Road speed recommendation method, apparatus, and electronic device

Abstract

This disclosure provides a method, apparatus, and electronic device for road speed recommendation, relating to the field of computer technology, particularly artificial intelligence, large-scale models, natural language processing, deep learning, mapping, and lane-level navigation. The specific implementation involves: acquiring vehicle trajectory data on roads associated with a map road network; wherein each road includes at least one road segment, and the vehicle trajectory data includes speed values ​​corresponding to multiple trajectory points; for any given road segment, determining a target trajectory point matching the road segment from the multiple trajectory points; determining the target trajectory speed of the road segment based on the speed value corresponding to the target trajectory point; fusing the target trajectory speed and target speed limit of at least one road segment to obtain the recommended speed for each road segment; wherein the recommended speed is used to provide speed recommendations for vehicles.

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, and in particular to the fields of artificial intelligence, large models, natural language processing, deep learning, mapping, lane-level navigation, and more specifically to a road speed recommendation method, apparatus, and electronic device. Background Technology

[0002] Currently, cars have become increasingly common in households, serving as an essential means of daily transportation. Simultaneously, intelligent driving technology is developing rapidly. Against this backdrop, driving speed has an increasingly significant impact on the driving experience. Specifically, maintaining a reasonable driving speed is crucial; it not only significantly improves road efficiency and reduces traffic congestion but also greatly enhances the comfort of passengers in complex and ever-changing road conditions, while simultaneously improving driving safety.

[0003] Current speed recommendations are either based on historical trajectories or maximum speed limits, which are not scientific or reasonable enough. How to provide more reasonable speed recommendations has become an urgent and significant problem to be solved. Summary of the Invention

[0004] This disclosure provides a road speed recommendation method, apparatus, and electronic device.

[0005] According to one aspect of this disclosure, a road speed recommendation method is provided, the method comprising: acquiring vehicle trajectory data on roads associated with a map road network; wherein the road includes at least one road segment, and the vehicle trajectory data includes speed values ​​corresponding to multiple trajectory points; for any one of the road segments, determining a target trajectory point matching the road segment from the multiple trajectory points; determining a target trajectory speed for the road segment based on the speed value corresponding to the target trajectory point; and fusing the target trajectory speed and a target speed limit of the at least one road segment to obtain a recommended speed for each road segment in the road; wherein the recommended speed is used to provide speed recommendations for vehicles.

[0006] According to another aspect of this disclosure, a road speed recommendation device is provided, the device comprising: a first acquisition module, configured to acquire vehicle trajectory data on roads associated with a map road network; wherein the road includes at least one road segment, and the vehicle trajectory data includes speed values ​​corresponding to multiple trajectory points; a first determination module, configured to, for any one of the road segments, determine a target trajectory point matching the road segment from the multiple trajectory points; a second determination module, configured to determine a target trajectory speed of the road segment based on the speed value corresponding to the target trajectory point; and a processing module, configured to fuse the target trajectory speed and target speed limit of the at least one road segment to obtain a recommended speed for each road segment in the road; wherein the recommended speed is used to provide speed recommendations for vehicles.

[0007] According to another aspect of this disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to said at least one processor; wherein the memory stores instructions executable by said at least one processor, said instructions being executed by said at least one processor to enable said at least one processor to perform the road speed recommendation method proposed in the foregoing aspect of this disclosure.

[0008] According to another aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions for causing a computer to execute the road speed recommendation method proposed in the above aspect of this disclosure.

[0009] According to another aspect of this disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements the road speed recommendation method proposed in the above aspect of this disclosure.

[0010] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0011] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0012] Figure 1 This is a schematic diagram according to an embodiment of the present disclosure; Figure 2 This is a schematic diagram according to another embodiment of the present disclosure; Figure 3 This is a schematic diagram according to another embodiment of the present disclosure; Figure 4 This is a schematic diagram according to another embodiment of the present disclosure; Figure 5It is based on the diagram of the angle provided in this disclosure; Figure 6 This is a schematic diagram according to another embodiment of the present disclosure; Figure 7 This is a schematic diagram of the structure of the map speed data mining device provided in this disclosure; Figure 8 This is a schematic diagram according to another embodiment of the present disclosure; Figure 9 This is a block diagram of an electronic device used to implement the road speed recommendation method of the embodiments of this disclosure. Detailed Implementation

[0013] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0014] This disclosure proposes a road speed recommendation method, apparatus, and electronic equipment.

[0015] Figure 1 This is a schematic diagram according to an embodiment of the present disclosure. It should be noted that the road speed recommendation method of the present disclosure can be applied to a road speed recommendation device, which can be configured in an electronic device so that the electronic device can perform the road speed recommendation function.

[0016] Among them, electronic devices can be any device with computing capabilities, such as personal computers (PCs), mobile terminals, servers, etc. Mobile terminals can be, for example, in-vehicle devices, mobile phones, tablets, personal digital assistants, wearable devices, smart speakers, servers, server clusters, and other hardware devices with various operating systems, touch screens and / or displays.

[0017] The road speed recommendation device can also be software within an electronic device, such as road speed recommendation software. In the following embodiments, an electronic device is used as an example for illustration.

[0018] like Figure 1 As shown, this road speed recommendation method may include the following steps: Step 101: Obtain vehicle trajectory data on roads associated with the map road network.

[0019] A road may include at least one road segment. It should be noted that a road segment, also called a road section, is a basic road unit. Any road can be divided according to road network topology, mileage, or intersections to obtain continuous basic road units. This disclosure does not limit the number of road segments included in a road; there may be one or more. Furthermore, it should be noted that a map road network is a digital abstraction of real-world roads on a map, a directed topological network composed of intersections, turning points, and road segments, used to accurately describe the spatial location, connectivity, and traffic rules of roads. The roads associated with a map road network can be determined based on the topological relationships (such as road connection methods) between road segments in the map road network, and the number of roads associated with a map road network may be, but is not limited to, one; this disclosure does not impose any restrictions on this.

[0020] The vehicle trajectory data can include speed values ​​corresponding to multiple trajectory points. It should be noted that vehicle trajectory data on any road can include multiple vehicle trajectories, and each vehicle trajectory can include multiple trajectory points. Each trajectory point can have corresponding timestamp and location information, which can be obtained through road network equipment or other means. For any trajectory point, the speed value corresponding to that trajectory point can be calculated based on the timestamp and location information of that trajectory point and its adjacent trajectory points.

[0021] Step 102: For any road segment, determine the target trajectory point that matches the road segment from multiple trajectory points.

[0022] As an example, for any road segment, the trajectory points whose location information matches the location information of the road segment can be determined from multiple trajectory points, and the matching trajectory points are determined as the target trajectory points that match the road segment.

[0023] It is understandable that a road segment can be regarded as a line segment with a start and an end. Therefore, as another example, a rectangular area can be formed with the length of the straight line segment between the start and end as the length and the width of the road segment as the width. For any trajectory point, it can be determined whether the trajectory point is located in the rectangular area based on the location information of the trajectory point. When the trajectory point is located in the rectangular area, the trajectory point is determined to be the target trajectory point that matches the road segment.

