CN111445715B - Intelligent city traffic scheduling method and scheduling equipment based on Internet of things communication - Google Patents
Intelligent city traffic scheduling method and scheduling equipment based on Internet of things communication Download PDFInfo
- Publication number
- CN111445715B CN111445715B CN202010265180.1A CN202010265180A CN111445715B CN 111445715 B CN111445715 B CN 111445715B CN 202010265180 A CN202010265180 A CN 202010265180A CN 111445715 B CN111445715 B CN 111445715B
- Authority
- CN
- China
- Prior art keywords
- path
- mapping
- determining
- current navigation
- network
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000004891 communication Methods 0.000 title claims abstract description 20
- 238000013507 mapping Methods 0.000 claims description 128
- 238000004590 computer program Methods 0.000 claims description 13
- 238000012163 sequencing technique Methods 0.000 claims description 8
- 230000004308 accommodation Effects 0.000 claims description 6
- 230000006399 behavior Effects 0.000 claims description 6
- 238000013527 convolutional neural network Methods 0.000 claims description 5
- 238000012545 processing Methods 0.000 description 5
- 238000001914 filtration Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000000692 anti-sense effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—Arrangements for giving variable traffic instructions
- G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
- G08G1/0968—Systems involving transmission of navigation instructions to the vehicle
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3446—Details of route searching algorithms, e.g. Dijkstra, A*, arc-flags, using precalculated routes
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3453—Special cost functions, i.e. other than distance or default speed limit of road segments
- G01C21/3492—Special cost functions, i.e. other than distance or default speed limit of road segments employing speed data or traffic data, e.g. real-time or historical
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/09—Arrangements for giving variable traffic instructions
- G08G1/0962—Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
- G08G1/0968—Systems involving transmission of navigation instructions to the vehicle
- G08G1/096833—Systems involving transmission of navigation instructions to the vehicle where different aspects are considered when computing the route
Abstract
The application relates to a smart city traffic scheduling method and device based on internet of things communication. When the intelligent city traffic scheduling method based on the internet of things communication is applied, the current navigation path can be obtained from the vehicle-mounted controller corresponding to each vehicle in the current block, and the driving path network of the current block is generated. And then determining the congestion coefficient of the current block according to the determined path intersection point of the traveling path network, and generating the priority of each current navigation path when the congestion coefficient exceeds a set value. In this way, each current navigation path can be adjusted according to the priority and issued to the corresponding vehicle-mounted controller, and then the step of determining the driving path network of the current block based on each current navigation path in the current block is returned. Therefore, continuous and uninterrupted traffic scheduling of the current block can be realized, and traffic jam caused by scheduling failure is avoided.
Description
Technical Field
The application relates to the technical field of smart cities, in particular to a smart city traffic scheduling method and scheduling equipment based on Internet of things communication.
Background
Smart cities (Smartcities) are information-based cities constructed based on information technology. The smart city makes the system and service of each city industry through, thereby realizing the high-efficiency application of city resources, the convenient optimization of city management and the quality improvement of city life. Along with the development of internet of things communication, the informatization degree of the smart city can be further improved by the combination of the internet of everything technology and the smart city. Although the smart city can solve the pain point problem of many traditional cities, the smart city still has the phenomenon that traffic scheduling is not in place in the aspect of improving traffic congestion.
Disclosure of Invention
The application provides a smart city traffic scheduling method and device based on Internet of things communication, so that the phenomenon that traffic scheduling is not in place in a smart city is improved.
According to a first aspect of the present disclosure, there is provided a smart city traffic scheduling method based on internet of things communication, applied to a scheduling device, the method including:
acquiring a current navigation path generated by an on-board controller based on destination information sent by terminal equipment communicated with the on-board controller from the on-board controller corresponding to each vehicle in the current block;
determining a driving path network of the current block based on each current navigation path in the current block; the driving path network is obtained according to each current navigation path, the number of lanes of each street corresponding to the current block and the number of traffic lights of each street;
determining a path intersection point in the driving path network; the route intersection point is used for representing that the vehicle has a vehicle passing behavior when running according to the corresponding current navigation route;
determining the congestion coefficient of the current block according to the path intersection point; when the congestion coefficient exceeds a set value, generating the priority of each current navigation path according to the destination corresponding to the current navigation path; the congestion coefficient is used for representing the weighted sum of differences between the expected time when the vehicle in the current block travels to the destination according to the current navigation path and the actual time when the vehicle travels to the destination according to the travel path network;
and adjusting each current navigation path in the driving path network according to the priority, issuing each adjusted current navigation path to a corresponding vehicle-mounted controller, and then returning to the step of determining the driving path network of the current block based on each current navigation path in the current block.
Optionally, the generating the priority of each current navigation path according to the destination corresponding to the current navigation path includes:
determining keyword information of a destination corresponding to each current navigation path;
extracting a feature vector of the keyword information;
inputting the feature vector into a convolutional neural network trained in advance to identify so as to obtain the probability of emergency degree for representing the keyword information;
and sequencing the keyword information according to the sequence from high to low of the urgency probability and generating the priority of each current navigation path according to the sequencing sequence.
Optionally, the extracting the feature vector of the keyword information includes:
determining category information and characteristic parameters of the keyword information;
determining a first semantic and a second semantic corresponding to the keyword information according to the category information;
adjusting the characteristic parameters under the first semantic meaning and the second semantic meaning;
and determining the feature vector of the keyword information according to the first feature parameter under the first semantic condition and the second feature parameter under the second semantic condition.
