Intelligent traffic management system and method based on artificial intelligence

Abstract

The present invention relates to the field of intelligent traffic management technology, specifically to an intelligent traffic management system and method based on artificial intelligence, wherein the system includes a road section congestion assessment module, wherein the road section congestion assessment module obtains traffic road condition information in each road section in a traffic layout model in real time through artificial intelligence technology and image recognition technology, and analyzes the road section congestion assessment value corresponding to each road section in the traffic layout model. The present invention can realize dynamic adjustment of the traffic light display time planning scheme of the corresponding road section according to the vehicle conditions of the road section, and in the adjustment process, taking into account the associated coordinated interference road section set corresponding to each road section, and the adjustment coordinated coefficient set of each element in the obtained associated coordinated interference road section set based on the corresponding road section, realizes joint control adjustment between different traffic lights, reduces the interference effect on the traffic congestion situation in the subsequent connected road sections caused by the adjustment of the traffic congestion situation at the corresponding intersection, and realizes effective management of traffic data.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent traffic management, and specifically to an intelligent traffic management system and method based on artificial intelligence. Background Art

[0002] Smart traffic management is an important trend in the current development of urban traffic. It uses new technologies such as artificial intelligence, big data analysis, the Internet of Things, and cloud computing to realize the intelligence, networking, and informatization of the transportation system.

[0003] Smart traffic management is achieved by integrating advanced traffic management systems, information technology, data communication transmission technology, and computer processing technology to achieve comprehensive perception, automatic analysis, active control, and high-quality services of traffic flows, thereby ensuring traffic safety, alleviating traffic congestion, increasing road capacity, and improving traffic management levels and the quality of public travel services.

[0004] In the existing intelligent traffic management system based on artificial intelligence, the formulation of the display time planning scheme corresponding to the traffic light is often achieved through manual preset. Even for the existing traffic lights with dynamically changeable display time planning schemes, the light changing method adopted is often to directly call up the preset display time planning scheme in the database by monitoring the traffic flow at the traffic light intersection through a camera. This method cannot realize the joint control of the display time planning schemes between traffic lights, which often leads to unreasonable situations in the called traffic light display time planning schemes. The relief of the corresponding traffic congestion at the corresponding intersection leads to further aggravation of the traffic congestion in the subsequent connected sections. Therefore, the existing technology has major defects. Summary of the invention

[0005] The purpose of the present invention is to provide an intelligent traffic management system and method based on artificial intelligence to solve the problems raised in the above background technology.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: an intelligent traffic management method based on artificial intelligence, the method comprising the following steps:

[0007] S1. Divide the area to be tested into different traffic control areas, obtain the traffic light equipment information and corresponding path distribution information in each traffic control area, and build a traffic layout model corresponding to each traffic control area;

[0008] S2. According to the connection relationship between each road section in the traffic layout model, a set of associated cooperative interference road sections corresponding to each road section in the traffic layout model is constructed;

[0009] S3, using artificial intelligence technology and image recognition technology to obtain real-time traffic information on each road section in the traffic layout model, and analyzing the road congestion assessment value corresponding to each road section in the traffic layout model;

[0010] S4, combining the historical section congestion adjustment coefficient of each section in the traffic layout model and the obtained section congestion assessment value of the corresponding section, analyzing the predicted value of the section congestion adjustment coefficient corresponding to the corresponding section in the traffic layout model; combining the associated coordinated interference section set corresponding to the section, adjusting the coordinated coefficient set of each element in the obtained associated coordinated interference section set based on the corresponding section respectively;

[0011] S5. Obtain a congestion coordination adjustment coefficient set for each road section in the traffic layout model according to the predicted value of the road section congestion adjustment coefficient corresponding to each road section in the traffic layout model and the respective corresponding adjustment coordination coefficients when the corresponding road section belongs to the associated coordinated interference road section set of other road sections, and adjust the traffic lights in the corresponding road section based on the congestion coordination adjustment coefficient set of each road section;

[0012] S6. Continuously monitor the traffic condition information of the corresponding road section within the preset time period after the traffic lights in the traffic layout model are adjusted, feed back to the administrator of the corresponding traffic control area, and jump to step S3 with the obtained monitoring results.

[0013] Furthermore, the traffic light equipment information includes the location coordinates of the traffic light and the time display scheme of the traffic light, wherein the time display scheme of the traffic light is the duration of a lighting cycle of the corresponding traffic light, and the planning content of the green light duration and the red light duration corresponding to each traffic direction in a lighting cycle; a traffic direction corresponding to each lane in the road section;

[0014] The path distribution information is a set of path information corresponding to all paths in the corresponding traffic control area; the path information includes the distribution area of ​​each path and the lane layout of the corresponding path;

[0015] In the traffic layout model corresponding to each traffic control area constructed, a proportional scaling model of the path distribution area of ​​the corresponding traffic control area is constructed according to the path distribution area in the obtained path distribution information, which is recorded as a first path distribution scaling model; in combination with the lane layouts at different positions in each path in the path distribution information, the lanes of each path are marked in the first path distribution scaling model, and the time display scheme of the traffic light is bound to the time display scheme of the corresponding traffic light in the first path distribution scaling model, so as to obtain a traffic layout model corresponding to the corresponding traffic control area;

[0016] In the process of constructing the associated collaborative interference section set corresponding to each road section in the traffic layout model, the road section between two adjacent traffic light intersections is recorded as a road section, and the associated collaborative interference section set corresponding to each road section in the traffic layout model is a set consisting of all road sections connected to the corresponding road section in the corresponding traffic layout model.

