Construction site vehicle congestion monitoring system and method

Abstract

The present invention discloses a construction site vehicle congestion monitoring system and method. The system includes a transport route determination module for receiving transport tasks containing transport information uploaded by each construction site in real time and determining the transport route based on the transport information; a congestion probability determination module for determining sampling points and the congestion probability at the sampling points based on the transport route; an image data classification module for periodically acquiring image data at the sampling points; and a fluctuation analysis module for performing content recognition and fluctuation analysis on the image data to determine the congestion situation. The present invention obtains transport tasks for each construction site, plans paths using a map model, performs theoretical analysis on the planned paths, determines sampling points with high congestion probabilities, acquires corresponding image data, and then determines the actual congestion situation. This method utilizes computing resources at a very high rate and is easy to use.

Description

Technical Field

[0001] The present invention belongs to the technical field of vehicle monitoring, and in particular relates to a system and method for monitoring vehicle congestion at a construction site. Background Art

[0002] With the rapid urbanization of my country, more and more construction sites are appearing in every corner of the city. Whether transporting construction materials or silt and debris, large numbers of construction vehicles frequently enter and exit these sites. These sites are connected to urban roads. Given the current increasing congestion in urban traffic, the added pressure of construction vehicles entering and leaving the sites will undoubtedly exacerbate the congestion. Currently, there is no solution for monitoring construction vehicles entering and leaving the sites to identify congestion and plan transportation routes. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide a construction site vehicle congestion monitoring system and method, so as to facilitate the judgment of congestion conditions and the planning of transportation routes.

[0004] In order to solve the above technical problems, the present invention provides a construction site vehicle congestion monitoring system, comprising:

[0005] The transport route determination module is used to receive transport tasks containing transport information uploaded by each construction site in real time and determine the transport route based on the transport information; wherein the transport information includes the transport destination and transport time;

[0006] a congestion probability determination module, configured to determine sampling points and congestion probabilities at the sampling points according to the transport path;

[0007] An image data classification module is used to periodically acquire image data at sampling points and classify each image data according to the congestion probability; wherein the image data contains sampling point labels and time information;

[0008] The fluctuation analysis module is used to perform content recognition on the image data, intercept the image data stream within a preset time range according to the content recognition result, perform fluctuation analysis on the image data stream, and determine the congestion situation.

[0009] Furthermore, the transport path determination module includes:

[0010] A marking point generating unit, configured to obtain location data of each construction site and generate a marking point based on the location data;

[0011] A marking point insertion unit, configured to insert the marking point into a preset regional model to obtain a regional model containing the marking point; wherein the marking point is a circular point with a radius, and the radius is related to the scale of the construction site;

[0012] a traffic network acquisition unit, configured to establish a connection channel with an urban construction database, determine a scale according to the regional model, and acquire a traffic network from the urban construction database according to the scale;

[0013] The path analysis unit is used to insert the access network into the regional model, receive the transportation tasks containing the transportation destinations uploaded by each construction site in real time, and determine the transportation path in the regional model containing the access network based on the location data of the construction site and the transportation destination.

[0014] Furthermore, the path analysis unit includes:

[0015] A priority calculation subunit, configured to obtain the sum of the radius of the identification points corresponding to the transport destination and the construction site, and determine the priority of the transport task based on the sum of the radius;

[0016] A classification subunit, configured to classify the transport tasks according to the transport time to obtain transport tasks indexed by time periods;

[0017] The first execution subunit is configured to extract a transport task whose priority reaches a preset threshold from the transport tasks indexed by time periods, and determine an optimal transport path based on the transport task; wherein the optimal transport path has the shortest transport distance;

[0018] The second execution subunit is used to determine the transportation path according to other tasks in the transportation task indexed by the time period.

[0019] Furthermore, the congestion probability determination module includes:

[0020] The congestion level determination unit is used to extract transportation tasks in different time periods, obtain historical traffic flow data for the time period, and determine the congestion level;

[0021] The intersection analysis unit is used to obtain the intersections of the transportation routes and the number of intersections within the same time period;

[0022] a probability calculation unit, configured to input the congestion level and the number of crossing paths into a trained empirical formula to calculate a congestion probability of the intersection;

[0023] The sampling point marking unit is configured to compare the congestion probability with a preset probability threshold, and when the congestion probability reaches the preset probability threshold, mark the intersection as a sampling point.

