A construction project quality detection method and system based on big data

Abstract

The present invention discloses a construction project quality detection method and system based on big data, which specifically relates to the field of quality detection technology; by acquiring historical engineering project data, extracting construction node records, quality assessment data and environmental impact data, segmenting the construction nodes based on engineering standards, and identifying quality calibration nodes, potential problem nodes and construction abnormality nodes. A node association matrix model is constructed, the quality conduction factors between nodes are analyzed, a risk assessment matrix is ​​generated, and the weights of multidimensional influencing factors are calculated, and an environmental quality interactive correlation factor set is output. In combination with the risk assessment matrix and the environmental quality interactive correlation factor set, a quality risk prediction model is constructed to generate a quality abnormality warning data set. By combining real-time monitoring data with a quality abnormality warning data set, a quality detection and evaluation result is generated, and construction quality improvement suggestions are output, thereby improving the accuracy and efficiency of construction quality management.

Description

Technical Field

[0001] The present invention relates to the field of quality inspection technology, and more specifically, to a construction project quality inspection method and system based on big data. Background Art

[0002] Traditional construction project quality inspection methods rely on manual inspections and regular checks, which have problems such as slow response, narrow inspection coverage, and delayed data processing, and are unable to detect and deal with potential quality risks in real time. Traditional methods are difficult to cope with various changes and emergencies during the construction process, which can easily lead to delayed discovery of quality problems and may even cause major safety accidents. Existing quality inspection methods cannot effectively integrate and analyze multi-dimensional data such as construction node records, environmental impacts, and quality assessments, and lack the ability to comprehensively predict and warn of potential risks in the construction process.

[0003] In order to solve the above problems, a technical solution is now provided. Summary of the invention

[0004] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a construction project quality detection method and system based on big data to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A construction project quality detection method based on big data includes the following steps:

[0007] Obtain historical engineering project data, and extract construction node records, quality assessment data, and environmental impact data based on the historical engineering project data;

[0008] The construction node records are processed in sections according to the engineering standards to obtain the quality calibration node set, potential problem node set and construction abnormal node set;

[0009] Based on the quality calibration node set and the potential problem node set, a node association matrix model is constructed to analyze the quality conduction factors between nodes and generate a risk assessment matrix;

[0010] Based on the construction abnormality node set, according to the environmental impact data and quality assessment data, the weights of multi-dimensional influencing factors are determined, and the environmental quality interactive correlation factor set is output;

[0011] Combining the risk assessment matrix and the set of environmental quality interactive correlation factors, a quality risk prediction model is constructed to predict the distribution of potential quality problems and generate a quality anomaly warning data set;

[0012] By collecting real-time monitoring data of the current construction nodes and analyzing it in combination with the quality abnormality warning data set, quality inspection and evaluation results are generated, and construction quality improvement suggestions are output.

[0013] In a preferred embodiment, historical engineering project data is obtained, and construction node records, quality assessment data and environmental impact data are extracted based on the historical engineering project data, specifically:

[0014] Extract construction node records from historical engineering project data, including construction phase division and the time, material usage and process records of each construction node;

[0015] Extract quality assessment data from historical engineering project data, including the qualified rate, unqualified items and rectification records of construction nodes;

[0016] Environmental impact data are extracted from historical engineering project data, including climate conditions, geological conditions and construction noise levels in the areas where the construction nodes are located.

[0017] In a preferred embodiment, the construction node records are processed in sections according to the engineering standards to obtain a quality calibration node set, a potential problem node set and a construction abnormality node set, specifically:

[0018] Collect statistics on the time, material usage and process records in the construction node records, compare them with the corresponding engineering standard requirements, and generate a node deviation data set;

[0019] Based on the node deviation data set, determine the deviation level of each node and segment the nodes into high deviation, medium deviation and low deviation;

[0020] Mark low-deviation nodes as quality calibration node sets;

[0021] Mark the medium-deviation nodes as potential problem nodes;

[0022] The high deviation nodes are marked as construction abnormal node sets.

