Data processing method, device, equipment and medium for building decoration construction
Through artificial intelligence and machine vision technology, real-time comparison in the building decoration industry is solved, and real-time deviation detection and rectification are realized, and construction management efficiency is improved.
Patent Information
- Application Number
- CN202410047439.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-01-12
- Publication Date
- 2024-11-22
- Estimated Expiration
- 2044-01-12
AI Technical Summary
In the architectural decoration industry, the real-time comparison between the result image and the planned image after the decoration is completed is poor, and the accuracy of the comparison results is low, making it difficult to make timely rectification.
Using artificial intelligence technology and machine vision technology, the actual construction data and building planning data are obtained through preset time configuration, the effect and progress comparison is performed, deviation reminder signals are generated, and the pre-trained model is used to predict future trends and identify abnormal behaviors. , improve the real-time and accuracy of comparison.
Real-time deviation detection and rectification in building decoration construction has been realized, the rectification cost has been reduced, and the accuracy of comparison results and construction management efficiency have been improved.
Smart Images

Figure CN117910700B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a data processing method, device, equipment and medium for building decoration construction. Background Art
[0002] Currently in the building decoration industry, after the decoration is completed, the decoration differences are determined based on the comparison of the result image and the planned image. This has poor real-time performance, is not conducive to timely rectification, and is based on simple image comparison, and the accuracy of the comparison results is low. Summary of the invention
[0003] Based on this, it is necessary to address the technical problems that in the existing technology in the building decoration industry, after the decoration is completed, the decoration differences are determined based on the comparison of the result image and the planned image, which has poor real-time performance and is not conducive to timely rectification, and the accuracy of the comparison results is low based on simple image comparison. A data processing method, device, equipment and medium for building decoration construction are proposed.
[0004] In a first aspect, a data processing method for building decoration construction is provided, the method comprising:
[0005] According to the preset time configuration, the actual construction data and building planning data corresponding to the target building decoration object are obtained;
[0006] Based on artificial intelligence technology and machine vision technology, a deviation comparison is performed according to the actual construction data and the building planning data to obtain a target comparison result, wherein the target comparison result includes an effect comparison result and / or a progress comparison result;
[0007] A deviation warning signal is generated according to the target comparison result.
[0008] Furthermore, the step of performing deviation comparison based on the actual construction data and the building planning data to obtain a target comparison result based on artificial intelligence technology and machine vision technology includes:
[0009] Based on the preset effect extraction rules, the construction effect data is determined according to the actual construction data;
[0010] Based on the effect extraction rule, and according to the building planning data, determining planning effect data;
[0011] Based on a preset first splicing rule, the construction effect data and the planning effect data are spliced to obtain first spliced data;
[0012] The first spliced data is input into a pre-trained effect comparison model for deviation comparison to obtain an effect comparison result in the target comparison result, wherein the effect comparison model is a model trained based on artificial intelligence technology, machine vision technology and image matching technology.
[0013] Furthermore, the step of performing deviation comparison based on the actual construction data and the building planning data to obtain a target comparison result based on artificial intelligence technology and machine vision technology also includes:
[0014] Based on the preset progress extraction rules, the construction progress data is determined according to the actual construction data;
[0015] Based on the progress extraction rule, and according to the building planning data, determining planning progress data;
[0016] Based on a preset second splicing rule, the construction progress data and the planning progress data are spliced to obtain second spliced data;
[0017] Inputting the second spliced data into a pre-trained progress prediction model for classification prediction to obtain a first prediction vector, wherein the progress prediction model is a model trained based on artificial intelligence technology;
[0018] A progress comparison result of the target comparison result is determined according to the first prediction vector and the planning progress data.
[0019] Furthermore, after the step of performing deviation comparison based on the actual construction data and the building planning data based on artificial intelligence technology and machine vision technology to obtain a target comparison result, the method further includes:
[0020] Extracting effect image pairs at each viewing angle according to the construction effect data and the planning effect data;
[0021] Based on the image matching technology, searching for deviation points of each effect image pair to obtain image pair deviation point data;
[0022] Based on a preset marking rule, according to the deviation point data of the image pair, marking the deviation points of the effect image pair corresponding to the deviation point data of the image pair to obtain a marked image pair;
[0023] An interface display is performed according to each of the marked image pairs, the effect comparison results and the progress comparison results to obtain a target interface, wherein a first area in the target interface is generated based on effect display rules, each of the marked image pairs and the effect comparison results, and a second area in the target interface is generated based on progress display rules and the progress comparison results, and an effect deviation comparison diagram corresponding to each of the marked image pairs is displayed in the first area.
[0024] Furthermore, the method further comprises:
[0025] Inputting the planning effect data and each of the construction effect data corresponding to the target building decoration object into a pre-trained effect trend prediction model to perform future trend prediction, and obtain an effect trend prediction result;
[0026] The planning progress data and each of the construction progress data corresponding to the target building decoration object are input into a pre-trained progress trend prediction model to perform future trend prediction to obtain a progress trend prediction result.
[0027] Furthermore, the images in the actual construction data are images processed by privacy computing technology, wherein the privacy computing technology includes: one or more of stickman generation technology and cartoon man generation technology.
