AI-based global traffic adaptive regulation and control method and system

Abstract

The invention relates to the technical field of traffic regulation and control, and discloses an AI-based global traffic adaptive regulation and control method and system, and the method comprises the steps: determining the type of information needing to be collected for a target intersection based on a current date and a current time period, and collecting the multi-dimensional information of the target intersection based on the information type; and according to the multi-dimensional information of the target intersection and a traffic control AI model which is trained to converge in advance, generating a target traffic light control parameter for the target intersection, and executing a corresponding traffic light control operation based on the target traffic light control parameter corresponding to the target intersection. And the traffic flow congestion condition and the pedestrian flow congestion condition of the target intersection are slowed down through the adjusted traffic light. Therefore, the accuracy and the reliability of the traffic light control parameters can be improved, the traffic regulation and control accuracy, the reliability, the efficiency and the convenience of the intersection are further improved, and the vehicle driving smoothness and the road safety of the intersection and related roads are improved.

Description

Technical Field

[0001] This invention relates to the field of traffic control technology, and in particular to an AI-based adaptive traffic control method and system for the entire domain. Background Technology

[0002] With the acceleration of urbanization and the continuous growth of motor vehicle ownership, urban road traffic pressure is increasing day by day, and traffic congestion has become one of the key issues restricting urban development. Therefore, traffic lights play a vital role in road traffic control.

[0003] Currently, most traffic control methods involve setting a fixed operating mode for traffic lights before implementation. The traffic lights then perform monotonous traffic control based on this mode, meaning they cycle through red and green lights according to a pre-set program. However, traffic flow at the same intersection varies at different times and various unexpected traffic events may occur. A single traffic light operating mode cannot adapt to the complex and ever-changing traffic scenarios. Therefore, existing traffic control methods suffer from low accuracy and efficiency. Clearly, providing a method that improves the accuracy and efficiency of traffic control is of paramount importance. Summary of the Invention

[0004] This invention provides an AI-based adaptive traffic control method and system that can improve the accuracy and efficiency of road traffic control, thereby improving vehicle flow and road safety.

[0005] To address the aforementioned technical problems, the first aspect of this invention discloses an AI-based adaptive traffic control method for the entire traffic domain, the method comprising: For any identified target intersection, based on the current date and current time period, determine the type of information to be collected for that target intersection, and collect multi-dimensional information about that target intersection based on the information type; Based on the multi-dimensional information of the target intersection and the pre-trained converged traffic control AI model, target traffic light control parameters for the target intersection are generated, and corresponding traffic light control operations are performed based on the target traffic light control parameters of the target intersection, so as to alleviate traffic congestion and pedestrian congestion at the target intersection through the adjusted traffic lights. The multi-dimensional information includes the inherent multi-dimensional information of the target intersection and the current variable multi-dimensional information of the target intersection; the inherent multi-dimensional information includes the intersection type information, the number of traffic lights, and the traffic direction information of the target intersection; the current variable multi-dimensional information includes the current traffic conditions and the current traffic light operating parameters of the target intersection.

[0006] As an optional implementation, in the first aspect of the invention, after generating the target traffic light control parameters for the target intersection, the method further includes: Identify associated locations that have a locational connection with the target intersection and affect vehicle traffic. The associated locations include one or more of the following: the preceding intersection, the following intersection, and the following destination. Determine the current traffic conditions at the associated location and, based on the target traffic light control parameters, determine the predicted vehicle traffic conditions at the target intersection; Based on the current traffic conditions and the predicted vehicle traffic conditions, determine whether the associated location meets the preset traffic light association control trigger conditions; When it is determined that the associated location meets the triggering condition for traffic light association control, the traffic lights corresponding to the associated location are subjected to corresponding linkage control operations based on the current traffic conditions and the predicted vehicle traffic conditions.

[0007] As an optional implementation, in the first aspect of the present invention, determining whether the associated location meets the preset traffic light association control triggering conditions based on the current traffic conditions and the predicted vehicle traffic conditions includes: Based on the current traffic conditions, analyze the current vehicle capacity of the associated locations, and determine the current congestion severity of the associated locations based on the current traffic conditions. Based on the predicted vehicle traffic conditions, the current vehicle capacity, and the current congestion severity, determine whether the associated location meets the preset vehicle capacity conditions for the current traffic light traffic scenario; When it is determined that the associated location does not meet the vehicle capacity conditions of the current traffic light traffic scenario, the associated location is determined to meet the preset traffic light association control trigger conditions. When it is determined that the associated location meets the vehicle capacity conditions of the current traffic light passage scenario, the vehicle capacity of the vacant area corresponding to the associated location is determined based on the first waiting time of the associated location and the current traffic situation; based on the vehicle capacity of the vacant area, it is determined whether the associated location meets the vehicle replacement capacity conditions of the preset next traffic light passage scenario. When it is determined that the associated location meets the vehicle replacement and accommodation conditions for the next traffic light passage scenario, it is determined that the associated location does not meet the preset traffic light association control trigger conditions. When it is determined that the associated location does not meet the vehicle replacement and capacity conditions for the next traffic light passage scenario, the associated location is determined to meet the preset traffic light association control trigger conditions.

[0008] As an optional implementation, in the first aspect of the present invention, the step of performing corresponding linkage control operations on the traffic lights corresponding to the associated location based on the current traffic conditions and the predicted vehicle traffic conditions includes: Based on the predicted vehicle traffic conditions, determine the first level of smooth traffic and the first level of congestion in the area corresponding to the target intersection, and based on the current traffic conditions, determine the second level of smooth traffic and the second level of congestion in the area corresponding to the associated location. When the associated location precedes the target intersection, if the first traffic flow level is greater than or equal to a preset traffic flow level threshold and the second congestion level is greater than or equal to a preset congestion level threshold, the traffic light corresponding to the associated location will have its corresponding traffic indication time extended; if the first congestion level is greater than or equal to a preset congestion level threshold and the second traffic flow level is greater than or equal to a preset traffic flow level threshold, the traffic light corresponding to the associated location will have its corresponding stop indication time extended. When the associated location is after the target intersection, and when both the first congestion level and the second congestion level are greater than or equal to a preset congestion level threshold, the traffic light corresponding to the associated location will be extended accordingly.

[0009] As an optional implementation, in the first aspect of the present invention, generating target traffic light control parameters for the target intersection based on multi-dimensional information of the target intersection and a pre-trained, converged traffic control AI model includes: Identify the target area related to the target intersection and subject to traffic control, and perform corresponding sub-region division operations on the target area based on the multi-dimensional information of the target intersection, the special location information of the target area, and the special lane function information, to obtain one or more sub-regions; Based on the special location information and special lane function information of each sub-region, a first traffic control priority for each sub-region is determined, and based on the current date, the current time period, and the current traffic conditions of each sub-region, a second traffic control priority for each sub-region is determined. Based on the current traffic light operating parameters of the target intersection, determine the actual traffic control sequence corresponding to all the sub-areas; Based on the first traffic control priority, the second traffic control priority, and the actual traffic control sequence, determine whether all the sub-areas meet the preset additional control conditions; When it is determined that all the sub-regions do not meet the additional control conditions, the current traffic light operating parameters are determined as the target traffic light control parameters for the target intersection. When it is determined that all the sub-regions meet the additional control conditions, the corresponding parameter adjustment operation is performed on the current traffic light operating parameters according to the first traffic control priority and the second traffic control priority, so as to obtain the target traffic light control parameters for the target intersection, so as to realize the traffic linkage control among multiple sub-regions.

[0010] As an optional implementation, in a first aspect of the present invention, determining whether all the sub-regions meet preset additional control conditions based on the first traffic control priority, the second traffic control priority, and the actual traffic control sequence includes: Based on the first traffic control priority and the second traffic control priority, determine the expected traffic control sequence for all the sub-regions; Determine whether the actual traffic control sequence and the expected traffic control sequence meet the preset hard sequence matching conditions; When it is determined that the actual traffic control sequence and the expected traffic control sequence meet the hard sequence matching condition, it is determined that all the sub-regions do not meet the preset additional control conditions. When it is determined that the actual traffic control sequence and the expected traffic control sequence do not meet the hard sequence matching condition, it is determined whether the actual traffic control sequence and the expected traffic control sequence meet the preset final control effect matching condition. When it is determined that the actual traffic control sequence and the expected traffic control sequence meet the final control effect matching condition, it is determined that all the sub-regions do not meet the preset additional control conditions. When it is determined that the actual traffic control sequence and the expected traffic control sequence do not meet the final control effect matching condition, all the sub-regions are determined to meet the preset additional control conditions.

