Engineering data supervision method and apparatus, and storage medium and electronic apparatus

Abstract

The embodiments of the present invention relate to the technical field of engineering supervision techniques. Provided are an engineering data supervision method and apparatus, and a storage medium and an electronic apparatus. The method comprises: acquiring engineering data; performing pixel extraction on image data by means of a preset first model, so as to obtain a pixel matrix of the image data; on the basis of the pixel matrix, determining on-site progress information of a construction site; and performing matching processing on the on-site progress information and engineering progress data, and when the matching result does not meet a matching condition, determining that the engineering progress data is abnormal. By means of the present invention, the problem of the engineering data supervision accuracy being low is solved, thereby achieving the effect of improving the engineering supervision precision and efficiency.

Description

Engineering data supervision method, device, storage medium and electronic device Technical Field

[0001] The embodiments of the present invention relate to the field of communications, and in particular, to an engineering data supervision method, device, storage medium, and electronic device. Background Art

[0002] With the continued development of urban construction in my country, numerous construction projects are facing increasing investment, tighter deadlines, and stricter O&M requirements. This presents new challenges for project management, particularly for general contracting (EPC). Large-scale EPC projects are more complex to manage than traditional smaller-lot projects. EPC contractors face challenges in leveraging the advantages of EPC to improve management efficiency, deliver high-quality projects, and achieve digital handover throughout the entire process.

[0003] There is currently no better solution to the above problems.

[0004] Summary of the Invention

[0005] Embodiments of the present invention provide a method, device, storage medium, and electronic device for project data supervision, to at least solve the problem of inaccurate project supervision in related technologies.

[0006] According to one embodiment of the present invention, a method for supervising engineering data is provided, comprising:

[0007] Acquiring engineering data, wherein the engineering data includes image data of the engineering site and engineering progress data;

[0008] Performing pixel extraction on the image data using a preset first model to obtain a pixel matrix of the image data;

[0009] determining on-site progress information of the construction site based on the pixel matrix;

[0010] The on-site progress information is matched with the project progress data, and if the matching result does not meet the matching condition, it is determined that an abnormality exists in the project progress data.

[0011] In an exemplary embodiment, when the matching process is performed on the site progress information and the project progress data, and the matching result does not meet the matching condition, the method further includes:

[0012] Acquiring data features of abnormal engineering progress data, wherein the data features include occurrence time and coordinate information of the abnormal engineering progress data;

[0013] Determining an abnormal data feature matrix of the abnormal engineering progress data based on the data features and the abnormal engineering progress data;

[0014] Performing feature analysis on the abnormal data feature matrix to determine the abnormal data matrix features;

[0015] When the abnormal data matrix feature does not meet the abnormal characterization condition, it is determined that the project progress data is abnormal.

[0016] In an exemplary embodiment, determining the on-site progress information of the construction site based on the pixel matrix includes:

[0017] Acquire a historical pixel matrix, wherein the historical pixel matrix is ​​obtained based on historical image data and stored in the target area;

[0018] Calculating an error value between the historical pixel matrix and the pixel matrix;

[0019] The on-site progress information is determined according to the error value.

[0020] In an exemplary embodiment, before determining the on-site progress information of the construction site based on the pixel matrix, the method further includes:

[0021] determining a matrix type of the pixel matrix based on the image data;

[0022] When the pixel matrix is ​​a first type matrix, performing matrix conversion processing on the pixel matrix to obtain a first matrix;

[0023] Performing gradient calculation on the first matrix using a preset first operator to obtain an edge strength matrix;

[0024] performing edge classification on the edge intensity matrix based on a preset edge threshold to determine edge detection information of the image data;

[0025] Determine whether the image data has an abnormality according to the edge detection information.

[0026] In an exemplary embodiment, before performing pixel extraction on the image data using a preset first model to obtain a pixel matrix of the image data, the method further includes:

[0027] The image data is subjected to denoising processing by wavelet transform to obtain denoised image data, wherein the pixel extraction is performed based on the denoised image data.

[0028] According to another embodiment of the present invention, there is provided an engineering data monitoring device, comprising:

[0029] A data acquisition module, configured to acquire engineering data, wherein the engineering data includes image data of the engineering site and engineering progress data;

[0030] a pixel extraction module, configured to extract pixels from the image data using a preset first model to obtain a pixel matrix of the image data;

[0031] a progress determination module, configured to determine on-site progress information of the construction site based on the pixel matrix;

[0032] The first abnormality judgment module is used to match the on-site progress information with the project progress data, and determine that an abnormality exists in the project progress data if the matching result does not meet the matching condition.