[0017] In the present invention, due to the different connection relationships between different road sections, the associated coordinated interference road section sets corresponding to the various road sections are different, and the associated coordinated interference road section set corresponding to each element in the associated coordinated interference road section set corresponding to the corresponding road section includes the corresponding road section.

[0018] Further, the traffic condition information includes the density of passing vehicles in the corresponding road section, the quotient of the number of passing vehicles in each lane at the traffic light intersection of the corresponding road section within the latest preset unit time divided by the preset unit time, and the density of passing vehicles in a preset area belonging to the corresponding road section at the traffic light intersection; the passing vehicle density represents the ratio of the number of passing vehicles in the corresponding road section to the area of ​​the corresponding road section;

[0019] When analyzing the road congestion assessment value corresponding to each road section in the traffic layout model, the following formula is used:

[0020] YP g =VD g +μ·RVD g +μ1·LVD g ,

[0021] Among them, YP g VD represents the road congestion assessment value corresponding to the g-th road section in the traffic layout model; g RVD represents the vehicle density of the g-th road segment in the traffic layout model in the most recently acquired traffic information. g LVD represents the density of vehicles passing through the preset area at the traffic light intersection in the g-th road section in the traffic layout model in the most recently acquired traffic condition information; g Indicates the maximum value of the quotient of the number of vehicles passing through each lane at the traffic light intersection of the corresponding road section in the latest preset unit time divided by the preset unit time in the most recently acquired traffic condition information of the g-th road section in the traffic layout model;

[0022] μ and μ1 are both evaluation conversion coefficients, and μ and μ1 are both constants preset in the database.

[0023] When evaluating the congestion assessment value corresponding to each road section in the present invention, the assessment is performed from three perspectives, namely, the vehicle density of the entire road section, the vehicle density of the corresponding road section within a preset radius at the traffic light intersection, and the ratio of the number of vehicles passing through each lane at the traffic light intersection of the corresponding road section within the most recent preset unit time to the time.

[0024] Furthermore, the historical road section congestion adjustment coefficient represents the adjustment coefficient of the duration of each color light in the corresponding traffic light of the corresponding road section in the historical data, and the adjustment object of the adjustment coefficient is the ratio of the duration of the green light corresponding to the traffic direction of each lane to the duration of the light cycle in the corresponding traffic light; the adjustment coefficient is equal to the ratio of the corresponding data of the corresponding adjustment object after adjustment and before adjustment;

[0025] When analyzing the predicted value of the road congestion adjustment coefficient corresponding to the corresponding road section in the traffic layout model, the historical road congestion adjustment coefficient of each road section in the traffic layout model and the obtained road congestion assessment value of the corresponding road section are combined to construct a historical congestion adjustment data pair for each traffic direction corresponding to the adjustment object of the corresponding road section, which is recorded as (YPL, TX).

[0026] Each pair of historical congestion adjustment data of the corresponding adjustment object for each traffic direction of the corresponding road section corresponds to a maximum monotonic change time interval, the maximum monotonic change time interval contains one or more adjustment time points corresponding to the road section congestion adjustment coefficients of the corresponding traffic direction, and the road section congestion adjustment coefficients of the corresponding adjustment time points adjacent to the maximum monotonic change time interval and the road section congestion adjustment coefficients corresponding to any adjustment time point in the maximum monotonic change time interval do not show a monotonic change trend; the congestion adjustment coefficients of the various road sections involved in the maximum monotonic change time interval show a monotonic change trend, and the maximum monotonic change interval indicates that the congestion adjustment coefficients of the various road sections corresponding to the corresponding time interval are all greater than or equal to 1 or are all less than 1;

[0027] Wherein, TX represents the product of the congestion adjustment coefficients of each road section involved in the corresponding maximum monotonic change time interval of the corresponding historical congestion adjustment data; YPL represents the maximum value of the congestion assessment values ​​of each road section of the corresponding road section in the corresponding maximum monotonic change time interval of the corresponding historical congestion adjustment data;

[0028] According to the Sigmoid function model, function fitting is performed on each pair of historical congestion adjustment data of the adjustment object corresponding to each traffic direction of the corresponding road section, and the obtained function is recorded as the congestion adjustment fitting function of the corresponding traffic direction of the corresponding road section; the function value after substituting the section congestion assessment value of the corresponding road section in the traffic layout model into the congestion adjustment fitting function of the corresponding traffic direction of the corresponding road section is recorded as the predicted value of the section congestion adjustment coefficient corresponding to the corresponding traffic direction of the corresponding road section in the traffic layout model.