[0011] As an optional implementation, in the first aspect of the present invention, the method further includes: Determine traffic control records for multiple intersections within a target time period, and based on the traffic control records, perform corresponding update operations on the training samples of the traffic control AI model. Based on the updated training samples, the traffic control AI model is subjected to corresponding update and iteration operations.

[0012] As an optional implementation, in the first aspect of the present invention, the step of performing a corresponding update operation on the training samples of the traffic control AI model based on the traffic control records includes: Determine the trained control scheme of the traffic control AI model, and based on the trained control scheme, determine whether there are conflicting control contents in the traffic control record; When it is determined that the traffic control record does not contain the conflict control content, the traffic control record is directly added to the training sample of the traffic control AI model to obtain the updated training sample. When it is determined that the traffic control record contains conflicting control content, it is determined whether the conflicting control content meets the preset effective optimization conditions. When it is determined that the conflict control content meets the effective optimization conditions, the corresponding replacement update operation is performed on the training sample of the traffic control AI model based on the conflict control content, and the content in the traffic control record other than the conflict control content is directly added to the training sample of the traffic control AI model to obtain the updated training sample.

[0013] A second aspect of this invention discloses an AI-based adaptive traffic control system for the entire domain, the system comprising: The information collection module is used to determine the type of information to be collected for any given target intersection based on the current date and time period, and to collect multi-dimensional information about the target intersection based on the information type. The control parameter determination module is used to generate target traffic light control parameters for the target intersection based on the multi-dimensional information of the target intersection and the traffic control AI model that has been pre-trained to convergence. The traffic light control module is used to perform corresponding traffic light control operations based on the target traffic light control parameters corresponding to the target intersection, so as to alleviate the traffic congestion and pedestrian congestion at the target intersection through the adjusted traffic lights. The multi-dimensional information includes the inherent multi-dimensional information of the target intersection and the current variable multi-dimensional information of the target intersection; the inherent multi-dimensional information includes the intersection type information, the number of traffic lights, and the traffic direction information of the target intersection; the current variable multi-dimensional information includes the current traffic conditions and the current traffic light operating parameters of the target intersection.

[0014] As an optional implementation, in a second aspect of the invention, the system further includes: The linkage control module is used to, after the control parameter determination module generates target traffic light control parameters for the target intersection, determine associated locations that have a positional connection and influence on vehicle traffic at the target intersection. These associated locations include one or more of the preceding intersection, following intersection, and subsequent destination corresponding to the target intersection. The module then determines the current traffic situation at each associated location and, based on the target traffic light control parameters, determines the predicted vehicle traffic situation at the target intersection. Based on the current traffic situation and the predicted vehicle traffic situation, the module determines whether the associated location meets a preset traffic light linkage control trigger condition. When the associated location meets the traffic light linkage control trigger condition, the module performs corresponding linkage control operations on the traffic light corresponding to the associated location based on the current traffic situation and the predicted vehicle traffic situation.

[0015] As an optional implementation, in a second aspect of the present invention, the method by which the linkage control module determines whether the associated location meets the preset traffic light linkage control triggering conditions based on the current traffic conditions and the predicted vehicle traffic conditions specifically includes: Based on the current traffic conditions, analyze the current vehicle capacity of the associated locations, and determine the current congestion severity of the associated locations based on the current traffic conditions. Based on the predicted vehicle traffic conditions, the current vehicle capacity, and the current congestion severity, determine whether the associated location meets the preset vehicle capacity conditions for the current traffic light traffic scenario; When it is determined that the associated location does not meet the vehicle capacity conditions of the current traffic light traffic scenario, the associated location is determined to meet the preset traffic light association control trigger conditions. When it is determined that the associated location meets the vehicle capacity conditions of the current traffic light passage scenario, the vehicle capacity of the vacant area corresponding to the associated location is determined based on the first waiting time of the associated location and the current traffic situation; based on the vehicle capacity of the vacant area, it is determined whether the associated location meets the vehicle replacement capacity conditions of the preset next traffic light passage scenario. When it is determined that the associated location meets the vehicle replacement and accommodation conditions for the next traffic light passage scenario, it is determined that the associated location does not meet the preset traffic light association control trigger conditions. When it is determined that the associated location does not meet the vehicle replacement and capacity conditions for the next traffic light passage scenario, the associated location is determined to meet the preset traffic light association control trigger conditions.

[0016] As an optional implementation, in the second aspect of the present invention, the linkage control module performs corresponding linkage control operations on the traffic lights corresponding to the associated location based on the current traffic conditions and the predicted vehicle traffic conditions, specifically including: Based on the predicted vehicle traffic conditions, determine the first level of smooth traffic and the first level of congestion in the area corresponding to the target intersection, and based on the current traffic conditions, determine the second level of smooth traffic and the second level of congestion in the area corresponding to the associated location. When the associated location precedes the target intersection, if the first traffic flow level is greater than or equal to a preset traffic flow level threshold and the second congestion level is greater than or equal to a preset congestion level threshold, the traffic light corresponding to the associated location will have its corresponding traffic indication time extended; if the first congestion level is greater than or equal to a preset congestion level threshold and the second traffic flow level is greater than or equal to a preset traffic flow level threshold, the traffic light corresponding to the associated location will have its corresponding stop indication time extended. When the associated location is after the target intersection, and when both the first congestion level and the second congestion level are greater than or equal to a preset congestion level threshold, the traffic light corresponding to the associated location will be extended accordingly.

[0017] As an optional implementation, in the second aspect of the present invention, the method by which the control parameter determination module generates target traffic light control parameters for the target intersection based on the multi-dimensional information of the target intersection and a pre-trained, converged traffic control AI model specifically includes: Identify the target area related to the target intersection and subject to traffic control, and perform corresponding sub-region division operations on the target area based on the multi-dimensional information of the target intersection, the special location information of the target area, and the special lane function information, to obtain one or more sub-regions; Based on the special location information and special lane function information of each sub-region, a first traffic control priority for each sub-region is determined, and based on the current date, the current time period, and the current traffic conditions of each sub-region, a second traffic control priority for each sub-region is determined. Based on the current traffic light operating parameters of the target intersection, determine the actual traffic control sequence corresponding to all the sub-areas; Based on the first traffic control priority, the second traffic control priority, and the actual traffic control sequence, determine whether all the sub-areas meet the preset additional control conditions; When it is determined that all the sub-regions do not meet the additional control conditions, the current traffic light operating parameters are determined as the target traffic light control parameters for the target intersection. When it is determined that all the sub-regions meet the additional control conditions, the corresponding parameter adjustment operation is performed on the current traffic light operating parameters according to the first traffic control priority and the second traffic control priority, so as to obtain the target traffic light control parameters for the target intersection, so as to realize the traffic linkage control among multiple sub-regions.

[0018] As an optional implementation, in a second aspect of the present invention, the method by which the control parameter determination module determines whether all the sub-regions meet the preset additional control conditions based on the first traffic control priority, the second traffic control priority, and the actual traffic control sequence specifically includes: Based on the first traffic control priority and the second traffic control priority, determine the expected traffic control sequence for all the sub-regions; Determine whether the actual traffic control sequence and the expected traffic control sequence meet the preset hard sequence matching conditions; When it is determined that the actual traffic control sequence and the expected traffic control sequence meet the hard sequence matching condition, it is determined that all the sub-regions do not meet the preset additional control conditions. When it is determined that the actual traffic control sequence and the expected traffic control sequence do not meet the hard sequence matching condition, it is determined whether the actual traffic control sequence and the expected traffic control sequence meet the preset final control effect matching condition. When it is determined that the actual traffic control sequence and the expected traffic control sequence meet the final control effect matching condition, it is determined that all the sub-regions do not meet the preset additional control conditions. When it is determined that the actual traffic control sequence and the expected traffic control sequence do not meet the final control effect matching condition, all the sub-regions are determined to meet the preset additional control conditions.

[0019] As an optional implementation, in a second aspect of the invention, the system further includes: The model update and iteration module is used to determine the traffic control records for multiple intersections within a target time period, and to perform corresponding update operations on the training samples of the traffic control AI model based on the traffic control records. Based on the updated training samples, the traffic control AI model is subjected to corresponding update and iteration operations.

[0020] As an optional implementation, in the second aspect of the present invention, the method by which the model update iteration module performs corresponding update operations on the training samples of the traffic control AI model based on the traffic control records specifically includes: Determine the trained control scheme of the traffic control AI model, and based on the trained control scheme, determine whether there are conflicting control contents in the traffic control record; When it is determined that the traffic control record does not contain the conflict control content, the traffic control record is directly added to the training sample of the traffic control AI model to obtain the updated training sample. When it is determined that the traffic control record contains conflicting control content, it is determined whether the conflicting control content meets the preset effective optimization conditions. When it is determined that the conflict control content meets the effective optimization conditions, the corresponding replacement update operation is performed on the training sample of the traffic control AI model based on the conflict control content, and the content in the traffic control record other than the conflict control content is directly added to the training sample of the traffic control AI model to obtain the updated training sample.

