A method, system, device and readable storage medium for engineering cost prediction

Abstract

The present application provides a project cost prediction method, system, device and readable storage medium. By obtaining a grayscale image of engineering design, determining an inclination feature matrix of the grayscale image of engineering design according to a preset recognition window, and then determining the grayscale neighborhood difference value of each pixel point in the grayscale image of engineering design, all building bodies in the grayscale image of engineering design and the building coverage degree of each building body are determined according to the grayscale neighborhood difference values of all pixel points; for each building body, multiple co-occurrence skew difference values of each pixel point in the building body are determined, multiple grayscale texture-like matrices are determined according to all the co-occurrence skew difference values, and a set of material parameters of the building body is determined according to all the grayscale texture-like matrices; the material type of the building body is determined through the set of material parameters of each building body, so that the demand for various engineering materials in a project can be determined more accurately, the cost of engineering materials can be estimated more accurately, and thus the accuracy of the estimation of the cost of engineering materials can be improved.

Description

Technical Field

[0001] The present application relates to the field of engineering technology. More specifically, the present application relates to a project cost prediction method, system, device and readable storage medium. Background Art

[0002] Engineering generally refers to the actual construction stage in building and engineering projects, including the construction processes of various building, civil engineering, infrastructure and other projects. This stage involves a series of activities such as specific physical construction, project management, material procurement, human resource allocation, etc. Project cost refers to the comprehensive calculation and management process of various resources and costs in a construction project. It covers the whole process of a project from planning, design, construction to completion, including cost estimation, analysis and control of various aspects such as human resources, materials, equipment, construction methods, construction period, etc.

[0003] Currently, the commonly used methods for predicting the cost of engineering materials mainly include manual calculation, machine learning, statistical analysis, etc. However, manual calculation may have calculation errors, machine learning has poor applicability to different engineering projects and is prone to incorrect estimation, and statistical analysis is prone to errors due to incomplete data collection. Therefore, the above methods for predicting the cost of engineering materials all have the problem of low estimation accuracy. Summary of the Invention

[0004] The present application provides a project cost prediction method, system, device and readable storage medium to solve the problem of low estimation accuracy of engineering material cost.

[0005] To solve the above technical problems, the present application adopts the following technical solutions:

[0006] In the first aspect, the present application provides a project cost prediction method, specifically including the following steps:

[0007] Obtain an engineering design grayscale image, extract the tilt feature of the engineering design grayscale image according to a preset recognition window to obtain a tilt feature matrix;

[0008] Determine the gray-level neighborhood difference value of each pixel point in the engineering design grayscale image according to the tilt feature matrix, and determine all building main bodies and the building coverage degree of each building main body in the engineering design grayscale image according to the gray-level neighborhood difference values of all pixel points;

[0009] For each building main body, determine multiple co-occurrence skew difference values of each pixel point in the building main body, and determine multiple gray-level texture-like matrices according to all the co-occurrence skew difference values;

[0010] Determine the material parameter set of the building main body according to all grayscale texture-like matrices, determine the material type of the building main body through the material parameter set of each building main body, and then predict the engineering material cost based on the material type of each building main body and the building coverage degree of each building main body.

[0011] In some embodiments, obtaining the engineering design grayscale image specifically includes:

[0012] Obtain the engineering design drawing;

[0013] Convert the engineering design drawing into an engineering design grayscale image.

[0014] In some embodiments, extracting the tilt feature from the engineering design grayscale image according to the preset recognition window to obtain the tilt feature matrix specifically includes:

[0015] Determine the horizontal change rate and vertical change rate of each pixel point in the engineering design grayscale image according to the size of the recognition window;

[0016] Determine the tilt feature value of each pixel point according to the horizontal change rate and vertical change rate of each pixel point in the engineering design grayscale image, and then obtain the tilt feature matrix, wherein the tilt feature value of each pixel point is determined according to the following formula:

[0017]

[0018] Where is the tilt feature value of the th row and th column in the tilt feature matrix, is the horizontal change rate of the pixel point in the th row and th column of the engineering design grayscale image, is the vertical change rate of the pixel point in the th row and th column of the engineering design grayscale image, represents taking the arctangent value.

[0019] In some embodiments, determining the horizontal change rate and vertical change rate of each pixel point in the engineering design grayscale image according to the size of the recognition window specifically includes:

[0020] Obtain the grayscale value of each pixel point in the engineering design grayscale image;

[0021] Determine the corresponding horizontal change rate and vertical change rate of each pixel point according to the grayscale value of each pixel point in the engineering design grayscale image, wherein the horizontal change rate and vertical change rate are determined according to the following formula:

[0022]

[0023] Among them, is the horizontal change rate of the pixel at the th row and th column in the engineering design grayscale image, is the vertical change rate of the pixel at the th row and th column in the engineering design grayscale image, is the grayscale value of the pixel at the th row and th column in the engineering design grayscale image, is the grayscale value of the pixel at the th row and th column in the engineering design grayscale image, is the grayscale value of the pixel at the th row and th column in the engineering design grayscale image, is the grayscale value of the pixel at the th row and th column in the engineering design grayscale image.

[0024] In some embodiments, determining all building bodies in the engineering design grayscale image and the building coverage of each building body according to the grayscale neighborhood difference values of all pixel points specifically includes:

[0025] Determining an engineering design contour matrix according to a preset grayscale neighborhood difference threshold and all grayscale neighborhood difference values;

[0026] Determining all building bodies in the engineering design grayscale image and the building coverage of each building body according to the engineering design contour matrix.