[0024] Furthermore, the fluctuation analysis module includes:

[0025] an adjacent image acquisition unit, configured to acquire adjacent image data according to time information in the image data;

[0026] a logic operation unit, configured to perform a logic operation on the adjacent image data to determine a dynamic contour and a background contour in the image data;

[0027] a speed calculation unit, configured to determine a center point of the dynamic contour, calculate an offset distance of the center point, and calculate a movement speed of the dynamic contour according to the offset distance;

[0028] a value score calculation unit, configured to calculate the number of the dynamic profiles, input the movement speed and number into a trained analysis model, and obtain a value score;

[0029] The data stream interception unit is used to compare the value score with a preset score threshold, and when the value reaches the preset score threshold, intercept the image data stream within a preset time range based on the transportation time.

[0030] Furthermore, the fluctuation analysis module further includes:

[0031] a color value conversion unit, configured to perform color value conversion on the image data stream according to a preset conversion formula to obtain a feature image stream;

[0032] A feature value group generating unit, configured to calculate the feature value of each feature image in the feature image stream and generate a feature value group;

[0033] The statistical analysis unit is used to perform statistical analysis on the characteristic value group to determine the congestion situation.

[0034] The present invention also provides a method for monitoring vehicle congestion at a construction site, comprising:

[0035] Receive in real time the transport tasks containing transport information uploaded by each construction site, and determine the transport route based on the transport information; wherein the transport information includes the transport destination and transport time;

[0036] Determining sampling points and congestion probabilities at the sampling points according to the transport route;

[0037] acquiring image data at sampling points at regular intervals, and classifying each image data according to the congestion probability; wherein the image data contains sampling point labels and time information;

[0038] Content recognition is performed on the image data, an image data stream within a preset time range is intercepted according to the content recognition result, and a fluctuation analysis is performed on the image data stream to determine the congestion situation.

[0039] Furthermore, the real-time receiving of transport tasks containing transport information uploaded by each construction site and determining a transport route according to the transport information includes:

[0040] Obtaining location data of each construction site and generating identification points based on the location data;

[0041] Inserting the identification point into a preset regional model to obtain a regional model containing the identification point; wherein the identification point is a circular point with a radius, and the radius is related to the scale of the construction site;

[0042] Establishing a connection channel with an urban construction database, determining a scale according to the regional model, and obtaining a traffic network in the urban construction database according to the scale;

[0043] The traffic network is inserted into the regional model, and the transportation tasks containing the transportation destinations uploaded by each construction site are received in real time. The transportation path is determined in the regional model containing the traffic network according to the location data of the construction site and the transportation destination.

[0044] Furthermore, the step of receiving in real time the transport tasks including the transport destinations uploaded by each construction site and determining the transport routes in the regional model including the traffic network according to the location data of the construction site and the transport destinations includes:

[0045] Obtaining the sum of the radius of the identification points corresponding to the transport destination and the construction site, and determining the priority of the transport task based on the sum of the radius;

[0046] Classifying the transport tasks according to the transport time to obtain transport tasks indexed by time periods;

[0047] Extracting a transport task whose priority reaches a preset threshold from the transport tasks indexed by time periods, and determining an optimal transport path based on the transport task; wherein the optimal transport path has the shortest transport distance;

[0048] Determine the transport route based on other tasks in the transport task indexed by time period.

[0049] Furthermore, the step of determining the sampling points and the congestion probability at the sampling points according to the transportation path includes:

[0050] Extract transportation tasks in different time periods, obtain historical traffic flow data for that time period, and determine the congestion level;

[0051] Get the intersection points of transportation routes and the number of intersection paths within the same time period;

[0052] Inputting the congestion level and the number of intersection paths into a trained empirical formula to calculate the congestion probability of the intersection;

[0053] The congestion probability is compared with a preset probability threshold, and when the congestion probability reaches the preset probability threshold, the intersection is marked as a sampling point.

[0054] The implementation of the present invention has the following beneficial effects: the present invention obtains the transportation tasks of each construction site, performs path planning through a map model, performs theoretical analysis on the planned path, determines sampling points with a high probability of congestion, obtains corresponding image data, and then determines the actual congestion situation. The utilization rate of computing resources is extremely high and the method is easy to use. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0056] Figure 1 This is a structural block diagram of a construction site vehicle congestion monitoring system according to embodiment 1 of the present invention.

[0057] Figure 2 This is a structural block diagram of the transport path determination module in Example 1 of the present invention.

[0058] Figure 3 This is a structural block diagram of the congestion probability determination module in the first embodiment of the present invention.

