Three-dimensional GIM model dynamic updating method for capital construction

Abstract

The invention relates to the technical field of image processing, in particular to a three-dimensional GIM model dynamic updating method for capital construction, and the method comprises the steps: building a three-dimensional GIM model through extracting sample image information of different construction links of various types of target object construction; the risk feature characterization parameters of all construction links of all types of target object construction can be calculated by determining feature highlighting factors of all construction links of all types of target object construction, and the purpose is to quantify the feature highlighting conditions of the construction links corresponding to all types of target object construction; risk characteristic parameters corresponding to the construction links are calculated to represent the conditions, and construction link data information with high data representation can be preferentially extracted for analysis when a three-dimensional GIM model is constructed subsequently corresponding to the type of target objects; therefore, the dynamic updating operation efficiency of the three-dimensional GIM model is improved on the premise of ensuring the accuracy of the dynamic updating of the three-dimensional GIM model.

Description

Technical Field

[0001] The present invention relates to the field of image processing technology, and in particular to a method for dynamically updating a three-dimensional GIM model for infrastructure. Background Art

[0002] With the rapid development of information technology, 3D geographic information modeling (GIM) technology, with its powerful spatial data processing and visualization capabilities, has gradually become a core technical tool for engineering planning, design, construction, and operation and maintenance in the field of infrastructure construction. 3D GIM models can integrate multi-source information such as topography, geological conditions, and building structures, presenting them in an intuitive and three-dimensional manner, providing comprehensive and accurate data support for engineering decision-making. However, infrastructure projects are characterized by long construction cycles, complex and changing environments, and numerous stakeholders. During the construction process, design changes, project progress, and discrepancies between actual on-site conditions and the original design frequently occur. This requires that 3D GIM models be dynamically updated in a timely and accurate manner to reflect the latest status of the project.

[0003] Chinese Patent Publication No. CN116342325A discloses a three-dimensional GIM management and control system for infrastructure. The system comprises a data layer, a platform layer, an application layer, and a presentation layer. The data layer provides raw and basic data; the platform layer provides the processes, reports, graphics, and three-dimensional basic functional support required for system management, as well as business operations and expansion mechanisms and carriers; the application layer provides application models for infrastructure project management; and the presentation layer supports large-screen display and monitoring applications. Regardless of the source or location of the data or documents, users can use it to organize, verify, and collect asset data, connecting team members anywhere and sharing data across teams.

[0004] Chinese Patent Publication No. CN118628679B discloses a method for dynamically updating a 3D geological model. The method comprises: inputting new geophysical data and a block model into a local update module, outputting a new local model; inputting the new local model into a model splicing module, generating a sub-regional grid model based on the global definition of the overall grid of the 3D geological model to be updated; and uploading the sub-regional grid model to the global model. This method utilizes a hierarchical and block-based modeling approach for geological modeling, and through hierarchical updating, utilizes model parameters to unify the parameter standards of the structural model and the attribute model, achieving the goal of updating and integrating models at different scales.

[0005] However, the prior art still has the following problems: The existing technology does not consider the three-dimensional GIM model of different types of target objects in different construction links. Due to its high spatial complexity, it directly uses the complete sample image of the target object construction project for comparison, resulting in slow data transmission rate and low dynamic update efficiency. Summary of the Invention

[0006] To this end, the present invention provides a dynamic updating method for a three-dimensional GIM model for infrastructure, so as to overcome the problem that the three-dimensional GIM model in the prior art does not take into account the different construction links of different types of target objects, and directly uses the complete sample image of the target object construction project for comparison, resulting in a slow data transmission rate and low dynamic update efficiency.