Optionally, the adjusting each current navigation path in the travel path network according to the priority includes:
carrying out path planning again for each current navigation path in sequence according to the sequence of the priority from high to low; the higher the priority, the smaller the difference between the expected time and the actual time corresponding to the current leading navigation path after the path planning.
Optionally, the determining a driving path network of the current block based on each current navigation path in the current block includes:
listing the street topology corresponding to the current block to obtain a street topology graph corresponding to the current block; the street topological graph comprises a plurality of line segments and nodes for connecting the line segments, wherein the line segments are used for representing streets, the nodes are used for representing intersections of intercommunicated streets, and each line segment is provided with a first weight coefficient for representing the number of lanes of the street corresponding to the line segment and a second weight coefficient for representing the number of traffic lights of the intersections of the street corresponding to the line segment;
mapping each current navigation path to the street topological graph to obtain a mapping path corresponding to each current navigation path;
determining, for each line segment in the street topology map, whether a mapping path falling into the line segment is multiple;
if the number of the mapping paths intersected with the nodes corresponding to the line segments is multiple, determining saturation coefficients of the multiple mapping paths falling into the line segments relative to the line segments according to the number of lanes corresponding to the line segments and the number of traffic lights; the saturation coefficient is used for representing the vehicle accommodation condition of a street corresponding to the line segment;
establishing a corresponding relation between the saturation coefficient and a corresponding line segment in the street topological graph; and obtaining the driving path network based on the corresponding relation and the street topological graph containing the mapping path.
Optionally, the determining a path intersection point in the travel path network includes:
judging whether a first mapping path and a second mapping path in the driving path network are intersected or not;
determining that a path intersection exists between the first mapping path and the second mapping path when the first mapping path and the second mapping path intersect;
when the first mapping path and the second mapping path are not intersected, determining whether the first mapping path and the second mapping path fall into the same line segment; if the first mapping path and the second mapping path fall into the first mapping path, judging whether a saturation coefficient of a line segment where the first mapping path and the second mapping path fall into is larger than a set coefficient, if so, determining that a path intersection point exists between the first mapping path and the second mapping path, and if not, determining that a path intersection point does not exist between the first mapping path and the second mapping path; if the mapping path does not fall into the first mapping path, determining that no path intersection exists between the first mapping path and the second mapping path;
and determining a path intersection point between the determined first mapping path and the second mapping path as a path intersection point in the driving path network.
Optionally, the determining a congestion coefficient of the current block according to the path intersection includes:
determining a relative position between each path intersection point in the network of travel paths and other path intersection points in the network of travel paths;
determining congestion loss of each current navigation path corresponding to each path intersection point according to a plurality of relative positions corresponding to each path intersection point; the congestion loss is used for representing the time loss of the vehicles corresponding to each current navigation path when the vehicles carry out the vehicle passing at the path intersection points corresponding to the vehicles;
determining the expected time when the vehicle corresponding to each current navigation path runs to the destination according to the current navigation path corresponding to the vehicle;
determining the actual time when the vehicle corresponding to each current navigation path travels to the destination according to the travel path network by taking the time loss corresponding to each current navigation path as a reference;
determining a difference value between the expected time and the actual time corresponding to each current navigation path;
counting the time difference average value of the difference value corresponding to each path intersection point, and weighting the time difference average value corresponding to each path intersection point according to the intersection point position of each path intersection point in the driving path network to obtain a target average value; and determining the congestion coefficient of the current block according to the target average value corresponding to each path intersection point.
According to a second aspect of the present disclosure, there is provided a scheduling apparatus comprising: the system comprises a processor, a memory and a network interface, wherein the memory and the network interface are connected with the processor; the network interface is connected with a nonvolatile memory in the dispatching equipment; when the processor is operated, the computer program is called from the nonvolatile memory through the network interface, and the computer program is operated through the memory so as to execute the method.
According to a third aspect of the present disclosure, a readable storage medium applied to a computer is provided, and a computer program is burned on the readable storage medium, and when the computer program runs in a memory of a scheduling device, the method is implemented.
When the intelligent city traffic scheduling method and the intelligent city traffic scheduling equipment based on the internet of things communication are applied, the current navigation path can be obtained from the vehicle-mounted controller corresponding to each vehicle in the current block, and the driving path network of the current block is generated. And then determining the congestion coefficient of the current block according to the determined path intersection point of the traveling path network, and generating the priority of each current navigation path when the congestion coefficient exceeds a set value. In this way, each current navigation path can be adjusted according to the priority and issued to the corresponding vehicle-mounted controller, and then the step of determining the driving path network of the current block based on each current navigation path in the current block is returned. Therefore, continuous and uninterrupted traffic scheduling of the current block can be realized, and traffic jam caused by scheduling failure is avoided.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and together with the description, serve to explain the principles of the application.
Fig. 1 is a system architecture diagram of a smart city traffic scheduling system based on internet of things communication according to an exemplary embodiment of the present application.
Fig. 2 is a flowchart illustrating a smart city traffic scheduling method based on internet of things communication according to an exemplary embodiment of the present application.
Fig. 3 is a block diagram illustrating an embodiment of a smart city traffic scheduling device based on internet of things communication according to an exemplary embodiment of the present application.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with aspects of the present application.
It is to be understood that although the terms first, second, third, etc. may be used herein to describe various information, such information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the present application. The word "if" as used herein may be interpreted as "at … …" or "when … …" or "in response to a determination", depending on the context.
In order to solve the technical problem that traffic scheduling is not in place, the invention discloses a smart city traffic scheduling method and scheduling equipment based on Internet of things communication. Before explaining the scheduling method, the entire usage scenario of the scheduling method is first explained.