[0027] In some embodiments, determining all building bodies in the engineering design grayscale image and the building coverage of each building body according to the engineering design contour matrix specifically includes:

[0028] Taking the points with a value of 1 in the engineering design contour matrix as the boundaries of the building bodies, and then identifying all building bodies;

[0029] Determining the number of pixel points in each building body;

[0030] Determining the area of each building body according to the number of pixel points in each building body and the scale of the engineering design grayscale image.

[0031] In some embodiments, determining the material type of each building body through the material parameter set of each building body specifically includes:

[0032] Determining multiple material deviation values of each building body according to the material parameter set of each building body and a preset plurality of material center values;

[0033] Determine the material type of each building main body according to all the material deviation values of each building main body.

[0034] In a second aspect, a project cost prediction system includes a project material cost prediction unit, and the project material cost prediction unit includes:

[0035] An inclination feature matrix determination module, configured to obtain an engineering design grayscale image, extract inclination features from the engineering design grayscale image according to a preset recognition window, and obtain an inclination feature matrix;

[0036] A building coverage determination module, configured to determine the grayscale neighborhood difference value of each pixel point in the engineering design grayscale image according to the inclination feature matrix, and determine all building main bodies in the engineering design grayscale image and the building coverage of each building main body according to the grayscale neighborhood difference values of all pixel points;

[0037] A grayscale texture-like matrix determination module, configured to, for each building main body, determine multiple co-occurrence skew difference values of each pixel point in the building main body, and determine multiple grayscale texture-like matrices according to all the co-occurrence skew difference values;

[0038] A project material cost prediction module, configured to determine the material parameter set of each building main body according to all the grayscale texture-like matrices, determine the material type of each building main body through the material parameter set of each building main body, and further predict the project material cost according to the material type of each building main body and the building coverage of each building main body.

[0039] In a third aspect, the present application provides a computer device, which includes a memory and a processor, the memory stores code, and the processor is configured to obtain the code and execute the above project cost prediction method.

[0040] In a fourth aspect, the present application provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the above project cost prediction method is implemented.

[0041] The technical solution provided by the embodiments disclosed in the present application has the following beneficial effects:

[0042] In a project cost prediction method, system, device, and readable storage medium provided by the present application, first, for the sake of aesthetics and high resolution, the engineering design drawings are generally color drawings. Converting the engineering design drawings into grayscale drawings facilitates subsequent image processing. The inclination feature values in the engineering design drawings are extracted using a preset recognition window, which can determine the direction with the smallest change in the grayscale value of each pixel point, thereby improving the accuracy of identifying the building main body contour in subsequent steps. The grayscale neighborhood difference values of each pixel point in the engineering design grayscale drawing are determined through the inclination feature matrix, and the similarity between each pixel point and its adjacent pixel points is determined to extract multiple building main bodies and the building coverage of each building main body in the engineering design grayscale drawing, facilitating subsequent prediction of engineering materials, and thus enabling a more accurate project cost to be obtained. By extracting the grayscale slope difference values in different directions of each building main body, the grayscale texture matrix containing the material texture features of the building main body is determined, and then the material texture features in the grayscale texture matrix are extracted, facilitating subsequent determination of the material types required for each building main body. Engineering design grayscale drawings usually use different filling patterns to fill the building main bodies to distinguish the material types used for the building main bodies. In the present application, by extracting the texture detail features within different building main bodies to determine the material type of each building main body, the demand for various engineering materials in the project can be determined more accurately, and the project material cost can be estimated more accurately, thereby improving the accuracy of the project material cost estimate. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 is an exemplary flowchart of a project cost prediction method according to some embodiments of the present application;

[0044] Figure 2 is an exemplary flowchart of determining all building main bodies and the building coverage of each building main body in the engineering design grayscale drawing according to some embodiments of the present application;

[0045] Figure 3 is a schematic diagram of exemplary hardware and / or software of a project material cost prediction unit according to some embodiments of the present application;

[0046] Figure 4 is a schematic diagram of the structure of a computer device for implementing the project cost prediction method according to some embodiments of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0047] The core of this application provides a project cost prediction method, system, device, and readable storage medium. By obtaining the engineering design grayscale image, determining the tilt feature matrix of the engineering design grayscale image according to a preset recognition window, and then determining the grayscale neighborhood difference value of each pixel point in the engineering design grayscale image, all building entities in the engineering design grayscale image and the building coverage degree of each building entity are determined based on the grayscale neighborhood difference values of all pixel points; for each building entity, multiple co-occurrence skew difference values of each pixel point within the building entity are determined, multiple grayscale texture-like matrices are determined based on all the co-occurrence skew difference values, and the material parameter set of the building entity is determined based on all the grayscale texture-like matrices; the material type of the building entity is determined through the material parameter set of each building entity, so that the demand for various engineering materials in the project can be determined more accurately, and the cost of engineering materials can be estimated more accurately, thereby improving the accuracy of engineering material cost estimation.

[0048] To better understand the above technical solution, the following will detail the above technical solution in combination with the specification drawings and specific implementation manners. Refer to Figure 1 FIG. , which is an exemplary flowchart of a project cost prediction method shown in some embodiments of the present application. The project cost prediction method 100 mainly includes the following steps:

[0049] In step 101, obtain the engineering design grayscale image, and perform tilt feature extraction on the engineering design grayscale image according to a preset recognition window to obtain a tilt feature matrix.

