Vehicle passage guidance information pushing method, device and electronic equipment

Abstract

The application discloses a vehicle passing guidance information pushing method and device and electronic equipment, and is applied to the technical fields of intelligent traffic, vehicles and traffic control systems. The vehicle passing guidance information pushing method comprises the following steps: acquiring traffic flow parameters of a road area; determining a target traffic scene of the road area according to a matching result of the traffic flow parameters and reference traffic flow parameter intervals of at least two reference traffic scenes; performing grid division on the road area according to grid division parameters corresponding to the target traffic scene to obtain a grid division result; and in the case that a vehicle enters the road area, pushing vehicle passing guidance information to the vehicle according to vehicle state information of the vehicle, a target grid unit corresponding to the vehicle and state information of a target signal lamp, the target signal lamp being determined based on a signal lamp associated with the target grid unit. The method can solve the technical problem of low accuracy of vehicle passing guidance information pushing.

Description

Technical Field

[0001] This application belongs to the technical field of intelligent transportation, vehicles, and traffic control systems, and particularly relates to a method, device, and electronic device for pushing vehicle traffic guidance information. Background Technology

[0002] Vehicle traffic guidance information refers to the auxiliary information provided by the cloud control platform to drivers or autonomous vehicles to help vehicles pass through roads safely and efficiently, such as suggested vehicle speed, guide lanes, and traffic light status.

[0003] In related technologies, vehicle traffic guidance information can be implemented based on a spatial matching scheme using fixed geographic graticets. For example, the spatial matching scheme involves pre-dividing the road area into several geographic graticets of the same size and associating each geographic graticet with a corresponding traffic light. The cloud control platform obtains the vehicle's location coordinates in real time and maps them to the corresponding geographic graticet. Once a vehicle is determined to have entered a target geographic graticet associated with a traffic light, the real-time status of the traffic light associated with that target geographic graticet is pushed to the vehicle. However, using fixed-size geographic graticets cannot adapt to different traffic conditions. Because all geographic graticets have the same coverage and triggering conditions, regardless of whether the traffic situation on the road is sparse with vehicles traveling at high speeds or dense with vehicles traveling at low speeds, the vehicle traffic guidance information is triggered at the same fixed geographic graticet. This results in situations where, in high-speed driving scenarios, the guidance timing is too late, the vehicle traffic guidance information is outdated, or the vehicle cannot react effectively in time; in low-speed, slow-moving scenarios, the guidance timing is too early, and the vehicle traffic guidance information has no practical reference value, leading to a low accuracy rate in pushing vehicle traffic guidance information. Summary of the Invention

[0004] This application provides a method, apparatus, and electronic device for pushing vehicle traffic guidance information, which can solve the problem of low accuracy in pushing vehicle traffic guidance information.

[0005] In a first aspect, embodiments of this application provide a method for pushing vehicle traffic guidance information. This method includes: acquiring traffic flow parameters of a road area; determining a target traffic scenario of the road area based on the matching results of the traffic flow parameters and reference traffic flow parameter intervals of at least two reference traffic scenarios; dividing the road area into grids based on grid division parameters corresponding to the target traffic scenario to obtain a grid division result; wherein the grid division result includes m grid units, each of the m grid units corresponding to at least one traffic light, and m is a positive integer greater than 2; when a vehicle enters the road area, pushing vehicle traffic guidance information to the vehicle based on the vehicle's status information, the target grid unit corresponding to the vehicle, and the status information of the target traffic light, wherein the target traffic light is determined based on the traffic light associated with the target grid unit.

[0006] Secondly, embodiments of this application provide a vehicle traffic guidance information push device, which includes: an acquisition module for acquiring traffic flow parameters of a road area; determining a target traffic scenario of the road area based on the matching results of the traffic flow parameters and reference traffic flow parameter intervals of at least two reference traffic scenarios; dividing the first road area into grids according to the grid division parameters corresponding to the target traffic scenario to obtain a grid division result, the grid division result including m grid units, each grid unit corresponding to at least one traffic light, where m is a positive integer greater than 2; when a vehicle enters the road area, pushing vehicle traffic guidance information to the vehicle based on the vehicle status information of the vehicle, the target grid unit corresponding to the vehicle, and the status information of the target traffic light, wherein the target traffic light is determined based on the traffic light associated with the target grid unit.

[0007] Thirdly, embodiments of this application provide an electronic device, the device comprising: a processor and a memory storing computer program instructions; the processor, when executing the computer program instructions, implements a vehicle traffic guidance information push method as described in any of the first aspects.

[0008] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer program instructions, which, when executed by a processor, implement a vehicle passage guidance information push method as described in any of the first aspects.

[0009] Fifthly, embodiments of this application provide a computer program product, which includes a computer program or instructions. When the computer program or instructions are executed by a processor, they implement a vehicle traffic guidance information push method as described in any of the first aspects.

[0010] The vehicle traffic guidance information push method, device, electronic device, computer-readable storage medium, and computer program product of this application embodiment acquire traffic flow parameters of a road area and dynamically identify the target traffic scenario currently in the road area based on the matching results obtained by matching the traffic flow parameters with reference traffic flow parameter intervals of at least two reference traffic scenarios. After determining the target traffic scenario, the road area is adaptively divided into grids according to the grid division parameters corresponding to the target traffic scenario, generating a grid division result including m grid units that match the current traffic conditions, and establishing a correspondence between each grid unit and at least one traffic light. Thus, when a vehicle enters the road area, the cloud control platform can further integrate the vehicle's real-time status information, the target grid unit in which the vehicle is located, and the real-time status information of the target traffic light determined based on the target grid unit, to push personalized vehicle traffic guidance information to the vehicle. This dynamic and adaptive grid division mechanism fundamentally solves the problem of mismatch between guidance timing and actual vehicle needs, enabling the timing of vehicle traffic guidance information push to be accurately matched with the real-time status of vehicles and real-time traffic flow conditions. This significantly improves the accuracy and practicality of vehicle traffic guidance information push and effectively solves the technical problem of low accuracy in vehicle traffic guidance information push. Attached Figure Description

[0011] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 A flowchart illustrating a vehicle traffic guidance information push method provided in some embodiments of this application is shown. Figure 2 This document illustrates a flowchart illustrating a specific implementation of step 120 provided in some embodiments of this application. Figure 3 The diagram illustrates a specific implementation of step 130 provided in some embodiments of this application; Figure 4 The diagram illustrates a flowchart of the method for determining a target traffic light in a vehicle traffic guidance information push method provided in some embodiments of this application. Figure 5 The diagram shows a flowchart illustrating the method for determining a target grid cell in a vehicle traffic guidance information push method provided in some embodiments of this application; Figure 6 A flowchart illustrating a specific implementation of step 1602 provided in some embodiments of this application is shown; Figure 7The diagram illustrates a specific implementation of step 16024 provided in some embodiments of this application; Figure 8 A flowchart illustrating a specific implementation of step 140 provided in some embodiments of this application is shown; Figure 9 The diagram shows a structural schematic of a vehicle traffic guidance information push device provided in some embodiments of this application; Figure 10 The diagram shows a schematic representation of the structure of an electronic device provided in some embodiments of this application. Detailed Implementation

[0013] The features and exemplary embodiments of various aspects of this application will be described in detail below. To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain this application and not to limit it. For those skilled in the art, this application can be implemented without some of these specific details. The following description of the embodiments is merely to provide a better understanding of this application by illustrating examples.

[0014] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes said element.

[0015] It should be noted that the acquisition, storage, use, and processing of data in this application embodiment all comply with the relevant provisions of national laws and regulations.

[0016] It should be noted that in the embodiments of this application, certain software, components, models and other existing solutions in the industry may be mentioned. These should be regarded as exemplary and are only intended to illustrate the feasibility of implementing the technical solution of this application. However, it does not mean that the applicant has used or necessarily used the solution.

[0017] Before describing the technical solutions provided in the embodiments of this application, in order to facilitate understanding of the embodiments of this application, this application first provides a detailed description of the relevant technologies involved: With the rapid development of intelligent connected vehicles and vehicle-road cooperative technologies, traffic light warnings have become a core means of improving road traffic safety and efficiency. The needs of intelligent connected vehicles for traffic light warnings can be summarized in four dimensions: sufficient lead time, wide coverage, accurate matching, and efficient response.

[0018] In related technologies, vehicle guidance information related to traffic light warnings can be implemented using a spatial matching scheme based on fixed geographic grids. However, when traffic flow parameters change, a mismatch occurs between the triggering timing of vehicle guidance information and the actual needs of vehicles. Specifically, when vehicles are traveling at high speeds, the limited coverage of the fixed grid results in insufficient warning distance, causing vehicles to receive the guidance information too late and be unable to react effectively in a timely manner. When vehicles are traveling at low speeds, the same grid division results in excessively long warning distances, rendering the pushed vehicle guidance information lacking practical reference value. Furthermore, the contradiction between low spatial indexing efficiency and the fixed warning distance design further exacerbates these problems, reducing the accuracy of vehicle guidance information delivery and affecting the real-time response capability of the cloud control platform.

[0019] For example, in a typical application scenario at an intersection of a major urban road, traffic is heavy during the morning rush hour, with vehicles moving slowly at low speeds. In this situation, a fixed geographic grid scheme triggers guidance information pushes even when vehicles are still far from the traffic lights. However, due to the slow speed, the traffic light status may have changed by the time the vehicle actually arrives at the intersection, rendering the guidance information ineffective. At night, when traffic is light, vehicles travel at higher speeds. With the trigger point in the fixed grid scheme too close to the intersection, vehicles do not have sufficient time to adjust their driving strategies when receiving guidance information. More importantly, in special scenarios such as construction zones or ramps, abrupt changes in traffic flow parameters cause the association between fixed grid units and traffic lights to fail to adapt to local traffic characteristics, resulting in decreased matching accuracy. Consequently, the vehicle guidance information pushed by the cloud control platform cannot effectively support vehicle decision-making.

[0020] In summary, the spatial matching scheme based on fixed geographic grids in related technologies has the following technical problems that are difficult to solve: the coverage of a single grid is limited, resulting in insufficient reaction time for high-speed vehicles and making it difficult to meet real-time requirements; the fixed warning distance cannot simultaneously meet the long-distance response requirements of high-speed scenarios and the anti-interference requirements of low-speed scenarios; the characteristics of scenarios such as urban main roads, construction sections, and highway ramps are significantly different, and the adaptability of general algorithms is poor.

[0021] To address the problems in the aforementioned related technologies, embodiments of this application provide a method, apparatus, electronic device, computer-readable storage medium, and computer program product for pushing vehicle traffic guidance information. The following is a description of the accompanying drawings. Figure 1 To be continued Figure 8 The method for pushing vehicle traffic guidance information provided in this application will be described in detail through specific embodiments and application scenarios.

[0022] The vehicle traffic guidance information push method provided in this application can be applied to the fields of intelligent connected vehicles and vehicle-road cooperation, specifically applicable to various traffic scenarios such as urban arterial roads, highway ramps, construction sections, and suburban roads. This method can serve intelligent connected vehicles with different levels of automation, from L1 to L5. By providing real-time vehicle traffic guidance information to vehicles, it can effectively assist vehicles in adjusting their driving strategies in advance, thereby avoiding traffic accidents such as rear-end collisions, merging conflicts, and running red lights caused by untimely warnings or improper guidance, significantly improving road safety and traffic efficiency. For example, in dense traffic scenarios on urban arterial roads, this method can provide accurate close-range guidance for slow-moving vehicles, avoiding misjudgments caused by premature information push; in highway ramp scenarios, it can provide sufficient advance warning for high-speed vehicles, ensuring that vehicles have enough time to safely merge or decelerate.

[0023] Figure 1 The diagram illustrates a flowchart of a vehicle traffic guidance information push method provided in some embodiments of this application. For example... Figure 1 As shown, the method for pushing vehicle traffic guidance information may include steps 110 to 140.

