BIM-based traffic engineering electronic sand table simulation and analysis system

Abstract

The invention relates to a BIM-based traffic engineering electronic sand table simulation and analysis system, and relates to the technical field of traffic engineering data processing, and the method comprises the steps: obtaining a calibration influence range, collecting a building layout topology according to the calibration influence range, carrying out the sample matching, obtaining a first-stage sample traffic flow recording data set, and a second-stage sample traffic flow recording data set, recursive fusion is carried out to obtain a traffic flow calibration result; obtaining a first traffic engineering BIM model of the sand table simulation area; performing a traffic test according to the traffic flow calibration result to obtain a first sand table simulation test result; and when the first sand table simulation test result is a test qualified identifier, sending the first traffic engineering BIM model to a traffic engineering layout design client. The technical problem that in the prior art, due to the fact that traffic engineering electronic sand table simulation depends on subjective set cases, the number of iterative optimization times in the subsequent traffic engineering model application process is large is solved.

Description

Technical Field

[0001] The present invention relates to the field of traffic engineering data processing, and in particular to a traffic engineering electronic sandbox simulation and analysis system based on BIM. Background Art

[0002] With the development of information technology, electronic sandbox simulation technology for traffic engineering based on building information modeling (BIM) has emerged. It simulates traffic flow, traffic management and planning by creating digital models to improve the accuracy and efficiency of design.

[0003] Although the application of BIM technology in traffic engineering provides a more intuitive means of simulation and analysis, the existing electronic sandbox simulation system still relies on subjective experience when configuring use cases and lacks sufficient consideration of the complexity of actual traffic scenarios. This approach may result in the designed traffic road layout requiring multiple iterative adjustments in actual applications, thereby reducing work efficiency and project progress. Summary of the invention

[0004] The present invention aims to solve the technical problem in the prior art that the electronic sandbox simulation of traffic engineering relies on subjectively set use cases, resulting in a large number of iterative optimization times in the subsequent traffic engineering model application process, and provides a BIM-based electronic sandbox simulation and analysis system for traffic engineering to solve the problem.

[0005] The technical solution of the present invention to solve the above technical problems is as follows:

[0006] The present invention provides a traffic engineering electronic sandbox simulation and analysis system based on BIM, and the system execution steps include: performing an influence range analysis based on a sandbox simulation area to obtain a calibrated influence range, and collecting a building layout topology according to the calibrated influence range; performing a first-level matching of associated samples according to the building layout topology to obtain a first-level sample traffic flow record data set, wherein the first-level sample traffic flow record data set has a building layout topology label set; based on the building layout topology label set, traversing the first-level sample traffic flow record data set to perform a second-level matching of associated samples to obtain a second-level sample traffic flow record data set; recursively fusing the first-level sample traffic flow record data set and the second-level sample traffic flow record data set to obtain a traffic flow calibration result; obtaining a first traffic engineering BIM model in a sandbox simulation area; performing a traffic test on the first traffic engineering BIM model according to the traffic flow calibration result to obtain a first sandbox simulation test result; when the first sandbox simulation test result is a test pass mark, sending the first traffic engineering BIM model to a traffic engineering layout design client.

[0007] The beneficial effects of the present invention are: by utilizing two-level scene sample matching, traffic flow calibration results of associated samples are collected; the traffic flow calibration results are used as use cases for traffic engineering sandbox simulation tests, and the first traffic engineering BIM model is further optimized based on the test results. The traffic engineering sandbox simulation test cases determined by big data are more objective, which can improve the stability of the test results and achieve the technical effect of reducing the number of optimization times when the subsequent first traffic engineering BIM model is applied. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Figure 1 A flow chart of the BIM-based traffic engineering electronic sandbox simulation and analysis system provided by the present invention;

[0009] Figure 2 A schematic diagram of the structure of an electronic device provided by the present invention;

[0010] Figure 3 A schematic diagram of the structure of a computer-readable storage medium provided by the present invention.

[0011] In the accompanying drawings, the components represented by the reference numerals are described as follows:

[0012] Electronic device 500 , memory 510 , processor 520 , first computer program 511 , computer-readable storage medium 600 , second computer program 611 . DETAILED DESCRIPTION

[0013] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0014] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0015] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or explanation". Any embodiment described as "for example" in the present invention is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present invention.

