Urban Internet of Vehicles traffic management system and method

Abstract

The invention discloses an urban Internet of Vehicles traffic management system and method, and belongs to the technical field of Internet of Vehicles. Extracting a vehicle log through user authorization, and generating vehicle operation data and regional traffic data; based on the vehicle operation data, constructing a regional traffic vehicle distribution map, and calculating a road congestion index of the region; based on the vehicle operation data and the regional traffic data, calculating the time required by the staff to arrive at the congested region, and constructing a traffic evaluation model; generating an early warning list when the congestion duration is greater than the duration required by the worker to arrive at the congestion area; the early warning lists of all the areas in the city are fed back to an urban traffic administrator according to the road congestion indexes from large to small, and the urban traffic administrator is assisted in transferring workers; therefore, the traffic management efficiency is improved, and the congestion problem is relieved.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle networking, and in particular to a city vehicle networking traffic management system and method. Background Art

[0002] The Internet of Vehicles is an important field that has developed with the development of the Internet of Things technology. It refers to the on-board equipment on the vehicle making effective use of all vehicle dynamic information on the information network platform through wireless communication technology, and providing different functional services during vehicle operation. The concept of the Internet of Vehicles originated from the Internet of Things. It is a typical application of the Internet of Things technology in the field of transportation systems, and it is also an integrated technology for the future development of information communication, environmental protection, energy conservation, and safety.

[0003] As an important part of smart cities, the Internet of Vehicles can realize data sharing between vehicles and urban traffic. In urban traffic management, congestion has always been a concern of people. Therefore, how to assist urban traffic managers to solve traffic congestion and realize urban traffic management has become a problem we need to solve. Summary of the invention

[0004] The purpose of the present invention is to provide a city vehicle network traffic management system and method to solve the problems raised in the above background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0006] A method for urban vehicle network traffic management, the method comprising the following steps:

[0007] Step S100: With user authorization, extract vehicle logs and generate vehicle operation data and regional traffic data;

[0008] Step S200: constructing a regional traffic vehicle distribution map based on vehicle operation data and calculating a regional road congestion index;

[0009] Step S300: Based on the vehicle operation data and regional traffic data, the time required for the staff to reach the congested area is calculated, and a traffic assessment model is constructed;

[0010] Step S400: When the congestion duration is longer than the time required for staff to reach the congested area, a warning list is generated; the warning list of all areas in the city is fed back to the city traffic administrator according to the road congestion index from large to small, to assist the city traffic administrator in mobilizing staff.

[0011] Furthermore, the specific implementation process of step S100 includes:

[0012] Step S101: Divide the urban traffic section into regions according to the distribution of traffic lights, and construct a region set S = {sa |a∈[1,A]}, where s a represents the ath area, A represents the total number of areas in the urban traffic division area;

[0013] Due to the different road conditions in different areas, such as different road widths, different daily usage frequencies of different roads, and large-scale events held by shops along some roads, which will lead to changes in road conditions, it is necessary to divide the city into A areas and effectively manage urban traffic through traffic management in different areas.

[0014] Step S102: With user authorization, connect to the Internet of Vehicles, extract vehicle logs in the area through the Internet of Vehicles cloud, and collect vehicle operation data through the vehicle's own sensors; directly obtain regional traffic data through regional traffic facilities, and the regional traffic data includes road capacity, the time required for staff to reach the congested area, and the maximum number of stopped vehicles that does not affect road capacity.