[0029] Furthermore, when the adjustment coordination coefficient set of each element in the obtained associated coordinated interference section set is based on the corresponding section, the associated coordinated interference section set corresponding to the section is obtained, and the adjustment coordination coefficient set of the a-th element in the associated coordinated interference section set corresponding to the section based on the corresponding section is recorded as GXa, and the n-th element in GXa is recorded as GXa {n} ,

[0030] G JZ {n} =Q n {(TXX a -1) TDX a ·YPX a MXa / M+YPX},

[0031] Among them, TXX a It represents the predicted value of the congestion adjustment coefficient corresponding to the ath element in the associated cooperative interference road section set corresponding to the road section when the traffic direction is the corresponding road section; TDX a Indicates the corresponding adjustment object when the ath element in the associated cooperative interference section set corresponding to the section is directed to the corresponding section; YPX a represents the road section congestion assessment value corresponding to the ath element in the associated coordinated interference road section set corresponding to the road section; MXa represents the road section area corresponding to the ath element in the associated coordinated interference road section set corresponding to the corresponding road section; M represents the road section area of ​​the corresponding road section;

[0032] YPX represents the road congestion assessment value corresponding to the corresponding road section; Q n {} represents the congestion adjustment fitting function corresponding to the nth traffic direction of the corresponding road section.

[0033] Furthermore, when obtaining the congestion coordination adjustment coefficient set of each road section in the traffic layout model, the congestion coordination adjustment coefficient of the i-th road section in the traffic layout model is recorded as CSi, and the b-th element in CSi is recorded as CSi {b} ,

[0034] ,

[0035] Among them, TX （i，b） TXX represents the predicted value of the road congestion adjustment coefficient corresponding to the b-th traffic direction of the i-th road section in the traffic layout model; （i，b，a） represents the value of the bth element in the adjustment coordination coefficient set of the ath element in the associated coordinated interference section set of the i-th section in the traffic layout model based on the corresponding section; ai represents the total number of elements in the associated coordinated interference section set of the i-th section in the traffic layout model;

[0036] When adjusting the traffic lights in the corresponding road sections based on the congestion coordination adjustment coefficient set of each road section, each element in the congestion coordination adjustment coefficient set of the corresponding road section is multiplied by the corresponding adjustment object to obtain a new adjustment object.

[0037] An intelligent traffic management system based on artificial intelligence, the system includes the following modules:

[0038] A traffic layout model building module, wherein the traffic layout model building module divides the area to be tested into different traffic control areas, obtains the traffic light equipment information and the corresponding path distribution information in each traffic control area, and builds a traffic layout model corresponding to each traffic control area;

[0039] A road section relationship analysis module, wherein the road section relationship analysis module constructs an associated collaborative interference road section set corresponding to each road section in the traffic layout model according to the connection relationship between each road section in the traffic layout model;

[0040] A road congestion assessment module, which uses artificial intelligence technology and image recognition technology to obtain real-time traffic information on each road section in the traffic layout model, and analyzes the road congestion assessment value corresponding to each road section in the traffic layout model;

[0041] A road section coordinated regulation analysis module, wherein the road section coordinated regulation analysis module combines the historical road section congestion regulation coefficient of each road section in the traffic layout model and the obtained road section congestion assessment value of the corresponding road section, analyzes the predicted value of the road section congestion regulation coefficient corresponding to the corresponding road section in the traffic layout model; combines the associated coordinated interference road section set corresponding to the road section, and adjusts the coordinated coefficient set of each element in the obtained associated coordinated interference road section set based on the corresponding road section;

[0042] A traffic regulation intelligent management module, wherein the traffic regulation intelligent management module obtains a congestion coordination adjustment coefficient set for each road section in the traffic layout model according to the predicted value of the road section congestion adjustment coefficient corresponding to each road section in the traffic layout model and the respective corresponding adjustment coordination coefficients when the corresponding road section belongs to the associated coordinated interference road section set of other road sections, and adjusts the traffic lights in the corresponding road section based on the congestion coordination adjustment coefficient set of each road section;

[0043] The traffic regulation follow-up tracking module continuously monitors the traffic condition information of the corresponding road section within a preset time period after the traffic lights in the traffic layout model are adjusted, and feeds back to the administrator of the corresponding traffic control area.

[0044] Furthermore, the road section coordinated regulation analysis module includes a congestion regulation coefficient prediction unit and a regulation coordinated coefficient set acquisition unit.

[0045] The congestion adjustment coefficient prediction unit analyzes the predicted value of the section congestion adjustment coefficient corresponding to the corresponding section in the traffic layout model in combination with the historical section congestion adjustment coefficient of each section in the traffic layout model and the obtained section congestion evaluation value of the corresponding section;

[0046] The adjustment coordination coefficient set acquisition unit combines the associated coordinated interference road section set corresponding to the road section, and obtains the adjustment coordination coefficient set of each element in the associated coordinated interference road section set based on the corresponding road section.

