time window is considered, a random salt value is added to prevent attacks, the record length is calculated and the authenticity is verified, and finally the comprehensive encryption strength is evaluated ; ; Among them, represents the comprehensive encryption strength; The SHA-256 hash function is used to enhance the immutability of data; is the encrypted operation record obtained from the first formula; The role-based weight function reflects the influence of different permission levels on the encryption strength; is the operator's permission level; The time window function adjusts the encryption strength according to the valid time period; is the valid time window to ensure that the encryption is valid within a specific time period; The length function calculates the length of the encrypted record to increase the complexity; The random salt value increases the randomness and uniqueness of the hash result to prevent rainbow table attacks; and are non-linear adjustment parameters used to adjust the non-linear characteristics of the overall encryption strength; The private key is used to verify the identity during decryption; The verification function ensures the authenticity and integrity of the encrypted record; According to the results, the encryption parameters are optimized, the Byzantine fault-tolerant consensus mechanism is applied to verify and synchronize the encrypted record to the blockchain, and integrity verification is performed to generate the encrypted operation record.

[0065] This formula aims to, firstly, ensure that certain types of operations can still be performed on the data in the encrypted state; secondly, enhance the immutability of the data to prevent malicious attacks; thirdly, adjust the encryption strength according to the permission level, consider the influence of the time window, and add a random salt value to improve the randomness and uniqueness of the hash result; finally, calculate the record length and verify the authenticity, and evaluate the comprehensive encryption strength . These steps work together to ensure the security and reliability of each operation record during the construction process.

[0066] The following briefly introduces the design reasons for each item of this formula: ; Operation Details : The operation content of specific measurement events is used to describe the specific situation of each operation in detail; Timestamp : Ensure the accuracy of the time point of each operation; Operator Identification : Confirm the legitimacy of the operator by comparing with the pre-registered identity information database; Public Key : Used to encrypt sensitive information to ensure that only the recipient with the corresponding private key can decrypt it; The following briefly introduces the acquisition methods of each parameter of this formula: Operation Details and Timestamp from the real-time collected data set; Operator Identification Obtained through the identity authentication system; Public Key Obtained from the security certificate authority.

[0067] The following briefly introduces the design reasons for each item of this formula:

[0068] ; Hash Function : The main purpose of introducing the hash function is to enhance the immutability of data. By applying the SHA-256 hash algorithm to the encrypted operation record a unique hash value is generated to ensure that any modification to the original data can be immediately detected, thereby improving the integrity and anti-tampering ability of the data.

[0069] Role-based Weight Function and Time Window Function : These two functions work together to adjust the encryption strength according to the operator's permission level and the valid time period of the operation. Users with different permission levels have different security requirements for the system, and the time window function ensures that the encryption is valid within a specific time period to prevent the misuse or abuse of expired data. This design enhances the flexibility and adaptability of the system and can better meet different application scenarios and security requirements.

[0070] Length Function and Random Salt Value : By calculating the length of the encrypted record and adding a random salt value, the complexity and uniqueness of the encryption result are increased. This not only improves the randomness of the hash result but also effectively prevents common cracking methods such as rainbow table attacks, further enhancing the security of the data.

[0071] Exponential Function : This part is used to combine the private key and Verification Function , ensuring that only the recipient with the correct private key can decrypt and verify the authenticity and integrity of the encrypted record. The introduction of the non-linear adjustment parameter makes the adjustment of the overall encryption strength more flexible and can dynamically optimize the encryption effect according to the actual situation.

[0072] The following briefly introduces the acquisition methods of each parameter in this formula:

[0073] Hash function Use the standard library function; the encrypted operation record Obtained from the first formula; role-based weight function Defined according to the user role; permission level Obtained from the permission management system; time window function Dynamically calculated according to the preset rules; valid time window Set by the system administrator; length function Directly calculate the string length; random salt value Randomly generated; non-linear adjustment parameter and Set by experts; private key Obtained from the security certificate center; verification function Use the standard library function.