As shown in fig. 1 in the specification, a schematic system architecture of a smart city traffic scheduling system 900 based on internet of things communication according to the present invention is disclosed, in the smart city traffic scheduling system 900, a scheduling device 800 serving as a junction device for performing traffic scheduling on a current block to alleviate traffic congestion is in communication with an on-board controller 750 of each vehicle 700 in the current block.
In addition, in practical applications, each in-vehicle controller 750 is also connected with a terminal device 600. The terminal device 600 may be a mobile phone of a user. The user may transmit the destination information to the on-board controller 750 through the terminal device 600, and the on-board controller 750 may plan a path according to the destination information, and further, the on-board controller 750 may also be used to control the automatic driving of the vehicle 700 according to the planned path. The scheduling apparatus 800 may implement scheduling of the vehicle 700 of the current block by communicating with each on-board controller 750, thereby improving traffic congestion.
Please refer to fig. 2 in the specification, which is a schematic flow chart of a smart city traffic scheduling method based on internet of things communication according to the present invention, the smart city traffic scheduling method can be applied to the scheduling device shown in fig. 1, and the method specifically includes the following steps.
S810, acquiring a current navigation path generated by the vehicle-mounted controller based on destination information sent by the terminal equipment communicated with the vehicle-mounted controller from the vehicle-mounted controller corresponding to each vehicle in the current block.
In S810, the geographic location of the destination corresponding to the destination information may be located in the current block or in another block, which is not limited herein.
S820, determining a driving path network of the current block based on each current navigation path in the current block; and the driving path network is obtained according to each current navigation path, the number of lanes of each street corresponding to the current block and the number of traffic lights of each street.
S830, determining a path intersection point in the driving path network; the route intersection point is used for representing that the vehicle has a vehicle passing behavior when driving according to the corresponding current navigation route.
In S830, the route intersection may be determined according to the current navigation route intersected in the driving route network, or may be determined according to the number of lanes and the number of traffic lights of the street corresponding to the current navigation route that is not intersected. The specific manner of determining the path intersection will be explained in the following sub-steps.
S840, determining the congestion coefficient of the current block according to the path intersection point; when the congestion coefficient exceeds a set value, generating the priority of each current navigation path according to the destination corresponding to the current navigation path; wherein the congestion coefficient is used for representing a weighted sum of differences between a desired time when a vehicle in the current block travels to the destination according to the current navigation path and an actual time when the vehicle travels to the destination according to the travel path network.
In S840, the priority is used to characterize the urgency corresponding to the current navigation path. For example, if the destination corresponding to the navigation path L1 is a hospital and the destination corresponding to the navigation path L2 is a restaurant, it may be determined that the priority of the navigation path L1 is greater than the priority of the navigation path L1.
S850, adjusting each current navigation path in the driving path network according to the priority, sending each adjusted current navigation path to the corresponding vehicle-mounted controller, and then returning to the step of determining the driving path network of the current block based on each current navigation path in the current block.
In S850, the adjustment of each current route is performed to reduce the route intersections in the travel route network, so that traffic congestion caused by a vehicle passing behavior between vehicles can be effectively improved. The vehicle-mounted controller can adjust the driving path according to the adjusted current navigation path or prompt the driver to adjust the driving path.
In S850, in order to ensure efficient and reliable traffic scheduling, it is necessary to take into account the case where the driver refuses to perform the travel path adjustment. Therefore, after the adjusted current navigation path is issued to the vehicle-mounted controller, the scheduling device may determine the driving path network of the current block based on each current navigation path in the current block again. In this way, continuous and uninterrupted traffic scheduling for the current block can be achieved.
On the basis, by executing S810-S850, the current navigation path can be acquired from the vehicle-mounted controller corresponding to each vehicle in the current block, and the driving path network of the current block can be generated. And then determining the congestion coefficient of the current block according to the determined path intersection point of the traveling path network, and generating the priority of each current navigation path when the congestion coefficient exceeds a set value. In this way, each current navigation path can be adjusted according to the priority and issued to the corresponding vehicle-mounted controller, and then the step of determining the driving path network of the current block based on each current navigation path in the current block is returned. Therefore, continuous and uninterrupted traffic scheduling of the current block can be realized, and traffic jam caused by scheduling failure is avoided.
In one possible implementation manner, in order to accurately determine the travel path network of the current navigation path, the determining of the travel path network of the current neighborhood based on each current navigation path in the current neighborhood described in S820 may specifically include what is described in the following sub-steps.
S821, listing the street topology corresponding to the current block to obtain a street topology map corresponding to the current block; the street topological graph comprises a plurality of line segments and nodes for connecting the line segments, wherein the line segments are used for representing streets, the nodes are used for representing intersections of intercommunicated streets, and each line segment is provided with a first weight coefficient for representing the number of lanes of the street corresponding to the line segment and a second weight coefficient for representing the number of traffic lights of the intersections of the street corresponding to the line segment.
It can be understood that the street topological graph is obtained by performing topological mapping on the current block, the intercommunication condition among the streets of the current block, the number of lanes of the streets and the number of traffic lights at the intersection can be simplified, and the dispatching equipment can conveniently and accurately determine the street topological graph.
S822, mapping each current navigation path to the street topological graph to obtain a mapping path corresponding to each current navigation path.
In S822, each current navigation path is mapped, so that the mapping paths can be processed uniformly.
S823, for each line segment in the street topology map, determining whether the mapping path falling into the line segment is multiple.
In S823, it may be determined whether the mapping path falls into a segment by determining whether the mapping path intersects a node corresponding to the segment. It will be appreciated that different streets are characterized by different line segments, and that two streets with corners or turns can then be represented in the street topology by two line segments connected to each other and having corresponding angles. Therefore, the street distribution situation of the current block can be greatly simplified, and the calculation load of the dispatching equipment is reduced.