[0047] Compared with the prior art, the beneficial effects achieved by the present invention are: the present invention can dynamically adjust the traffic light display time planning scheme of the corresponding road section according to the vehicle conditions of the road section, and in the adjustment process, the associated collaborative interference road section set corresponding to each road section is taken into account, and the adjustment collaborative coefficient set of each element in the obtained associated collaborative interference road section set is based on the corresponding road section, respectively, to achieve joint control adjustment between different traffic lights, reduce the interference effect on the traffic congestion situation in the subsequent connected sections caused by the adjustment of the traffic congestion situation at the corresponding intersection, and achieve effective management of traffic data. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] 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:

[0049] Figure 1 It is a structural schematic diagram of the intelligent traffic management system based on artificial intelligence of the present invention;

[0050] Figure 2 It is a flow chart of the intelligent traffic management method based on artificial intelligence of the present invention. DETAILED DESCRIPTION

[0051] 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.

[0052] See also Figure 1 The present invention provides a technical solution: an intelligent traffic management system based on artificial intelligence, the system includes the following modules:

[0053] A traffic layout model building module, wherein the traffic layout model building module divides the area to be tested into different traffic control areas, obtains the traffic light equipment information and the corresponding path distribution information in each traffic control area, and builds a traffic layout model corresponding to each traffic control area;

[0054] A road section relationship analysis module, wherein the road section relationship analysis module constructs an associated collaborative interference road section set corresponding to each road section in the traffic layout model according to the connection relationship between each road section in the traffic layout model;

[0055] A road congestion assessment module, which uses artificial intelligence technology and image recognition technology to obtain real-time traffic information on each road section in the traffic layout model, and analyzes the road congestion assessment value corresponding to each road section in the traffic layout model;

[0056] A road section coordinated regulation analysis module, the road section coordinated regulation analysis module includes a congestion regulation coefficient prediction unit and a regulation coordinated coefficient set acquisition unit,

[0057] The congestion adjustment coefficient prediction unit analyzes the predicted value of the section congestion adjustment coefficient corresponding to the corresponding section in the traffic layout model in combination with the historical section congestion adjustment coefficient of each section in the traffic layout model and the obtained section congestion evaluation value of the corresponding section;

[0058] The adjustment coordination coefficient set acquisition unit combines the associated coordinated interference road section set corresponding to the road section, and respectively obtains the adjustment coordination coefficient set based on the corresponding road section for each element in the obtained associated coordinated interference road section set;

[0059] A traffic regulation intelligent management module, wherein the traffic regulation intelligent management module obtains a congestion coordination adjustment coefficient set for each road section in the traffic layout model according to the predicted value of the road section congestion adjustment coefficient corresponding to each road section in the traffic layout model and the respective corresponding adjustment coordination coefficients when the corresponding road section belongs to the associated coordinated interference road section set of other road sections, and adjusts the traffic lights in the corresponding road section based on the congestion coordination adjustment coefficient set of each road section;

[0060] The traffic regulation follow-up tracking module continuously monitors the traffic condition information of the corresponding road section within a preset time period after the traffic lights in the traffic layout model are adjusted, and feeds back to the administrator of the corresponding traffic control area.

[0061] like Figure 2 As shown, the intelligent traffic management method based on artificial intelligence comprises the following steps:

[0062] S1. Divide the area to be tested into different traffic control areas, obtain the traffic light equipment information and corresponding path distribution information in each traffic control area, and build a traffic layout model corresponding to each traffic control area;

[0063] The traffic light equipment information includes the location coordinates of the traffic light and the time display scheme of the traffic light. The time display scheme of the traffic light is the duration of a lighting cycle of the corresponding traffic light, and the planning content of the green light duration and the red light duration corresponding to each traffic direction in a lighting cycle; a traffic direction corresponding to each lane in the road section;

[0064] The path distribution information is a set of path information corresponding to all paths in the corresponding traffic control area; the path information includes the distribution area of ​​each path and the lane layout of the corresponding path;

[0065] In the traffic layout model corresponding to each traffic control area constructed, a proportional scaling model of the path distribution area of ​​the corresponding traffic control area is constructed according to the path distribution area in the obtained path distribution information, which is recorded as the first path distribution scaling model; combined with the lane layout at different positions in each path in the path distribution information, the lanes of each path are marked in the first path distribution scaling model, and the time display scheme of the traffic light is bound to the time display scheme of the corresponding traffic light in the first path distribution scaling model, so as to obtain the traffic layout model corresponding to the corresponding traffic control area.

[0066] S2. According to the connection relationship between each road section in the traffic layout model, a set of associated cooperative interference road sections corresponding to each road section in the traffic layout model is constructed;

[0067] In the process of constructing the associated collaborative interference section set corresponding to each road section in the traffic layout model, the road section between two adjacent traffic light intersections is recorded as a road section, and the associated collaborative interference section set corresponding to each road section in the traffic layout model is a set consisting of all road sections connected to the corresponding road section in the corresponding traffic layout model.