[0024] As another example, for any trajectory point, the vertical distance d from the trajectory point to the straight line segment L between the start and end points of the road segment can be determined based on the location information of the trajectory point. When the vertical distance d is less than a set distance threshold, and the projection point of the trajectory point on the straight line segment L is located between the start and end points of the straight line segment L, then the trajectory point is determined to be the target trajectory point matching the road segment.

[0025] It should be noted that this disclosure does not limit the number of target trajectory points that match the road segment; there may be one or more.

[0026] Step 103: Determine the target trajectory speed of the road segment based on the speed value corresponding to the target trajectory point.

[0027] As an example, when there is only one target trajectory point, the corresponding speed value of the target trajectory point can be determined as the target trajectory speed of that road segment.

[0028] As another example, when there are multiple target trajectory points, the speed values ​​corresponding to the multiple target trajectory points can be weighted and summed to obtain the target trajectory speed of the road segment.

[0029] As another example, when there are multiple target trajectory points, the target quantile value among the velocity values ​​corresponding to the multiple target trajectory points can be determined as the target trajectory velocity of the road segment.

[0030] The target quantile value can be obtained by arranging the velocity values ​​corresponding to multiple target trajectory points in ascending order to obtain a sorted sequence, and determining the velocity value at the corresponding percentage position in the sorted sequence as the target quantile value. For example, the target quantile value can be the 50th quantile value (i.e., the median), the 60th quantile value, etc., which can be set as needed.

[0031] Step 104: The target trajectory speed and target speed limit of at least one road segment are fused to obtain the recommended speed for each road segment in the road; wherein, the recommended speed is used to provide speed recommendations for vehicles.

[0032] The target speed limit can be the upper and / or lower limit of the permissible driving speed for a road segment used for safety constraints.

[0033] Each road segment may have a corresponding speed limit. It should be noted that the speed limits for different road segments may be the same or different, and this disclosure does not impose any restrictions on this.

[0034] As an example, for any road segment, the minimum value between the target trajectory speed and the target speed limit of the road segment can be taken and used as the initial road segment speed. The road segment speeds of each road segment in the road to which the road segment belongs can be weighted and summed to obtain the target road segment speed. The target road segment speed can be determined as the recommended speed of each road segment in the road to which the road segment belongs. Thus, the recommended speeds of each road segment in the map road network can be updated. Therefore, the updated recommended speeds of each road segment in the map road network can be used for speed recommendation.

[0035] The road speed recommendation method of this disclosure acquires vehicle trajectory data on roads associated with a map road network. Each road includes at least one road segment. The vehicle trajectory data includes speed values ​​corresponding to multiple trajectory points. For any road segment, a target trajectory point matching the road segment is determined from the multiple trajectory points. Based on the speed value corresponding to the target trajectory point, a target trajectory speed for the road segment is determined. The target trajectory speed and target speed limit of at least one road segment are fused to obtain the recommended speed for each road segment. The recommended speed is used to provide speed recommendations for vehicles. Therefore, by combining the real road conditions reflected by the vehicle trajectory with the road speed limit, the recommended speed can both comply with safety regulations and conform to the actual road traffic conditions, improving the accuracy and practicality of speed recommendations. Simultaneously, speed calculation and fusion based on each road segment makes the recommended speeds of adjacent road segments more continuous and smooth, maintaining the continuity and consistency of recommended speeds between adjacent road segments and avoiding sudden speed changes. This allows for a more realistic and reliable speed reference in scenarios such as navigation route planning and vehicle assisted driving, helping to improve road traffic efficiency and driving safety, and enhancing the user's driving experience.

[0036] like Figure 2 As shown, this disclosure also proposes a road speed recommendation method. Figure 2 This is a schematic diagram according to another embodiment of the present disclosure. The road speed recommendation method may include the following steps: Step 201: Obtain vehicle trajectory data on roads associated with the map road network.

[0037] It should be noted that the execution process of step 201 can refer to the execution process of any embodiment of this disclosure, and will not be repeated here.

[0038] Step 202: For any road segment, determine the matching degree information between any trajectory point in the vehicle trajectory data and the road segment.

[0039] The vehicle trajectory data can also include the orientation angle corresponding to any trajectory point. For example, the orientation angle of a trajectory point can be determined based on the direction of the line connecting the trajectory point to its adjacent trajectory point on the same vehicle trajectory.

[0040] Among them, a scoring system can be used to represent the matching information. That is, in the scoring system, the matching information can be quantified into a specific value and has a certain range of values, such as 0 to 100, 0 to 10, etc.

[0041] Among them, a rating system can be used to represent the matching information. That is, in the rating system, the matching information can be divided into several discrete levels, such as "high", "medium" and "low", or use numerical levels such as 1, 2, 3, etc., or use letter levels such as "A+", "A", "A-", "B+", etc.

[0042] Alternatively, in some embodiments, such as Figure 3 As shown, step 202 can be achieved by using the following steps 2021 to 2025: Step 2021: For any trajectory point, determine the trajectory point as the first trajectory point.

[0043] In this embodiment of the disclosure, for any trajectory point, the trajectory point can be determined as the first trajectory point.

[0044] Step 2022: Based on the location information of the first trajectory point and the location information of the road segment, determine the distance between the first trajectory point and the road segment.

[0045] As an example, the vertical distance between the first trajectory point and the line connecting the start and end points of the road segment can be determined based on the location information of the first trajectory point, as well as the location information of the start and end points of the road segment, and this vertical distance can be used as the distance between the first trajectory point and the road segment.

[0046] As another example, the distance between the first trajectory point and the center point of the road segment can be determined based on the location information of the first trajectory point and the location information of the center point of the road segment, and this distance can be used as the distance between the first trajectory point and the road segment.

[0047] As another example, the distance between the first trajectory point and the starting point can be determined based on the location information of the first trajectory point and the location information of the starting point of the road segment, and the distance between the first trajectory point and the ending point can be determined based on the location information of the first trajectory point and the location information of the ending point of the road segment; the minimum value of the distance between the first trajectory point and the starting point and the distance between the first trajectory point and the ending point is determined as the distance between the first trajectory point and the road segment.

[0048] Step 2023: Determine the directional consistency score between the first trajectory point and the road segment based on the orientation angle corresponding to the first trajectory point and the road segment direction.

[0049] The direction of a road segment can be, for example, the direction from the starting point of the road segment to its ending point, or the tangent direction of the center point of the road segment.

[0050] As an example, the angle difference can be determined based on the orientation angle corresponding to the first trajectory point and the azimuth angle corresponding to the road segment direction; the directional consistency score between the first trajectory point and the road segment can be determined based on the angle difference.

[0051] Among them, the angle difference can be negatively correlated with the directional consistency score, that is, the larger the angle difference, the smaller the directional consistency score, and vice versa.