[0074] Suppose in a large bridge construction project. First, the system cleans, standardizes, and performs multi-dimensional data analysis on the measurement data set, and prepares a secure environment through the role-based access control model and the time lock mechanism; then, the system uses the homomorphic encryption algorithm for the operation details , timestamp and the operator's identity identifier to perform encryption processing, obtaining the encrypted operation record , where , for example ; then, after calculating , the system enhances the non-forgeability through the hash function , adjusts the weight in combination with the permission level, considers the influence of the time window, adds a random salt value to prevent attacks, calculates the record length and verifies , assuming ; finally, optimize the encryption parameters according to the result, apply the Byzantine fault-tolerant consensus mechanism to verify and synchronize the encrypted record to the blockchain, and perform integrity verification to generate the encrypted operation record.

[0075] Through the above steps, the full - process automation and intelligence from data cleaning to encryption processing and then to comprehensive encryption strength assessment are achieved, significantly improving the security and reliability of each operation record during the construction process. Assuming the set threshold is 0.95, since is greater than the set threshold, it indicates that the encryption strength is high enough to effectively prevent data tampering or leakage, ensuring the construction quality and security.

[0076] To solve the problem of inaccurate mapping and deviation assessment of measured data in existing construction management, in some embodiments, in step 103, the use of augmented reality technology to overlay the BIM model is used to accurately map the measured data in the data log, and the support vector machine algorithm is introduced to automatically classify and risk - assess the deviation data between the measured data and the preset standard data to identify the quality risk area and generate a rectification suggestion report. The rectification suggestion report contains specific rectification measures for the quality risk area, including: Using augmented reality technology to overlay the BIM model to accurately map the measured data of each operation point at the construction site in the data log, obtaining a three - dimensional visualization interface; based on the three - dimensional visualization interface, combining spatial analysis technology to compare the measured data with the preset standard data to generate deviation data; introducing the support vector machine algorithm to automatically classify and risk - assess the deviation data, identify the quality risk area, and generate a quality risk assessment report; according to the quality risk assessment report, comprehensively considering construction progress and resource allocation factors, formulating targeted rectification measures to generate a rectification suggestion report.

[0077] In this embodiment, first, the three - dimensional visualization interface includes combining the BIM model with the actual construction scene through augmented reality (AR) technology, enabling engineers to intuitively view the measured data; second, the deviation comparison result refers to the difference data obtained by comparing the specific values measured on - site with the preset standard data set in advance, used to identify deviations; third, the quality risk assessment report is a document generated after classifying and risk - assessing the deviation data, containing detailed information on potential quality risk areas; finally, the rectification suggestion report is formulated based on the quality risk assessment report, aiming to guide the implementation of specific rectification measures to ensure that problems are solved in a timely manner.

[0078] In the embodiments of the present application, first, the system uses augmented reality technology to superimpose the BIM model onto the actual construction environment to form a three-dimensional visualization interface, enabling the measured data to be intuitively displayed; second, in combination with spatial analysis technology, the system performs a detailed comparison process on the measured data and the preset standard data at each operation point at the construction site to generate a deviation comparison result, ensuring that every detail is accurately captured; third, the support vector machine (SVM) algorithm is used to automatically classify the deviation data and perform a risk assessment to identify the quality risk areas and generate a detailed quality risk assessment report; finally, based on the content of the assessment report, the system comprehensively considers the construction progress and resource allocation situation to formulate targeted rectification measures and finally generate a rectification suggestion report to ensure that the rectification measures are scientific, reasonable and easy to implement.

[0079] The following is a specific example: Suppose in a high-rise residential building construction project, first, the engineer wears AR glasses to view the construction site and visually compare the actual measurement results with the BIM model on the glasses screen to form a three-dimensional visualization interface; second, the system automatically detects and records the actual measurement values of all key parts (such as wall thickness, steel bar spacing, etc.) and compares them with the preset standard data to generate a detailed deviation comparison result; third, the system uses the support vector machine algorithm to classify and risk-assess these deviation data, identifies that the thickness of some walls does not meet the design requirements, immediately generates a report containing specific rectification measures, and prompts relevant personnel to correct the problem in a timely manner to avoid subsequent rework; finally, the project manager formulates specific rectification measures based on the content in the quality risk assessment report, comprehensively considering the current construction progress and available resources, to ensure that each quality problem can be efficiently solved. Through the above steps, the full process automation and intelligence from data mapping to deviation assessment and then to the implementation of rectification measures are realized, significantly improving the construction quality and efficiency.