[0059] Figure 4 This is a first structural block diagram of the fluctuation analysis module in Example 1 of the present invention.

[0060] Figure 5 This is the second component structure block diagram of the fluctuation analysis module in the blockchain-based smart construction site vehicle congestion monitoring system.

[0061] Figure 6 This is a flow chart of a method for monitoring vehicle congestion on a construction site according to a second embodiment of the present invention. DETAILED DESCRIPTION

[0062] The following descriptions of the embodiments refer to the accompanying drawings to illustrate specific embodiments in which the present invention may be implemented.

[0063] Please refer to Figure 1 As shown, the first embodiment of the present invention provides a construction site vehicle congestion monitoring system 10, comprising:

[0064] The transport route determination module 11 is used to receive transport tasks containing transport information uploaded by each construction site in real time and determine the transport route based on the transport information; wherein the transport information includes the transport destination and transport time;

[0065] a congestion probability determination module 12, configured to determine sampling points and congestion probabilities at the sampling points according to the transport path;

[0066] An image data classification module 13 is used to periodically acquire image data at sampling points and classify each image data according to the congestion probability; wherein the image data contains sampling point labels and time information;

[0067] The fluctuation analysis module 14 is used to perform content recognition on the image data, intercept the image data stream within a preset time range according to the content recognition result, perform fluctuation analysis on the image data stream, and determine the congestion situation.

[0068] It should be noted that for a construction site, there is usually no vehicle congestion problem inside the site. The real vehicle congestion problem occurs within the influence range of the construction site. Specifically, the logistics data related to the construction site will cause congestion on the roads involved in the construction site.

[0069] First, in one area, there are often many construction sites under construction at the same time. The transportation tasks of these construction sites are different. The transportation route can be determined based on these transportation tasks. The transportation information includes the transportation time. Accordingly, the transportation route also contains time information.

[0070] Figure 2 This is a structural block diagram of the transport path determination module 11. The transport path determination module 11 includes:

[0071] The identification point generating unit 111 is used to obtain the location data of each construction site and generate identification points according to the location data;

[0072] The marking point inserting unit 112 is used to insert the marking point into a preset regional model to obtain a regional model containing the marking point; wherein the marking point is a circular point with a radius, and the radius is related to the scale of the construction site;

[0073] A traffic network acquisition unit 113 is configured to establish a connection channel with an urban construction database, determine a scale according to the regional model, and acquire a traffic network from the urban construction database according to the scale;

[0074] The path analysis unit 114 is used to insert the access network into the regional model, receive the transportation tasks containing the transportation destinations uploaded by each construction site in real time, and determine the transportation path in the regional model containing the access network based on the location data of the construction site and the transportation destination.

[0075] The above content provides a specific transportation route determination solution. First, a map is generated that matches the area to be inspected. In the map, each construction site is represented by an identification point. The identification point is a circle with a size. The larger the identification point, the larger the scale of the corresponding construction site. The transportation route can be determined in the map through a preset algorithm, and then the congestion situation can be analyzed based on the transportation route.

[0076] It should be noted that the transportation route contains time information, and transportation routes in different time periods will not affect each other and cause congestion.

[0077] In one embodiment of the present invention, the path analysis unit 114 is defined as comprising:

[0078] A priority calculation subunit, configured to obtain the sum of the radius of the identification points corresponding to the transport destination and the construction site, and determine the priority of the transport task based on the sum of the radius;

[0079] A classification subunit, configured to classify the transport tasks according to the transport time to obtain transport tasks indexed by time periods;

[0080] The first execution subunit is configured to extract a transport task whose priority reaches a preset threshold from the transport tasks indexed by time periods, and determine an optimal transport path based on the transport task; wherein the optimal transport path has the shortest transport distance;

[0081] The second execution subunit is used to determine the transportation path according to other tasks in the transportation task indexed by the time period.

[0082] For the path analysis process, different transportation tasks have priorities. Since some large construction sites have more transportation tasks, which can easily lead to congestion, during the path determination process, we try to ensure that the transportation distance of large construction sites is as short as possible.

[0083] Of course, transportation distance and transportation time are not the same concept. If the transportation distance is short, the congestion is likely to be the most serious. On the contrary, the transportation time will be shorter for small construction sites with a slightly longer transportation distance.