[0028] Furthermore, after the step of acquiring the actual construction data and building planning data corresponding to the target building decoration object according to the preset time configuration, it also includes:
[0029] Based on the target detection technology, extracting the behavior characteristic data of each construction worker according to the actual construction data;
[0030] Inputting the behavior feature data into a pre-trained abnormal behavior prediction model for classification prediction to obtain a second prediction vector;
[0031] Taking the vector element whose value in the second prediction vector is greater than a preset probability as the target element;
[0032] The behavior category corresponding to each target element corresponding to the behavior feature data is taken as an abnormal behavior category.
[0033] In a second aspect, a data processing device for building decoration construction is provided, the device comprising:
[0034] The data acquisition module is used to acquire the actual construction data and building planning data corresponding to the target building decoration object according to the preset time configuration;
[0035] A comparison module, for performing deviation comparison between the actual construction data and the building planning data based on artificial intelligence technology and machine vision technology to obtain a target comparison result, wherein the target comparison result includes an effect comparison result and / or a progress comparison result;
[0036] The deviation reminder signal generating module is used to generate a deviation reminder signal according to the target comparison result.
[0037] In a third aspect, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the data processing method for building decoration construction when executing the computer program.
[0038] In a fourth aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the data processing method for building decoration construction are implemented.
[0039] This application obtains the actual construction data and building planning data corresponding to the target building decoration object according to the preset time configuration, and based on artificial intelligence technology and machine vision technology, performs deviation comparison according to the actual construction data and the building planning data to obtain the target comparison result, which includes the effect comparison result and / or the progress comparison result. According to the target comparison result, a deviation reminder signal is generated. Thereby, the deviation comparison according to the preset time configuration is realized, the real-time performance is improved, and the rectification is timely reminded through the deviation reminder signal, which reduces the rectification cost; based on artificial intelligence technology and machine vision technology, the deviation comparison is performed according to the actual construction data and the building planning data. Compared with the comparison based on images only, the data considered in this application is richer and combined with artificial intelligence technology and machine vision technology, which is conducive to improving the accuracy of the determined target comparison result. BRIEF DESCRIPTION OF THE DRAWINGS
[0040] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0041] in:
[0042] Figure 1 An application environment diagram of a data processing method for building decoration construction in one embodiment;
[0043] Figure 2A flowchart of a data processing method for building decoration construction in one embodiment;
[0044] Figure 3 A structural block diagram of a data processing device for building decoration construction in one embodiment;
[0045] Figure 4 FIG. 4 is a structural block diagram of a computer device in one embodiment. DETAILED DESCRIPTION
[0046] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0047] The data processing method for building decoration construction provided by the embodiment of the present invention can be applied in Figure 1 In the application environment, the client 110 communicates with the server 120 through the network.
[0048] The server 120 can obtain the actual construction data and building planning data corresponding to the target building decoration object through the client 110 according to the preset time configuration. The server 120 is used to perform deviation comparison based on the actual construction data and the building planning data based on artificial intelligence technology and machine vision technology to obtain a target comparison result, and the target comparison result includes an effect comparison result and / or a progress comparison result. According to the target comparison result, a deviation reminder signal is generated. Thereby, the deviation comparison according to the preset time configuration is realized, the real-time performance is improved, and the rectification is timely reminded through the deviation reminder signal, which reduces the rectification cost; based on artificial intelligence technology and machine vision technology, the deviation comparison is performed according to the actual construction data and the building planning data. Compared with the comparison based on images only, the data considered in this application is richer and combined with artificial intelligence technology and machine vision technology, which is conducive to improving the accuracy of the determined target comparison results.
[0049] The client 110 may be, but is not limited to, various personal computers, laptop computers, smart phones, tablet computers, and portable wearable devices. The server 120 may be implemented by an independent server or a server cluster consisting of multiple servers. The present invention is described in detail below through specific embodiments.
[0050] See also Figure 2 As shown, Figure 2 A flow chart of a data processing method for building decoration construction provided by an embodiment of the present invention includes the following steps:
[0051] S1: According to the preset time configuration, obtain the actual construction data and building planning data corresponding to the target building decoration object;
[0052] The preset time configuration is a pre-set time configuration, which can be a time interval or multiple time points.
[0053] The target building decoration object is the object of building decoration that you want to evaluate. For example, the target building decoration object is a house. Building decoration includes but is not limited to: interior decoration, home installation, furniture installation, and interior decoration.
[0054] Specifically, the actual construction data and building planning data corresponding to the target building decoration object input by the user can be obtained, the actual construction data and building planning data corresponding to the target building decoration object can be obtained from a preset storage space, and the actual construction data and building planning data corresponding to the target building decoration object can also be obtained from a third-party application.
[0055] Actual construction data refers to data collected during the construction process of building decoration. Actual construction data includes: construction videos, construction images and construction text data. Construction text data is data used to describe construction-related information (such as effects and progress). The construction video in the actual construction data can be a video obtained by installing a camera at the construction site and monitoring it with the camera, or it can be a video taken with other shooting equipment. The construction image can be an image taken by a camera at the construction site, or it can be an image taken with other shooting equipment (such as a mobile phone). The construction image can also be an image corresponding to the acceptance document and an image corresponding to the construction billboard.
[0056] Optionally, the actual construction data is the original collected data.