[0080] To solve the problem of inaccurate classification and risk assessment of deviation data in existing construction management, in some embodiments, the introduction of the support vector machine algorithm to automatically classify and risk-assess the deviation data, identify the quality risk areas, and generate a quality risk assessment report includes: Introduce the support vector machine algorithm to automatically classify the deviation data and generate a classification result; based on the classification result, perform a risk assessment process on the classified deviation data based on the support vector machine algorithm to identify the quality risk areas and generate a risk assessment conclusion; based on the risk assessment conclusion, comprehensively organize all the identified quality risk information to generate a quality risk assessment report.

[0081] In this embodiment, first, the deviation data includes the differences between the actual measurement values of each working point at the construction site and the preset standards, which is used to identify potential problems during the construction process; second, the classification result is obtained by automatically classifying the deviation data through the support vector machine (SVM) algorithm, distinguishing different types of deviations; third, the risk assessment conclusion refers to identifying which areas have significant quality risks through further analysis of the classified deviation data; finally, the quality risk assessment report is a document generated by comprehensively organizing all the identified quality risk information, providing detailed suggestions for rectification measures to ensure that problems can be solved in a timely and effective manner.

[0082] In the embodiment of the present application, first, the system uses the deviation data and introduces the support vector machine algorithm to perform automatic classification processing on it to generate a classification result; second, according to the classification result, the system applies the support vector machine algorithm again to perform risk assessment processing on the classified deviation data, identifies specific quality risk areas, and generates a risk assessment conclusion; third, based on the risk assessment conclusion, the system comprehensively organizes all the identified quality risk information; finally, the system generates a detailed quality risk assessment report, provides specific suggestions for rectification measures, and ensures that each quality problem can be solved efficiently.

[0083] The following is a specific example: Suppose in a large bridge construction project, first, engineers collect the deviation data of each working point at the construction site, including the differences between the actual measurement values such as wall thickness and steel bar spacing and the design standards; second, the system uses this deviation data and introduces the support vector machine algorithm to perform automatic classification processing on it to generate a classification result, for example, some wall thicknesses do not meet the standards, while there are problems with the steel bar spacing in some areas; third, according to the classification result, the system applies the support vector machine algorithm again to perform risk assessment processing on the classified deviation data, identifies specific quality risk areas, and generates a risk assessment conclusion, such as some wall thickness deviations may affect the structural safety; finally, based on the risk assessment conclusion, the system comprehensively organizes all the identified quality risk information, generates a detailed quality risk assessment report, and provides specific suggestions for rectification measures, such as increasing the wall thickness or adjusting the steel bar spacing. Through the above steps, the full process automation and intelligence from deviation data classification to risk assessment and then to rectification measure suggestions are realized, significantly improving the construction quality and efficiency.

[0084] This application takes into account that in order to solve the problems of inaccurate classification of deviation data and risk assessment in existing construction management, especially the difficulty in effectively identifying key quality risk areas and prioritizing them, this application further provides an alternative solution. In the prior art, due to problems such as simple deviation data processing methods, lack of spatial distribution analysis, and insufficiently intelligent risk assessment models, potential quality risks have not been discovered and processed in a timely manner. Therefore, the inventive embodiments propose this alternative solution, which comprehensively evaluates and automatically classifies deviation data by introducing the support vector machine algorithm combined with hash function mapping, quality voting mechanism, and multi-dimensional data analysis technology, and generates a detailed quality risk assessment report to solve the above technical problems.

[0085] Optionally, the introduction of the support vector machine algorithm for automatically classifying and processing risk assessment of deviation data, identifying quality risk areas, and generating a quality risk assessment report includes: Comprehensively evaluate and analyze the spatial distribution of deviation data, identify key areas that have a significant impact on the overall project quality and safety and prioritize them, introduce a quality voting mechanism to assign weights to each deviation point, and prepare the input data required for the support vector machine algorithm; ;