[0007] To achieve the above objectives, the present invention provides a method for dynamically updating a three-dimensional GIM model for infrastructure, comprising: Extract sample image information of various construction links of various types of infrastructure objects to construct a 3D GIM model to determine the characteristic highlight factors of each construction link of different types of construction objects; Calculate the risk characteristic characterization parameters of each construction link of each type of target object based on the characteristic highlighting factor to determine the risk characteristic highlighting ranking sequence of each construction link of each type of target object; Obtaining the actual image of the target object uploaded by the user and the sample image information of the corresponding construction link, and obtaining the risk characteristic representation parameters of each construction link of the corresponding type of target object based on the sample image information; Determine the construction risk period based on the risk characteristic parameters, analyze the uploaded actual image of the target object type according to the determined construction risk period, and calculate the mean similarity to determine whether there is an anomaly; if there is an anomaly, enable the 3D modeling tool to dynamically update the 3D GIM model; Among them, the process of obtaining the feature highlighting factor includes comparing the sample image information of each construction link of the construction of a single type of target object with the sample image information of the corresponding construction link of other types of target objects, solving the mean similarity, and obtaining the spatial complexity of each construction link of the construction of a single type of target object.

[0008] Furthermore, the process of determining the construction risk period based on the risk characteristic parameters includes: Based on the sample image information uploaded by the user, the maximum risk characteristic parameters of each construction link of the corresponding type of target construction are obtained; If the maximum risk characteristic parameter is greater than a predetermined risk characteristic parameter threshold, it is determined to be the first risk period; If the maximum risk characteristic parameter is less than or equal to a predetermined risk characteristic parameter threshold, it is determined to be the second risk period.

[0009] Furthermore, the process of obtaining the spatial complexity of each construction link of a single type of target construction includes: Calibrate the equipment space ratio and construction area of ​​a single construction link for a single type of target; Calculating the ratio of the equipment space ratio of the target object construction to a predetermined equipment space ratio threshold as a first space complexity factor; Calculating a ratio of a construction area of ​​the target object to a predetermined construction area threshold as a second spatial complexity factor; The first space complexity factor and the second space complexity factor are weighted and summed to determine the space complexity.

[0010] Furthermore, the process of calculating the risk characteristic parameters of each construction link of each type of target includes: Obtain feature saliency factors, including similarity mean and spatial complexity; Determining a ratio of a preset similarity standard threshold to the similarity mean as a first feature highlighting factor; Determining a ratio of the spatial complexity to a preset spatial complexity standard threshold as a second feature highlighting factor; The sum of the first feature highlighting factor and the second feature highlighting factor is determined as the risk feature characterization parameter.

[0011] Furthermore, the process of determining the risk characteristics and highlighting the ranking sequence of each construction link of each type of target construction includes: Determine the risk characteristic parameters corresponding to each construction link of a single type of target construction; The risk characteristic characterization parameters are sorted in order from large to small to obtain a risk highlighting sorting sequence.

[0012] Furthermore, the process of analyzing the actual image of the uploaded target type according to the determined construction risk period includes: In the first risk cycle, a risk feature highlighting ranking sequence is obtained based on the sample image information of the construction link of the corresponding type of target object, and the actual image of the corresponding construction link is sequentially called and compared with the local sample image information of the corresponding construction link according to the risk feature highlighting ranking sequence to determine whether there is any abnormality; In the second risk period, the actual image of the complete construction project of the target type uploaded by the user is obtained and compared with the complete sample image information of the corresponding construction project to determine whether there is any abnormality.

[0013] Furthermore, in the first risk cycle, the process of determining whether there is an abnormality includes, Determining a comparison order for actual images of the target object to be constructed based on the risk feature highlighting ranking sequence; The actual image of the corresponding construction link and the sample image information of the corresponding construction link are sequentially called for comparison according to the comparison order; If the similarity corresponding to the actual image of any construction link is less than the preset construction link similarity standard threshold, it is determined that an abnormality exists.

[0014] Furthermore, the process of determining the comparison order of the actual images of the target object to be constructed according to the risk feature highlighting ranking sequence includes: Determine the risk highlighting ranking sequence in sequence, determine the corresponding construction links in sequence, and compare the sample images of the construction links with the actual images in sequence.