[0068] S3, using artificial intelligence technology and image recognition technology to obtain real-time traffic information on each road section in the traffic layout model, and analyzing the road congestion assessment value corresponding to each road section in the traffic layout model;

[0069] The traffic condition information includes the density of passing vehicles in the corresponding road section, the quotient of the number of passing vehicles in each lane at the traffic light intersection of the corresponding road section within the latest preset unit time divided by the preset unit time, and the density of passing vehicles in the preset area belonging to the corresponding road section at the traffic light intersection; the passing vehicle density represents the ratio of the number of passing vehicles in the corresponding road section to the area of ​​the corresponding road section;

[0070] When acquiring traffic condition information in this embodiment, the traffic condition in the corresponding road section is first photographed through the camera on the corresponding road section, and the vehicles in the photographed image are identified and located through artificial intelligence technology and image recognition technology, and the number of vehicles in the image is counted to achieve summary statistics of traffic condition data in the corresponding road section.

[0071] When analyzing the road congestion assessment value corresponding to each road section in the traffic layout model, the following formula is used:

[0072] YP g =VD g +μ·RVD g +μ1·LVD g ,

[0073] Among them, YP g VD represents the road congestion assessment value corresponding to the g-th road section in the traffic layout model; g RVD represents the vehicle density of the g-th road segment in the traffic layout model in the most recently acquired traffic information. g LVD represents the density of vehicles passing through the preset area at the traffic light intersection in the g-th road section in the traffic layout model in the most recently acquired traffic condition information; g Indicates the maximum value of the quotient of the number of vehicles passing through each lane at the traffic light intersection of the corresponding road section in the latest preset unit time divided by the preset unit time in the most recently acquired traffic condition information of the g-th road section in the traffic layout model;

[0074] μ and μ1 are both evaluation conversion coefficients, and μ and μ1 are both constants preset in the database.

[0075] S4, combining the historical section congestion adjustment coefficient of each section in the traffic layout model and the obtained section congestion assessment value of the corresponding section, analyzing the predicted value of the section congestion adjustment coefficient corresponding to the corresponding section in the traffic layout model; combining the associated coordinated interference section set corresponding to the section, adjusting the coordinated coefficient set of each element in the obtained associated coordinated interference section set based on the corresponding section respectively;

[0076] The historical road section congestion adjustment coefficient represents the adjustment coefficient of the duration of each color light in the corresponding traffic light of the corresponding road section in the historical data. The adjustment object of the adjustment coefficient is the ratio of the duration of the green light corresponding to the traffic direction of each lane to the duration of the light cycle in the corresponding traffic light. The adjustment coefficient is equal to the ratio of the corresponding data of the corresponding adjustment object after adjustment and before adjustment.

[0077] When analyzing the predicted value of the road congestion adjustment coefficient corresponding to the corresponding road section in the traffic layout model, the historical road congestion adjustment coefficient of each road section in the traffic layout model and the obtained road congestion assessment value of the corresponding road section are combined to construct a historical congestion adjustment data pair for each traffic direction corresponding to the adjustment object of the corresponding road section, which is recorded as (YPL, TX).

[0078] Each pair of historical congestion adjustment data of the corresponding adjustment object for each traffic direction of the corresponding road section corresponds to a maximum monotonic change time interval, the maximum monotonic change time interval contains one or more adjustment time points corresponding to the road section congestion adjustment coefficients of the corresponding traffic direction, and the road section congestion adjustment coefficients of the corresponding adjustment time points adjacent to the maximum monotonic change time interval and the road section congestion adjustment coefficients corresponding to any adjustment time point in the maximum monotonic change time interval do not show a monotonic change trend; the congestion adjustment coefficients of the various road sections involved in the maximum monotonic change time interval show a monotonic change trend, and the maximum monotonic change interval indicates that the congestion adjustment coefficients of the various road sections corresponding to the corresponding time interval are all greater than or equal to 1 or are all less than 1;

[0079] Wherein, TX represents the product of the congestion adjustment coefficients of each road section involved in the corresponding maximum monotonic change time interval of the corresponding historical congestion adjustment data; YPL represents the maximum value of the congestion assessment values ​​of each road section of the corresponding road section in the corresponding maximum monotonic change time interval of the corresponding historical congestion adjustment data;

[0080] According to the Sigmoid function model, function fitting is performed on each pair of historical congestion adjustment data of the adjustment object corresponding to each traffic direction of the corresponding road section, and the obtained function is recorded as the congestion adjustment fitting function of the corresponding traffic direction of the corresponding road section; the function value after substituting the section congestion assessment value of the corresponding road section in the traffic layout model into the congestion adjustment fitting function of the corresponding traffic direction of the corresponding road section is recorded as the predicted value of the section congestion adjustment coefficient corresponding to the corresponding traffic direction of the corresponding road section in the traffic layout model.