[0021] A third aspect of this invention discloses another AI-based adaptive traffic control system for the entire domain, the system comprising: Memory containing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the AI-based adaptive traffic control method disclosed in the first aspect of the present invention.

[0022] The fourth aspect of the present invention discloses a computer storage medium storing computer instructions, which, when invoked, are used to execute the AI-based adaptive traffic control method for the entire domain disclosed in the first aspect of the present invention.

[0023] Compared with the prior art, the embodiments of the present invention have the following beneficial effects: In this embodiment of the invention, for any identified target intersection, based on the current date and current time period, the type of information to be collected for the target intersection is determined, and multi-dimensional information of the target intersection is collected based on this information type. Based on the multi-dimensional information of the target intersection and a pre-trained, converged traffic control AI model, target traffic light control parameters for the target intersection are generated. Corresponding traffic light control operations are then executed based on these parameters to alleviate traffic and pedestrian congestion at the target intersection through adjusted traffic lights. The multi-dimensional information includes the inherent multi-dimensional information of the target intersection and the current variable multi-dimensional information of the target intersection. The inherent multi-dimensional information includes the intersection type, number of traffic lights, and traffic direction information of the target intersection. The current variable multi-dimensional information includes the current traffic conditions and current traffic light operating parameters of the target intersection. It is evident that this invention can realize the traffic control function of the target intersection based on multi-dimensional information and traffic control AI model, thereby alleviating traffic congestion and pedestrian congestion at the target intersection. This is beneficial to improving the comprehensiveness and rationality of the whole-area traffic adaptive control method, which in turn improves the accuracy and reliability of the determined traffic light control parameters, thereby improving the accuracy and reliability of traffic control at the intersection, improving the efficiency and convenience of traffic control at the intersection, and further improving the smoothness of vehicle traffic and road safety at the intersection and related roads. Attached Figure Description

[0024] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0025] Figure 1 This is a flowchart illustrating an AI-based adaptive traffic control method for the entire domain, as disclosed in an embodiment of the present invention. Figure 2 This is a flowchart illustrating another AI-based adaptive traffic control method for the entire domain, as disclosed in an embodiment of the present invention. Figure 3 This is a schematic diagram of the structure of an AI-based adaptive traffic control system disclosed in an embodiment of the present invention; Figure 4 This is a schematic diagram of another AI-based adaptive traffic control system disclosed in an embodiment of the present invention; Figure 5This is a schematic diagram of another AI-based adaptive traffic control system disclosed in an embodiment of the present invention. Detailed Implementation

[0026] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0027] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, apparatus, product, or end that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or ends.

[0028] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0029] This invention discloses an AI-based adaptive traffic control method and system for the entire traffic area. Based on multi-dimensional information and a traffic control AI model, it can achieve traffic control functions at target intersections, alleviating traffic and pedestrian congestion. This improves the comprehensiveness and rationality of the adaptive traffic control method, thereby enhancing the accuracy and reliability of the determined traffic light control parameters. Ultimately, this improves the accuracy and reliability of traffic control at intersections, increasing efficiency and convenience, and further enhancing the smooth flow of traffic and road safety at intersections and related roads. Detailed explanations follow.

[0030] Example 1 Please see Figure 1 , Figure 1 This is a flowchart illustrating an AI-based adaptive traffic control method for the entire domain, as disclosed in an embodiment of the present invention. Wherein, Figure 1The described method can be applied to an AI-based global traffic adaptive control system, which may include a server, including a local server or a cloud server; this embodiment of the invention is not limited to this. Figure 1 As shown, this AI-based global traffic adaptive control method includes the following operations: 101. For any given target intersection, based on the current date and time period, determine the type of information to be collected for that target intersection, and collect multi-dimensional information about that target intersection based on the information type.

[0031] Optionally, the multi-dimensional information includes the inherent multi-dimensional information of the target intersection and the current variable multi-dimensional information of the target intersection. Further, the inherent multi-dimensional information includes the intersection type information, traffic light quantity information, and traffic direction information of the target intersection. Further, the current variable multi-dimensional information includes the current traffic conditions and current traffic light operating parameters of the target intersection. This embodiment of the invention does not impose any limitations.

[0032] Optional, intersection type information, for example: three-way intersection, four-way intersection, etc., are not limited in this embodiment of the invention.

[0033] Optionally, the current traffic conditions may include, but are not limited to, congestion, vehicle flow, and pedestrian flow, and are not limited in this embodiment of the invention.

[0034] 102. Based on the multi-dimensional information of the target intersection and the pre-trained converged traffic control AI model, generate target traffic light control parameters for the target intersection, and execute corresponding traffic light control operations based on the target traffic light control parameters of the target intersection, so as to alleviate traffic congestion and pedestrian congestion at the target intersection through the adjusted traffic lights.

[0035] As can be seen, the AI-based adaptive traffic control system described in this embodiment of the invention can realize the traffic control function of the target intersection based on the multi-dimensional information of the target intersection and the traffic control AI model, so as to alleviate the traffic congestion and pedestrian congestion at the target intersection. This is conducive to improving the comprehensiveness and rationality of the adaptive traffic control method, and thus conducive to improving the accuracy and reliability of the determined traffic light control parameters. This, in turn, is conducive to improving the accuracy and reliability of traffic control at the intersection, improving the efficiency and convenience of traffic control at the intersection, and further conducive to improving the smoothness of vehicle traffic and road safety at the intersection and related roads.

[0036] In an optional embodiment, after generating the target traffic light control parameters for the target intersection as described above, the method may further include the following operations: Identify associated locations that have a locational connection with the target intersection and affect vehicle traffic. These associated locations include one or more of the following: the preceding intersection, the following intersection, and the following destination. Determine the current traffic conditions at the associated location and, based on the target traffic light control parameters, determine the predicted vehicle traffic conditions at the target intersection; Based on the current traffic conditions and predicted vehicle traffic, determine whether the associated locations meet the preset traffic light association control trigger conditions; When it is determined that the associated location meets the triggering conditions for traffic light linkage control, the corresponding linkage control operation is performed on the traffic light corresponding to the associated location based on the current traffic conditions and the predicted vehicle traffic conditions.

[0037] Optionally, the destination can be exemplified by: highway entrance, scenic spot entrance, parking lot entrance, expected parking spot, entrance to a specific location, etc., but this embodiment of the invention does not limit the destination.

[0038] Optionally, there is a locational connection with the target intersection. For example, the associated location is within a preset distance range from the target intersection, there are no other intersections in the middle section formed by the associated location and the target intersection, or the associated location and the target intersection share a traffic light, etc. This embodiment of the invention does not impose any limitations.

[0039] Optionally, there may be a traffic impact at the target intersection. For example, congestion at the target intersection may affect the traffic flow at related locations to some extent; congestion at related locations may affect the traffic flow at the target intersection to some extent; or the traffic at the target intersection and related locations may be mostly or completely the same. This embodiment of the invention does not impose any limitations.

[0040] Optionally, the predicted vehicle traffic conditions at the target intersection may include, but are not limited to, one or more of the following under the target traffic light control parameters: traffic flow, number of vehicles, vehicle speed, area occupied by vehicles, specific vehicle types, and specific vehicle characteristics. This embodiment of the invention does not limit these parameters.

[0041] Further optional, when it is determined that the associated location does not meet the triggering conditions for traffic light association control, the above steps of determining the current traffic situation of the associated location and determining the predicted vehicle traffic situation of the target intersection based on the target traffic light control parameters are executed again. This embodiment of the invention does not limit the scope of the steps.

[0042] Optionally, for example: when multiple consecutive straight intersections are detected to be blocked, that is, when the current congestion severity is greater than a threshold, the intersections are controlled to remain open for a period of time to expel some vehicles; or, if the current vehicle load capacity of the current area indicates that it is overloaded, then the vehicles should be continuously discharged; furthermore, seamless driving is considered, for example, vehicles at the following intersections do not need to brake to pass through multiple intersections in front, efficiently dealing with congestion; for example, after half of the vehicles at the preceding intersection have passed, vehicles at the following intersection are allowed to pass, thus forming continuous driving; before a group of vehicles arrives from behind, if there are no vehicles in the current area, other directions are allowed to pass first; if there is a lot of congestion at the following intersection, it is quickly released; if there is not much congestion, it is allowed to wait until half of the vehicles have passed for a seamless transition. This embodiment of the invention is not limited.