[0086] Among them, represents the risk score of each deviation point; is used by the support vector machine algorithm for automatic classification and evaluation; is the difference data extracted from the deviation comparison result; is the hash function mapping, is the hash function (such as SHA-256), is the hash function parameter for adjusting the spatial distribution of the difference data; is the weight function based on quality voting, represents the quality influencing factors of each deviation point; is a non-linear adjustment parameter for adjusting the non-linear characteristics of the score; is the region function, represents the location information of the deviation point, used to adjust the risk score according to the location; After calculating , integrate the risk scores of all deviation points, combine the regional influence coefficient and timestamp information, adjust the score through the time deviation function, and apply matrix transformation technology to integrate multi-dimensional data into a one-dimensional format. Highlight the key risk areas identified as having a relatively high risk score after being evaluated by the support vector machine algorithm according to the priority adjustment factor, and generate a quality risk assessment report; among them, the quality risk assessment report is calculated by the following formula: ; Among them, represents a quality risk assessment report; and are non-linear functions used to adjust the report generation method; is the risk score of the is the th deviation point; is the influence coefficient of the region where the th deviation point is located, considering the importance of different regions; is the total number of deviation points; is a matrix transformation function used to integrate multi-dimensional data into a one-dimensional report format; is a priority adjustment factor to ensure that key risk areas are highlighted in the report.

[0087] This formula aims to achieve intelligent classification and risk assessment of deviation data by comprehensively evaluating the deviation comparison results and analyzing the spatial distribution, and introducing advanced machine learning and support vector machine algorithms. Specifically, first, the system prepares the input data using a hash function mapping and a quality voting mechanism to ensure that each deviation point can obtain a reasonable weight according to its spatial distribution and quality influencing factors; second, through the support vector machine algorithm classifies the deviation data, and adjusts the risk score in combination with the regional location to ensure the accuracy and rationality of the score; third, the system integrates the risk scores of all deviation points, considers the regional influence coefficient and timestamp information, and applies matrix transformation technology to integrate multi-dimensional data into a one-dimensional format to highlight key risk areas; finally, generates the final quality risk assessment report, and ensures the rationality and accuracy of the conclusion through visualization tools and expert reviews. These steps work together to ensure the effective processing and risk assessment of each piece of deviation data during the construction process, improving construction quality and safety.

[0088] The following briefly introduces the design reasons for each item of this formula: ; Differential data : The differential data extracted from the deviation comparison results is used as the input for the support vector machine algorithm; Hash function mapping : Ensure that the spatial distribution characteristics of the differential data are fully considered; Weight function based on quality voting : Assign weights according to the quality influencing factors of each deviation point; : This part is used to adjust the risk score according to the position information of the deviation point to ensure that the score can reflect the impact of different positions on the overall construction quality. By introducing a non-linear adjustment parameter and the regional function , the system can dynamically adjust its risk score according to the specific location of the deviation points, so that the deviations in the critical area receive higher attention, thereby improving the accuracy and pertinence of risk assessment.

[0089] The following briefly introduces the acquisition methods of the parameters in this formula: Difference data From the deviation comparison result; Hash function Use standard library functions such as SHA-256; Hash function parameters Set by experts; Weight function based on quality voting Dynamically calculated according to preset rules; Quality impact factors Obtained from the quality management system; Nonlinear adjustment parameters Set by experts; Region function Dynamically calculated according to preset rules; Location information From the records of the measuring device.

[0090] The following briefly introduces the design reasons for each item in this formula: ; : This part is used to integrate the risk scores of all deviation points and conduct a comprehensive evaluation by combining the regional influence coefficient and timestamp information. By weighting and summing the risk scores of each deviation point, the regional influence coefficient and the time deviation function and then applying the nonlinear function for adjustment, it ensures that the final score can comprehensively consider the influence of spatial distribution and time factors, improving the scientificity and rationality of the evaluation result. : This part is used to integrate multi-dimensional data into a one-dimensional report format and highlight critical risk areas according to the priority adjustment factor. By using the matrix transformation function to simplify the multi-dimensional data into an easy-to-understand one-dimensional format, and at the same time applying the priority adjustment factor to ensure that important risk areas are highlighted in the report. This design not only improves the readability and practicality of the report, but also ensures that key issues can be discovered and processed in a timely manner, enhancing the effect of construction management and quality control.

[0091] The following briefly introduces the acquisition methods of the parameters in this formula: Risk score Calculated; Regional influence coefficient Dynamically calculated according to preset rules; Time deviation function Dynamically calculated according to preset rules; Measurement event timestamp From the records of the measuring device; Total number of deviation points Statistically analyzed by the system; non-linear function and Using standard library functions; matrix transformation function Using standard library functions; priority adjustment factor Set by experts.