[0084] Figure 3 FIG. 1 is a structural block diagram of the congestion probability determination module 12. The congestion probability determination module 12 includes:

[0085] The congestion level determination unit 121 is used to extract transportation tasks in different time periods, obtain historical traffic flow data for the time period, and determine the congestion level;

[0086] The intersection analysis unit 122 is used to obtain the intersections of the transport routes and the number of intersections within the same time period;

[0087] a probability calculation unit 123, configured to input the congestion level and the number of intersecting paths into a trained empirical formula to calculate a congestion probability at an intersection;

[0088] The sampling point marking unit 124 is configured to compare the congestion probability with a preset probability threshold, and mark the intersection as a sampling point when the congestion probability reaches the preset probability threshold.

[0089] The probability of congestion at the intersection of the transport route is very high. Therefore, the intersection needs to be considered. If the intersection is smooth, then for the congestion in the driving section, it is only necessary to receive feedback from the transport staff.

[0090] The congestion level and the number of cross paths are two dependent variables of the jam probability. The higher the congestion level, the higher the jam probability. The more cross paths there are, the higher the jam probability.

[0091] The image data classification module 13 and the fluctuation analysis module 14 are specific execution modules, which are used to determine sampling points and perform further analysis on the sampling points to determine specific congestion conditions.

[0092] Figure 4 FIG1 is a first structural block diagram of the fluctuation analysis module 14. The fluctuation analysis module 14 includes:

[0093] an adjacent image acquisition unit 141, configured to acquire adjacent image data according to time information in the image data;

[0094] a logic operation unit 142, configured to perform a logic operation on the adjacent image data to determine a dynamic contour and a background contour in the image data;

[0095] A speed calculation unit 143 is used to determine the center point of the dynamic contour, calculate the offset distance of the center point, and calculate the movement speed of the dynamic contour according to the offset distance;

[0096] a value score calculation unit 144 for calculating the number of the dynamic profiles, inputting the movement speed and number into a trained analysis model to obtain a value score;

[0097] The data stream interception unit 145 is configured to compare the value score with a preset score threshold, and when the value reaches the preset score threshold, intercept the image data stream within a preset time range based on the transportation time.

[0098] The fluctuation analysis module 14 has two parts: one is contour recognition, and the other is fluctuation analysis. For the contour recognition process, several adjacent images are first obtained, and logical operations are performed on these images to determine the dynamic area and the static area. Among them, the static area is regarded as the background contour; for the dynamic area, it represents the moving vehicles, and the speed and number of the vehicles can be obtained by dynamic contour analysis.

[0099] The speed and quantity of movement reflect the actual situation of the road section. By inputting these two parameters into the analysis model, a value score can be obtained. When the value score reaches a certain level, it means that congestion may have occurred in the area. Therefore, by obtaining the image data stream within a certain time range, the area can be dynamically analyzed to further determine the congestion situation.

[0100] Figure 5 FIG. 1 is a second structural block diagram of the fluctuation analysis module 14. The fluctuation analysis module 14 further includes:

[0101] A color value conversion unit 146 is configured to perform color value conversion on the image data stream according to a preset conversion formula to obtain a feature image stream;

[0102] The feature value group generating unit 147 is used to calculate the feature value of each feature image in the feature image stream and generate a feature value group;

[0103] The statistical analysis unit 148 is used to perform statistical analysis on the characteristic value group to determine the congestion situation.

[0104] The above content is a specific limitation of the fluctuation analysis process. The conversion formula can adopt a grayscale conversion formula. The characteristic image is a grayscale image. There is only one value of a pixel in the grayscale image. The characteristic value of the characteristic image can be obtained by calculating the average value of all pixel values; accordingly, the image data stream corresponds to the characteristic value group; by performing statistical analysis on the characteristic value group, the congestion situation can be further determined.

[0105] Corresponding to the first embodiment of the present invention, which is a system for monitoring vehicle congestion at a construction site, the second embodiment of the present invention provides a method for monitoring vehicle congestion at a construction site, such as Figure 6 As shown, the method includes:

[0106] Step S100: receiving transport tasks containing transport information uploaded by each construction site in real time, and determining a transport route based on the transport information; wherein the transport information includes a transport destination and a transport time;

[0107] Step S200, determining sampling points and congestion probabilities at the sampling points according to the transportation route;

[0108] Step S300, regularly acquiring image data at sampling points, and classifying each image data according to the congestion probability; wherein the image data contains sampling point labels and time information;

[0109] Step S400 , performing content recognition on the image data, intercepting an image data stream within a preset time range according to the content recognition result, performing fluctuation analysis on the image data stream, and determining a congestion situation.