[0043] As can be seen, this optional embodiment can provide a traffic light linkage control method corresponding to the associated location of the target intersection. When it is determined that the associated location meets the traffic light control triggering conditions, the linkage control operation is executed according to the current traffic situation and the predicted vehicle traffic situation. This is conducive to improving the comprehensiveness and rationality of the traffic light linkage control method corresponding to the associated location, thereby improving the accuracy and reliability of traffic light linkage control, as well as the timeliness and efficiency of traffic light linkage control. This is conducive to improving the accuracy and efficiency of congestion mitigation in roads involving multiple traffic lights.

[0044] In another optional embodiment, the above-mentioned determination of whether the associated location meets the preset traffic light association control triggering conditions based on the current traffic conditions and predicted vehicle traffic conditions may include: Based on the current traffic conditions, analyze the current vehicle capacity of the associated locations, and determine the current congestion severity of the associated locations based on the current traffic conditions. Based on the predicted vehicle traffic conditions, current vehicle capacity, and current congestion severity, determine whether the associated location meets the preset vehicle capacity conditions for the current traffic light traffic scenario. When it is determined that the associated location does not meet the vehicle capacity conditions of the current traffic light traffic scenario, the associated location is determined to meet the preset traffic light association control trigger conditions. When it is determined that the associated location meets the vehicle capacity conditions of the current traffic light passage scenario, the vehicle capacity of the corresponding empty area is determined based on the first waiting time of the associated location and the current traffic situation; based on the vehicle capacity of the empty area, it is determined whether the associated location meets the vehicle replacement capacity conditions of the preset next traffic light passage scenario. When it is determined that the associated location meets the vehicle replacement and capacity conditions for the next traffic light passage scenario, it is determined that the associated location does not meet the preset traffic light association control trigger conditions. When it is determined that the associated location does not meet the vehicle replacement capacity conditions for the next traffic light passage scenario, the associated location is determined to meet the preset traffic light association control trigger conditions.

[0045] Optionally, the current traffic light passage scenario can be understood as the current green / red light time scenario; the next traffic light passage scenario can be understood as the next green / red light time scenario, and this embodiment of the invention does not limit it.

[0046] Further optionally, the above-mentioned determination of whether the associated location meets the preset vehicle capacity conditions for the current traffic light scenario based on predicted vehicle traffic conditions, current vehicle capacity, and current congestion severity may include: Based on the current vehicle capacity and the current congestion severity, determine the current number of vehicles that the associated location can accommodate, and based on the predicted vehicle traffic conditions, determine the current number of vehicles that need to be accommodated. Determine whether the current number of vehicles that can be accommodated is greater than or equal to the current required number of vehicles. If the judgment result is yes, it is determined that the associated location meets the preset vehicle capacity conditions for the current traffic light traffic scenario; if the judgment result is no, it is determined that the associated location does not meet the preset vehicle capacity conditions for the current traffic light traffic scenario.

[0047] Optionally, the vehicle capacity of the current traffic light scenario can be illustrated by, for example, whether the associated location can accommodate the vehicles that have arrived / are already in the current time scenario. If vehicles in the current time scenario are already surging out (for example, if they are already congested before even reaching the area, or if they are already congested in the middle of the intersection), then emergency associated control is required. That is, if the associated location is ahead, the green light time of the associated location is extended or the red light time of the intersection behind the associated location is extended to reduce the number of vehicles that the associated location needs to accommodate. The same applies to other situations. This embodiment of the invention does not limit the scope of the invention.

[0048] Further optionally, the above-mentioned determination of whether the associated location meets the preset vehicle replacement capacity conditions for the next traffic light scenario based on the availability of additional vehicles in the vacant area may include: Determine the expected number of vehicles passing through the target intersection in the next traffic light scenario, and determine the number of additional vehicles that can be accommodated based on the availability of additional vehicles in the vacant area. Determine whether the number of additional vehicles that can be accommodated is greater than or equal to the expected number of vehicles passing through; If the judgment result is yes, it is determined that the associated location meets the preset vehicle replacement and capacity conditions for the next traffic light passage scenario; if the judgment result is no, it is determined that the associated location does not meet the preset vehicle replacement and capacity conditions for the next traffic light passage scenario.

[0049] Optionally, the vehicle takeover capacity conditions for the next traffic light scenario can be illustrated as follows: Assume the target intersection is the intersection behind the associated location, and the associated location can accommodate all arriving vehicles in the current time scenario. Further, for example, when the intersection behind the associated location turns green again (i.e., the next time scenario), can the associated location, in addition to the currently existing vehicles, accommodate vehicles arriving in the next time scenario? If the red light time at the associated location is long, it needs to accommodate vehicles from more than one traffic light scenario; if the red light time at the associated location is appropriate, it only needs to accommodate vehicles from less than one traffic light scenario. The vehicles in the next time scene; further, if the associated location can fully accommodate the vehicles arriving in the next time scene, or if the traffic light corresponding to the associated location in the next time scene is open (i.e., the front part of the vehicles leaves and the rear part of the vehicles enter to achieve accommodation and replacement), then it is determined that the vehicle replacement and accommodation conditions for the next traffic light scene are met; if the associated location cannot fully accommodate the vehicles arriving in the next time scene, then it is determined that the vehicle replacement and accommodation conditions for the next traffic light scene are not met; in addition, the same logic applies to the situation when the associated location is the intersection behind the target intersection, and the embodiments of the present invention do not limit it.

[0050] Optionally, the vehicle capacity of the vacant area corresponding to the associated location can be added. For example, when the target intersection is the intersection behind the associated location, the vehicle capacity of the vacant area is added for the area involved in the associated location; when the associated location is the intersection behind the target intersection, the vehicle capacity of the vacant area is added for the area involved in the target intersection. This embodiment of the invention does not limit this.

[0051] As can be seen, this optional embodiment can determine the vehicle capacity conditions of the current traffic light traffic scene and the vehicle takeover capacity conditions of the next traffic light traffic scene at the associated location, thereby determining the result of the traffic light association control triggering condition being met. This is beneficial to improving the comprehensiveness, rationality, and progressiveness of the method for determining the result of the traffic light association control triggering condition being met, and thus improving the accuracy and reliability of the determined result of the traffic light association control triggering condition being met. In this way, it is beneficial to improve the timeliness and accuracy of the traffic light association control operation based on the result of the traffic light association control triggering condition being met.

[0052] In another optional embodiment, the above-mentioned linkage control operation on the traffic lights corresponding to the associated locations based on the current traffic conditions and predicted vehicle traffic conditions may include: Based on the predicted vehicle traffic conditions, determine the first level of smooth traffic and the first level of congestion in the area corresponding to the target intersection, and based on the current traffic conditions, determine the second level of smooth traffic and the second level of congestion in the area corresponding to the associated location. When the associated location precedes the target intersection, if the first traffic flow level is greater than or equal to a preset traffic flow level threshold and the second congestion level is greater than or equal to a preset congestion level threshold, the corresponding traffic light at the associated location will have its passage indication time extended; if the first congestion level is greater than or equal to a preset congestion level threshold and the second traffic flow level is greater than or equal to a preset traffic flow level threshold, the corresponding stop indication time at the associated location will be extended. When the associated location is located after the target intersection, if both the first congestion level and the second congestion level are greater than or equal to the preset congestion level threshold, the corresponding traffic light at the associated location will be extended accordingly.

[0053] Optionally, for example, traffic can be controlled at the intersection behind after half of the vehicles have passed through the intersection ahead, thus forming a continuous relay of traffic; or, if there are no vehicles in the current area before a group of vehicles arrives at the intersection behind, vehicles from other directions can be allowed to pass first; or, if the intersection behind is very congested, priority can be given to vehicles at the intersection behind, and if the congestion at the intersection behind is not severe, priority can be given to vehicles at other intersections or the current intersection to pass for a period of time before vehicles at the intersection behind can pass seamlessly. This embodiment of the invention does not limit the scope of the invention.

[0054] Optionally, if the area ahead is congested while the current area is relatively clear, the red light time in the current area can be extended; if the current area is congested while the area ahead is relatively clear, the green light time in the current area can be extended; if the current area, the area ahead, and / or the area behind are all congested, the green light time in the congested area can be extended. This embodiment of the invention does not impose any limitations.

[0055] Optionally, the passage indication time can be understood as the green light time, and the stop indication time can be understood as the red light time. This embodiment of the invention does not limit this.