[0050] In some embodiments, obtaining the engineering design grayscale image can be implemented by the following steps:

[0051] Obtain the engineering design drawing;

[0052] Convert the engineering design drawing into an engineering design grayscale image, where the engineering design grayscale image can be determined according to the following formula:

[0053]

[0054] where is the grayscale value of the pixel point in the th row and th column of the engineering design grayscale image, is the red component value of the pixel point in the th row and th column of the engineering design drawing, is the green component value of the pixel point in the th row and th column of the engineering design drawing, is the blue component value of the pixel point in the th row and th column of the engineering design drawing.

[0055] It should be noted that the engineering design drawing in this embodiment may be a CAD drawing containing engineering project drawings. In other embodiments, it may also be other drawings containing engineering project drawings, which are not limited here.

[0056] In some embodiments, the extraction of the tilt feature of the engineering design grayscale image according to a preset recognition window to obtain the tilt feature matrix can be implemented by the following steps:

[0057] Determine the horizontal change rate and vertical change rate of each pixel point in the engineering design grayscale image according to the size of the recognition window;

[0058] Determine the tilt feature value of each pixel point in the engineering design grayscale image according to the horizontal change rate and vertical change rate of each pixel point, and then obtain the tilt feature matrix. Among them, the tilt feature value of each pixel point can be determined according to the following formula:

[0059]

[0060] Where is the tilt feature value of the pixel point in the row and column, is the horizontal change rate of the pixel point in the row and column, is the vertical change rate of the pixel point in the row and column, represents taking the arctangent value.

[0061] It should be noted that the tilt feature value in this application is an angle value. The tilt feature value of a pixel point is used to reflect the change direction of the grayscale value of the pixel point. For example, if the tilt feature value of a pixel point is 30°, it means that the change degree of the grayscale value of the pixel point in this direction is the smallest, that is, the other pixel points in this direction and this pixel point are points on the same line, and this direction may be the tangent direction of the curve of the edge of a building main body at this point.

[0062] In some embodiments, the determination of the horizontal change rate and vertical change rate of each pixel point in the engineering design grayscale image according to the size of the recognition window can be implemented by the following steps:

[0063] Obtain the grayscale value of each pixel point in the engineering design grayscale image;

[0064] Determine the corresponding horizontal change rate and vertical change rate of each pixel point according to the grayscale value of each pixel point in the engineering design grayscale image, where the horizontal change rate and vertical change rate can be determined according to the following formula:

[0065]

[0066] Among them, is the horizontal change rate of the pixel at the -th row and the -th column, is the vertical change rate of the pixel at the -th row and the -th column, is the grayscale value of the pixel at the -th row and the -th column, is the grayscale value of the pixel at the -th row and the -th column, The grayscale value of the pixel at the -th row and the -th column, is the grayscale value of the pixel at the -th row and the -th column, is the size of the recognition window.

[0067] In specific implementation, the recognition window can be a square window with equal length and width and an odd number, and the minimum size of the recognition window is . The smaller the recognition window, the higher the accuracy of feature extraction for each pixel in the engineering design grayscale image.

[0068] It should be noted that for the sake of beauty and high resolution, the engineering design drawing is generally a color drawing. After converting the engineering design drawing into a grayscale image, it is convenient for subsequent image processing; by extracting the inclination feature value in the engineering design drawing with a preset recognition window, the direction with the smallest change in the grayscale value of each pixel can be determined, thereby improving the accuracy of recognizing the outline of the building main body in the subsequent steps.

[0069] In step 102, according to the inclination feature matrix, determine the grayscale neighborhood difference value of each pixel in the engineering design grayscale image, and determine all building main bodies and the building coverage degree of each building main body in the engineering design grayscale image according to the grayscale neighborhood difference values of all pixels.

[0070] In some embodiments, determining the grayscale neighborhood difference value of each pixel in the engineering design grayscale image according to the inclination feature matrix can be implemented by the following steps:

[0071] Obtain the inclination feature matrix;

[0072] Obtain the horizontal change rate and vertical change rate of each pixel in the engineering design grayscale image;

[0073] Determine the gray - level neighborhood difference value of each pixel point in the engineering design gray - level image according to the tilt feature matrix, the horizontal change rate and the vertical change rate of each pixel point in the engineering design gray - level image, where the gray - level neighborhood difference value can be determined according to the following formula:

[0074]

[0075] Wherein, is the gray - level neighborhood difference value of the pixel point in the th row and th column of the engineering design gray - level image, is the tilt feature value of the th row and th column in the tilt feature matrix, is the tilt feature value of the th row and th column in the tilt feature matrix, is the tilt feature value of the th row and th column in the tilt feature matrix, is the tilt feature value of the th row and th column in the tilt feature matrix, is the vertical change rate of the pixel point in the th row and th column of the engineering design gray - level image, is the vertical change rate of the pixel point in the th row and th column of the engineering design gray - level image, is the horizontal change rate of the pixel point in the th row and th column of the engineering design gray - level image, is the horizontal change rate of the pixel point in the th row and th column of the engineering design gray - level image.

[0076] It should be noted that in this application, the gray - level neighborhood difference value reflects the similarity between the corresponding pixel point and its surrounding adjacent pixel points. The larger the gray - level neighborhood difference value, the greater the difference between the corresponding pixel point and its surrounding pixel points, and the more likely this pixel point is the boundary between two regions in the engineering design gray - level image.