[0023] In a preferred embodiment, based on the quality calibration node set and the potential problem node set, a node association matrix model is constructed, the quality conduction factors between nodes are analyzed, and a risk assessment matrix is ​​generated, specifically:

[0024] Classify the node data in the quality calibration node set, and extract the logical associations between construction processes and the construction time series;

[0025] Map the association relationship between the nodes in the potential problem node set and the quality calibration node set to the multidimensional space to construct a node association matrix model;

[0026] According to the node association matrix model, determine the quality conduction path between different nodes and identify the node conduction factors, including process influencing factors, material usage factors and environmental adaptation factors;

[0027] Based on the node transmission factor, the quality risk between nodes is quantitatively evaluated to generate the risk transmission value between nodes;

[0028] The risk transmission values ​​between comprehensive nodes are used to construct a risk assessment matrix.

[0029] In a preferred embodiment, based on the construction abnormality node set, according to the environmental impact data and quality assessment data, the weights of multidimensional impact factors are determined, and the environmental quality interactive correlation factor set is output, specifically:

[0030] Extracting the environmental impact data of nodes from the construction anomaly node set, including climate conditions, geological characteristics and construction noise levels;

[0031] Extract node quality assessment data from the abnormal construction node set, including unqualified item records, rectification cycle and rectification results;

[0032] Normalize environmental impact data and quality assessment data, and map data of different dimensions to a unified weight analysis framework;

[0033] Based on the weight analysis framework, determine the multi-dimensional influencing factor weights of each abnormal construction node, including environmental weight, material weight and process weight;

[0034] The weights of multidimensional influencing factors are summarized to generate a set of interactive correlation factors of environmental quality.

[0035] In a preferred embodiment, a quality risk prediction model is constructed by combining the risk assessment matrix and the environmental quality interactive correlation factor set to predict the distribution location of potential quality problems and generate a quality anomaly warning data set, specifically:

[0036] The risk transmission value between nodes in the risk assessment matrix is ​​integrated with the weights of multi-dimensional influencing factors in the environmental quality interactive correlation factor set to establish a quality risk prediction model.

[0037] According to the quality risk prediction model, the location of nodes with problems is predicted and a risk node distribution map is generated;

[0038] Prioritize the risk node distribution map and mark high-risk nodes, medium-risk nodes, and low-risk nodes;

[0039] The output results of the comprehensive quality risk prediction model are used to generate a quality anomaly warning data set, including risk node distribution and risk level.

[0040] In a preferred embodiment, by collecting real-time monitoring data of the current construction node and analyzing it in combination with the quality abnormality warning data set, quality inspection and evaluation results are generated, and construction quality improvement suggestions are output, specifically:

[0041] Collect real-time monitoring data of current construction nodes, including node construction progress, actual material usage and current process completion rate, and classify them according to construction stage and node number;

[0042] The classified real-time monitoring data is projected into the quality abnormality warning data set, and matched with the risk node distribution and risk level according to dimensions such as timeline, node number, and material usage, to evaluate the correlation between the current construction node and the risk node, and output the matching evaluation results;

[0043] Based on the matching assessment results, the risk change trend of the current construction node is evaluated, the quality inspection assessment results are generated, and construction quality improvement suggestions are output.

[0044] On the other hand, the present invention provides a construction project quality detection system based on big data, including a data extraction module, a node segmentation module, a correlation analysis module, a factor weight determination module, a risk prediction module and an evaluation improvement module;

[0045] Data extraction module, which obtains historical engineering project data and extracts construction node records, quality assessment data and environmental impact data based on the historical engineering project data;

[0046] The node segmentation module segments the construction node records according to the engineering standards to obtain the quality calibration node set, potential problem node set and construction abnormal node set;

[0047] The correlation analysis module builds a node correlation matrix model based on the quality calibration node set and the potential problem node set, analyzes the quality conduction factors between nodes, and generates a risk assessment matrix;

[0048] The factor weight determination module determines the weights of multi-dimensional influencing factors based on the construction abnormality node set, environmental impact data and quality assessment data, and outputs the environmental quality interactive correlation factor set;

[0049] The risk prediction module combines the risk assessment matrix and the environmental quality interactive correlation factor set to build a quality risk prediction model, predict the distribution location of potential quality problems, and generate a quality anomaly warning data set;

[0050] The evaluation and improvement module collects real-time monitoring data of the current construction nodes, analyzes it in combination with the quality abnormality warning data set, generates quality inspection and evaluation results, and outputs construction quality improvement suggestions.