[0033] According to yet another embodiment of the present invention, a computer-readable storage medium is provided, in which a computer program is stored. The computer program is configured to execute the steps of any one of the above method embodiments when run.

[0034] According to another embodiment of the present invention, an electronic device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to perform the steps in any one of the above method embodiments.

[0035] Through the present invention, by monitoring image data and automatically detecting the construction progress data recorded in the record document based on the image monitoring results, it is possible to accurately judge whether the construction progress data in the record document is accurate. Therefore, the problem of inaccurate project supervision can be solved, thereby achieving the effect of improving the accuracy and efficiency of project supervision. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] FIG1 is a flow chart of engineering data supervision according to an embodiment of the present invention;

[0037] FIG2 is a structural block diagram of a project data monitoring device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0038] Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings and in combination with embodiments.

[0039] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0040] In this embodiment, a method for supervising engineering data is provided. FIG1 is a flow chart of a method for supervising engineering data according to an embodiment of the present invention. As shown in FIG1 , the flow chart includes the following steps:

[0041] Step S101, obtaining engineering data, wherein the engineering data includes image data of the engineering site and engineering progress data, and the engineering progress data is obtained by identifying and counting engineering documents stored in the system;

[0042] In this embodiment, images of the construction site are collected through cameras installed at the construction site to obtain image data of the construction site. During the construction process, it is usually required to upload relevant project documents, such as project progress descriptions arranged by date, project safety records, design documents for different project stages, construction inspection documents, project cost documents, quality control record documents, contract management records, organization and coordination records and other data documents. Therefore, ORC recognition or text semantic recognition can be performed on these documents to obtain the project progress data uploaded by relevant units.

[0043] The image data includes (but is not limited to) pictures, audio or video data.

[0044] Step S102: performing pixel extraction on the image data using a preset first model to obtain a pixel matrix of the image data;

[0045] In this embodiment, pixel extraction is performed on the image data to form a pixel matrix, and then the project progress is judged based on the relevant characteristics of the pixel matrix. Compared with manual data review, this can not only reduce labor consumption but also improve the accuracy of project progress judgment.

[0046] Step S103: determining on-site progress information of the construction site based on the pixel matrix;

[0047] In this embodiment, during construction, as the project progresses, the image of the construction site will change, thereby causing changes in the image pixels, which is reflected in the pixel matrix as changes in the elements in the pixel matrix. Therefore, the on-site progress information of the construction site can be determined by observing the changes in the elements of the pixel matrix.

[0048] For example, the initial pixel matrix is Then when the pixel matrix changes to , it means that the project has advanced to the location of the site corresponding to the sub-matrix [0 1 1], and so on.

[0049] Step S104 : matching the site progress information with the project progress data, and determining that an anomaly exists in the project progress data when the matching result does not satisfy a matching condition.

[0050] In this embodiment, according to the relevant engineering supervision requirements, the construction party is required to upload engineering documents or engineering project information regularly. At this time, these engineering documents or project information can be identified through the semantic recognition model to determine the engineering progress data uploaded by the construction party. Subsequently, the supervision party or the project party A matches the engineering progress data with the aforementioned determined on-site progress information to determine whether the data uploaded by the construction party is true, thereby achieving accurate management of the construction site.

[0051] Of course, the data information determined by the semantic recognition model also includes (but is not limited to) information such as material consumption and personnel deployment. The material consumption and personnel deployment information can also form a relevant data matrix and calculate the correlation between it and the aforementioned on-site progress information, thereby assisting in determining whether the relevant data is accurate.

[0052] Through the above steps, by monitoring the image data and automatically detecting the construction progress data recorded in the record document based on the image monitoring results, it is possible to accurately determine whether the construction progress data in the record document is accurate, thereby solving the problem of low accuracy in project supervision and improving the accuracy and efficiency of project supervision.

[0053] Therefore, the problem can be solved and the effect of improvement can be achieved

[0054] The execution entity of the above steps may be a base station, a terminal, etc., but is not limited thereto.

[0055] In an optional embodiment, when the matching process is performed on the site progress information and the project progress data, and the matching result does not satisfy the matching condition, the method further includes:

[0056] Step S1041, obtaining data features of abnormal engineering progress data, wherein the data features include the occurrence time and coordinate information of the abnormal engineering progress data;

[0057] Step S1042, determining an abnormal data feature matrix of the abnormal engineering progress data based on the data features and the abnormal engineering progress data;

[0058] Step S1043, performing feature analysis processing on the abnormal data feature matrix to determine the abnormal data matrix features;

[0059] Step S1044 : When the abnormal data matrix feature does not satisfy the abnormal characterization condition, it is determined that the project progress data is abnormal.