[0077] In some embodiments, determining all building main bodies in the engineering design gray - level image and the building coverage degree of each building main body according to the gray - level neighborhood difference values of all pixel points can be implemented by the following steps:

[0078] Determine the engineering design contour matrix according to a preset gray - level neighborhood difference threshold and all the gray - level neighborhood difference values;

[0079] Determine all building bodies in the engineering design grayscale image and the building coverage degree of each building body according to the engineering design contour matrix.

[0080] In some embodiments, the engineering design contour matrix is determined according to a preset grayscale neighborhood difference threshold and all grayscale neighborhood difference values. Specifically, in implementation, by comparing the grayscale neighborhood difference value of each pixel point in the engineering design grayscale image with the grayscale neighborhood difference threshold, the engineering design contour value of the pixel point whose grayscale neighborhood difference value is greater than the grayscale neighborhood difference threshold is set to 1, and the engineering design contour value of the pixel point whose grayscale neighborhood difference value is less than the grayscale neighborhood difference threshold is set to 0, so as to obtain the engineering design contour matrix.

[0081] It should be noted that in this application, the engineering design contour matrix is a matrix that only contains the boundary information of each closed image in the engineering design grayscale image determined according to each grayscale neighborhood difference value in the engineering design grayscale image.

[0082] In some embodiments, determining all building bodies in the engineering design grayscale image and the building coverage degree of each building body according to the engineering design contour matrix can be implemented by the following steps:

[0083] Take the points with a value of 1 in the engineering design contour matrix as the boundaries of the building bodies, and then identify all building bodies;

[0084] Determine the number of pixel points in each building body;

[0085] Determine the area of each building body according to the number of pixel points in each building body and the scale of the engineering design grayscale image.

[0086] Specifically, in implementation, connect the adjacent points with an engineering design contour value of 1 in the engineering design contour matrix, and then obtain a plurality of closed figures. Each closed figure is a building body, and multiply the number of pixel points in each building body by the scale of the engineering design grayscale image, and take the obtained value as the building coverage degree of the building body.

[0087] It should be noted that in this application, the building coverage degree refers to the size of the coverage area of the corresponding building body in the engineering design grayscale image.

[0088] In addition, it should be noted that in this application, the grayscale neighborhood difference value of each pixel point in the engineering design grayscale image is determined through the tilt feature matrix, and the similarity between each pixel point and its adjacent pixel points is determined, so as to extract a plurality of building bodies in the engineering design grayscale image and the building coverage degree of each building body, which is convenient for subsequent estimation of engineering materials, and thus a more accurate project cost can be obtained.

[0089] In step 103, for each building body, determine the multiple co-occurrence skew differences of each pixel point within the building body, and determine multiple gray-scale texture-like matrices based on all the co-occurrence skew differences.

[0090] In some embodiments, for each building body, determine the multiple co-occurrence skew differences of each pixel point within the building body, where the co-occurrence skew differences can be determined according to the following formula:

[0091]

[0092] where is the first co-occurrence skew difference of the pixel point in the th row and th column of the engineering design grayscale image, is the second co-occurrence skew difference of the pixel point in the th row and th column of the engineering design grayscale image, is the third co-occurrence skew difference of the pixel point in the th row and th column of the engineering design grayscale image, is the fourth co-occurrence skew difference of the pixel point in the th row and th column of the engineering design grayscale image, is the grayscale value of the pixel point in the th row and th column of the engineering design grayscale image, is the grayscale value of the pixel point in the th row and th column of the engineering design grayscale image, is the grayscale value of the pixel point in the th row and th column of the engineering design grayscale image, is the grayscale value of the pixel point in the th row and th column of the engineering design grayscale image, is the grayscale value of the pixel point in the th row and th column of the engineering design grayscale image.

[0093] It should be noted that the co-occurrence skew difference of a pixel point in this application is a parameter used to measure the degree of gray-scale change of the pixel point in the direction corresponding to the co-occurrence skew difference.

[0094] In some embodiments, determining multiple gray-scale texture-like matrices based on all the co-occurrence skew differences can be implemented by the following steps:

[0095] Obtain the grayscale value and multiple co-occurrence skew differences of each pixel point within each building body;

[0096] Determine multiple gray-scale texture-like matrices of each building body based on the gray-scale values of all pixel points and all co-occurrence slope differences within each building body. Among them, each gray-scale texture-like matrix can be determined according to the following formula:

[0097]

[0098] Among them, is the gray-scale co-occurrence value at the th row and th column of the th gray-scale texture-like matrix of the th building body. represents the total number of pixel points with a gray-scale value of and a co-occurrence slope difference of in the th building body.

[0099] It should be noted that in this application, the gray-scale texture-like matrix is a matrix composed of multiple gray-scale co-occurrence values. Each gray-scale co-occurrence value represents the appearance frequency of pixel points with equal gray-scale change degrees in the corresponding pixel point neighborhood, that is, pixel points with similar textures.

[0100] In addition, it should be noted that in this application, by extracting the gray-scale slope differences in different directions of each building body, the gray-scale texture-like matrix containing the material texture characteristics of the building body is determined, which is convenient for subsequent determination of the material types required for each building body.

[0101] In step 104, determine the material parameter set of each building body according to all the gray-scale texture-like matrices of each building body. Determine the material type of each building body through the material parameter set of each building body, and then predict the engineering material cost based on the material type of each building body and the building coverage degree of each building body.