[0056] As can be seen, this optional embodiment can match the corresponding traffic light indication time control method according to the positional relationship between the associated location and the target intersection, as well as the comparison relationship between the first smoothness and the first congestion level of the area corresponding to the target intersection and the second smoothness and the second congestion level of the area corresponding to the associated location. This is beneficial to improving the comprehensiveness and rationality of the traffic light indication time control method, as well as the diversity, flexibility and pertinence of the traffic light indication time control method, and thus the accuracy and reliability of the associated traffic light indication time control.

[0057] In another optional embodiment, the generation of target traffic light control parameters for the target intersection based on the multi-dimensional information of the target intersection and the pre-trained, converged traffic control AI model may include: Identify the target area related to the target intersection that needs to be traffic controlled, and perform corresponding sub-region division operations on the target area based on the multi-dimensional information of the target intersection, the special location information of the target area, and the special lane function information, to obtain one or more sub-regions; Based on the special location information and special lane function information of each sub-area, the first traffic control priority of each sub-area is determined, and based on the current date, current time period and the current traffic conditions of each sub-area, the second traffic control priority of each sub-area is determined. Based on the current traffic light operating parameters of the target intersection, determine the actual traffic control sequence for all sub-areas; Based on the first traffic control priority, the second traffic control priority, and the actual traffic control sequence, determine whether all sub-areas meet the preset additional control conditions. When it is determined that all sub-regions do not meet the additional control conditions, the current traffic light operating parameters are set as the target traffic light control parameters for that target intersection. When it is determined that all sub-regions meet the additional control conditions, the corresponding parameter adjustment operation is performed on the current traffic light operating parameters according to the first traffic control priority and the second traffic control priority, so as to obtain the target traffic light control parameters for the target intersection and realize traffic linkage control between multiple sub-regions.

[0058] Optionally, special location information for the target area may be provided. For example, if the target area is a tourist attraction, business district, sidewalk, parking lot entrance, or other place with high vehicle / pedestrian traffic, then traffic control should be prioritized. This embodiment of the invention does not impose any limitations on this.

[0059] Optionally, the special lane function information of the target area can be used as an example: if the target area is a lane with special characteristics such as an emergency lane, fire lane, tidal flow lane, or bus lane, then traffic control should be prioritized. This embodiment of the invention does not limit this.

[0060] Optionally, for example, the control priority of special locations / special lanes is higher than that of ordinary roads; for example, the control priority of areas with high traffic congestion is higher than that of areas with low traffic congestion; for example, the control priority of tidal lanes is higher than that of ordinary lanes within a preset time period. This embodiment of the invention does not limit these possibilities.

[0061] Optionally, the actual traffic control sequence corresponding to all sub-regions can be understood as the actual release sequence of all sub-regions, and this embodiment of the invention does not limit this.

[0062] Further optionally, the above-mentioned adjustment of the current traffic light operating parameters according to the first traffic control priority and the second traffic control priority to obtain the target traffic light control parameters for the target intersection may include: Based on the first and second traffic control priorities, determine the expected release order for all sub-areas and the expected release duration for all sub-areas. Based on the expected release sequence and expected release duration, perform corresponding parameter adjustment operations on the current traffic light operating parameters to obtain the target traffic light control parameters for the target intersection.

[0063] As can be seen, this optional embodiment can provide a traffic linkage control method between multiple sub-regions. When all sub-regions meet the additional control conditions, the current traffic light operating parameters are adjusted according to the determined first traffic control priority and second traffic control priority. This is beneficial to improving the comprehensiveness and rationality of the traffic linkage control method between multiple sub-regions, thereby improving the accuracy and reliability of traffic linkage control between multiple sub-regions, and thus helping to optimize the traffic order of multiple sub-regions and alleviate congestion.

[0064] In another optional embodiment, the above-mentioned determination of whether all sub-regions meet the preset additional control conditions based on the first traffic control priority, the second traffic control priority, and the actual traffic control sequence may include: Based on the first and second traffic control priorities, the expected traffic control sequence for each sub-area is determined. Determine whether the actual traffic control sequence and the expected traffic control sequence meet the preset hard sequence matching conditions; When it is determined that the actual traffic control sequence and the expected traffic control sequence meet the hard sequence matching condition, it is determined that all sub-areas do not meet the preset additional control conditions. When it is determined that the actual traffic control sequence and the expected traffic control sequence do not meet the hard sequence matching condition, it is determined whether the actual traffic control sequence and the expected traffic control sequence meet the preset final control effect matching condition. When it is determined that the actual traffic control sequence and the expected traffic control sequence meet the conditions for matching the final control effect, it is determined that all sub-areas do not meet the preset additional control conditions. When it is determined that the actual traffic control sequence and the expected traffic control sequence do not meet the conditions for matching the final control effect, all sub-areas are determined to meet the preset additional control conditions.

[0065] Further optionally, the above determination of whether the actual traffic control sequence and the expected traffic control sequence meet the preset hard sequence matching conditions may include: Determine whether the actual traffic control sequence is exactly the same as the expected traffic control sequence; When the judgment result is yes, it is determined that the actual traffic control sequence and the expected traffic control sequence meet the preset hard sequence matching conditions; when the judgment result is no, it is determined that the actual traffic control sequence and the expected traffic control sequence do not meet the preset hard sequence matching conditions.

[0066] Further optionally, the above determination of whether the actual traffic control sequence and the expected traffic control sequence meet the preset final control effect matching conditions may include: The first level of traffic congestion mitigation is determined based on the actual traffic control sequence, and the second level of traffic congestion mitigation is determined based on the expected traffic control sequence. Determine whether the congestion relief for the second vehicle is better than that for the first vehicle. If the judgment result is yes, it is determined that the actual traffic control sequence and the expected traffic control sequence do not meet the preset final control effect matching conditions; if the judgment result is no, it is determined that the actual traffic control sequence and the expected traffic control sequence meet the preset final control effect matching conditions.

[0067] Furthermore, for example: Assuming the actual traffic control sequence is to control the left area first and then the right area, and the expected traffic control sequence is to control the right area first and then the left area, and the left area and the right area have the same regional characteristics, (1) Assuming the congestion situation of the left area and the right area is the same and the vehicle traffic situation of the two areas is the same under the same conditions, then the vehicle congestion mitigation effect brought about by the two control sequences is likely to be the same, and the probability of unexpected congestion mitigation difference is low. Therefore, it is determined that the actual traffic control sequence and the expected traffic control sequence meet the preset final control effect matching condition; (2) Assuming the congestion situation of the left area and the right area is different, the vehicle congestion mitigation effect brought about by the expected traffic control sequence is better than that of the actual traffic control sequence. Therefore, it is determined that the actual traffic control sequence and the expected traffic control sequence do not meet the preset final control effect matching condition. This embodiment of the invention does not limit this.

[0068] As can be seen, this optional embodiment can determine the satisfaction of hard sequence matching conditions and the satisfaction of final control effect matching conditions, and thus determine the satisfaction result of additional control conditions. This is beneficial to improving the comprehensiveness, rationality and progressiveness of the method for determining the satisfaction result of additional control conditions, and thus beneficial to improving the accuracy and reliability of the determined satisfaction result of additional control conditions. In turn, it is beneficial to improve the execution accuracy and timeliness of the sub-regional additional control operations triggered by the satisfaction result of additional control conditions.

[0069] Example 2 Please see Figure 2 , Figure 2This is a flowchart illustrating another AI-based adaptive traffic control method for the entire domain, as disclosed in an embodiment of the present invention. Figure 2 The described method can be applied to an AI-based global traffic adaptive control system, which may include a server, including a local server or a cloud server; this embodiment of the invention is not limited to this. Figure 2 As shown, this AI-based global traffic adaptive control method includes the following operations: 201. For any given target intersection, based on the current date and time period, determine the type of information to be collected for that target intersection, and collect multi-dimensional information about that target intersection based on the information type.

[0070] 202. Based on the multi-dimensional information of the target intersection and the pre-trained converged traffic control AI model, generate target traffic light control parameters for the target intersection, and execute corresponding traffic light control operations based on the target traffic light control parameters of the target intersection, so as to alleviate traffic congestion and pedestrian congestion at the target intersection through the adjusted traffic lights.

[0071] 203. Determine the traffic control records for multiple intersections within the target time period, and based on the traffic control records, perform corresponding update operations on the training samples of the traffic control AI model.

[0072] 204. Based on the updated training samples, perform corresponding update and iteration operations on the traffic control AI model.

[0073] In this embodiment of the invention, for other descriptions of steps 201-204, please refer to the other detailed descriptions of steps 101-102 in Embodiment 1. These descriptions will not be repeated in this embodiment of the invention.