[0052] As an example, assuming the orientation angle corresponding to the first trajectory point is θ1, and the azimuth angle corresponding to the road segment direction is θ2, the angle difference can be determined using the following formula: (1) (2) in, The absolute difference; For the angle difference; Furthermore, a preset mapping function can be used to determine the directional consistency score corresponding to the angle difference.

[0053] The mapping function can be a piecewise linear decreasing function, or it can be an exponential decreasing function, a logarithmic decreasing function, etc. This disclosure does not impose any restrictions on it.

[0054] Step 2024: Determine the continuity score of the first trajectory point based on the matching degree information between a set number of trajectory points located before the first trajectory point in the same vehicle trajectory and the road segment.

[0055] The quantity can be preset, such as 2, 3, etc., and this disclosure does not limit it.

[0056] As an example, assuming that the matching information is represented by a scoring system, that is, the matching information is a matching score, the continuity score of the first trajectory point can be determined based on the matching scores of a set number of trajectory points located between the first trajectory points in the same vehicle trajectory and the road segment before them.

[0057] For example, the matching scores of a set number of trajectory points located between the first trajectory points in the same vehicle trajectory and the road segment can be weighted and summed to obtain an initial score; then, based on the initial score, the continuity score of the first trajectory point can be determined.

[0058] For example, assuming the set quantity is 5, the matching scores of the 5 trajectory points preceding the first trajectory point in the same vehicle trajectory and the road segment preceding it can be weighted and summed to obtain an initial score. Then, based on the initial score, the continuity score of the first trajectory point can be determined. For instance, the initial score can be used as the continuity score of the first trajectory point; or, if the initial score is greater than a set score threshold, the first set score is used as the continuity score of the first trajectory point; if the initial score is not greater than the set score threshold, the second set score is used as the continuity score of the first trajectory point, where the first set score is greater than the second set score.

[0059] Step 2025: Based on at least one of distance, direction consistency score and coherence score, determine the matching degree information between the first trajectory point and the road segment.

[0060] As an example, a distance score can be determined based on distance and using appropriate mapping rules; the distance score, directional consistency score, and coherence score can be weighted and summed to obtain the target score; finally, based on the target score, the matching degree information between the first trajectory point and the road segment can be determined. For example, the target score can be used as the matching degree information between the first trajectory point and the road segment, or the matching degree level corresponding to the target score can be used as the matching degree information between the first trajectory point and the road segment, and so on.

[0061] Among them, distance can be negatively correlated with distance score, that is, the greater the distance, the smaller the distance score, and vice versa.

[0062] Therefore, it is possible to comprehensively calculate the matching degree between trajectory points and road segments from multiple dimensions such as spatial distance, directional consistency and trajectory continuity. Compared with single-dimensional matching, it is more comprehensive and robust. It can effectively reduce the impact of complex scenarios such as positioning noise, trajectory drift and road segment intersection on the matching results, which helps to improve the accuracy and stability of trajectory point and road segment matching, and lay a solid data foundation for subsequent accurate calculation of target trajectory speed of road segments and generation of reliable recommended speed.

[0063] Step 203: Based on the matching degree information, determine the target trajectory point that matches the road segment from multiple trajectory points.

[0064] As an example, when the matching information is a matching score, for any trajectory point, if the matching score of the trajectory point is greater than a set score threshold, then the trajectory point is determined to be the target trajectory point that matches the road segment.

[0065] As another example, when the matching degree information is a matching degree level, for any trajectory point, if the matching degree level of the trajectory point is greater than the set level, then the trajectory point is determined to be the target trajectory point that matches the road segment.

[0066] Therefore, by flexibly adapting to both matching score and matching level judgment methods, the target trajectory points can be filtered. This not only improves the universality and adaptability of the trajectory point matching judgment logic, but also maintains the stability and reliability of the target trajectory point selection results, effectively filtering low-quality and mismatched trajectory data, and providing accurate and reliable data support for subsequent road segment speed calculation and speed recommendation.

[0067] Step 204: Determine the target trajectory speed of the road segment based on the speed value corresponding to the target trajectory point.

[0068] Step 205: The target trajectory speed and target speed limit of at least one road segment are fused to obtain the recommended speed for each road segment in the road; wherein, the recommended speed is used to provide speed recommendations for vehicles.

[0069] It should be noted that the execution process of steps 204 to 205 can refer to the execution process of any embodiment of this disclosure, and will not be described in detail here.

[0070] As one possible implementation, for any road segment, a reference speed is determined based on the target trajectory speed and target speed limit of the road segment, combined with at least one of the road grade and road form of the road to which the road segment belongs; the reference speeds of each road segment in the road are weighted and summed to obtain a first speed; and a recommended speed for the road segment is determined based on the first speed.

[0071] The road classification can include, but is not limited to: expressway, first-class highway, second-class highway, etc., or expressway, main road, secondary road and branch road, etc.

[0072] The road types can include, but are not limited to: straight lines, curves, ramps, roundabouts, bridges, tunnels, elevated roads, underground roads, intersections, etc.

[0073] For any road segment, in order to determine the reference speed of the road segment based on the target trajectory speed and target speed limit of the road segment, combined with at least one of the road grade and road form of the road to which the road segment belongs, as an example, a correspondence between the combination of road grade and road form and the speed determination strategy can be established in advance and the correspondence can be saved. Then, for any road segment, after determining the road grade and road form of the road to which the road segment belongs, the corresponding speed determination strategy is determined, and the reference speed of the road segment is determined based on the target trajectory speed and target speed limit of the road segment using the speed determination strategy.

[0074] For example, when the road class of road segment A is a highway, the road shape is a straight line, and the target trajectory speed of the road segment is less than the highest speed limit in the target speed limit, the reference speed of the road segment can be obtained by weighted summing of the target trajectory speed and the highest speed limit in the target speed limit.

[0075] For example, when road segment B belongs to a minor road and is a straight road, if the target trajectory speed of the road segment is greater than the maximum speed limit in the target speed limit, the maximum speed limit of the road segment can be determined as the reference speed of the road segment; if the target trajectory speed of the road segment is less than the minimum speed limit in the target speed limit, the minimum speed limit can be determined as the reference speed of the road segment; if the target trajectory speed of the road segment is neither less than the minimum speed limit in the target speed limit nor greater than the maximum speed limit in the target speed limit, the target trajectory speed can be determined as the reference speed of the road segment.

[0076] Furthermore, in this embodiment of the disclosure, for any road segment, the reference speeds of each road segment in the road to which the road segment belongs are weighted and summed to obtain a first speed, and a recommended speed for the road segment can be determined based on the first speed. For example, the first speed can be determined as the recommended speed of any road segment in the road to which the road segment belongs.