[0102] In some embodiments, determine the material parameter set of each building body according to all the gray-scale texture-like matrices of each building body. Specifically, when implemented, the material parameter set can be determined according to the following formula:

[0103]

[0104] is the th material parameter in the material parameter set of the th building body. is the gray-scale co-occurrence value at the th row and th column of the th row and th column of the ​

[0105] It should be noted that the material parameter set described in this application is a parameter set used to identify the material categories of the corresponding building main bodies, and each material parameter in the material parameter set is a material texture feature extracted from the corresponding direction in the building main body.

[0106] In some embodiments, determining the material type of each building main body through the material parameter set of each building main body can be achieved by the following steps:

[0107] Determine multiple material deviation values of each building main body according to the material parameter set of each building main body and a preset multiple of material central values;

[0108] Determine the material type of each building main body according to all the material deviation values of each building main body.

[0109] When specifically implemented, the material deviation value of each building main body can be determined according to the following formula:

[0110]

[0111] is the material deviation value between the material parameter set of the th building main body and the material central value of the th material type, is the material central value of the th material type, is the th material parameter in the material parameter set of the th building main body.

[0112] It should be noted that the material central value is preset according to historical experimental data. Different material central values correspond to different material types. The material deviation value refers to the degree of difference between the corresponding building main body and the corresponding material type. The smaller the material deviation value, the more likely the corresponding building main body is the corresponding material type.

[0113] When specifically implemented, the material type corresponding to the smallest material deviation value can be used as the material type of the building main body, and then the material type of each building main body can be determined.

[0114] In some embodiments, predicting the engineering material cost according to the material type of each building main body and the building coverage of each building main body can be achieved by the following method:

[0115] Obtain the elevation of the engineering design drawing;

[0116] Obtain the building coverage and the corresponding material type of each building main body;

[0117] Obtain the price data of the engineering materials of each material type;

[0118] Determine the project material cost based on the elevation of the project design drawing, the building coverage of each building main body, and the price data of the project materials corresponding to the material types, where the project material cost can be determined according to the following formula:

[0119]

[0120] Wherein, is the project material cost, is the elevation of the project design drawing, is the total number of building main bodies, is the th building coverage of the building main body, is the th price of the project materials corresponding to the material type of the building main body. In this application, the price of the project materials can be selected within the price fluctuation range of the project materials. For example, the average price of the project materials over a period of time can be used as the price of the project materials, and no specific limitation is made here.

[0121] It should be noted that engineering design grayscale maps usually fill building main bodies with different filling patterns to distinguish the material types used for the building main bodies. For example, the building main body materials mainly include concrete, solid bricks, wood, etc., and the texture detail features of concrete, solid bricks, and wood in the engineering design grayscale map are different. In this application, the texture detail features within different building main bodies are extracted to determine the material type of each building main body, and finally the prediction of the project material cost is realized, that is, a relatively accurate prediction of the project material cost is realized through an image processing method.

[0122] In addition, on the other hand of this application, in some embodiments, this application provides a project cost prediction system, which includes a project material cost prediction unit. Refer to Figure 3 , this figure is a schematic diagram of the exemplary hardware and / or software of the project material cost prediction unit shown in some embodiments of this application. The project material cost prediction unit 300 includes: an inclination feature matrix determination module 301, a building coverage determination module 302, a grayscale texture matrix determination module 303, and a project material cost prediction module 304, which are described as follows:

[0123] The inclination feature matrix determination module 301. In this application, the inclination feature matrix determination module 301 is mainly used to obtain the engineering design grayscale map, extract the inclination features of the engineering design grayscale map according to a preset recognition window, and obtain an inclination feature matrix;

[0124] The building coverage determination module 302. In the present application, the building coverage determination module 302 mainly determines the gray-level neighborhood difference value of each pixel point in the engineering design gray-scale image according to the inclination feature matrix, and determines all building main bodies in the engineering design gray-scale image and the building coverage of each building main body according to the gray-level neighborhood difference values of all pixel points;

[0125] The material parameter set determination module 303. In the present application, the material parameter set determination module 303 is mainly used to determine, for each building main body, multiple co-occurrence inclination difference values of each pixel point within the building main body, and determine multiple gray-scale texture-like matrices according to all the co-occurrence inclination difference values;

[0126] The engineering material cost prediction module 304. In the present application, the engineering material cost prediction module 304 is mainly used to determine the material parameter set of the building main body according to all the gray-scale texture-like matrices, determine the material type of the building main body through the material parameter set of each building main body, and then predict the engineering material cost based on the material type of each building main body and the building coverage of each building main body.

[0127] In addition, the present application also provides a computer device, which includes a memory and a processor. The memory stores code, and the processor is configured to obtain the code and execute the above-mentioned engineering cost prediction method.

[0128] In some embodiments, refer to Figure 4 , this figure is a schematic structural diagram of a computer device for implementing the engineering cost prediction method according to some embodiments of the present application. The engineering cost prediction method in the above embodiments can be implemented by Figure 4 the computer device shown. The computer device 400 includes at least one processor 401, a communication bus 402, a memory 403, and at least one communication interface 404.

[0129] The processor 401 can be a general-purpose central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more for controlling the execution of the engineering cost prediction method in the present application.

[0130] The communication bus 402 may include a path for transmitting information between the above components.