[0015] Furthermore, the specific implementation process of step S200 includes:

[0016] Step S201: In area s a In the process, based on the vehicle operation data, the distribution of all vehicles on the roads in the region is extracted to construct a regional traffic vehicle distribution map;

[0017] Step S202: marking the working status of all vehicles in the regional traffic vehicle distribution map; based on the route information of the vehicle, the vehicle is divided into three working statuses: normal working status, abnormal working status and stopped working status; if the vehicle has not arrived at the destination, the vehicle is marked as a normal working status; if the vehicle has arrived at the destination and the vehicle is still running, the vehicle is marked as an abnormal working status; if the vehicle is no longer running, the vehicle is marked as a stopped working status;

[0018] Step S203: Count the number of vehicles in normal working state, abnormal working state and stopped working state in the regional traffic vehicle distribution map, which are recorded as U, P and O respectively; calculate the regional s based on the regional traffic vehicle distribution map. a Road congestion index: r = (U + P) / UPO, where UPO represents area s a road capacity value.

[0019] Because not all drivers in the regional Internet of Vehicles use the Internet of Vehicles for route planning, when calculating the congestion index, it is necessary to add the running vehicles that have not performed route planning and other vehicles that have performed route planning to obtain the total number of regional traffic vehicles P, thereby achieving a more accurate calculation of the regional road congestion index.

[0020] Furthermore, the specific implementation process of step S300 includes:

[0021] Step S301: Calculate the area s based on the regional traffic data a Time required for workers to reach the congested area: Among them, t b represents the time required for the staff to reach the congested area in the bth historical data, and B represents the total number of historical data;

[0022] Since the work locations of staff in different areas are at different distances from the congested area, the time required for the staff to reach the intersection after receiving the instructions is also different; at the same time, the work locations of staff in the same area are at the same distance from the same congested area. Since other factors will have a certain impact on the required time, such as the reaction speed of different staff and the different network signals in different areas, it is necessary to take the average of historical data to improve the accuracy of the calculation.

[0023] Step S302: construct a traffic congestion model, input the road congestion index, the number of vehicles in a stopped working state and the road capacity value, and output the congestion duration;

[0024] Traffic congestion model: T = a1*r+a2*e -O′ *UPO+c, Among them, O1 means that area s is not affected a The maximum value of the vehicle in the stopped working state of the road capacity, O' represents the area s a The influencing factors of the inner road capacity, a1 and a2 represent the model parameters, and c represents the random error of the model;

[0025] Step S303: Optimizing the traffic congestion model:

[0026] The predicted congestion duration and the actual congestion duration in the historical data are fitted. The fitting formula for the predicted congestion duration and the actual congestion duration is: Where w represents the fitting value of the predicted congestion duration and the actual congestion duration, T' represents the actual value of the congestion duration, (TT') b It represents the difference between the predicted value of congestion duration and the actual value of congestion duration in the historical data of item b;

[0027] The model parameters a1, a2 and the random error c of the model are continuously updated until the fitting value of the predicted congestion duration and the actual congestion duration reaches the minimum, then the updating is stopped to obtain the optimal solution of the model parameters a1, a2 and the random error c of the model, and the optimization of the traffic congestion model is completed.

[0028] Furthermore, the specific implementation process of step S400 includes:

[0029] Based on real-time vehicle operation data and real-time regional traffic data, the optimized traffic congestion model outputs the area s a The congestion duration of area s a The congestion duration is longer than that of area s a When the time required for the staff to reach the congested area is recorded, the area s a The road congestion index and regional traffic vehicle distribution map are used to generate an early warning list; the early warning list of all areas in the city is fed back to the city traffic administrator according to the road congestion index from large to small, assisting the city traffic administrator in mobilizing staff.

[0030] When the congestion duration of an area is less than or equal to the time required for staff to reach the congested area, when the staff arrives at the congested area, the traffic congestion state has changed to normal, and there is no need for staff to clear the traffic. Therefore, the congestion duration of the area is calculated through the traffic congestion model to improve the efficiency of traffic management.