[0081] When the adjustment coordination coefficient set of each element in the obtained associated coordinated interference section set is based on the corresponding section, the associated coordinated interference section set corresponding to the section is obtained, and the adjustment coordination coefficient set of the ath element in the associated coordinated interference section set corresponding to the section based on the corresponding section is recorded as GXa, and the nth element in GXa is recorded as GXa {n} ,

[0082] G JZ {n} =Q n {(TXX a -1) TDX a ·YPX a MXa / M+YPX},

[0083] Among them, TXX aIt represents the predicted value of the congestion adjustment coefficient corresponding to the ath element in the associated cooperative interference road section set corresponding to the road section when the traffic direction is the corresponding road section; TDX a Indicates the corresponding adjustment object when the ath element in the associated cooperative interference section set corresponding to the section is directed to the corresponding section; YPX a represents the road section congestion assessment value corresponding to the ath element in the associated coordinated interference road section set corresponding to the road section; MXa represents the road section area corresponding to the ath element in the associated coordinated interference road section set corresponding to the corresponding road section; M represents the road section area of ​​the corresponding road section;

[0084] YPX represents the road congestion assessment value corresponding to the corresponding road section; Q n {} represents the congestion adjustment fitting function corresponding to the nth traffic direction of the corresponding road section.

[0085] S5. Obtain a congestion coordination adjustment coefficient set for each road section in the traffic layout model according to the predicted value of the road section congestion adjustment coefficient corresponding to each road section in the traffic layout model and the respective corresponding adjustment coordination coefficients when the corresponding road section belongs to the associated coordinated interference road section set of other road sections, and adjust the traffic lights in the corresponding road section based on the congestion coordination adjustment coefficient set of each road section;

[0086] When obtaining the congestion coordination adjustment coefficient set for each road section in the traffic layout model, the congestion coordination adjustment coefficient of the i-th road section in the traffic layout model is recorded as CSi, and the b-th element in CSi is recorded as CSi {b} ,

[0087] ,

[0088] Among them, TX （i，b） TXX represents the predicted value of the road congestion adjustment coefficient corresponding to the b-th traffic direction of the i-th road section in the traffic layout model; （i，b，a） represents the value of the bth element in the adjustment coordination coefficient set of the ath element in the associated coordinated interference section set of the i-th section in the traffic layout model based on the corresponding section; ai represents the total number of elements in the associated coordinated interference section set of the i-th section in the traffic layout model;

[0089] When adjusting the traffic lights in the corresponding road sections based on the congestion coordination adjustment coefficient set of each road section, each element in the congestion coordination adjustment coefficient set of the corresponding road section is multiplied by the corresponding adjustment object to obtain a new adjustment object.

[0090] S6. Continuously monitor the traffic condition information of the corresponding road section within the preset time period after the traffic lights in the traffic layout model are adjusted, feed back to the administrator of the corresponding traffic control area, and jump to step S3 with the obtained monitoring results.

[0091] The method in this embodiment is an iterative process. After the traffic lights are adjusted, it is still necessary to continuously monitor the corresponding traffic control area and continuously adjust the traffic lights according to the monitoring results.

[0092] 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.

[0093] Finally, it should be noted that the above description 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. The intelligent traffic management method based on artificial intelligence is characterized by: The method comprises the following steps: S1. Divide the area to be tested into different traffic control areas, obtain the traffic light equipment information and corresponding path distribution information in each traffic control area, and build a traffic layout model corresponding to each traffic control area; S2. According to the connection relationship between each road section in the traffic layout model, a set of associated cooperative interference road sections corresponding to each road section in the traffic layout model is constructed; S3, using artificial intelligence technology and image recognition technology to obtain real-time traffic information on each road section in the traffic layout model, and analyzing the road congestion assessment value corresponding to each road section in the traffic layout model; S4, combining the historical section congestion adjustment coefficient of each section in the traffic layout model and the obtained section congestion assessment value of the corresponding section, analyzing the predicted value of the section congestion adjustment coefficient corresponding to the corresponding section in the traffic layout model; combining the associated coordinated interference section set corresponding to the section, adjusting the coordinated coefficient set of each element in the obtained associated coordinated interference section set based on the corresponding section respectively; S5. Obtain a congestion coordination adjustment coefficient set for each road section in the traffic layout model according to the predicted value of the road section congestion adjustment coefficient corresponding to each road section in the traffic layout model and the respective corresponding adjustment coordination coefficients when the corresponding road section belongs to the associated coordinated interference road section set of other road sections, and adjust the traffic lights in the corresponding road section based on the congestion coordination adjustment coefficient set of each road section; S6. Continuously monitor the traffic condition information of the corresponding road section within the preset time period after the traffic lights in the traffic layout model are adjusted, feed back to the administrator of the corresponding traffic control area, and jump to step S3 with the obtained monitoring results.