[0077] Therefore, based on the target trajectory speed and speed limit, the reference speed can be further determined by combining the inherent attributes of the road network such as road grade and road shape, making the reference speed more in line with the actual road traffic conditions and design specifications. By weighted summing of the reference speeds of each road segment to obtain the first speed, the smooth transition of speed between adjacent road segments and the overall continuity can be achieved, avoiding sudden speed changes. Finally, the recommended speed determined based on the first speed combines the realism of real-time road conditions with the rationality of the road network structure, and can provide safer, more stable and more realistic speed recommendation results for navigation and intelligent driving.

[0078] To obtain the speed limit for any road segment, one possible approach is to acquire a road segment image for any given road segment, perform information recognition on the road segment image to obtain the road segment speed limit information, obtain the historical speed limit of the road segment from the road network data of the map road network, and determine the target speed limit of the road segment based on the road segment speed limit information and the historical speed limit of the road segment.

[0079] The road segment images can display speed limit information, such as the maximum and minimum driving speeds. As an example, to obtain road segment images, relevant users or devices can photograph traffic signs displaying speed limit information on any road segment and upload them to the implementing entity of this disclosure. Thus, the implementing entity of this disclosure can obtain road segment images for any road segment.

[0080] Among them, the road network data of the map road network can be used to describe relevant information about roads, and can include historical speed limits for each road segment.

[0081] Among them, the historical speed limit can be the speed limit value that has been determined for the corresponding road section in a historical period (such as the most recent 3 days, the most recent 3 months, etc.). For example, it can be the legal speed limit value marked in the road network data in the past, or the historical speed limit record of the corresponding road section due to construction, control, etc. This disclosure does not restrict it.

[0082] For example, a deep learning model, i.e. a pre-trained object detection model, can be used to detect objects in road segment images to identify speed limit sign areas in the road segment images. Then, OCR (Optical Character Recognition) can be performed on the detected speed limit sign areas, or a natural language model or a large model can be used to understand the image features or image encoding information of the speed limit sign areas, identify the numbers or characters displayed in the speed limit sign areas, and parse them into the corresponding speed limit values, using the speed limit values ​​as the road segment speed limit information.

[0083] Finally, the timestamp information of the road segment image can be compared with the timestamp information corresponding to the historical speed limit of the road segment. If the timestamp information of the road segment image is later than the timestamp information corresponding to the historical speed limit of the road segment, the speed limit in the road segment speed limit information is determined as the target speed limit of the road segment; otherwise, the historical speed limit of the road segment is determined as the target speed limit of the road segment.

[0084] Therefore, by identifying information from road segment images, real-time speed limit information can be obtained. Combined with historical speed limits, the target speed limit can be determined. This fully utilizes the image recognition technology's ability to perceive real-world road information, improving the real-time nature and accuracy of speed limit information acquisition. Furthermore, by verifying and supplementing with historical speed limits, deviations in speed limit results caused by image occlusion, blurring, or misidentification can be effectively avoided. This results in a more reliable target speed limit that better reflects actual road conditions, providing a solid basis for subsequent accurate and stable road speed recommendations.

[0085] It is understandable that when a road network includes multiple roads, the recommended speeds of adjacent roads may be abnormal. For example, the recommended speeds of road segments belonging to different roads but adjacent in control position may jump, i.e., the difference in recommended speeds is large. Therefore, in one possible implementation of this disclosure, multiple roads can be checked based on the recommended speeds of each road segment to determine whether there is a target road segment with abnormal speed. If a target road segment is determined to exist, a first road segment adjacent to the target road segment is determined based on the topological relationship of the multiple roads, and the recommended speed of the target road segment is corrected according to the recommended speed of the first road segment.

[0086] It should be noted that the first road segment adjacent to the target road segment can be one or more, and this disclosure does not impose any restrictions on this.

[0087] For example, the recommended speed for the first road segment and the recommended speed for the target road segment can be weighted and summed to obtain the target speed value, and the recommended speed for the target road segment can be corrected based on this target speed value.

[0088] For example, if a road segment has a recommended speed of 80 km / h, and the recommended speeds of the adjacent road segments before and after it are both 40 km / h, and the road segments are connected as a single road in the topological structure of the road network, then the road segment can be identified as a target road segment with an abnormal speed. The speed can then be corrected based on the recommended speed of 40 km / h of the adjacent first road segment to make the speed distribution of the entire road continuous and reasonable.

[0089] Therefore, by comprehensively verifying the recommended speeds of road segments across multiple roads globally, it can promptly identify target road segments with abnormal speeds, effectively avoiding unreasonable recommended speeds caused by data biases and calculation errors, and ensuring the overall reliability of speed recommendations. Simultaneously, based on the road topology, the recommended speeds of adjacent first road segments are used to correct target road segments, fully balancing the continuity of the road network and traffic logic. This ensures that the corrected recommended speeds align with the traffic rhythm of adjacent road segments and conform to actual road conditions, further improving the accuracy and rationality of recommended speeds. This provides a more stable and reliable speed reference for navigation, intelligent driving, and other scenarios, contributing to improved overall road traffic efficiency and driving safety.

[0090] To enable the verification of multiple roads, one possible approach is to identify any road segment as the target road segment if the recommended speed for that segment is not included in the set speed range.

[0091] The speed range can be preset, for example, 0~120km / h, and this disclosure does not impose any restrictions on it.

[0092] As another possible implementation, for any road segment among multiple roads, the road segment is determined as the target road segment based on the difference between the recommended speed of the road segment and the recommended speed of the adjacent road segments being greater than a set difference threshold.

[0093] For any given road segment, the adjacent road segments may belong to the same road segment or may belong to different roads; this disclosure does not impose any restrictions on this.

[0094] The threshold value for the difference can be preset, and this disclosure does not restrict its value.

[0095] Therefore, the target road segment can be judged from two dimensions: the rationality of the recommended speed itself and the consistency of speeds between adjacent road segments. This can filter out abnormal speed values ​​that exceed the reasonable range and effectively identify sudden speed changes that differ too much from adjacent road segments, making the judgment of abnormal speed road segments more comprehensive and rigorous, and reducing the probability of misjudgment and omission. Through clear and quantifiable judgment conditions, the identification of abnormal road segments can be automated and standardized, providing a solid basis for subsequent accurate correction of recommended speeds and ensuring the smooth and reliable speed of the overall road network.

[0096] The road speed recommendation method of this disclosure determines the matching degree information between any trajectory point in the vehicle trajectory data and the road segment for any given road segment. Based on the matching degree information, a target trajectory point matching the road segment is determined from multiple trajectory points. This enables accurate matching between trajectory points and road segments, avoiding speed data distortion caused by trajectory drift, positioning errors, and other factors, thus improving the reliability and accuracy of target trajectory point selection. By filtering valid trajectory points based on the matching degree information, abnormal data and noise interference can be effectively filtered out, providing a real and effective data foundation for subsequent calculation of the target trajectory speed of the road segment, thereby improving the accuracy and reliability of the final recommended speed.

[0097] like Figure 4 As shown, this disclosure also proposes a road speed recommendation method. Figure 4 This is a schematic diagram according to another embodiment of the present disclosure. The road speed recommendation method may include the following steps: Step 401: Obtain vehicle trajectory data on roads associated with the map road network.