[0031] An urban vehicle network traffic management system, the system comprising a data acquisition module, a congestion analysis module, a model building module and a subject conversion module;

[0032] The data acquisition module includes a region division unit and a collection unit, which generates vehicle operation data and regional traffic data by extracting vehicle logs;

[0033] The congestion analysis module includes a vehicle distribution unit and a congestion index unit, which are used to construct a regional traffic vehicle distribution map and calculate the regional road congestion index;

[0034] The model building module includes an arrival unit and a model unit, which are used to calculate the time required for staff to reach the congested area and build a traffic assessment model;

[0035] The feedback module generates a warning list when the congestion duration is longer than the time required for staff to reach the congested area; and feeds back the warning list of all areas in the city to the city traffic administrator according to the road congestion index from large to small, to assist the city traffic administrator in mobilizing staff.

[0036] Further, the data acquisition module includes a region division unit and a collection unit;

[0037] The area division unit divides the urban traffic section into areas according to the distribution of traffic lights, and constructs an area set S = {s a |a∈[1,A]}, where s a represents the ath area, A represents the total number of areas in the urban traffic division area;

[0038] The collection unit, with user authorization, connects to the Internet of Vehicles, extracts vehicle logs in the area through the Internet of Vehicles cloud, and collects vehicle operation data through the vehicle's own sensors; directly obtains regional traffic data through regional traffic facilities, and the regional traffic data includes road capacity, the time required for staff to reach the congested area, and the maximum number of stopped vehicles that does not affect road capacity.

[0039] Further, the congestion analysis module includes a vehicle distribution unit and a congestion index unit;

[0040] The vehicle distribution unit, in area s a In the process, based on the vehicle operation data, the distribution of all vehicles on the roads in the region is extracted to construct a regional traffic vehicle distribution map;

[0041] The congestion index unit marks the working status of all vehicles in the regional traffic vehicle distribution map; based on the route information of the vehicle, the vehicle is divided into three working statuses: normal working status, abnormal working status and stopped working status; if the vehicle has not reached the destination, the vehicle is marked as a normal working status; if the vehicle has reached the destination and the vehicle is still running, the vehicle is marked as an abnormal working status; if the vehicle is no longer running, the vehicle is marked as a stopped working status; the number of vehicles in the normal working status, abnormal working status and stopped working status in the regional traffic vehicle distribution map is counted, and recorded as U, P and O respectively; based on the regional traffic vehicle distribution map, the regional s is calculated. a Road congestion index: r = (U + P) / UPO, where UPO represents area s a road capacity value.

[0042] Further, the model building module includes an arrival unit and a model unit;

[0043] The arrival unit calculates the area s based on the regional traffic data. a The time required for the staff to reach the congested area: t = Among them, t b represents the time required for the staff to reach the congested area in the bth historical data, and B represents the total number of historical data;

[0044] The model unit constructs a traffic congestion model, inputs the road congestion index, the number of vehicles in a stopped working state and the road traffic capacity value, and outputs the congestion duration; Traffic congestion model: T = a1*r + a2*e -O′ *UPO+c, Among them, O1 means that area s is not affected a The maximum value of the vehicle in the stopped working state of the road capacity, O' represents the area s aThe influencing factors of the road capacity, a1 and a2 represent the model parameters, and c represents the random error of the model; the traffic congestion model is optimized: the predicted value of congestion duration and the actual value of congestion duration in the historical data are fitted, and the fitting formula of the predicted value of congestion duration and the actual value of congestion duration is: Where w represents the fitting value of the predicted congestion duration and the actual congestion duration, T' represents the actual value of the congestion duration, (TT') b Represents the difference between the predicted congestion duration and the actual congestion duration in the bth historical data; continuously update the model parameters a1, a2 and the random error c of the model until the fitting value of the predicted congestion duration and the actual congestion duration reaches the minimum, stop updating, obtain the optimal solution of the model parameters a1, a2 and the random error c of the model, and the traffic congestion model optimization is completed.

[0045] Furthermore, the feedback module: based on the real-time vehicle operation data and the real-time regional traffic data, outputs the area s by the optimized traffic congestion model a The congestion duration of area s a The congestion duration is longer than that of area s a When the time required for the staff to reach the congested area is recorded, the area s a The road congestion index and regional traffic vehicle distribution map are used to generate an early warning list; the early warning list of all areas in the city is fed back to the city traffic administrator according to the road congestion index from large to small, assisting the city traffic administrator in mobilizing staff.