[0051] Technical effects and advantages of a construction project quality detection method and system based on big data of the present invention:

[0052] 1. By acquiring historical engineering project data and extracting construction node records, quality assessment data and environmental impact data, combined with engineering standards for segmented processing, quality calibration nodes, potential problem nodes and abnormal construction nodes can be effectively identified to discover quality risks in construction in advance. A node association matrix model is constructed based on the quality calibration node set and the potential problem node set, the quality transmission factor is analyzed, and a risk assessment matrix is ​​generated to quantify and evaluate the quality risks between different nodes. By calculating the weights of multidimensional influencing factors and generating a set of environmental quality interactive correlation factors, the ability to accurately identify environmental factors and quality problems during the construction process is improved.

[0053] 2. Combining the risk assessment matrix and the environmental quality interaction factor set, the quality risk prediction model constructed can effectively predict the distribution of potential quality problems and generate a quality anomaly warning data set, providing timely decision support for construction managers. By combining real-time monitoring data with quality anomaly warning data sets, it is possible to generate construction quality assessment results and put forward improvement suggestions, thereby improving the efficiency of construction quality management, reducing quality risks, and reducing project costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 A schematic diagram of a construction project quality detection method based on big data according to the present invention;

[0055] Figure 2 It is a structural schematic diagram of a construction project quality detection system based on big data of the present invention. DETAILED DESCRIPTION

[0056] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0057] Example 1

[0058] Figure 1 The present invention provides a construction project quality detection method based on big data, which includes the following steps:

[0059] Obtain historical engineering project data, and extract construction node records, quality assessment data, and environmental impact data based on the historical engineering project data;

[0060] The construction node records are processed in sections according to the engineering standards to obtain the quality calibration node set, potential problem node set and construction abnormal node set;

[0061] Based on the quality calibration node set and the potential problem node set, a node association matrix model is constructed to analyze the quality conduction factors between nodes and generate a risk assessment matrix;

[0062] Based on the construction abnormality node set, according to the environmental impact data and quality assessment data, the weights of multi-dimensional influencing factors are determined, and the environmental quality interactive correlation factor set is output;

[0063] Combining the risk assessment matrix and the set of environmental quality interactive correlation factors, a quality risk prediction model is constructed to predict the distribution of potential quality problems and generate a quality anomaly warning data set;

[0064] By collecting real-time monitoring data of the current construction nodes and analyzing it in combination with the quality abnormality warning data set, quality inspection and evaluation results are generated, and construction quality improvement suggestions are output.

[0065] Specifically, historical project data is obtained, and based on the historical project data, construction node records, quality assessment data, and environmental impact data are extracted, including:

[0066] Extract construction node records from historical engineering project data, including construction phase division and the time, material usage and process records of each construction node; specifically, construction phase division refers to dividing the entire project into several stages (such as foundation construction, main structure construction, decoration stage, etc.) according to the construction plan of the project, and marking the key construction activities of each stage; the time of each construction node refers to recording the start time, end time and time (construction period) of each construction node; material usage refers to the type, quantity and quality of materials used in the construction process (such as the strength grade of steel bars, the grade of concrete, etc.); process records refer to specific construction processes and operation processes, such as the completion of construction steps such as formwork installation and concrete pouring;

[0067] Extract quality assessment data from historical engineering project data, including the qualified rate, unqualified items and rectification records of construction nodes; specifically, the qualified rate of construction nodes refers to the proportion of the part of the construction activities at that node that meets the design standards or specification requirements to the total construction volume; unqualified items refer to specific problems that do not meet the standards or design requirements during construction, such as cracks, water leaks, etc.; rectification records refer to the rectification time, measures and final acceptance results for unqualified items;

