A highway lane management system

Abstract

This invention relates to the field of traffic management technology and discloses a highway lane management system, comprising a data fusion module, a state simulation module, a risk identification module, a simulation strategy module, a strategy optimization module, and an instruction execution module. It obtains a fused traffic state dataset by performing spatiotemporal fusion processing on multi-source real-time traffic data; establishes a dynamic traffic state mapping relationship to calculate future traffic operation states; identifies traffic bottleneck areas and traffic flow conflict risk areas caused by lane function pre-adjustment in the current and future time periods to generate a risk area set; performs simulation pre-playing on the risk area set to obtain a control strategy set; selects the control strategy with the optimal expected benefit index from the control strategy set as the final execution strategy, and generates lane function switching instructions for the target highway segment; and issues the lane function switching instructions to the lane control facilities to execute dynamic lane management. This invention can improve the efficiency of highway lane management.

Description

Technical Field

[0001] This invention relates to the field of traffic management technology, and in particular to a highway lane management system. Background Technology

[0002] In the field of highway operation and management, lane management, as a core component to ensure road traffic efficiency and improve traffic safety, directly impacts the overall operational quality of highways through its level of intelligence and precision. Currently, existing technologies still have many shortcomings in the full-process application of highway lane management, particularly in key areas such as traffic data processing, traffic condition prediction, risk prevention and control, and management strategy optimization, where the limitations of technology application are particularly prominent.

[0003] At the data processing and state prediction level, existing technologies lack the systematic processing capability for multi-source real-time traffic data on highways. For traffic data of different dimensions and collection frequencies, such as cross-sectional flow, average speed, and event alarms, professional spatiotemporal fusion processing is not conducted; traffic state analysis relies solely on single-type data or fragmented, scattered data. This approach not only leads to a one-sided and incomplete portrayal of the overall road traffic state but also reduces data accuracy, failing to form a fusion traffic state dataset that comprehensively reflects the actual road traffic operation. Furthermore, existing technologies have not established a dynamic traffic state mapping relationship that fits the actual road conditions, nor have they achieved advanced calculations to predict traffic operation states. They can only conduct passive lane management operations based on current traffic conditions, making it difficult to accurately predict future traffic trends and identify potential traffic bottlenecks in advance. This results in a lack of foresight and predictability in lane management, hindering flexible responses to dynamic changes in traffic flow and easily leading to localized traffic congestion.

[0004] At the level of risk prevention and strategy optimization, the application of existing technologies also has significant shortcomings. In the lane function adjustment stage, without combining pre-set lane function adjustment plans with simulation analysis of traffic flow operation status, blindly executing lane function switching and other adjustment operations can easily trigger safety risks such as traffic flow conflicts. It also fails to accurately identify and delineate the scope of risk impact, thus failing to form an effective risk area set. In the control strategy formulation stage, for identified traffic risk areas, targeted simulation exercises and multi-strategy matching analyses are not conducted. Management work relies solely on fixed lane management models or experience-based control strategies, lacking a scientific and systematic set of control strategies as support. This results in poor adaptability of the formulated control strategies to actual traffic risks, and insufficient targeting and effectiveness. In the strategy execution and optimization stage, a standardized strategy selection mechanism and closed-loop execution process have not been established. Simply issuing management instructions such as lane switching cannot guarantee the compliance and accuracy of the instruction execution process, nor can it dynamically adjust and optimize existing management strategies based on actual feedback data after instruction execution. This results in low overall efficiency and insufficient flexibility in lane management, making it difficult to meet the actual needs of efficient traffic and safety control under high-volume, fast-paced highway conditions. Summary of the Invention

[0005] To achieve the above objectives, the present invention provides a highway lane management system, comprising a data fusion module, a state simulation module, a risk identification module, a simulation strategy module, a strategy optimization module, and an instruction execution module, wherein: The data fusion module is used to acquire multi-source real-time traffic data of the target highway segment and perform spatiotemporal fusion processing on the multi-source real-time traffic data to obtain a fused traffic status dataset of the target highway segment. The state extrapolation module is used to establish a dynamic traffic state mapping relationship for the target highway segment based on the fused traffic state dataset, and to perform advanced extrapolation calculations on the future traffic operation state of the target highway segment based on the dynamic traffic state mapping relationship. The risk identification module is used to identify traffic bottleneck areas and traffic flow conflict risk areas caused by lane function pre-adjustment in the target highway segment during the current and future periods based on the advanced extrapolation calculation results, so as to generate a risk area set for the target highway segment. The simulation strategy module is used to perform simulation pre-runs on the risk area set to obtain the control strategy set for the target highway section; The strategy selection module is used to select the control strategy with the best expected benefit index in the control strategy set as the final execution strategy for the target highway segment, and generate a lane function switching instruction for the target highway segment based on the final execution strategy. The instruction execution module is used to send the lane function switching instruction to the lane control facility corresponding to the target highway section in order to perform dynamic lane management.

[0006] In a preferred embodiment, when the data fusion module acquires multi-source real-time traffic data of the target highway segment and performs spatiotemporal fusion processing on the multi-source real-time traffic data to obtain a fused traffic state dataset of the target highway segment, it is specifically used for: Collect cross-sectional flow data, average speed data, and event alarm data of the target highway section, and integrate the cross-sectional flow data, average speed data, and event alarm data into multi-source real-time traffic data of the target highway section; Spatiotemporal registration is performed on the multi-source real-time traffic data so that the multi-source real-time traffic data corresponds to a unified time reference and road location coordinate system; After time synchronization and spatial location matching are completed, the multi-source real-time traffic data is subjected to quality verification and cleaning to obtain the standard traffic data of the target highway section. The feature parameters reflecting traffic operation status in the standard traffic data are obtained, and the feature parameters are fused at the feature level to obtain the fused traffic status dataset of the target highway segment.

[0007] In a preferred embodiment, when the state extrapolation module performs the following operations: establishing a dynamic traffic state mapping relationship for the target highway segment based on the fused traffic state dataset, and performing advanced extrapolation calculations on the future traffic operation state of the target highway segment based on the dynamic traffic state mapping relationship: Extract the basic traffic state parameters of the target highway segment in the discrete space from the fused traffic state dataset; The basic traffic state parameters are input into the dynamic traffic state mapping relationship to obtain the spatiotemporal evolution parameter set of the traffic state of the target highway segment. The spatiotemporal evolution parameter set of the traffic state includes: state transition weight matrix and inertia factor. Based on the state transition weight matrix and the inertia factor, a forward projection calculation formula for future traffic conditions is constructed, and the traffic condition prediction value of the target highway segment in the future preset time period is calculated using the forward projection calculation formula.

[0008] In a preferred embodiment, the advanced calculation formula is: ; In the formula, The first result obtained from the deduction In the future, discrete road segments Standardized traffic state prediction vector at any given time. The inertia factor is obtained from the historical stability analysis in the dynamic traffic state mapping relationship. In order to be in The first segment of the target highway at the specified time Standardized traffic state vectors for each discrete road segment The preset global impact coefficient, For the state transition weight matrix from the th The section to the first The status of each road segment affects the weight. In order to be in The first segment of the target highway at the specified time Standardized traffic state vectors for each discrete road segment In order to be with the first A set of discrete road segments that are spatially adjacent and have traffic flow associations.

[0009] In a preferred embodiment, when the risk identification module performs calculations based on advanced projections to identify traffic bottleneck areas and traffic flow conflict risk areas caused by lane function pre-adjustment in the target highway segment during the current and future periods, in order to generate a risk area set for the target highway segment, it is specifically used for: The traffic state prediction values ​​of discrete road segments in the target highway segment are summarized during a preset time period to obtain the advanced extrapolation calculation results of the target highway segment. Extract the predicted traffic state values ​​of the target highway segment from the advanced simulation calculation results; The predicted traffic state value for the preset time period is compared with the preset traffic state threshold, and continuous road segments in which the predicted traffic state value continuously exceeds the preset traffic state threshold are identified. The continuous road segments are determined as traffic bottleneck areas of the target highway segment. Based on the lane function pre-adjustment scheme of the target highway section, and combined with the advanced simulation calculation results, the traffic flow operation status of the target highway section in the future preset time period is simulated under two scenarios: implementing the pre-adjustment scheme and not implementing the pre-adjustment scheme. For the same road segment in the same future preset time period, compare the traffic flow operation status under the scenarios of execution and non-execution. When the status index deteriorates beyond the preset conflict tolerance, the road segment is marked as a potential traffic flow conflict road segment of the target highway segment. By integrating the traffic bottleneck areas with the potential traffic flow conflict sections, a risk area set for the target highway section is obtained.

[0010] In a preferred embodiment, when the simulation strategy module performs a simulation of the risk area set to obtain the control strategy set for the target highway segment, it is specifically used for: Identify the spatiotemporal characteristics and risk causes of the concentrated risk areas; Based on the spatiotemporal characteristics and the causes of risk, the risk regions in the risk region concentration are classified to obtain the risk region set of the target highway segment. Based on the aforementioned risk region set, the control scenarios of the target highway section are matched and simulated to obtain preliminary control strategy fragments for the control scenarios. The initial control strategy fragment is spatiotemporally coupled and logically verified to obtain the initial control strategy fragment of the target highway segment. The preliminary control strategy fragments are fused and optimized to obtain the control strategy set for the target highway segment.

[0011] In a preferred embodiment, when the simulation strategy module performs strategy matching and simulation on the control scenario of the target highway segment based on the categorized risk region set to obtain a preliminary control strategy fragment of the control scenario, it is specifically used for: Based on the aforementioned risk area classification set, a typical control scenario for the target highway section is constructed; The typical control scenarios are semantically matched with the preset traffic control strategy knowledge graph, and a subset of candidate strategies associated with the typical control scenarios are retrieved. Multi-dimensional simulation is performed on the candidate strategy subset to obtain the quantified change of the candidate strategy subset; Based on the quantified change, the expected comprehensive effectiveness value of the candidate strategies in the candidate strategy subset is quantified using the strategy comprehensive effectiveness evaluation formula. Based on the expected comprehensive effectiveness value, the candidate strategies are sorted and optimized to obtain preliminary control strategy fragments for the typical control scenario.