[0046] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: in a city vehicle network traffic management system and method provided by the present invention, after user authorization, vehicle logs are extracted to generate vehicle operation data and regional traffic data; based on the vehicle operation data, a regional traffic vehicle distribution map is constructed, and the road congestion index of the region is calculated; based on the vehicle operation data and the regional traffic data, the time required for staff to reach the congested area is calculated, and a traffic assessment model is constructed; when the congestion duration is greater than the time required for staff to reach the congested area, an early warning list is generated; the early warning lists of all areas in the city are fed back to the city traffic administrator according to the road congestion index from large to small, to assist the city traffic administrator in mobilizing the staff; thereby improving the efficiency of traffic management and alleviating the congestion problem. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0048] Figure 1 It is a structural schematic diagram of a city vehicle network traffic management system of the present invention;

[0049] Figure 2 It is a schematic diagram of the steps of a city vehicle network traffic management method of the present invention. DETAILED DESCRIPTION

[0050] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0051] See also Figure 1-Figure 2 , the present invention provides a technical solution:

[0052] A method for urban vehicle network traffic management, the method comprising the following steps:

[0053] Step S100: With user authorization, extract vehicle logs and generate vehicle operation data and regional traffic data;

[0054] Step S200: constructing a regional traffic vehicle distribution map based on vehicle operation data and calculating a regional road congestion index;

[0055] Step S300: Based on the vehicle operation data and regional traffic data, the time required for the staff to reach the congested area is calculated, and a traffic assessment model is constructed;

[0056] Step S400: When the congestion duration is longer than the time required for staff to reach the congested area, a warning list is generated; the warning list of all areas in the city is fed back to the city traffic administrator according to the road congestion index from large to small, to assist the city traffic administrator in mobilizing staff.

[0057] Specifically, the specific implementation process of step S100 includes:

[0058] Step S101: Divide the urban traffic section into regions according to the distribution of traffic lights, and construct a region set S = {s a |a∈[1,A]}, where s a represents the ath area, A represents the total number of areas in the urban traffic division area;

[0059] For example, city T is divided into urban traffic sections according to the distribution of traffic lights, and the regional set S = {s 1 ,s 2 ,s 3 ,s 4 ,s 5 ,s 6}, A=6.

[0060] Step S102: With user authorization, connect to the Internet of Vehicles, extract vehicle logs in the area through the Internet of Vehicles cloud, and collect vehicle operation data through the vehicle's own sensors; directly obtain regional traffic data through regional traffic facilities, and the regional traffic data includes road capacity, the time required for staff to reach the congested area, and the maximum number of stopped vehicles that does not affect road capacity.

[0061] Specifically, the specific implementation process of step S200 includes:

[0062] Step S201: In area s a In the process, based on the vehicle operation data, the distribution of all vehicles on the roads in the region is extracted to construct a regional traffic vehicle distribution map;

[0063] Step S202: Mark the working status of all vehicles in the regional traffic vehicle distribution map; based on the route information of the vehicle, divide the vehicle into three working statuses: normal working status, abnormal working status and stopped working status; if the vehicle has not arrived at the destination, the vehicle is marked as normal working status; if the vehicle has arrived at the destination and the vehicle is still running, the vehicle is marked as abnormal working status; if the vehicle is no longer running, the vehicle is marked as stopped working status;

[0064] Step S203: Count the number of vehicles in normal working state, abnormal working state and stopped working state in the regional traffic vehicle distribution map, which are recorded as U, P and O respectively; calculate the regional s based on the regional traffic vehicle distribution map. a Road congestion index: r = (U + P) / UPO, where UPO represents area s a road capacity value.