[0068] Environmental impact data is extracted from historical engineering project data, including climate conditions, geological conditions and construction noise levels in the areas where the construction nodes are located; specifically, climate conditions refer to weather conditions during construction (such as temperature, rainfall, wind speed, etc.), which may have a direct impact on construction quality and progress; geological conditions refer to the foundation soil type, bearing capacity and groundwater level of the construction site, which have an important impact on foundation construction; construction noise level refers to the noise intensity during the construction process and its impact on construction personnel or the surrounding environment, usually expressed in decibels.

[0069] Specifically, the construction node records are processed in sections according to the engineering standards to obtain the quality calibration node set, potential problem node set and construction abnormal node set, including:

[0070] Statistics are collected on the time, material usage and process records in the construction node records, and compared with the corresponding engineering standard requirements to generate a node deviation data set; specifically, time statistics refers to recording the actual completion time of each construction node, comparing it with the planned construction period or standard construction period, and analyzing the time deviation; material usage statistics refers to statistics on the type, quantity and quality of materials used in construction, and checking whether they meet the construction design and relevant specifications; process record statistics refers to sorting out the operation procedures and execution status of the construction nodes, and comparing them with the process requirements specified in the engineering standards; the node deviation data set refers to quantifying all deviations (such as time overdue, insufficient material usage, etc.) and aggregating them into a structured data set;

[0071] Based on the node deviation data set, the deviation level of each node is determined, and the nodes are segmented into high deviation, medium deviation and low deviation. Specifically, the deviation level classification means that the deviation degree of each node is divided into three categories: high, medium and low by setting the deviation threshold. For example, a time deviation exceeding 10% is a high deviation, 5%-10% is a medium deviation, and less than 5% is a low deviation.

[0072] Mark low-deviation nodes as quality calibration node sets;

[0073] Mark the medium-deviation nodes as potential problem nodes;

[0074] The high deviation nodes are marked as construction abnormal node sets.

[0075] Specifically, based on the quality calibration node set and the potential problem node set, a node association matrix model is constructed to analyze the quality conduction factors between nodes and generate a risk assessment matrix, including:

[0076] The node data in the quality calibration node set are classified to extract the logical association and construction time series between the construction processes. Specifically, the quality calibration node data classification refers to extracting the node data that meets the standards from the quality calibration node set, and classifying and arranging them according to the construction type, process content and time characteristics of the node. The logical association refers to analyzing the dependency relationship between the construction processes. For example, the completion of a certain process is a prerequisite for the start of the subsequent process (such as concrete can only be poured after the steel bars are tied). The construction time series refers to arranging the construction nodes in the order of completion time to form a time series, which is convenient for identifying the temporal dependency relationship between processes.

[0077] The association relationship between the nodes in the potential problem node set and the quality calibration node set is mapped to the multidimensional space to construct a node association matrix model; specifically, the association relationship between the potential problem node and the quality calibration node refers to determining the degree of association between the two by comparing the process requirements and time plan of the potential problem node with the actual completion status of the quality calibration node; multidimensional space mapping refers to expressing the association relationship between nodes into multiple dimensions, such as process association strength, time dependence and material matching degree, to form a quantifiable mathematical model;

[0078] According to the node association matrix model, the quality conduction path between different nodes is determined, and the node conduction factors are identified, including process influencing factors, material usage factors and environmental adaptability factors. Specifically, the quality conduction path refers to the transmission path of quality problems between construction nodes through the association matrix analysis. For example, the problem of steel bar binding may be transmitted to the concrete pouring link, thereby affecting the overall quality. The process influencing factor refers to the direct impact of the quality of a certain process on the subsequent process, such as steel bar binding affecting the stability of concrete pouring. The material usage factor refers to the possibility that material quality problems may be transmitted from one node to the subsequent nodes, such as the template quality problem affecting the surface flatness of the concrete. The environmental adaptability factor refers to the impact of environmental conditions (such as climate) on multiple nodes, such as high humidity affecting the template and concrete curing effect.