[0098] Step 402: For any road segment, determine the target trajectory point that matches the road segment from multiple trajectory points in the vehicle trajectory data.

[0099] It should be noted that the execution process of steps 401 to 402 can refer to the execution process of any embodiment of this disclosure, and will not be repeated here.

[0100] It is understandable that among multiple trajectory points, there may be trajectory points whose speed values ​​do not meet the requirements. For example, the speed value may be low due to road construction, or the speed value may be high due to the trajectory behavior of individual vehicles. Therefore, in one possible implementation of this disclosure embodiment, when any trajectory point has a corresponding vehicle trajectory, and each trajectory point also carries timestamp information and orientation angle, at least one of the following methods can be used to filter multiple trajectory points in the vehicle trajectory data: 1. Filter the second trajectory point from multiple trajectory points; wherein the timestamp information of the second trajectory point is included within the set time value range.

[0101] The time range can be preset, such as [7:00, 9:00] or [17:00, 19:00] daily, and can be set as needed. It's understood that [7:00, 9:00] daily can represent the morning rush hour, and [17:00, 19:00] daily can represent the evening rush hour, filtering out multiple trajectory points that fall within the above time range. By filtering trajectory points during special periods such as morning and evening rush hours, the interference of peak congestion on normal road condition speed calculations can be eliminated, improving the accuracy and stability of speed determination for subsequent road segments.

[0102] 2. Filter the third trajectory point from multiple trajectory points; wherein, the trajectory point is the one with the third trajectory point as the vertex, and the angle formed by the third trajectory point and the two adjacent trajectory points in the vehicle trajectory to which the third trajectory point belongs is greater than the set angle threshold.

[0103] The angle threshold can be preset, such as 30°, 45°, etc., and this disclosure does not limit it.

[0104] As an example, suppose a trajectory point is B, and the angle formed by B with its preceding trajectory point A and its following trajectory point C in the vehicle trajectory to which B belongs is as follows: Figure 5 As shown; when the angle is greater than the set angle threshold, it indicates that trajectory point B is a messy trajectory point. It can be determined that trajectory point B is the third trajectory point, and trajectory point B can be filtered out from the vehicle trajectory data.

[0105] 3. Filter out the fourth trajectory point from multiple trajectory points; where the velocity value corresponding to the fourth trajectory point is abnormal.

[0106] As an example, if the speed value corresponding to a certain trajectory point is less than 0 km / h, or the speed value corresponding to the trajectory point is greater than 120 km / h, then the trajectory point can be determined as a trajectory point with an abnormal speed value, that is, the fourth trajectory point, and then the trajectory point can be filtered out from the vehicle trajectory data.

[0107] Therefore, the original trajectory points can be filtered in multiple layers from multiple dimensions such as time validity, trajectory rationality, and speed authenticity, eliminating invalid trajectory data with time anomalies, sudden changes in trajectory angles, and abnormal speed values. This effectively reduces the interference of abnormal situations such as noise, drift, and sudden stops and turns on subsequent matching and speed calculation, improves the quality and reliability of trajectory data, and provides an effective data foundation for accurate road segment matching, target trajectory speed calculation, and final recommended speed generation.

[0108] Step 403: Obtain the weight of any target trajectory point.

[0109] As an example, such as Figure 6 As shown, step 403 can be achieved by using the following steps 4031 to 4033: Step 4031: For any target trajectory point, determine the distance between the target trajectory point and the road segment based on the location information of the target trajectory point and the location information of the road segment.

[0110] It should be noted that the method for determining the distance between the trajectory point and the road segment in any of the above embodiments is also applicable to this embodiment, and will not be elaborated here.

[0111] Step 4032: Obtain the time stamp information of the target trajectory point and the time matching degree of the current moment.

[0112] Time matching degree can be used to measure the similarity or time correlation between the timestamp information of a target trajectory point and the current time. The higher the time matching degree, the more valuable the historical driving status of the target trajectory point is to the current road conditions; the lower the time matching degree, the lower the correlation between the historical driving status of the target trajectory point and the current road conditions, and the less valuable it is to the reference.

[0113] As an example, when the timestamp information of the target trajectory point and the current time both belong to the same preset time period, the time matching degree can be determined to be the set value; when the timestamp information of the target trajectory point and the current time do not belong to the same preset time period, the time matching degree can be determined based on the time difference between the timestamp information of the target trajectory point and the current time.

[0114] The preset time period can be pre-set, such as [9:00-12:00] on weekdays, [12:00-13:00] on weekdays, [13:00-17:00] on weekdays within the same quarter, [13:00-17:00] on weekdays within the same calendar month, [9:00-12:00] in summer, [9:00-12:00] on non-working days within the same calendar month, etc. It can be set as needed, and this disclosure does not impose any restrictions on it.

[0115] The set value can be preset, such as 1, 100, etc., and this disclosure does not restrict it.

[0116] As an example, when the timestamp information of the target trajectory point and the current time both belong to the same preset time period, the time matching degree can be determined to be 1; when the timestamp information of the target trajectory point and the current time do not belong to the same preset time period, a preset mapping rule can be used to determine the time matching degree based on the time difference between the timestamp information of the target trajectory point and the current time. The preset mapping rule can be a logarithmic decreasing function, an exponential decreasing function, etc., and this disclosure does not limit it.

[0117] Therefore, by combining preset time period matching with time difference quantification calculation, the time matching degree can be flexibly and accurately determined. This can assign a uniform and stable time matching degree to trajectory data within the same time period, maintaining the effective reuse of traffic data in similar time periods, and can also dynamically adjust the time matching degree of trajectory data in different time periods according to the time difference, fully reflecting the timeliness differences of trajectory data. This method can balance the simplicity of the judgment logic and the execution efficiency, while effectively weakening the influence of historical trajectories in non-adjacent time periods, making the weight allocation more in line with the actual traffic patterns of roads in different time periods, and further improving the accuracy and timeliness of target trajectory speed and recommended speed.

[0118] Step 4033: Determine the weight of the target trajectory point based on at least one of distance and time matching information.

[0119] As an example, a distance score can be obtained based on the distance; the distance score and time matching information can be weighted and summed to obtain a reference value, and this reference value can be determined as the weight of the target trajectory point.

[0120] Among them, distance can be negatively correlated with distance score, that is, the greater the distance, the smaller the distance score, and vice versa.

[0121] Therefore, weights can be assigned to target trajectory points from two dimensions: spatial matching degree (i.e., the distance between the trajectory point and the road segment) and temporal timeliness (i.e., the matching degree between the timestamp and the current moment). For example, trajectory points that are closer to the road segment and whose time is closer to the current moment can have a higher weight ratio, which fully reflects the spatial accuracy and temporal validity of the trajectory data. This multi-dimensional weight setting method can effectively avoid the problem of trajectory points with too long history or location offset reducing the accuracy of speed calculation. It makes the weighted target trajectory speed more reflective of the current real traffic status of the road, further improving the accuracy and timeliness of speed calculation, and providing a data foundation for finally generating road recommended speeds that fit real-time traffic conditions.