[0065] For example: the number of vehicles in normal working state, abnormal working state and stopped working state in area s1 are 100, 300 and 20 respectively, and the road capacity value UPO of area s1 is 200, then the road congestion index r of area s1 is (100+300) / 200=2.

[0066] Specifically, the specific implementation process of step S300 includes:

[0067] Step S301: Calculate the area s based on the regional traffic data a Time required for workers to reach the congested area: Among them, t b represents the time required for the staff to reach the congested area in the bth historical data, and B represents the total number of historical data;

[0068] Step S302: construct a traffic congestion model, input the road congestion index, the number of vehicles in a stopped working state and the road capacity value, and output the congestion duration;

[0069] Traffic congestion model: T = a1*r+a2*e -O′ *UPO+c, Among them, O1 means that area s is not affected a The maximum value of the vehicle in the stopped working state of the road capacity, O' represents the area s a The influencing factors of the inner road capacity, a1 and a2 represent the model parameters, and c represents the random error of the model;

[0070] Step S303: Optimizing the traffic congestion model:

[0071] The predicted congestion duration and the actual congestion duration in the historical data are fitted. The fitting formula for the predicted congestion duration and the actual congestion duration is: Where w represents the fitting value of the predicted congestion duration and the actual congestion duration, T' represents the actual value of the congestion duration, (TT') b It represents the difference between the predicted value of congestion duration and the actual value of congestion duration in the historical data of item b;

[0072] The model parameters a1, a2 and the random error c of the model are continuously updated until the fitting value of the predicted congestion duration and the actual congestion duration reaches the minimum, then the updating is stopped to obtain the optimal solution of the model parameters a1, a2 and the random error c of the model, and the optimization of the traffic congestion model is completed.

[0073] Specifically, the specific implementation process of step S400 includes:

[0074] Based on real-time vehicle operation data and real-time regional traffic data, the optimized traffic congestion model outputs the area s a The congestion duration of area s a The congestion duration is longer than that of area s a When the time required for the staff to reach the congested area is recorded, the area s a The road congestion index and regional traffic vehicle distribution map are used to generate an early warning list; the early warning list of all areas in the city is fed back to the city traffic administrator according to the road congestion index from large to small, assisting the city traffic administrator in mobilizing staff.

[0075] An urban vehicle network traffic management system, the system includes a data collection module, a congestion analysis module, a model building module and a subject conversion module;

[0076] The data collection module includes a regional division unit and a collection unit, which generates vehicle operation data and regional traffic data by extracting vehicle logs;

[0077] The congestion analysis module includes a vehicle distribution unit and a congestion index unit, which are used to construct a regional traffic vehicle distribution map and calculate the regional road congestion index;

[0078] The model building module includes an arrival unit and a model unit, which are used to calculate the time required for staff to reach the congested area and build a traffic assessment model;

[0079] The feedback module generates a warning list when the congestion duration is longer than the time required for staff to reach the congested area; the warning list of all areas in the city is fed back to the city traffic administrator according to the road congestion index from large to small, to assist the city traffic administrator in mobilizing staff.

[0080] Preferably, the data acquisition module includes a region division unit and a collection unit;

[0081] The regional division unit divides the urban traffic section into regions according to the distribution of traffic lights and constructs a regional set S = {s a |a∈[1,A]}, where s a represents the ath area, A represents the total number of areas in the urban traffic division area;

[0082] The collection unit, with user authorization, connects to the Internet of Vehicles, extracts vehicle logs in the area through the Internet of Vehicles cloud, and collects vehicle operation data through the vehicle's own sensors; it directly obtains regional traffic data through regional traffic facilities. The regional traffic data includes road capacity, the time required for staff to reach the congested area, and the maximum number of stopped vehicles that does not affect road capacity.