[0079] Based on the node conduction factor, the quality risk between nodes is quantitatively evaluated to generate the risk conduction value between nodes; for example, assuming that the process influence factor of the steel bar binding node is 0.7, the material usage factor is 0.5, and the correlation value of the conduction path is 0.8, the risk conduction value calculation formula is:

[0080] Risk transmission value = process factor weight * associated value + material factor weight * associated value;

[0081] The risk transmission values ​​between comprehensive nodes are used to construct a risk assessment matrix.

[0082] Specifically, based on the construction abnormality node set, according to the environmental impact data and quality assessment data, the weights of multidimensional influencing factors are determined, and the environmental quality interactive correlation factor set is output, including:

[0083] Extracting the environmental impact data of nodes from the construction anomaly node set, including climate conditions, geological characteristics and construction noise levels;

[0084] Extract node quality assessment data from the abnormal construction node set, including unqualified item records, rectification cycle and rectification results;

[0085] Normalize the environmental impact data and quality assessment data, and map the data of different dimensions to a unified weight analysis framework; specifically, the weight analysis framework: by assigning weights to each type of data, it reflects the relative impact on construction quality;

[0086] Based on the weight analysis framework, the weights of the multi-dimensional influencing factors of each abnormal construction node are determined, including environmental weight, material weight and process weight; specifically, based on the weight analysis framework, weights are assigned to each dimension;

[0087] The weights of multidimensional influencing factors are summarized to generate a set of interactive correlation factors of environmental quality.

[0088] Specifically, the risk assessment matrix and the environmental quality interactive correlation factor set are used to build a quality risk prediction model, predict the distribution of potential quality problems, and generate a quality anomaly warning data set, including:

[0089] The risk transmission value between nodes in the risk assessment matrix is ​​integrated with the weights of multi-dimensional influencing factors in the environmental quality interactive correlation factor set to establish a quality risk prediction model.

[0090] According to the quality risk prediction model, the location of nodes with problems is predicted and a risk node distribution map is generated;

[0091] Prioritize the risk node distribution map and mark high-risk nodes, medium-risk nodes, and low-risk nodes;

[0092] The output results of the comprehensive quality risk prediction model are used to generate a quality anomaly warning data set, including risk node distribution and risk level.

[0093] Specifically, by collecting real-time monitoring data of the current construction node and analyzing it in combination with the quality abnormality warning data set, quality inspection and evaluation results are generated, and construction quality improvement suggestions are output, including:

[0094] Collect real-time monitoring data of current construction nodes, including node construction progress, actual material usage and current process completion rate, and classify them according to construction stage and node number;

[0095] The classified real-time monitoring data is projected into the quality anomaly warning data set, and matched with the risk node distribution and risk level according to dimensions such as timeline, node number and material usage, to evaluate the correlation between the current construction node and the risk node, and output the matching evaluation results; specifically, the timeline refers to comparing the real-time data with the scheduled construction progress to check whether there is a progress delay problem; the node number refers to matching with the existing risk node information to determine the similarity between the current node status and the existing high-risk nodes; the material usage refers to comparing the actual material data used with the design and quality standards to ensure that there are no problems with the materials used; for example, during the construction process, the actual material usage of the node (such as cement) exceeds the standard value and has a high similarity with the risk node (such as excessive material use leading to crack risk), and the node will be marked as having a possible quality risk;

[0096] Based on the matching assessment results, the risk change trend of the current construction node is evaluated, the quality inspection assessment results are generated, and construction quality improvement suggestions are output.

[0097] Example 2

[0098] The difference between Example 2 of the present invention and Example 1 is that this example introduces a construction project quality inspection system based on big data.