S824, if the number of the mapping paths intersected with the nodes corresponding to the line segments is multiple, determining saturation coefficients of the multiple mapping paths falling into the line segments relative to the line segments according to the number of lanes corresponding to the line segments and the number of traffic lights; and the saturation coefficient is used for representing the vehicle accommodation condition of the street corresponding to the line segment.
In S824, the larger the saturation factor, the worse the street-to-vehicle accommodation, and the smaller the saturation factor, the better the street-to-vehicle accommodation.
S825, establishing a corresponding relation between the saturation coefficient and a corresponding line segment in the street topological graph; and obtaining the driving path network based on the corresponding relation and the street topological graph containing the mapping path.
In specific implementation, based on the above S821-S825, the travel path network of the current navigation path can be accurately determined.
On the basis of S821-S825, determining the path intersection point in the travel path network described in S830 may be specifically implemented by the following sub-steps.
And S831, judging whether the first mapping path and the second mapping path in the traveling path network intersect.
S832, determining that a path intersection exists between the first mapping path and the second mapping path when the first mapping path and the second mapping path intersect.
S833, when the first mapping path and the second mapping path are disjoint, determining whether the first mapping path and the second mapping path fall into the same line segment; if the first mapping path and the second mapping path fall into the first mapping path, judging whether a saturation coefficient of a line segment where the first mapping path and the second mapping path fall into is larger than a set coefficient, if so, determining that a path intersection point exists between the first mapping path and the second mapping path, and if not, determining that a path intersection point does not exist between the first mapping path and the second mapping path; and if the path does not fall into the first mapping path, determining that no path intersection exists between the first mapping path and the second mapping path.
S834, determining a path intersection point between the determined first mapping path and the second mapping path as a path intersection point in the travel path network.
In S831 to S834, the first mapped path and the second mapped path are two mapped paths that are different in the travel path network. That is, S831 to S834 are determined for every two different mapping paths in the travel path network. For example, the mapped paths in the travel path network are f1, f2, and f 3. Then the above determinations of f1 and f2, f2 and f3, and f3 and f1 may be made in parallel or in series when executing S831-S834. Therefore, all the path intersections in the travel path network can be accurately and reliably determined.
In a specific example, the step of determining the congestion coefficient of the current block according to the path intersection described in S840 may specifically include what is described in the following sub-step.
S8411, determining a relative position between each route intersection in the travel route network and other route intersections in the travel route network.
In S8411, the relative positional relationship may be a distance taken by the path intersection along the line segment. It should be noted that the relative positional relationship is not a straight-line distance between the path intersections.
S8412, determining congestion loss of each current navigation path corresponding to each path intersection point according to the plurality of relative positions corresponding to each path intersection point; and the congestion loss is used for representing the time loss of the vehicles corresponding to each current navigation path when the vehicles carry out the vehicle passing at the path intersection points corresponding to the vehicles.
S8413, determining expected time when the vehicle corresponding to each current navigation path runs to the destination according to the current navigation path corresponding to the vehicle.
S8414, determining an actual time when the vehicle corresponding to each current navigation path travels to the destination according to the travel path network, based on the time loss corresponding to each current navigation path.
S8415, determining a difference between the expected time and the actual time corresponding to each current navigation path.
S8416, counting the time difference average value of the difference value corresponding to each path intersection point, and weighting the time difference average value corresponding to each path intersection point according to the intersection point position of each path intersection point in the driving path network to obtain a target average value; and determining the congestion coefficient of the current block according to the target average value corresponding to each path intersection point.
It is understood that through S8411-S8416, it is possible to analyze the congestion time generated by the vehicle passing behavior occurring at each of the path intersections based on the difference between the desired time when the vehicle travels to the destination according to the current navigation route and the actual time when the vehicle travels to the destination according to the travel route network, and to take into account the intersection position of each of the path intersections in the travel route network. Therefore, the congestion coefficient of the current block can be accurately determined.
In the present embodiment, the congestion coefficient may be a rational number between 0 and 1.
Further, in an alternative embodiment, in order to ensure the confidence of the generated priority, the step of generating the priority of each current navigation path according to the destination corresponding to the current navigation path, which is described in S840, may specifically include what is described in the following steps: firstly determining keyword information of a destination corresponding to each current navigation path, secondly extracting a feature vector of the keyword information, then inputting the feature vector into a convolutional neural network trained in advance for identification to obtain an emergency degree probability for representing the keyword information, and finally sequencing the keyword information according to the emergency degree probability from high to low and generating the priority of each current navigation path according to a sequencing sequence.
In the present embodiment, the keyword information may be "hospital", "museum", "bar", "school", and "examination room", etc. Convolutional neural networks can be trained over a large number of training sets. The training set comprises keyword information, urgency information and associated pairing information of time interval information. It can be understood that the urgency probability is obtained by identifying the feature vector, and the time interval information of different keyword information can be taken into account, so that the confidence of the priority of each current navigation path is ensured.
Further, in the above step, extracting the feature vector of the keyword information may specifically include the content described in the following substeps.
Firstly, the category information and the characteristic parameter of the keyword information are determined.
And secondly, determining a first semantic and a second semantic corresponding to the keyword information according to the category information.
And then, adjusting the characteristic parameters under the first semantic meaning and the second semantic meaning.
And finally, determining the feature vector of the keyword information according to the first feature parameter under the first semantic condition and the second feature parameter under the second semantic condition.