[0131] The memory 403 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or may also be an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disks or other magnetic storage devices, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 403 may exist independently and be connected to the processor 401 through the communication bus 402. The memory 403 may also be integrated with the processor 401.

[0132] Among them, the memory 403 is used to store the program code for executing the solution of this application and is controlled by the processor 401 for execution. The processor 401 is used to execute the program code stored in the memory 403. The program code may include one or more software modules. The engineering cost prediction method in the above embodiments may be implemented by one or more software modules in the program code in the processor 401 and the memory 403.

[0133] The communication interface 404 uses any device such as a transceiver to communicate with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.

[0134] In a specific implementation, as an embodiment, the computer device may include multiple processors, and each of these processors may be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor. Here, the processor may refer to one or more devices, circuits, and / or processing cores for processing data (such as computer program instructions).

[0135] The above-mentioned computer device may be a general-purpose computer device or a special-purpose computer device. In a specific implementation, the computer device may be a desktop computer, a portable computer, a network server, a personal digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device or an embedded device. The embodiment of the present application does not limit the type of computer device.

[0136] In addition, the present application also provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the above-mentioned project cost prediction method is implemented.

[0137] In summary, in the project cost prediction method, system, device and readable storage medium disclosed in the embodiments of the present application, firstly, the project design drawing is generally a color drawing for the sake of beauty and high resolution, and the project design drawing is converted into a grayscale image to facilitate subsequent image processing; the tilt feature value in the project design drawing is extracted using a preset recognition window, and the direction in which the grayscale value of each pixel point changes the least can be determined, thereby improving the accuracy of identifying the outline of the building body in the subsequent steps; the grayscale neighbor difference value of each pixel point in the project design grayscale image is determined by the tilt feature matrix, and the similarity between each pixel point and the adjacent pixel points is determined, thereby extracting multiple building bodies in the project design grayscale image and the building coverage of each building body, which is convenient for the subsequent prediction of engineering materials. The grayscale slope difference values in different directions of each building body are extracted to determine the grayscale texture matrix containing the material texture features of the building body, and then the material texture features in the grayscale texture matrix are extracted to facilitate the subsequent determination of the material type required for each building body. The engineering design grayscale map usually uses different filling patterns to fill the building body to distinguish the material type used by the building body. In this application, the material type of each building body is determined by extracting the texture detail features in different building bodies, which can more accurately determine the demand for various engineering materials in the engineering project, and can more accurately estimate the cost of engineering materials, thereby improving the accuracy of the engineering material cost estimate.

[0138] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0139] Obviously, those skilled in the art can make various changes and modifications to this application without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalent technologies, this application is also intended to include these modifications and variations.