[0074] As can be seen, the embodiments of the present invention can realize the traffic control function of the target intersection based on the multi-dimensional information of the target intersection and the traffic control AI model, so as to alleviate the traffic congestion and pedestrian congestion at the target intersection. This is conducive to improving the comprehensiveness and rationality of the whole-domain adaptive traffic control method, and thus improving the accuracy and reliability of the determined traffic light control parameters. This, in turn, is conducive to improving the accuracy and reliability of traffic control at the intersection, improving the efficiency and convenience of traffic control at the intersection, and further improving the smoothness of vehicle traffic and road safety at the intersection and related roads. In addition, it can also provide a method for updating and iterating the traffic control AI model based on the traffic control records of multiple intersections within the target time period. This is conducive to improving the comprehensiveness and rationality of the update and iteration method of the traffic control AI model, and thus improving the accuracy and real-time performance of the update and iteration of the traffic control AI model. This is conducive to improving the application accuracy and traffic control effect of the traffic control AI model.

[0075] In an optional embodiment, the above-mentioned update operation on the training samples of the traffic control AI model based on traffic control records may include: Determine the trained control scheme of the traffic control AI model, and based on the trained control scheme, determine whether there are conflicting control contents in the traffic control records; When it is determined that there is no conflicting control content in the traffic control record, the traffic control record is directly added to the training sample of the traffic control AI model to obtain the updated training sample. When it is determined that there are conflicting control contents in the traffic control record, it is determined whether the conflicting control contents meet the preset effective optimization conditions. When it is determined that the conflict control content meets the effective optimization conditions, the corresponding replacement update operation is performed on the training samples of the traffic control AI model based on the conflict control content, and the content in the traffic control record other than the conflict control content is directly added to the training samples of the traffic control AI model to obtain the updated training samples.

[0076] Optional, conflict control content, for example: for the same traffic scenario, if scheme A is used based on the trained control scheme, while scheme B is used based on the traffic control records, and the two schemes are different, then conflict control content is identified. This embodiment of the invention does not limit this.

[0077] Optionally, the above determination of whether the conflict control content meets the preset effective optimization conditions can be illustrated by the following example: assuming the conflict control content is the latest control plan determined by staff based on actual needs or the latest policies, that is, the conflict control content is the current optimal plan, and this conflict control content is taken as the standard for the same traffic scenario, then the conflict control content is determined to meet the preset effective optimization conditions; assuming the conflict control content is a control plan obtained due to system / model / equipment errors, then the conflict control content is determined not to meet the preset effective optimization conditions. This embodiment of the invention does not impose any limitations.

[0078] Optionally, the above-mentioned replacement update operation is performed on the training samples of the traffic control AI model based on the conflict control content. For example, the existing training sample content that has a conflict relationship with the conflict control content in the training samples of the traffic control AI model is deleted, and the conflict control content is added to the training samples of the traffic control AI model. This embodiment of the invention is not limited.

[0079] Further optionally, when it is determined that the conflict control content does not meet the effective optimization conditions, the content other than the conflict control content in the traffic control record is directly added to the training sample of the traffic control AI model to obtain an updated training sample. This embodiment of the invention does not limit the scope of the invention.

[0080] As can be seen, this optional embodiment can match the corresponding training text update method for conflicting control content in traffic control records and for non-conflicting control content in traffic control records, which is conducive to improving the comprehensiveness and rationality of the training text update method, as well as the diversity, flexibility and pertinence of the training text update method, thereby improving the update accuracy and reliability of the training text, and thus improving the applicability and fit of the determined updated training text.

[0081] Example 3 Please see Figure 3 , Figure 3 This is a schematic diagram of the structure of an AI-based adaptive traffic control system disclosed in an embodiment of the present invention. Figure 3 The described system may include a server, which may be a local server or a cloud server; this embodiment of the invention does not limit the scope. Figure 3 As shown, this AI-based global traffic adaptive control system may include: The information collection module 301 is used to determine the type of information to be collected for any given target intersection based on the current date and time period, and to collect multi-dimensional information about the target intersection based on the information type.

[0082] The control parameter determination module 302 is used to generate target traffic light control parameters for the target intersection based on the multi-dimensional information of the target intersection and the traffic control AI model that has been pre-trained to convergence.

[0083] The traffic light control module 303 is used to perform corresponding traffic light control operations based on the target traffic light control parameters corresponding to the target intersection, so as to alleviate the traffic congestion and pedestrian congestion at the target intersection through the adjusted traffic lights. The multi-dimensional information includes the inherent multi-dimensional information of the target intersection and the current variable multi-dimensional information of the target intersection; the inherent multi-dimensional information includes the intersection type information, the number of traffic lights, and the traffic direction information of the target intersection; the current variable multi-dimensional information includes the current traffic conditions and the current traffic light operating parameters of the target intersection.

[0084] It is evident that implementation Figure 3 The described AI-based adaptive traffic control system can realize traffic control functions at target intersections based on multi-dimensional information and traffic control AI models, thereby alleviating traffic congestion and pedestrian congestion. This improves the comprehensiveness and rationality of the adaptive traffic control method, which in turn improves the accuracy and reliability of the determined traffic light control parameters. Consequently, it enhances the accuracy and reliability of traffic control at intersections, improves the efficiency and convenience of traffic control at intersections, and further improves the smoothness of vehicle traffic and road safety at intersections and related roads.

[0085] In an optional embodiment, such as Figure 4 As shown, the system may also include: The linkage control module 304 is used to determine, after the control parameter determination module 302 generates the target traffic light control parameters for the target intersection, related locations that have a positional connection with the target intersection and affect vehicle traffic. The related locations include one or more of the preceding intersection, subsequent intersection, and subsequent destination corresponding to the target intersection; determine the current traffic situation of the related locations; and determine the predicted vehicle traffic situation of the target intersection based on the target traffic light control parameters; determine whether the related locations meet the preset traffic light linkage control trigger conditions based on the current traffic situation and the predicted vehicle traffic situation; and when it is determined that the related locations meet the traffic light linkage control trigger conditions, perform corresponding linkage control operations on the traffic lights corresponding to the related locations based on the current traffic situation and the predicted vehicle traffic situation.

[0086] It is evident that implementation Figure 4The described system can provide a traffic light linkage control method corresponding to the associated locations of target intersections. When it is determined that the associated locations meet the traffic light control trigger conditions, linkage control operations are performed according to the current traffic conditions and predicted vehicle traffic conditions. This helps to improve the comprehensiveness and rationality of the traffic light linkage control method corresponding to the associated locations, thereby improving the accuracy and reliability of traffic light linkage control, as well as the timeliness and efficiency of traffic light linkage control. In this way, it helps to improve the accuracy and efficiency of congestion mitigation in areas involving multiple traffic lights.

[0087] In another optional embodiment, the linkage control module 304 determines whether the associated location meets the preset traffic light linkage control triggering conditions based on the current traffic conditions and predicted vehicle traffic conditions. Specifically, this includes: Based on the current traffic conditions, analyze the current vehicle capacity of the associated locations, and determine the current congestion severity of the associated locations based on the current traffic conditions. Based on the predicted vehicle traffic conditions, current vehicle capacity, and current congestion severity, determine whether the associated location meets the preset vehicle capacity conditions for the current traffic light traffic scenario. When it is determined that the associated location does not meet the vehicle capacity conditions of the current traffic light traffic scenario, the associated location is determined to meet the preset traffic light association control trigger conditions. When it is determined that the associated location meets the vehicle capacity conditions of the current traffic light passage scenario, the vehicle capacity of the corresponding empty area is determined based on the first waiting time of the associated location and the current traffic situation; based on the vehicle capacity of the empty area, it is determined whether the associated location meets the vehicle replacement capacity conditions of the preset next traffic light passage scenario. When it is determined that the associated location meets the vehicle replacement and capacity conditions for the next traffic light passage scenario, it is determined that the associated location does not meet the preset traffic light association control trigger conditions. When it is determined that the associated location does not meet the vehicle replacement capacity conditions for the next traffic light passage scenario, the associated location is determined to meet the preset traffic light association control trigger conditions.

[0088] It is evident that implementation Figure 4The described system can also determine the vehicle capacity conditions for the current traffic light traffic scene at the associated location and the vehicle takeover capacity conditions for the next traffic light traffic scene, thereby determining the result of the traffic light association control triggering condition being met. This helps to improve the comprehensiveness, rationality, and progressiveness of the method for determining the result of the traffic light association control triggering condition being met, which in turn helps to improve the accuracy and reliability of the determined result of the traffic light association control triggering condition being met, and thus helps to improve the timeliness and accuracy of the traffic light association control operation based on the result of the traffic light association control triggering condition being met.