[0057] Optionally, the actual construction data is data obtained after processing the original collected data, and the processing method includes: privacy computing technology, image denoising, image enhancement, edge detection, text error correction, and video denoising. One or more.
[0058] The architectural planning data includes, but is not limited to: architectural decoration design drawings (for example, drawings designed by CAD (Computer Aided Diagnosis)), architectural decoration three-dimensional models, and progress planning data.
[0059] S2: Based on artificial intelligence technology and machine vision technology, a deviation comparison is performed according to the actual construction data and the building planning data to obtain a target comparison result, wherein the target comparison result includes an effect comparison result and / or a progress comparison result;
[0060] Specifically, based on artificial intelligence technology and machine vision technology, an effect deviation comparison is performed according to the actual construction data and the building planning data to obtain an effect comparison result, and / or, based on artificial intelligence technology and machine vision technology, a progress deviation comparison is performed according to the actual construction data and the building planning data to obtain a progress comparison result.
[0061] The effect comparison results include but are not limited to: target object and effect deviation category. The target object is the object of architectural decoration, for example, the target object is: a wardrobe. The effect deviation category includes but is not limited to: contour deviation, color deviation, size deviation, surface line deviation and surface flatness deviation.
[0062] The progress comparison results include but are not limited to: target object, current progress and progress deviation status.
[0063] S3: Generate a deviation warning signal according to the target comparison result.
[0064] Specifically, based on the signal generation method corresponding to the effect deviation, a deviation reminder signal is generated according to the effect deviation category in the effect comparison result; based on the signal generation method corresponding to the progress deviation, a deviation reminder signal is generated according to the progress comparison result.
[0065] The deviation reminder signal is used to remind construction personnel and supervisors of any deviations, which helps them to correct the deviations in time.
[0066] This embodiment obtains the actual construction data and building planning data corresponding to the target building decoration object according to the preset time configuration, and performs deviation comparison based on the actual construction data and the building planning data based on artificial intelligence technology and machine vision technology to obtain the target comparison result, which includes the effect comparison result and / or the progress comparison result. According to the target comparison result, a deviation reminder signal is generated. Thereby, the deviation comparison is performed according to the preset time configuration, the real-time performance is improved, and the rectification is timely reminded through the deviation reminder signal, which reduces the rectification cost; based on artificial intelligence technology and machine vision technology, the deviation comparison is performed according to the actual construction data and the building planning data. Compared with the comparison based on images only, the data considered in this application is richer and combined with artificial intelligence technology and machine vision technology, which is conducive to improving the accuracy of the determined target comparison result.
[0067] In one embodiment, the step of performing deviation comparison based on the actual construction data and the building planning data based on artificial intelligence technology and machine vision technology to obtain a target comparison result includes:
[0068] S211: Determine construction effect data based on the actual construction data based on a preset effect extraction rule;
[0069] Optionally, based on preset effect extraction rules, target object recognition, image region extraction corresponding to the target object, and text extraction are performed according to the actual construction data to obtain construction effect data.
[0070] Target object recognition is to use a model obtained by training based on a target detection network to perform target object recognition from the construction images of the actual construction data and / or the image frames of the construction video of the actual construction data.
[0071] S212: Determine planning effect data based on the effect extraction rule and the building planning data;
[0072] Optionally, based on preset effect extraction rules, target object recognition, image area extraction corresponding to the target object, and text extraction are performed according to the building planning data to obtain construction effect data.
[0073] It can be understood that both step S211 and step S212 adopt the same effect extraction rule, thereby achieving the determination of the construction effect data and the planning effect data based on the same extraction rule, providing a basis for improving the accuracy of the comparison.
[0074] S213: splicing the construction effect data and the planning effect data based on a preset first splicing rule to obtain first splicing data;
[0075] Specifically, based on a preset first splicing rule, the construction effect data and the planning effect data are spliced, and the spliced data is used as the first spliced data.
[0076] The preset first splicing rule includes but is not limited to: a first object splicing symbol and a first separation splicing symbol. The first object splicing symbol is used to splice the data corresponding to the same target object in the construction effect data and the data corresponding to the planning effect data, and the spliced data is used as the first data pair. The first separation splicing symbol is used to splice the first data pair, and the spliced data is used as the first spliced data.
[0077] S214: Inputting the first splicing data into a pre-trained effect comparison model for deviation comparison to obtain an effect comparison result in the target comparison result, wherein the effect comparison model is a model trained based on artificial intelligence technology, machine vision technology and image matching technology.
[0078] Specifically, the first spliced data is input into a pre-trained effect comparison model to perform deviation comparison on each target object to obtain a first comparison vector, and the object deviation category corresponding to the vector element in the first comparison vector that is greater than the first numerical value is used as the hit object deviation category, and the target object and deviation category corresponding to the object serial number in the hit object deviation category (that is, the effect deviation category in the effect comparison result) is used as a record data in the effect comparison result.
[0079] The pre-trained effect comparison model is a pre-trained multi-classification model. The model structure and model training method of the pre-trained effect comparison model can be selected from the existing technology and will not be described in detail here.
[0080] This embodiment adopts the same effect extraction rule, thereby realizing the determination of the construction effect data and the planning effect data based on the same extraction rule, providing a basis for improving the accuracy of the comparison; using a model trained based on artificial intelligence technology, machine vision technology and image matching technology to perform deviation comparison, the degree of automation of this application is improved, and the model is also helpful to improve the accuracy of the comparison; relative to comparison based only on images, this application considers richer data and combines artificial intelligence technology and machine vision technology, which is helpful to improve the accuracy of the determined target comparison results.