[0024] Step 110: Obtain traffic flow parameters for the road area; Step 120: Determine the target traffic scenario for the road area based on the matching results of the traffic flow parameters and the reference traffic flow parameter intervals of at least two reference traffic scenarios; Step 130: Divide the road area into grids according to the grid division parameters corresponding to the target traffic scenario to obtain the grid division result; wherein, the grid division result includes m grid units, each of the m grid units corresponds to at least one traffic light, and m is a positive integer greater than 2; Step 140: When a vehicle enters the road area, push vehicle traffic guidance information to the vehicle based on the vehicle status information, the target grid unit corresponding to the vehicle, and the status information of the target traffic light, and determine the target traffic light based on the traffic light associated with the target grid unit.

[0025] Therefore, by acquiring traffic flow parameters of the road area and matching them with the reference traffic flow parameter intervals of at least two reference traffic scenarios, the target traffic scenario currently in the road area is dynamically identified. After determining the target traffic scenario, the road area is adaptively divided into grids according to the grid division parameters corresponding to the target traffic scenario, generating a grid division result containing m grid units that match the current traffic conditions, and establishing a correspondence between each grid unit and at least one traffic light. Thus, when a vehicle enters the road area, the cloud control platform can further integrate the vehicle's real-time status information, the target grid unit the vehicle is in, and the real-time status information of the target traffic light determined based on that target grid unit, to push personalized vehicle traffic guidance information to the vehicle. This dynamic and adaptive grid division mechanism fundamentally solves the problem of mismatch between guidance timing and actual vehicle needs, enabling the push timing of vehicle traffic guidance information to accurately match the vehicle's real-time status and real-time traffic flow conditions, significantly improving the accuracy and practicality of vehicle traffic guidance information push, and effectively solving the technical problem of low accuracy in vehicle traffic guidance information push.

[0026] The vehicle traffic guidance information push method adopted in this application embodiment allows the cloud control platform to automatically expand the grid coverage area according to the corresponding traffic scenario when vehicles are traveling at high speeds. This provides sufficient advance warning time, ensuring that vehicles have enough time to receive and respond to the traffic guidance information before reaching the intersection, effectively avoiding the problem of untimely response due to insufficient warning distance. In low-speed, slow-moving scenarios, the cloud control platform can adaptively reduce the grid coverage area to prevent the vehicle traffic guidance information push method from being pushed too early. This avoids the vehicle traffic guidance information push method becoming invalid due to changes in traffic light status when vehicles arrive at the intersection, ensuring that the pushed vehicle traffic guidance information push method has practical reference value.

[0027] The steps described above are explained in detail below.

[0028] First, regarding step 110, the traffic flow parameters involved in this embodiment refer to a set of data used to quantify road traffic conditions. These parameters reflect the real-time traffic load and operational efficiency of the road area. Traffic flow parameters may include, but are not limited to: traffic flow Q (vehicles / minute), traffic density D (vehicles / km), and vehicle speed V (km / h).

[0029] In this step, traffic flow parameters can be obtained in real time by deploying geomagnetic sensors, loop detectors, or video surveillance equipment in the road area to collect data such as traffic flow, traffic density, and vehicle speed. Alternatively, traffic flow parameters can be obtained directly from vehicles through vehicle-to-infrastructure (V2I) communication with intelligent connected vehicles, acquiring vehicle driving data such as anonymized location, speed, and acceleration, and then aggregating and statistically analyzing this data to calculate the traffic flow parameters for the road area. Alternatively, traffic flow parameters can also be obtained by periodically assessing the traffic conditions in the road area through historical data analysis and converting this assessment into traffic flow parameters.

[0030] Secondly, regarding step 120, the reference traffic scenario in this embodiment refers to predefined different traffic condition models, each corresponding to a specific set of traffic flow parameter intervals. The reference traffic scenario describes typical traffic conditions that may occur on a road at different times or under different conditions. For example, the reference traffic scenario can be defined according to traffic flow state, such as peak-hour congestion scenario, off-peak smooth flow scenario, and nighttime low-flow scenario; or it can be defined according to road physical characteristics, such as urban arterial road scenario, construction section scenario, and highway ramp scenario; or it can be defined according to real-time dynamic environmental factors, such as sunny day scenario, rainstorm scenario, low visibility scenario, and high visibility scenario.

[0031] In this embodiment, traffic flow refers to the number of vehicles passing through a certain cross-section of a road per unit time, effectively representing the level of congestion in a road area. Traffic flow can be obtained by deploying devices such as induction coils, video recognition systems, or radar sensors on the road to collect vehicle passage data in real time, or by statistically analyzing GPS data uploaded by vehicles. Traffic density refers to the number of vehicles contained in a unit length of road, effectively representing the degree of congestion in a road area. Traffic density can be obtained by analyzing road surveillance videos using image processing technology to count the number of vehicles within the road area. Vehicle speed refers to the average speed of vehicles traveling on the road area, reflecting traffic efficiency. Vehicle speed can be obtained by directly measuring it with radar speedometers or video speed measurement systems, or by calculating the average speed using vehicle GPS data.

[0032] The reference traffic flow parameter range in this application embodiment is a pre-defined range of traffic flow parameters used to describe a specific traffic scenario. The reference traffic flow parameter range can be determined based on historical data analysis, expert experience, or traffic simulation models.

[0033] In some embodiments of this application, to improve the accuracy and comprehensiveness of the target traffic scene determination and to achieve accurate determination of subsequent vehicle traffic guidance information, the traffic flow parameters correspondingly include traffic flow, traffic density, and vehicle speed, and the reference traffic flow parameter range includes a reference traffic flow range, a reference traffic density range, and a reference vehicle speed range; based on this, as... Figure 2 As shown, step 120 above may specifically include steps 1201 to 1205.

[0034] Step 1201: Match traffic flow with the reference traffic flow range of each of the at least two reference traffic scenarios to obtain a matching score between traffic flow and each reference traffic scenario; Step 1202: Match traffic density with the reference traffic density range of each of the at least two reference traffic scenarios to obtain a matching score between traffic density and each reference traffic scenario; Step 1203: Match vehicle speed with the reference vehicle speed range of each of the at least two reference traffic scenarios to obtain a matching score between vehicle speed and each reference traffic scenario; Step 1204: Based on the matching scores of traffic flow, traffic density, and vehicle speed, obtain a comprehensive matching score between traffic flow parameters and each reference traffic scenario; Step 1205: Determine the reference traffic scenario corresponding to the higher score among the at least two comprehensive matching scores as the target traffic scenario for the road area.

[0035] The matching score in steps 1201 to 1203 represents the degree of fit between a single parameter in the current real-time traffic flow parameters and the corresponding parameter range of a certain reference traffic scenario. The matching score calculates the distance or similarity between the real-time acquired traffic flow value and the preset boundary or center value of the reference traffic flow range for each reference traffic scenario, and maps this distance or similarity to the corresponding matching score. For example, the highest score is obtained if the real-time traffic flow falls completely within the flow range of a certain reference scenario; the further it deviates from the flow range, the lower the score.

[0036] The comprehensive matching score in this embodiment is the result of a comprehensive evaluation of the matching scores of traffic flow, traffic density, and vehicle speed. The comprehensive matching score in step 1204 can be achieved through weighted averaging, weighted summation, or a machine learning model. For example, in weighted averaging, different weights can be assigned to the importance of traffic scenario determination based on different parameters.

[0037] In step 1205, after obtaining the comprehensive matching scores of all reference traffic scenarios, the reference traffic scenario with the highest score is selected as the target traffic scenario that best represents the current real traffic conditions of the road by comparison.

[0038] Therefore, by introducing traffic flow, traffic density, and vehicle speed, and by combining sub-item matching scores with comprehensive matching scores, the traffic conditions of the current road area can be assessed more comprehensively and precisely. This effectively avoids misjudgments that may be caused by a single parameter or simple matching, and significantly improves the accuracy and comprehensiveness of the target traffic scenario determination.

[0039] Furthermore, regarding step 130, the grid division parameters in this embodiment refer to a set of set values ​​used to guide the spatial division of road areas. The grid division parameters may include, but are not limited to: grid side length range, geolocation coding precision level, and shape. The geolocation coding precision level refers to the level of detail used to generate the grid geolocation code. The geolocation coding precision level can be a preset level; for example, a higher geolocation coding precision level indicates higher precision. The geolocation coding precision level determines the length or complexity of the unique identifier of each grid cell, thereby affecting the granularity of the grid cell and the accuracy of positioning. For example, it can be set to specify the number of bits in the coding string. In this step, the specific values ​​of the grid division parameters can be adjusted according to the determined target traffic scenario to achieve refined management of the road area. The grid side length range refers to the range of allowed grid cell side lengths during grid division. The grid side length range can be preset according to the characteristics of the road area, the dynamic changes in traffic flow parameters, and the required level of detail in vehicle traffic guidance information.

[0040] The grid division result in this application refers to a series of geographic area units formed after spatially dividing the road area according to grid division parameters. Each grid unit represents a specific sub-area within the road area and is assigned a unique identifier. The grid unit is the smallest spatial granularity for pushing vehicle traffic guidance information and can be associated with traffic facility information within its coverage area, such as traffic lights. Traffic lights are traffic control devices installed at road intersections or specific road sections to indicate the passage of vehicles and pedestrians.

[0041] In some embodiments of this application, before step 130, a dynamic mapping relationship between a reference traffic scene, a reference geolocation coding precision level, and a reference grid side length interval can be pre-established. This dynamic mapping relationship can adaptively adjust the geolocation coding precision level according to traffic flow parameters, thereby dynamically changing the grid side length L, so that the grid division result is accurately adapted to the current traffic scene.

[0042] The dynamic mapping relationship between the reference geolocation coding precision level n and the reference raster side length L can be achieved by the following formula (1): L=5×2^(8-n)(1) Where n∈[6,8].

[0043] By adjusting the value of n, the grid side length that matches different traffic scenarios can be obtained.

[0044] For example, when the reference traffic scenario is a low-traffic nighttime scenario / highway ramp scenario, n=6, L=20-30 meters, the grid cells are appropriately enlarged. While covering a warning range of 200-300 meters, the number of unnecessary grid cells is reduced, making the delivery of warning information in low-traffic nighttime scenarios / highway ramp scenarios more efficient. When the reference traffic scenario is a smooth off-peak hour scenario / urban main road scenario, n=7, L=10-15 meters, providing a moderate warning coverage and matching accuracy. When the reference traffic scenario is a congested peak hour scenario / construction section scenario, when n=8, L=5-10 meters, the grid cells are refined and reduced, which can accurately match the complex deployment needs of temporary traffic lights, lane subdivision, etc., and effectively avoid matching confusion between multiple vehicles and multiple traffic lights.

[0045] Thus, a dynamic adjustment mechanism effectively balances matching accuracy and computational efficiency. It eliminates the need for a uniformly dense grid to avoid wasting computational resources, and also avoids using excessively large grids to prevent matching ambiguity. Verification through multiple scenarios shows that compared to a fixed grid scheme, the computational resource consumption of the dynamically adjusted scheme is reduced by approximately 32%. Simultaneously, because the grid side length is highly adapted to real-time traffic flow conditions, the spatial matching error between traffic lights and vehicles can be controlled within 0.5 meters, compared to the matching error of over 1.2 meters caused by boundary effects in the fixed grid scheme, resulting in an improvement in matching accuracy of approximately 58%.

[0046] In some embodiments of this application, in order to dynamically and precisely determine the grid division parameters according to the target traffic scene and ensure that the grid division results can effectively support subsequent vehicle positioning and information push, the grid division parameters include the geolocation coding accuracy level and the grid side length interval, and the grid division results also include the grid geolocation coding of each grid unit; based on this, such as Figure 3 As shown, step 130 above may include steps 1301 to 1303.

[0047] Step 1301: Determine the target grid side length corresponding to the traffic flow parameters based on the grid side length interval corresponding to the target traffic scene.

[0048] The grid side length interval refers to the allowable range of grid cell side lengths for a specific target traffic scenario. For example, the grid side length interval for low-flow nighttime / highway ramp scenarios is relatively large, ranging from 20 to 30 meters, to ensure sufficient early warning coverage; the grid side length interval for smooth off-peak / urban arterial road scenarios is moderate, ranging from 10 to 15 meters; and the grid side length interval for congested peak-peak / construction road scenarios is relatively small, ranging from 5 to 10 meters, to avoid prematurely pushing invalid information. The target grid side length refers to the specific side length value ultimately determined from the grid side length interval and used for actual grid division under the current traffic flow parameters.