[0016] Embodiment 1:

[0017] like Figure 1 As shown, the embodiment of the present invention provides a BIM-based traffic engineering electronic sandbox simulation and analysis system, and the system execution steps include:

[0018] S10: performing influence range analysis based on the sandbox simulation area to obtain a calibrated influence range, and collecting building layout topology according to the calibrated influence range;

[0019] Further, based on the sandbox simulation area, an impact range analysis is performed to obtain a calibrated impact range. Step S10 includes:

[0020] Step 1: Setting a first radius constraint interval through a user terminal, wherein the first radius constraint interval includes a first radius lower limit value and a first radius upper limit value;

[0021] Step 2: taking the median of the first radius constraint interval to obtain a first median radius;

[0022] Step 3: construct a first influence range to be analyzed with the first median radius, and overlap the center of the sandbox simulation area with the center of the first influence range to be analyzed to obtain a pseudo-circular area;

[0023] Step 4: Perform flow correlation analysis on the pseudo-circular area and the sandbox simulation area to obtain a Pearson correlation coefficient;

[0024] Step 5A: when the Pearson correlation coefficient is less than or equal to the Pearson correlation coefficient threshold, constructing a second radius constraint interval based on the first radius lower limit value and the first median radius;

[0025] Step 6A: When the interval step length of the second radius constraint interval is greater than or equal to the convergence step length threshold, the second radius constraint interval is returned to step 2 to execute a loop;

[0026] Step 7A: When the interval step size of the second radius constraint interval is less than the convergence step size threshold, the median value of the second radius constraint interval is taken to configure the calibrated influence range for the sandbox simulation area.

[0027] Furthermore, the step S10 execution step further includes:

[0028] Step 5B: when the Pearson correlation coefficient is greater than the Pearson correlation coefficient threshold, constructing a third radius constraint interval based on the first median radius and the first radius upper limit value;

[0029] Step 6B: When the interval step length of the third radius constraint interval is greater than or equal to the convergence step length threshold, the third radius constraint interval is returned to step 2 to execute a loop;

[0030] Step 7B: When the interval step size of the third radius constraint interval is less than the convergence step size threshold, the median value of the third radius constraint interval is taken to configure the calibrated influence range for the sandbox simulation area.

[0031] Specifically, the sandbox simulation area refers to the specific geographical area used to simulate traffic flow and layout in the electronic sandbox simulation system of traffic engineering; the calibrated influence range refers to the surrounding geographical range that will affect the traffic flow in the sandbox simulation area; the building layout topology refers to the collection of layout information of buildings within the calibrated influence range, including the location, shape and mutual connection relationship of the buildings.

[0032] The impact range analysis process is as follows:

[0033] The user end refers to the operation interface that allows users to input and adjust parameters; the first radius constraint interval refers to a range defined by the user. This range is defined by the length of the radius and is used to preliminarily determine the impact range of the sandbox simulation area; the first radius lower limit value and the first radius upper limit value are the two boundary values ​​of this constraint interval, representing the possible minimum and maximum radii of the impact range respectively. Generally speaking, the minimum radius defaults to 0m and the maximum radius defaults to 300000m.

[0034] In detail, the user inputs two key parameters - the lower limit and upper limit of the first radius - by operating the user-side interface. Based on the lower limit and upper limit of the first radius, the first radius constraint interval is constructed. A preliminary circular area is defined by the first radius constraint interval. This area is considered to be the geographical scope that may be affected by the sandbox simulation area, which is conducive to screening out areas that have a real impact on traffic flow within a wide geographical range, thereby providing a reasonable starting point for subsequent detailed analysis and simulation.

[0035] Taking the median means calculating the geometric midpoint of the first radius constraint interval, that is, the average of the first radius lower limit value and the first radius upper limit value. The first median radius is this median value, which represents the central radius value of the sandbox simulation area influence range in the preliminary analysis. This value will be used to construct the influence range to be analyzed.

[0036] The first impact range to be analyzed refers to the circular area determined by using this median radius with the sandbox simulation area as the center. This area will be used for further traffic flow analysis; the pseudo-annular area refers to the annular area between the center of the sandbox simulation area and the center of the first impact range to be analyzed after the two overlap. This annular area represents the area within a certain range outside the sandbox simulation area. Together with the sandbox simulation area, it constitutes a complete analysis area.

[0037] A first traffic flow record data set of the pseudo-circular area and a second traffic flow record data set of the sandbox simulation area are collected, and the first traffic flow record data set corresponds to the second traffic flow record data set one-to-one at the collection time; the first traffic flow record data set is arranged from small to large to construct a first traffic flow record data sequence; according to the one-to-one correspondence at the collection time, the second traffic flow record data set is sorted based on the first traffic flow record data sequence to obtain a second traffic flow record data sequence.