[0015] Furthermore, in the second risk cycle, the process of determining whether an abnormality exists includes: If the similarity between the actual image of the complete construction project of the target object uploaded by the current user and the complete sample image information of the corresponding construction project is less than the preset complete construction similarity standard threshold, it is determined that an abnormality exists.

[0016] Furthermore, the actual images of the target object construction uploaded by the user terminal must include complete sample images of the target object construction project and local sample images of each construction link of the target object construction.

[0017] Compared with the prior art, the present invention establishes a 3D GIM model by extracting sample image information from different construction stages of each type of target construction. By determining the feature salience factor for each construction stage of each type of target construction, the risk characteristic characterization parameter for each construction stage of each type of target construction can be calculated, thereby quickly determining the risk characteristic salience ranking sequence for each construction stage of each type of target construction. This improves the efficiency of dynamic updating of the 3D GIM model of the target construction. Furthermore, by obtaining the actual images of the target construction uploaded by the user and the sample image information of the corresponding construction stage, the maximum risk characteristic characterization parameter for each construction stage of each type of target construction can be accurately obtained, thereby improving the accuracy of the 3D GIM model of the target construction. This overcomes the problem of low efficiency and low accuracy in dynamic updating of the 3D GIM model of the corresponding type of target construction caused by different feature salience factors in different construction stages of different types of target construction in the prior art. By determining a comparison order for the 3D GIM model of each construction stage of the target construction, and by sequentially comparing the actual images of the corresponding construction stages with the sample image information of the corresponding construction stages according to the comparison order, it can be accurately determined whether the 3D modeling tool has been enabled for dynamic updating of the 3D GIM model of the target construction uploaded by the user.

[0018] In particular, the present invention comprehensively considers the differences in dynamic updating of three-dimensional GIM models of different construction links by comparing sample image information of different construction links of a single type of target with sample image information of corresponding construction links of other types of targets. In actual situations, some types of target construction have more obvious prominent features in certain construction links, and some risk features of some types of target construction are relatively similar to the corresponding construction links of other types of targets. Therefore, the risk feature characterization of sample image information features of each construction link is different. In some cases, it is possible to identify whether to enable the three-dimensional modeling tool for dynamic updating of the three-dimensional GIM model based on the sample image information of the construction link with obvious risk feature characterization. Therefore, the present invention considers determining the risk feature characterization parameters of each construction link to provide data support for the selection of the three-dimensional modeling tool when performing dynamic update analysis of the three-dimensional GIM model of the target object to be constructed, and then adaptively selects the dynamic update method for the three-dimensional model. While ensuring reliability, the data processing volume is reduced, thereby improving the efficiency and accuracy of the dynamic update of the three-dimensional GIM model of the target object construction.

[0019] In particular, this invention provides a crucial dimension for determining whether dynamic updates of the 3D GIM model are enabled by capturing the spatial complexity of each construction phase for a single type of target. Spatial complexity reflects the structural characteristics of each phase of the target's construction. Environmental factors affecting different types of targets may lead to differences in spatial complexity across different phases. Combining spatial complexity with sample image information similarity reveals the prominence of construction phase features and the data representation.

[0020] In particular, the present invention analyzes image information in the case where the maximum risk characteristic characterization parameter is greater than a predetermined risk characteristic characterization parameter threshold benchmark. In the above case, the construction of the target object of the corresponding type has a construction link with more prominent risk characteristics, and the data characterization is strong. Therefore, the comparison order of the actual images of each construction link of the target object of the type is determined according to the risk highlighting sorting sequence, and the actual images of the corresponding construction links are called in turn according to the comparison order to compare with the three-dimensional GIM model sample image information of the corresponding construction link. This can reduce the noise data introduced by the comparison of the complete version of the construction project sample image information, and give priority to analyzing the actual images corresponding to the links with strong data characterization, thereby improving the efficiency of the dynamic update of the three-dimensional GIM model while ensuring reliability, and ensuring the accuracy of the dynamic update of the three-dimensional GIM model. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 A flowchart of a method for dynamically updating a three-dimensional GIM model for infrastructure construction according to an embodiment of the present invention; Figure 2A flowchart for determining a construction risk period based on the risk characteristic parameters according to an embodiment of the present invention; Figure 3 A flowchart of the steps for obtaining the spatial complexity of each construction link of a single type of target object according to an embodiment of the present invention; Figure 4 Flowchart of the steps for calculating risk characteristic parameters of each construction link for each type of target object according to an embodiment of the present invention. DETAILED DESCRIPTION