In detail, the above steps can be specifically realized by the method described in the following steps.
(1) And analyzing the keyword information to obtain the category information and the characteristic parameters of the keyword information.
In this embodiment, the feature parameters are used to characterize the sense keywords and the anti-sense keywords of the keyword information.
(2) Under the condition that the keyword information is determined to have a first semantic meaning and a second semantic meaning according to the category information, determining a first Hamming distance between each feature parameter of the keyword information under the second semantic meaning and each feature parameter of the keyword information under the first semantic meaning according to the feature parameters of the keyword information under the first semantic meaning and the parameter weight thereof, and transferring the feature parameters to the first semantic meaning, wherein the first Hamming distance between the feature parameters of the keyword information under the second semantic meaning and the feature parameters under the first semantic meaning is smaller than a set Hamming distance.
In this embodiment, the first semantic and the second semantic are opposite semantics.
(3) And under the condition that the second semantic meaning corresponding to the keyword information comprises a plurality of characteristic parameters, determining a second Hamming distance between the characteristic parameters of the keyword information under the second semantic meaning according to the characteristic parameters of the keyword information under the first semantic meaning and the parameter weight thereof, and filtering the characteristic parameters under the second semantic meaning according to the second Hamming distance between the characteristic parameters.
(4) And setting a parameter grade for each feature parameter reserved for the filtering according to the feature parameters of the keyword information under the first semantic and the parameter weight thereof, and transferring each feature parameter reserved for the filtering to the first semantic according to the parameter grade.
(5) Respectively carrying out normalization processing on a first characteristic parameter of the keyword information under the first semantic meaning and a second characteristic parameter of the keyword information under the second semantic meaning to obtain a first processing result corresponding to the first characteristic parameter and a second processing result corresponding to the second characteristic parameter.
(6) And integrating the first processing result and the second processing result to obtain the feature vector of the keyword information.
When the steps are executed, the semantics of the keyword information can be deeply analyzed, semanteme analysis and classification can be carried out, and then the feature vector of the keyword information can be accurately determined.
In a specific example, the step of adjusting each current navigation path in the travel path network according to the priority described in S850 may be specifically implemented by a method described in the following steps: carrying out path planning again for each current navigation path in sequence according to the sequence of the priority from high to low; the higher the priority, the smaller the difference between the expected time and the actual time corresponding to the current leading navigation path after the path planning.
It can be understood that, through the above, it can be ensured that all current navigation paths can reduce the difference between the corresponding expected time and the actual time after the path planning, so as to reduce the congestion phenomenon when the vehicle runs in the current block.
On the basis, the embodiment of the invention also discloses a smart city traffic scheduling device 200 based on the communication of the internet of things, and the specific description of the smart city traffic scheduling device 200 is as follows.
A1. The utility model provides a wisdom urban traffic scheduling device based on thing communication of networking, is applied to the scheduling equipment, the device includes:
the route obtaining module 201 is configured to obtain, from an on-vehicle controller corresponding to each vehicle in a current block, a current navigation route generated by the on-vehicle controller based on destination information sent by a terminal device in communication with the on-vehicle controller.
A network determining module 202, configured to determine a driving path network of a current block based on each current navigation path in the current block; and the driving path network is obtained according to each current navigation path, the number of lanes of each street corresponding to the current block and the number of traffic lights of each street.
An intersection determination module 203, configured to determine a path intersection in the travel path network; the route intersection point is used for representing that the vehicle has a vehicle passing behavior when driving according to the corresponding current navigation route.
A coefficient determining module 204, configured to determine a congestion coefficient of the current block according to the path intersection; when the congestion coefficient exceeds a set value, generating the priority of each current navigation path according to the destination corresponding to the current navigation path; wherein the congestion coefficient is used for representing a weighted sum of differences between a desired time when a vehicle in the current block travels to the destination according to the current navigation path and an actual time when the vehicle travels to the destination according to the travel path network.
And the path adjusting module 205 is configured to adjust each current navigation path in the travel path network according to the priority, send each adjusted current navigation path to the corresponding vehicle-mounted controller, and then return to the step of determining the travel path network of the current block based on each current navigation path in the current block.
A2. The apparatus of a1, the coefficient determining module 204 is specifically configured to:
determining keyword information of a destination corresponding to each current navigation path;
extracting a feature vector of the keyword information;
inputting the feature vector into a convolutional neural network trained in advance to identify so as to obtain the probability of emergency degree for representing the keyword information;
and sequencing the keyword information according to the sequence from high to low of the urgency probability and generating the priority of each current navigation path according to the sequencing sequence.
A3. The apparatus of a2, the coefficient determination module 204, further configured to:
determining category information and characteristic parameters of the keyword information;
determining a first semantic and a second semantic corresponding to the keyword information according to the category information;
adjusting the characteristic parameters under the first semantic meaning and the second semantic meaning;
and determining the feature vector of the keyword information according to the first feature parameter under the first semantic condition and the second feature parameter under the second semantic condition.
A4. The apparatus of a1, the path adjustment module 205 is specifically configured to:
carrying out path planning again for each current navigation path in sequence according to the sequence of the priority from high to low; the higher the priority, the smaller the difference between the expected time and the actual time corresponding to the current leading navigation path after the path planning.