[0038] Furthermore, the Pearson correlation analysis function is obtained: Among them, r represents the Pearson correlation coefficient, x i The i-th traffic flow record data representing the first traffic flow record data sequence, y i the i-th traffic flow record data representing the second traffic flow record data sequence, a mean value of the traffic flow record data representing the first traffic flow record data sequence, The traffic flow record data mean value representing the second traffic flow record data sequence is processed according to the Pearson correlation analysis function to obtain the Pearson correlation coefficient.

[0039] Generally speaking, if the correlation is stronger, the traffic flow in the pseudo-circular area is larger, and the traffic flow in the sandbox simulation area is larger, so there is only a positive correlation between the two, so the analysis results of the negative correlation are treated as a weak correlation. Preferably, the Pearson correlation coefficient threshold is set by the user, and the default is 0.2, and the convergence step threshold is set by the user, and the default is 2000m;

[0040] In one implementation, when the Pearson correlation coefficient is less than or equal to the Pearson correlation coefficient threshold, it means that the radius is large, so there is no correlation, so the radius needs to be reduced. At this time, a second radius constraint interval is constructed based on the first radius lower limit and the first median radius. Then, if the interval step of the second radius constraint interval is greater than or equal to the convergence step threshold, it means that the constraint interval is still large and cannot converge, and the second radius constraint interval is returned to step 2 to execute the loop. When the interval step of the second radius constraint interval is less than the convergence step threshold, it means that the constraint interval can converge, and the median of the second radius constraint interval is taken to configure the calibrated influence range for the sandbox simulation area. At this time, the calibrated influence range has a greater impact on the flow of the sandbox simulation area, which can ensure the accuracy of the subsequent sandbox simulation.

[0041] In another implementation, when the Pearson correlation coefficient is greater than the Pearson correlation coefficient threshold, it indicates that the correlation is strong and the radius needs to be increased to continue the analysis. At this time, a third radius constraint interval is constructed based on the first median radius and the first radius upper limit value. Similarly, when the interval step of the third radius constraint interval is greater than or equal to the convergence step threshold, the third radius constraint interval is returned to step 2 to execute the loop; when the interval step of the third radius constraint interval is less than the convergence step threshold, the median value of the third radius constraint interval is taken to configure the calibrated influence range for the sandbox simulation area.

[0042] By accurately identifying the impact range, it can be ensured that the traffic flow data subsequently counted are all within the impact range, avoiding interference from redundant data, thereby improving the accuracy of the analysis results.

[0043] S20: performing primary matching of associated samples according to the building layout topology to obtain a primary sample traffic flow record data set, wherein the primary sample traffic flow record data set has a building layout topology label set;

[0044] Specifically, building layout topology refers to the spatial layout and interconnected structure of buildings in the sandbox simulation area; associated sample first-level matching refers to comparing the building layout topology of the sandbox simulation area with historical or existing traffic flow data to find sample data sets with similar building layout characteristics; first-level sample traffic flow record data sets refer to traffic flow data sets similar to the building layout topology of the sandbox simulation area obtained after first-level matching; building layout topology label set refers to the set of building layout features corresponding to the first-level sample traffic flow record data set, and these labels are used to identify and distinguish different building layout topology features. The first-level sample traffic flow record data set obtained through first-level matching can be used as the basis for traffic flow prediction and analysis in the sandbox simulation area.

[0045] S30: Based on the building layout topology label set, traverse the first-level sample traffic flow record data set to perform secondary matching of associated samples to obtain a second-level sample traffic flow record data set;

[0046] Specifically, the associated sample secondary matching refers to further refining the matching process on the basis of the primary matching to find samples similar to the building layout topology label set; the secondary sample traffic flow record dataset refers to the traffic flow dataset obtained after the secondary matching and matched with the building layout topology label set.

[0047] S40: recursively merge the first-level sample traffic flow record data set and the second-level sample traffic flow record data set to obtain a traffic flow calibration result;

[0048] Furthermore, the first-level sample traffic flow record data set and the second-level sample traffic flow record data set are recursively merged to obtain a traffic flow calibration result, and the execution steps include:

[0049] Grouping the secondary sample traffic flow record data set according to the primary sample traffic flow record data set to obtain multiple groups of secondary sample traffic flow record data;

[0050] Performing mode analysis on the multiple groups of secondary sample traffic flow record data respectively to obtain multiple secondary sample traffic flow mode values;

[0051] A mode analysis is performed on the plurality of secondary sample traffic flow mode values ​​and the primary sample traffic flow record data set to obtain the traffic flow calibration result.