[0089] In another optional embodiment, the linkage control module 304 performs corresponding linkage control operations on the traffic lights corresponding to the associated locations based on the current traffic conditions and predicted vehicle traffic conditions. Specifically, this includes: Based on the predicted vehicle traffic conditions, determine the first level of smooth traffic and the first level of congestion in the area corresponding to the target intersection, and based on the current traffic conditions, determine the second level of smooth traffic and the second level of congestion in the area corresponding to the associated location. When the associated location precedes the target intersection, if the first traffic flow level is greater than or equal to a preset traffic flow level threshold and the second congestion level is greater than or equal to a preset congestion level threshold, the corresponding traffic light at the associated location will have its passage indication time extended; if the first congestion level is greater than or equal to a preset congestion level threshold and the second traffic flow level is greater than or equal to a preset traffic flow level threshold, the corresponding stop indication time at the associated location will be extended. When the associated location is located after the target intersection, if both the first congestion level and the second congestion level are greater than or equal to the preset congestion level threshold, the corresponding traffic light at the associated location will be extended accordingly.

[0090] It is evident that implementation Figure 4 The described system can also match corresponding traffic light timing control methods based on the positional relationship between the associated location and the target intersection, as well as the comparison between the first smoothness and first congestion level of the area corresponding to the target intersection and the second smoothness and second congestion level of the area corresponding to the associated location. This helps to improve the comprehensiveness and rationality of traffic light timing control methods, enhance their diversity, flexibility, and pertinence, and ultimately improve the accuracy and reliability of associated traffic light timing control.

[0091] In another optional embodiment, the control parameter determination module 302 generates target traffic light control parameters for the target intersection based on the multi-dimensional information of the target intersection and a pre-trained, converged traffic control AI model, specifically including the following methods: Identify the target area related to the target intersection that needs to be traffic controlled, and perform corresponding sub-region division operations on the target area based on the multi-dimensional information of the target intersection, the special location information of the target area, and the special lane function information, to obtain one or more sub-regions; Based on the special location information and special lane function information of each sub-area, the first traffic control priority of each sub-area is determined, and based on the current date, current time period and the current traffic conditions of each sub-area, the second traffic control priority of each sub-area is determined. Based on the current traffic light operating parameters of the target intersection, determine the actual traffic control sequence for all sub-areas; Based on the first traffic control priority, the second traffic control priority, and the actual traffic control sequence, determine whether all sub-areas meet the preset additional control conditions. When it is determined that all sub-regions do not meet the additional control conditions, the current traffic light operating parameters are set as the target traffic light control parameters for that target intersection. When it is determined that all sub-regions meet the additional control conditions, the corresponding parameter adjustment operation is performed on the current traffic light operating parameters according to the first traffic control priority and the second traffic control priority, so as to obtain the target traffic light control parameters for the target intersection and realize traffic linkage control between multiple sub-regions.

[0092] It is evident that implementation Figure 4 The described system can also provide traffic linkage control methods between multiple sub-regions. When all sub-regions meet the additional control conditions, the current traffic light operating parameters are adjusted according to the determined first and second traffic control priorities. This helps to improve the comprehensiveness and rationality of traffic linkage control methods between multiple sub-regions, thereby improving the accuracy and reliability of traffic linkage control between multiple sub-regions, and thus helping to optimize traffic order and alleviate congestion in multiple sub-regions.

[0093] In another optional embodiment, the control parameter determination module 302 determines whether all sub-regions meet the preset additional control conditions based on the first traffic control priority, the second traffic control priority, and the actual traffic control sequence, specifically including the following methods: Based on the first and second traffic control priorities, the expected traffic control sequence for each sub-area is determined. Determine whether the actual traffic control sequence and the expected traffic control sequence meet the preset hard sequence matching conditions; When it is determined that the actual traffic control sequence and the expected traffic control sequence meet the hard sequence matching condition, it is determined that all sub-areas do not meet the preset additional control conditions. When it is determined that the actual traffic control sequence and the expected traffic control sequence do not meet the hard sequence matching condition, it is determined whether the actual traffic control sequence and the expected traffic control sequence meet the preset final control effect matching condition. When it is determined that the actual traffic control sequence and the expected traffic control sequence meet the conditions for matching the final control effect, it is determined that all sub-areas do not meet the preset additional control conditions. When it is determined that the actual traffic control sequence and the expected traffic control sequence do not meet the conditions for matching the final control effect, all sub-areas are determined to meet the preset additional control conditions.

[0094] It is evident that implementation Figure 4 The described system can also determine the satisfaction of hard sequence matching conditions and the satisfaction of final control effect matching conditions, thereby determining the satisfaction of additional control conditions. This helps to improve the comprehensiveness, rationality, and progressiveness of the method for determining the satisfaction of additional control conditions, which in turn helps to improve the accuracy and reliability of the determined satisfaction of additional control conditions. This, in turn, helps to improve the accuracy and timeliness of the execution of additional control operations in sub-regions triggered by the satisfaction of additional control conditions.

[0095] In yet another alternative embodiment, such as Figure 4 As shown, the system may also include: The model update and iteration module 305 is used to determine the traffic control records for multiple intersections within the target time period, and to perform corresponding update operations on the training samples of the traffic control AI model based on the traffic control records. Based on the updated training samples, perform corresponding update and iteration operations on the traffic control AI model.

[0096] It is evident that implementation Figure 4 The described system can also provide a way to update and iterate the traffic control AI model based on traffic control records for multiple intersections within a target time period. This helps to improve the comprehensiveness and rationality of the update and iteration method of the traffic control AI model, thereby improving the accuracy and real-time performance of the update and iteration of the traffic control AI model, and ultimately improving the application accuracy and traffic control effect of the traffic control AI model.

[0097] In another optional embodiment, the model update iteration module 305 performs corresponding update operations on the training samples of the traffic control AI model based on traffic control records in the following specific ways: Determine the trained control scheme of the traffic control AI model, and based on the trained control scheme, determine whether there are conflicting control contents in the traffic control records; When it is determined that there is no conflicting control content in the traffic control record, the traffic control record is directly added to the training sample of the traffic control AI model to obtain the updated training sample. When it is determined that there are conflicting control contents in the traffic control record, it is determined whether the conflicting control contents meet the preset effective optimization conditions. When it is determined that the conflict control content meets the effective optimization conditions, the corresponding replacement update operation is performed on the training samples of the traffic control AI model based on the conflict control content, and the content in the traffic control record other than the conflict control content is directly added to the training samples of the traffic control AI model to obtain the updated training samples.

[0098] It is evident that implementation Figure 4 The described system can also match corresponding training text update methods for conflicting control content in traffic control records and for non-conflicting control content in traffic control records. This helps to improve the comprehensiveness and rationality of the training text update methods, as well as the diversity, flexibility and pertinence of the training text update methods. In turn, it helps to improve the update accuracy and reliability of the training text, thereby improving the applicability and relevance of the determined updated training text.

[0099] Example 4 Please see Figure 5 , Figure 5 This is a schematic diagram of another AI-based adaptive traffic control system disclosed in an embodiment of the present invention. Figure 5 The described system may include a server, which may be a local server or a cloud server; this embodiment of the invention does not limit the scope. Figure 5 As shown, the system may include: Memory 401 storing executable program code; Processor 402 coupled to memory 401; Furthermore, it may also include an input interface 403 coupled to the processor 402 and an output interface 404; The processor 402 calls the executable program code stored in the memory 401 to execute the steps in the AI-based adaptive traffic control method described in Embodiment 1 or Embodiment 2.

[0100] Example 5 This invention discloses a computer storage medium that stores a computer program for electronic data interchange, wherein the computer program causes a computer to execute the steps in the AI-based adaptive traffic control method described in Embodiment 1 or Embodiment 2.

[0101] Example 6 This invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to perform the steps in the AI-based adaptive traffic control method described in Embodiment 1 or Embodiment 2.

[0102] The device embodiments described above are merely illustrative. The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0103] Through the detailed description of the above embodiments, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, including read-only memory (ROM), random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), one-time programmable read-only memory (OTPROM), electrically-Erasable Programmable Read-Only Memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0104] Finally, it should be noted that the AI-based adaptive traffic control method and system disclosed in the embodiments of this invention are merely preferred embodiments of the invention and are only used to illustrate the technical solutions of the invention, not to limit it. Although the invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this invention.