[0012] In a preferred embodiment, the formula for evaluating the overall effectiveness of the strategy is: ; In the formula, For the first The expected overall effectiveness of each candidate strategy To evaluate the total number of dimensions, For the first Normalized weight coefficients for each evaluation dimension For the first A nonlinear standardized function for the change in each evaluation dimension. For the first The quantitative change in each evaluation dimension.

[0013] In a preferred embodiment, when the strategy selection module executes the selection of the control strategy with the optimal expected benefit index from the control strategy set as the final execution strategy for the target highway segment, and generates a lane function switching instruction for the target highway segment based on the final execution strategy, it is specifically used for: Obtain the expected benefit indicators of the centralized control strategy; Based on the preset indicator weight allocation rules, the expected benefit indicators are weighted and fused to obtain the comprehensive evaluation value of the regulation strategy; The comprehensive evaluation value is optimized, and the control strategy with the highest comprehensive evaluation value is taken as the final execution strategy for the target highway section. Based on the lane function adjustment scheme in the final execution strategy, a lane function switching instruction for the target highway segment is generated.

[0014] In a preferred embodiment, when the instruction execution module executes the command to send the lane function switching command to the lane control facility corresponding to the target highway segment to perform dynamic lane management, it is specifically used for: The compliance of the lane function switching command is verified to obtain the command to be issued for the target highway section; Based on the type of lane control facilities and communication interface protocol in the target highway section, the instruction to be issued is encoded into a drive control signal for the target highway section; The drive control signal is synchronously sent to the affected lane control facilities in the target highway section; Receive instruction reception confirmation and status feedback signals from the lane control facility; Based on the status feedback signal, it is confirmed that the lane function switching command has been successfully executed, thereby completing the closed-loop control of dynamic lane management.

[0015] In addition, the present invention also provides a highway lane management method, comprising: Acquire multi-source real-time traffic data of the target highway segment, and perform spatiotemporal fusion processing on the multi-source real-time traffic data to obtain a fused traffic status dataset of the target highway segment. Based on the fused traffic state dataset, a dynamic traffic state mapping relationship is established for the target highway segment, and based on the dynamic traffic state mapping relationship, a forward-looking calculation is performed on the future traffic operation state of the target highway segment. Based on the results of advanced simulation calculations, traffic bottleneck areas and traffic flow conflict risk areas caused by lane function pre-adjustment are identified in the target highway segment in the current and future time periods, so as to generate a risk area set for the target highway segment. The risk area set is simulated and pre-run to obtain the control strategy set for the target highway section; The control strategy with the best expected benefit index in the control strategy set is selected as the final execution strategy for the target highway segment, and a lane function switching instruction for the target highway segment is generated based on the final execution strategy. The lane function switching command is sent to the lane control facility corresponding to the target highway section to perform dynamic lane management.

[0016] Compared with the prior art, the present invention has the following beneficial effects: 1. In terms of traffic data processing and state prediction, this invention provides comprehensive and forward-looking decision-making basis for highway lane management through multi-source traffic data fusion and accurate state extrapolation. It collects real-time traffic data from multiple sources, including cross-sectional flow, average speed, and event alarms, and performs spatiotemporal registration, quality verification, and feature-level fusion to form an accurate fused traffic state dataset. Based on this dataset, a dynamic traffic state mapping relationship is established, and future traffic operation states are predicted through advanced extrapolation calculation formulas, identifying traffic bottleneck areas and potential traffic flow conflict risk areas in advance, making lane management more predictive. Compared to the shortcomings of existing technologies that overemphasize individual vehicle control while neglecting the identification of overall road segment bottlenecks, and the technical limitations of only achieving passive management, this invention shifts lane management from passive response to proactive prediction, providing forward-looking data support for the formulation of subsequent control strategies, fundamentally solving the core problem of the lack of predictability in traditional management models.

[0017] 2. In terms of traffic risk prevention and control strategy optimization, this invention significantly improves the scientific nature and effectiveness of lane management by leveraging simulation optimization and a closed-loop execution mechanism. It performs simulation pre-playing and strategy matching on a risk area set, generates multiple control strategies, selects the scheme with the optimal expected benefits, and generates lane function switching instructions. After compliance verification and coding, these instructions are sent to the lane control facilities, simultaneously receiving status feedback signals to form closed-loop control, achieving precise implementation of dynamic lane management and effectively improving highway traffic efficiency and safety. Compared to existing technologies that are complex in model, have high hardware requirements, and are difficult to implement, this invention, while ensuring technological advancement, also considers the convenience of engineering applications, reduces environmental limitations for actual deployment, and can quickly adapt to the management needs of the entire highway mainline, completely changing the traditional experience-based management model.

[0018] 3. This invention breaks through the limitations and incomplete systems of existing technologies, forming a complete technical solution integrating data fusion, state simulation, risk identification, simulation strategies, and optimal execution. This solution can dynamically adapt the optimal lane management strategy based on the traffic operation characteristics of different sections and time periods of highways, effectively alleviating traffic congestion, reducing the risk of traffic conflicts, and improving the smoothness and safety of road traffic. Simultaneously, the technical system of this invention possesses good versatility and scalability, flexibly adapting to the management needs of different highway operating scenarios, providing solid technical support for the intelligent and refined upgrading of highway lane management, and has significant engineering application value and promotional significance. Attached Figure Description

[0019] Figure 1 A system architecture diagram of a highway lane management system provided in an embodiment of the present invention; Figure 2 This is a flowchart illustrating a highway lane management system according to an embodiment of the present invention.

[0020] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0021] To provide a clearer understanding of the technical features, objectives, and effects of the present invention, specific embodiments are now described. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention; that is, the described embodiments are only a part of the embodiments of the invention, not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0022] In practice, the server-side equipment deployed in the highway lane management system provided by this invention consists of one or more devices. The aforementioned highway lane management system can be implemented as: a business instance, a virtual machine, or hardware devices. For example, the highway lane management system can be implemented as a business instance deployed on one or more devices in a cloud node. Simply put, the highway lane management system can be understood as software deployed on a cloud node, used to provide a highway lane management system to various user terminals. Alternatively, the highway lane management system can also be implemented as a virtual machine deployed on one or more devices in a cloud node. This virtual machine contains application software for managing various user terminals. Alternatively, the highway lane management system can also be implemented as a server composed of numerous identical or different types of hardware devices, with one or more hardware devices configured to provide the highway lane management system to various user terminals.

[0023] In terms of implementation, the highway lane management system and user terminal provided by this invention are mutually compatible. That is, if the highway lane management system is implemented as an application installed on a cloud service platform, then the user terminal is a client that establishes a communication connection with the application; or if the highway lane management system is implemented as a website, then the user terminal is implemented as a webpage; or if the highway lane management system is implemented as a cloud service platform, then the user terminal is implemented as a mini-program in an instant messaging application.

[0024] like Figure 1 The diagram shown is a system architecture diagram of a highway lane management system provided in an embodiment of the present invention.

[0025] The highway lane management system 100 described in this invention can be located on a cloud server. In terms of implementation, it can function as one or more service devices, or as an application installed on the cloud (e.g., a mobile service operator's server, server cluster, etc.), or it can be developed as a website. Depending on the functions implemented, the highway lane management system 100 may include a data fusion module 101, a state inference module 102, a risk identification module 103, a simulation strategy module 104, a strategy optimization module 105, and an instruction execution module 106. The modules described in this invention can also be referred to as units, which are a series of computer program segments that can be executed by the processor of an electronic device and perform a fixed function, stored in the memory of the electronic device.

[0026] In this embodiment of the invention, in a highway lane management system, each of the above-mentioned modules can be implemented independently and can call other modules. Here, "calling" can be understood as a module connecting to multiple modules of another type and providing corresponding services to those connected modules. In the highway lane management system provided by this embodiment of the invention, without modifying the program code, the applicability of a highway lane management system architecture can be adjusted by adding modules and directly calling them, achieving cluster-based horizontal expansion to quickly and flexibly expand the highway lane management system. In practical applications, the above-mentioned modules can be set in the same device or different devices, or they can be set in a virtual device, such as a service instance in a cloud server.

[0027] The following describes, with reference to specific embodiments, each component of a highway lane management system and its specific workflow: The data fusion module 101 is used to acquire multi-source real-time traffic data of the target highway segment and perform spatiotemporal fusion processing on the multi-source real-time traffic data to obtain a fused traffic status dataset of the target highway segment.

[0028] In this embodiment of the invention, when the data fusion module acquires multi-source real-time traffic data of a target highway segment and performs spatiotemporal fusion processing on the multi-source real-time traffic data to obtain a fused traffic state dataset of the target highway segment, it is specifically used for: Collect cross-sectional flow data, average speed data, and event alarm data of the target highway section, and integrate the cross-sectional flow data, average speed data, and event alarm data into multi-source real-time traffic data of the target highway section; Spatiotemporal registration is performed on the multi-source real-time traffic data so that the multi-source real-time traffic data corresponds to a unified time reference and road location coordinate system; After time synchronization and spatial location matching are completed, the multi-source real-time traffic data is subjected to quality verification and cleaning to obtain the standard traffic data of the target highway section. The feature parameters reflecting traffic operation status in the standard traffic data are obtained, and the feature parameters are fused at the feature level to obtain the fused traffic status dataset of the target highway segment.

[0029] Traffic flow data is collected at cross-sections by traffic flow detection devices deployed along the target highway section. This data records the number of vehicles passing through each detection section per unit time. Average speed data is collected by speed measurement devices to accurately capture the average speed of vehicles at different locations within the road section. Event alarm data is obtained through road monitoring systems, manual reporting channels, and feedback from vehicle terminals. This data covers abnormal events affecting traffic operation, such as traffic accidents, road construction, and vehicle malfunctions. These three types of data are aggregated and integrated to form multi-source real-time traffic data for the target highway section.