[0049] In one example, a mapping table between traffic flow parameters and grid side lengths for a target traffic scenario can be pre-built. After obtaining real-time traffic flow parameters, the corresponding target grid side length can be directly looked up and determined from this mapping table.

[0050] In another example, the grid side length interval corresponding to the target traffic scene can be pre-divided into n reference sub-intervals, each reference sub-interval being associated with a grid side length value. When determining the target grid side length, first, the target sub-interval matching the current traffic flow parameters is determined from the n reference sub-intervals, and then the grid side length value associated with that target sub-interval is determined as the target grid side length.

[0051] In another example, a pre-defined function can be used to calculate the grid side length, with traffic flow parameters as the independent variable. Real-time traffic flow parameters are input into this function, and the target grid side length is calculated and output.

[0052] Step 1302: Divide the road area into grids according to the target grid side length to obtain m grid cells.

[0053] In this step, after determining the target grid side length, the road area can be gridded based on a geographic coordinate system, starting from a certain starting point. The grid is then divided using the target grid side length as the basic unit of division. Grid cells are generated one by one according to the target grid side length until the entire road area is covered. Each grid cell has the same size, which is the square of the target grid side length. m is a positive integer greater than 2, and its specific value depends on the relative size of the road area and the target grid side length. The larger the target grid side length, the smaller m is; conversely, the smaller the target grid side length, the larger m is.

[0054] Step 1303: Generate the raster geolocation code for each raster unit based on the geolocation coding precision level and the geolocation information of each raster unit.

[0055] Raster geolocation coding is a geographically significant identifier that uniquely identifies each raster cell. It accurately represents the location of a raster cell in geospatial space and can be used for rapid retrieval, location, and association with other information.

[0056] In this step, the latitude and longitude coordinates of the center point or boundary vertex of each grid cell can be obtained as geographic location information. Then, according to the preset geographic location coding precision level, a preset coding algorithm, such as the Geohash algorithm, is used to encode and convert the geographic location information to generate a grid geographic location code that corresponds one-to-one with each grid cell, such as wtw3u7e.

[0057] Therefore, by dynamically and adaptively determining the geolocation coding accuracy level and target raster side length interval through real-time traffic scenes and traffic flow parameters in the road area, the raster division process becomes more flexible and adaptable, ensuring that the granularity of the raster unit matches the current traffic conditions. Simultaneously, generating a unique raster geolocation code for each raster unit significantly improves the identification efficiency and positioning accuracy of the raster unit, enabling vehicle traffic guidance information to more accurately reflect local traffic conditions and enhancing the effectiveness of vehicle traffic guidance information.

[0058] In some embodiments of this application, after the grid division is completed and before step 140 is executed, a step of associating and binding traffic light and lane information for each divided grid unit may be included.

[0059] Specifically, for each of the m grid cells obtained, the traffic light groups included or controlled within the geographical area of ​​that grid cell are determined. These traffic light groups include fixed traffic lights and temporary traffic lights, such as mobile traffic lights temporarily deployed in construction sections. Simultaneously, lane information within the geographical area of ​​that grid cell is acquired, including lane number, lane direction of travel, and lane type, such as straight lane, left-turn lane, right-turn lane, or bus lane.

[0060] Based on this, a binding relationship between lanes and traffic lights is established using the NEMA ring grid phase structure. The NEMA ring grid phase structure is a standardized traffic signal control phase model that, by defining the correspondence between traffic light phases and lane travel directions, clearly identifies which phase of which traffic light controls each lane. For example, a straight-ahead lane is bound to a straight-ahead phase traffic light, a left-turn lane is bound to a dedicated left-turn phase traffic light, and a right-turn lane is bound to a dedicated right-turn phase traffic light.

[0061] After the above binding is completed, the binding information is associated with and stored in relation to the grid geolocation code of the grid unit. That is, each grid unit not only contains its spatial location and extent information, but also associates and stores information about the traffic light groups, lanes, and the binding relationships between lanes and traffic lights within that grid unit. Using the grid geolocation code as a spatial index, the traffic control facility configuration corresponding to any grid unit can be quickly retrieved.

[0062] In this way, when a vehicle is located to a specific grid cell, the cloud control platform can not only obtain the spatial position of that grid cell, but also directly obtain the status of the traffic lights associated with that grid cell and the lane-level traffic rules, providing a complete data foundation for subsequently generating precise lane-level guidance information. For example, when pushing information in the nearby area, the system can directly provide lane-level guidance information such as "Lane 2, red light countdown 5 seconds, prepare to stop," based on the pre-established binding relationship between the lane and the corresponding traffic light.

[0063] In some embodiments of this application, in order to accurately select the target traffic light most relevant to the current vehicle traffic guidance from the traffic lights associated with the target grid unit, and to avoid pushing inaccurate or redundant vehicle traffic guidance information, before step 140 above, such as Figure 4 As shown, the vehicle traffic guidance information determination method provided in this application embodiment may further include steps 1501 to 1502.

[0064] Step 1501: When the number of traffic lights associated with the target grid cell is at least two, obtain the target traffic light filtering rules associated with the target traffic scene based on the association between the reference traffic scene and the reference traffic light filtering rules.

[0065] The reference traffic light selection rule is a pre-defined logic or algorithm for different reference traffic scenarios, used to guide the selection of a target traffic light from multiple traffic lights. The reference traffic light selection rule can be determined based on factors such as the traffic light's geographical location, control direction, priority, historical data, or real-time traffic conditions.

[0066] The association relationships in this application embodiment include a one-to-one or many-to-one mapping relationship between reference traffic scenarios and reference traffic light selection rules. These association relationships can be implemented using lookup tables, decision tree models, expert system rule bases, or machine learning models. The target traffic light selection rule is a specific target traffic light selection rule that is dynamically selected from preset reference traffic light selection rules based on the target traffic scenario of the current road area, and is the most suitable for the current traffic conditions.

[0067] Step 1502: Select target traffic lights from at least two traffic lights according to the target traffic light selection rules.

[0068] In this step, target traffic light filtering rules can be applied to at least two traffic lights associated with the target grid cell to identify one or more traffic lights that best meet the current vehicle traffic guidance requirements.

[0069] In one example, the target traffic light selection rule associated with an urban main road scene can employ a weighted priority algorithm. Specifically, the priority score for each candidate traffic light can be calculated using the following formula (2): P=0.4×(1 / D)+0.3×(1 / v)+0.3×R(2) Where D is the distance between the vehicle's position and the stop line associated with the traffic light, v is the vehicle's current speed, and R is the traffic light priority level, with a value ranging from 0 to 7.

[0070] In this way, the P-value is calculated for each traffic light in the candidate traffic light set C, and the traffic light with the largest P-value is selected as the target traffic light. This weighted priority algorithm comprehensively considers three dimensions: distance, speed, and the inherent priority of the traffic light, ensuring that the selected target traffic light can optimally match the traffic demand of the city's main roads.

[0071] In another example, the target traffic light filtering rule associated with a construction section scene can prioritize identifying grid cells G containing temporary traffic lights. t The system matches vehicles based on spatial and heading constraints. Specifically, it can select vehicles that are no more than 300 meters away from temporary traffic lights and whose heading angle differs from the direction controlled by the temporary traffic light by no more than 30°, and push temporary traffic light warning information to these vehicles. This ensures accurate matching of the control range of temporary traffic lights in construction sections and avoids pushing invalid warning information to irrelevant vehicles.

[0072] In another example, the target traffic light filtering rule associated with the highway ramp scene can reduce the warning matching range to 200 meters, and set the fan-shaped search angle to θ±45° with the vehicle's direction of travel as the central axis. Furthermore, ramp-specific traffic lights can be matched using the following formula (3): D=200×(1-k / K0)(3) Where D is the matching distance, k is the ramp curvature, and K0 is the reference curvature, with a value of 0.02m. -1 .

[0073] This fully considers the geometric characteristics of high-speed ramps and vehicle driving characteristics, ensuring high-precision matching within a limited warning range.

[0074] Therefore, by accurately selecting the most relevant target traffic lights from multiple traffic lights based on real-time traffic conditions and preset target traffic light filtering rules associated with the target traffic scenario, the accuracy and relevance of vehicle traffic guidance information are significantly improved, avoiding inaccurate or redundant vehicle traffic guidance information caused by improper selection of traffic lights.

[0075] In some embodiments of this application, before step 1501 above, a step of obtaining the status information of at least two traffic lights is further included, which may specifically include: The real-time data of at least two traffic lights within the corresponding area of ​​the target grid cell are dynamically weighted and fused to generate fused traffic light status information, which is then aggregated to form a candidate traffic light set. This dynamic weighted fusion process specifically includes the following steps: First, calculate the data quality indicators for each traffic light. These indicators include data integrity, data timeliness, and data stability. Among these, data integrity indicator C... i The calculation method is the ratio of the number of valid fields to the total number of fields. The total number of fields includes six key fields such as light status, countdown, and timing scheme. The total number of fields is used to measure the completeness of the data fields for a single traffic light. Data timeliness index T i This can be achieved using the following formula (4): T i =1-|t-t0| / 3(4) Where t is the data acquisition time and t0 is the current processing time.

[0076] It is worth noting here that the maximum effective window T max The time limit is set to 3 seconds. If |t-t0| exceeds 3 seconds, the data is considered to have expired.

[0077] Data stability index S i The calculation method is S i =1 - Data fluctuation amplitude in the past 10 minutes, data stability index S i It is used to measure the degree of fluctuation of traffic light data within a recent time window; the smaller the fluctuation, the higher the stability.

[0078] Secondly, the comprehensive weight of each traffic light can be calculated based on the various data quality indicators using the following formula (5): W i =0.3×C i +0.4×T i +0.3×S i (5) Among them, data integrity index C i The weighting coefficient is 0.3, and the data timeliness index T iThe weighting coefficient is 0.4, and the data stability index S i The weighting factor is 0.3.

[0079] Furthermore, based on the comprehensive weight of each traffic light, the countdown data can be weighted and fused using the following formula (6): T=Σ(W i ×T i ) / ΣW i (6) Where T represents the merged countdown data. In this way, by using a comprehensive weight as a coefficient to perform a weighted average of the countdown data of each traffic light, the interference of abnormal data from individual traffic lights on the overall result can be effectively suppressed, thereby improving the accuracy and robustness of the countdown data.

[0080] Then, the data of all traffic lights within the corresponding area of ​​the target grid cell are aggregated to form a candidate set C = {C1, C2, ..., C}. m}, where m is the number of candidate traffic lights.

[0081] In this way, by dynamically weighting and fusing traffic light data, the problems of diverse sources and inconsistent quality of traffic light data in traditional systems can be effectively solved. Through comprehensive quantitative evaluation and weighted fusion of data integrity, timeliness and stability, incomplete, unreliable, or volatile data is automatically filtered out, ensuring that the traffic light status information input to the subsequent screening process is accurate and reliable, and providing high-quality data support for improving the accuracy of vehicle traffic guidance information.

[0082] Next, regarding step 140, the vehicle status information in this embodiment refers to real-time data of the vehicle while it is driving on the road, which may include, but is not limited to: vehicle position, vehicle speed, acceleration, heading angle, lane number, and On-Board Unit (OBU) data. The vehicle position can be represented by the vehicle's latitude and longitude. The OBU refers to a communication and computing device installed on the vehicle, used to collect vehicle positioning data, with an output or refresh frequency of at least 10 times per second, and to obtain vehicle status information, enabling data interaction with roadside equipment and the cloud control platform.

[0083] In this embodiment, the target grid cell refers to a grid cell related to the vehicle's current position and expected travel path. The target grid cell can be the grid cell the vehicle is currently in, or it can be the grid cell the vehicle is about to enter. The target traffic light refers to a traffic light associated with the target grid cell and that has a direct impact on vehicle passage.

[0084] The vehicle traffic guidance information in this application refers to suggestions or instructions pushed to vehicles to assist drivers or autonomous driving systems in safe and efficient passage. Vehicle traffic guidance information may include, but is not limited to: suggested speed, recommended lane, real-time status of the target traffic light, and predicted changes in the target traffic light.

