Regional highway data modeling method and system based on GIS and BIM

Abstract

The invention relates to the technical field of digital model processing, in particular to a regional highway data modeling method and system based on GIS and BIM, and the method mainly comprises the steps of building a BIM model and building an engineering scene of a regional highway based on a GIS system. Obtaining predicted traffic flow data of each unit road section at a corresponding moment through a neural network prediction model, setting a traffic flow threshold value of each unit road section, and judging whether to send a traffic flow early warning signal or not through the predicted traffic flow data and the traffic flow threshold value; and determining whether to generate a traffic flow distribution planning route according to whether an immersion phenomenon occurs and whether a traffic flow early warning signal occurs in combination with whether the immersion phenomenon occurs. According to the method, more reference data during road use are fused, additional functions of traffic flow prediction and traffic flow distribution and control are realized, the data are accessed in real time through the universal database, the calculability of traffic BIM data is improved, and the interactivity and convenience of BIM model attributes and real-time services are enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of digital model processing, and in particular to a regional highway data modeling method and system based on GIS and BIM. Background Art

[0002] BIM is a building information model, which is a method of integrating buildings in the process of building design, construction and management using digital technology and information technology. BIM can achieve model management and collaborative work of buildings throughout the entire building life cycle, from design, construction to operation.

[0003] GIS is a geographic information system that uses computer technology to acquire, store, process, analyze and display geographic information. GIS can combine geographic spatial information with attribute data to assist in various planning, management and decision-making tasks. GIS is widely used in urban planning, environmental protection, resource management and other fields. BIM and GIS are closely related in the fields of architecture and urban planning. By integrating BIM and GIS technology, seamless connection between spatial data and building models can be achieved, providing more comprehensive and accurate information support for the design, construction and management of buildings.

[0004] In the existing technology, the road-based BIM and GIS models remain at the stage of simple interaction and three-dimensional visualization to facilitate the work of staff. However, the use of the road itself is not integrated into the BIM and GIS models, such as the reference and impact of traffic flow on the model. The convenience of use for staff needs to be improved. Summary of the invention

[0005] The purpose of the present invention is to provide a regional highway data modeling method and system based on GIS and BIM to solve the above problems in the prior art.

[0006] The embodiments of the present invention are implemented by the following technical solutions:

[0007] In a first aspect, the present invention provides a regional highway data modeling method based on GIS and BIM, comprising:

[0008] Acquire the data of regional roads to establish a BIM model of the regional roads, construct an engineering scene of the regional roads based on the GIS system, and load the BIM model into the engineering scene;

[0009] Divide the regional highway into several unit sections, obtain the historical traffic flow data of the unit sections, the time corresponding to the historical traffic flow data and the basic data of the unit sections, pre-process the historical traffic flow data, the time corresponding to the historical traffic flow data and the basic data of the regional highway, and establish a neural network prediction model;

[0010] The predicted traffic flow data of each unit section at the corresponding time is obtained through the neural network prediction model, and the traffic flow threshold of each unit section is set. The predicted traffic flow data and the traffic flow threshold are used to determine whether to issue a traffic flow warning signal;

[0011] Obtain current weather forecast information, determine whether infrastructure on a unit road section is submerged based on the weather forecast information, and determine whether to generate a traffic flow allocation planning route based on whether submergence occurs and whether there is a traffic flow warning signal;

[0012] If a traffic flow distribution planning route is generated, the traffic flow distribution planning route is mapped to the engineering scenario.

[0013] In one embodiment of the present invention, the engineering scenario of constructing a regional highway based on a GIS system includes:

[0014] Establish a three-dimensional spatial coordinate system, obtain the spatial vector point set data of regional highway related facilities, and map the spatial vector point set data to the three-dimensional spatial coordinate system;

[0015] And the three-dimensional coordinate system of space is gridded.