[0052] Specifically, the traffic flow calibration result represents the result of recursively fusing the first-level sample traffic flow record data set and the second-level sample traffic flow record data set, and the detailed process is as follows: since each first-level sample traffic flow record data corresponds to multiple second-level sample traffic flow record data, the second-level sample traffic flow record data set is firstly grouped according to the first-level sample traffic flow record data set to obtain multiple groups of second-level sample traffic flow record data; further, each group of the multiple groups of second-level sample traffic flow record data is subjected to mode analysis to obtain multiple second-level sample traffic flow mode values; further, the multiple second-level sample traffic flow mode values ​​are subjected to mode analysis with the first-level sample traffic flow record data set to obtain the traffic flow calibration result.

[0053] The mode analysis process is preferably as follows:

[0054] Taking the mode analysis of any group of secondary sample traffic flow record data as an example, the user presets a traffic flow deviation threshold, and then performs cluster analysis on a group of secondary sample traffic flow record data according to the traffic flow deviation threshold to obtain multiple clusters of secondary sample traffic flow record data; then delete the clusters whose number of samples in the cluster is less than the fitting number threshold preset by the user to obtain updated multiple clusters of secondary sample traffic flow record data, and perform mean calculation on the retained multiple clusters of secondary sample traffic flow record data to obtain the mode value of the secondary sample traffic flow of the corresponding group.

[0055] Through two-level sampling, the data volume is increased to ensure objectivity, and the traffic flow calibration results obtained through recursive fusion can provide more reliable test cases for subsequent sandbox simulations.

[0056] S50: Obtaining a first traffic engineering BIM model of the sandbox simulation area;

[0057] S60: performing a traffic test on the first traffic engineering BIM model according to the traffic flow calibration result to obtain a first sandbox simulation test result;

[0058] S70: When the first sandbox simulation test result is a test pass mark, the first traffic engineering BIM model is sent to the traffic engineering layout design client.

[0059] Specifically, the first traffic engineering BIM model refers to the traffic engineering design model to be constructed, and the traffic test refers to the traffic simulation on the first traffic engineering BIM model according to the traffic flow calibration results, and the test indicators of the simulation process are collected, preferably including traffic volume, average vehicle speed, number of vehicles per unit length of road, ratio of real-time density to road congestion density, etc., and the threshold range of each test indicator is set through the user terminal; when any one of the test indicators does not belong to the corresponding test indicator threshold range, the first sand table simulation test result is a test failure mark, otherwise the first sand table simulation test result is a test pass mark. Since the sand table simulation of traffic is relatively mature, it will not be elaborated here.

[0060] The traffic engineering layout design client refers to the traffic engineering layout management terminal. When the first sandbox simulation test result is a qualified test mark, it means that the current design can meet the needs of most traffic flows. At this time, the first traffic engineering BIM model can be sent to the traffic engineering layout design client.

[0061] Furthermore, the execution step further includes step S80, and step S80 further includes the steps of:

[0062] S81: When the first sandbox simulation test result is a test failure mark, traffic topology optimization is performed on the first traffic engineering BIM model to obtain a second traffic engineering BIM model, wherein the second sandbox simulation test result of the second traffic engineering BIM model is a test pass mark;

[0063] S82: Send the second traffic engineering BIM model to the traffic engineering layout design client.

[0064] Further, when the first sandbox simulation test result is a test failure mark, the first traffic engineering BIM model is subjected to traffic topology optimization to obtain a second traffic engineering BIM model, and the execution steps include:

[0065] Performing several random adjustments on the first traffic engineering BIM model to obtain several initial traffic engineering BIM models;

[0066] According to the traffic flow calibration results, the several initial traffic engineering BIM models are traversed to perform traffic tests to obtain several sandbox simulation test results;

[0067] When any one of the plurality of sandbox simulation test results is marked as a qualified test, the second traffic engineering BIM model is obtained;

[0068] When the results of the sandbox simulation tests are all marked as unqualified tests, a topological taboo neighborhood is configured for the initial traffic engineering BIM models based on a taboo structure similarity threshold, wherein the traffic engineering BIM models whose topological structure similarity between the topological taboo neighborhood representation and the initial traffic engineering BIM models is less than or equal to the taboo structure similarity threshold do not participate in the subsequent traffic topology optimization;

[0069] A traffic topology optimization cycle is performed on the first traffic engineering BIM model according to the topological taboo neighborhood.