[0085] In some embodiments of this application, prior to step 140, the method for determining vehicle traffic guidance information may further include a step of acquiring and preprocessing vehicle status information, specifically including: Step 1: Real-time consumption of vehicle data based on message queues. Specifically, subscribe to the topic in the high-concurrency distributed message queue Kafka used for transmitting basic vehicle messages, and consume Basic SafetyMessages (BSMs) in real time, with a push frequency of no less than 10 Hz. The consumption configuration can be set to a pull interval of no more than 50 milliseconds, a single batch pull of no more than 100 records, automatic retrying upon consumption failure (maximum of 3 retries), and an exponential backoff strategy using retry intervals of 10 milliseconds, 30 milliseconds, and 50 milliseconds. Extract core fields from the consumed data, including vehicle identifier, longitude, latitude, vehicle speed, heading angle, lane number, on-board unit device number, and timestamp. Latitude and longitude are retained to 6 decimal places, and the timestamp precision is 1 millisecond.

[0086] Step two involves data cleaning and caching based on scheduled tasks. Specifically, a periodic scheduled task is initiated to process the batch-fetched raw data. The default execution cycle is 100 milliseconds, which is automatically shortened to 50 milliseconds when the data volume suddenly increases to 1000 records per second or more. The data cleaning process may include: removing duplicate data with the same vehicle identifier and timestamp; and removing expired data where the difference between the current time and the data timestamp exceeds 5 seconds. The cleaned data is then written to a remote terminal dictionary service cluster for caching.

[0087] Step 3: Provide a standardized vehicle status query interface. Specifically, deploy a descriptive status transmission interface that supports Hypertext Transfer Protocol (HTTP) and Hypertext Transfer Security Protocol (HTTP). The response time for a single vehicle identifier query should not exceed 50 milliseconds, and the response time for a batch query of no more than 100 vehicles should not exceed 200 milliseconds, returning data in a lightweight data exchange format. When the interface call volume reaches 1000 queries per second, a degradation strategy will be automatically triggered to prioritize the availability of the core grid query function.

[0088] The data access and preprocessing process in steps one through three provides efficient data support for subsequent multi-grid combination queries and early warning matching. For example, when the system constructs an early warning zone of 200 to 300 meters, it needs to batch query the status information of all vehicles within a certain geohash grid to quickly filter out target vehicles that are "200 to 300 meters away from the traffic light and have a heading angle difference of no more than 60 degrees". In one example, at an intersection on a main urban road, the traffic light status in the grid with the geohash code wtw3u7e changes. The multi-grid combination module obtains the real-time location and speed of 86 vehicles in that grid through the batch query interface, and filters out 62 target vehicles for early warning push based on the early warning conditions.

[0089] Step four: Validation of vehicle status data. Specifically, in multiple consecutive frames of data, data is deemed invalid and discarded if any of the following anomalies exist: a position difference greater than 5 meters, indicating a sudden change in vehicle position that does not conform to the laws of physical motion; a speed change greater than 20 kilometers per hour, indicating an instantaneous change in vehicle speed that does not conform to actual driving patterns, possibly caused by sensor malfunction; a heading angle change greater than 30 degrees, indicating a significant change in driving direction that does not conform to the physical characteristics of vehicle steering. Only high-quality datasets that pass the validation can be used as vehicle status information in step 140 to generate vehicle traffic guidance information.

[0090] Furthermore, following step four above, a multi-source positioning improved extended Kalman filter fusion algorithm can be used to fuse positioning data from four sources: the global navigation satellite system, the inertial measurement unit, the lidar, and the vehicle-mounted unit, outputting high-frequency, high-precision vehicle positioning results. In practical implementation, a state equation as shown in formula (7) can be constructed: X k =A×X k-1 +B×u k-1 +w k-1 (7) Wherein, the state vector X k It includes multi-dimensional motion parameters such as position, velocity, acceleration, and attitude angle.

[0091] Construct the observation equation as shown in equation (8): Z k =H×X k +v k (8) Wherein, the observation vector Z k This includes multi-source horizontal and vertical coordinate data collected by multiple sensors, including the Global Navigation Satellite System, Inertial Measurement Unit, LiDAR, and vehicle-mounted unit. The weights of each sensor are optimized using the observation noise covariance matrix. For example, the weight of the vehicle-mounted unit data is set to 0.3.

[0092] Experiments have verified that the improved extended Kalman filter fusion algorithm for multi-source positioning described above can output high-quality vehicle positioning results with a frequency of no less than 10Hz and a positioning accuracy of no more than 0.3 meters, effectively correcting the vehicle's positional deviation within the grid cell. This multi-source positioning fusion scheme overcomes the performance limitations of a single sensor, achieving high-precision, highly stable, and scenario-adaptive positioning output, providing direct support for accurate traffic light matching and early warning information delivery. Specifically, this is reflected in the following four aspects: First, positioning accuracy is significantly improved, effectively correcting grid matching deviations. Specifically, by fusing data from four sources—Global Navigation Satellite System, Inertial Measurement Unit, LiDAR, and onboard sensors—and optimizing sensor weight allocation, positioning accuracy is improved to within 0.3 meters, an improvement of approximately 70% compared to single-source positioning solutions. Based on this, it can accurately correct vehicle position deviations within grid cells, ensuring that the matching error when a vehicle crosses Geohash boundary grids does not exceed 0.5 meters, providing a data foundation for lane-level precise guidance.

[0093] Secondly, it enhances scenario adaptability and addresses positioning challenges in special scenarios. Specifically, through a multi-source complementary mechanism, it effectively addresses the inherent limitations of single sensors. For example, when the Global Navigation Satellite System (GNSS) signal fails in tunnels or severely obstructed scenarios, the inertial measurement unit (INS) and lidar are fused for positioning to compensate, ensuring that positioning accuracy within tunnels does not significantly decrease. When severe weather conditions such as heavy rain or dense fog cause lidar data fluctuations, the vehicle-mounted unit and INS jointly provide a stable positioning reference. This allows for comprehensive adaptation to diverse scenarios such as urban main roads, highway ramps, and tunnels. Tests have verified that the positioning success rate in tunnel scenarios can reach over 99.5%, effectively solving the problem of positioning failure of single vehicle positioning solutions in special scenarios.

[0094] Third, it enhances data reliability and automatically filters out abnormal interference. The multi-source positioning improved extended Kalman filter fusion algorithm optimizes the observation noise covariance matrix. For example, by setting the noise variance of the vehicle unit data to 0.0025 and the global navigation satellite system (GNSS) data to 0.01, it can automatically filter out transient interference from sensors, such as GNSS signal jumps or LiDAR misidentification. Simultaneously, the multi-source data cross-validation mechanism effectively eliminates invalid data from a single sensor, ensuring the continuity and stability of the positioning output. The positioning data validity rate can reach over 99.8%, providing highly reliable input for the accurate calculation of early warning lead time.

[0095] Fourth, it fully meets real-time requirements and is compatible with high-level autonomous driving. This fusion positioning scheme is highly compatible with the real-time requirements of the multi-grid combination query and scene-based matching steps proposed in the embodiments of this application. It can ensure that the end-to-end latency from data acquisition to positioning result output does not exceed 300 milliseconds, which fully meets the strict real-time requirements of L3 and above autonomous driving systems.

[0096] In some embodiments of this application, the grid division result also includes the grid geographic location code of each grid cell, and the vehicle status information includes the vehicle location; before step 140 above, such as Figure 5 As shown, the above method for determining vehicle traffic guidance information may also include steps 1601 to 1603.

[0097] Step 1601: Based on the vehicle's position, determine the first target grid cell where the vehicle is located from m grid cells. The vehicle position refers to the position where the vehicle is detected to have entered the road area.

[0098] In this step, the vehicle's location can be compared one by one with the geographic coverage of the pre-divided m grid cells to determine which grid cell the vehicle currently falls within and identify it as the first target grid cell. Alternatively, the vehicle's real-time latitude and longitude can be encoded according to a preset geolocation coding precision level to generate a geohash code with target precision matching the current target traffic scene. This geohash code is then precisely matched with the grid geolocation codes of each grid cell generated in step 1303, and the grid cell with matching codes is identified as the first target grid cell. For example, if the vehicle's real-time latitude and longitude are x=120.315689 and y=31.456783, its geohash code with target precision n=7 is "wtw3u7e", which serves as the geohash code corresponding to the vehicle's location. This geohash code is then compared with the grid geolocation code corresponding to each of the m grid cells to obtain the first target grid cell.

[0099] Step 1602: Based on the grid geographic location code of the first target grid cell, determine the second target grid cell associated with the first target grid cell from m grid cells. The second target grid cell is located ahead of the vehicle's driving path.

[0100] In this step, the grid geographic location code of the first target grid cell can be used to quickly find the codes of grid cells that are geographically adjacent to it through coding rules or a preset adjacency table. Then, combined with the vehicle's current driving direction, for example, by inferring from the vehicle's heading angle or historical trajectory, the grid cells located ahead of the vehicle's driving path are selected from these adjacent grid cells as the second target grid cell.

[0101] Step 1603: The first target grid cell and the second target grid cell are determined as target grid cells.

[0102] In this step, by combining the grid cells of the vehicle's current position and the position of the vehicle ahead, a more forward-looking and complete target grid cell is formed, which can provide more comprehensive and timely traffic guidance information.

[0103] Therefore, by using the first target grid cell where the vehicle is currently located and the second target grid cell ahead of its driving path as the target grid cell, the cloud control platform can acquire and analyze the traffic conditions and traffic light status in the area ahead of the vehicle earlier. This allows for the generation and delivery of more predictive and instructive vehicle traffic guidance information, avoiding the guidance lag problem that may occur if only the current location information is used. This significantly improves the timeliness and effectiveness of traffic guidance information, helps drivers make decisions in advance, and improves driving safety and traffic efficiency.

[0104] In some embodiments of this application, the raster geolocation code includes a prefix string and extended characters. By dividing the raster geolocation code into a prefix string and extended characters, a hierarchical representation of geolocation can be achieved. The prefix string represents a larger area, while the extended characters further refine the location within that area. This hierarchical structure facilitates rapid location and filtering of relevant raster cells. If n=7, the raster geolocation code is wtw3u7e, the prefix string is wtw3u7, and the extended character is e. The prefix string represents a parent raster region that is one level higher than the first target raster cell and has a larger geographical range. Vehicle status information includes the vehicle heading angle; based on this, such as Figure 6 As shown, step 1602 may specifically include steps 16021 to 16024.

[0105] Step 16021: Generate at least two reference raster geolocation codes based on the prefix string of the first target raster cell, wherein the prefix strings of the reference raster geolocation codes are adjacent to the prefix strings of the first target raster cell.

[0106] In this step, the prefix string "wtw3u7e" of the raster geolocation code of the first target raster cell can be extracted, for example, "wtw3u7". Then, at least two adjacent prefix strings geographically adjacent to this prefix string are enumerated, such as "wtw3u6" and "wtw3u8". Each adjacent prefix string represents an adjacent parent geographic region that directly borders the parent region of the first target raster cell. Next, the raster geolocation codes of all child raster cells corresponding to each adjacent prefix string at the current coding precision level are generated as the reference raster geolocation codes. Each reference raster geolocation code can correspond to one or more first candidate raster cells. For example, when the coding precision level n=7, each 6-bit prefix string corresponds to 32 7-bit raster cells. By enumerating 8 adjacent prefix strings, the raster geolocation codes corresponding to a total of 256 raster cells can be determined as reference raster geolocation codes.

[0107] Step 16022: Determine the first candidate raster cell from the m raster cells that corresponds to each of the geolocation codes of at least two reference raster geolocation codes.

[0108] In this step, after a set of reference raster geolocation codes are generated, the cloud control platform will search for all raster cells that match the reference raster geolocation codes from the pre-divided m raster cells based on these reference raster geolocation codes.

[0109] In this way, all raster cells whose parent codes are geographically adjacent to the raster geolocation code of the first target raster cell are included in the initial candidate raster cells. Even if the complete raster geolocation codes of these initial candidate raster cells are not adjacent to the raster geolocation code of the first target raster cell in terms of coding value, they are geographically adjacent. This fundamentally solves the problem of missing neighboring raster cells caused by coding boundary jumps in the Geohash scheme of related technologies, eliminates the boundary effect, ensures the continuity and integrity of the warning area in geospatial space, and avoids the occurrence of warning blind spots.