2. The intelligent traffic management method based on artificial intelligence according to claim 1 is characterized in that: The traffic light equipment information includes the location coordinates of the traffic light and the time display scheme of the traffic light. The time display scheme of the traffic light is the duration of a lighting cycle of the corresponding traffic light, and the planning content of the green light duration and the red light duration corresponding to each traffic direction in a lighting cycle; a traffic direction corresponding to each lane in the road section; The path distribution information is a set of path information corresponding to all paths in the corresponding traffic control area; the path information includes the distribution area of ​​each path and the lane layout of the corresponding path; In the traffic layout model corresponding to each traffic control area constructed, a proportional scaling model of the path distribution area of ​​the corresponding traffic control area is constructed according to the path distribution area in the obtained path distribution information, which is recorded as the first path distribution scaling model; in combination with the lane layouts at different positions in each path in the path distribution information, the lanes of each path are marked in the first path distribution scaling model, and the time display scheme of the traffic light is bound to the time display scheme of the corresponding traffic light in the first path distribution scaling model, so as to obtain the traffic layout model corresponding to the corresponding traffic control area; In the process of constructing the associated collaborative interference section set corresponding to each road section in the traffic layout model, the road section between two adjacent traffic light intersections is recorded as a road section, and the associated collaborative interference section set corresponding to each road section in the traffic layout model is a set consisting of all road sections connected to the corresponding road section in the corresponding traffic layout model.

3. The intelligent traffic management method based on artificial intelligence according to claim 1 is characterized in that: When acquiring the traffic condition information, the vehicle in the captured image of the camera is identified and located by artificial intelligence technology and image recognition technology, and the traffic condition information includes the density of passing vehicles in the corresponding road section, the quotient of the number of passing vehicles in each lane at the traffic light intersection of the corresponding road section within the most recent preset unit time divided by the preset unit time, and the density of passing vehicles in a preset area belonging to the corresponding road section at the traffic light intersection; The vehicle density refers to the ratio of the number of vehicles passing through the corresponding road section to the area of ​​the corresponding road section; When analyzing the road congestion assessment value corresponding to each road section in the traffic layout model, the following formula is used: YP g =VD g +μ·RVD g +μ1·LVD g , Among them, YP g VD represents the road congestion assessment value corresponding to the g-th road section in the traffic layout model; g RVD represents the vehicle density of the g-th road segment in the traffic layout model in the most recently acquired traffic information. g LVD represents the density of vehicles passing through the preset area at the traffic light intersection in the g-th road section in the traffic layout model in the most recently acquired traffic condition information; g Indicates the maximum value of the quotient of the number of vehicles passing through each lane at the traffic light intersection of the corresponding road section in the latest preset unit time divided by the preset unit time in the most recently acquired traffic condition information of the g-th road section in the traffic layout model; μ and μ1 are both evaluation conversion coefficients, and μ and μ1 are both constants preset in the database.

4. The intelligent traffic management method based on artificial intelligence according to claim 2 is characterized in that: The historical road section congestion adjustment coefficient represents the adjustment coefficient of the duration of each color light in the corresponding traffic light of the corresponding road section in the historical data. The adjustment object of the adjustment coefficient is the ratio of the duration of the green light corresponding to the traffic direction of each lane to the duration of the light cycle in the corresponding traffic light. The adjustment coefficient is equal to the ratio of the corresponding data of the corresponding adjustment object after adjustment to that before adjustment; When analyzing the predicted value of the road congestion adjustment coefficient corresponding to the corresponding road section in the traffic layout model, the historical road congestion adjustment coefficient of each road section in the traffic layout model and the obtained road congestion assessment value of the corresponding road section are combined to construct a historical congestion adjustment data pair for each traffic direction corresponding to the adjustment object of the corresponding road section, which is recorded as (YPL, TX). Each pair of historical congestion adjustment data of the corresponding adjustment object for each traffic direction of the corresponding road section corresponds to a maximum monotonic change time interval, the maximum monotonic change time interval contains one or more adjustment time points corresponding to the road section congestion adjustment coefficients of the corresponding traffic direction, and the road section congestion adjustment coefficients of the corresponding adjustment time points adjacent to the maximum monotonic change time interval and the road section congestion adjustment coefficients corresponding to any adjustment time point in the maximum monotonic change time interval do not show a monotonic change trend; the congestion adjustment coefficients of the various road sections involved in the maximum monotonic change time interval show a monotonic change trend, and the maximum monotonic change interval indicates that the congestion adjustment coefficients of the various road sections corresponding to the corresponding time interval are all greater than or equal to 1 or are all less than 1; Wherein, TX represents the product of the congestion adjustment coefficients of each road section involved in the corresponding maximum monotonic change time interval of the corresponding historical congestion adjustment data; YPL represents the maximum value of the congestion assessment value of each road section in the maximum monotonic change time interval corresponding to the corresponding historical congestion adjustment data; According to the Sigmoid function model, function fitting is performed on each pair of historical congestion adjustment data of the adjustment object corresponding to each traffic direction of the corresponding road section, and the obtained function is recorded as the congestion adjustment fitting function of the corresponding traffic direction of the corresponding road section; the function value after substituting the section congestion assessment value of the corresponding road section in the traffic layout model into the congestion adjustment fitting function of the corresponding traffic direction of the corresponding road section is recorded as the predicted value of the section congestion adjustment coefficient corresponding to the corresponding traffic direction of the corresponding road section in the traffic layout model.