[0030] A unified time benchmark is established, using standard time as a reference, to calibrate the timestamps of cross-sectional flow data, average speed data, and event alarm data. This ensures consistent time recording accuracy across all data and eliminates deviations caused by time differences in data collection from different devices. A unified road location coordinate system is established, clearly defining the coordinates of the road segment's start and end points and key cross-sections. The collection locations corresponding to various data types are mapped and labeled according to this coordinate system, ensuring that each data point accurately corresponds to a specific road location. This completes the spatiotemporal registration of multi-source real-time traffic data and achieves unification between the time benchmark and the road location coordinate system.

[0031] A data quality verification and cleaning framework was established, comprising three core stages: integrity check, reasonableness verification, and outlier removal. The integrity check stage verifies for missing or disconnected data, ensuring no data is omitted from critical time periods and locations. The reasonableness verification stage, based on normal highway traffic patterns, determines whether the data is within a reasonable range, such as whether average vehicle speed meets the speed limit for the section and whether there are any extreme values ​​for cross-sectional flow that are significantly inconsistent with reality. The outlier removal stage removes verified outlier data and supplements missing data with reasonable data from adjacent time periods and locations, ultimately obtaining standard traffic data for the target highway section.

[0032] This study delves into the composition of standard traffic data, extracting core characteristic parameters reflecting traffic operation status, including peak cross-sectional flow, average driving speed, speed fluctuation amplitude, event impact duration, and event impact range. A feature-level fusion method is employed to systematically integrate the extracted characteristic parameters. By establishing a feature correlation model, the inherent relationships between different parameters are explored, such as the negative correlation between cross-sectional flow and average speed, and the impact patterns of event alarm data on speed and flow. This correlation information is integrated into the fusion process to form a fused traffic status dataset that comprehensively and accurately characterizes the traffic operation status of the target highway segment.

[0033] The beneficial effects are: collecting and integrating three types of core traffic data, comprehensively covering key information such as traffic volume, traffic efficiency and abnormal events on the target highway section, forming multi-source real-time traffic data, avoiding the problem of one-sided traffic status description caused by single data types, and providing rich and comprehensive basic data support for subsequent fusion processing.

[0034] By establishing a unified time reference and road location coordinate system through spatiotemporal registration, the differences in time recording accuracy and spatial location identification of data from different sources are eliminated. This ensures that cross-sectional flow, average speed, and event alarm data can be accurately matched in the spatiotemporal dimension, enabling various types of data to have the prerequisites for collaborative analysis and improving the correlation and usability of the data.

[0035] After synchronization and matching, the multi-source real-time traffic data is subjected to quality verification and cleaning to remove outliers, supplement missing data, and correct logical contradictions, so as to ensure the accuracy, integrity and consistency of the data and generate standard traffic data. This provides a high-quality and reliable data foundation for subsequent feature extraction and fusion, and avoids the interference of poor data on the analysis results.

[0036] The core feature parameters reflecting traffic operation status are accurately extracted from standard traffic data, covering key dimensions such as flow rate, speed, and event impact. Then, the intrinsic relationship between different parameters is explored through feature-level fusion. The scattered features are integrated into a fused traffic status dataset that can comprehensively and accurately represent traffic operation status, which greatly improves the feature representation capability of the data and provides strong data support for subsequent traffic status projection and risk identification.

[0037] The state projection module 102 is used to establish a dynamic traffic state mapping relationship for the target highway segment based on the fused traffic state dataset, and to perform advanced projection calculations on the future traffic operation state of the target highway segment based on the dynamic traffic state mapping relationship.

[0038] In this embodiment of the invention, when the state extrapolation module performs the following operations: establishing a dynamic traffic state mapping relationship for the target highway segment based on the fused traffic state dataset, and performing advanced extrapolation calculations on the future traffic operation state of the target highway segment based on the dynamic traffic state mapping relationship: Extract the basic traffic state parameters of the target highway segment in the discrete space from the fused traffic state dataset; The basic traffic state parameters are input into the dynamic traffic state mapping relationship to obtain the spatiotemporal evolution parameter set of the traffic state of the target highway segment. The spatiotemporal evolution parameter set of the traffic state includes: state transition weight matrix and inertia factor. Based on the state transition weight matrix and the inertia factor, a forward projection calculation formula for future traffic conditions is constructed, and the traffic condition prediction value of the target highway segment in the future preset time period is calculated using the forward projection calculation formula.

[0039] The advanced calculation formula is as follows: ; In the formula, The first result obtained from the deduction In the future, discrete road segments Standardized traffic state prediction vector at any given time. The inertia factor is obtained from the historical stability analysis in the dynamic traffic state mapping relationship. In order to be in The first segment of the target highway at the specified time Standardized traffic state vectors for each discrete road segment The preset global impact coefficient, For the state transition weight matrix from the th The section to the first The status of each road segment affects the weight. In order to be in The first segment of the target highway at the specified time Standardized traffic state vectors for each discrete road segment In order to be with the first A set of discrete road segments that are spatially adjacent and have traffic flow associations.

[0040] This study delves into the structure and content of the integrated traffic state dataset, focusing on core traffic information within the discrete space of the target highway segment. This discrete space comprises independent areas defined by different road section cross-sections, key entrances and exits, and interchanges. Parameters directly reflecting the basic traffic conditions of each discrete space are extracted from the dataset, covering key indicators such as vehicle traffic volume, average speed, road occupancy, and traffic density. This ensures the comprehensiveness and accuracy of the extracted parameters, forming the basic traffic state parameters of the target highway segment in the discrete space.

[0041] A dynamic traffic state mapping model is constructed based on highway traffic flow patterns, historical traffic state evolution data, and the logical relationships between different traffic parameters. Extracted basic traffic state parameters are input according to the model's required format. The model analyzes the current values, trends, and interrelationships of each parameter to calculate core parameters characterizing the temporal evolution trend and spatial propagation pattern of traffic states. These parameters are specifically represented by a state transition weight matrix and an inertia factor. The state transition weight matrix reflects the strength of traffic state transformations between different discrete spaces, while the inertia factor reflects the degree to which the current traffic state maintains its original trend. Together, they constitute the spatiotemporal evolution parameter set of the target highway segment's traffic state.

[0042] By combining the state transition weight matrix and inertia factor in the spatiotemporal evolution parameter set of traffic conditions, and based on the principles of traffic flow dynamics and historical traffic forecasting experience, a forward-looking calculation logic for future traffic conditions is constructed. This logic clarifies how the state transition weight matrix quantifies the mutual influence of traffic conditions in different regions, and how the inertia factor adjusts the intensity of the current state's influence on future trends, organically combining the two to form a complete calculation process. Following this process, by substituting basic traffic state parameters and spatiotemporal evolution parameters, the changes in traffic conditions in each discrete space within a preset future time period are gradually derived, including increases or decreases in traffic volume, fluctuations in driving speed, and the distribution of traffic density. Finally, the predicted traffic conditions of the target highway segment in the preset future time period are calculated.

[0043] The deduced first The standardized traffic state prediction vector of a discrete road segment at a specific future time is the core result calculated by combining the standardized traffic state vector of the current time of the road segment, the inertia factor, the global influence coefficient, the state influence weight, and the standardized traffic state vector of the current time of adjacent related road segments. It directly clarifies the traffic state of the road segment at a specific future time and provides a key reference for traffic management decisions.

[0044] The inertia factor originates from the historical stability analysis in the dynamic traffic state mapping relationship. By sorting out the past traffic state change data of the target highway segment, the ability and change pattern of traffic state in different time periods are analyzed, the degree of influence of historical traffic state on current and future traffic state is judged, and the specific value of the inertia factor is determined based on the quantitative analysis of this degree of influence.

[0045] No. The standardized traffic state vector of a discrete road segment at the current moment is a data vector formed by standardizing traffic state indicators such as traffic flow, speed, and vehicle density of the road segment at the current moment. It is formed by collecting raw data from real-time traffic monitoring equipment of the road segment, converting it into comparable values ​​according to unified standardization rules, and integrating them to form a vector that can comprehensively reflect the current traffic state of the road segment.

[0046] The preset global impact coefficient is a fixed value that is pre-set based on the overall traffic operation characteristics, management needs and historical traffic control experience of the target highway segment. It is used to adjust the overall impact of the traffic status of adjacent road segments on the future traffic status of the current road segment, and to ensure that the simulation results conform to the overall traffic operation law of the road segment.

[0047] From the The section to the first The state influence weights of each road segment are derived from the state transition weight matrix, which is constructed based on factors such as the traffic flow correlation strength, road connectivity, and capacity differences among the discrete road segments of the target highway. Through analysis of the... The section and the first Data such as traffic flow exchange volume and travel path correlation between road segments are used to determine the first... The traffic status of the first road segment affects the first The degree of influence of traffic conditions on each road segment is quantified to form the state influence weight.

[0048] No. The standardized traffic state vector of the current road segment is obtained in the same way as the first road segment. The standardized traffic state vectors of the discrete road segments at the current time are consistent, and this is achieved by collecting the first... Real-time traffic monitoring data for each road segment is processed and standardized to form vector data that accurately reflects the current traffic status of that road segment.

[0049] With the The set of discrete road segments that are spatially adjacent and have traffic flow associations is determined by analyzing the road network structure of the target highway segment, and then selecting those segments that are adjacent to the first discrete road segment. All discrete road segments that are directly adjacent in spatial location and have actual traffic flow exchange, travel route connection, and other related relationships are integrated into a road segment set, which clarifies the relationship between the first and second discrete road segments. The range of adjacent road segments affected by the traffic conditions of a discrete road segment.

[0050] The significance of this formula lies in its ability to accurately predict the standardized traffic state vector for each discrete segment of a target highway at a specific future time, providing a scientific basis for dynamic traffic management. The formula preserves the historical continuity of the current traffic state of the segment through an inertia factor, ensuring that the prediction results do not deviate from the development trend of the segment's own traffic state. By using a global influence coefficient, state influence weight, and the traffic state vectors of adjacent related segments, it comprehensively considers the influence of adjacent segments on the current segment, enabling the prediction results to reflect the interaction of traffic flows between segments. Through this comprehensive calculation method, it fully considers both the segment's own inertia and the influence of surrounding segments, accurately predicting future traffic states. This provides reliable data support for the formulation of dynamic traffic management measures such as lane function switching and traffic diversion, ensuring the efficiency and safety of highway traffic operations.