A5. The apparatus of a1, the network determining module 202 is specifically configured to:
listing the street topology corresponding to the current block to obtain a street topology graph corresponding to the current block; the street topological graph comprises a plurality of line segments and nodes for connecting the line segments, wherein the line segments are used for representing streets, the nodes are used for representing intersections of intercommunicated streets, and each line segment is provided with a first weight coefficient for representing the number of lanes of the street corresponding to the line segment and a second weight coefficient for representing the number of traffic lights of the intersections of the street corresponding to the line segment;
mapping each current navigation path to the street topological graph to obtain a mapping path corresponding to each current navigation path;
determining, for each line segment in the street topology map, whether a mapping path falling into the line segment is multiple;
if the number of the mapping paths intersected with the nodes corresponding to the line segments is multiple, determining saturation coefficients of the multiple mapping paths falling into the line segments relative to the line segments according to the number of lanes corresponding to the line segments and the number of traffic lights; the saturation coefficient is used for representing the vehicle accommodation condition of a street corresponding to the line segment;
establishing a corresponding relation between the saturation coefficient and a corresponding line segment in the street topological graph; and obtaining the driving path network based on the corresponding relation and the street topological graph containing the mapping path.
A6. The apparatus of a5, the intersection determination module 203 is specifically configured to:
judging whether a first mapping path and a second mapping path in the driving path network are intersected or not;
determining that a path intersection exists between the first mapping path and the second mapping path when the first mapping path and the second mapping path intersect;
when the first mapping path and the second mapping path are not intersected, determining whether the first mapping path and the second mapping path fall into the same line segment; if the first mapping path and the second mapping path fall into the first mapping path, judging whether a saturation coefficient of a line segment where the first mapping path and the second mapping path fall into is larger than a set coefficient, if so, determining that a path intersection point exists between the first mapping path and the second mapping path, and if not, determining that a path intersection point does not exist between the first mapping path and the second mapping path; if the mapping path does not fall into the first mapping path, determining that no path intersection exists between the first mapping path and the second mapping path;
and determining a path intersection point between the determined first mapping path and the second mapping path as a path intersection point in the driving path network.
A7. The apparatus of a6, the coefficient determining module 204 is specifically configured to:
determining a relative position between each path intersection point in the network of travel paths and other path intersection points in the network of travel paths;
determining congestion loss of each current navigation path corresponding to each path intersection point according to a plurality of relative positions corresponding to each path intersection point; the congestion loss is used for representing the time loss of the vehicles corresponding to each current navigation path when the vehicles carry out the vehicle passing at the path intersection points corresponding to the vehicles;
determining the expected time when the vehicle corresponding to each current navigation path runs to the destination according to the current navigation path corresponding to the vehicle;
determining the actual time when the vehicle corresponding to each current navigation path travels to the destination according to the travel path network by taking the time loss corresponding to each current navigation path as a reference;
determining a difference value between the expected time and the actual time corresponding to each current navigation path;
counting the time difference average value of the difference value corresponding to each path intersection point, and weighting the time difference average value corresponding to each path intersection point according to the intersection point position of each path intersection point in the driving path network to obtain a target average value; and determining the congestion coefficient of the current block according to the target average value corresponding to each path intersection point.
For the device embodiments, since they substantially correspond to the method embodiments, reference may be made to the partial description of the method embodiments for relevant points. The above-described embodiments of the apparatus are merely illustrative, wherein the modules described as separate parts may or may not be physically separate, and the parts displayed as modules may or may not be physical modules, may be located in one place, or may be distributed on a plurality of network modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of the application. One of ordinary skill in the art can understand and implement it without inventive effort.
On the basis, the scheduling device is also disclosed, and comprises: the system comprises a processor, a memory and a network interface, wherein the memory and the network interface are connected with the processor, and the network interface is connected with a nonvolatile memory in the scheduling equipment. When the processor is running, the processor calls the computer program from the nonvolatile memory through the network interface and runs the computer program through the memory so as to execute the method.
On the basis, the method is further applied to a readable storage medium of a computer, wherein a computer program is burned on the readable storage medium, and the method is realized when the computer program runs in a memory of the scheduling device.
Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only.
It will be understood that the present application is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof.
Claims (9)
1. A smart city traffic scheduling method based on Internet of things communication is applied to scheduling equipment, and comprises the following steps:
acquiring a current navigation path generated by an on-board controller based on destination information sent by terminal equipment communicated with the on-board controller from the on-board controller corresponding to each vehicle in the current block;
determining a driving path network of the current block based on each current navigation path in the current block; the driving path network is obtained according to each current navigation path, the number of lanes of each street corresponding to the current block and the number of traffic lights of each street;
determining a path intersection point in the driving path network; the route intersection point is used for representing that the vehicle has a vehicle passing behavior when running according to the corresponding current navigation route;
determining the congestion coefficient of the current block according to the path intersection point; when the congestion coefficient exceeds a set value, generating the priority of each current navigation path according to the destination corresponding to the current navigation path; the congestion coefficient is used for representing the weighted sum of differences between the expected time when the vehicle in the current block travels to the destination according to the current navigation path and the actual time when the vehicle travels to the destination according to the travel path network;
and adjusting each current navigation path in the driving path network according to the priority, issuing each adjusted current navigation path to a corresponding vehicle-mounted controller, and then returning to the step of determining the driving path network of the current block based on each current navigation path in the current block.
2. The method of claim 1, wherein generating the priority for each current navigation path according to the destination to which the current navigation path corresponds comprises:
determining keyword information of a destination corresponding to each current navigation path;
extracting a feature vector of the keyword information;
inputting the feature vector into a convolutional neural network trained in advance to identify so as to obtain the probability of emergency degree for representing the keyword information;
and sequencing the keyword information according to the sequence from high to low of the urgency probability and generating the priority of each current navigation path according to the sequencing sequence.