[0081] In one embodiment, the step of performing deviation comparison based on the actual construction data and the building planning data based on artificial intelligence technology and machine vision technology to obtain a target comparison result further includes:
[0082] S221: Determine construction progress data based on the actual construction data based on a preset progress extraction rule;
[0083] Optionally, based on preset progress extraction rules, target object recognition, image area corresponding to the target object, and text extraction are performed according to the actual construction data to obtain construction progress data.
[0084] S222: Determine planning progress data based on the progress extraction rule and the building planning data;
[0085] Optionally, based on the progress extraction rule, target object recognition, image area corresponding to the target object, and text extraction are performed according to the building planning data to obtain planning progress data.
[0086] It can be understood that both step S221 and step S222 adopt the same progress extraction rule, thereby achieving the determination of the construction progress data and the planning progress data based on the same extraction rule, providing a basis for improving the accuracy of the comparison.
[0087] S223: splicing the construction progress data and the planning progress data based on a preset second splicing rule to obtain second splicing data;
[0088] Specifically, based on a preset second splicing rule, the construction progress data and the planning progress data are spliced, and the spliced data is used as the second spliced data.
[0089] The preset second splicing rule includes but is not limited to: a second object splicing symbol and a second separation splicing symbol. The second object splicing symbol is used to splice the data corresponding to the same target object in the construction progress data and the data corresponding to the planning progress data, and the spliced data is used as the second data pair. The second separation splicing symbol is used to splice the second data pair, and the spliced data is used as the second spliced data.
[0090] S224: inputting the second spliced data into a pre-trained progress prediction model for classification prediction to obtain a first prediction vector, wherein the progress prediction model is a model trained based on artificial intelligence technology;
[0091] S225: Determine a progress comparison result of the target comparison result according to the first prediction vector and the planning progress data.
[0092] Specifically, the second spliced data is input into a pre-trained progress prediction model to perform progress classification prediction for each target object to obtain a first prediction vector, and the progress corresponding to the vector element corresponding to the first value in the first prediction vector is taken as the target progress, and the target progress of the target object is compared with the current planned progress of the target object in the planned progress data (that is, the planned progress corresponding to the current time). If they are the same, the progress deviation result is determined to be the same. If the target progress of the target object is the same as any one of the historical planned progress corresponding to the current planned progress of the target object in the planned progress data (that is, the planned progress before the planned progress corresponding to the current time), the progress deviation result is determined to be behind. If the target progress of the target object is the same as any one of the future planned progress corresponding to the current planned progress of the target object in the planned progress data (that is, the planned progress after the planned progress corresponding to the current time), the progress deviation result is determined to be ahead, and the target object and the progress deviation result corresponding to the target object (that is, the progress deviation state in the progress comparison result) and the target progress (that is, the current progress in the progress comparison result) are taken as a record data in the progress comparison result.
[0093] The progress prediction model is a multi-classification model. The model structure and model training method of the progress prediction model can be selected from the existing technology and will not be described in detail here.
[0094] This embodiment adopts the same progress extraction rule, thereby realizing the determination of the construction progress data and the planning progress data based on the same extraction rule, providing a basis for improving the accuracy of the comparison; the deviation comparison is performed by using a model trained based on artificial intelligence technology, machine vision technology and image matching technology, which improves the degree of automation of this application, and the model is also conducive to improving the accuracy of the comparison; compared with the comparison based only on images, this application considers richer data and combines artificial intelligence technology and machine vision technology, which is conducive to improving the accuracy of the determined target comparison results.
[0095] In one embodiment, after the step of performing deviation comparison based on the actual construction data and the building planning data based on artificial intelligence technology and machine vision technology to obtain a target comparison result, the step further includes:
[0096] S41: extracting effect image pairs at each viewing angle according to the construction effect data and the planning effect data based on a preset resolution configuration;
[0097] Perspective refers to the perspective from which the target object is viewed.
[0098] Specifically, based on the preset resolution configuration, two effect images based on the construction effect data and the planning effect data at the same viewing angle are taken as an effect image pair. Based on the preset resolution configuration, it is beneficial to make the resolutions of the extracted effect images the same, so that the viewing angles and specifications of the effect images in the effect image pair are the same.
[0099] S42: Based on the image matching technology, searching for deviation points of each effect image pair to obtain image pair deviation point data;
[0100] Specifically, based on image matching technology, target object recognition, image area extraction corresponding to the target object, deviation classification prediction of each pixel point, and connectivity of deviation pixels are performed for each effect image pair to obtain the deviation connected area corresponding to each target object. The deviation connected areas corresponding to each target object of the effect image pair are used as image pair deviation point data.
[0101] The deviation classification prediction of each pixel point is implemented based on the classification model. The pixel point corresponding to the vector element greater than the second value in the vector obtained by the deviation classification prediction of the pixel point is taken as the deviation pixel point.
[0102] The deviation pixel points are connected, and the adjacent deviation pixel points are connected, and each image area after the connection is regarded as a deviation connected area.