[0016] In one embodiment of the present invention, establishing a neural network prediction model includes:

[0017] The historical traffic flow data of the unit road section and the time corresponding to the historical traffic flow data are divided into a training set and a validation set, and the basic data of the unit road section is used to correspond the result data to the unit road section;

[0018] Establish input layer, hidden layer and output layer, set weights and biases of input layer, hidden layer and output layer respectively, and select activation function;

[0019] The historical traffic flow data and the time corresponding to the historical traffic flow data are normalized, and feature extraction is performed to obtain the feature set x = [x1, x2, ..., x n ] T ;

[0020]

[0021] Where x1, x2, ..., x n is the data feature, T is the number of dimensions, y is the neural network output, m is the number of input layers, ω ij is the output from the i-th sample of the input layer to the j-th hidden layer, x is the input sample, c i is the cluster center of the data, σ i is the network weight from the input layer to the hidden layer, λ is the bias, μ is the weight coefficient, ζ kis the network weight from the hidden layer to the output layer, and d is the number of hidden layers.

[0022] In one embodiment of the present invention, the setting of the traffic flow threshold of each unit road section includes:

[0023]

[0024] In the formula, Q j is the vehicle threshold, F N F is the average weight of vehicles in the unit road section during the statistical period, M is the maximum load of the unit section, s j is the average width of the car in the unit road section during the statistical time, s f is the maximum width of the unit section, l n is the number of roads in the unit section, l m is the overall average number of regional highways, z max is the number of cars within the statistical time, T l is the statistical time, α and β are proportional coefficients, and α+β=1.

[0025] In one embodiment of the present invention, the step of determining whether to issue a traffic flow warning signal by predicting traffic flow data and traffic flow thresholds includes:

[0026] If the predicted traffic flow data does not exceed the traffic flow threshold, no traffic flow warning signal will be issued;

[0027] If the predicted traffic volume exceeds the traffic volume threshold, but does not exceed the traffic volume threshold to not exceed twice the traffic volume threshold, a normal traffic volume warning signal is issued;

[0028] If the predicted traffic volume exceeds the traffic volume threshold but does not exceed twice the traffic volume threshold, a severe traffic volume warning signal is issued.

[0029] In one embodiment of the present invention, the determining whether to generate a traffic flow allocation planning route according to whether the immersion phenomenon occurs and whether a traffic flow warning signal is generated includes:

[0030] If the current traffic flow warning signal is a normal traffic flow warning signal and no flooding occurs, the traffic flow allocation planning route will not be generated;

[0031] If the current traffic flow warning signal is a normal traffic flow warning signal and immersion occurs, the traffic flow warning signal is changed to a severe traffic flow warning signal, and the traffic flow allocation planning route is not generated;

[0032] If the current traffic flow warning signal is a severe traffic flow warning signal and no flooding occurs, the traffic flow allocation planning route will not be generated;

[0033] If the current traffic flow warning signal is a severe traffic flow warning signal and flooding occurs, a traffic flow allocation planning route is generated.

[0034] In one embodiment of the present invention, generating a traffic flow allocation planning route includes:

[0035] Obtain a road network diagram of the regional highway in the current engineering scenario, and obtain the first unit road section where a serious traffic warning signal and immersion occur in the engineering scenario;

[0036] Acquire a second unit section and a third unit section with branches adjacent to the first unit section, and traverse all routes from the second unit section to the third unit section, or from the third unit section to the second unit section;

[0037] The shortest route and the shortest time route are saved, and an evaluation model is established. The evaluation values ​​of the shortest route and the shortest time route are calculated through the evaluation model, and the route with high evaluation value is selected to be mapped to the engineering scenario.

[0038] In one embodiment of the present invention, establishing the optimization model includes:

[0039]

[0040] In the formula, A i Assign values ​​to the traffic flow warning signal. The normal traffic flow warning signal is 0.8w, the severe traffic flow warning signal is 0.1w, and the no traffic flow warning signal is w. i Assign a value to the immersion phenomenon, where immersion occurs is 0.1p, and where no immersion occurs is p, η is the current traffic volume, S, t1, u k They are the distance, time and number of traffic lights from the second unit section to the third unit section, or from the third unit section to the second unit section, respectively. w and p are natural numbers.