[0060] In this embodiment, in order to further determine the abnormal situation of the project progress data, a multi-dimensional data matrix can be constructed based on the time and place of occurrence of the abnormal data and the abnormal data itself. Then, the severity of the data abnormality can be further determined by judging the frequency and number of occurrence of the abnormal data, so as to determine whether the relevant abnormality is a data recognition and collection error or human falsification. Specifically, the degree of the abnormal situation can be evaluated by weighting or calculating the average value of the elements or sub-matrices in the matrix, thereby determining the severity and priority of the abnormal situation.

[0061] Among them, the coordinate information of the abnormal project progress data includes the coordinate information of the construction site corresponding to the abnormal project progress data; the matrix characteristics of the abnormal data include the frequency of occurrence, element distribution, change trend and other characteristics of the abnormal data in the matrix; the characterization conditions include (but are not limited to) whether the frequency is less than the threshold, whether the element distribution conforms to the Gaussian distribution, etc.

[0062] For example, first obtain the data features according to Table 1:

[0063] Table 1

[0064] This gives the anomaly matrix Among them, 01 indicates abnormal data, and 00 indicates normal data. At this time, since the data in the third column is normal, the data in the third column is discarded, and then the remaining matrix is ​​normalized to obtain a feature matrix that is convenient for calculation; then the feature matrix is ​​feature analyzed to determine the frequency of abnormal data and other characteristics, and finally, it is determined whether it meets the characterization conditions based on the relevant characteristics.

[0065] It should be noted that in addition to constructing a multidimensional matrix based on the time when the abnormal data occurred and the corresponding construction site coordinates, multiple multidimensional abnormal data matrices can also be formed according to the type of abnormal data (such as quality abnormalities, construction safety abnormalities, material usage abnormalities, environmental protection data abnormalities), the degree of abnormality (the difference between normal data or national standards), and the time when the abnormal data occurred, and the correlation between these abnormal data matrices can be calculated to determine whether the relevant abnormalities are caused by artificial falsification or data collection abnormalities.

[0066] In an optional embodiment, determining the on-site progress information of the construction site based on the pixel matrix includes:

[0067] Step S1031, obtaining a historical pixel matrix, wherein the historical pixel matrix is ​​obtained based on historical image data and stored in the target area;

[0068] Step S1032, calculating the error value between the historical pixel matrix and the pixel matrix;

[0069] Step S1033: Determine the on-site progress information according to the error value.

[0070] In this embodiment, the difference between the real-time pixel matrix and the historical pixel matrix is ​​calculated to determine the pixel change at the relevant position, and then the relevant progress can be determined.

[0071] For example, the historical pixel matrix is The pixel matrix obtained in real time is The error between the two is then calculated to determine whether there is progress at the construction site and the progress status.

[0072] In an optional embodiment, before determining the on-site progress information of the construction site based on the pixel matrix, the method further includes:

[0073] Step S10301: determining the matrix type of the pixel matrix based on the image data;

[0074] Step S10302: When the pixel matrix is ​​a first type matrix, perform matrix conversion processing on the pixel matrix to obtain a first matrix;

[0075] Step S10303: performing gradient calculation on the first matrix using a preset first operator to obtain an edge strength matrix;

[0076] Step S10304: performing edge classification on the edge intensity matrix based on a preset edge threshold to determine edge detection information of the image data;

[0077] Step S10305: Determine whether the image data has any abnormality based on the edge detection information.

[0078] In this embodiment, since the construction site is relatively complex, before confirming the progress, the boundary lines between each construction site and the surrounding environment must be determined through edge detection to facilitate the progress identification of the actual construction site. At the same time, the data collection is judged to be abnormal by whether the edge detection results are normal, so as to avoid data falsification caused by artificial synthetic images; since the values ​​of color pixels may be large, when performing calculations, it is necessary to first convert the pixel matrix of the color pixels (corresponding to the aforementioned first type of matrix) into a grayscale matrix (corresponding to the aforementioned first matrix) that is easy to calculate, and then calculate the pixel edge strength separately, and use this to determine whether the relevant pixels are edge pixels that can be cut and classified, and thus determine the edge detection situation.

[0079] Among them, the first operator can be (but not limited to) Roberts operator, Laplacian operator, Sobel operator, etc., and can be selected according to actual needs; the preset edge threshold can be obtained by data classification statistics of past project data.