[0092] Suppose in a large commercial complex construction project. First, the system comprehensively evaluates the deviation comparison results and conducts spatial distribution analysis, identifies significant deviations in the thickness of certain walls and the positions of structural supports, and performs priority ranking; then, a quality voting mechanism is introduced to assign weights to each deviation point, preparing the input data required for the support vector machine algorithm, such as , suppose ; then, the system integrates the risk scores of all deviation points, combines the regional impact coefficient and timestamp information, adjusts the scores through the time deviation function, and applies matrix transformation technology to integrate multi-dimensional data into a one-dimensional format, highlighting key risk areas according to the priority adjustment factor, such as , suppose ; finally, review the content of the report to ensure accuracy, use visualization tools to convert the data into charts, introduce expert reviews to ensure the rationality of the conclusions, and distribute the report to the responsible parties, establishing a tracking mechanism to monitor the implementation progress of the rectification measures.

[0093] Through the above steps, the full process automation and intelligence from the comprehensive evaluation of deviation data to automatic classification and risk assessment and then to report generation are realized, significantly improving the processing accuracy of each deviation data and the accuracy of risk assessment during the construction process. Suppose the set threshold is 0.85, because and are both greater than the set threshold, so it shows that the system can effectively identify and highlight key quality risk areas, ensuring the construction quality and safety.

[0094] To solve the problems of unscientific distribution of rectification measures and lagging performance evaluation in existing construction management, in some embodiments, in step 104, the specific rectification measures formulated for the identified quality risk areas are automatically matched and assigned according to the preset rules and weight scoring model. By collecting feedback on the rectification effect, adjusting the rules and methods for guiding the distribution of specific rectification measures, a closed-loop quality management process is formed, including: Intelligently match and automatically assign the specific rectification measures formulated according to the rectification suggestion report to generate a task assignment list; based on the task assignment list, utilize smart contract technology and record the execution status of each task through a blockchain system built in the entire construction project management to obtain a task execution progress record; by collecting the rectification effect feedback in the task execution progress record, combine real-time data analysis technology and machine learning algorithms to establish a dynamic performance evaluation system and generate a preliminary performance evaluation result reflecting the actual rectification effect; utilize the preliminary performance evaluation result, introduce historical data mining and expert system optimization mechanisms, adjust the task assignment strategy, and update the weight scoring model to form a closed-loop quality management process.

[0095] In this embodiment, first, the multi-dimensional evaluation system includes data in multiple dimensions such as time, cost, and quality, which is used to comprehensively evaluate the effectiveness of rectification measures; second, the dynamic weight scoring model is a task priority and resource allocation rule that is continuously adjusted according to the actual situation to ensure the scientificity and rationality of rectification measures; third, the task assignment list refers to a task list automatically generated according to the rectification suggestion report, which clarifies the responsible person, completion time, and required resources for each task; finally, the dynamic performance evaluation system continuously tracks the rectification effect through real-time data analysis and machine learning algorithms, and adjusts the strategy according to the feedback to ensure the efficient operation of the quality management process.

[0096] In the embodiment of the present application, first, the system combines the multi-dimensional evaluation system and the dynamic weight scoring model to intelligently match and automatically assign the specific rectification measures formulated according to the rectification suggestion report to generate a task assignment list; second, based on the task assignment list, the system utilizes smart contract technology and the blockchain system to record the execution status of each task to ensure transparent distribution of tasks and traceability of execution status; third, by continuously collecting the rectification effect feedback in the task execution progress record, combine real-time data analysis technology and machine learning algorithms to establish a dynamic performance evaluation system and generate a preliminary performance evaluation result reflecting the actual rectification effect; finally, utilize the preliminary performance evaluation result, introduce historical data mining and expert system optimization mechanisms, and continuously adjust the task assignment strategy and update the weight scoring model to ensure continuous improvement and optimization of rectification measures, and ultimately form a closed-loop quality management process.