[0103] S43: Based on a preset marking rule, according to the deviation point data of the image pair, marking the deviation points of the effect image pair corresponding to the deviation point data of the image pair to obtain a marked image pair;
[0104] The preset marking rule may adopt a border of a preset color.
[0105] Specifically, based on the preset marking rules, according to the deviation point data of the image pair, the deviation connected area of the effect image pair corresponding to the deviation point data of the image pair is marked, for example, the outline of the deviation connected area is changed to a preset color, and the marked effect image pair is used as a marked image pair.
[0106] S44: Performing interface display according to each of the marked image pairs, the effect comparison results and the progress comparison results to obtain a target interface, wherein a first area in the target interface is generated based on effect display rules, each of the marked image pairs and the effect comparison results, and a second area in the target interface is generated based on progress display rules and the progress comparison results, and the first area displays an effect deviation comparison diagram corresponding to each of the marked image pairs.
[0107] Specifically, an interface (eg, a web page) is displayed according to each of the marked image pairs, the effect comparison results, and the progress comparison results, and the displayed section is used as a target interface.
[0108] Optionally, based on the forms of tables, charts, dashboards, images, etc., an interface display is performed according to each of the marked image pairs, the effect comparison results, and the progress comparison results to obtain a target interface.
[0109] This embodiment marks the deviation points of the effect image pair corresponding to the deviation point data of the image pair based on preset marking rules for interface display, thereby visually displaying the deviation points, which is beneficial for construction personnel to quickly find the places that need rectification, improves the rectification efficiency, and is beneficial to improving the accuracy of rectification; by displaying the progress comparison results on the interface, it is beneficial for construction personnel and supervisors to quickly determine the progress deviation.
[0110] In one embodiment, the method further comprises:
[0111] S51: inputting the planning effect data and each of the construction effect data corresponding to the target building decoration object into a pre-trained effect trend prediction model to perform future trend prediction, and obtain an effect trend prediction result;
[0112] The various construction effect data corresponding to the target building decoration object are all the construction effect data that have been collected corresponding to the target building decoration object.
[0113] Specifically, the planning effect data and the construction effect data corresponding to the target building decoration object are spliced and input into a pre-trained effect trend prediction model to perform future trend prediction, and the predicted data is used as the effect trend prediction result.
[0114] The optional pre-trained effect trend prediction model is a model trained based on the ARIMA model. The ARIMA model is called Autoregressive Integrated Moving Average Model in English and the integrated autoregressive moving average model in Chinese.
[0115] S52: Inputting the planning progress data and each of the construction progress data corresponding to the target building decoration object into a pre-trained progress trend prediction model to perform future trend prediction and obtain a progress trend prediction result.
[0116] The various construction progress data corresponding to the target building decoration object are all the construction progress data corresponding to the target building decoration object that have been collected.
[0117] Specifically, the planning progress data and the construction progress data corresponding to the target building decoration object are spliced and input into a pre-trained progress trend prediction model to perform future trend prediction, and the predicted data is used as the progress trend prediction result.
[0118] The optional pre-trained progress trend prediction model is a model trained based on the ARI MA model.
[0119] This embodiment helps construction personnel and supervisors to quickly formulate rectification strategies by predicting future trends of effects; and helps construction management personnel to quickly deploy resources to ensure that the entire target building decoration object is completed on schedule by predicting future trends of progress.
[0120] In one embodiment, the image in the actual construction data is an image processed by privacy computing technology, wherein the privacy computing technology includes: one or more of stickman generation technology and cartoon man generation technology.
[0121] Specifically, the stickman generation technology is to replace part or all of the image area corresponding to the human body in the image with a stickman, wherein the stickman shows the skeleton and head of the human body.
[0122] The cartoon human generation technology is to replace part or all of the image area corresponding to the human body in the image with a cartoon image.
[0123] It is understandable that the privacy computing technology may also adopt other privacy computing methods, which are not limited here.
[0124] The images in the actual construction data of this embodiment are images processed by privacy computing technology, thereby protecting the privacy of construction workers and / or supervisors.
[0125] In one embodiment, after the step of acquiring the actual construction data and building planning data corresponding to the target building decoration object according to the preset time configuration, the method further includes:
[0126] S61: extracting behavior feature data of each construction worker based on the actual construction data based on target detection technology;
[0127] Specifically, a target detection model is used to extract the image area corresponding to each construction worker from the actual construction data, and based on the model obtained by artificial intelligence, features are extracted from the data corresponding to the image area, and the extracted features are used as behavioral feature data.
[0128] Models obtained based on artificial intelligence, for example, models obtained by training based on feature extraction algorithms. Feature extraction algorithms include but are not limited to: HOG, SIFT, SURF.
[0129] HOG is the abbreviation of Histogram of Oriented Gradient, which is a feature descriptor used for target detection in computer vision and image processing. It can be combined with OPENCV's SVM classifier for image recognition.
[0130] SIFT (Scale-invariant feature transform) is an algorithm for detecting local features. The algorithm obtains features by finding the feature points (interest points, or corner points) in an image and their related scale and orientation descriptors, and performs image feature point matching, achieving good results.
[0131] SURF (Speeded Up Robust Features) feature extraction technology is a widely used machine vision technology that aims to detect and identify feature points in images. Surf feature extraction technology is an extremely effective feature extraction method that can extract a lot of important information from images.