[0041] In a second aspect, the present invention further provides a regional highway data modeling system based on GIS and BIM, comprising:

[0042] The engineering model building module is configured to acquire data of the regional highway to build a BIM model of the regional highway, construct an engineering scene of the regional highway based on the GIS system, and load the BIM model into the engineering scene;

[0043] The prediction model building module is configured to segment the regional highway into a plurality of unit sections, obtain the historical traffic flow data of the unit sections, the time corresponding to the historical traffic flow data and the basic data of the unit sections, and pre-process the historical traffic flow data, the time corresponding to the historical traffic flow data and the basic data of the regional highway to establish a neural network prediction model;

[0044] The traffic flow prediction module is configured to obtain the predicted traffic flow data of each unit road section at a corresponding time through a neural network prediction model, and set a traffic flow threshold for each unit road section, and determine whether to issue a traffic flow warning signal based on the predicted traffic flow data and the traffic flow threshold;

[0045] The route allocation module is configured to obtain current weather forecast information, determine whether the infrastructure of the unit road section is submerged based on the weather forecast information, and determine whether to generate a traffic flow allocation planning route based on whether the submergence occurs and whether there is a traffic flow warning signal; if a traffic flow allocation planning route is generated, map the traffic flow allocation planning route to the engineering scenario;

[0046] The main control module is used to connect with the engineering model building module, the prediction model building module, the traffic flow prediction module and the route allocation module, and is used to execute the above-mentioned regional highway data modeling method based on GIS and BIM.

[0047] The technical solution of the embodiment of the present invention has at least the following advantages and beneficial effects:

[0048] The method provided by the present invention mainly includes the establishment of a BIM model and a construction scenario of a regional highway based on a GIS system, the predicted traffic flow data of each unit section at the corresponding time is obtained through a neural network prediction model, and the traffic flow threshold of each unit section is set, and the traffic flow warning signal is determined by the predicted traffic flow data and the traffic flow threshold; combined with whether the immersion phenomenon occurs, whether the traffic flow distribution planning route is generated according to whether the immersion phenomenon occurs and whether the traffic flow warning signal is generated. Through the above method, more reference data when the road is used are integrated into the BIM model and GIS system of the highway, and the additional functions of traffic flow prediction and traffic flow distribution and control are realized. The data is accessed in real time through a general database, the computability of traffic BIM data is improved, and the interactivity and convenience of BIM model attributes and real-time business are enhanced. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0050] Figure 1 It is a schematic diagram of the process of the present invention. DETAILED DESCRIPTION

[0051] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0052] The terms "first, second" and the like in the specification and claims of this application and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. The naming or numbering of steps in this application does not mean that the steps in the method flow must be executed in the time / logical sequence indicated by the naming or numbering. The named or numbered process steps can be changed in the execution order according to the technical purpose to be achieved, as long as the same or similar technical effects can be achieved.

[0053] The division of modules in this application is a logical division. In actual application, there may be other division methods, for example, multiple modules may be combined or integrated into another system, or some features may be ignored or not executed.

[0054] Please refer to Figure 1 The regional highway data modeling method based on GIS and BIM provided by the present invention is characterized by comprising:

[0055] S101: Acquire data of regional roads to establish a BIM model of the regional roads, construct an engineering scene of the regional roads based on the GIS system, and load the BIM model into the engineering scene;

[0056] Among them, the data of regional highways include key parts such as main lanes, central dividing strips, auxiliary roads, and roadside facilities. Secondly, based on national standards, the highway facility component models of each part and the corresponding vector elements are encoded so that basic geospatial operations can be performed based on coding mapping.

[0057] S102: Divide the regional highway into several unit sections, obtain historical traffic flow data of the unit sections, the time corresponding to the historical traffic flow data, and basic data of the unit sections, and pre-process the historical traffic flow data, the time corresponding to the historical traffic flow data, and the basic data of the regional highway to establish a neural network prediction model;

[0058] Among them, the basic data of the unit road section is not used for direct calculation and practical application of the neural network prediction model, but is mainly used to set an identification mark for the unit road section, such as extracting the section code, length, width and other information from the basic data of the unit road section.