[0122] Step 404: Based on the weight of each target trajectory point, the speed values ​​corresponding to multiple target trajectory points are weighted and summed to obtain the target trajectory speed of the road segment.

[0123] In this embodiment of the disclosure, the speed values ​​corresponding to multiple target trajectory points can be weighted and summed based on the weight of each target trajectory point to obtain the target trajectory speed of the corresponding road segment.

[0124] Step 405: The target trajectory speed and target speed limit of at least one road segment are fused to obtain the recommended speed for each road segment in the road; wherein, the recommended speed is used to provide speed recommendations for vehicles.

[0125] It should be noted that the execution process of step 405 can refer to the execution process of any embodiment of this disclosure, and will not be described in detail here.

[0126] The road speed recommendation method of this disclosure obtains the weight of any target trajectory point; based on the weight of each target trajectory point, the speed values ​​corresponding to multiple target trajectory points are weighted and summed to obtain the target trajectory speed of the road segment. Therefore, by assigning corresponding weights to different target trajectory points, differentiated consideration of the speed values ​​of each trajectory point can be achieved. For example, the speed reference value of high-quality, high-matching trajectory points (such as trajectory points with accurate positioning and consistent direction) can be highlighted, while the impact of low-quality trajectory points with slight deviations on the results can be weakened, thereby effectively reducing the interference of abnormal trajectory data. Finally, calculating the target trajectory speed through weighted summation more closely reflects the actual road traffic conditions, improving the accuracy and reliability of the target trajectory speed. This provides more meaningful data support for subsequent fusion of speed limits and generation of reasonable recommended speeds, further maintaining the scientific validity and practicality of the entire road speed recommendation method.

[0127] To clearly illustrate the road speed recommendation method disclosed herein, a detailed explanation is provided below with examples.

[0128] As an example, the road speed recommendation method of this disclosure is applied to a map speed data mining device for illustrative purposes. Figure 7 This is a schematic diagram of the device, as shown below. Figure 7 As shown, the map speed data mining device may include a trajectory preprocessing module 701, a trajectory speed fitting module 702, a sign speed limit recognition module 703, a road speed fusion module 704, a road speed smoothing quality inspection module 705, and a data output module 706, wherein: 1. The trajectory preprocessing module 701 is used to clean and filter the trajectory data (referred to as vehicle trajectory data in this disclosure); for any road network link (referred to as road segment in this disclosure) in the map road network, the target trajectory point matching the road network link is determined based on the matching confidence between the road network link and any trajectory point (referred to as matching degree information in this disclosure).

[0129] Optionally, in some embodiments, when cleaning and filtering the trajectory data, trajectory points during morning and evening rush hours can be filtered out based on the timestamp information of the trajectory data, and are denoted as second trajectory points in this disclosure; messy trajectory points can be filtered out based on the bend angle of the trajectory points, and are denoted as third trajectory points in this disclosure; and trajectory points with abnormal speed values ​​can be filtered out, and are denoted as fourth trajectory points in this disclosure.

[0130] 2. The trajectory speed fitting module 702 can be used to determine the target quantile value among the speed values ​​of all target trajectory points corresponding to the road network link as the trajectory fitting speed of the road network link (referred to as the target trajectory speed in this disclosure) when there are multiple target trajectory points.

[0131] 3. The sign speed limit recognition module 703 is used to recognize the image data corresponding to any road network link collected, and compare the speed limit recognition result corresponding to the image data with the speed data corresponding to the road network link in the map road network (referred to as the historical speed limit in this disclosure) to update the link speed limit data of the road network link in the map road network (referred to as the target speed limit in this disclosure).

[0132] IV. Road speed fusion module 704 is used to generate link chains (referred to as roads in this disclosure) based on map topology relationships; wherein, a link chain can be composed of at least one corresponding road network link; for any road network link, the trajectory fitting speed and link speed limit data of the road network link are fused together with the road level and road form of the link chain to which the road network link belongs to obtain the initial speed of the road network link (referred to as reference speed in this disclosure); for any link chain, the initial speeds of each road network link in the link chain are weighted and averaged to determine the chain speed (referred to as first speed in this disclosure); the first speed is used to update the link speed of each road network link in the corresponding link chain in the map road network (referred to as recommended speed in this disclosure).

[0133] 5. The road speed smoothing quality inspection module 705 is used to inspect the link speed of each road network link in the map road network to determine whether there are any jumps or abnormal link speeds. When there are abnormal link speeds, the module can smooth the jumps or abnormal link speeds according to the map topology to obtain the corrected link speeds.

[0134] 6. Data output module 706 updates the link speeds of each road network link after smoothing quality inspection to the map for speed recommendation.

[0135] In summary, the map velocity data mining device disclosed herein has at least the following advantages: 1. It can integrate multi-source information such as vehicle trajectory speed data, speed limit sign data, and map road network data to achieve effective fusion and comprehensive utilization of multi-source speed data. It outputs continuous, smooth, and reasonable road network link speed data, improves the integrity and accuracy of speed data, and enhances the accuracy and rationality of the link speed of a given road network link. This allows it to provide more realistic and reliable speed references in scenarios such as navigation route planning and vehicle assisted driving, which helps improve road traffic efficiency and driving safety, and enhances the user's driving experience.

[0136] 2. Based on trajectory speed data and map road network data, it can effectively filter and eliminate abnormal trajectory data generated during congested periods such as morning and evening rush hours, accurately match valid trajectory points to the corresponding road network links, and calculate the quantile value based on the speed of all valid trajectory points matched to the same road network link, which is used as the benchmark trajectory speed of that road network link, thereby improving the reliability and representativeness of trajectory speed.

[0137] 3. It can integrate the trajectory speed of road network links, road network data and speed limit sign data, and perform multi-dimensional fusion and global smoothing of road network link speeds, so that the speed transition between adjacent road network links is natural, improves the speed jump problem, and enhances the overall consistency and usability of map speed data.

[0138] To achieve the above embodiments, this disclosure also provides a road speed recommendation device. For example... Figure 8 As shown, Figure 8 This is a schematic diagram according to another embodiment of the present disclosure. The road speed recommendation device 800 may include: a first acquisition module 801, a first determination module 802, a second determination module 803, and a processing module 804.

[0139] The first acquisition module 801 is used to acquire vehicle trajectory data on roads associated with the map road network; wherein the road includes at least one road segment, and the vehicle trajectory data includes speed values ​​corresponding to multiple trajectory points.

[0140] The first determining module 802 is used to determine, for any given road segment, a target trajectory point that matches the road segment from multiple trajectory points.

[0141] The second determining module 803 is used to determine the target trajectory speed of the road segment based on the speed value corresponding to the target trajectory point.

[0142] The processing module 804 is used to fuse the target trajectory speed and the target speed limit of at least one road segment to obtain the recommended speed for each road segment in the road; wherein, the recommended speed is used to provide speed recommendations for vehicles.