[0080] In an optional embodiment, before performing pixel extraction on the image data using a preset first model to obtain a pixel matrix of the image data, the method further includes:

[0081] Step S10201 , performing denoising processing on the image data by wavelet transform to obtain denoised image data, wherein the pixel extraction is performed based on the denoised image data.

[0082] In this embodiment, the image data is denoised by wavelet transform, which can reduce the interference of noise in the image acquisition process on image pixels, thereby improving the accuracy of the image.

[0083] Through the description of the above embodiments, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus the necessary general hardware platform, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present invention.

[0084] This embodiment also provides an engineering data monitoring device for implementing the above-described embodiments and preferred implementations. Details already described will not be repeated. As used below, the term "module" may refer to a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented using software, implementation using hardware, or a combination of software and hardware, is also possible and contemplated.

[0085] FIG2 is a structural block diagram of a project data monitoring device according to an embodiment of the present invention. As shown in FIG2 , the device includes:

[0086] The data acquisition module 21 is used to obtain engineering data, wherein the engineering data includes image data of the engineering site and engineering progress data, and the engineering progress data is obtained by identifying and counting engineering documents stored in the system;

[0087] a pixel extraction module 22, configured to extract pixels from the image data using a preset first model to obtain a pixel matrix of the image data;

[0088] a progress determination module 23, configured to determine on-site progress information of the construction site based on the pixel matrix;

[0089] The first abnormality judgment module 24 is configured to match the on-site progress information with the project progress data, and determine that an abnormality exists in the project progress data if the matching result does not satisfy a matching condition.

[0090] In an optional embodiment, the device further comprises:

[0091] a feature extraction module for matching the on-site progress information with the project progress data and obtaining data features of the abnormal project progress data if the matching result does not meet the matching condition, wherein the data features include the occurrence time and coordinate information of the abnormal project progress data;

[0092] an abnormal matrix module, configured to determine an abnormal data feature matrix of the abnormal engineering progress data based on the data features and the abnormal engineering progress data;

[0093] A feature analysis module is used to perform feature analysis on the abnormal data feature matrix to determine the abnormal data matrix features;

[0094] The abnormality determination module is used to determine that the engineering progress data has an abnormality when the abnormal data matrix characteristics do not meet the abnormality characterization conditions.

[0095] In an optional embodiment, the progress determination module 23 includes:

[0096] A historical data unit, configured to obtain a historical pixel matrix, wherein the historical pixel matrix is ​​obtained based on historical image data and stored in a target area;

[0097] an error calculation unit, configured to calculate an error value between the historical pixel matrix and the pixel matrix;

[0098] A progress determination unit is configured to determine the on-site progress information according to the error value.

[0099] In an optional embodiment, the device further comprises:

[0100] a type determination module, configured to determine a matrix type of the pixel matrix based on the image data before determining on-site progress information of the construction site based on the pixel matrix;

[0101] a matrix conversion module, configured to perform matrix conversion processing on the pixel matrix to obtain a first matrix when the pixel matrix is ​​a first type matrix;

[0102] a gradient calculation module, configured to perform gradient calculation on the first matrix using a preset first operator to obtain an edge intensity matrix;

[0103] an edge detection module, configured to perform edge classification on the edge intensity matrix based on a preset edge threshold value to determine edge detection information of the image data;

[0104] The second abnormality judgment module is used to determine whether there is an abnormality in the image data according to the edge detection information.

[0105] In an optional embodiment, the device further comprises:

[0106] A denoising module is used to perform denoising on the image data by wavelet transform before performing pixel extraction on the image data by a preset first model to obtain a pixel matrix of the image data, so as to obtain denoised image data, wherein the pixel extraction is performed based on the denoised image data.

[0107] It should be noted that the above modules can be implemented through software or hardware. For the latter, it can be implemented in the following ways, but not limited to: the above modules are all located in the same processor; or the above modules are located in different processors in any combination.

[0108] An embodiment of the present invention further provides a computer-readable storage medium, in which a computer program is stored. The computer program is configured to execute the steps of any one of the above method embodiments when running.

[0109] In an exemplary embodiment, the computer-readable storage medium may include, but is not limited to, various media that can store computer programs, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk, or an optical disk.

[0110] An embodiment of the present invention further provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0111] In an exemplary embodiment, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0112] For specific examples in this embodiment, reference may be made to the examples described in the above embodiments and exemplary implementation modes, and this embodiment will not be described in detail here.