[0051] The beneficial effects are as follows: By focusing on the core information in the integrated traffic state dataset, basic parameters such as vehicle traffic volume, average speed, road occupancy, and traffic density are accurately extracted for the discrete space of the target highway segment. This ensures that the extracted parameters comprehensively cover the basic traffic conditions of each discrete space, providing accurate and specific input data for subsequent state mapping and extrapolation, and avoiding extrapolation biases caused by missing or redundant parameters.

[0052] The dynamic traffic state mapping relationship is constructed based on highway traffic flow patterns, historical state evolution data, and parameter correlation logic, enabling precise capture of the inherent changing patterns of traffic states. By inputting basic traffic state parameters into this mapping relationship and analyzing the current values, trends, and mutual influences of these parameters, a state transition weight matrix and an inertia factor are generated. The state transition weight matrix quantifies the intensity of traffic state transformations between different discrete spaces, while the inertia factor reflects the degree to which the current state maintains its original trend. Together, these form a set of spatiotemporal evolution parameters for traffic states, providing a core quantitative basis for predicting future traffic states.

[0053] By combining the state transition weight matrix and inertia factor, and based on traffic flow dynamics principles and historical prediction experience, a logically rigorous calculation process for predicting future traffic conditions is constructed. This process considers both the mutual influence of traffic states in adjacent discrete spaces and the inertial trend of current traffic states, ensuring that the prediction logic closely aligns with actual traffic operation patterns. By substituting basic traffic state parameters and spatiotemporal evolution parameters, the changes in traffic states in each discrete space within a preset future time period are gradually derived, accurately outputting traffic state prediction values. This advance prediction of future traffic operation trends provides forward-looking data support for subsequent risk identification, enabling lane management to shift from passive response to proactive prediction.

[0054] The formula relates the first through the inertia factor. The standardized traffic state vector of each discrete road segment at the current moment fully preserves the historical trend of traffic state changes, ensuring the temporal continuity of the simulation results. At the same time, the influence of adjacent road segments is quantified by the state transition weight matrix, and the overall effect intensity is adjusted by combining the global influence coefficient, accurately capturing the spatial propagation characteristics of traffic flow, and realizing the collaborative simulation of time and space dimensions.

[0055] The state transition weight matrix is ​​determined based on factors such as the spatial location relationship of road segments and the intensity of traffic flow association, which enables the precise quantification of the impact of adjacent road segments on the target road segment and avoids deviations caused by general estimation. The associated road segments clearly define the spatial influence range to ensure that only adjacent road segments with actual traffic flow association are included, excluding interference from irrelevant road segments and improving the pertinence and accuracy of the simulation.

[0056] The inertia factor, obtained through historical stability analysis, can dynamically reflect the ability of traffic conditions to maintain their original trends and adapt to the stability differences of traffic flow at different times. The global influence coefficient can be preset based on the traffic operation patterns of highways and historical prediction experience, flexibly adjusting the overall intensity of spatial correlation influence, so that the formula can adapt to the dynamic changes under different traffic scenarios and enhance the flexibility and adaptability of the extrapolation.

[0057] The formula will eventually output the first... The standardized traffic state prediction vectors for each discrete road segment at future times are provided. These vectors have a unified format and standardized indicators, and can comprehensively and accurately represent the future traffic operation status. The standardized results facilitate threshold comparison and state analysis by the subsequent risk identification module, providing unified and reliable data support for the identification of traffic bottleneck areas and conflict risk areas, and ensuring the smooth operation of subsequent processes.

[0058] The risk identification module 103 is used to identify traffic bottleneck areas and traffic flow conflict risk areas caused by lane function pre-adjustment in the target highway segment during the current and future periods based on the advanced extrapolation calculation results, so as to generate a risk area set for the target highway segment.

[0059] In this embodiment of the invention, when the risk identification module performs calculations based on advanced projections to identify traffic bottleneck areas and traffic flow conflict risk areas caused by lane function pre-adjustment in the target highway segment during the current and future periods, in order to generate a risk area set for the target highway segment, it is specifically used for: The traffic state prediction values ​​of discrete road segments in the target highway segment are summarized during a preset time period to obtain the advanced extrapolation calculation results of the target highway segment. Extract the predicted traffic state values ​​of the target highway segment from the advanced simulation calculation results; The predicted traffic state value for the preset time period is compared with the preset traffic state threshold, and continuous road segments in which the predicted traffic state value continuously exceeds the preset traffic state threshold are identified. The continuous road segments are determined as traffic bottleneck areas of the target highway segment. Based on the lane function pre-adjustment scheme of the target highway section, and combined with the advanced simulation calculation results, the traffic flow operation status of the target highway section in the future preset time period is simulated under two scenarios: implementing the pre-adjustment scheme and not implementing the pre-adjustment scheme. For the same road segment in the same future preset time period, compare the traffic flow operation status under the scenarios of execution and non-execution. When the status index deteriorates beyond the preset conflict tolerance, the road segment is marked as a potential traffic flow conflict road segment of the target highway segment. By integrating the traffic bottleneck areas with the potential traffic flow conflict sections, a risk area set for the target highway section is obtained.

[0060] Relevant information for all discrete road segments within the target highway is collected, defining the preset time period for each segment. Traffic state predictions for each segment at each time point within that preset time period are retrieved, covering core traffic state indicators such as traffic flow, speed, and vehicle density. Following the spatial distribution and temporal order of the discrete road segments, the predicted traffic state values ​​for all segments are systematically organized and summarized to form a comprehensive dataset reflecting the overall traffic state change trend of the target highway segment within the preset time period. This yields the advanced extrapolation calculation results for the target highway segment.

[0061] Open the dataset of advanced projection calculations for the target highway segment. Based on the classification criteria of traffic state indicators, filter out all the predicted data used to describe traffic operation. These data constitute the predicted traffic state values ​​for the target highway segment. Classify and organize the extracted predicted traffic state values, establishing a correspondence between discrete road segments and time nodes within a preset time period. This ensures that the predicted traffic state value for each discrete road segment at each time node is clearly available, preparing for subsequent comparisons with preset traffic state thresholds.

[0062] The specific values ​​of the preset traffic state thresholds are clearly defined. These thresholds are established based on the highway's design capacity, historical traffic congestion data, and traffic management standards, covering standard values ​​corresponding to key indicators such as upper limits for traffic flow, lower limits for driving speed, and upper limits for vehicle density. The predicted traffic state values ​​of each discrete road segment at each time point within the preset time period are compared one by one with the corresponding preset traffic state thresholds, and the time points when the predicted value of each discrete road segment exceeds the threshold are recorded. The comparison results are continuously tracked to identify continuously distributed discrete road segments whose predicted traffic state values ​​consistently exceed the preset traffic state thresholds within the preset time period. These continuous road segments are designated as traffic bottleneck areas of the target highway segment.

[0063] The pre-adjustment plan for lane functions of the target highway segment was retrieved, clarifying the core content of the plan, such as the type, scope, and implementation time of lane function changes. Based on the advanced simulation calculation results and supporting data, a traffic flow operation simulation environment was built, in which two simulation scenarios were constructed. One scenario strictly followed the requirements of the pre-adjustment plan, setting parameters such as lane function and traffic direction to simulate the traffic flow operation of the target highway segment within a preset future time period. The other scenario maintained the existing lane functions unchanged, with other initial conditions consistent with the first scenario, also simulating the traffic flow operation within a preset future time period. Finally, traffic flow operation data for the target highway segment under both scenarios were obtained.

[0064] Core status indicators for assessing traffic flow operation are identified, including vehicle throughput efficiency, traffic flow stability, and vehicle merging frequency. A preset conflict tolerance for each indicator is defined, which is an acceptable range based on traffic safety standards and historical conflict event data. For each discrete segment within the target highway segment, status indicator data under two simulated scenarios within the same preset future time period are extracted, and the numerical differences of the same indicator under the two scenarios are compared one by one. When the deterioration of any status indicator of a segment exceeds the corresponding preset conflict tolerance under the scenario of implementing the pre-adjustment plan, the segment is marked as a potential traffic flow conflict segment of the target highway segment.

[0065] The specific scope, distribution, and corresponding traffic conditions of the identified traffic bottleneck areas are analyzed. Information on potential traffic flow conflict sections, including their identification, conflict risk types, and deterioration of relevant status indicators, is compiled. The information from both types of areas is integrated in a unified format, duplicate section information is removed, and spatial relationships between sections are supplemented to form a complete dataset containing all risk areas, resulting in the risk area set for the target highway section.

[0066] The beneficial effects are as follows: The system collects traffic state prediction values ​​for every discrete segment of the target highway within a preset time period. These prediction values ​​comprehensively cover core traffic indicators such as traffic volume, average speed, and traffic density for each discrete segment. These scattered prediction values ​​are systematically summarized according to segment location and time sequence, ensuring no omissions or duplications, forming advanced extrapolation calculation results that fully reflect the overall traffic prediction situation of the target highway segment, providing comprehensive basic data support for subsequent risk identification.

[0067] The core data directly representing traffic operation status is precisely selected from the advanced simulation calculation results. Auxiliary information with low correlation to traffic status is eliminated, and key information such as traffic efficiency, road congestion, and traffic flow trends of each discrete road segment at different times within a preset time period is focused. By classifying and organizing the data, clear predicted traffic status values ​​are formed, making subsequent comparisons with thresholds more targeted and avoiding irrelevant data from interfering with the accuracy of risk identification.

[0068] The preset traffic state thresholds are formulated based on the highway's design capacity, historical congestion criteria, and traffic management requirements, clearly defining the upper limit of indicators for normal road operation. The predicted traffic state values ​​within a preset time period are compared one by one with these thresholds, accurately recording road segments where the predicted values ​​exceed the thresholds and the duration thereof. Road segments that consistently exceed the thresholds and are spatially continuous are then identified as traffic bottleneck areas. This process, through the dual constraints of quantitative standards and duration, ensures that the identification of traffic bottleneck areas is accurate and consistent with actual traffic scenarios, providing a clear target for subsequent targeted regulation.