[0110] Step 16023: Based on the spherical distance between the center position of each first candidate grid cell and the vehicle position, and the difference in heading angle between the preset heading angle corresponding to each first candidate grid cell and the vehicle heading angle, select second candidate grid cells that meet preset conditions from at least two first candidate grid cells. The preset conditions include that the spherical distance is within the reference spherical distance range and the heading angle difference is less than or equal to the preset heading angle difference.

[0111] The spherical distance measures the proximity of candidate grid cells to the vehicle's current position, ensuring that the selected grid cells are physically reachable. The heading angle difference is used to determine the consistency between the candidate grid cell's preset travel direction and the vehicle's current heading angle, thus excluding grid cells that do not match the vehicle's travel intention. Preset conditions limit the reasonable range of distance and heading angle differences to ensure the accuracy of the selection results. For example, the heading angle difference can be calculated using a vector dot product or the absolute value of the angle difference, such as |θ-θ i In this step, by combining two dimensions—spatial distance and vehicle direction of travel—the initially selected first candidate grid cells can be further refined. The reference spherical distance range can be [200, 300], and the preset heading angle difference can be 60°.

[0112] For example, the spherical distance between the center position of the first candidate grid cell and the vehicle position can be achieved by the following formula (9): D = 2R × arcsin [sin 2 ((lat2-lat1) / 2)+cos(lat1)×cos(lat2)×sin 2 ((lon2-lon1) / 2)])(9) Where R = Earth's average radius (6371 km); (lat1, lon1) = vehicle's latitude and longitude; (lat2, lon2) = grid cell center's latitude and longitude.

[0113] Step 16024: Perform grid continuity verification on the second candidate grid cell and the first target grid cell, and determine the second target grid cell related to the first target grid cell based on the grid continuity verification result.

[0114] In this step, grid continuity verification ensures that there is a physically traversable connection between the selected second candidate grid cell and the first target grid cell. Even if the second candidate grid cell is selected through spherical distance and heading angle, it is still necessary to verify whether they are truly adjacent or connected in the road topology. For example, the verification can check whether two grid cells share a complete edge or a vertex, or whether there is a traversable road connection. This eliminates grid cells that are geographically close but not actually directly traversable, thereby improving the accuracy and reliability of the determination of the second target grid cell.

[0115] It should be noted that, in order to reduce unnecessary consumption of computing resources and improve the execution efficiency of raster continuity verification, continuity verification can be performed only on raster units in the second candidate raster units whose raster geographic location coding prefix matching degree with the first target raster unit is lower than a preset threshold, while raster units whose prefix matching degree reaches the preset threshold can be exempted from verification.

[0116] Prefix matching degree refers to the number of consecutive characters that are identical from the first character in the geolocation codes of two raster cells. The preset threshold can be set to the current raster geolocation code length n minus 1, i.e., n-1 bits. Taking n=7 as an example, when the first 6 bits of the Geohash codes of two raster cells are identical, it indicates that they belong to the same parent raster region and have a natural containment or close adjacency relationship in geographic space. Their spatial continuity is fully guaranteed, and no additional continuity check is needed. However, when the prefix matching degree of the Geohash codes of two raster cells is less than 6 bits, it indicates that they span different parent raster regions. Although they may be adjacent in code values, there may be a false proximity in geographic space. Therefore, raster continuity check is required. By checking whether they share boundaries or vertices, their spatial continuity is ultimately determined. In this way, while ensuring that the warning area is continuous without breaks, the computational overhead of raster continuity check can be effectively reduced, further improving the real-time response performance of the cloud control platform.

[0117] Therefore, by introducing a hierarchical representation of the prefix string and extended characters of the grid geolocation code, combined with vehicle heading angle information, and using spherical distance and heading angle difference for multi-dimensional filtering, as well as the final grid continuity verification, the second target grid cell ahead of the vehicle's driving path can be identified more accurately. This significantly improves the accuracy of predicting the vehicle's future driving intentions and avoids misjudgments caused by simple adjacency relationships in complex road conditions, thus providing more accurate and effective vehicle traffic guidance information.

[0118] In some embodiments of this application, the Geohash algorithm filters neighboring rasters through prefix matching. However, adjacent coded prefixes do not necessarily mean geographical proximity, especially for rasters that cross parent coded boundaries. For example, the parent raster of the central raster is "wtw3u7," and some of its neighboring child rasters with the parent coded "wtw3u6" may have matching coded prefixes, but their actual geographical distance may exceed 300 meters, constituting pseudo-neighborhood and needing to be filtered out. Based on this, as... Figure 7 As shown, step 16024 may specifically include steps 160241 and 160242.

[0119] Step 160241: If the grid continuity verification result is used to characterize that the second candidate grid cell and the first target grid cell share a complete edge or a vertex, determine the second target grid cell associated with the first target grid cell based on the second candidate grid cell.

[0120] In this step, the grid continuity verification result is used to characterize whether the second candidate grid cell and the first target grid cell share a complete edge or a vertex. This means that the two grid cells are geographically closely connected; for example, there is a common boundary line or a common intersection point between the second candidate grid cell and the first target grid cell. This can be determined by comparing the geographic coordinate ranges of the two grid cells to determine whether there is an overlap or adjacent boundary. For example, if the coordinate ranges of a certain edge of the two grid cells are completely consistent, then they share a complete edge. Alternatively, the characteristics of grid geolocation encoding can also be used for judgment. After confirming spatial continuity, the second target grid cell associated with the first target grid cell is determined based on the second candidate grid cell. That is, the second candidate grid cell that meets the conditions is directly confirmed as the target grid cell in front of the vehicle, indicating that the candidate grid cell is a valid and feasible extension of the driving path. After confirming that the grid continuity verification is passed, the cloud control platform can directly determine the currently selected second candidate grid cell as the second target grid cell.

[0121] Step 160242: If the grid continuity verification result is used to characterize that the second candidate grid cell and the first target grid cell do not share a complete edge or a vertex, at least two reference grid geolocation codes are regenerated according to the prefix string of the first target grid cell until a preset number of regenerations is reached, wherein the regenerated at least two reference grid geolocation codes are different from the at least two reference grid geolocation codes.

[0122] The preset number of regenerations can be an integer value, such as 3 times, which means that a maximum of 3 different search strategies can be tried.

[0123] In this step, the raster continuity check result is used to characterize that the second candidate raster cell and the first target raster cell do not share a complete edge or a vertex. This means that the second candidate raster cell and the first target raster cell are not closely connected in geospatial space; there may be gaps, they may be separated by other raster cells, or they may simply be far apart and not directly adjacent. When this occurs, at least two reference raster geolocation codes are regenerated based on the prefix string of the first target raster cell, until a preset number of regenerations is reached. This provides a mechanism for backtracking and re-searching when the second candidate raster cell is not continuous in the initial screening, in order to find a more suitable second target raster cell.

[0124] In this embodiment, the search range can be expanded or adjusted by regenerating the reference raster geolocation code. For example, when generating the reference raster geolocation code for the first time, only codes directly adjacent to the extended characters of the first target raster unit may be considered. During regeneration, codes secondarily adjacent to the extended characters of the first target raster unit may be considered, or new reference codes may be generated within a larger neighborhood. The preset number of regenerations can be 3, indicating that a maximum of 3 different search strategies can be tried. The regenerated at least two reference raster geolocation codes are different from the original at least two reference raster geolocation codes, ensuring that the search range or direction is different each time the reference code is regenerated, avoiding repeated searches of the same area, and improving search efficiency and success rate.

[0125] Therefore, when determining the second target grid cell ahead of the vehicle, a grid continuity check is performed. If the initially selected second candidate grid cell is geographically discontinuous with the first target grid cell, a reference grid geolocation code can be regenerated and the selection process repeated until a continuous grid cell is found or a preset number of searches is reached. This effectively avoids path determination errors caused by discontinuous grid cells and significantly improves the accuracy of determining the second target grid cell.

[0126] In some embodiments of this application, even if the second candidate grid cell and the first target grid cell are geometrically continuous in practical applications, it is still necessary to consider the precise matching degree between the center position of the second candidate grid cell and the current position of the vehicle, so as to ensure that the determined second target grid cell can more accurately reflect the vehicle's driving path and immediate needs, thereby providing more accurate traffic guidance information. Based on this, the above step 160241 may specifically include: if the planar distance between the center position of the second candidate grid cell and the vehicle position is less than or equal to a preset planar distance value, the second candidate grid cell is determined as the second target grid cell related to the first target grid cell; if the planar distance between the center position of the second candidate grid cell and the vehicle position is greater than the preset planar distance value, the center position of the second candidate grid cell is adjusted according to the reference adjustment direction to obtain the adjusted center position; the reference adjustment direction is the direction towards the vehicle position; the planar distance between the center position of the second candidate grid cell and the vehicle position is recalculated based on the adjusted center position until the planar distance between the adjusted center position of the second candidate grid cell and the vehicle position is less than or equal to the preset planar distance value.

[0127] The planar distance between the center position of the second candidate grid cell and the vehicle position refers to the straight-line distance between the geometric center point of the second candidate grid cell and the current position point of the vehicle on a two-dimensional plane.

[0128] The preset planar distance value in this embodiment is a pre-set threshold value used to determine whether the proximity between the center position of the second candidate grid cell and the vehicle position meets the requirements. This preset planar distance value can be set according to factors such as the actual application scenario, road type, vehicle speed, and the average size of the grid cell. For example, in urban roads, to improve guidance accuracy, the preset planar distance value can be set smaller; while in scenarios such as highways, the preset planar distance value can be appropriately widened. The preset planar distance value can also be optimized and adjusted through actual test data or simulation. For example, the preset planar distance value can be 0.5 meters.

[0129] In this step, the planar distance value PD can be obtained using the following formula (10): PD [(lat2-lat1) 2 ×(111319.9m / °) 2 +(lon2-lon1) 2 ×(111319.9×cos(lat1)) 2 (10) Where lat1 and lon1 are the latitude and longitude of the vehicle, lat2 and lon1 are the latitude and longitude of the center of the corrected second candidate grid cell, and 111319.9 is the constant of the arc length per degree of the Earth's meridian, in meters per degree.

[0130] In this embodiment, the reference adjustment direction is used to indicate the direction for virtual adjustment of the center position of the second candidate grid cell, specifically pointing to the vehicle's position. This reference adjustment direction can be determined by calculating the vector pointing from the center position of the second candidate grid cell to the vehicle's current position. For example, if the vehicle is located northeast of the second candidate grid cell, then the reference adjustment direction is northeast.

[0131] In this embodiment, when the planar distance between the center position of the second candidate grid cell and the vehicle position is greater than 0.5, an iterative approximation method can be used. Each time, the cell moves a preset step size along the reference adjustment direction, gradually bringing the center position of the second candidate grid cell closer to the vehicle position. After adjusting the center position of the second candidate grid cell, the planar distance between the adjusted center position and the vehicle position needs to be calculated again using the above formula (10). Through repeated calculations, the effect of each center position adjustment can be evaluated and used as feedback for the iterative process, until the planar distance between the adjusted center position of the second candidate grid cell and the vehicle position is less than or equal to the preset planar distance value, at which point the iterative process stops. This ensures that the determined second target grid cell is sufficiently close to the vehicle position in space, thereby improving the accuracy of guidance.

[0132] If the vehicle is currently located within the first target grid cell, its position coordinates are (116.397, 39.909). After grid continuity verification, the center position coordinates of a second candidate grid cell are identified as (116.398, 39.910). At this time, the cloud control platform sets a preset planar distance value of 5 meters. First, the planar distance between the center position (116.398, 39.910) of the second candidate grid cell and the vehicle position (116.397, 39.909) is calculated using the above formula (10). If the calculation result is 3 meters, which is less than or equal to the preset planar distance value of 5 meters, the cloud control platform will directly determine the second candidate grid cell as the second target grid cell related to the first target grid cell. If the calculation result is 8 meters, which is greater than the preset planar distance value of 5 meters, the reference adjustment direction from the center position of the second candidate grid cell to the vehicle position will be determined. For example, with the reference adjustment direction pointing southwest, the center position of the second candidate grid cell is adjusted to (116.3975, 39.9095). The cloud control platform will recalculate the planar distance between the adjusted center position (116.3975, 39.9095) and the vehicle position (116.397, 39.909). If the calculated result is 4 meters, which is less than or equal to the preset planar distance value of 5 meters, the adjustment process stops, and the second candidate grid cell, with its adjusted virtual center position as the reference, is determined as the second target grid cell associated with the first target grid cell. If the calculated result is still greater than 5 meters, the adjustment and recalculation will continue along the southwest direction as the reference adjustment direction until the calculated result is less than or equal to 5 meters.