[0022] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0023] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0024] See also Figure 1 As shown, it is a flowchart of the steps of a method for dynamically updating a three-dimensional GIM model for infrastructure construction according to an embodiment of the present invention. The present invention provides a method for dynamically updating a three-dimensional GIM model for infrastructure construction, comprising: Step S1: extracting sample image information of each construction link of each type of infrastructure target and constructing a three-dimensional GIM model to determine the characteristic highlighting factors of each construction link of different types of target; Step S2: Calculate the risk characteristic characterization parameters of each construction link of each type of target object based on the characteristic highlighting factor to determine the risk characteristic highlighting ranking sequence of each construction link of each type of target object; Step S3: Acquire the actual image of the target object uploaded by the user and the sample image information of the corresponding construction link, and acquire the risk characteristic parameters of each construction link of the corresponding type of target object based on the sample image information; Step S4: determining a construction risk period based on the risk characteristic parameters, and analyzing the uploaded actual image of the target object type according to the determined construction risk period to calculate the mean similarity to determine whether there is an anomaly; if an anomaly exists, activating a 3D modeling tool to dynamically update the 3D GIM model; Among them, the process of obtaining the feature highlighting factor includes comparing the sample image information of each construction link of the construction of a single type of target object with the sample image information of the corresponding construction link of other types of target objects, solving the mean similarity, and obtaining the spatial complexity of each construction link of the construction of a single type of target object.

[0025] It is understandable that there is no limitation on the type of target objects for infrastructure construction. In practice, it can be a substation, a transmission line, a bridge project, a road project, or other forms, which will not be elaborated here.

[0026] It is understandable that there is no limitation on the division of the various construction links of the target object construction. In implementation, it can be the foundation site construction link, the main structure construction link, the electrical installation construction link, the full life cycle management equipment installation link, or other forms can be adopted, which will not be repeated here.

[0027] It is understandable that there is no limit on the duration of the risk cycle. In practice, it can be 2 to 10 days. In practice, the cycle duration is preferably 2 days. Other forms can also be used, which will not be repeated here.

[0028] Specifically, the present invention establishes a three-dimensional GIM model by extracting sample image information of different construction links of each type of target object construction, and calculates the risk characteristic characterization parameters of each construction link of each type of target object construction by determining the characteristic highlighting factors of each construction link of each type of target object construction. The purpose is to quantify the characteristic highlighting of the construction links corresponding to each type of target object construction. In actual situations, there are obvious differences between the construction links of some types of target object construction and the corresponding construction links of other types of target object construction, and the construction links have a certain degree of complexity. In this case, the characteristic highlighting of the construction links corresponding to this type of target object has strong data characterization. Therefore, by identifying the characteristic highlighting factors and calculating the risk characteristic parameters corresponding to each construction link to characterize the above situation, for this type of target object, when constructing the three-dimensional GIM model in the subsequent construction, the data information of the construction links with strong data characterization can be preferentially extracted for analysis, thereby improving the dynamic update operation efficiency of the three-dimensional GIM model while ensuring the accuracy of the dynamic update of the three-dimensional GIM model.

[0029] It is understandable that there is no limitation on the method of determining the similarity between sample images. The corresponding sample image processing algorithm or model can be imported into the logic component to implement the corresponding function. There is no specific limitation on the sample image processing algorithm. For example, the method of calculating the similarity index can be used, or a pre-trained deep learning model can be used to extract the feature representation of the data information, and then the cosine similarity between the features is calculated as the similarity. Of course, other methods can also be used, which will not be repeated here.