[0097] The following is a specific example: Suppose in a large shopping mall construction project. First, based on the rectification suggestion report, the project manager combines multi-dimensional evaluation systems such as time, cost, and quality, and a dynamic weight scoring model to perform intelligent matching and automated assignment processing on various rectification measures, generating a detailed task assignment list that clarifies the responsible person, completion time, and required resources for each task. Second, based on the task assignment list, the system uses smart contract technology to ensure the transparent distribution of each task and records the execution status of each task through the blockchain system to ensure that all operations are tamper-proof and traceable throughout the process. Third, by continuously collecting feedback on the rectification effect in the task execution progress record, the system combines real-time data analysis technology and machine learning algorithms to establish a dynamic performance evaluation system, generating a preliminary performance evaluation result reflecting the actual rectification effect and promptly discovering and solving existing problems. Finally, using these preliminary performance evaluation results, the system introduces historical data mining and expert system optimization mechanisms to continuously adjust the task assignment strategy and update the weight scoring model to ensure the continuous improvement and optimization of the rectification measures. Through the above steps, the full process automation and intelligence from task intelligent assignment to execution status record, then to performance evaluation and strategy optimization are achieved, significantly improving the construction quality and efficiency.

[0098] Figure 2 The present application embodiment provides a structural schematic diagram of a building intelligent actual measurement and quality management system, as Figure 2 shown. The device includes: A capture module 21 for capturing in real time the environmental parameters, material flow path during the construction of the building, and the spatial geometric information of key parts of the building to obtain a measurement data set; A recording module 22 for encrypting the measurement data set using distributed ledger technology combined with a homomorphic encryption algorithm, recording the operation details, time stamps, and operator identity identifiers of all actual measurement activities carried out at each construction site operation point in the encrypted state, and applying graph theory analysis technology to evaluate the dependency relationship between each construction site operation point to generate a data log; A mapping module 23 for using augmented reality technology to overlay a BIM model, performing precise mapping processing on the actual measurement data in the data log, introducing a support vector machine algorithm to automatically classify and perform risk assessment processing on the deviation data between the actual measurement data and the preset standard data to identify quality risk areas, and generating a rectification suggestion report, where the rectification suggestion report includes specific rectification measures for the quality risk areas; An adjustment module 24 for automatically matching and assigning the specific rectification measures formulated for the quality risk areas according to preset rules and a weight scoring model, and adjusting the rules and methods for guiding the distribution of specific rectification measures by collecting feedback on the rectification effect to form a closed-loop quality management process.

[0099] Figure 2 The described building intelligent actual measurement and quantity management system can execute Figure 1 A building intelligent actual measurement and quantity management method described in the illustrated embodiment, the implementation principle and technical effects of which will not be elaborated further. For each module and unit in the building intelligent actual measurement and quantity management system in the above embodiment, the specific manner of performing operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0100] In a possible design, Figure 2 The building intelligent actual measurement and quantity management system of the illustrated embodiment can be implemented as a computing device, such as Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32; The storage component 31 stores one or more computer instructions, where the one or more computer instructions are called and executed by the processing component 32.

[0101] The processing component 32 is used for: Real-time capture the environmental parameters, material flow paths during the construction process of the building, and the spatial geometric information of the key parts of the building to obtain a measurement data set; use distributed ledger technology combined with homomorphic encryption algorithm to encrypt the measurement data set, record the operation details, timestamps and operator identity identifiers of all actual measurement activities carried out at each operation point at the construction site under the encrypted state, and apply graph theory analysis technology to evaluate the dependency relationship between each operation point at the construction site to generate a data log; use augmented reality technology to overlay the BIM model, perform precise mapping processing on the actual measurement data in the data log, introduce a support vector machine algorithm to automatically classify and risk assess the deviation data between the actual measurement data and the preset standard data to identify quality risk areas and generate a rectification suggestion report, where the rectification suggestion report contains specific rectification measures for the quality risk areas; automatically match and assign the specific rectification measures formulated for the quality risk areas according to preset rules and a weight scoring model, and adjust the rules and methods for guiding the distribution of specific rectification measures by collecting rectification effect feedback to form a closed-loop quality management process.

[0102] Among them, the processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components for executing the above method.

[0103] The storage component 31 is configured to store various types of data to support the operation of the terminal. The storage component 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 read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0104] Of course, the computing device may necessarily further include other components, such as an input / output interface, a display component, a communication component, etc.

[0105] The input / output interface provides an interface between the processing component and the peripheral interface module, and the above-mentioned peripheral interface module may be an output device, an input device, etc.

[0106] The communication component is configured to facilitate communication between the computing device and other devices in a wired or wireless manner, etc.

[0107] Among them, the computing device may be a physical device or an elastic computing host provided by a cloud computing platform, etc. At this time, the computing device may refer to a cloud server, and the above-mentioned processing component, storage component, etc. may be basic server resources leased or purchased from a cloud computing platform.