[0133] Therefore, by calculating the planar distance between the center position of the second candidate grid cell and the vehicle position, and combining iterative adjustment mechanism of the center position of the second candidate grid cell, it is ensured that the determined second target grid cell is spatially highly matched with the real-time position of the vehicle. This enables the vehicle traffic guidance information determined based on this to more accurately point to the area that the vehicle is about to enter, avoiding inaccurate guidance caused by slight deviations between the grid cell and the actual path of the vehicle, thereby significantly improving the accuracy and reliability of the vehicle traffic guidance information.

[0134] In some embodiments of this application, the target grid unit includes a first target grid unit and a second target grid unit. These first and second target grid units are two key areas used for segmented management and guidance of vehicle travel paths. They can be continuous or logically related, together constituting key nodes for vehicle travel within the road area. Vehicle status information includes first vehicle status information and second vehicle status information. The first status information corresponds to the state of the target traffic light when the vehicle enters the first target grid unit, and the second status information corresponds to the state of the target traffic light when the vehicle enters the second target grid unit. Vehicle traffic guidance information includes first vehicle traffic guidance information and second vehicle traffic guidance information. The number of second target grid units is at least one. Before executing step 140, a first target grid unit and at least one second target grid unit can be divided into different guidance areas based on the distance between the reference position of the first target grid unit and the reference boundary position associated with the target traffic light, and the distance between the reference position of each second target grid unit and the reference boundary position associated with the target traffic light. For example, it can be divided into three levels: the far zone, corresponding to a distance range of 250 meters to 300 meters; the middle zone, corresponding to a distance range of 150 meters to 250 meters; and the near zone, corresponding to a distance range of 0 meters to 150 meters.

[0135] Based on this, such as Figure 8 As shown, step 140 above may specifically include steps 1401 to 1405.

[0136] Step 1401: When a vehicle enters the area corresponding to the first target grid unit, first vehicle traffic guidance information is generated based on the vehicle's first vehicle status information, the first traffic guidance strategy information corresponding to the first target grid unit, and the first status information of the target traffic light. The first vehicle traffic guidance information is then pushed to the vehicle. The first traffic guidance strategy information is determined based on the distance between the reference position of the first target grid unit and the reference boundary position associated with the target traffic light.

[0137] The reference position of the first target grid cell refers to a benchmark point used to characterize the spatial position of the grid cell, which can be selected as the geometric center point, entry point, or the current actual position of the vehicle. The reference boundary position refers to a key location point in the traffic light control area, which can be selected as the stop line associated with the traffic light, the center line of the intersection, or the lane merging point. The distance between the reference position of the first target grid cell and the reference boundary position associated with the target traffic light can be calculated using the spherical distance formula described above. The first state information refers to the real-time state of the target traffic light when a vehicle enters the area corresponding to the first target grid cell, such as red light, green light, yellow light, or countdown, etc. The first state information can be obtained from the traffic signal control system.

[0138] In this step, the first warning lead time can be calculated based on the vehicle speed v1 and the first distance D1 in the first vehicle status information. The first warning lead time t a1 The calculation formula can be set as t a1 =D1 / v1×3.6+t0, where t0 is the basic reaction time, which can be set to 2 seconds. Simultaneously, upper and lower limits are set for the early warning lead time: t a1 No less than 3 seconds to ensure sufficient reaction time for the driver or autonomous driving system; a1 The time should not exceed 36 seconds to avoid premature information delivery leading to failure. This is based on the warning zone level of the first distance D1 and the first warning lead time t. a1 Determine the first passage guidance strategy information.

[0139] The first traffic guidance strategy information refers to the guidance rules and push content framework generated based on the relative spatial and temporal relationships between vehicles and traffic lights, which may specifically include any of the following: When the distance between the reference position of the first target grid cell and the reference boundary position associated with the target traffic light is within the far zone, the first traffic guidance strategy information is determined to be a far zone push strategy. The push content framework may include: distance to the intersection ahead, current traffic light color, and estimated arrival time. For example, "Intersection 300 meters ahead, traffic light status: green, estimated arrival time 12 seconds", frequency 1Hz.

[0140] When the distance between the reference position of the first target grid cell and the reference boundary position associated with the target traffic light is within the middle zone, the first traffic guidance strategy information is determined to be a middle zone push strategy. The push content framework may include the distance to the intersection ahead, the traffic light countdown, and the recommended speed. For example, "Intersection ahead 200 meters, green light countdown 25 seconds, recommended speed 35km / h", frequency 1Hz; When the distance between the reference position of the first target grid cell and the reference boundary position associated with the target traffic light is within the near zone, the first traffic guidance strategy information is determined to be a near zone push strategy. The push content framework may include lane number, traffic light countdown, and driving suggestions. For example, "Lane 2, red light countdown 5 seconds, prepare to stop," at a frequency of 1Hz.

[0141] Step 1402: When a vehicle enters the area corresponding to the second target grid unit, second vehicle traffic guidance information is generated based on the vehicle's second vehicle status information, the second traffic guidance strategy information corresponding to the second target grid unit, and the second status information of the target traffic light. The second vehicle traffic guidance information is then pushed to the vehicle. The second traffic guidance strategy information is determined based on the distance between the reference position of the second target grid unit and the reference boundary position associated with the target traffic light.

[0142] It should be noted that the specific implementation of determining the second traffic guidance strategy information and generating the second vehicle traffic guidance information in step 1402 is the same as that of determining the first traffic guidance strategy information and generating the first vehicle traffic guidance information in step 1401. The only difference is that the input data is replaced with the distance between the reference position of the second target grid cell and the reference boundary position associated with the target traffic light, the second vehicle status information, and the second light status information. Therefore, the relevant details can be referred to in step 1401, and will not be elaborated here.

[0143] Therefore, the embodiments of this application can provide phased and refined vehicle traffic guidance information based on the specific location and vehicle status of the vehicle at different stages of driving, as well as the real-time changes of the target traffic lights, effectively improving the accuracy and timeliness of vehicle traffic guidance information.

[0144] In some embodiments of this application, before performing the step 140 above to push vehicle traffic guidance information to the vehicle, the above vehicle traffic guidance information pushing method may further include determining a push mode for pushing vehicle traffic guidance information based on the vehicle's autonomous driving level and navigation map accuracy, and pushing vehicle traffic guidance information to the vehicle based on the push mode.

[0145] In this context, "push mode" refers to the granularity and presentation method of the information content used by the cloud control platform when sending vehicle traffic guidance information to the vehicle. Push modes can include, but are not limited to: lane-level guidance mode, map-based mode, and mapless mode. Lane-level guidance mode is suitable for scenarios where the autonomous driving level is L3 or higher and high-precision maps are available. Map-based mode is suitable for scenarios where the autonomous driving level is lower than L3 but an in-vehicle navigation map is available. Mapless mode is suitable for scenarios where neither high-precision maps nor standard navigation maps are available.

[0146] Therefore, by automatically switching the push mode based on the level of autonomous driving and the availability of high-precision maps, guidance information can be provided to vehicles of different automation levels, matching their perception and decision-making capabilities. For example, for low-level vehicles or scenarios with missing maps, basic warning prompts are provided to ensure the universality and accessibility of the information; for high-level autonomous vehicles and scenarios with complete maps, lane-level precise guidance is provided. This adaptive push mechanism effectively avoids the problems of information overload or insufficient information, improving the applicability of vehicle traffic guidance information and user experience.

[0147] In some embodiments of this application, the above-mentioned vehicle traffic guidance information push method may further include: when vehicle positioning data failure is detected, based on the historical valid state quantities before the positioning data failure, outputting the predicted value of the real-time vehicle state through a Kalman prediction model, and determining the predicted value as the vehicle state information used to generate vehicle traffic guidance information.

[0148] Specifically, the historical valid state quantities before the positioning data expires may include, but are not limited to: the complete state parameters of the last valid positioning frame, such as the vehicle's latitude and longitude, speed, acceleration, and heading angle; the state change trend of the last 5 frames of valid positioning data, such as the rate of change of speed and the rate of change of heading angle, used to calibrate the process noise parameters of the Kalman prediction model; and the system preset parameters, including the process noise covariance matrix Q and the observation noise covariance matrix shared with the improved extended Kalman filter algorithm. The process noise covariance matrix can be set as a diagonal matrix Q=diag([1e-4, 1e-4, 1e-3, 1e-3, 1e-2, 1e-2]), and the observation noise covariance matrix uses the preset values ​​corresponding to the aforementioned vehicle unit, global navigation satellite system, and lidar.

[0149] Thus, based on the aforementioned historical valid state quantities, the real-time vehicle state prediction values ​​output by the Kalman prediction model specifically include: predicting the vehicle position, i.e., the latitude and longitude of the vehicle at the current moment, with an accuracy of no more than 0.5 meters, and maintaining consistency with the matching error requirements of the boundary grid; predicting dynamic parameters, i.e., driving speed, acceleration, and heading angle, ensuring consistency with the physical motion laws of the vehicle and no sudden changes; and a state reliability index, i.e., the error variance of the prediction result, used to judge the effectiveness of the prediction, triggering a downgrade warning when the variance is greater than 1 meter.

[0150] It is worth noting that the input data of the Kalman prediction model is all taken from a high-quality dataset that has passed continuous frame verification before the positioning failure. In this way, the embodiments of this application can effectively fill the vehicle positioning gap window in the scenario of loss of global navigation satellite system signal or temporary sensor failure, and ensure the continuity and stability of vehicle traffic guidance information push.

[0151] The following example, taking the morning rush hour on a main urban road in a certain road area, illustrates the complete process of the vehicle traffic guidance information push method provided in this application embodiment.

[0152] Step 1: Traffic Flow Parameter Acquisition and Dynamic Grid Division. Real-time acquisition of traffic flow parameters for the road area. For example, traffic flow Q is 80 vehicles / minute, traffic density D is 25 vehicles / km, and vehicle speed V is 25 km / h. The cloud control platform matches these traffic flow parameters with the reference traffic flow parameter range of a predefined reference traffic scenario, identifying the current traffic scenario in the road area as a morning rush hour congestion scenario on an urban arterial road. Based on the grid division parameters corresponding to this morning rush hour congestion scenario on an urban arterial road, the geolocation coding precision level is dynamically adjusted, i.e., the Geohash coding length n is 7. The rectangular grid side length L is calculated to be 10 meters according to the formula L=5×2^(8-n). After dividing the road area into grids with a rectangular grid side length L of 10 meters, a corresponding geolocation code (Geohash code) is generated for each grid unit. The geolocation code for the grid unit containing a vehicle is "wtw3u7e". The grid unit is equipped with 3 sets of traffic lights and 3 lanes, namely lane 1 (left turn), lane 2 (straight), and lane 3 (right turn).

[0153] Step Two: Vehicle Status Data Access and Preprocessing. Vehicle basic safety message data is subscribed to and consumed in real-time via a Kafka message queue to obtain vehicle status information, including vehicle identifier V-20250601, real-time vehicle location coordinates (120.315689, 31.456783), speed (35 km / h), and heading angle (95 degrees). After deduplication and cleaning of expired data by a scheduled task every 100 milliseconds, valid data is written to the Redis cluster cache. Vehicle status is queried through a standardized descriptive status transmission interface. A single query response time of less than 50 milliseconds, and data verified through continuous frame validation, with position differences, speed abrupt changes, and heading angle abrupt changes all within preset thresholds, are confirmed as high-quality and valid data.