3. The method of claim 2, wherein the extracting the feature vector of the keyword information comprises:
determining category information and characteristic parameters of the keyword information;
determining a first semantic and a second semantic corresponding to the keyword information according to the category information;
adjusting the characteristic parameters under the first semantic meaning and the second semantic meaning;
and determining the feature vector of the keyword information according to the first feature parameter under the first semantic condition and the second feature parameter under the second semantic condition.
4. The method of claim 1, wherein said adjusting each current navigation path in the network of travel paths according to the priority comprises:
carrying out path planning again for each current navigation path in sequence according to the sequence of the priority from high to low; the higher the priority, the smaller the difference between the expected time and the actual time corresponding to the current leading navigation path after the path planning.
5. The method of claim 1, wherein determining the travel path network for the current neighborhood based on each current navigation path in the current neighborhood comprises:
listing the street topology corresponding to the current block to obtain a street topology graph corresponding to the current block; the street topological graph comprises a plurality of line segments and nodes for connecting the line segments, wherein the line segments are used for representing streets, the nodes are used for representing intersections of intercommunicated streets, and each line segment is provided with a first weight coefficient for representing the number of lanes of the street corresponding to the line segment and a second weight coefficient for representing the number of traffic lights of the intersections of the street corresponding to the line segment;
mapping each current navigation path to the street topological graph to obtain a mapping path corresponding to each current navigation path;
determining, for each line segment in the street topology map, whether a mapping path falling into the line segment is multiple;
if the number of the mapping paths intersected with the nodes corresponding to the line segments is multiple, determining saturation coefficients of the multiple mapping paths falling into the line segments relative to the line segments according to the number of lanes corresponding to the line segments and the number of traffic lights; the saturation coefficient is used for representing the vehicle accommodation condition of a street corresponding to the line segment;
establishing a corresponding relation between the saturation coefficient and a corresponding line segment in the street topological graph; and obtaining the driving path network based on the corresponding relation and the street topological graph containing the mapping path.
6. The method of claim 5, wherein the determining a path intersection in the network of travel paths comprises:
judging whether a first mapping path and a second mapping path in the driving path network are intersected or not;
determining that a path intersection exists between the first mapping path and the second mapping path when the first mapping path and the second mapping path intersect;
when the first mapping path and the second mapping path are not intersected, determining whether the first mapping path and the second mapping path fall into the same line segment; if the first mapping path and the second mapping path fall into the first mapping path, judging whether a saturation coefficient of a line segment where the first mapping path and the second mapping path fall into is larger than a set coefficient, if so, determining that a path intersection point exists between the first mapping path and the second mapping path, and if not, determining that a path intersection point does not exist between the first mapping path and the second mapping path; if the mapping path does not fall into the first mapping path, determining that no path intersection exists between the first mapping path and the second mapping path;
and determining a path intersection point between the determined first mapping path and the second mapping path as a path intersection point in the driving path network.
7. The method of claim 6, wherein determining the congestion coefficient of the current block from the path intersection comprises:
determining a relative position between each path intersection point in the network of travel paths and other path intersection points in the network of travel paths;
determining congestion loss of each current navigation path corresponding to each path intersection point according to a plurality of relative positions corresponding to each path intersection point; the congestion loss is used for representing the time loss of the vehicles corresponding to each current navigation path when the vehicles carry out the vehicle passing at the path intersection points corresponding to the vehicles;
determining the expected time when the vehicle corresponding to each current navigation path runs to the destination according to the current navigation path corresponding to the vehicle;
determining the actual time when the vehicle corresponding to each current navigation path travels to the destination according to the travel path network by taking the time loss corresponding to each current navigation path as a reference;
determining a difference value between the expected time and the actual time corresponding to each current navigation path;
counting the time difference average value of the difference value corresponding to each path intersection point, and weighting the time difference average value corresponding to each path intersection point according to the intersection point position of each path intersection point in the driving path network to obtain a target average value; and determining the congestion coefficient of the current block according to the target average value corresponding to each path intersection point.
8. A scheduling apparatus, comprising:
a processor, and
a memory and a network interface connected with the processor;
the network interface is connected with a nonvolatile memory in the dispatching equipment;
the processor, when running, retrieves a computer program from the non-volatile memory via the network interface and runs the computer program via the memory to perform the method of any of claims 1-7.
9. A readable storage medium applied to a computer, wherein the readable storage medium is burned with a computer program, and the computer program realizes the method of any one of the above claims 1-7 when the computer program runs in a memory of a scheduling device.