[0143] In one possible implementation of this disclosure, the first determining module 802 is configured to: determine the matching degree information between any trajectory point in the vehicle trajectory data and the road segment for any road segment; and determine the target trajectory point that matches the road segment from multiple trajectory points based on the matching degree information.

[0144] In one possible implementation of this disclosure, the vehicle trajectory data further includes orientation angles corresponding to multiple trajectory points; a first determining module 802 is configured to: determine any trajectory point as a first trajectory point; determine the distance between the first trajectory point and the road segment based on the location information of the first trajectory point and the location information of the road segment; determine the directional consistency score between the first trajectory point and the road segment based on the orientation angle corresponding to the first trajectory point and the road segment direction; determine the continuity score of the first trajectory point based on the matching degree information between a predetermined number of trajectory points preceding the first trajectory point in the same vehicle trajectory and the road segment; and determine the matching degree information between the first trajectory point and the road segment based on at least one of the distance, directional consistency score, and continuity score.

[0145] In one possible implementation of this disclosure, matching degree information is used to indicate matching degree score; the first determining module 802 is used to: for any trajectory point, in response to the matching degree score of the trajectory point being greater than a set score threshold, determine the trajectory point as a target trajectory point matching the road segment.

[0146] In one possible implementation of this disclosure, the road speed recommendation device 800 may further include: The second acquisition module is used to acquire the road segment image corresponding to any given road segment.

[0147] The recognition module is used to identify information from road segment images to obtain the speed limit information for the aforementioned road segment.

[0148] The third acquisition module is used to obtain the historical speed limits of road segments from the road network data of the map road network.

[0149] The third determining module is used to determine the target speed limit for a road segment based on the road segment speed limit information and the historical speed limit of the road segment.

[0150] In one possible implementation of this disclosure, the processing module 804 is configured to: for any road segment, determine a reference speed for the road segment based on the target trajectory speed and target speed limit of the road segment, combined with at least one of the road grade and road form of the road to which the road segment belongs; perform a weighted summation of the reference speeds of each road segment in the road to obtain a first speed; and determine a recommended speed for the road segment based on the first speed.

[0151] In one possible implementation of this disclosure, there are multiple roads; the road speed recommendation device 800 may further include: The inspection module is used to inspect multiple roads based on the recommended speeds of each road segment to determine whether there are target road segments with abnormal speeds.

[0152] The fourth determination module is used to determine the first road segment adjacent to the target road segment based on the topological relationship of multiple roads, when the existence of the target road segment is determined.

[0153] The correction module is used to correct the recommended speed of the target road segment based on the recommended speed corresponding to the first road segment.

[0154] In one possible implementation of this disclosure, the verification module is configured to: for any road segment among multiple roads, determine the road segment as a target road segment in response to the recommended speed corresponding to the road segment not being included in a set speed value range; and / or, for any road segment among multiple roads, determine the road segment as a target road segment based on the difference between the recommended speed of the road segment and the recommended speed of the adjacent road segments of the road segment being greater than a set difference threshold.

[0155] In one possible implementation of this disclosure, there are multiple target trajectory points; the second determining module 803 is used to: obtain the weight of any target trajectory point; and, based on the weight of each target trajectory point, perform a weighted summation of the speed values ​​corresponding to the multiple target trajectory points to obtain the target trajectory speed of the road segment.

[0156] In one possible implementation of this disclosure, the second determining module 803 is configured to: for any target trajectory point, determine the distance between the target trajectory point and the road segment based on the location information of the target trajectory point and the location information of the road segment; obtain the time matching degree between the timestamp information of the target trajectory point and the current time; and determine the weight of the target trajectory point based on at least one of the distance and time matching degree information.

[0157] In one possible implementation of this disclosure, the second determining module 803 is configured to: determine the time matching degree as a set value in response to the fact that the timestamp information of the target trajectory point and the current time both belong to the same preset time period; and determine the time matching degree based on the time difference between the timestamp information of the target trajectory point and the current time in response to the fact that the timestamp information of the target trajectory point and the current time do not belong to the same preset time period.

[0158] In one possible implementation of this disclosure, each trajectory point has a corresponding vehicle trajectory; the vehicle trajectory data also includes timestamp information and orientation angles corresponding to multiple trajectory points; the road speed recommendation device 800 may further include at least one of the following: The first filtering module is used to filter the second trajectory point from multiple trajectory points; wherein the timestamp information of the second trajectory point is included within a set time value range.

[0159] The second filtering module is used to filter the third trajectory point among multiple trajectory points; wherein, the trajectory point is the one with the third trajectory point as the vertex and the angle formed by the two adjacent trajectory points in the vehicle trajectory to which the third trajectory point belongs is greater than a set angle threshold.

[0160] The third filtering module is used to filter the fourth trajectory point among multiple trajectory points; the velocity value corresponding to the fourth trajectory point is abnormal.

[0161] It should be noted that the road speed recommendation device provided in this embodiment can achieve the above-mentioned... Figures 1 to 3 The method implementation of the road speed recommendation method embodiment is the same as that of the method embodiment, and can achieve the same technical effect. Therefore, the parts that are the same as those of the method embodiment and the beneficial effects will not be described in detail here.

[0162] The road speed recommendation device of this disclosure acquires vehicle trajectory data on roads associated with a map road network. Each road includes at least one road segment, and the vehicle trajectory data includes speed values ​​corresponding to multiple trajectory points. For any road segment, a target trajectory point matching the road segment is determined from the multiple trajectory points. Based on the speed value corresponding to the target trajectory point, a target trajectory speed for the road segment is determined. The target trajectory speed and target speed limit of at least one road segment are fused to obtain a recommended speed for each road segment. This recommended speed is used to provide speed recommendations for vehicles. Therefore, by combining the real road conditions reflected by the vehicle trajectory with the road speed limit, the recommended speed ensures that it complies with safety regulations and reflects the actual road traffic conditions, improving the accuracy and practicality of speed recommendations. Simultaneously, by calculating and fusing speeds based on each road segment, the recommended speeds of adjacent road segments become more continuous and smooth, maintaining the continuity and consistency of recommended speeds between adjacent road segments and avoiding sudden speed changes. This allows for more realistic and reliable speed references in scenarios such as navigation route planning and vehicle assisted driving, helping to improve road traffic efficiency and driving safety, and enhancing the user's driving experience.

[0163] In the technical solutions disclosed herein, the collection, storage, use, processing, transmission, provision, and disclosure of any type of information, such as user personal information, are all carried out with the user's consent and comply with relevant laws and regulations, and do not violate public order and good morals.

[0164] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0165] Figure 9 A schematic block diagram of an example electronic device 900 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0166] like Figure 9 As shown, device 900 includes a computing unit 901, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 902 or a computer program loaded from storage unit 908 into random access memory (RAM) 903. RAM 903 may also store various programs and data required for the operation of device 900. The computing unit 901, ROM 902, and RAM 903 are interconnected via bus 904. Input / output (I / O) interface 905 is also connected to bus 904.