[0154] Step 3: Multi-grid combination and warning area construction. Obtain the real-time latitude and longitude coordinates of the vehicle (120.315689, 31.456783) and heading angle of 95 degrees. Convert the real-time latitude and longitude coordinates of the vehicle's real-time location into Geohash code "wtw3u7e" and use it as the first target grid cell. Extract its prefix string "wtw3u7", enumerate 8 geographically adjacent parent codes, and obtain all child grids under each adjacent parent code to form an initial candidate grid set. After filtering by spherical distance and heading angle difference, retain grids within 200 to 300 meters of the vehicle and with a heading angle difference of no more than 60 degrees. After grid continuity verification and boundary correction, a warning area is finally obtained consisting of 20 continuous rectangular grids. Divide the warning area into three levels according to distance: 3 grids in the far zone, 14 grids in the middle zone, and 3 grids in the near zone.

[0155] Step 4: Multi-source data fusion processing. All traffic light data associated with the 20 grids within the warning area are aggregated, and dynamic weighted fusion processing is performed on each traffic light data. Specifically, the comprehensive weight W1 for roadside unit data is 0.945, the comprehensive weight W2 for traffic police data is 0.85, and the comprehensive weight W3 for traffic research institute data is 0.859. After weighted fusion, the green light countdown for the target traffic light is obtained as 21 seconds. Simultaneously, improved extended Kalman filter fusion processing is applied to the four-source positioning data from the Global Navigation Satellite System, Inertial Measurement Unit, LiDAR, and vehicle-mounted unit, outputting the corrected vehicle positioning result P(120.315695, 31.456788), achieving a positioning accuracy of 0.25 meters.

[0156] Step 5: Calculate the advance warning time. Based on the vehicle's current speed v of 35 km / h and the spherical distance D between the vehicle's position and the stop line associated with the target traffic light of 280 meters, calculate the advance warning time: t a =280 / 35×3.6+2=28.8 seconds. This value falls within the effective range of 3 to 36 seconds, indicating an effective advance warning. Since the current distance of 280 meters is in the far-field range, the far-field push strategy is adopted.

[0157] Step Six: Scenario-based Traffic Light Matching. The cloud control platform identifies the current target traffic scenario as an urban arterial road scenario and uses a weighted priority algorithm to filter candidate traffic lights. The priority score of the candidate traffic light is calculated as: P = 0.4 × (1 / 280 × 100) + 0.3 × (1 / 35) + 0.3 × 5 ≈ 1.651. After comparison, this traffic light has the highest priority score and is selected as the target traffic light for this warning.

[0158] Step Seven: Multi-level Early Warning Push. As the vehicle approaches from a distance, the cloud control platform dynamically updates the vehicle status and traffic light status, pushing traffic guidance information to the vehicle in stages, with a push frequency of 1 Hz for each stage. When the vehicle is in the far zone and about 300 meters away from the traffic light, the push notification will say "Intersection 300 meters ahead, green light, estimated arrival time 28.8 seconds"; When the vehicle enters the central area and is about 200 meters away from the traffic light, the push notification will say: "Intersection 200 meters ahead, green light countdown 18 seconds, recommended speed 35 km / h"; When a vehicle enters the proximity zone and is approximately 100 meters from the traffic light, the notification message reads: "Lane 2, green light countdown 8 seconds, maintain speed."

[0159] Through the complete process described above, the vehicle traffic guidance information push method provided in this application embodiment can provide accurate, real-time, and tiered traffic guidance information services for intelligent connected vehicles.

[0160] Based on the vehicle traffic guidance information push method provided in the above embodiments, this application also provides a specific implementation of the vehicle traffic guidance information push device. Please refer to the following embodiments.

[0161] See Figure 9 The vehicle traffic guidance information push device 20 provided in this application embodiment includes an acquisition module 201, a determination module 202, a grid division module 203, and an information push module 204.

[0162] Module 201 is used to acquire traffic flow parameters for the road area; The determination module 202 is used to determine the target traffic scenario of the road area based on the matching results of traffic flow parameters and reference traffic flow parameter intervals of at least two reference traffic scenarios. The grid division module 203 is used to divide the first road area into grids according to the grid division parameters corresponding to the target traffic scene, and obtain the grid division result. The grid division result includes m grid units, each grid unit corresponds to at least one traffic light, and m is a positive integer greater than 2. The information push module 204 is used to push vehicle traffic guidance information to the vehicle based on the vehicle status information, the target grid unit corresponding to the vehicle, and the status information of the target traffic light when the vehicle enters the road area. The target traffic light is determined based on the traffic light associated with the target grid unit.

[0163] Therefore, by acquiring traffic flow parameters of the road area through module 201, and using the matching results obtained by module 202 matching the traffic flow parameters with the reference traffic flow parameter intervals of at least two reference traffic scenarios, the target traffic scenario currently in the road area is dynamically identified. After determining the target traffic scenario using module 202, the grid division module 203 performs adaptive grid division of the road area according to the grid division parameters corresponding to the target traffic scenario, generating a grid division result including m grid units that match the current traffic conditions, and establishing a correspondence between each grid unit and at least one traffic light. Thus, when a vehicle enters the road area using information push module 204, the cloud control platform can further integrate the vehicle's real-time status information, the target grid unit in which the vehicle is located, and the real-time status information of the target traffic light determined based on the target grid unit, to push personalized vehicle traffic guidance information to the vehicle. This dynamic and adaptive grid division mechanism fundamentally solves the problem of mismatch between guidance timing and actual vehicle needs, enabling the timing of vehicle traffic guidance information push to be accurately matched with the real-time status of vehicles and real-time traffic flow conditions. This significantly improves the accuracy and practicality of vehicle traffic guidance information push and effectively solves the technical problem of low accuracy in vehicle traffic guidance information push.

[0164] In some embodiments of this application, the grid division module 203 is used to determine the target grid side length corresponding to the traffic flow parameters based on the grid side length interval corresponding to the target traffic scene, when the grid division parameters include the geolocation coding accuracy level and the grid side length interval, and the grid division result also includes the grid geolocation code of each grid unit; divide the road area into grids according to the target grid side length to obtain m grid units; and generate the grid geolocation code of each grid unit according to the geolocation coding accuracy level and the geolocation information of each grid unit.

[0165] In some embodiments of this application, the vehicle traffic guidance information push device 200 provided in this application may further include a filtering module.

[0166] The filtering module is used to, before performing the step of pushing vehicle traffic guidance information to the vehicle based on the vehicle status information, the target grid unit corresponding to the vehicle, and the status information of the target traffic light, obtain the target traffic light filtering rules associated with the target traffic scene according to the association relationship between the reference traffic scene and the reference traffic light filtering rules, when there are at least two traffic lights associated with the target grid unit; and filter the target traffic light from at least two traffic lights according to the target traffic light filtering rules.

[0167] In some embodiments of this application, the determining module 202 provided in this application can also be used to: determine the first target grid cell where the vehicle is located from m grid cells based on the vehicle's location, when the grid division result also includes the grid geographic location code of each grid cell and the vehicle status information includes the vehicle's location; determine the second target grid cell associated with the first target grid cell from m grid cells based on the grid geographic location code of the first target grid cell, the second target grid cell being located ahead of the vehicle's driving path; and determine the first target grid cell and the second target grid cell as target grid cells.

[0168] In some embodiments of this application, the determining module 202 provided in this application can also be used to: generate at least two reference grid geolocation codes based on the prefix string of the first target grid cell, where the grid geolocation code includes a prefix string and an extended character, and the vehicle status information includes the vehicle heading angle; determine a first candidate grid cell from m grid cells corresponding to each of the at least two reference grid geolocation codes; filter a second candidate grid cell from the at least two first candidate grid cells that meets preset conditions based on the spherical distance between the center position of each first candidate grid cell and the vehicle position, and the heading angle difference between the preset heading angle corresponding to each first candidate grid cell and the vehicle heading angle, wherein the preset conditions include the spherical distance being within the reference spherical distance range and the heading angle difference being less than or equal to the preset heading angle difference; perform grid continuity verification on the second candidate grid cell and the first target grid cell, and determine the second target grid cell related to the first target grid cell based on the grid continuity verification result.

[0169] In some embodiments of this application, the determining module 202 provided in this application can also be used to: determine the second target raster unit related to the first target raster unit based on the second candidate raster unit when the raster continuity verification result is used to characterize that the second candidate raster unit and the first target raster unit share a complete edge or a vertex; and regenerate at least two reference raster geolocation codes based on the prefix string of the first target raster unit when the raster continuity verification result is used to characterize that the second candidate raster unit and the first target raster unit do not share a complete edge or a vertex, until a preset number of regenerations is reached; and the regenerated at least two reference raster geolocation codes are different from the at least two reference raster geolocation codes.

[0170] In some embodiments of this application, the determining module 202 provided in this application can also be used to: determine the second candidate grid cell as the second target grid cell associated with the first target grid cell when the planar distance between the center position of the second candidate grid cell and the vehicle position is less than or equal to a preset planar distance value; adjust the center position of the second candidate grid cell according to a reference adjustment direction when the planar distance between the center position of the second candidate grid cell and the vehicle position is greater than the preset planar distance value; and recalculate the planar distance between the center position of the second candidate grid cell and the vehicle position based on the adjusted center position until the planar distance between the adjusted center position of the second candidate grid cell and the vehicle position is less than or equal to the preset planar distance value.

[0171] In some embodiments of this application, the information push module 204 can be specifically used to perform the following steps when the target grid unit includes a first target grid unit and a second target grid unit; the vehicle status information includes first vehicle status information and second vehicle status information, the status information includes first status information and second status information, the first status information corresponds to the status of the target traffic light when the vehicle enters the first target grid unit, the second status information corresponds to the status of the target traffic light when the vehicle enters the second target grid unit, and the vehicle traffic guidance information includes first vehicle traffic guidance information and second vehicle traffic guidance information: when the vehicle enters the area corresponding to the first target grid unit, based on the vehicle's first vehicle status information and the status of the target traffic light corresponding to the first target grid unit... First traffic guidance information is generated based on the first traffic guidance strategy information and the first state information of the target traffic light, and the first vehicle traffic guidance information is pushed to the vehicle. The first traffic guidance strategy information is determined based on the distance between the reference position of the first target grid unit and the reference boundary position associated with the target traffic light. When the vehicle enters the area corresponding to the second target grid unit, second vehicle traffic guidance information is generated based on the second vehicle state information of the vehicle, the second traffic guidance strategy information corresponding to the second target grid unit, and the second state information of the target traffic light, and the second vehicle traffic guidance information is pushed to the vehicle. The second traffic guidance strategy information is determined based on the distance between the reference position of the second target grid unit and the reference boundary position associated with the target traffic light.

[0172] In some embodiments of this application, the determining module 202 provided in this application can also be used to, when traffic flow parameters include traffic volume, traffic density, and vehicle speed, and the reference traffic flow parameter range includes a reference traffic volume range, a reference traffic density range, and a reference vehicle speed range, match traffic volume with the reference traffic volume range of each of at least two reference traffic scenarios to obtain a matching score between traffic volume and each reference traffic scenario; match traffic density with the reference traffic density range of each of at least two reference traffic scenarios to obtain a matching score between traffic density and each reference traffic scenario; match vehicle speed with the reference vehicle speed range of each of at least two reference traffic scenarios to obtain a matching score between vehicle speed and each reference traffic scenario; obtain a comprehensive matching score between traffic flow parameters and each reference traffic scenario based on the matching scores of traffic volume, traffic density, and vehicle speed; and determine the reference traffic scenario corresponding to the higher score among the at least two comprehensive matching scores as the target traffic scenario for the road area.

[0173] The various modules of the vehicle traffic guidance information push device 200 provided in this application embodiment can realize Figures 1 to 8 The functions of each step in the provided vehicle traffic guidance information push method, and the corresponding technical effects they achieve, will not be elaborated here for the sake of brevity.

[0174] Figure 10 The diagram shows a schematic representation of the hardware structure of an electronic device provided in some embodiments of this application.

[0175] The electronic device 30 may include a processor 301 and a memory 302 storing computer program instructions.

[0176] Specifically, the processor 301 may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.

[0177] Memory 302 may include mass storage for data or instructions. For example, and not limitingly, memory 302 may include a hard disk drive (HDD), floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 302 may include removable or non-removable (or fixed) media. Where appropriate, memory 302 may be internal or external to the integrated gateway disaster recovery device. In a particular embodiment, memory 302 is non-volatile solid-state memory.