[0132] The target detection model is a model trained based on the target detection network and is used to detect the human body (that is, the target).
[0133] S62: Inputting the behavior feature data into a pre-trained abnormal behavior prediction model for classification prediction to obtain a second prediction vector;
[0134] Specifically, the behavior feature data is input into a pre-trained abnormal behavior prediction model for classification prediction, and a vector obtained by the classification prediction is used as a second prediction vector.
[0135] The pre-trained abnormal behavior prediction model is a pre-trained multi-classification model. The model structure and model training method of the pre-trained abnormal behavior prediction model can be selected from the existing technology and will not be described in detail here.
[0136] S63: taking the vector element whose value in the second prediction vector is greater than a preset probability as a target element;
[0137] S64: taking the behavior category corresponding to each target element corresponding to the behavior feature data as an abnormal behavior category.
[0138] This embodiment uses target detection technology and a pre-trained abnormal behavior prediction model to determine the abnormal behavior category of the construction personnel from the actual construction data, thereby providing a basis for correcting the abnormal behavior of the construction personnel and also providing a basis for determining the risk of building decoration construction based on the abnormal behavior category.
[0139] See also Figure 3 As shown, in one embodiment, a data processing device for building decoration construction is provided, the device comprising:
[0140] The data acquisition module 801 is used to acquire the actual construction data and building planning data corresponding to the target building decoration object according to the preset time configuration;
[0141] A comparison module 802 is used to perform deviation comparison based on the actual construction data and the building planning data based on artificial intelligence technology and machine vision technology to obtain a target comparison result, wherein the target comparison result includes an effect comparison result and / or a progress comparison result;
[0142] The deviation warning signal generating module 803 is used to generate a deviation warning signal according to the target comparison result.
[0143] This embodiment obtains the actual construction data and building planning data corresponding to the target building decoration object according to the preset time configuration, and performs deviation comparison based on the actual construction data and the building planning data based on artificial intelligence technology and machine vision technology to obtain the target comparison result, which includes the effect comparison result and / or the progress comparison result. According to the target comparison result, a deviation reminder signal is generated. Thereby, the deviation comparison is performed according to the preset time configuration, the real-time performance is improved, and the rectification is timely reminded through the deviation reminder signal, which reduces the rectification cost; based on artificial intelligence technology and machine vision technology, the deviation comparison is performed according to the actual construction data and the building planning data. Compared with the comparison based on images only, the data considered in this application is richer and combined with artificial intelligence technology and machine vision technology, which is conducive to improving the accuracy of the determined target comparison result.
[0144] In one embodiment, the step of performing deviation comparison based on the actual construction data and the building planning data based on artificial intelligence technology and machine vision technology in the comparison module 802 to obtain a target comparison result includes:
[0145] Based on the preset effect extraction rules, the construction effect data is determined according to the actual construction data;
[0146] Based on the effect extraction rule, and according to the building planning data, determining planning effect data;
[0147] Based on a preset first splicing rule, the construction effect data and the planning effect data are spliced to obtain first spliced data;
[0148] The first spliced data is input into a pre-trained effect comparison model for deviation comparison to obtain an effect comparison result in the target comparison result, wherein the effect comparison model is a model trained based on artificial intelligence technology, machine vision technology and image matching technology.
[0149] In one embodiment, the step of performing deviation comparison based on the actual construction data and the building planning data based on artificial intelligence technology and machine vision technology to obtain a target comparison result in the comparison module 802 further includes:
[0150] Based on the preset progress extraction rules, the construction progress data is determined according to the actual construction data;
[0151] Based on the progress extraction rule, and according to the building planning data, determining planning progress data;
[0152] Based on a preset second splicing rule, the construction progress data and the planning progress data are spliced to obtain second spliced data;
[0153] Inputting the second spliced data into a pre-trained progress prediction model for classification prediction to obtain a first prediction vector, wherein the progress prediction model is a model trained based on artificial intelligence technology;
[0154] A progress comparison result of the target comparison result is determined according to the first prediction vector and the planning progress data.
[0155] In one embodiment, the device further comprises: a visualization module, wherein the visualization module is configured to:
[0156] Extracting effect image pairs at each viewing angle according to the construction effect data and the planning effect data;
[0157] Based on the image matching technology, searching for deviation points of each effect image pair to obtain image pair deviation point data;
[0158] Based on a preset marking rule, according to the deviation point data of the image pair, marking the deviation points of the effect image pair corresponding to the deviation point data of the image pair to obtain a marked image pair;
[0159] An interface display is performed according to each of the marked image pairs, the effect comparison results and the progress comparison results to obtain a target interface, wherein a first area in the target interface is generated based on effect display rules, each of the marked image pairs and the effect comparison results, and a second area in the target interface is generated based on progress display rules and the progress comparison results, and an effect deviation comparison diagram corresponding to each of the marked image pairs is displayed in the first area.
[0160] In one embodiment, the apparatus further comprises: a first trend prediction module and a second trend prediction module;
[0161] The first trend prediction module is used to input the planning effect data and each of the construction effect data corresponding to the target building decoration object into a pre-trained effect trend prediction model to perform future trend prediction and obtain an effect trend prediction result;
[0162] The second trend prediction module is used to input the planning progress data and each of the construction progress data corresponding to the target building decoration object into a pre-trained progress trend prediction model to perform future trend prediction and obtain a progress trend prediction result.