[0070] Specifically, when the first sandbox simulation test result is a test failure mark, it means that the first traffic engineering BIM model still needs to be optimized. At this time, the traffic topology of the first traffic engineering BIM model is optimized to obtain the second traffic engineering BIM model, wherein the second traffic engineering BIM model is the optimized traffic engineering BIM model, and the second sandbox simulation test result of the second traffic engineering BIM model is a test pass mark, and then the second traffic engineering BIM model is sent to the traffic engineering layout design client.

[0071] The traffic topology optimization process is as follows:

[0072] Random adjustment: The first traffic engineering BIM model is randomly adjusted multiple times to generate multiple initial traffic engineering BIM models. The purpose of this step is to explore different traffic layout possibilities.

[0073] Traffic test: Based on the traffic flow calibration results, traffic tests are conducted on each initial traffic engineering BIM model to obtain several sandbox simulation test results. This step aims to evaluate the traffic performance of each initial model.

[0074] Result evaluation: Check the sandbox simulation test results. If any result is marked as a qualified test, the corresponding BIM model will be determined as the second transportation engineering BIM model.

[0075] Configure topological taboo neighborhood: If all sandbox simulation test results are marked as test failure, the topological taboo neighborhood is determined based on the taboo structure similarity threshold to exclude models whose topological structures are too similar to the initial model.

[0076] Optimization loop: Based on the topological taboo neighborhood, the first traffic engineering BIM model is continuously subjected to traffic topology optimization loops until a model that meets the test requirements is found.

[0077] Preferably, a structural similarity analysis function is constructed: Among them, SIM represents the structural similarity, A and B represent two topological structures respectively, |A| represents the volume of topological structure A, |B| represents the volume of topological structure B, and |A∩B| represents the intersection volume of A and B.

[0078] Finding better traffic layout solutions through random adjustment and iterative optimization helps to systematically explore the space of possible solutions and gradually approach the optimal solution. By excluding models with high structural similarity, it can avoid falling into local optimality, thereby increasing the probability of finding the global optimal solution. This step reflects the flexibility and adaptability of the solution, and can continuously adjust and optimize the BIM model according to the test results until it meets the needs of actual traffic engineering.

[0079] Further, first-level matching of associated samples is performed according to the building layout topology to obtain a first-level sample traffic flow record data set, and the execution steps include:

[0080] Obtain building layout topology labels and traffic flow record data of samples to be analyzed;

[0081] Performing similarity binary evaluation on the building layout topology label and the building layout topology to obtain similarity binary parameters;

[0082] When the similarity binary parameter is 1, the traffic flow record data is added to the primary sample traffic flow record data set;

[0083] When the similarity binary parameter is 0, the sample to be analyzed is updated.

[0084] Specifically, traffic flow record data refers to data that records traffic flow within a specific time period. These data can be used to analyze traffic patterns and trends. Similarity binary evaluation is an evaluation method used to quantify the similarity between two building layout topologies, which usually produces a parameter between 0 and 1, called the similarity binary parameter. When the similarity binary parameter is 1, it means that the two building layout topologies are exactly the same; when it is 0, it means that they are completely different. The first-level sample traffic flow record dataset refers to a traffic flow dataset that is similar to the building layout topology of the sandbox simulation area after the first-level matching.

[0085] The specific steps of associated sample matching are as follows:

[0086] Data acquisition: First, collect the building layout topology labels and corresponding traffic flow record data of the samples to be analyzed.

[0087] Similarity evaluation: Next, a similarity binary evaluation is performed on the collected building layout topology labels and the building layout topology of the sandbox simulation area to calculate a similarity binary parameter.

[0088] Dataset Updates:

[0089] If the similarity binary parameter is 1, that is, the sample to be analyzed completely matches the building layout topology of the sandbox simulation area, then the traffic flow record data of the sample is added to the first-level sample traffic flow record data set.

[0090] If the similarity binary parameter is 0, that is, the sample to be analyzed does not match the architectural layout topology of the sandbox simulation area at all, then the sample to be analyzed needs to be updated, possibly by reselecting the sample or adjusting the architectural layout topology label of the sample to improve the matching accuracy.