[0083] Preferably, the congestion analysis module includes a vehicle distribution unit and a congestion index unit;

[0084] Vehicle distribution unit, in area s a In the process, based on the vehicle operation data, the distribution of all vehicles on the roads in the region is extracted to construct a regional traffic vehicle distribution map;

[0085] The congestion index unit marks the working status of all vehicles in the regional traffic vehicle distribution map; based on the route information of the vehicle, the vehicle is divided into three working states: normal working state, abnormal working state and stopped working state; if the vehicle has not reached the destination, the vehicle is marked as normal working state; if the vehicle has reached the destination and the vehicle is still running, the vehicle is marked as abnormal working state; if the vehicle is no longer running, the vehicle is marked as stopped working state; the number of vehicles in normal working state, abnormal working state and stopped working state in the regional traffic vehicle distribution map is counted, and recorded as U, P and O respectively; based on the regional traffic vehicle distribution map, the regional s is calculated. aRoad congestion index: r = (U + P) / UPO, where UPO represents area s a road capacity value.

[0086] Preferably, the model building module includes an arrival unit and a model unit;

[0087] Arrival unit, based on regional traffic data, calculates the area s a Time required for workers to reach the congested area: Among them, t b represents the time required for the staff to reach the congested area in the bth historical data, and B represents the total number of historical data;

[0088] Model unit, builds traffic congestion model, inputs road congestion index, number of vehicles in stopped working state and road capacity value, and outputs congestion duration; Traffic congestion model: T = a1*r+a2*e -O′ *UPO+c, Among them, O1 means that area s is not affected a The maximum value of the vehicle in the stopped working state of the road capacity, O' represents the area s a The influencing factors of the road capacity, a1 and a2 represent the model parameters, and c represents the random error of the model; the traffic congestion model is optimized: the predicted value of congestion duration and the actual value of congestion duration in the historical data are fitted, and the fitting formula of the predicted value of congestion duration and the actual value of congestion duration is: Where w represents the fitting value of the predicted congestion duration and the actual congestion duration, T' represents the actual value of the congestion duration, (TT') b Represents the difference between the predicted congestion duration and the actual congestion duration in the bth historical data; continuously update the model parameters a1, a2 and the random error c of the model until the fitting value of the predicted congestion duration and the actual congestion duration reaches the minimum, stop updating, obtain the optimal solution of the model parameters a1, a2 and the random error c of the model, and the traffic congestion model optimization is completed.

[0089] Preferably, the feedback module: based on the real-time vehicle operation data and the real-time regional traffic data, the optimized traffic congestion model outputs the area s a The congestion duration of area s a The congestion duration is longer than that of area s a When the time required for the staff to reach the congested area is recorded, the area s a The road congestion index and regional traffic vehicle distribution map are used to generate an early warning list; the early warning list of all areas in the city is fed back to the city traffic administrator according to the road congestion index from large to small, assisting the city traffic administrator in mobilizing staff.

[0090] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0091] Finally, it should be noted that the above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for urban vehicle network traffic management, characterized in that: The method comprises the following steps: Step S100: With user authorization, extract vehicle logs and generate vehicle operation data and regional traffic data; Step S200: constructing a regional traffic vehicle distribution map based on vehicle operation data and calculating a regional road congestion index; Step S300: Based on the vehicle operation data and regional traffic data, the time required for the staff to reach the congested area is calculated, and a traffic assessment model is constructed; Step S400: When the congestion duration is longer than the time required for staff to reach the congested area, a warning list is generated; the warning list of all areas in the city is fed back to the city traffic administrator according to the road congestion index from large to small, to assist the city traffic administrator in mobilizing staff.

2. A method for urban vehicle network traffic management according to claim 1, characterized in that: The specific implementation process of step S100 includes: Step S101: Divide the urban traffic section into regions according to the distribution of traffic lights, and construct a region set S = {s a |a∈[1,A]}, where s a represents the ath area, A represents the total number of areas in the urban traffic division area; Step S102: With user authorization, connect to the Internet of Vehicles, extract vehicle logs in the area through the Internet of Vehicles cloud, and collect vehicle operation data through the vehicle's own sensors; directly obtain regional traffic data through regional traffic facilities, and the regional traffic data includes road capacity, the time required for staff to reach the congested area, and the maximum number of stopped vehicles that does not affect road capacity.