[0113] Obviously, those skilled in the art will appreciate that the various modules or steps of the present invention described above can be implemented using a general-purpose computing device, can be centralized on a single computing device, or can be distributed across a network of multiple computing devices. They can be implemented using program code executable by the computing device, and thus, can be stored in a storage device and executed by the computing device. In some cases, the steps shown or described herein can be performed in a different order than that shown, or can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0114] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the principles of the present invention are intended to be within the scope of protection of the present invention.

Claims

1. An engineering data supervision method, characterized in that, it includes: Obtain engineering data, wherein the engineering data includes image data of the engineering site and engineering progress data, and the engineering progress data is identified and statistically obtained from engineering documents stored in the system; Extract pixels from the image data through a preset first model to obtain a pixel matrix of the image data; Based on the pixel matrix, determine the on-site progress information of the construction site; Match the on-site progress information with the engineering progress data, and in the case where the matching result does not meet the matching condition, determine that the engineering progress data is abnormal.

2. The method according to claim 1, characterized in that, when matching the on-site progress information with the engineering progress data and in the case where the matching result does not meet the matching condition, the method further includes: Obtain the data characteristics of the abnormal engineering progress data, wherein the data characteristics include the occurrence time and coordinate information of the abnormal engineering progress data; Based on the data characteristics and the abnormal engineering progress data, determine the abnormal data characteristic matrix of the abnormal engineering progress data; Perform feature analysis processing on the abnormal data characteristic matrix to determine the abnormal data matrix characteristics; In the case where the abnormal data matrix characteristics do not meet the abnormal characterization conditions, determine that the engineering progress data is abnormal.

3. The method according to claim 1, characterized in that, the determining the on-site progress information of the construction site based on the pixel matrix includes: Obtain a historical pixel matrix, wherein the historical pixel matrix is obtained based on historical image data and stored in the target area; Calculate the error value between the historical pixel matrix and the pixel matrix; Determine the on-site progress information according to the error value.

4. The method according to claim 1, characterized in that, before determining the on-site progress information of the construction site based on the pixel matrix, the method further includes: Based on the image data, determine the matrix type of the pixel matrix; In the case where the pixel matrix is a first type matrix, perform matrix transformation processing on the pixel matrix to obtain a first matrix; Perform gradient calculation on the first matrix through a preset first operator to obtain an edge intensity matrix; Based on a preset edge threshold, classify the edges of the edge intensity matrix to determine the edge detection information of the image data; Determine whether the image data is abnormal according to the edge detection information.

5. The method according to claim 1, characterized in that, before extracting pixels from the image data through a preset first model to obtain the pixel matrix of the image data, the method further includes: Perform denoising processing on the image data through wavelet transform to obtain denoised image data, wherein the pixel extraction is based on the denoised image data.

6. An engineering data supervision device, characterized in that, it includes: A data acquisition module, configured to acquire engineering data, wherein the engineering data includes image data of the engineering site and engineering progress data, and the engineering progress data is obtained by identifying and counting engineering documents stored in the system; A pixel extraction module, configured to perform pixel extraction on the image data through a preset first model to obtain a pixel matrix of the image data; A progress determination module, configured to determine the on-site progress information of the construction site based on the pixel matrix; A first anomaly determination module, configured to perform a matching process on the on-site progress information and the engineering progress data, and determine that the engineering progress data is abnormal when the matching result does not meet the matching condition.

7. The device according to claim 6, wherein, the progress determination module includes: A historical data unit, configured to acquire a historical pixel matrix, wherein the historical pixel matrix is obtained based on historical image data and stored in a target area; An error calculation unit, configured to calculate an error value between the historical pixel matrix and the pixel matrix; A progress determination unit, configured to determine the on-site progress information according to the error value.

8. The device according to claim 6, wherein, the device further includes: A type determination module, configured to determine the matrix type of the pixel matrix based on the image data before determining the on-site progress information of the construction site based on the pixel matrix; A matrix transformation module, configured to perform matrix transformation processing on the pixel matrix to obtain a first matrix when the pixel matrix is a first type of matrix; A gradient calculation module, configured to perform gradient calculation on the first matrix through a preset first operator to obtain an edge intensity matrix; An edge detection module, configured to perform edge classification on the edge intensity matrix based on a preset edge threshold to determine the edge detection information of the image data; A second anomaly determination module, configured to determine whether the image data is abnormal according to the edge detection information.

9. A computer-readable storage medium, wherein, a computer program is stored in the computer-readable storage medium, and the computer program is configured to execute the method described in any one of claims 1 to 5 when running.

10. An electronic device, including a memory and a processor, wherein, a computer program is stored in the memory, and the processor is configured to run the computer program to execute the method described in any one of claims 1 to 5.

Images