[0099] Figure 2 A structural schematic diagram of a construction project quality detection system based on big data of the present invention is given, a construction project quality detection system based on big data, including a data extraction module, a node segmentation module, a correlation analysis module, a factor weight determination module, a risk prediction module and an evaluation improvement module;

[0100] Data extraction module, which obtains historical engineering project data and extracts construction node records, quality assessment data and environmental impact data based on the historical engineering project data;

[0101] The node segmentation module segments the construction node records according to the engineering standards to obtain the quality calibration node set, potential problem node set and construction abnormal node set;

[0102] The correlation analysis module builds a node correlation matrix model based on the quality calibration node set and the potential problem node set, analyzes the quality conduction factors between nodes, and generates a risk assessment matrix;

[0103] The factor weight determination module determines the weights of multi-dimensional influencing factors based on the construction abnormality node set, environmental impact data and quality assessment data, and outputs the environmental quality interactive correlation factor set;

[0104] The risk prediction module combines the risk assessment matrix and the environmental quality interactive correlation factor set to build a quality risk prediction model, predict the distribution location of potential quality problems, and generate a quality anomaly warning data set;

[0105] The evaluation and improvement module collects real-time monitoring data of the current construction nodes, analyzes it in combination with the quality abnormality warning data set, generates quality inspection and evaluation results, and outputs construction quality improvement suggestions.

[0106] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and thresholds in the formula are set by technicians in this field according to actual conditions.

[0107] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0108] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0109] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and modules described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0110] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0111] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, and may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0112] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0113] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0114] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0115] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A construction project quality detection method based on big data, characterized in that: The steps include: Obtain historical engineering project data, and extract construction node records, quality assessment data, and environmental impact data based on the historical engineering project data; The construction node records are processed in sections according to the engineering standards to obtain the quality calibration node set, potential problem node set and construction abnormal node set; Based on the quality calibration node set and the potential problem node set, a node association matrix model is constructed to analyze the quality conduction factors between nodes and generate a risk assessment matrix; Based on the construction abnormality node set, according to the environmental impact data and quality assessment data, the weights of multi-dimensional influencing factors are determined, and the environmental quality interactive correlation factor set is output; Combining the risk assessment matrix and the set of environmental quality interactive correlation factors, a quality risk prediction model is constructed to predict the distribution of potential quality problems and generate a quality anomaly warning data set; By collecting real-time monitoring data of the current construction nodes and analyzing it in combination with the quality abnormality warning data set, quality inspection and evaluation results are generated, and construction quality improvement suggestions are output.

2. A construction project quality detection method based on big data according to claim 1, characterized in that: Obtain historical engineering project data, and extract construction node records, quality assessment data, and environmental impact data based on the historical engineering project data, specifically: Extract construction node records from historical engineering project data, including construction phase division and the time, material usage and process records of each construction node; Extract quality assessment data from historical engineering project data, including the qualified rate, unqualified items and rectification records of construction nodes; Environmental impact data are extracted from historical engineering project data, including climate conditions, geological conditions and construction noise levels in the areas where the construction nodes are located.

3. A construction project quality detection method based on big data according to claim 1, characterized in that: The construction node records are processed in sections according to the engineering standards to obtain the quality calibration node set, potential problem node set and construction abnormal node set, which are as follows: Collect statistics on the time, material usage and process records in the construction node records, compare them with the corresponding engineering standard requirements, and generate a node deviation data set; Based on the node deviation data set, determine the deviation level of each node and segment the nodes into high deviation, medium deviation and low deviation; Mark low-deviation nodes as quality calibration node sets; Mark the medium-deviation nodes as potential problem nodes; The high deviation nodes are marked as construction abnormal node sets.

4. A construction project quality detection method based on big data according to claim 1, characterized in that: Based on the quality calibration node set and the potential problem node set, a node association matrix model is constructed to analyze the quality conduction factors between nodes and generate a risk assessment matrix, which is as follows: Classify the node data in the quality calibration node set, and extract the logical associations between construction processes and the construction time series; Map the association relationship between the nodes in the potential problem node set and the quality calibration node set to the multidimensional space to construct a node association matrix model; According to the node association matrix model, determine the quality conduction path between different nodes and identify the node conduction factors, including process influencing factors, material usage factors and environmental adaptation factors; Based on the node transmission factor, the quality risk between nodes is quantitatively evaluated to generate the risk transmission value between nodes; The risk transmission values ​​between comprehensive nodes are used to construct a risk assessment matrix.