[0108] The embodiment of the present application also provides a computer storage medium storing a computer program, and when the computer program is executed by a computer, it can implement the above Figure 1 shown embodiment of a method for actual measurement and quality management of building intelligentization.

[0109] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the above-described systems, devices, and units can refer to the corresponding processes in the foregoing method embodiments, and will not be described herein again.

[0110] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative labor.

[0111] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0112] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, and are not intended to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for actual measurement and management of building intelligence, characterized in that, Including: Real-time capturing the environmental parameters, material flow paths during the construction process of the building, and the spatial geometric information of the key parts of the building to obtain a measurement data set; Using distributed ledger technology combined with homomorphic encryption algorithm to encrypt the measurement data set, recording the operation details, timestamps, and operator identity identifiers of all actual measurement activities carried out at each construction site operation point in the encrypted state, and applying graph theory analysis technology to evaluate the dependency relationships between operation points at the construction site to generate a data log; Using augmented reality technology to overlay the BIM model, performing precise mapping processing on the actual measurement data in the data log, introducing the support vector machine algorithm to automatically classify and perform risk assessment processing on the deviation data between the actual measurement data and the preset standard data to identify quality risk areas, generating a rectification suggestion report, and the rectification suggestion report includes specific rectification measures for the quality risk areas; Automatically matching and assigning the specific rectification measures formulated for the quality risk areas according to the preset rules and weight scoring model, and adjusting the rules and methods for guiding the distribution of specific rectification measures by collecting rectification effect feedback to form a closed-loop quality management process.

2. The method according to claim 1, wherein The using of distributed ledger technology combined with homomorphic encryption algorithm to encrypt the measurement data set, recording the operation details, timestamps, and operator identity identifiers of all actual measurement activities carried out at each construction site operation point in the encrypted state, and applying graph theory analysis technology to evaluate the dependency relationships between operation points at the construction site to generate a data log includes: Using distributed ledger technology combined with homomorphic encryption algorithm to encrypt the operation details, timestamps, and operator identity identifiers of all actual measurement activities carried out at each construction site operation point to obtain encrypted operation records; According to the encrypted operation records, adopting the Byzantine fault-tolerant consensus mechanism to verify and reach a consensus among multiple system nodes in the distributed ledger technology, and adding the encrypted operation records to the blockchain to generate a preliminary data log; Using the preliminary data log and applying graph theory analysis technology to model and analyze the dependency relationships between operation points at the construction site to obtain a dependency relationship model; Based on the dependency relationship model, combined with the construction progress plan formulated in advance according to the specific requirements and design requirements set by the project, optimizing and adjusting the on-site operation process, and encrypting and recording the optimized on-site operation process again using distributed ledger technology and homomorphic encryption algorithm to generate a data log.

3. The method according to claim 2, wherein The according to the encrypted operation records, adopting the Byzantine fault-tolerant consensus mechanism to verify and reach a consensus among multiple system nodes in the distributed ledger technology, and adding the encrypted operation records to the blockchain to generate a preliminary data log includes: Adopting the Byzantine fault-tolerant consensus mechanism to perform validity verification processing on the encrypted operation records corresponding to each actual measurement activity to obtain verification results; Based on the verification results, performing consistency confirmation processing among multiple system nodes in the distributed ledger technology to generate a consensus decision; Using the consensus decision, add the encrypted operation records to the blockchain to form a block structure, and synchronize them to all system nodes in the distributed ledger technology to obtain block-based operation records; Apply graph theory analysis technology to evaluate the dependency relationships between operation points at the construction site, and at the same time integrate all block-based operation records to generate a preliminary data log.

4. The method according to claim 2, wherein Based on the dependency relationship model, combined with the construction schedule plan formulated in advance according to the specific requirements and design requirements set for the project, optimize and adjust the on-site operation process, and encrypt and record the optimized on-site operation process again using the distributed ledger technology and the homomorphic encryption algorithm to generate a data log, including: Using the dependency relationship model, model and analyze the dependency relationships between operation points at the construction site to obtain the dependency relationship analysis results; According to the dependency relationship analysis results, combined with specific requirements and the construction schedule plan, optimize and adjust the on-site operation process to generate an optimized on-site operation process plan; Based on the optimized on-site operation process plan, apply the distributed ledger technology and the homomorphic encryption algorithm to encrypt the details of each activity operation, time stamps, and operator identity identifiers in the on-site operation process plan to obtain encrypted optimized operation process records; According to the encrypted optimized operation process records, use the Byzantine fault tolerance consensus mechanism to verify and reach an agreement among multiple system nodes in the distributed ledger technology, add the encrypted optimized operation process records to the blockchain to form a block structure, and synchronize them to all system nodes to obtain block-based optimized operation process records; Using the block-based optimized operation process records, integrate all block-based information related to the optimized on-site operation process to generate a data log.