[0110] Furthermore, the real-time receiving of transport tasks containing transport information uploaded by each construction site and determining a transport route according to the transport information includes:

[0111] Obtaining location data of each construction site and generating identification points based on the location data;

[0112] Inserting the identification point into a preset regional model to obtain a regional model containing the identification point; wherein the identification point is a circular point with a radius, and the radius is related to the scale of the construction site;

[0113] Establishing a connection channel with an urban construction database, determining a scale according to the regional model, and obtaining a traffic network in the urban construction database according to the scale;

[0114] The traffic network is inserted into the regional model, and the transportation tasks containing the transportation destinations uploaded by each construction site are received in real time. The transportation path is determined in the regional model containing the traffic network according to the location data of the construction site and the transportation destination.

[0115] Specifically, the step of receiving in real time the transport tasks including the transport destinations uploaded by each construction site and determining the transport routes in the regional model including the traffic network according to the location data of the construction site and the transport destinations includes:

[0116] Obtaining the sum of the radius of the identification points corresponding to the transport destination and the construction site, and determining the priority of the transport task based on the sum of the radius;

[0117] Classifying the transport tasks according to the transport time to obtain transport tasks indexed by time periods;

[0118] Extracting a transport task whose priority reaches a preset threshold from the transport tasks indexed by time periods, and determining an optimal transport path based on the transport task; wherein the optimal transport path has the shortest transport distance;

[0119] Determine the transport route based on other tasks in the transport task indexed by time period.

[0120] As a preferred embodiment of the technical solution of the present invention, the step of determining the sampling points and the congestion probability at the sampling points according to the transportation path includes:

[0121] Extract transportation tasks in different time periods, obtain historical traffic flow data for that time period, and determine the congestion level;

[0122] Get the intersection points of transportation routes and the number of intersection paths within the same time period;

[0123] Inputting the congestion level and the number of intersection paths into a trained empirical formula to calculate the congestion probability of the intersection;

[0124] The congestion probability is compared with a preset probability threshold, and when the congestion probability reaches the preset probability threshold, the intersection is marked as a sampling point.

[0125] Regarding the working principle and process of the construction site vehicle congestion monitoring method of this embodiment, please refer to the description of the aforementioned embodiment 1 of the present invention, which will not be repeated here.

[0126] From the above description, it can be seen that compared with the existing technology, the beneficial effects of the present invention are: the present invention obtains the transportation tasks of each construction site, plans the path through the map model, performs theoretical analysis on the planned path, determines the sampling points with a higher probability of congestion, obtains the corresponding image data, and then judges the actual congestion situation. The utilization rate of computing resources is extremely high and it is easy to use.

[0127] The above disclosure is merely a preferred embodiment of the present invention and is not intended to limit the scope of the present invention. Therefore, equivalent changes made according to the claims of the present invention are still within the scope of the present invention.

Claims

1. A construction site vehicle congestion monitoring system, characterized in that: include: The transport route determination module is used to receive transport tasks containing transport information uploaded by each construction site in real time and determine the transport route based on the transport information; wherein the transport information includes the transport destination and transport time; The congestion probability determination module is used to analyze the intersection of transportation routes, dynamically calculate the congestion probability based on historical traffic flow, and mark the sampling points; An image data classification module is used to periodically acquire image data at sampling points and classify each image data according to the congestion probability; wherein the image data contains sampling point labels and time information; A fluctuation analysis module is used to perform content recognition on the image data, intercept the image data stream within a preset time range based on the content recognition result, perform fluctuation analysis on the image data stream, and determine the congestion situation; The transport path determination module includes: A marking point generating unit, configured to obtain location data of each construction site and generate a marking point based on the location data; A marking point insertion unit, configured to insert the marking point into a preset regional model to obtain a regional model containing the marking point; wherein the marking point is a circular point with a radius, and the radius is related to the scale of the construction site; a traffic network acquisition unit, configured to establish a connection channel with an urban construction database, determine a scale according to the regional model, and acquire a traffic network from the urban construction database according to the scale; a path analysis unit, configured to insert the traffic network into the regional model, receive in real time the transport tasks containing transport destinations uploaded by each construction site, and determine the transport path in the regional model containing the traffic network based on the location data of the construction site and the transport destinations; The path analysis unit includes: A priority calculation subunit, configured to obtain the sum of the radius of the identification points corresponding to the transport destination and the construction site, and determine the priority of the transport task based on the sum of the radius; A classification subunit, configured to classify the transport tasks according to the transport time to obtain transport tasks indexed by time periods; The first execution subunit is configured to extract a transport task whose priority reaches a preset threshold from the transport tasks indexed by time periods, and determine an optimal transport path based on the transport task; wherein the optimal transport path has the shortest transport distance; The second execution subunit is used to determine the transportation path according to other tasks in the transportation task indexed by the time period; The congestion probability determination module includes: The congestion level determination unit is used to extract transportation tasks in different time periods, obtain historical traffic flow data for the time period, and determine the congestion level; The intersection analysis unit is used to obtain the intersections of the transportation routes and the number of intersections within the same time period; a probability calculation unit, configured to input the congestion level and the number of crossing paths into a trained empirical formula to calculate a congestion probability of the intersection; The sampling point marking unit is configured to compare the congestion probability with a preset probability threshold, and when the congestion probability reaches the preset probability threshold, mark the intersection as a sampling point.