[0091] Further, similarity binary evaluation is performed on the building layout topology label and the building layout topology to obtain similarity binary parameters, and the execution steps include:

[0092] Obtaining a building layout topology comparison network, wherein the building layout topology comparison network includes a first topology feature extraction channel, a second topology feature extraction channel and a similarity binary channel, and the first topology feature extraction channel and the second topology feature extraction channel are twin neural networks;

[0093] Inputting the building layout topology label into the first topology feature extraction channel to obtain a first topology feature;

[0094] Inputting the building layout topology into the second topological feature extraction channel to obtain a second topological feature;

[0095] The first topological feature and the second topological feature are input into the similarity binary channel to obtain the similarity binary parameter, wherein when the structural similarity is greater than or equal to the structural similarity threshold, the similarity binary parameter is equal to 1, and when the structural similarity is less than the structural similarity threshold, the similarity binary parameter is equal to 0.

[0096] Specifically, the building layout topology comparison network refers to a specially designed neural network architecture for comparing and evaluating the similarity between two building layout topologies; the first topology feature extraction channel and the second topology feature extraction channel are two parts in the comparison network, which process the building layout topology label and the actual building layout respectively to extract key features; the twin neural network refers to two neural networks with the same structure but processing different inputs, which are used here to extract and compare the features of the building layout; the similarity binary channel is another part in the comparison network, which receives the outputs of the two topology feature extraction channels and calculates a similarity binary parameter; the structural similarity refers to the degree of structural similarity between two building layout topologies, and the structural similarity threshold is a preset standard used to determine whether the two layouts are similar enough; the structural similarity is preferably calculated by the aforementioned structural similarity analysis function.

[0097] The similarity binary channel of the building layout topology comparison network is a linear analysis channel constructed based on the structural similarity analysis function. The first topology feature extraction channel and the second topology feature extraction channel are machine learning networks trained based on the building layout topology historical data and the topology feature identification data. Preferably, the convolutional neural network is trained with the topology feature identification data as supervision and the building layout topology historical data as input to obtain the first topology feature extraction channel and the second topology feature extraction channel.

[0098] The specific steps are as follows:

[0099] Feature extraction:

[0100] The building layout topology labels are input into the first topology feature extraction channel to extract topology features related to the labels.

[0101] The actual building layout is input into the second topological feature extraction channel to extract the topological features of the actual layout.

[0102] Similarity evaluation: The topological features obtained by the two topological feature extraction channels are input into the similarity binary channel, which will calculate a similarity binary parameter based on the comparison result of the structural similarity and the preset structural similarity threshold, as follows:

[0103] If the structural similarity is greater than or equal to the structural similarity threshold, the similarity binary parameter is set to 1, indicating that the two building layout topologies are sufficiently similar.

[0104] If the structural similarity is less than the structural similarity threshold, the similarity binary parameter is set to 0, indicating that the two building layout topologies are not similar.

[0105] The BIM-based traffic engineering electronic sandbox simulation and analysis system provided by the embodiment of the present invention has at least the following technical effects:

[0106] 1. By utilizing two-level scene sample matching, the traffic flow calibration results of related samples are collected; the traffic flow calibration results are used as use cases for the traffic engineering sandbox simulation test, and the first traffic engineering BIM model is further optimized based on the test results. The traffic engineering sandbox simulation test cases determined by big data are more objective, which can improve the stability of the test results and achieve the technical effect of reducing the number of optimization times when the subsequent first traffic engineering BIM model is applied.

[0107] 2. Finding better traffic layout solutions through random adjustment and iterative optimization. This method helps to systematically explore the space of possible solutions and gradually approach the optimal solution. By excluding models with high structural similarity, it can avoid falling into local optimality, thereby increasing the probability of finding the global optimal solution. This step reflects the flexibility and adaptability of the solution, and can continuously adjust and optimize the BIM model according to the test results until it meets the needs of actual traffic engineering.