[0030] It can be understood that for the similarity mean, during implementation, the actual image of the uploaded target object type is analyzed, the cosine similarity between the features is calculated as the similarity value, and the average value of all these similarity values ​​in the historical period of three months before the implementation of the system is determined as the similarity mean.

[0031] It is understood that there is no limitation on the 3D modeling tool, and the 3D GIM model can be dynamically updated in any of ArcGIS Pro, CityEngine, and SketchUp. Other methods may also be used, which will not be described in detail here.

[0032] It is understood that there is no limitation on the method of enabling the dynamic update of the 3D GIM model by using the 3D modeling tool. In implementation, the 3D modeling tool ArcGIS Pro is selected. By adding data layers, remote sensing images, point cloud data, and vector data are loaded into the workspace. After data preprocessing, the preprocessed data is imported into the 3D modeling tool and integrated with the existing 3D GIM model for dynamic update. For vector data, it is directly imported and matched with the corresponding elements in the model. For point cloud data, it is converted into surface or volume data of the 3D model through point cloud processing algorithms and integrated with the existing model, thereby achieving dynamic update of the GIM model.

[0033] See also Figure 2 As shown, it is a flow chart of determining the construction risk period based on the risk characteristic parameters according to an embodiment of the present invention. The process of determining the construction risk period based on the risk characteristic parameters according to the present invention includes: Based on the sample image information uploaded by the user, the maximum risk characteristic parameters of each construction link of the corresponding type of target construction are obtained; If the maximum risk characteristic parameter is greater than a predetermined risk characteristic parameter threshold, it is determined to be the first risk period; If the maximum risk characteristic parameter is less than or equal to a predetermined risk characteristic parameter threshold, it is determined to be the second risk period.

[0034] In implementation, the predetermined risk characterization parameter threshold is in the interval [2.15, 2.45].

[0035] See also Figure 3 As shown, it is a flowchart of the steps of obtaining the spatial complexity of each construction link of a single type of target construction according to an embodiment of the present invention. The process of obtaining the spatial complexity of each construction link of a single type of target construction according to the present invention includes: Calibrate the equipment space ratio and construction area of ​​a single construction link for a single type of target; Calculating the ratio of the equipment space ratio of the target object construction to a predetermined equipment space ratio threshold as a first space complexity factor; Calculating a ratio of a construction area of ​​the target object to a predetermined construction area threshold as a second spatial complexity factor; The first space complexity factor and the second space complexity factor are weighted and summed to determine the space complexity.

[0036] It can be understood that there is no limitation on the equipment space ratio, which can be the ratio of the space volume or area occupied by the equipment in the three-dimensional model to the total space volume or area. In implementation, the equipment space ratio is preferably the ratio of the space volume occupied by the equipment in the three-dimensional model to the total space volume.

[0037] In implementation, the equipment space ratio threshold and the construction area threshold are pre-set, wherein the product of the average value of the equipment space ratio within the three-month historical period of this system and the precision coefficient is used as the equipment space ratio threshold, and the precision coefficient is between the interval [0.90, 0.98]. The product of the average value of the construction area within the three-month historical period of this system and the deviation coefficient is used as the construction area threshold, and the deviation coefficient is between the interval [0.95, 0.99].

[0038] Specifically, this method provides an important characteristic dimension for the construction of a target object by obtaining the spatial complexity of each construction link for a single type of target object. Spatial complexity reflects the prominent characteristics of construction links such as the foundation site construction link, the main structure construction link, and the electrical installation construction link. Environmental factors of different types of targets may cause different spatial complexities in different construction links of the target object. Combining spatial complexity with the similarity of sample image information can characterize the prominent characteristics of the construction links.