5. The construction project quality detection method based on big data according to claim 1 is characterized in that: Based on the construction abnormality node set, according to the environmental impact data and quality assessment data, the weights of multidimensional influencing factors are determined, and the environmental quality interactive correlation factor set is output, which is specifically: Extracting the environmental impact data of nodes from the construction anomaly node set, including climate conditions, geological characteristics and construction noise levels; Extract node quality assessment data from the abnormal construction node set, including unqualified item records, rectification cycle and rectification results; Normalize environmental impact data and quality assessment data, and map data of different dimensions to a unified weight analysis framework; Based on the weight analysis framework, determine the multi-dimensional influencing factor weights of each abnormal construction node, including environmental weight, material weight and process weight; The weights of multidimensional influencing factors are summarized to generate a set of interactive correlation factors of environmental quality.

6. A construction project quality detection method based on big data according to claim 1, characterized in that: Combining the risk assessment matrix and the set of environmental quality interactive correlation factors, a quality risk prediction model is constructed to predict the distribution of potential quality problems and generate a quality anomaly warning data set, specifically: The risk transmission value between nodes in the risk assessment matrix is ​​integrated with the weights of multi-dimensional influencing factors in the environmental quality interactive correlation factor set to establish a quality risk prediction model. According to the quality risk prediction model, the location of nodes with problems is predicted and a risk node distribution map is generated; Prioritize the risk node distribution map and mark high-risk nodes, medium-risk nodes, and low-risk nodes; The output results of the comprehensive quality risk prediction model are used to generate a quality anomaly warning data set, including risk node distribution and risk level.

7. The construction project quality detection method based on big data according to claim 1 is characterized in that: By collecting real-time monitoring data of the current construction nodes and analyzing it in combination with the quality abnormality warning data set, we can generate quality inspection and evaluation results and output construction quality improvement suggestions, specifically: Collect real-time monitoring data of current construction nodes, including node construction progress, actual material usage and current process completion rate, and classify them according to construction stage and node number; The classified real-time monitoring data is projected into the quality abnormality warning data set, and matched with the risk node distribution and risk level according to dimensions such as timeline, node number, and material usage, to evaluate the correlation between the current construction node and the risk node, and output the matching evaluation results; Based on the matching assessment results, the risk change trend of the current construction node is evaluated, the quality inspection assessment results are generated, and construction quality improvement suggestions are output.

8. A construction project quality detection system based on big data, used to implement the construction project quality detection system based on big data as described in any one of claims 1 to 7, characterized in that: It includes data extraction module, node segmentation module, association analysis module, factor weight determination module, risk prediction module and assessment improvement module; Data extraction module, which obtains historical engineering project data and extracts construction node records, quality assessment data and environmental impact data based on the historical engineering project data; The node segmentation module segments the construction node records according to the engineering standards to obtain the quality calibration node set, potential problem node set and construction abnormal node set; The correlation analysis module builds a node correlation matrix model based on the quality calibration node set and the potential problem node set, analyzes the quality conduction factors between nodes, and generates a risk assessment matrix; The factor weight determination module determines the weights of multi-dimensional influencing factors based on the construction abnormality node set, environmental impact data and quality assessment data, and outputs the environmental quality interactive correlation factor set; The risk prediction module combines the risk assessment matrix and the environmental quality interactive correlation factor set to build a quality risk prediction model, predict the distribution location of potential quality problems, and generate a quality anomaly warning data set; The evaluation and improvement module collects real-time monitoring data of the current construction nodes, analyzes it in combination with the quality abnormality warning data set, generates quality inspection and evaluation results, and outputs construction quality improvement suggestions.

Images