5. The intelligent traffic management method based on artificial intelligence according to claim 4 is characterized in that: When the adjustment coordination coefficient set of each element in the obtained associated coordinated interference section set is based on the corresponding section, the associated coordinated interference section set corresponding to the section is obtained, and the adjustment coordination coefficient set of the ath element in the associated coordinated interference section set corresponding to the section based on the corresponding section is recorded as GXa, and the nth element in GXa is recorded as GXa {n} , GXa {n} =Q n {(TXX a −1.·TDX a ·YPX a ·MXa / M+YPX}, Among them, TXX a It represents the predicted value of the congestion adjustment coefficient corresponding to the ath element in the associated cooperative interference road section set corresponding to the road section when the traffic direction is the corresponding road section; TDX a Indicates the corresponding adjustment object when the ath element in the associated cooperative interference section set corresponding to the section is directed to the corresponding section; YPX a represents the road section congestion assessment value corresponding to the ath element in the associated coordinated interference road section set corresponding to the road section; MXa represents the road section area corresponding to the ath element in the associated coordinated interference road section set corresponding to the corresponding road section; M represents the road section area of ​​the corresponding road section; YPX represents the road congestion assessment value corresponding to the corresponding road section; Q n {} represents the congestion adjustment fitting function corresponding to the nth traffic direction of the corresponding road section.

6. The intelligent traffic management method based on artificial intelligence according to claim 4 is characterized in that: When obtaining the congestion coordination adjustment coefficient set for each road section in the traffic layout model, the congestion coordination adjustment coefficient of the i-th road section in the traffic layout model is recorded as CSi, and the b-th element in CSi is recorded as CSi {b} , ， Among them, TX （i，b） TXX represents the predicted value of the road congestion adjustment coefficient corresponding to the b-th traffic direction of the i-th road section in the traffic layout model; （i，b，a） represents the value of the bth element in the adjustment coordination coefficient set of the ath element in the associated coordinated interference section set of the i-th section in the traffic layout model based on the corresponding section; ai represents the total number of elements in the associated coordinated interference section set of the i-th section in the traffic layout model; When adjusting the traffic lights in the corresponding road sections based on the congestion coordination adjustment coefficient set of each road section, each element in the congestion coordination adjustment coefficient set of the corresponding road section is multiplied by the corresponding adjustment object to obtain a new adjustment object.

7. The intelligent traffic management system based on artificial intelligence is characterized by: The system includes the following modules: A traffic layout model building module, wherein the traffic layout model building module divides the area to be tested into different traffic control areas, obtains the traffic light equipment information and the corresponding path distribution information in each traffic control area, and builds a traffic layout model corresponding to each traffic control area; A road section relationship analysis module, wherein the road section relationship analysis module constructs an associated collaborative interference road section set corresponding to each road section in the traffic layout model according to the connection relationship between each road section in the traffic layout model; A road congestion assessment module, which uses artificial intelligence technology and image recognition technology to obtain real-time traffic information on each road section in the traffic layout model, and analyzes the road congestion assessment value corresponding to each road section in the traffic layout model; A road section collaborative adjustment analysis module, wherein the road section collaborative adjustment analysis module combines the historical road section congestion adjustment coefficient of each road section in the traffic layout model and the obtained road section congestion assessment value of the corresponding road section to analyze the predicted value of the road section congestion adjustment coefficient corresponding to the corresponding road section in the traffic layout model; Combined with the associated coordinated interference road section set corresponding to the road section, adjusting the coordinated coefficient set of each element in the obtained associated coordinated interference road section set based on the corresponding road section; A traffic regulation intelligent management module, wherein the traffic regulation intelligent management module obtains a congestion coordination adjustment coefficient set for each road section in the traffic layout model according to the predicted value of the road section congestion adjustment coefficient corresponding to each road section in the traffic layout model and the respective corresponding adjustment coordination coefficients when the corresponding road section belongs to the associated coordinated interference road section set of other road sections, and adjusts the traffic lights in the corresponding road section based on the congestion coordination adjustment coefficient set of each road section; The traffic regulation follow-up tracking module continuously monitors the traffic condition information of the corresponding road section within a preset time period after the traffic lights in the traffic layout model are adjusted, and feeds back to the administrator of the corresponding traffic control area.

8. The intelligent traffic management system based on artificial intelligence according to claim 7 is characterized by: The road section coordinated regulation analysis module includes a congestion regulation coefficient prediction unit and a regulation coordinated coefficient set acquisition unit. The congestion adjustment coefficient prediction unit analyzes the predicted value of the section congestion adjustment coefficient corresponding to the corresponding section in the traffic layout model in combination with the historical section congestion adjustment coefficient of each section in the traffic layout model and the obtained section congestion evaluation value of the corresponding section; The adjustment coordination coefficient set acquisition unit combines the associated coordinated interference road section set corresponding to the road section, and obtains the adjustment coordination coefficient set of each element in the associated coordinated interference road section set based on the corresponding road section.

Images