[0069] Based on lane function pre-adjustment schemes, a traffic flow simulation framework is built using advanced simulation calculations. Two scenarios are constructed: one with the pre-adjustment scheme implemented and the other without. The framework recreates the traffic flow patterns on highways and the impact logic of lane function adjustments on traffic flow. It simulates the traffic flow routes, speed changes, merging and merging behaviors within a preset time period, fully presenting the traffic flow changes brought about by the pre-adjustment schemes. This provides an intuitive scenario comparison basis for predicting conflict risks.

[0070] For the same road segment and the same future time period, traffic flow operation indicators under two scenarios are compared one by one, with a focus on whether there is a significant decrease in speed or a sharp increase in density, indicating a deterioration in the condition. A preset conflict tolerance is set based on traffic safety standards and road operating comfort. When the indicators deteriorate beyond this tolerance, the road segment is marked as a potential traffic flow conflict segment. This method accurately identifies the conflict risk points caused by pre-adjustment plans through scenario comparison, proactively avoiding traffic safety hazards caused by blind adjustments.

[0071] A risk area integration framework is established, classifying identified traffic bottleneck areas according to characteristics such as congestion level and impact range, and categorizing marked potential traffic flow conflict sections according to risk level and involved lanes. The key attributes of both types of areas are then integrated through an information aggregation module. This results in a clearly structured and comprehensive risk area set, fully covering core traffic risk points for the current and future periods. This provides clear and focused risk targets for subsequent simulation strategy development, ensuring more targeted control strategies.

[0072] The simulation strategy module 104 is used to perform simulation pre-playing on the risk area set to obtain the control strategy set for the target highway section.

[0073] In this embodiment of the invention, when the simulation strategy module performs a simulation of the risk area set to obtain the control strategy set for the target highway segment, it is specifically used for: Identify the spatiotemporal characteristics and risk causes of the concentrated risk areas; Based on the spatiotemporal characteristics and the causes of risk, the risk regions in the risk region concentration are classified to obtain the risk region set of the target highway segment. Based on the aforementioned risk region set, the control scenarios of the target highway section are matched and simulated to obtain preliminary control strategy fragments for the control scenarios. The initial control strategy fragment is spatiotemporally coupled and logically verified to obtain the initial control strategy fragment of the target highway segment. The preliminary control strategy fragments are fused and optimized to obtain the control strategy set for the target highway segment.

[0074] When the simulation strategy module performs strategy matching and simulation based on the categorized risk region set to obtain a preliminary control strategy fragment for the control scenario of the target highway section, it is specifically used for: Based on the aforementioned risk area classification set, a typical control scenario for the target highway section is constructed; The typical control scenarios are semantically matched with the preset traffic control strategy knowledge graph, and a subset of candidate strategies associated with the typical control scenarios are retrieved. Multi-dimensional simulation is performed on the candidate strategy subset to obtain the quantified change of the candidate strategy subset; Based on the quantified change, the expected comprehensive effectiveness value of the candidate strategies in the candidate strategy subset is quantified using the strategy comprehensive effectiveness evaluation formula. Based on the expected comprehensive effectiveness value, the candidate strategies are sorted and optimized to obtain preliminary control strategy fragments for the typical control scenario.

[0075] The formula for evaluating the overall effectiveness of the strategy is as follows: ; In the formula, For the first The expected overall effectiveness of each candidate strategy To evaluate the total number of dimensions, For the first Normalized weight coefficients for each evaluation dimension For the first A nonlinear standardized function for the change in each evaluation dimension. For the first The quantitative change in each evaluation dimension.

[0076] Complete data on the risk area set was retrieved, including the distribution location, coverage area, and time periods of risk occurrence and duration for each risk area. By analyzing the spatial distribution patterns of each risk area, its concentrated road segments, adjacent relationships, and correlation with road structure were identified. Simultaneously, the temporal trends of risk changes were analyzed to determine high-incidence periods, duration, and evolution characteristics over time, thereby identifying the spatiotemporal characteristics of the risk areas. Combining basic data of the target highway segment, including road alignment, number of lanes, and capacity, as well as historical traffic incident records and traffic flow data, a combination of on-site verification and comprehensive data analysis was employed to identify the main factors causing the risks, including excessive traffic volume, road design defects, and traffic flow conflicts, accurately pinpointing the risk causes for each risk area.

[0077] The core dimensions for risk area classification are established, primarily based on the duration of risk, spatial distribution density, and core triggering factors in the risk causes. Clear classification standards are then developed. The spatiotemporal characteristic data and risk cause information of each risk area are compared against the classification standards one by one, grouping risk areas with similar spatiotemporal characteristics and consistent risk causes into the same category. After completing the comparison and classification of all risk areas, detailed information on risk areas within each category is compiled, including category name, core characteristics, common causes, and a list of areas, forming a categorized risk area set for the target highway segment.

[0078] This study delves into the categorized risk area sets, clarifying the core issues, impact scope, and control needs of each risk area category. Based on the traffic operation conditions of the target highway section, typical control scenarios corresponding to each risk area category are constructed. A pre-defined traffic control strategy knowledge graph is retrieved, containing a vast amount of mature strategies with relevant applicable scenarios, implementation conditions, and control objectives. Key elements of typical control scenarios are matched with the semantic information of the strategies in the knowledge graph to identify a subset of highly adaptable candidate strategies. A simulation platform is built to recreate the traffic environment of the target highway. Each strategy from the candidate strategy subset is imported into the platform for simulation, and changes in traffic operation indicators after strategy implementation are monitored and recorded. Based on this, preliminary control strategy fragments for the control scenarios are obtained.

[0079] We collected preliminary control strategy fragments corresponding to all typical control scenarios, and analyzed the implementation period, area of ​​effect, control measures, and core objectives of each strategy fragment. From a temporal perspective, we checked whether there was any overlap or conflict in the implementation periods of different strategy fragments, ensuring that strategy fragments implemented within the same time period would not interfere with each other. From a spatial perspective, we verified whether the areas of effect of each strategy fragment were reasonably connected, avoiding control gaps or redundant control, thus achieving spatiotemporal coupling. Simultaneously, by comparing the basic logic of traffic control with the actual situation of the target highway, we checked whether the control measures of each strategy fragment were feasible, whether the logical relationships between the measures were smooth, and whether they could effectively address the corresponding type of risk, completing logical verification and ultimately obtaining verified preliminary control strategy fragments.

[0080] This paper summarizes preliminary control strategy fragments after spatiotemporal coupling and logical verification, and analyzes the correlation and complementarity between the fragments. For strategy fragments acting on the same area or addressing similar risks, core control measures are extracted, duplicate content is removed, and integrated into a more comprehensive and efficient combined strategy. For strategy fragments with some conflicts but consistent core objectives, the implementation details and intensity of control measures are adjusted based on risk mitigation priorities and actual traffic operation needs to achieve coordinated optimization of strategy fragments. All optimized strategy content is systematically organized according to risk category, implementation order, and applicable scenarios to form a control strategy set for target highway sections that covers various risk response solutions, is logically rigorous, and can be directly applied.

[0081] A thorough analysis of the risk area categorized by type was conducted to clarify the specific distribution location, risk level, impact range, and core risk characteristics of each type of risk area. Simultaneously, basic information on the target highway segment was retrieved, including road alignment, number of lanes, traffic capacity, and historical traffic flow data. Combining the spatiotemporal distribution patterns of the risk areas with the basic conditions of the road segments, the key triggers for the risks were identified and categorized according to risk type, impact level, and time of occurrence. This resulted in the construction of a typical control scenario that accurately reflects the actual traffic risk situation of the target highway segment. This scenario fully includes key information such as the risk background, core issues, and control requirements.

[0082] A pre-defined traffic control strategy knowledge graph stores a massive amount of practically validated traffic control strategies. Each strategy is associated with semantic information such as applicable scenario descriptions, implementation conditions, and control objectives. Typical control scenarios are decomposed into key semantic elements, including risk type, road segment characteristics, and control needs. A semantic similarity comparison method is used to match these semantic elements with the applicable scenario semantic information of each control strategy in the knowledge graph. All control strategies that meet the semantic matching requirements are selected and organized according to their degree of association, forming a subset of candidate strategies associated with typical control scenarios.

[0083] A multi-dimensional simulation platform was built to recreate the traffic operation environment of the target highway segment, covering key elements such as road structure, traffic flow characteristics, and risk area distribution. The evaluation dimensions of the simulation were clearly defined, including core dimensions such as traffic efficiency, safety level, and congestion mitigation effect, with each dimension corresponding to specific monitoring indicators. Each candidate strategy from the candidate strategy subset was imported into the simulation platform and run for a preset duration under the same initial traffic environment and risk scenario. Changes in the indicators of each evaluation dimension were monitored and recorded in real time. By comparing these changes with the initial state indicators, the quantitative change for each candidate strategy was calculated.

[0084] The core dimensions for evaluating the comprehensive effectiveness of strategies are clearly defined, including safety assurance, efficiency improvement, and balanced regulation. The weight of each dimension is determined based on its importance to traffic control. Based on the obtained quantified changes, the effectiveness score of each candidate strategy on each evaluation dimension is calculated. The scores of each dimension are then weighted and summed according to their respective weights to quantify the expected comprehensive effectiveness value of each candidate strategy. This value comprehensively reflects the overall effect of the candidate strategies in mitigating risks and improving traffic operation, providing a quantitative basis for strategy selection.

[0085] The expected comprehensive effectiveness values ​​of all candidate strategies are sorted and ranked from highest to lowest, with higher values ​​indicating better overall control effects. Candidate strategies with higher expected comprehensive effectiveness values ​​are prioritized. Considering the core needs of typical control scenarios and the actual conditions of road sections, strategies incompatible with the basic conditions of the road sections are eliminated, ultimately determining the optimal candidate strategy. This strategy is then broken down and refined according to implementation steps, key operational points, and applicable scope, forming preliminary control strategy fragments for typical control scenarios that can directly guide traffic control operations.

[0086] No. The expected comprehensive effectiveness value of each candidate strategy is the core result calculated by combining the normalized weight coefficients of the evaluation dimensions, the nonlinear standardized function of the change in the corresponding evaluation dimension, and the quantitative change in the evaluation dimension. It directly reflects the expected implementation effect of the candidate strategy under the comprehensive evaluation dimensions, and provides a key basis for the ranking and selection of strategies.