[0039] See also Figure 4 As shown, it is a flowchart of the steps of calculating the risk characteristic characterization parameters of each construction link of each type of target object according to an embodiment of the present invention. The process of calculating the risk characteristic characterization parameters of each construction link of each type of target object according to the present invention includes: Obtain feature saliency factors, including similarity mean and spatial complexity; Determining a ratio of a preset similarity standard threshold to the similarity mean as a first feature highlighting factor; Determining a ratio of the spatial complexity to a preset spatial complexity standard threshold as a second feature highlighting factor; The sum of the first feature highlighting factor and the second feature highlighting factor is determined as the risk feature characterization parameter.

[0040] In implementation, the preset similarity standard threshold is pre-set, wherein the similarity mean of the construction links of each type of target object is predetermined, and the similarity threshold is set as the product of the similarity mean and the precision coefficient, and the precision coefficient is selected within the interval [0.90, 0.95].

[0041] In implementation, the preset spatial complexity standard threshold is obtained by pre-setting, wherein the spatial complexity of data information of different construction links of various types of target objects is predetermined, the spatial complexity mean is calculated, and the spatial complexity standard threshold is set as the product of the spatial complexity mean and the complexity offset coefficient, and the complexity offset coefficient is between the interval [1.1, 1.2].

[0042] The present invention compares the sample image information of different construction links of a single type of target with the sample image information of the corresponding construction links of other types of targets, and comprehensively considers the differences in the prominent features of different construction links. In actual situations, the three-dimensional GIM models of some target construction have more obvious prominent features in certain construction links, and the prominent features of the construction links of the three-dimensional GIM models of some types of targets are relatively similar to the corresponding construction links of other types of targets. Therefore, the risk feature characterization of the sample image information of each construction link is different. In some cases, the three-dimensional GIM model situation can be identified based on the sample image information of the link with strong risk feature characterization. Therefore, the present invention considers determining the risk feature characterization parameters of each construction link to provide data support for selecting whether to enable the dynamic update of the three-dimensional modeling tool when performing subsequent dynamic update of the three-dimensional GIM model of the target construction, and then adaptively selects the dynamic update method of the three-dimensional GIM model for the target construction, while ensuring reliability, reducing the data processing volume and improving the dynamic update efficiency of the three-dimensional GIM model.

[0043] Specifically, the process of determining the risk characteristics and highlighting the ranking sequence of each construction link of each type of target construction includes: Determine the risk characteristic parameters corresponding to each construction link of a single type of target construction; The risk characteristic characterization parameters are sorted in order from large to small to obtain a risk highlighting sorting sequence.

[0044] Specifically, the process of analyzing the actual image of the uploaded target type according to the determined construction risk cycle includes: In the first risk cycle, a risk feature highlighting ranking sequence is obtained based on the sample image information of the construction link of the corresponding type of target object, and the actual image of the corresponding construction link is sequentially called and compared with the local sample image information of the corresponding construction link according to the risk feature highlighting ranking sequence to determine whether there is any abnormality; In the second risk period, the actual image of the complete construction project of the target type uploaded by the user is obtained and compared with the complete sample image information of the corresponding construction project to determine whether there is any abnormality.

[0045] Specifically, in the first risk cycle, the process of determining whether there is an abnormality in the 3D GIM model includes: Determining a comparison order for actual images of the target object to be constructed based on the risk feature highlighting ranking sequence; The actual image of the corresponding construction link and the sample image information of the corresponding construction link are sequentially called for comparison according to the comparison order; If the similarity corresponding to the actual image of each construction link is greater than the preset construction link similarity standard threshold, the 3D GIM model is determined to meet the standard; If the similarity corresponding to the actual image of any construction link is less than the preset construction link similarity standard threshold, it is determined that there is an abnormality in the 3D GIM model, and the dynamic update of the 3D modeling tool is enabled.

[0046] In implementation, the similarity standard threshold for the construction link is pre-set, and several sample image information of the same type and the same construction link of the same target object are obtained in advance, and the mean similarity between the sample image information is determined. The ratio of the similarity mean to the offset coefficient is determined as the similarity standard threshold for the construction link, and the local image offset coefficient is selected between the interval [0.90, 0.95].