3. The urban vehicle network traffic management method according to claim 2 is characterized in that: The specific implementation process of step S200 includes: Step S201: In area s a In the process, based on the vehicle operation data, the distribution of all vehicles on the roads in the region is extracted to construct a regional traffic vehicle distribution map; Step S202: marking the working status of all vehicles in the regional traffic vehicle distribution map; based on the route information of the vehicle, the vehicle is divided into three working statuses: normal working status, abnormal working status and stopped working status; if the vehicle has not arrived at the destination, the vehicle is marked as a normal working status; if the vehicle has arrived at the destination and the vehicle is still running, the vehicle is marked as an abnormal working status; if the vehicle is no longer running, the vehicle is marked as a stopped working status; Step S203: Count the number of vehicles in normal working state, abnormal working state and stopped working state in the regional traffic vehicle distribution map, which are recorded as U, P and O respectively; calculate the regional s based on the regional traffic vehicle distribution map. a Road congestion index: r=(U+P) / UPO, where UPO represents the area s a road capacity value.

4. The urban vehicle network traffic management method according to claim 3 is characterized in that: The specific implementation process of step S300 includes: Step S301: Calculate the area s based on the regional traffic data a Time required for staff to reach the congested area: Among them, t b represents the time required for the staff to reach the congested area in the bth historical data, and B represents the total number of historical data; Step S302: construct a traffic congestion model, input the road congestion index, the number of vehicles in a stopped working state and the road capacity value, and output the congestion duration; Traffic congestion model: T = a1*r+a2*e -O′ *UPO+c, Among them, O1 means that area s is not affected a The maximum value of the vehicle in the stopped working state of the road capacity, O' represents the area s a The influencing factors of the inner road capacity, a1 and a2 represent the model parameters, and c represents the random error of the model; Step S303: Optimizing the traffic congestion model: The predicted congestion duration and the actual congestion duration in the historical data are fitted. The fitting formula for the predicted congestion duration and the actual congestion duration is: Where w represents the fitting value of the predicted congestion duration and the actual congestion duration, T' represents the actual value of the congestion duration, (TT') b It represents the difference between the predicted value of congestion duration and the actual value of congestion duration in the historical data of item b; The model parameters a1, a2 and the random error c of the model are continuously updated until the fitting value of the predicted congestion duration and the actual congestion duration reaches the minimum, then the updating is stopped to obtain the optimal solution of the model parameters a1, a2 and the random error c of the model, and the optimization of the traffic congestion model is completed.

5. The urban vehicle network traffic management method according to claim 4 is characterized in that: The specific implementation process of step S400 includes: Based on real-time vehicle operation data and real-time regional traffic data, the optimized traffic congestion model outputs the area s a The congestion duration of area s a The congestion duration is longer than that of area s a When the time required for the staff to reach the congested area is recorded, the area s a The road congestion index and regional traffic vehicle distribution map are used to generate an early warning list; the early warning list of all areas in the city is fed back to the city traffic administrator according to the road congestion index from large to small, assisting the city traffic administrator in mobilizing staff.

6. A city vehicle network traffic management system, characterized in that: The system includes a data acquisition module, a congestion analysis module, a model building module and a subject conversion module; The data acquisition module includes a region division unit and a collection unit, which generates vehicle operation data and regional traffic data by extracting vehicle logs; The congestion analysis module includes a vehicle distribution unit and a congestion index unit, which are used to construct a regional traffic vehicle distribution map and calculate the regional road congestion index; The model building module includes an arrival unit and a model unit, which are used to calculate the time required for staff to reach the congested area and build a traffic assessment model; The feedback module generates a warning list when the congestion duration is longer than the time required for staff to reach the congested area; and feeds back the warning list of all areas in the city to the city traffic administrator according to the road congestion index from large to small, to assist the city traffic administrator in mobilizing staff.