[0087] The total number of evaluation dimensions is determined based on the core objectives and actual needs of traffic control, covering all dimensions closely related to the effectiveness of traffic control, such as safety assurance, traffic efficiency, congestion relief, and operational stability. By sorting out the core demands and influencing factors of traffic control, all dimensions that need to be included in the evaluation are identified and their numbers are counted.

[0088] No. The normalized weight coefficients for each assessment dimension are determined based on the importance of each assessment dimension to the overall effect of traffic control. First, by surveying traffic management experts and analyzing historical control cases, the initial weights of each assessment dimension are determined. Then, all initial weights are processed to make the sum of the weights of all assessment dimensions equal, forming normalized weight coefficients, ensuring that the weight proportions of each dimension are reasonable and comparable.

[0089] No. The nonlinear standardization function for the changes in evaluation dimensions is designed to convert the quantitative changes in evaluation dimensions of different magnitudes and units into standardized values ​​of a unified scale. The function is constructed based on the characteristics of the evaluation dimensions and the data distribution patterns. By performing nonlinear transformation on the quantitative changes, it eliminates the dimensional differences between different dimensions, enabling the performance contributions of each dimension to be directly accumulated and calculated.

[0090] No. The quantitative changes in each evaluation dimension were obtained through multi-dimensional simulation of the candidate strategy. During the simulation, the changes before and after the implementation of the candidate strategy were recorded. The quantitative change in an evaluation dimension is obtained by subtracting the pre-implementation value from the post-implementation value. This quantitative change directly reflects the regulatory effect of the candidate strategy on that dimension.

[0091] The significance of this formula lies in its comprehensive and precise quantification of the first... The expected comprehensive effectiveness value of each candidate strategy provides a scientific quantitative basis for ranking and selecting candidate strategies. The formula reflects the difference in importance of each evaluation dimension through normalized weight coefficients, ensuring that the important dimensions have a more prominent impact on the comprehensive effectiveness; it unifies the scale of the quantitative changes of each evaluation dimension through a nonlinear standardization function, avoiding evaluation bias caused by differences in dimensions; by accumulating the effectiveness contributions of each dimension after standardization, it comprehensively considers the performance of the candidate strategy on all evaluation dimensions, and finally obtains the expected comprehensive effectiveness value that can comprehensively reflect the overall regulatory effect of the candidate strategy, helping to screen out the regulatory strategy with the best comprehensive performance.

[0092] The beneficial effects are: comprehensively analyzing the core information of the risk area set, accurately capturing the spatial distribution, coverage, and temporal characteristics of each risk area, such as the time of occurrence and duration. Combining advanced simulation data with historical traffic management experience, it deeply traces the root causes of risk formation, such as traffic bottlenecks stemming from insufficient road capacity, and potential conflict sections arising from traffic flow changes caused by lane adjustments, providing a clear risk positioning basis for the subsequent development of targeted strategies.

[0093] Based on the similarity of the spatiotemporal characteristics and commonalities of the causes of risk areas, clear classification criteria are established to integrate scattered risk areas by type. This ensures a unified approach to responding to the same type of risk, avoiding the inefficiency of developing separate strategies for each risk area. It also makes the overall distribution and severity of risks more intuitive, laying the foundation for subsequent batch matching and control strategies.

[0094] Typical control scenarios are constructed based on a categorized risk region set, with each scenario corresponding to the core characteristics and response objectives of a specific risk type. Suitable candidate strategies are selected from a pre-defined traffic control strategy knowledge graph through semantic matching. The effectiveness of these strategies is then verified through multi-dimensional simulations, quantifying indicators such as the degree of risk mitigation and changes in traffic efficiency after implementation. Finally, highly targeted and feasible preliminary control strategy fragments are selected to ensure accurate matching between strategies and risk types.

[0095] By integrating preliminary strategy fragments from different control scenarios through a spatiotemporal coupling framework, it ensures that strategies within the same time and region are conflict-free, and that strategies across different time periods and regions are seamlessly connected, forming a spatiotemporally coordinated control logic. A logical verification mechanism then checks the feasibility, security, and effectiveness of the strategies, eliminating content that could introduce new risks or logical contradictions, thus ensuring the rigor and reliability of the preliminary control strategy fragments.

[0096] The verified preliminary control strategy fragments are prioritized, with strategies targeting high-risk areas and demonstrating significant control effects being retained first. Through effect superposition analysis, the advantages of different strategies are integrated, and duplicate or weakly effective strategies are eliminated to form a complete set of control strategies. This strategy set not only covers targeted solutions for various risks but also achieves synergistic effects among strategies, providing a rich and high-quality selection for subsequent strategy optimization.

[0097] Based on the core characteristics of risk area clusters categorized by type, and combined with the road structure, traffic flow patterns, and management needs of the target highway segments, key elements for different risk types are extracted. A standardized scenario framework is established, clarifying the boundary conditions, core risk points, and control objectives for each scenario, forming typical control scenarios covering various risk scenarios. This makes subsequent strategy matching more targeted and avoids the problem of insufficient adaptability caused by generalized strategies.

[0098] The pre-defined traffic control strategy knowledge graph integrates professional knowledge, historical cases, and industry standards for highway traffic control, including semantic information such as applicable scenarios, implementation conditions, and expected effects. Through a semantic matching mechanism, the core features of typical control scenarios are compared one-to-one with the semantic descriptions of strategies in the knowledge graph, accurately identifying highly adaptable control strategies. Rapid retrieval forms a subset of candidate strategies, avoiding the inefficiency of blind screening and providing high-quality strategy options for subsequent simulations.

[0099] A multi-dimensional simulation platform closely mirroring actual traffic operation patterns is built to recreate traffic environments under typical control scenarios, incorporating each strategy from a subset of candidate strategies. The platform simulates the dynamic changes in traffic flow after strategy implementation, recording specific changes in key indicators such as the degree of risk mitigation, the extent of improvement in traffic efficiency, and the reduction in the number of traffic conflicts, generating quantifiable changes. This provides a clear and intuitive presentation of the actual effects of each strategy, offering objective and accurate quantitative data for subsequent comprehensive performance evaluation.

[0100] The comprehensive effectiveness evaluation formula for strategies reflects the importance of each evaluation dimension through normalized weight coefficients and eliminates dimensional differences between different indicators using a nonlinear standardization function. Based on quantified changes, the formula comprehensively integrates the performance of each dimension to accurately calculate the expected comprehensive effectiveness value of each candidate strategy. This enables quantitative comparison of strategy effects, avoids selection bias caused by subjective judgment, and makes strategy evaluation more scientific.

[0101] Based on the expected comprehensive effectiveness value, candidate strategies are ranked from highest to lowest, prioritizing the selection of strategies with the best overall performance. Considering the actual constraints of typical control scenarios, infeasible strategies are further eliminated, and strategies with strong adaptability and significant effects are selected as the core content. This results in a preliminary control strategy fragment that is highly targeted and feasible, laying a high-quality foundation for subsequent spatiotemporal coupling and logical verification.

[0102] The formula integrates the performance of various evaluation dimensions, transforming the effects of candidate strategies in risk mitigation, efficiency improvement, cost control, and other aspects into specific expected comprehensive performance values. This enables quantitative comparison of strategy effectiveness, avoids biases caused by subjective judgment, and provides clear and objective core criteria for strategy ranking and selection, making strategy selection more scientific.

[0103] The total number of evaluation dimensions covers the key impact aspects of strategy implementation, ensuring a comprehensive consideration of the actual value of candidate strategies from different perspectives. Normalized weighting coefficients are allocated based on the differences in importance among the dimensions, ensuring that the core evaluation direction dominates the overall effectiveness while also taking into account the impact of secondary dimensions, achieving a balanced evaluation across multiple dimensions and avoiding the one-sidedness of judging from a single dimension.

[0104] Nonlinear standardization functions, tailored to the characteristics of indicators across different evaluation dimensions, transform quantitative changes with varying dimensions and numerical ranges into standardized values ​​under a unified standard. This eliminates interference from differences between indicators, making data from different dimensions that were previously incomparable comparable, and ensuring the rigorous logic and reliable results of the comprehensive performance value calculation.

[0105] The quantitative changes are directly derived from the multi-dimensional simulation results of candidate strategies, accurately recording the specific changes in each evaluation dimension after strategy implementation. The formula is calculated based on this objective data, precisely capturing the actual effects of candidate strategies. This ensures that the expected comprehensive effectiveness value truly reflects the strategy's adaptability to typical control scenarios, providing high-quality data support for subsequent strategy selection.

[0106] The strategy selection module 105 is used to select the control strategy with the best expected benefit index in the control strategy set as the final execution strategy for the target highway segment, and generate a lane function switching instruction for the target highway segment based on the final execution strategy.

[0107] In this embodiment of the invention, when the strategy selection module executes the selection of the control strategy with the optimal expected benefit index from the control strategy set as the final execution strategy for the target highway segment, and generates a lane function switching instruction for the target highway segment based on the final execution strategy, it is specifically used for: Obtain the expected benefit indicators of the centralized control strategy; Based on the preset indicator weight allocation rules, the expected benefit indicators are weighted and fused to obtain the comprehensive evaluation value of the regulation strategy; The comprehensive evaluation value is optimized, and the control strategy with the highest comprehensive evaluation value is taken as the final execution strategy for the target highway section. Based on the lane function adjustment scheme in the final execution strategy, a lane function switching instruction for the target highway segment is generated.

[0108] Retrieve the expected benefit indicators for each control strategy from the control strategy set. These indicators are the core quantitative results formed during the simulation and pre-run of the strategy, covering content directly related to the implementation effect of the strategy, such as the degree of risk mitigation, the extent of improvement in traffic efficiency, the effectiveness of implementation cost control, and the improvement of traffic safety, to ensure comprehensive acquisition of the expected benefit data for each control strategy.