[0047] Specifically, the process of determining the comparison order of the actual images of the target object to be constructed according to the risk feature highlighting ranking sequence includes: The construction links corresponding to the risk highlighting sorting sequence are determined in sequence, the sorting of each construction link is obtained, and the serial number sorting of the construction link is generated; the sample images of the construction links are compared with the actual images in sequence.

[0048] Among them, each construction link corresponds to the construction link serial number one by one.

[0049] In implementation, optionally, The construction links can be assigned serial numbers. For example, the four construction links are: 1-foundation site construction link, 2-main structure construction link, 3-electrical installation construction link, and 4-full life cycle management equipment installation link. For example, the risk characteristic characterization parameter of the construction monitoring visualization foundation site construction link is 2.60, the risk characteristic characterization parameter of the construction monitoring visualization main structure construction link is 2.70, the risk characteristic characterization parameter of the construction monitoring visualization electrical installation construction link is 2.55, and the risk characteristic characterization parameter of the full life cycle management equipment installation link is 2.65; The corresponding feature prominence ranking sequence is 2.70, 2.65, 2.60, and 2.55; The corresponding parts are ranked as 2, 4, 1, and 3.

[0050] Specifically, in the second risk cycle, the process of determining whether there is an abnormality includes: If the similarity between the actual image of the complete construction project of the target object uploaded by the current user and the complete sample image information of the corresponding construction project is less than the preset complete construction similarity standard threshold, it is determined that an anomaly exists and the 3D modeling tool is enabled to dynamically update the 3D GIM model; If the similarity between the actual image of the complete construction project of the target object uploaded by the current user and the complete sample image information of the corresponding construction project is greater than or equal to the preset complete construction similarity standard threshold, it is determined that there is no abnormality and the dynamic update of the three-dimensional modeling tool is not enabled.

[0051] Specifically, the sample similarity standard threshold of the complete construction link is pre-set. Several complete sample image information of all construction links of the same type of target construction are obtained in advance, and the mean similarity between the complete sample image information is determined. The ratio of the similarity mean to the offset coefficient is determined as the construction chain link similarity standard threshold. The complete image offset coefficient is selected between the interval [1.10, 1.15].

[0052] Specifically, the actual images of the target object construction uploaded by the user terminal must include complete sample images of the target object construction project and local sample images of each construction link of the target object construction.

[0053] Thus far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art may make equivalent changes or substitutions to the relevant technical features, and the technical solutions after such changes or substitutions will fall within the scope of protection of the present invention.

Claims

1. A method for dynamically updating a three-dimensional GIM model for infrastructure, characterized in that: include: Extract sample image information of various construction links of various types of infrastructure objects to construct a 3D GIM model to determine the characteristic highlight factors of each construction link of different types of construction objects; Calculate the risk characteristic characterization parameters of each construction link of each type of target object based on the characteristic highlighting factor to determine the risk characteristic highlighting ranking sequence of each construction link of each type of target object; Obtaining the actual image of the target object uploaded by the user and the sample image information of the corresponding construction link, and obtaining the risk characteristic representation parameters of each construction link of the corresponding type of target object based on the sample image information; Determine a construction risk period based on the risk characteristic parameters, and analyze the uploaded actual image of the target object type according to the determined construction risk period to calculate the mean similarity to determine whether there is an anomaly; When an anomaly occurs, the 3D modeling tool is enabled to dynamically update the 3D GIM model; Among them, the process of obtaining the feature highlighting factor includes comparing the sample image information of each construction link of the construction of a single type of target object with the sample image information of the corresponding construction link of other types of target objects, solving the mean similarity, and obtaining the spatial complexity of each construction link of the construction of a single type of target object.

2. The method for dynamically updating a three-dimensional GIM model for infrastructure construction according to claim 1, characterized in that: The process of determining the construction risk period based on the risk characteristic parameters includes: Based on the sample image information uploaded by the user, the maximum risk characteristic parameters of each construction link of the corresponding type of target construction are obtained; If the maximum risk characteristic parameter is greater than a predetermined risk characteristic parameter threshold, it is determined to be the first risk period; If the maximum risk characteristic parameter is less than or equal to a predetermined risk characteristic parameter threshold, it is determined to be the second risk period.