[0108] Embodiment 2:

[0109] See also Figure 2 , Figure 2 Schematic diagram of an electronic device provided by an embodiment of the present invention. Figure 2 As shown, an embodiment of the present invention provides an electronic device 500, including a memory 510, a processor 520, and a first computer program 511 stored in the memory 510 and executable on the processor 520. When the processor 520 executes the first computer program 511, the following steps are implemented:

[0110] Performing an influence range analysis based on the sandbox simulation area to obtain a calibrated influence range, and collecting the building layout topology based on the calibrated influence range;

[0111] Performing primary matching of associated samples according to the building layout topology to obtain a primary sample traffic flow record data set, wherein the primary sample traffic flow record data set has a building layout topology label set;

[0112] Based on the building layout topology label set, traverse the first-level sample traffic flow record data set to perform secondary matching of associated samples to obtain a second-level sample traffic flow record data set;

[0113] Recursively merging the first-level sample traffic flow record data set and the second-level sample traffic flow record data set to obtain a traffic flow calibration result;

[0114] Obtain the first traffic engineering BIM model of the sandbox simulation area;

[0115] Performing a traffic test on the first traffic engineering BIM model according to the traffic flow calibration result to obtain a first sandbox simulation test result;

[0116] When the first sandbox simulation test result is marked as a qualified test, the first traffic engineering BIM model is sent to the traffic engineering layout design client.

[0117] Embodiment three:

[0118] See also Figure 3 , Figure 3 A schematic diagram of an embodiment of a computer-readable storage medium provided in an embodiment of the present invention. Figure 3 As shown, this embodiment provides a computer-readable storage medium 600, on which a second computer program 611 is stored. When the second computer program 611 is executed by a processor, the following steps are implemented:

[0119] Performing an influence range analysis based on the sandbox simulation area to obtain a calibrated influence range, and collecting the building layout topology based on the calibrated influence range;

[0120] Performing primary matching of associated samples according to the building layout topology to obtain a primary sample traffic flow record data set, wherein the primary sample traffic flow record data set has a building layout topology label set;

[0121] Based on the building layout topology label set, traverse the first-level sample traffic flow record data set to perform secondary matching of associated samples to obtain a second-level sample traffic flow record data set;

[0122] Recursively merging the first-level sample traffic flow record data set and the second-level sample traffic flow record data set to obtain a traffic flow calibration result;

[0123] Obtain the first traffic engineering BIM model of the sandbox simulation area;

[0124] Performing a traffic test on the first traffic engineering BIM model according to the traffic flow calibration result to obtain a first sandbox simulation test result;

[0125] When the first sandbox simulation test result is marked as a qualified test, the first traffic engineering BIM model is sent to the traffic engineering layout design client.

[0126] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0127] Those skilled in the art will appreciate that embodiments of the present invention may be provided as systems, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0128] The present invention is described with reference to flowcharts and / or block diagrams of systems, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0129] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0130] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0131] Although preferred embodiments of the present invention have been described, additional changes and modifications may occur to these embodiments once those skilled in the art understand the basic inventive concepts.

[0132] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention belong to the scope of the present invention and its equivalent technologies, the present invention is also intended to include these changes and variations.

Claims

1. The BIM-based traffic engineering electronic sandbox simulation and analysis system is characterized by: The system execution steps include: Performing an influence range analysis based on the sandbox simulation area to obtain a calibrated influence range, and collecting the building layout topology based on the calibrated influence range; Performing primary matching of associated samples according to the building layout topology to obtain a primary sample traffic flow record data set, wherein the primary sample traffic flow record data set has a building layout topology label set; Based on the building layout topology label set, traverse the first-level sample traffic flow record data set to perform secondary matching of associated samples to obtain a second-level sample traffic flow record data set; Recursively merging the first-level sample traffic flow record data set and the second-level sample traffic flow record data set to obtain a traffic flow calibration result; Obtain the first traffic engineering BIM model of the sandbox simulation area; Performing a traffic test on the first traffic engineering BIM model according to the traffic flow calibration result to obtain a first sandbox simulation test result; When the first sandbox simulation test result is marked as a qualified test, the first traffic engineering BIM model is sent to the traffic engineering layout design client.

2. The system according to claim 1, characterized in that The execution steps also include: When the first sandbox simulation test result is a test failure mark, traffic topology optimization is performed on the first traffic engineering BIM model to obtain a second traffic engineering BIM model, wherein the second sandbox simulation test result of the second traffic engineering BIM model is a test pass mark; The second traffic engineering BIM model is sent to the traffic engineering layout design client.