7. The urban vehicle network traffic management system according to claim 6, characterized in that: The data acquisition module includes a region division unit and a collection unit; The area division unit divides the urban traffic section into areas according to the distribution of traffic lights, and constructs an area set S = {s a |a∈[1,A]}, where s a represents the ath area, A represents the total number of areas in the urban traffic division area; The collection unit, with user authorization, connects to the Internet of Vehicles, extracts vehicle logs in the area through the Internet of Vehicles cloud, and collects vehicle operation data through the vehicle's own sensors; directly obtains regional traffic data through regional traffic facilities, and the regional traffic data includes road capacity, the time required for staff to reach the congested area, and the maximum number of stopped vehicles that does not affect road capacity.

8. The urban vehicle network traffic management system according to claim 7 is characterized by: The congestion analysis module includes a vehicle distribution unit and a congestion index unit; The vehicle distribution unit, in area s a In the process, based on the vehicle operation data, the distribution of all vehicles on the roads in the region is extracted to construct a regional traffic vehicle distribution map; The congestion index unit marks the working status of all vehicles in the regional traffic vehicle distribution map; based on the route information of the vehicles, the vehicles are divided into three working statuses: normal working status, abnormal working status and stopped working status; If the vehicle has not arrived at the destination, the vehicle is marked as a normal working state; if the vehicle has arrived at the destination and the vehicle is still running, the vehicle is marked as an abnormal working state; if the vehicle is no longer running, the vehicle is marked as a stopped working state; the number of vehicles in the normal working state, abnormal working state and stopped working state in the regional traffic vehicle distribution map is counted as U, P and O respectively; Based on the regional traffic vehicle distribution map, calculate the area s a Road congestion index: r = (U + P) / UPO, where UPO represents area s a road capacity value.

9. The urban vehicle network traffic management system according to claim 8, characterized in that: The model building module includes an arrival unit and a model unit; The arrival unit calculates the area s based on the regional traffic data. a Time required for staff to reach the congested area: Among them, t b represents the time required for the staff to reach the congested area in the bth historical data, and B represents the total number of historical data; The model unit constructs a traffic congestion model, inputs the road congestion index, the number of vehicles in a stopped working state and the road traffic capacity value, and outputs the congestion duration; Traffic congestion model: T = a1*r + a2*e -O′ *UPO+c, Among them, O1 means that area s is not affected a The maximum value of the vehicle in the stopped working state of the road capacity, O' represents the area s a The influencing factors of the road capacity, a1 and a2 represent the model parameters, and c represents the random error of the model; the traffic congestion model is optimized: the predicted value of congestion duration and the actual value of congestion duration in the historical data are fitted, and the fitting formula of the predicted value of congestion duration and the actual value of congestion duration is: Where w represents the fitting value of the predicted congestion duration and the actual congestion duration, T' represents the actual value of the congestion duration, (TT') b Represents the difference between the predicted congestion duration and the actual congestion duration in the bth historical data; continuously update the model parameters a1, a2 and the random error c of the model until the fitting value of the predicted congestion duration and the actual congestion duration reaches the minimum, stop updating, obtain the optimal solution of the model parameters a1, a2 and the random error c of the model, and the traffic congestion model optimization is completed.

10. The urban vehicle network traffic management system according to claim 9, characterized in that: The feedback module: based on real-time vehicle operation data and real-time regional traffic data, the optimized traffic congestion model outputs the area s a The congestion duration of area s a The congestion duration is longer than that of area s a When the time required for the staff to reach the congested area is recorded, the area s a The road congestion index and regional traffic vehicle distribution map are used to generate an early warning list; the early warning list of all areas in the city is fed back to the city traffic administrator according to the road congestion index from large to small, assisting the city traffic administrator in mobilizing staff.

Images