3. The method for dynamically updating a three-dimensional GIM model for infrastructure construction according to claim 1, characterized in that: The process of obtaining the spatial complexity of each construction link of a single type of target construction includes: Calibrate the equipment space ratio and construction area of ​​a single construction link for a single type of target; Calculating the ratio of the equipment space ratio of the target object construction to a predetermined equipment space ratio threshold as a first space complexity factor; Calculating a ratio of a construction area of ​​the target object to a predetermined construction area threshold as a second spatial complexity factor; The first space complexity factor and the second space complexity factor are weighted and summed to determine the space complexity.

4. The method for dynamically updating a three-dimensional GIM model for infrastructure construction according to claim 3, characterized in that: The process of calculating the risk characteristic parameters of each construction link for each type of target includes: Obtain feature saliency factors, including similarity mean and spatial complexity; Determining a ratio of a preset similarity standard threshold to the similarity mean as a first feature highlighting factor; Determining a ratio of the spatial complexity to a preset spatial complexity standard threshold as a second feature highlighting factor; The sum of the first feature highlighting factor and the second feature highlighting factor is determined as the risk feature characterization parameter.

5. The method for dynamically updating a three-dimensional GIM model for infrastructure construction according to claim 1, characterized in that: The process of determining the risk characteristics and highlighting the ranking sequence of each construction link of each type of target construction includes: Determine the risk characteristic parameters corresponding to each construction link of a single type of target construction; The risk characteristic characterization parameters are sorted in order from large to small to obtain a risk highlighting sorting sequence.

6. The method for dynamically updating a three-dimensional GIM model for infrastructure construction according to claim 2, characterized in that: The process of analyzing the actual image of the uploaded target type according to the determined construction risk cycle includes: In the first risk cycle, a risk feature highlighting ranking sequence is obtained based on the sample image information of the construction link of the corresponding type of target object, and the actual image of the corresponding construction link is sequentially called and compared with the local sample image information of the corresponding construction link according to the risk feature highlighting ranking sequence to determine whether there is any abnormality; In the second risk period, the actual image of the complete construction project of the target type uploaded by the user is obtained and compared with the complete sample image information of the corresponding construction project to determine whether there is any abnormality.

7. The method for dynamically updating a three-dimensional GIM model for infrastructure construction according to claim 6, characterized in that: In the first risk cycle, the process of determining whether there is an abnormality includes, Determining a comparison order for actual images of the target object to be constructed based on the risk feature highlighting ranking sequence; The actual image of the corresponding construction link and the sample image information of the corresponding construction link are sequentially called for comparison according to the comparison order; If the similarity corresponding to the actual image of any construction link is less than the preset construction link similarity standard threshold, it is determined that an abnormality exists.

8. The method for dynamically updating a three-dimensional GIM model for infrastructure construction according to claim 6, characterized in that: The process of determining the comparison order of the actual images of the target object to be constructed according to the risk feature highlighting ranking sequence includes: Determine the risk highlighting ranking sequence in sequence, determine the corresponding construction links in sequence, and compare the sample images of the construction links with the actual images in sequence.

9. The method for dynamically updating a three-dimensional GIM model for infrastructure construction according to claim 6, wherein: In the second risk cycle, the process of determining whether there is an abnormality includes: If the similarity between the actual image of the complete construction project of the target object uploaded by the current user and the complete sample image information of the corresponding construction project is less than the preset complete construction similarity standard threshold, it is determined that an abnormality exists.

10. The method for dynamically updating a three-dimensional GIM model for infrastructure construction according to claim 1, characterized in that: The actual images of the target object construction uploaded by the user terminal include complete sample images of the target object construction project and local sample images of each construction link of the target object construction.

Images