Priority Applications (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010265180.1A CN111445715B (en) | 2020-04-07 | 2020-04-07 | Intelligent city traffic scheduling method and scheduling equipment based on Internet of things communication |
| CN202011063050.6A CN112258876A (en) | 2020-04-07 | 2020-04-07 | Smart city management method and device based on Internet of things |
| CN202011057994.2A CN112233446A (en) | 2020-04-07 | 2020-04-07 | Intelligent traffic processing method and scheduling equipment based on informatization and Internet of things |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010265180.1A CN111445715B (en) | 2020-04-07 | 2020-04-07 | Intelligent city traffic scheduling method and scheduling equipment based on Internet of things communication |
Related Child Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011063050.6A Division CN112258876A (en) | 2020-04-07 | 2020-04-07 | Smart city management method and device based on Internet of things |
| CN202011057994.2A Division CN112233446A (en) | 2020-04-07 | 2020-04-07 | Intelligent traffic processing method and scheduling equipment based on informatization and Internet of things |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111445715A CN111445715A (en) | 2020-07-24 |
| CN111445715B true CN111445715B (en) | 2020-11-13 |
Family
ID=71651611
Family Applications (3)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011057994.2A Withdrawn CN112233446A (en) | 2020-04-07 | 2020-04-07 | Intelligent traffic processing method and scheduling equipment based on informatization and Internet of things |
| CN202010265180.1A Active CN111445715B (en) | 2020-04-07 | 2020-04-07 | Intelligent city traffic scheduling method and scheduling equipment based on Internet of things communication |
| CN202011063050.6A Withdrawn CN112258876A (en) | 2020-04-07 | 2020-04-07 | Smart city management method and device based on Internet of things |
Family Applications Before (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011057994.2A Withdrawn CN112233446A (en) | 2020-04-07 | 2020-04-07 | Intelligent traffic processing method and scheduling equipment based on informatization and Internet of things |
Family Applications After (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011063050.6A Withdrawn CN112258876A (en) | 2020-04-07 | 2020-04-07 | Smart city management method and device based on Internet of things |
Country Status (1)
| Country | Link |
|---|---|
| CN (3) | CN112233446A (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112289041B (en) * | 2020-10-25 | 2021-12-03 | 上海智能交通有限公司 | Intelligent parking lot management method based on hotspot positioning and information sharing and cloud platform |
| CN112581757B (en) * | 2020-12-09 | 2021-11-16 | 广东君略科技咨询有限公司 | Intelligent traffic information processing method and device and server |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR100871293B1 (en) * | 2007-05-07 | 2008-12-01 | 팅크웨어(주) | Apparatus and method for guide crossroad in navigation system |
| CN102706356B (en) * | 2012-05-29 | 2017-03-15 | 中兴通讯股份有限公司 | A kind of method of path navigation, base station, core net and system |
| DE102013209235A1 (en) * | 2013-05-17 | 2014-11-20 | Siemens Aktiengesellschaft | Method and device for position determination |
| CN105825677B (en) * | 2016-05-31 | 2018-10-09 | 武汉大学 | A kind of urban traffic blocking prediction technique based on improvement BML models |
| US10204515B2 (en) * | 2016-11-02 | 2019-02-12 | Here Global B.V. | Automated traffic signal outage notification with SPaT information |
-
2020
- 2020-04-07 CN CN202011057994.2A patent/CN112233446A/en not_active Withdrawn
- 2020-04-07 CN CN202010265180.1A patent/CN111445715B/en active Active
- 2020-04-07 CN CN202011063050.6A patent/CN112258876A/en not_active Withdrawn
Also Published As
| Publication number | Publication date |
|---|---|
| CN112258876A (en) | 2021-01-22 |
| CN111445715A (en) | 2020-07-24 |
| CN112233446A (en) | 2021-01-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102467827B (en) | Traffic information providing system and terminal and use it to provide the method for transport information | |
| CN108072381A (en) | A kind of method and device of path planning | |
| CN111445715B (en) | Intelligent city traffic scheduling method and scheduling equipment based on Internet of things communication | |
| CN109740811A (en) | Passage speed prediction technique, device and storage medium | |
| CN102819950A (en) | Carrying aid decision making system and method for traffic tool | |
| CN107101643A (en) | A kind of share-car matching process | |
| CN105117790A (en) | Fare estimating method and apparatus | |
| CN111473789B (en) | Navigation route planning method, device and equipment | |
| CN110598917B (en) | Destination prediction method, system and storage medium based on path track | |
| CN113052405B (en) | Traffic jam prediction and optimization method based on Internet of things and artificial intelligence | |
| CN108248611A (en) | A kind of method of automatic Pilot, automobile control device, automobile and system | |
| CN111931079A (en) | Method and system for recommending online booking getting-on points | |
| CN110232474A (en) | Lap guard path method, device, server and storage medium | |
| CN111862590A (en) | Road condition prediction method, road condition prediction device and storage medium | |
| CN113532459A (en) | Predictive navigation route planning method and system | |
| CN111881243A (en) | Taxi track hotspot area analysis method and system | |
| CN111400425A (en) | Method and system for automatically optimizing and selecting path | |
| CN111337045A (en) | Vehicle navigation method and device | |
| CN107527105B (en) | Carpooling order combining method | |
| CN109670614A (en) | A kind of method, apparatus, equipment and storage medium handling order | |
| CN109685492A (en) | A kind of public transport mode of payment and device | |
| Kamiński et al. | Multiagent routing simulation with partial smart vehicles penetration | |
| Araldo et al. | Implementation & policy applications of AMOD in multi-modal activity-driven agent-based urban simulator simmobility | |
| Huo et al. | CHRT: Clustering-based hybrid re-routing system for traffic congestion avoidance | |
| US20200200555A1 (en) | System and method for controlling vehicular pollution concentration and providing maximum traffic flow throughput |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 650034 No. 204 West Ring Road, Wuhua District, Yunnan, Kunming Applicant after: Zhang Genbing Address before: Software Park Quanzhou city Fujian province Fengze District 362000 Building No. 9 Applicant before: Zhang Genbing |
|
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20201029 Address after: 7 / F, Shenzhen Greater China International Trading Plaza, No.1 Fuhua 1st Road, Fu'an community, Futian street, Futian District, Shenzhen, Guangdong 518000 Applicant after: Shenzhen Smart City Technology Development Group Co.,Ltd. Address before: 650034 No. 204 West Ring Road, Wuhua District, Yunnan, Kunming Applicant before: Zhang Genbing |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: Smart City Traffic Scheduling Method and Scheduling Equipment Based on IoT Communication Effective date of registration: 20231219 Granted publication date: 20201113 Pledgee: Societe Generale Bank Limited by Share Ltd. Shenzhen branch Pledgor: Shenzhen Smart City Technology Development Group Co.,Ltd. Registration number: Y2023980072779 |