2. The construction site vehicle congestion monitoring system according to claim 1, characterized in that: The fluctuation analysis module includes: an adjacent image acquisition unit, configured to acquire adjacent image data according to time information in the image data; a logic operation unit, configured to perform a logic operation on the adjacent image data to determine a dynamic contour and a background contour in the image data; a speed calculation unit, configured to determine a center point of the dynamic contour, calculate an offset distance of the center point, and calculate a motion speed of the dynamic contour according to the offset distance; a value score calculation unit, configured to calculate the number of the dynamic profiles, input the movement speed and number into a trained analysis model, and obtain a value score; The data stream interception unit is used to compare the value score with a preset score threshold, and when the value reaches the preset score threshold, intercept the image data stream within a preset time range based on the transportation time.

3. The construction site vehicle congestion monitoring system according to claim 2, characterized in that: The fluctuation analysis module also includes: a color value conversion unit, configured to perform color value conversion on the image data stream according to a preset conversion formula to obtain a feature image stream; A feature value group generating unit, configured to calculate the feature value of each feature image in the feature image stream and generate a feature value group; The statistical analysis unit is used to perform statistical analysis on the characteristic value group to determine the congestion situation.

4. A method for monitoring vehicle congestion at a construction site, characterized in that: include: Receive in real time the transport tasks containing transport information uploaded by each construction site, and determine the transport route based on the transport information; wherein the transport information includes the transport destination and transport time; Analyze the intersections of transportation routes, dynamically calculate the congestion probability based on historical traffic flow, and mark sampling points; acquiring image data at sampling points at regular intervals, and classifying each image data according to the congestion probability; wherein the image data contains sampling point labels and time information; performing content recognition on the image data, intercepting an image data stream within a preset time range according to the content recognition result, performing fluctuation analysis on the image data stream, and determining a congestion situation; The receiving of transport tasks containing transport information uploaded by each construction site in real time and determining a transport route according to the transport information includes: Obtaining location data of each construction site and generating identification points based on the location data; Inserting the identification point into a preset regional model to obtain a regional model containing the identification point; wherein the identification point is a circular point with a radius, and the radius is related to the scale of the construction site; Establishing a connection channel with an urban construction database, determining a scale according to the regional model, and obtaining a traffic network in the urban construction database according to the scale; Inserting the access network into the regional model, receiving in real time the transport tasks containing the transport destinations uploaded by each construction site, and determining the transport routes in the regional model containing the access network based on the location data of the construction site and the transport destinations; The step of receiving in real time the transport tasks including the transport destinations uploaded by each construction site and determining the transport routes in the regional model including the traffic network according to the location data of the construction site and the transport destinations comprises: Obtaining the sum of the radius of the identification points corresponding to the transport destination and the construction site, and determining the priority of the transport task based on the sum of the radius; Classifying the transport tasks according to the transport time to obtain transport tasks indexed by time periods; Extracting a transport task whose priority reaches a preset threshold from the transport tasks indexed by time periods, and determining an optimal transport path based on the transport task; wherein the optimal transport path has the shortest transport distance; Determine the transport route based on other tasks in the transport task indexed by time period; The steps of analyzing the intersections of transport routes, dynamically calculating the congestion probability based on historical traffic flow, and marking sampling points include: Extract transportation tasks in different time periods, obtain historical traffic flow data for that time period, and determine the congestion level; Get the intersection points of transportation routes and the number of intersection paths within the same time period; Inputting the congestion level and the number of intersection paths into a trained empirical formula to calculate the congestion probability of the intersection; The congestion probability is compared with a preset probability threshold, and when the congestion probability reaches the preset probability threshold, the intersection is marked as a sampling point.

Images