Claims

1. A method for predicting project cost, characterized in that, Including: Obtain the engineering design grayscale image, extract the tilt features of the engineering design grayscale image according to a preset recognition window, and obtain a tilt feature matrix; Determine the grayscale neighborhood difference value of each pixel point in the engineering design grayscale image according to the tilt feature matrix, and determine all building main bodies in the engineering design grayscale image and the building coverage degree of each building main body according to the grayscale neighborhood difference values of all pixel points; For each building main body, determine multiple co-occurrence skew difference values of each pixel point within the building main body, and determine multiple grayscale texture-like matrices according to all the co-occurrence skew difference values; Determine the material parameter set of the building main body according to all the grayscale texture-like matrices, determine the material type of the building main body through the material parameter set of each building main body, and further predict the engineering material cost based on the material type of each building main body and the building coverage degree of each building main body; Extracting the tilt features of the engineering design grayscale image according to a preset recognition window to obtain a tilt feature matrix specifically includes: Determine the horizontal change rate and vertical change rate of each pixel point in the engineering design grayscale image according to the size of the recognition window; Determine the tilt feature value of the pixel point according to the horizontal change rate and vertical change rate of each pixel point in the engineering design grayscale image, and then obtain a tilt feature matrix, where the tilt feature value of each pixel point is determined according to the following formula: Among them, is the tilt feature value of the th row and th column in the tilt feature matrix, is the horizontal change rate of the pixel at the th row and th column in the engineering design grayscale image, is the vertical change rate of the pixel at the th row and th column in the engineering design grayscale image, represents taking the arctangent value; The grayscale neighborhood difference value is determined according to the following formula: Among them, is the gray-level neighborhood difference value of the pixel at the th row and the th column in the engineering design grayscale image, is the tilt feature value at the th row and the th column in the tilt feature matrix, is the tilt feature value at the th row and the th column in the tilt feature matrix, is the tilt feature value at the th row and the th column in the tilt feature matrix, is the tilt feature value at the th row and the th column in the tilt feature matrix, is the longitudinal change rate of the pixel at the th row and the th column in the engineering design grayscale image, is the longitudinal change rate of the pixel at the th row and the th column in the engineering design grayscale image, is the transverse change rate of the pixel at the th row and the th column in the engineering design grayscale image, is the transverse change rate of the pixel at the th row and the th column in the engineering design grayscale image; The grayscale neighborhood difference value reflects the similarity between the corresponding pixel point and the surrounding adjacent pixel points. The larger the grayscale neighborhood difference value, the greater the difference between the corresponding pixel point and the surrounding pixel points, and the more likely the pixel point is the boundary between two regions in the engineering design grayscale image; Determining all building main bodies in the engineering design grayscale image and the building coverage degree of each building main body according to the grayscale neighborhood difference values of all pixel points specifically includes: Determine an engineering design contour matrix according to a preset grayscale neighborhood difference threshold and all the grayscale neighborhood difference values; Determine all building main bodies in the engineering design grayscale image and the building coverage degree of each building main body according to the engineering design contour matrix; Determining all building main bodies in the engineering design grayscale image and the building coverage degree of each building main body according to the engineering design contour matrix specifically includes: Take the points with a value of 1 in the engineering design contour matrix as the boundaries of the building main bodies, and then identify all building main bodies; Determine the number of pixel points within each building main body; Determine the area of the building main body according to the number of pixel points within each building main body and the scale of the engineering design grayscale image; The building coverage degree refers to the size of the coverage area of the corresponding building main body in the engineering design grayscale image; For each building main body, determine multiple co-occurrence skew difference values of each pixel point within the building main body, where the co-occurrence skew difference value is determined according to the following formula: Wherein, is the first co-occurrence diagonal difference value of the pixel at the th row and the th column in the engineering design grayscale image; is the second co-occurrence diagonal difference value of the pixel at the th row and the th column in the engineering design grayscale image; is the third co-occurrence diagonal difference value of the pixel at the th row and the th column in the engineering design grayscale image; is the fourth co-occurrence diagonal difference value of the pixel at the th row and the th column in the engineering design grayscale image; is the grayscale value of the pixel at the th row and the th column in the engineering design grayscale image; is the grayscale value of the pixel at the th row and the th column in the engineering design grayscale image; is the grayscale value of the pixel at the th row and the th column in the engineering design grayscale image; is the grayscale value of the pixel at the th row and the th column in the engineering design grayscale image; is the grayscale value of the pixel at the th row and the th column in the engineering design grayscale image; The co-occurrence skew difference value of a pixel point is a parameter used to measure the degree of grayscale change of the pixel point in the direction corresponding to the co-occurrence skew difference value; Determining multiple grayscale texture-like matrices according to all the co-occurrence skew difference values is implemented by the following steps: Obtain the grayscale value and multiple co-occurrence skew difference values of each pixel point within each building main body; Determine multiple gray - scale texture - like matrices of each building body according to the gray - scale values of all pixel points and all co - occurrence diagonal differences within each building body, where each gray - scale texture - like matrix is determined according to the following formula: Among them, is the th gray-level co-occurrence value of the th gray-level similar pattern matrix of the th row and th column of the th building body; represents the total number of pixels with a gray level of and a co-occurrence skew difference of in the th building body. The gray - scale texture - like matrix is a matrix composed of multiple gray - scale co - occurrence values. Each gray - scale co - occurrence value represents the occurrence frequency of pixel points with equal gray - scale change degrees within the neighborhood of the corresponding pixel point, that is, pixel points with similar textures; The set of material parameters is determined according to the following formula: For the th material parameter in the material parameter set of the th building main body, For the th gray-level co-occurrence value in the th gray-level pseudo-pattern matrix of the th row and th column of the The set of material parameters is a parameter set used to distinguish the material categories of the corresponding building bodies. Each material parameter in the set of material parameters is a material texture feature extracted from the building body in the corresponding direction.

2. The method according to claim 1, wherein Obtaining the engineering design gray - scale image specifically includes: Obtain the engineering design drawing; Convert the engineering design drawing into an engineering design gray - scale image.

3. The method according to claim 1, characterized in that, Determine the horizontal change rate and vertical change rate of each pixel point in the engineering design gray - scale image according to the size of the recognition window, which specifically includes: Obtain the gray - scale value of each pixel point in the engineering design gray - scale image; Determine the corresponding horizontal change rate and vertical change rate of each pixel point according to the gray - scale value of each pixel point in the engineering design gray - scale image, where the horizontal change rate and vertical change rate are determined according to the following formula: Among them, is the horizontal change rate of the pixel at the -th row and -th column in the engineering design grayscale image, is the vertical change rate of the pixel at the -th row and -th column in the engineering design grayscale image, is the grayscale value of the pixel at the -th row and -th column in the engineering design grayscale image, is the grayscale value of the pixel at the -th row and -th column in the engineering design grayscale image, is the grayscale value of the pixel at the -th row and -th column in the engineering design grayscale image, is the grayscale value of the pixel at the -th row and -th column in the engineering design grayscale image.

4. The method according to claim 1, wherein Determine the material type of each building body through the set of material parameters of each building body, which specifically includes: Determine multiple material deviation values of each building body according to the set of material parameters of each building body and multiple preset material central values; Determine the material type of each building body according to all the material deviation values of each building body.