[0059] S103: obtaining predicted traffic flow data at a corresponding time for each unit road section through a neural network prediction model, setting a traffic flow threshold for each unit road section, and determining whether to issue a traffic flow warning signal based on the predicted traffic flow data and the traffic flow threshold;

[0060] S104: obtaining current weather forecast information, judging whether infrastructure of a unit road section is submerged based on the weather forecast information, and determining whether to generate a traffic flow allocation planning route based on whether the submergence occurs and whether a traffic flow warning signal is generated;

[0061] In this embodiment, the weather forecast information can be used to determine whether the infrastructure of the unit road section is submerged. The three-dimensional data information of the infrastructure is collected, and then the rainfall in the weather forecast information is directly compared with the three-dimensional data information to determine whether the submergence phenomenon will occur, that is, the amount of accumulated water will submerge the infrastructure. If the submergence phenomenon occurs, the traffic warning signal should be changed.

[0062] S105: If a traffic flow distribution planning route is generated, the traffic flow distribution planning route is mapped to the engineering scenario.

[0063] The method provided by the invention mainly includes establishing a BIM model and constructing an engineering scenario of a regional highway based on a GIS system, obtaining the predicted traffic flow data of each unit section at the corresponding time through a neural network prediction model, and setting the traffic flow threshold of each unit section, and judging whether to issue a traffic flow warning signal through the predicted traffic flow data and the traffic flow threshold; combining whether the immersion phenomenon occurs, and determining whether to generate a traffic flow distribution planning route based on whether the immersion phenomenon occurs and whether there is a traffic flow warning signal. Through the above method, more reference data on road use are integrated into the BIM model and GIS system of the highway, realizing the additional functions of traffic flow prediction and traffic flow distribution and control, and accessing data in real time through a general database, thereby improving the computability of traffic BIM data and enhancing the interactivity and convenience of BIM model attributes and real-time business.

[0064] An exemplary implementation of the present invention, constructing a regional highway engineering scenario based on a GIS system includes:

[0065] A three-dimensional spatial coordinate system is established, the spatial vector point set data of regional highway related facilities are obtained, the spatial vector point set data is mapped to the three-dimensional spatial coordinate system; and the three-dimensional spatial coordinate system is gridded.

[0066] In this embodiment, based on the unit-divided vector linear data and the spatial vector point set data of some point-like facilities, the road section is divided into units and grids based on the vector topology data, ensuring the future data collection end to apply geographic scene data in fine-grained scenes such as autonomous driving and smart transportation. The solution first uses multiple types of vector space linear and point-like CAD data based on design data, and then performs unit space vector segmentation based on this, and models based on CGA rules.

[0067] In an exemplary embodiment of the present invention, establishing a neural network prediction model includes:

[0068] The historical traffic flow data of the unit road section and the time corresponding to the historical traffic flow data are divided into a training set and a validation set, and the basic data of the unit road section is used to correspond the result data to the unit road section;

[0069] Establish input layer, hidden layer and output layer, set weights and biases of input layer, hidden layer and output layer respectively, and select activation function;

[0070] The historical traffic flow data and the time corresponding to the historical traffic flow data are normalized, and feature extraction is performed to obtain the feature set x = [x1, x2, ..., x n ] T ;

[0071]

[0072] Where x1, x2, ..., x n is the data feature, T is the number of dimensions, y is the output of the neural network, m is the number of input layers, ωij is the output from the i-th sample of the input layer to the j-th hidden layer, x is the input sample, c i is the cluster center of the data, σ i is the network weight from the input layer to the hidden layer, λ is the bias, μ is the weight coefficient, ζk is the network weight from the hidden layer to the output layer, and d is the number of hidden layers.

[0073] In this embodiment, the normalization adopts min-max standardization, and the original data is scaled to [0, 1] according to a certain ratio.