5. The method according to claim 1, wherein Overlay the BIM model using augmented reality technology, perform precise mapping processing on the measured data in the data log, introduce the support vector machine algorithm to automatically classify and risk assess the deviation data between the measured data and the preset standard data to identify the quality risk areas, and generate a rectification suggestion report. The rectification suggestion report contains specific rectification measures for the quality risk areas, including: Overlay the BIM model using augmented reality technology, perform precise mapping processing on the measured data of each operation point at the construction site in the data log to obtain a three-dimensional visualization interface; Based on the three-dimensional visualization interface, combined with spatial analysis technology, compare the measured data with the preset standard data to generate deviation data; Introduce the support vector machine algorithm to automatically classify and risk assess the deviation data, identify the quality risk areas, and generate a quality risk assessment report; According to the quality risk assessment report, comprehensively consider the construction schedule and resource allocation factors, formulate targeted rectification measures, and generate a rectification suggestion report.

6. The method according to claim 5, wherein The introduction of the support vector machine algorithm to automatically classify and risk assess the deviation data, identify the quality risk areas, and generate a quality risk assessment report, including: Introduce the support vector machine algorithm to automatically classify the deviation data to generate a classification result; Based on the classification results, perform risk assessment processing on the classified deviation data using the support vector machine algorithm, identify the quality risk areas, and generate a risk assessment conclusion; Based on the risk assessment conclusion, comprehensively organize all identified quality risk information and generate a quality risk assessment report.

7. The method according to claim 1, wherein Automatically match and assign the specific rectification measures formulated for the identified quality risk areas according to the preset rules and weight scoring model. By collecting feedback on the rectification effect, adjust the rules and methods for guiding the distribution of specific rectification measures to form a closed-loop quality management process, including: Perform intelligent matching and automated assignment processing on the specific rectification measures formulated according to the rectification suggestion report to generate a task assignment list; Based on the task assignment list, utilize smart contract technology and record the execution status of each task through a blockchain system built in the entire building project management to obtain a task execution progress record; By collecting the feedback on the rectification effect in the task execution progress record, combine real-time data analysis technology and machine learning algorithms to establish a dynamic performance evaluation system and generate a preliminary performance evaluation result reflecting the actual rectification effect; Utilize the preliminary performance evaluation result, introduce historical data mining and expert system optimization mechanisms, adjust the task assignment strategy, and update the weight scoring model to form a closed-loop quality management process.

8. An actual measurement management system for building intelligentization, characterized in that, Including: A capture module for real-time capturing of environmental parameters, material flow paths during the construction process of the building, and spatial geometric information of key parts of the building to obtain a measurement data set; A recording module for encrypting the measurement data set using distributed ledger technology combined with homomorphic encryption algorithms, recording the operation details, timestamps, and operator identity identifiers of all actual measurement activities carried out at each construction site operation point in the encrypted state, and applying graph theory analysis technology to evaluate the dependency relationships between operation points at the construction site to generate a data log; A mapping module for using augmented reality technology to overlay the BIM model, perform precise mapping processing on the actual measurement data in the data log, introduce the support vector machine algorithm to automatically classify and perform risk assessment processing on the deviation data between the actual measurement data and the preset standard data to identify the quality risk areas, and generate a rectification suggestion report, which contains specific rectification measures for the quality risk areas; An adjustment module for automatically matching and assigning the specific rectification measures formulated for the quality risk areas according to the preset rules and weight scoring model. By collecting feedback on the rectification effect, adjust the rules and methods for guiding the distribution of specific rectification measures to form a closed-loop quality management process.

9. A computing device, characterized in that, Including a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a building intelligent actual measurement and quality management method as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that, Stores a computer program, and when the computer program is executed by the computer, it implements a building intelligent actual measurement and quality management method as described in any one of claims 1 to 7.

Images