[0163] In one embodiment, the image in the actual construction data is an image processed by privacy computing technology, wherein the privacy computing technology includes: one or more of stickman generation technology and cartoon man generation technology.
[0164] In one embodiment, the device further comprises: an abnormal behavior identification module, wherein the abnormal behavior identification module is used to:
[0165] Based on the target detection technology, extracting the behavior characteristic data of each construction worker according to the actual construction data;
[0166] Inputting the behavior feature data into a pre-trained abnormal behavior prediction model for classification prediction to obtain a second prediction vector;
[0167] Taking the vector element whose value in the second prediction vector is greater than a preset probability as the target element;
[0168] The behavior category corresponding to each target element corresponding to the behavior feature data is taken as an abnormal behavior category.
[0169] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 4 As shown. The computer device includes a processor, a memory, a network interface and a database connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile and / or volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external client via a network connection. When the computer program is executed by the processor, the functions or steps on the service side of a data processing method for building decoration construction are realized.
[0170] In one embodiment, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the following steps are implemented:
[0171] According to the preset time configuration, the actual construction data and building planning data corresponding to the target building decoration object are obtained;
[0172] Based on artificial intelligence technology and machine vision technology, a deviation comparison is performed according to the actual construction data and the building planning data to obtain a target comparison result, wherein the target comparison result includes an effect comparison result and / or a progress comparison result;
[0173] A deviation warning signal is generated according to the target comparison result.
[0174] This embodiment obtains the actual construction data and building planning data corresponding to the target building decoration object according to the preset time configuration, and performs deviation comparison based on the actual construction data and the building planning data based on artificial intelligence technology and machine vision technology to obtain the target comparison result, which includes the effect comparison result and / or the progress comparison result. According to the target comparison result, a deviation reminder signal is generated. Thereby, the deviation comparison is performed according to the preset time configuration, the real-time performance is improved, and the rectification is timely reminded through the deviation reminder signal, which reduces the rectification cost; based on artificial intelligence technology and machine vision technology, the deviation comparison is performed according to the actual construction data and the building planning data. Compared with the comparison based on images only, the data considered in this application is richer and combined with artificial intelligence technology and machine vision technology, which is conducive to improving the accuracy of the determined target comparison result.
[0175] In one embodiment, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps are implemented:
[0176] According to the preset time configuration, the actual construction data and building planning data corresponding to the target building decoration object are obtained;
[0177] Based on artificial intelligence technology and machine vision technology, a deviation comparison is performed according to the actual construction data and the building planning data to obtain a target comparison result, wherein the target comparison result includes an effect comparison result and / or a progress comparison result;
[0178] A deviation warning signal is generated according to the target comparison result.
[0179] This embodiment obtains the actual construction data and building planning data corresponding to the target building decoration object according to the preset time configuration, and performs deviation comparison based on the actual construction data and the building planning data based on artificial intelligence technology and machine vision technology to obtain the target comparison result, which includes the effect comparison result and / or the progress comparison result. According to the target comparison result, a deviation reminder signal is generated. Thereby, the deviation comparison is performed according to the preset time configuration, the real-time performance is improved, and the rectification is timely reminded through the deviation reminder signal, which reduces the rectification cost; based on artificial intelligence technology and machine vision technology, the deviation comparison is performed according to the actual construction data and the building planning data. Compared with the comparison based on images only, the data considered in this application is richer and combined with artificial intelligence technology and machine vision technology, which is conducive to improving the accuracy of the determined target comparison result.
[0180] It should be noted that the above functions or steps that can be implemented by the computer-readable storage medium or computer device can refer to the relevant descriptions on the server side and the client side in the aforementioned method embodiment. To avoid repetition, they will not be described one by one here.
[0181] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
[0182] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.
[0183] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.
Claims
1. A data processing method for building decoration construction, characterized in that: The method comprises: According to the preset time configuration, the actual construction data and building planning data corresponding to the target building decoration object are obtained, wherein the actual construction data includes: construction video, construction image and construction text data, and the building planning data includes: building decoration design drawings, building decoration three-dimensional models, and progress planning data; Based on artificial intelligence technology and machine vision technology, a deviation comparison is performed according to the actual construction data and the building planning data to obtain a target comparison result, wherein the target comparison result includes an effect comparison result and a progress comparison result, wherein the effect comparison result includes: a target object and an effect deviation category, and the progress comparison result includes: a target object, a current progress, and a progress deviation status; generating a deviation warning signal according to the target comparison result; The step of performing deviation comparison based on the actual construction data and the building planning data to obtain a target comparison result based on artificial intelligence technology and machine vision technology includes: Based on the preset effect extraction rules, the construction effect data is determined according to the actual construction data; Based on the effect extraction rule, and according to the building planning data, determining planning effect data; Based on a preset first splicing rule, the construction effect data and the planning effect data are spliced to obtain first spliced data; Inputting the first spliced data into a pre-trained effect comparison model for deviation comparison to obtain an effect comparison result in the target comparison result, wherein the effect comparison model is a model trained based on artificial intelligence technology, machine vision technology and image matching technology; The step of performing deviation comparison based on the actual construction data and the building planning data to obtain a target comparison result based on artificial intelligence technology and machine vision technology also includes: Based on the preset progress extraction rules, the construction progress data is determined according to the actual construction data; Based on the progress extraction rule, and according to the building planning data, determining planning progress data; Based on a preset second splicing rule, the construction progress data and the planning progress data are spliced to obtain second spliced data; Inputting the second spliced data into a pre-trained progress prediction model for classification prediction to obtain a first prediction vector, wherein the progress prediction model is a model trained based on artificial intelligence technology; Determining a progress comparison result of the target comparison result according to the first prediction vector and the planning progress data; The method further comprises: Inputting the planning effect data and each of the construction effect data corresponding to the target building decoration object into a pre-trained effect trend prediction model to perform future trend prediction, and obtain an effect trend prediction result; The planning progress data and each of the construction progress data corresponding to the target building decoration object are input into a pre-trained progress trend prediction model to perform future trend prediction to obtain a progress trend prediction result.