[0074] In an exemplary embodiment of the present invention, setting the traffic flow threshold of each unit road section includes:

[0075]

[0076] In the formula, Q j is the vehicle threshold, F N F is the average weight of vehicles in the unit road section during the statistical period, M is the maximum load of the unit section, s jis the average width of the car in the unit road section during the statistical time, s f is the maximum width of the unit section, l n is the number of roads in the unit section, l m is the overall average number of regional highways, z max is the number of cars within the statistical time, T l is the statistical time, α and β are proportional coefficients, and α+β=1.

[0077] In an exemplary embodiment of the present invention, determining whether to issue a traffic flow warning signal by predicting traffic flow data and traffic flow thresholds includes:

[0078] If the predicted traffic flow data does not exceed the traffic flow threshold, no traffic flow warning signal will be issued; if the predicted traffic flow number exceeds the traffic flow threshold, but does not exceed the traffic flow threshold to not exceed twice the traffic flow threshold, a normal traffic flow warning signal will be issued; if the predicted traffic flow number exceeds the traffic flow threshold to not exceed twice the traffic flow threshold, a severe traffic flow warning signal will be issued.

[0079] In an exemplary embodiment of the present invention, whether to generate a traffic flow allocation planning route according to whether the immersion phenomenon occurs and whether the traffic flow warning signal is issued includes:

[0080] If the current traffic flow warning signal is a normal traffic flow warning signal and no flooding occurs, the traffic flow allocation planning route will not be generated;

[0081] If the current traffic flow warning signal is a normal traffic flow warning signal and immersion occurs, the traffic flow warning signal is changed to a severe traffic flow warning signal, and the traffic flow allocation planning route is not generated;

[0082] If the current traffic flow warning signal is a severe traffic flow warning signal and no flooding occurs, the traffic flow allocation planning route will not be generated;

[0083] If the current traffic flow warning signal is a severe traffic flow warning signal and flooding occurs, a traffic flow allocation planning route is generated.

[0084] In an exemplary embodiment of the present invention, generating a traffic flow allocation planning route includes:

[0085] Obtain a road network diagram of the regional highway of the current engineering scenario, obtain the first unit section where severe traffic warning signals and immersion occur in the engineering scenario; obtain the second unit section and the third unit section with branches adjacent to the first unit section, traverse all routes from the second unit section to the third unit section, or from the third unit section to the second unit section; save the shortest route and the shortest time route, and establish an evaluation model, calculate the evaluation values ​​of the shortest route and the shortest time route respectively through the evaluation model, and select the route with high evaluation value to map to the engineering scenario.

[0086] On a normal highway, there are lanes in two directions, so the second unit section and the third unit section adjacent to the first unit section will be collected. The second unit section or the third unit section is selected as the entrance of the line traversal in one direction, and the other unit section is selected as the entrance of the line traversal in the other direction. In this embodiment, adjacent does not necessarily refer to the next adjacent unit section, because the adjacent unit section may have no branches. If the unit section adjacent to the first unit section has no branches, the search is performed from the next unit section until the second unit section and the third unit section with branches that are closest to the first unit section are found.

[0087] In an exemplary embodiment of the present invention, establishing an optimization model includes:

[0088]

[0089] In the formula, A i Assign values ​​to the traffic flow warning signal. The normal traffic flow warning signal is 0.8w, the severe traffic flow warning signal is 0.1w, and the no traffic flow warning signal is w. i is the value of the immersion phenomenon, where the immersion phenomenon occurs is 0.1p, and where the immersion phenomenon does not occur is p, η is the current traffic flow, s, t1, u k They are the distance, time and number of traffic lights from the second unit section to the third unit section, or from the third unit section to the second unit section, respectively. w and p are natural numbers.