[0109] The pre-defined indicator weighting rules are based on the core objectives of highway traffic control, historical control experience, and industry management requirements, clearly defining the importance of different expected benefit indicators in the comprehensive evaluation. According to these rules, each expected benefit indicator is assigned a corresponding weight, with higher weights allocated to core indicators such as the degree of risk mitigation and the extent of improvement in traffic efficiency, and appropriate weights allocated to secondary indicators such as the effectiveness of cost control. Through a weighted calculation method, each expected benefit indicator of each control strategy is multiplied by its corresponding weight and then summed to obtain a comprehensive evaluation value that reflects the overall effectiveness of the control strategy.

[0110] A comprehensive evaluation value-based selection mechanism is established. This mechanism uses the comprehensive evaluation value as the core evaluation criterion to systematically compare the comprehensive evaluation values ​​of all control strategies. Control strategies are ranked from highest to lowest comprehensive evaluation value; a higher comprehensive evaluation value indicates better overall performance in risk mitigation, efficiency improvement, and cost control. The control strategy with the highest comprehensive evaluation value in the ranking is directly selected as the final implementation strategy for the target highway segment, ensuring that the ultimately selected strategy has the optimal overall benefits.

[0111] This study delves into the lane function adjustment plan within the final execution strategy, clarifying key information such as the lane adjustment sections, original lane functions, target lane functions, implementation time, and transition methods. Following the standardized format of traffic management instructions, this key information is transformed into clear and unambiguous instructions, including the target audience, specific adjustment requirements, implementation timelines, and safety precautions. This ensures the instructions accurately convey all details of the lane function adjustment, generating lane function switching instructions for the target highway sections and providing a clear basis for the subsequent implementation of lane function adjustments.

[0112] The beneficial effects are as follows: It comprehensively retrieves the expected benefit indicators of each control strategy formed during the simulation and pre-run phase. These indicators cover core dimensions such as the degree of risk mitigation, the extent of improvement in traffic efficiency, the effectiveness of implementation cost control, and the improvement in traffic safety. It fully reflects the potential implementation value of each strategy, provides comprehensive and accurate basic data for subsequent comprehensive evaluation, and avoids the one-sidedness of strategy evaluation due to missing indicators.

[0113] The pre-defined indicator weighting rules are based on the core objectives of highway traffic control, historical management experience, and industry standards, clearly defining the differences in importance among different benefit indicators. These rules assign corresponding weights to each expected benefit indicator, with core indicators receiving higher weights and secondary indicators allocated appropriate weights. A weighted fusion calculation then transforms these multi-dimensional indicators into a single comprehensive evaluation value. This enables a quantitative assessment of the overall strategy's effectiveness, making the comparison of the merits of different strategies more intuitive and objective.

[0114] Using comprehensive evaluation as the core criterion, a clear selection mechanism is established to systematically compare and rank the comprehensive evaluation values ​​of all control strategies. The strategy with the highest comprehensive evaluation value is directly selected as the final execution strategy, ensuring that the selected strategy performs optimally in terms of risk control, efficiency improvement, and cost control. This avoids insufficient strategy adaptability caused by subjective decision-making, making lane management strategies more scientific and targeted.

[0115] This analysis delves into the lane function adjustment plan within the final implementation strategy, clarifying key details such as the adjusted road sections, original lane functions, target lane functions, implementation time, and transition methods. Following the standardized format of traffic management instructions, these details are translated into clear and unambiguous directives, covering core elements such as the target, adjustment requirements, timelines, and safety precautions. This ensures the instructions accurately convey all information regarding lane function adjustments, providing a clear basis for subsequent lane control facility operations and guaranteeing the smooth implementation of dynamic lane management.

[0116] The instruction execution module 106 is used to send the lane function switching instruction to the lane control facility corresponding to the target highway section in order to perform dynamic lane management.

[0117] In this embodiment of the invention, when the instruction execution module executes the command to send the lane function switching command to the lane control facility corresponding to the target highway segment to perform dynamic lane management, it is specifically used for: The compliance of the lane function switching command is verified to obtain the command to be issued for the target highway section; Based on the type of lane control facilities and communication interface protocol in the target highway section, the instruction to be issued is encoded into a drive control signal for the target highway section; The drive control signal is synchronously sent to the affected lane control facilities in the target highway section; Receive instruction reception confirmation and status feedback signals from the lane control facility; Based on the status feedback signal, it is confirmed that the lane function switching command has been successfully executed, thereby completing the closed-loop control of dynamic lane management.

[0118] A compliance verification system is established, based on relevant regulations for highway traffic management, operational specifications for lane control facilities, and road safety standards. Each lane function switching instruction is checked against the requirements of the system, including the affected road section, lane function type, execution time, and operating procedures, to ensure compliance. The system confirms that the instructions do not violate regulations, exceed the facility's operational scope, or endanger road safety. Upon successful verification, the instructions to be issued for the target highway section are obtained.

[0119] The specific types of all lane control facilities in the target highway section are identified, including variable lane signs, lane indicator lights, and traffic signal controllers. The communication interface protocols corresponding to each facility are determined to ensure a thorough understanding of the information transmission rules between the facilities and the control center. Based on the requirements of the facility type and communication protocol, the text content of the instructions to be issued is converted into specific format signals that the facilities can recognize and execute. This process strictly follows the encoding rules specified in the protocol to ensure that the signal format, transmission rate, and data structure are fully compatible with the facilities, generating the drive control signals for the target highway section.

[0120] A synchronized signal transmission mechanism is established. This mechanism can accurately locate all affected lane control facilities involved in the lane function switching command, and clearly define the specific location and communication address of each facility. Through a unified communication network, the drive control signal is simultaneously sent to all affected facilities, avoiding situations where some facilities execute first and others later due to time differences in signal transmission. This ensures that all relevant facilities can receive the command synchronously and prepare to execute the operation, guaranteeing the consistency of lane function switching.

[0121] A signal reception feedback monitoring platform is established to continuously monitor the feedback status of all lane control facilities receiving drive control signals. When a facility successfully receives a drive control signal, it automatically generates a command reception confirmation signal, indicating that the signal has been fully received. The facility then begins executing the command operation, and upon completion, generates a status receipt signal, providing detailed feedback on the facility's current operating status and command execution results. The monitoring platform collects both types of signals in real time to ensure a comprehensive understanding of the signal reception status and execution progress of each facility.

[0122] The collected status feedback signals are systematically analyzed to verify whether each affected lane control facility has reported successful execution. This confirms that the facility's operational status is completely consistent with the requirements of the lane function switching command, and that there are no execution failures or abnormal statuses. When all facilities report successful execution and the status meets expectations, it can be determined that the lane function switching command has been successfully executed, completing the closed-loop control process from command issuance to execution feedback, and ensuring the effective implementation of dynamic lane management.

[0123] The beneficial effects are as follows: A compliance verification system centered on highway traffic management regulations, lane control facility operation specifications, and road safety standards is established. This system verifies the adjusted road sections, lane function types, execution times, and operational procedures for each lane function switching instruction. It ensures that the instructions fully comply with relevant regulations, do not violate laws, exceed the facility's operational scope, or endanger road safety, and generates legal, compliant, and safe instructions to be issued, thus mitigating compliance risks and safety hazards during instruction execution from the outset.

[0124] A comprehensive review of the specific types of lane control facilities along the target highway section was conducted, identifying the corresponding communication interface protocols for various facilities such as variable lane signs, lane indicator lights, and traffic signal controllers, and mastering the information transmission rules between the facilities and the control center. Strictly adhering to the coding rules specified in the protocols, the text content of the instructions to be issued was converted into specific format signals that the facilities could directly recognize and execute. This ensured that the format, transmission rate, and data structure of the drive control signals were fully compatible with all types of facilities, providing technical support for the accurate transmission and execution of instructions.

[0125] Establish a precise signal synchronization mechanism by identifying all affected lane control facilities involved in the lane function switching command, and clarifying the specific location and communication address of each facility. Utilize a unified communication network to simultaneously send drive control signals to all affected facilities, completely avoiding the problem of some facilities executing first and others later due to time differences in signal transmission. This ensures that all relevant facilities receive the command synchronously and initiate the operation, guaranteeing the consistency and synchronicity of lane function switching and improving the collaborative effect of dynamic lane management.

[0126] A real-time signal reception feedback monitoring platform is established to continuously monitor the feedback status of all lane control facilities receiving drive control signals. When a facility successfully receives a drive control signal, it automatically generates and sends back a command reception confirmation signal, proving that the signal has been received completely and correctly. After executing the command operation, the facility generates a status feedback signal, providing detailed feedback on its current operating status and command execution result. The monitoring platform collects these two types of signals in real time, comprehensively and promptly grasping the signal reception status and execution progress of each facility, providing accurate basis for subsequent confirmation of command execution status.

[0127] All collected status feedback signals are systematically analyzed, and each affected lane control facility is checked to ensure that it has reported successful execution. This confirms that the actual operating status of the facility is completely consistent with the requirements of the lane function switching command, and that there are no issues such as execution failure or abnormal status. When all facilities meet the execution success conditions, the lane function switching command is considered to have been successfully executed, completing the closed-loop control of the entire process from command issuance, transmission, execution to feedback confirmation. This ensures the accurate implementation of dynamic lane management measures and guarantees the stability and safety of highway traffic operations.

[0128] Reference Figure 2 The diagram shown is a flowchart illustrating a highway lane management method according to an embodiment of the present invention. In this embodiment, the highway lane management method includes: Acquire multi-source real-time traffic data of the target highway segment, and perform spatiotemporal fusion processing on the multi-source real-time traffic data to obtain a fused traffic status dataset of the target highway segment. Based on the fused traffic state dataset, a dynamic traffic state mapping relationship is established for the target highway segment, and based on the dynamic traffic state mapping relationship, a forward-looking calculation is performed on the future traffic operation state of the target highway segment. Based on the results of advanced simulation calculations, traffic bottleneck areas and traffic flow conflict risk areas caused by lane function pre-adjustment are identified in the target highway segment in the current and future time periods, so as to generate a risk area set for the target highway segment. The risk area set is simulated and pre-run to obtain the control strategy set for the target highway section; The control strategy with the best expected benefit index in the control strategy set is selected as the final execution strategy for the target highway segment, and a lane function switching instruction for the target highway segment is generated based on the final execution strategy. The lane function switching command is sent to the lane control facility corresponding to the target highway section to perform dynamic lane management.