5. A project cost prediction system, characterized in that, It includes an engineering material cost prediction unit, and the engineering material cost prediction unit includes: An inclination feature matrix determination module, which is used to obtain the engineering design gray - scale image, extract the inclination features of the engineering design gray - scale image according to a preset recognition window, and obtain an inclination feature matrix; A building coverage determination module, which is used to determine the gray - scale neighborhood difference value of each pixel point in the engineering design gray - scale image according to the inclination feature matrix, and determine all building bodies in the engineering design gray - scale image and the building coverage of each building body according to the gray - scale neighborhood difference values of all pixel points; A gray - scale texture - like matrix determination module, which is used to, for each building body, determine multiple co - occurrence diagonal differences of each pixel point within the building body, and determine multiple gray - scale texture - like matrices according to all the co - occurrence diagonal differences; An engineering material cost prediction module, which is used to determine the set of material parameters of each building body according to all the gray - scale texture - like matrices, determine the material type of each building body through the set of material parameters of each building body, and then predict the engineering material cost based on the material type of each building body and the building coverage of each building body; Extract the inclination features of the engineering design gray - scale image according to a preset recognition window to obtain an inclination feature matrix, which specifically includes: Determine the horizontal change rate and vertical change rate of each pixel point in the engineering design gray - scale image according to the size of the recognition window; Determine the inclination feature value of each pixel point according to the horizontal change rate and vertical change rate of each pixel point in the engineering design gray - scale image, and then obtain an inclination feature matrix, where the inclination feature value of each pixel point is determined according to the following formula: Among them, is the tilt feature value at the -th row and -th column of the tilt feature matrix, is the horizontal change rate of the pixel at the -th row and -th column of the engineering design grayscale image, is the vertical change rate of the pixel at the -th row and -th column of the engineering design grayscale image, represents taking the arctangent value; The grayscale neighborhood difference value is determined according to the following formula: Among them, is the gray-level adjacent difference value of the pixel at the th row and th column in the engineering design grayscale image, is the tilt feature value at the th row and th column in the tilt feature matrix, is the tilt feature value at the th row and th column in the tilt feature matrix, is the tilt feature value at the th row and th column in the tilt feature matrix, is the tilt feature value at the th row and th column in the tilt feature matrix, is the longitudinal change rate of the pixel at the th row and th column in the engineering design grayscale image, is the longitudinal change rate of the pixel at the th row and th column in the engineering design grayscale image, is the transverse change rate of the pixel at the th row and th column in the engineering design grayscale image, and is the transverse change rate of the pixel at the th row and th column in the engineering design grayscale image; The grayscale neighborhood difference value reflects the similarity between the corresponding pixel point and the surrounding adjacent pixel points. The larger the grayscale neighborhood difference value, the greater the difference between the corresponding pixel point and the surrounding pixel points, and the more likely this pixel point is the boundary between two regions in the engineering design grayscale image; Determining all building bodies in the engineering design grayscale image and the building coverage degree of each building body according to the grayscale neighborhood difference values of all pixel points specifically includes: Determining an engineering design contour matrix according to a preset grayscale neighborhood difference threshold and all grayscale neighborhood difference values; Determining all building bodies in the engineering design grayscale image and the building coverage degree of each building body according to the engineering design contour matrix; Determining all building bodies in the engineering design grayscale image and the building coverage degree of each building body according to the engineering design contour matrix specifically includes: Taking the points with a value of 1 in the engineering design contour matrix as the boundaries of the building bodies, and then identifying all building bodies; Determining the number of pixel points in each building body; Determining the area of each building body according to the number of pixel points in each building body and the scale of the engineering design grayscale image; The building coverage degree refers to the size of the coverage area of the corresponding building body in the engineering design grayscale image; For each building body, determining multiple co-occurrence slope difference values of each pixel point in the building body, where the co-occurrence slope difference value is determined according to the following formula: wherein, is the first co-occurrence diagonal difference value of the pixel at the -th row and the -th column in the engineering design grayscale image, is the second co-occurrence diagonal difference value of the pixel at the -th row and the -th column in the engineering design grayscale image, is the third co-occurrence diagonal difference value of the pixel at the -th row and the -th column in the engineering design grayscale image, is the fourth co-occurrence diagonal difference value of the pixel at the -th row and the -th column in the engineering design grayscale image, is the grayscale value of the pixel at the -th row and the -th column in the engineering design grayscale image, is the grayscale value of the pixel at the -th row and the -th column in the engineering design grayscale image, is the grayscale value of the pixel at the -th row and the -th column in the engineering design grayscale image, is the grayscale value of the pixel at the -th row and the -th column in the engineering design grayscale image, is the grayscale value of the pixel at the -th row and the -th column in the engineering design grayscale image; The co-occurrence slope difference value of a pixel point is a parameter used to measure the degree of grayscale change of the pixel point in the direction corresponding to the co-occurrence slope difference value; Determining multiple grayscale texture-like matrices according to all co-occurrence slope difference values is implemented by the following steps: Obtaining the grayscale value and multiple co-occurrence slope difference values of each pixel point in each building body; Determining multiple grayscale texture-like matrices of each building body according to the grayscale values and all co-occurrence slope difference values of all pixel points in each building body, where each grayscale texture-like matrix is determined according to the following formula: Among them, is the th gray co-occurrence value in the th row and th column of the th gray co-occurrence matrix of the th building body; represents the total number of pixel points with a gray value of and a co-occurrence skew difference value of in the th building body. The grayscale texture-like matrix is a matrix composed of multiple grayscale co-occurrence values, and each grayscale co-occurrence value represents the occurrence frequency of pixel points with equal grayscale change degree, that is, similar texture, in the neighborhood of the corresponding pixel point; The material parameter set is determined according to the following formula: For the th material parameter in the set of material parameters of the th building body, For the th gray-scale texture-like matrix of the th building body, the gray-level co-occurrence value at the th row and the th column; The material parameter set is a parameter set used to identify the material category of the corresponding building body, and each material parameter in the material parameter set is the material texture feature extracted from the corresponding direction in the building body; 6. A computer device, characterized in that, The computer device includes a memory and a processor. The memory stores code, and the processor is configured to obtain the code and execute the engineering cost prediction method according to any one of claims 1 to 4.

7. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the engineering cost prediction method according to any one of claims 1 to 4.

Images