[0090] The present invention also provides a regional highway data modeling system based on GIS and BIM, including:

[0091] The engineering model building module is configured to acquire data of the regional highway to build a BIM model of the regional highway, construct an engineering scene of the regional highway based on the GIS system, and load the BIM model into the engineering scene;

[0092] The prediction model building module is configured to segment the regional highway into a plurality of unit sections, obtain the historical traffic flow data of the unit sections, the time corresponding to the historical traffic flow data and the basic data of the unit sections, and pre-process the historical traffic flow data, the time corresponding to the historical traffic flow data and the basic data of the regional highway to establish a neural network prediction model;

[0093] The traffic flow prediction module is configured to obtain the predicted traffic flow data of each unit road section at a corresponding time through a neural network prediction model, and set a traffic flow threshold for each unit road section, and determine whether to issue a traffic flow warning signal based on the predicted traffic flow data and the traffic flow threshold;

[0094] The route allocation module is configured to obtain current weather forecast information, determine whether the infrastructure of the unit road section is submerged based on the weather forecast information, and determine whether to generate a traffic flow allocation planning route based on whether the submergence occurs and whether there is a traffic flow warning signal; if a traffic flow allocation planning route is generated, map the traffic flow allocation planning route to the engineering scenario;

[0095] The main control module is used to connect with the engineering model building module, the prediction model building module, the traffic flow prediction module and the route allocation module, and is used to execute the above-mentioned regional highway data modeling method based on GIS and BIM.

[0096] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0097] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. The computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0098] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. Regional highway data modeling method based on GIS and BIM, characterized by: include: Acquire the data of regional roads to establish a BIM model of the regional roads, construct an engineering scene of the regional roads based on the GIS system, and load the BIM model into the engineering scene; Divide the regional highway into several unit sections, obtain the historical traffic flow data of the unit sections, the time corresponding to the historical traffic flow data and the basic data of the unit sections, pre-process the historical traffic flow data, the time corresponding to the historical traffic flow data and the basic data of the regional highway, and establish a neural network prediction model; The predicted traffic flow data of each unit section at the corresponding time is obtained through the neural network prediction model, and the traffic flow threshold of each unit section is set. The predicted traffic flow data and the traffic flow threshold are used to determine whether to issue a traffic flow warning signal; Obtain current weather forecast information, determine whether infrastructure on a unit road section is submerged based on the weather forecast information, and determine whether to generate a traffic flow allocation planning route based on whether submergence occurs and whether there is a traffic flow warning signal; If a traffic flow distribution planning route is generated, the traffic flow distribution planning route is mapped to the engineering scenario.

2. The regional highway data modeling method based on GIS and BIM according to claim 1 is characterized in that: The engineering scenarios for constructing regional highways based on the GIS system include: Establish a three-dimensional spatial coordinate system, obtain the spatial vector point set data of regional highway related facilities, and map the spatial vector point set data to the three-dimensional spatial coordinate system; And the three-dimensional coordinate system of space is gridded.

3. The regional highway data modeling method based on GIS and BIM according to claim 1 is characterized in that: The establishment of a neural network prediction model comprises: The historical traffic flow data of the unit road section and the time corresponding to the historical traffic flow data are divided into a training set and a validation set, and the basic data of the unit road section is used to correspond the result data to the unit road section; Establish input layer, hidden layer and output layer, set weights and biases of input layer, hidden layer and output layer respectively, and select activation function; The historical traffic flow data and the time corresponding to the historical traffic flow data are normalized, and feature extraction is performed to obtain the feature set x = [x1, x2, ..., x n ] T ; Where x1, x2, ..., x n is the data feature, T is the number of dimensions, y is the neural network output, m is the number of input layers, ω ij is the output from the i-th sample of the input layer to the j-th hidden layer, x is the input sample, c i is the cluster center of the data, σ i is the network weight from the input layer to the hidden layer, λ is the bias, μ is the weight coefficient, ζ k is the network weight from the hidden layer to the output layer, and d is the number of hidden layers.

4. The regional highway data modeling method based on GIS and BIM according to claim 3 is characterized in that: The setting of the traffic flow threshold of each unit road section includes: In the formula, Q j is the vehicle threshold, F N F is the average weight of vehicles in the unit road section during the statistical period, M is the maximum load of the unit section, s j is the average width of the car in the unit road section during the statistical time, s f is the maximum width of the unit section, l n is the number of roads in the unit section, l m is the overall average number of regional highways, z max is the number of cars within the statistical time, T1 is the statistical time, α and β are proportional coefficients, and α+β=1.