[0129] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0130] This application embodiment can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0131] The above description is merely a preferred embodiment of the present invention. It should be understood that the present invention is not limited to the forms disclosed herein and should not be construed as excluding other embodiments. It can be used in various other combinations, modifications, and environments, and can be altered within the scope of the concept described herein through the above teachings or related technologies or knowledge. Modifications and variations made by those skilled in the art that do not depart from the spirit and scope of the present invention should be within the protection scope of the appended claims.

[0132] It should be noted that, for the sake of simplicity, the foregoing method embodiments are described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

Claims

1. A highway lane management system, characterized in that, The system includes a data fusion module, a state deduction module, a risk identification module, a simulation strategy module, a strategy optimization module, and an instruction execution module, wherein: The data fusion module is used to acquire multi-source real-time traffic data of the target highway segment and perform spatiotemporal fusion processing on the multi-source real-time traffic data to obtain a fused traffic status dataset of the target highway segment. The state extrapolation module is used to establish a dynamic traffic state mapping relationship for the target highway segment based on the fused traffic state dataset, and to perform advanced extrapolation calculations on the future traffic operation state of the target highway segment based on the dynamic traffic state mapping relationship. The risk identification module is used to identify traffic bottleneck areas and traffic flow conflict risk areas caused by lane function pre-adjustment in the target highway segment during the current and future periods based on the advanced extrapolation calculation results, so as to generate a risk area set for the target highway segment. The simulation strategy module is used to perform simulation pre-runs on the risk area set to obtain the control strategy set for the target highway section; The strategy selection module is used to select the control strategy with the best expected benefit index in the control strategy set as the final execution strategy for the target highway segment, and generate a lane function switching instruction for the target highway segment based on the final execution strategy. The instruction execution module is used to send the lane function switching instruction to the lane control facility corresponding to the target highway section in order to perform dynamic lane management.

2. A highway lane management system as described in claim 1, characterized in that, When the data fusion module acquires multi-source real-time traffic data of the target highway segment and performs spatiotemporal fusion processing on the multi-source real-time traffic data to obtain the fused traffic state dataset of the target highway segment, it is specifically used for: Collect cross-sectional flow data, average speed data, and event alarm data of the target highway section, and integrate the cross-sectional flow data, average speed data, and event alarm data into multi-source real-time traffic data of the target highway section; Spatiotemporal registration is performed on the multi-source real-time traffic data so that the multi-source real-time traffic data corresponds to a unified time reference and road location coordinate system; After time synchronization and spatial location matching are completed, the multi-source real-time traffic data is subjected to quality verification and cleaning to obtain the standard traffic data of the target highway section. The feature parameters reflecting traffic operation status in the standard traffic data are obtained, and the feature parameters are fused at the feature level to obtain the fused traffic status dataset of the target highway segment.

3. A highway lane management system as described in claim 1, characterized in that, When the state projection module performs the following operations: establishing a dynamic traffic state mapping relationship for the target highway segment based on the fused traffic state dataset, and performing advanced projection calculations on the future traffic operation state of the target highway segment based on the dynamic traffic state mapping relationship, the module is specifically used for: Extract the basic traffic state parameters of the target highway segment in the discrete space from the fused traffic state dataset; The basic traffic state parameters are input into the dynamic traffic state mapping relationship to obtain the spatiotemporal evolution parameter set of the traffic state of the target highway segment. The spatiotemporal evolution parameter set of the traffic state includes: state transition weight matrix and inertia factor. Based on the state transition weight matrix and the inertia factor, a forward projection calculation formula for future traffic conditions is constructed, and the traffic condition prediction value of the target highway segment in the future preset time period is calculated using the forward projection calculation formula.

4. A highway lane management system as described in claim 3, characterized in that, The advanced calculation formula is as follows: ； In the formula, The first result obtained from the deduction In the future, discrete road segments Standardized traffic state prediction vector at any given time. The inertia factor is obtained from the historical stability analysis in the dynamic traffic state mapping relationship. In order to be in The first segment of the target highway at the specified time Standardized traffic state vectors for each discrete road segment The preset global impact coefficient, For the state transition weight matrix from the th The section to the first The status of each road segment affects the weight. In order to be in The first segment of the target highway at the specified time Standardized traffic state vectors for each discrete road segment In order to be with the first A set of discrete road segments that are spatially adjacent and have traffic flow associations.

5. A highway lane management system as described in claim 1, characterized in that, When the risk identification module performs calculations based on advanced projections to identify traffic bottleneck areas and traffic flow conflict risk areas caused by lane function pre-adjustment in the target highway segment during the current and future periods, in order to generate a risk area set for the target highway segment, it is specifically used for: The traffic state prediction values ​​of discrete road segments in the target highway segment are summarized during a preset time period to obtain the advanced extrapolation calculation results of the target highway segment. Extract the predicted traffic state values ​​of the target highway segment from the advanced simulation calculation results; The predicted traffic state value for the preset time period is compared with the preset traffic state threshold, and continuous road segments in which the predicted traffic state value continuously exceeds the preset traffic state threshold are identified. The continuous road segments are determined as traffic bottleneck areas of the target highway segment. Based on the lane function pre-adjustment scheme of the target highway section, and combined with the advanced simulation calculation results, the traffic flow operation status of the target highway section in the future preset time period is simulated under two scenarios: implementing the pre-adjustment scheme and not implementing the pre-adjustment scheme. For the same road segment in the same future preset time period, compare the traffic flow operation status under the scenarios of execution and non-execution. When the status index deteriorates beyond the preset conflict tolerance, the road segment is marked as a potential traffic flow conflict road segment of the target highway segment. By integrating the traffic bottleneck areas with the potential traffic flow conflict sections, a risk area set for the target highway section is obtained.

6. A highway lane management system as described in claim 1, characterized in that, When the simulation strategy module performs a simulation of the risk area set to obtain the control strategy set for the target highway segment, it is specifically used for: Identify the spatiotemporal characteristics and risk causes of the concentrated risk areas; Based on the spatiotemporal characteristics and the causes of risk, the risk regions in the risk region concentration are classified to obtain the risk region set of the target highway segment. Based on the aforementioned risk region set, the control scenarios of the target highway section are matched and simulated to obtain preliminary control strategy fragments for the control scenarios. The initial control strategy fragment is spatiotemporally coupled and logically verified to obtain the initial control strategy fragment of the target highway segment. The preliminary control strategy fragments are fused and optimized to obtain the control strategy set for the target highway segment.

7. A highway lane management system as described in claim 6, characterized in that, When the simulation strategy module performs strategy matching and simulation based on the categorized risk region set to obtain a preliminary control strategy fragment for the control scenario of the target highway section, it is specifically used for: Based on the aforementioned risk area classification set, a typical control scenario for the target highway section is constructed; The typical control scenarios are semantically matched with the preset traffic control strategy knowledge graph, and a subset of candidate strategies associated with the typical control scenarios are retrieved. Multi-dimensional simulation is performed on the candidate strategy subset to obtain the quantified change of the candidate strategy subset; Based on the quantified change, the expected comprehensive effectiveness value of the candidate strategies in the candidate strategy subset is quantified using the strategy comprehensive effectiveness evaluation formula. Based on the expected comprehensive effectiveness value, the candidate strategies are sorted and optimized to obtain a preliminary control strategy fragment for the typical control scenario. The formula for evaluating the overall effectiveness of the strategy is as follows: ； In the formula, For the first The expected overall effectiveness of each candidate strategy To evaluate the total number of dimensions, For the first Normalized weight coefficients for each evaluation dimension For the first A nonlinear standardized function for the change in each evaluation dimension. For the first The quantitative change in each evaluation dimension.

8. A highway lane management system as described in claim 1, characterized in that, When the strategy selection module executes the selection of the control strategy with the optimal expected benefit index from the control strategy set as the final execution strategy for the target highway segment, and generates lane function switching instructions for the target highway segment based on the final execution strategy, it is specifically used for: Obtain the expected benefit indicators of the centralized control strategy; Based on the preset indicator weight allocation rules, the expected benefit indicators are weighted and fused to obtain the comprehensive evaluation value of the regulation strategy; The comprehensive evaluation value is optimized, and the control strategy with the highest comprehensive evaluation value is taken as the final execution strategy for the target highway section. Based on the lane function adjustment scheme in the final execution strategy, a lane function switching instruction for the target highway segment is generated.

9. A highway lane management system as described in claim 1, characterized in that, When the instruction execution module executes the command to send the lane function switching command to the lane control facility corresponding to the target highway segment to perform dynamic lane management, it is specifically used for: The compliance of the lane function switching command is verified to obtain the command to be issued for the target highway section; Based on the type of lane control facilities and communication interface protocol in the target highway section, the instruction to be issued is encoded into a drive control signal for the target highway section; The drive control signal is synchronously sent to the affected lane control facilities in the target highway section; Receive instruction reception confirmation and status feedback signals from the lane control facility; Based on the status feedback signal, it is confirmed that the lane function switching command has been successfully executed, thereby completing the closed-loop control of dynamic lane management.

10. A method for managing highway lanes, characterized in that, include: Acquire multi-source real-time traffic data of the target highway segment, and perform spatiotemporal fusion processing on the multi-source real-time traffic data to obtain a fused traffic status dataset of the target highway segment. Based on the fused traffic state dataset, a dynamic traffic state mapping relationship is established for the target highway segment, and based on the dynamic traffic state mapping relationship, a forward-looking calculation is performed on the future traffic operation state of the target highway segment. Based on the results of advanced simulation calculations, traffic bottleneck areas and traffic flow conflict risk areas caused by lane function pre-adjustment are identified in the target highway segment in the current and future time periods, so as to generate a risk area set for the target highway segment. The risk area set is simulated and pre-run to obtain the control strategy set for the target highway section; The control strategy with the best expected benefit index in the control strategy set is selected as the final execution strategy for the target highway segment, and a lane function switching instruction for the target highway segment is generated based on the final execution strategy. The lane function switching command is sent to the lane control facility corresponding to the target highway section to perform dynamic lane management.

Images