3. The system according to claim 1, characterized in that Perform an impact range analysis based on the sandbox simulation area to obtain a calibrated impact range. The execution steps include: Step 1: Setting a first radius constraint interval through a user terminal, wherein the first radius constraint interval includes a first radius lower limit value and a first radius upper limit value; Step 2: taking the median of the first radius constraint interval to obtain a first median radius; Step 3: construct a first influence range to be analyzed with the first median radius, and overlap the center of the sandbox simulation area with the center of the first influence range to be analyzed to obtain a pseudo-circular area; Step 4: Perform flow correlation analysis on the pseudo-circular area and the sandbox simulation area to obtain a Pearson correlation coefficient; Step 5A: when the Pearson correlation coefficient is less than or equal to the Pearson correlation coefficient threshold, constructing a second radius constraint interval based on the first radius lower limit value and the first median radius; Step 6A: When the interval step length of the second radius constraint interval is greater than or equal to the convergence step length threshold, the second radius constraint interval is returned to step 2 to execute a loop; Step 7A: When the interval step size of the second radius constraint interval is less than the convergence step size threshold, the median value of the second radius constraint interval is taken to configure the calibrated influence range for the sandbox simulation area.

4. The system according to claim 3, characterized in that The execution steps also include: Step 5B: when the Pearson correlation coefficient is greater than the Pearson correlation coefficient threshold, constructing a third radius constraint interval based on the first median radius and the first radius upper limit value; Step 6B: When the interval step length of the third radius constraint interval is greater than or equal to the convergence step length threshold, the third radius constraint interval is returned to step 2 to execute a loop; Step 7B: When the interval step size of the third radius constraint interval is less than the convergence step size threshold, the median value of the third radius constraint interval is taken to configure the calibrated influence range for the sandbox simulation area.

5. The system according to claim 1, wherein: According to the building layout topology, the associated samples are matched at the first level to obtain a first level sample traffic flow record data set, and the execution steps include: Obtain building layout topology labels and traffic flow record data of samples to be analyzed; Performing similarity binary evaluation on the building layout topology label and the building layout topology to obtain similarity binary parameters; When the similarity binary parameter is 1, the traffic flow record data is added to the primary sample traffic flow record data set; When the similarity binary parameter is 0, the sample to be analyzed is updated.

6. The system according to claim 5, characterized in that Performing similarity binary evaluation on the building layout topology label and the building layout topology to obtain similarity binary parameters, the execution steps include: Obtaining a building layout topology comparison network, wherein the building layout topology comparison network includes a first topology feature extraction channel, a second topology feature extraction channel and a similarity binary channel, and the first topology feature extraction channel and the second topology feature extraction channel are twin neural networks; Inputting the building layout topology label into the first topology feature extraction channel to obtain a first topology feature; Inputting the building layout topology into the second topological feature extraction channel to obtain a second topological feature; The first topological feature and the second topological feature are input into the similarity binary channel to obtain the similarity binary parameter, wherein when the structural similarity is greater than or equal to the structural similarity threshold, the similarity binary parameter is equal to 1, and when the structural similarity is less than the structural similarity threshold, the similarity binary parameter is equal to 0.

7. The system according to claim 1, characterized in that Recursively merging the first-level sample traffic flow record data set and the second-level sample traffic flow record data set to obtain a traffic flow calibration result, the execution steps comprising: Grouping the secondary sample traffic flow record data set according to the primary sample traffic flow record data set to obtain multiple groups of secondary sample traffic flow record data; Performing mode analysis on the multiple groups of secondary sample traffic flow record data respectively to obtain multiple secondary sample traffic flow mode values; A mode analysis is performed on the plurality of secondary sample traffic flow mode values ​​and the primary sample traffic flow record data set to obtain the traffic flow calibration result.

8. The system according to claim 2, characterized in that When the first sandbox simulation test result is a test failure mark, traffic topology optimization is performed on the first traffic engineering BIM model to obtain a second traffic engineering BIM model, and the execution steps include: Performing several random adjustments on the first traffic engineering BIM model to obtain several initial traffic engineering BIM models; According to the traffic flow calibration results, the several initial traffic engineering BIM models are traversed to perform traffic tests to obtain several sandbox simulation test results; When any one of the plurality of sandbox simulation test results is marked as a qualified test, the second traffic engineering BIM model is obtained; When the results of the sandbox simulation tests are all marked as unqualified tests, a topological taboo neighborhood is configured for the initial traffic engineering BIM models based on a taboo structure similarity threshold, wherein the traffic engineering BIM models whose topological structure similarity between the topological taboo neighborhood representation and the initial traffic engineering BIM models is less than or equal to the taboo structure similarity threshold do not participate in the subsequent traffic topology optimization; A traffic topology optimization cycle is performed on the first traffic engineering BIM model according to the topological taboo neighborhood.

Images