5. The regional highway data modeling method based on GIS and BIM according to claim 4 is characterized in that: The determining whether to issue a traffic flow warning signal by predicting traffic flow data and traffic flow thresholds includes: If the predicted traffic flow data does not exceed the traffic flow threshold, no traffic flow warning signal will be issued; If the predicted traffic volume exceeds the traffic volume threshold, but does not exceed the traffic volume threshold to not exceed twice the traffic volume threshold, a normal traffic volume warning signal is issued; If the predicted traffic volume exceeds the traffic volume threshold but does not exceed twice the traffic volume threshold, a severe traffic volume warning signal is issued.

6. The regional highway data modeling method based on GIS and BIM according to claim 5 is characterized in that: The generating of a traffic flow distribution planning route according to whether the immersion phenomenon occurs and whether a traffic flow warning signal is generated includes: If the current traffic flow warning signal is a normal traffic flow warning signal and no flooding occurs, the traffic flow allocation planning route will not be generated; If the current traffic flow warning signal is a normal traffic flow warning signal and immersion occurs, the traffic flow warning signal is changed to a severe traffic flow warning signal, and the traffic flow allocation planning route is not generated; If the current traffic flow warning signal is a severe traffic flow warning signal and no flooding occurs, the traffic flow allocation planning route will not be generated; If the current traffic flow warning signal is a severe traffic flow warning signal and flooding occurs, a traffic flow allocation planning route is generated.

7. The regional highway data modeling method based on GIS and BIM according to claim 6 is characterized in that: The generating of the traffic flow distribution planning route comprises: Obtain a road network diagram of the regional highway in the current engineering scenario, and obtain the first unit road section where a serious traffic warning signal and immersion occur in the engineering scenario; Acquire a second unit section and a third unit section with branches adjacent to the first unit section, and traverse all routes from the second unit section to the third unit section, or from the third unit section to the second unit section; The shortest route and the shortest time route are saved, and an evaluation model is established. The evaluation values ​​of the shortest route and the shortest time route are calculated through the evaluation model, and the route with high evaluation value is selected to be mapped to the engineering scenario.

8. The regional highway data modeling method based on GIS and BIM according to claim 7 is characterized in that: The said optimization model establishment comprises: In the formula, A i Assign values ​​to the traffic flow warning signal. The normal traffic flow warning signal is 0.8w, the severe traffic flow warning signal is 0.1w, and the no traffic flow warning signal is w. i Assign a value to the immersion phenomenon, where immersion occurs is 0.1p, and where no immersion occurs is p, η is the current traffic volume, S, t1, u k They are the distance, time and number of traffic lights from the second unit section to the third unit section, or from the third unit section to the second unit section, respectively. w and p are natural numbers.

9. Regional highway data modeling system based on GIS and BIM, characterized by: include: The engineering model building module is configured to acquire data of the regional highway to build a BIM model of the regional highway, construct an engineering scene of the regional highway based on the GIS system, and load the BIM model into the engineering scene; The prediction model building module is configured to segment the regional highway into a plurality of unit sections, obtain the historical traffic flow data of the unit sections, the time corresponding to the historical traffic flow data and the basic data of the unit sections, and pre-process the historical traffic flow data, the time corresponding to the historical traffic flow data and the basic data of the regional highway to establish a neural network prediction model; The traffic flow prediction module is configured to obtain the predicted traffic flow data of each unit road section at a corresponding time through a neural network prediction model, and set a traffic flow threshold for each unit road section, and determine whether to issue a traffic flow warning signal based on the predicted traffic flow data and the traffic flow threshold; The route allocation module is configured to obtain current weather forecast information, determine whether the infrastructure of the unit road section is submerged based on the weather forecast information, and determine whether to generate a traffic flow allocation planning route based on whether the submergence occurs and whether there is a traffic flow warning signal; If a traffic flow distribution planning route is generated, the traffic flow distribution planning route is mapped to the engineering scenario; A main control module is used to connect with the engineering model building module, the prediction model building module, the traffic flow prediction module and the route allocation module, and is used to execute the regional highway data modeling method based on GIS and BIM as described in any one of claims 1-8.

Images