Claims

1. An AI-based adaptive traffic control method for the entire region, characterized in that, The method includes: For any identified target intersection, based on the current date and current time period, determine the type of information to be collected for that target intersection, and collect multi-dimensional information about that target intersection based on the information type; Based on the multi-dimensional information of the target intersection and the pre-trained converged traffic control AI model, target traffic light control parameters for the target intersection are generated, and corresponding traffic light control operations are performed based on the target traffic light control parameters of the target intersection, so as to alleviate traffic congestion and pedestrian congestion at the target intersection through the adjusted traffic lights. The multi-dimensional information includes the inherent multi-dimensional information of the target intersection and the current variable multi-dimensional information of the target intersection; the inherent multi-dimensional information includes the intersection type information, the number of traffic lights, and the traffic direction information of the target intersection; the current variable multi-dimensional information includes the current traffic conditions and the current traffic light operating parameters of the target intersection.

2. The AI-based adaptive traffic control method for the entire domain as described in claim 1, characterized in that, After generating the target traffic light control parameters for the target intersection, the method further includes: Identify associated locations that have a locational connection with the target intersection and affect vehicle traffic. The associated locations include one or more of the following: the preceding intersection, the following intersection, and the following destination. Determine the current traffic conditions at the associated location and, based on the target traffic light control parameters, determine the predicted vehicle traffic conditions at the target intersection; Based on the current traffic conditions and the predicted vehicle traffic conditions, determine whether the associated location meets the preset traffic light association control trigger conditions; When it is determined that the associated location meets the triggering condition for traffic light association control, the traffic lights corresponding to the associated location are subjected to corresponding linkage control operations based on the current traffic conditions and the predicted vehicle traffic conditions.

3. The AI-based adaptive traffic control method for the entire domain as described in claim 2, characterized in that, The step of determining whether the associated location meets the preset traffic light association control triggering conditions based on the current traffic conditions and the predicted vehicle traffic conditions includes: Based on the current traffic conditions, analyze the current vehicle capacity of the associated locations, and determine the current congestion severity of the associated locations based on the current traffic conditions. Based on the predicted vehicle traffic conditions, the current vehicle capacity, and the current congestion severity, determine whether the associated location meets the preset vehicle capacity conditions for the current traffic light traffic scenario; When it is determined that the associated location does not meet the vehicle capacity conditions of the current traffic light traffic scenario, the associated location is determined to meet the preset traffic light association control trigger conditions. When it is determined that the associated location meets the vehicle capacity conditions of the current traffic light passage scenario, the vehicle capacity of the vacant area corresponding to the associated location is determined based on the first waiting time of the associated location and the current traffic situation; based on the vehicle capacity of the vacant area, it is determined whether the associated location meets the vehicle replacement capacity conditions of the preset next traffic light passage scenario. When it is determined that the associated location meets the vehicle replacement and accommodation conditions for the next traffic light passage scenario, it is determined that the associated location does not meet the preset traffic light association control trigger conditions. When it is determined that the associated location does not meet the vehicle replacement and capacity conditions for the next traffic light passage scenario, the associated location is determined to meet the preset traffic light association control trigger conditions.

4. The AI-based adaptive traffic control method for the entire region according to claim 2, characterized in that, The step of performing corresponding linkage control operations on the traffic lights corresponding to the associated locations based on the current traffic conditions and the predicted vehicle traffic conditions includes: Based on the predicted vehicle traffic conditions, determine the first level of smooth traffic and the first level of congestion in the area corresponding to the target intersection, and based on the current traffic conditions, determine the second level of smooth traffic and the second level of congestion in the area corresponding to the associated location. When the associated location precedes the target intersection, if the first traffic flow level is greater than or equal to a preset traffic flow level threshold and the second congestion level is greater than or equal to a preset congestion level threshold, the traffic light corresponding to the associated location will have its corresponding traffic indication time extended; if the first congestion level is greater than or equal to a preset congestion level threshold and the second traffic flow level is greater than or equal to a preset traffic flow level threshold, the traffic light corresponding to the associated location will have its corresponding stop indication time extended. When the associated location is after the target intersection, and when both the first congestion level and the second congestion level are greater than or equal to a preset congestion level threshold, the traffic light corresponding to the associated location will be extended accordingly.

5. The AI-based adaptive traffic control method for the entire domain according to claim 1, characterized in that, The step involves generating target traffic light control parameters for the target intersection based on multi-dimensional information of the target intersection and a pre-trained, converged traffic control AI model, including: Identify the target area related to the target intersection and subject to traffic control, and perform corresponding sub-region division operations on the target area based on the multi-dimensional information of the target intersection, the special location information of the target area, and the special lane function information, to obtain one or more sub-regions; Based on the special location information and special lane function information of each sub-region, a first traffic control priority for each sub-region is determined, and based on the current date, the current time period, and the current traffic conditions of each sub-region, a second traffic control priority for each sub-region is determined. Based on the current traffic light operating parameters of the target intersection, determine the actual traffic control sequence corresponding to all the sub-areas; Based on the first traffic control priority, the second traffic control priority, and the actual traffic control sequence, determine whether all the sub-areas meet the preset additional control conditions; When it is determined that all the sub-regions do not meet the additional control conditions, the current traffic light operating parameters are determined as the target traffic light control parameters for the target intersection. When it is determined that all the sub-regions meet the additional control conditions, the corresponding parameter adjustment operation is performed on the current traffic light operating parameters according to the first traffic control priority and the second traffic control priority, so as to obtain the target traffic light control parameters for the target intersection, so as to realize the traffic linkage control among multiple sub-regions.

6. The AI-based adaptive traffic control method for the entire domain as described in claim 5, characterized in that, The step of determining whether all sub-regions meet preset additional control conditions based on the first traffic control priority, the second traffic control priority, and the actual traffic control sequence includes: Based on the first traffic control priority and the second traffic control priority, determine the expected traffic control sequence for all the sub-regions; Determine whether the actual traffic control sequence and the expected traffic control sequence meet the preset hard sequence matching conditions; When it is determined that the actual traffic control sequence and the expected traffic control sequence meet the hard sequence matching condition, it is determined that all the sub-regions do not meet the preset additional control conditions. When it is determined that the actual traffic control sequence and the expected traffic control sequence do not meet the hard sequence matching condition, it is determined whether the actual traffic control sequence and the expected traffic control sequence meet the preset final control effect matching condition. When it is determined that the actual traffic control sequence and the expected traffic control sequence meet the final control effect matching condition, it is determined that all the sub-regions do not meet the preset additional control conditions. When it is determined that the actual traffic control sequence and the expected traffic control sequence do not meet the final control effect matching condition, all the sub-regions are determined to meet the preset additional control conditions.

7. The AI-based adaptive traffic control method for the entire domain according to any one of claims 1-6, characterized in that, The method further includes: Determine traffic control records for multiple intersections within a target time period, and based on the traffic control records, perform corresponding update operations on the training samples of the traffic control AI model. Based on the updated training samples, the traffic control AI model is subjected to corresponding update and iteration operations; And, based on the traffic control records, performing corresponding update operations on the training samples of the traffic control AI model includes: Determine the trained control scheme of the traffic control AI model, and based on the trained control scheme, determine whether there are conflicting control contents in the traffic control record; When it is determined that the traffic control record does not contain the conflict control content, the traffic control record is directly added to the training sample of the traffic control AI model to obtain the updated training sample. When it is determined that the traffic control record contains conflicting control content, it is determined whether the conflicting control content meets the preset effective optimization conditions. When it is determined that the conflict control content meets the effective optimization conditions, the corresponding replacement update operation is performed on the training sample of the traffic control AI model based on the conflict control content, and the content in the traffic control record other than the conflict control content is directly added to the training sample of the traffic control AI model to obtain the updated training sample.

8. An AI-based adaptive traffic control system for the entire region, characterized in that, The system includes: The information collection module is used to determine the type of information to be collected for any given target intersection based on the current date and time period, and to collect multi-dimensional information about the target intersection based on the information type. The control parameter determination module is used to generate target traffic light control parameters for the target intersection based on the multi-dimensional information of the target intersection and the traffic control AI model that has been pre-trained to convergence. The traffic light control module is used to perform corresponding traffic light control operations based on the target traffic light control parameters corresponding to the target intersection, so as to alleviate the traffic congestion and pedestrian congestion at the target intersection through the adjusted traffic lights. The multi-dimensional information includes the inherent multi-dimensional information of the target intersection and the current variable multi-dimensional information of the target intersection; the inherent multi-dimensional information includes the intersection type information, the number of traffic lights, and the traffic direction information of the target intersection; the current variable multi-dimensional information includes the current traffic conditions and the current traffic light operating parameters of the target intersection.

9. An AI-based adaptive traffic control system for the entire region, characterized in that, The system includes: Memory containing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the AI-based adaptive traffic control method as described in any one of claims 1-7.

10. A computer storage medium, characterized in that, The computer storage medium stores computer instructions, which, when invoked, are used to execute the AI-based adaptive traffic control method for all regions as described in any one of claims 1-7.

Images