[0178] In a particular embodiment, memory 302 may include read-only memory (ROM), random access memory (RAM), disk storage media device, optical storage media device, flash memory device, electrical, optical, or other physical / tangible memory storage device. Therefore, typically, memory 302 includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the vehicle traffic guidance information push method in the above embodiments according to this application.

[0179] The processor 301 reads and executes computer program instructions stored in the memory 302 to implement any of the vehicle traffic guidance information push methods in the above embodiments.

[0180] In one example, electronic device 30 may further include communication interface 303 and bus 310. Wherein, as Figure 10 As shown, the processor 301, memory 302, and communication interface 303 are connected through bus 310 and complete communication with each other.

[0181] The communication interface 303 is mainly used to realize communication between various modules, devices, units and / or equipment in the embodiments of this application.

[0182] Bus 310 includes hardware, software, or both, that couples components of electronic device 30 together. For example, and not limitingly, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count Bus (LPC), a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VESA Local Bus, VLB), or other suitable buses, or a combination of two or more of these. Where appropriate, bus 310 may include one or more buses. Although specific buses are described and illustrated in the embodiments of this application, this application considers any suitable bus or interconnection.

[0183] The electronic device 30 can execute the vehicle traffic guidance information push method in the embodiments of this application, thereby achieving a combination of Figures 1 to 9 The method and device for pushing vehicle traffic guidance information are described.

[0184] Furthermore, in conjunction with the vehicle traffic guidance information push method in the above embodiments, this application embodiment can provide a computer-readable storage medium for implementation. This computer-readable storage medium stores computer program instructions; when these computer program instructions are executed by a processor, they implement any of the vehicle traffic guidance information push methods in the above embodiments. Examples of computer-readable storage media include non-transitory computer-readable storage media, such as portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, etc.

[0185] Furthermore, in conjunction with the vehicle traffic guidance information push method in the above embodiments, this application embodiment can provide a computer program product for implementation. This program product is stored in a storage medium and may specifically include a computer program or instructions. When executed by a processor, the computer program or instructions implement any of the vehicle traffic guidance information push methods in the above embodiments. This program product is executed by at least one processor to implement the various processes of the vehicle traffic guidance information push method embodiments described above, and can achieve the same technical effects. To avoid repetition, further details are omitted here.

[0186] It should be clarified that this application is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of this application is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of this application.

[0187] The functional blocks shown in the above block diagram can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of this disclosure are programs or code segments used to perform the required tasks. The programs or code segments can be stored on a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried on a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable read-only memory (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio frequency (RF) links, etc. Code segments can be downloaded via computer networks such as the Internet, intranets, etc.

[0188] It should also be noted that the exemplary embodiments mentioned in this application describe methods or systems based on a series of steps or apparatus. However, this application is not limited to the order of the above steps; that is, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0189] The aspects of this disclosure have been described above with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It should be understood that each block in the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable vehicle access guidance information delivery device to produce a machine such that these instructions, executed via the processor of the computer or other programmable vehicle access guidance information delivery device, enable the implementation of the functions / actions specified in one or more blocks of the flowchart illustrations and / or block diagrams. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field-programmable logic circuit. It is also understood that each block in the block diagrams and / or flowchart illustrations, and combinations of blocks in the block diagrams and / or flowchart illustrations, can also be implemented by special-purpose hardware performing the specified functions or actions, or can be implemented by a combination of special-purpose hardware and computer instructions.

[0190] The above description is merely a specific implementation of this application. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, modules, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. It should be understood that the protection scope of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the protection scope of this application.

Claims

1. A method for pushing vehicle traffic guidance information, characterized in that, include: Obtain traffic flow parameters for the road area; The target traffic scenario for the road area is determined based on the matching results of traffic flow parameters and reference traffic flow parameter intervals of at least two reference traffic scenarios. Based on the grid division parameters corresponding to the target traffic scene, the road area is divided into grids to obtain a grid division result; wherein, the grid division result includes m grid units, and each of the m grid units corresponds to at least one traffic light, where m is a positive integer greater than 2; When a vehicle enters the road area, vehicle traffic guidance information is pushed to the vehicle based on the vehicle status information, the target grid unit corresponding to the vehicle, and the status information of the target traffic light. The target traffic light is determined based on the traffic light associated with the target grid unit.

2. The method according to claim 1, characterized in that, The grid division parameters include geolocation coding precision level and grid side length range, and the grid division result also includes the grid geolocation code of each grid unit; The step of dividing the road area into grids according to the grid division parameters corresponding to the target traffic scene to obtain the grid division result includes: Based on the grid side length interval corresponding to the target traffic scene, determine the target grid side length corresponding to the traffic flow parameters; The road area is divided into grids according to the target grid side length to obtain the m grid units; Based on the geolocation coding precision level and the geolocation information of each grid cell, a grid geolocation code for each grid cell is generated.

3. The method according to claim 1, characterized in that, Before pushing vehicle traffic guidance information to the vehicle based on the vehicle status information, the target grid unit corresponding to the vehicle, and the status information of the target traffic light, the method further includes: When the number of traffic lights associated with the target grid cell is at least two, the target traffic light filtering rules associated with the target traffic scene are obtained according to the association between the reference traffic scene and the reference traffic light filtering rules. According to the target traffic light selection rules, a target traffic light is selected from at least two traffic lights.

4. The method according to any one of claims 1-3, characterized in that, The grid division result also includes the grid geographic location code of each grid unit; before pushing vehicle traffic guidance information to the vehicle based on the vehicle status information, the target grid unit corresponding to the vehicle, and the status information of the target traffic light, the method includes: Based on the vehicle's position, the first target grid cell where the vehicle is located is determined from the m grid cells, where the vehicle position refers to the position where the vehicle is detected to have entered the road area; Based on the grid geographic location code of the first target grid unit, a second target grid unit associated with the first target grid unit is determined from the m grid units, and the second target grid unit is located ahead of the vehicle's driving path; The first target grid cell and the second target grid cell are determined as the target grid cell.

5. The method according to claim 4, characterized in that, The grid geolocation code includes a prefix string and extended characters, and the vehicle status information includes the vehicle heading angle; the step of determining the second target grid cell associated with the first target grid cell from the m grid cells based on the grid geolocation code of the first target grid cell includes: Based on the prefix string of the first target raster cell, at least two reference raster geolocation codes are generated, wherein the prefix strings of the reference raster geolocation codes are adjacent to the prefix strings of the first target raster cell; From the m grid cells, determine the first candidate grid cell corresponding to each of the at least two reference grid geolocation codes; Based on the spherical distance between the center position of each first candidate grid cell and the vehicle position, and the difference in heading angle between the preset heading angle corresponding to each first candidate grid cell and the heading angle of the vehicle, a second candidate grid cell that meets preset conditions is selected from the at least two first candidate grid cells. The preset conditions include that the spherical distance is within the reference spherical distance range and the heading angle difference is less than or equal to the preset heading angle difference. Perform grid continuity verification on the second candidate grid cell and the first target grid cell, and determine the second target grid cell associated with the first target grid cell based on the grid continuity verification result.

6. The method according to claim 5, characterized in that, The step of determining the second target grid cell associated with the first target grid cell based on the grid continuity verification result includes: When the grid continuity verification result is used to characterize that the second candidate grid cell and the first target grid cell share a complete edge or a vertex, the second target grid cell associated with the first target grid cell is determined based on the second candidate grid cell. When the grid continuity verification result is used to characterize that the second candidate grid cell and the first target grid cell do not share a complete edge or a vertex, at least two reference grid geolocation codes are regenerated based on the prefix string of the first target grid cell until a preset number of regenerations is reached, wherein the regenerated at least two reference grid geolocation codes are different from the at least two reference grid geolocation codes.

7. The method according to claim 6, characterized in that, The step of determining the second target grid cell associated with the first target grid cell based on the second candidate grid cell includes: If the planar distance between the center position of the second candidate grid cell and the vehicle position is less than or equal to a preset planar distance value, the second candidate grid cell is determined as the second target grid cell associated with the first target grid cell; If the planar distance between the center position of the second candidate grid cell and the vehicle position is greater than the preset planar distance value, the center position of the second candidate grid cell is adjusted according to the reference adjustment direction to obtain the adjusted center position; the reference adjustment direction is the direction towards the vehicle position. The planar distance between the center position of the second candidate grid cell and the vehicle position is recalculated based on the adjusted center position until the planar distance between the adjusted center position of the second candidate grid cell and the vehicle position is less than or equal to a preset planar distance value.

8. The method according to any one of claims 1-3 or 5-7, characterized in that, The target grid unit includes a first target grid unit and a second target grid unit; the vehicle status information includes first vehicle status information and second vehicle status information, the status information includes first status information and second status information, the first status information corresponds to the status of the target traffic light when the vehicle enters the first target grid unit, the second status information corresponds to the status of the target traffic light when the vehicle enters the second target grid unit, and the vehicle traffic guidance information includes first vehicle traffic guidance information and second vehicle traffic guidance information. The step of pushing vehicle traffic guidance information to the vehicle based on the vehicle status information, the target grid unit corresponding to the vehicle, and the status information of the target traffic light includes: When the vehicle enters the area corresponding to the first target grid unit, first vehicle traffic guidance information is generated based on the first vehicle status information of the vehicle, the first traffic guidance strategy information corresponding to the first target grid unit, and the first status information of the target traffic light, and the first vehicle traffic guidance information is pushed to the vehicle. The first traffic guidance strategy information is determined based on the distance between the reference position of the first target grid unit and the reference boundary position associated with the target traffic light. When the vehicle enters the area corresponding to the second target grid unit, second vehicle traffic guidance information is generated based on the second vehicle status information of the vehicle, the second traffic guidance strategy information corresponding to the second target grid unit, and the second status information of the target traffic light. The second vehicle traffic guidance information is then pushed to the vehicle. The second traffic guidance strategy information is determined based on the distance between the reference position of the second target grid unit and the reference boundary position associated with the target traffic light.

9. The method according to any one of claims 1-3 or 5-7, characterized in that, The traffic flow parameters include traffic volume, traffic density, and vehicle speed, and the reference traffic flow parameter range includes a reference traffic volume range, a reference traffic density range, and a reference vehicle speed range. Determining the target traffic scenario for the road area based on the matching results of traffic flow parameters and reference traffic flow parameter intervals of at least two reference traffic scenarios includes: The traffic flow is matched with the reference traffic flow range of each of the at least two reference traffic scenarios to obtain a matching score between the traffic flow and each reference traffic scenario. The traffic density is matched with the reference traffic density range of each of the at least two reference traffic scenarios to obtain a matching score between the traffic density and each reference traffic scenario. The traffic flow speed is matched with the reference traffic flow speed range of each of the at least two reference traffic scenarios to obtain a matching score between the traffic flow speed and each reference traffic scenario. Based on the matching scores of the traffic flow with each reference traffic scenario, the matching scores of the traffic density with each reference traffic scenario, and the matching scores of the vehicle speed with each reference traffic scenario, a comprehensive matching score of the traffic flow parameters with each reference traffic scenario is obtained. The reference traffic scene corresponding to the higher score among at least two comprehensive matching scores is determined as the target traffic scene for the road area.

10. A vehicle traffic guidance information push device, characterized in that, The device includes: The acquisition module is used to acquire traffic flow parameters for the road area; The determination module is used to determine the target traffic scenario of the road area based on the matching results of traffic flow parameters and reference traffic flow parameter intervals of at least two reference traffic scenarios; The grid division module is used to divide the first road area into grids according to the grid division parameters corresponding to the target traffic scene, and obtain the grid division result. The grid division result includes m grid units, each grid unit corresponds to at least one traffic light, and m is a positive integer greater than 2. The information push module is used to push vehicle traffic guidance information to the vehicle when the vehicle enters the road area, based on the vehicle status information, the target grid unit corresponding to the vehicle, and the status information of the target traffic light. The target traffic light is determined based on the traffic light associated with the target grid unit.

11. An electronic device, characterized in that, The device includes: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, it implements the vehicle traffic guidance information push method as described in any one of claims 1-9.

Images