2. The data processing method for building decoration construction according to claim 1 is characterized in that: After the step of performing deviation comparison based on the actual construction data and the building planning data based on artificial intelligence technology and machine vision technology to obtain a target comparison result, the method further includes: Extracting effect image pairs at each viewing angle according to the construction effect data and the planning effect data; Based on the image matching technology, searching for deviation points of each effect image pair to obtain image pair deviation point data; Based on a preset marking rule, according to the deviation point data of the image pair, marking the deviation points of the effect image pair corresponding to the deviation point data of the image pair to obtain a marked image pair; An interface display is performed according to each of the marked image pairs, the effect comparison results and the progress comparison results to obtain a target interface, wherein a first area in the target interface is generated based on effect display rules, each of the marked image pairs and the effect comparison results, and a second area in the target interface is generated based on progress display rules and the progress comparison results, and an effect deviation comparison diagram corresponding to each of the marked image pairs is displayed in the first area.
3. The data processing method for building decoration construction according to claim 1 is characterized in that: The images in the actual construction data are images processed by privacy computing technology, wherein the privacy computing technology includes: one or more of stickman generation technology and cartoon man generation technology.
4. The data processing method for building decoration construction according to claim 1 is characterized in that: After the step of acquiring the actual construction data and building planning data corresponding to the target building decoration object according to the preset time configuration, the method further includes: Based on the target detection technology, extracting the behavior characteristic data of each construction worker according to the actual construction data; Inputting the behavior feature data into a pre-trained abnormal behavior prediction model for classification prediction to obtain a second prediction vector; Taking the vector element whose value in the second prediction vector is greater than a preset probability as the target element; The behavior category corresponding to each target element corresponding to the behavior feature data is taken as an abnormal behavior category.
5. A data processing device for building decoration construction, characterized in that: The device comprises: The data acquisition module is used to acquire the actual construction data and building planning data corresponding to the target building decoration object according to the preset time configuration, wherein the actual construction data includes: construction video, construction image and construction text data, and the building planning data includes: building decoration design drawings, building decoration three-dimensional models, and progress planning data; A comparison module, for performing deviation comparison based on the actual construction data and the building planning data based on artificial intelligence technology and machine vision technology to obtain a target comparison result, wherein the target comparison result includes an effect comparison result and a progress comparison result, wherein the effect comparison result includes: a target object and an effect deviation category, and the progress comparison result includes: a target object, a current progress, and a progress deviation status; A deviation warning signal generating module, used for generating a deviation warning signal according to the target comparison result; The step of performing deviation comparison based on the actual construction data and the building planning data to obtain a target comparison result based on artificial intelligence technology and machine vision technology includes: Based on the preset effect extraction rules, the construction effect data is determined according to the actual construction data; Based on the effect extraction rule, and according to the building planning data, determining planning effect data; Based on a preset first splicing rule, the construction effect data and the planning effect data are spliced to obtain first spliced data; Inputting the first spliced data into a pre-trained effect comparison model for deviation comparison to obtain an effect comparison result in the target comparison result, wherein the effect comparison model is a model trained based on artificial intelligence technology, machine vision technology and image matching technology; The step of performing deviation comparison based on the actual construction data and the building planning data to obtain a target comparison result based on artificial intelligence technology and machine vision technology also includes: Based on the preset progress extraction rules, the construction progress data is determined according to the actual construction data; Based on the progress extraction rule, and according to the building planning data, determining planning progress data; Based on a preset second splicing rule, the construction progress data and the planning progress data are spliced to obtain second spliced data; Inputting the second spliced data into a pre-trained progress prediction model for classification prediction to obtain a first prediction vector, wherein the progress prediction model is a model trained based on artificial intelligence technology; Determining a progress comparison result of the target comparison result according to the first prediction vector and the planning progress data; The device also includes: Inputting the planning effect data and each of the construction effect data corresponding to the target building decoration object into a pre-trained effect trend prediction model to perform future trend prediction, and obtain an effect trend prediction result; The planning progress data and each of the construction progress data corresponding to the target building decoration object are input into a pre-trained progress trend prediction model to perform future trend prediction to obtain a progress trend prediction result.
6. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the data processing method for building decoration construction as claimed in any one of claims 1 to 4 are implemented.
7. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the data processing method for building decoration construction as claimed in any one of claims 1 to 4 are implemented.