[0167] Multiple components in device 900 are connected to I / O interface 905, including: input unit 906, such as keyboard, mouse, etc.; output unit 907, such as various types of monitors, speakers, etc.; storage unit 908, such as disk, optical disk, etc.; and communication unit 909, such as network card, modem, wireless transceiver, etc. Communication unit 909 allows device 900 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0168] The computing unit 901 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 901 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 901 performs the various methods and processes described above, such as the road speed recommendation method. For example, in some embodiments, the road speed recommendation method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 908. In some embodiments, part or all of the computer program may be loaded and / or installed on device 900 via ROM 902 and / or communication unit 909. When the computer program is loaded into RAM 903 and executed by the computing unit 901, one or more steps of the road speed recommendation method described above may be performed. Alternatively, in other embodiments, the computing unit 901 may be configured to perform the road speed recommendation method by any other suitable means (e.g., by means of firmware).

[0169] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0170] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0171] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0172] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0173] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0174] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0175] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0176] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A road speed recommendation method, wherein, The method includes: Obtain vehicle trajectory data on roads associated with the map road network; wherein, the road includes at least one road segment, and the vehicle trajectory data includes speed values ​​corresponding to multiple trajectory points; For any of the road segments, a target trajectory point matching the road segment is determined from the plurality of trajectory points; Based on the velocity values ​​corresponding to the target trajectory points, the target trajectory velocity of the road segment is determined; The target trajectory speed and target speed limit of at least one road segment are fused to obtain the recommended speed for each road segment in the road; wherein the recommended speed is used to provide speed recommendations for vehicles.

2. The method according to claim 1, wherein, For any given road segment, determining a target trajectory point matching the road segment from the plurality of trajectory points includes: For any of the road segments, determine the matching degree information between any of the trajectory points in the vehicle trajectory data and the road segment; Based on the matching degree information, a target trajectory point that matches the road segment is determined from the plurality of trajectory points.

3. The method according to claim 2, wherein, The vehicle trajectory data also includes the orientation angles corresponding to the plurality of trajectory points; determining the matching degree information between any trajectory point in the vehicle trajectory data and the road segment includes: For any of the aforementioned trajectory points, the trajectory point is determined as the first trajectory point; Based on the location information of the first trajectory point and the location information of the road segment, the distance between the first trajectory point and the road segment is determined; Based on the orientation angle corresponding to the first trajectory point and the road segment direction, determine the directional consistency score between the first trajectory point and the road segment; Based on the matching degree information between the road segment and a set number of trajectory points located before the first trajectory point in the same vehicle trajectory, the continuity score of the first trajectory point is determined. Based on at least one of the distance, the direction consistency score, and the coherence score, the matching degree information between the first trajectory point and the road segment is determined.

4. The method according to claim 2, wherein, The matching degree information is used to indicate the matching degree score; The step of determining the target trajectory point matching the road segment from the plurality of trajectory points based on the matching degree information includes: For any of the trajectory points, if the matching score of the trajectory point is greater than a set score threshold, then the trajectory point is determined to be a target trajectory point that matches the road segment.

5. The method according to claim 1, wherein, The process of obtaining the target speed limit includes the following steps: For any of the aforementioned road segments, obtain the corresponding road segment image, and perform information recognition on the road segment image to obtain the road segment speed limit information; Obtain the historical speed limit of the road segment from the road network data of the map road network; Based on the road segment speed limit information and the historical speed limit of the road segment, the target speed limit of the road segment is determined.

6. The method according to claim 1, wherein, The process of fusing the target trajectory speed and target speed limit of the at least one road segment to obtain the recommended speed for each road segment includes: For any of the aforementioned road segments, a reference speed for the road segment is determined based on the target trajectory speed and target speed limit of the road segment, combined with at least one of the road grade and road type of the road to which the road segment belongs; The reference speeds of each road segment in the road are weighted and summed to obtain the first speed; Based on the first speed, the recommended speed for the road segment is determined.

7. The method according to claim 1, wherein, The roads are multiple; the method further includes: Based on the recommended speed of each road segment in the plurality of roads, the plurality of roads are examined to determine whether there are target road segments with abnormal speeds in the plurality of roads; If the target road segment is determined to exist, a first road segment adjacent to the target road segment is determined based on the topological relationship of the plurality of roads; The recommended speed for the target road segment is adjusted based on the recommended speed corresponding to the first road segment.

8. The method according to claim 7, wherein, The step of examining the multiple roads based on the recommended speeds of each road segment within the multiple roads to determine whether there are target road segments with abnormal speeds includes: For any one of the plurality of roads, in response to the recommended speed corresponding to the road segment not being included in the set speed value range, the road segment is determined to be the target road segment; and / or, For any one of the plurality of roads, the road segment is determined as the target road segment based on the fact that the difference between the recommended speed of the road segment and the recommended speed of the adjacent road segment is greater than a set difference threshold.

9. The method according to claim 1, wherein, The target trajectory points are multiple; determining the target trajectory speed of the road segment based on the speed values ​​corresponding to the target trajectory points includes: Obtain the weight of any of the target trajectory points; Based on the weights of each target trajectory point, the speed values ​​corresponding to multiple target trajectory points are weighted and summed to obtain the target trajectory speed of the road segment.

10. The method according to claim 9, wherein, The step of obtaining the weight of any of the target trajectory points includes: For any of the target trajectory points, the distance between the target trajectory point and the road segment is determined based on the location information of the target trajectory point and the location information of the road segment. Obtain the time matching degree between the timestamp information of the target trajectory point and the current time; The weight of the target trajectory point is determined based on at least one of the distance and the time matching information.

11. The method according to claim 10, wherein, The step of obtaining the time matching degree between the timestamp information of the target trajectory point and the current time includes: Since the timestamp information of the target trajectory point and the current time both belong to the same preset time period, the time matching degree is determined to be a set value. In response to the fact that the timestamp information of the target trajectory point and the current time do not belong to the same preset time period, the time matching degree is determined based on the time difference between the timestamp information of the target trajectory point and the current time.

12. The method according to any one of claims 1-11, wherein, Each of the trajectory points has a corresponding vehicle trajectory; the vehicle trajectory data also includes timestamp information and orientation angles corresponding to the plurality of trajectory points; before determining a target trajectory point matching the road segment from the plurality of trajectory points for any one of the road segments, the method further includes at least one of the following: Filter the second trajectory point from the plurality of trajectory points; wherein the timestamp information of the second trajectory point is included within a set time value range; Filter the third trajectory point among the plurality of trajectory points; wherein, the trajectory point is the one with the third trajectory point as the vertex and the angle formed by the two adjacent trajectory points in the vehicle trajectory to which the third trajectory point belongs is greater than a set angle threshold. Filter the fourth trajectory point among the plurality of trajectory points; wherein the velocity value corresponding to the fourth trajectory point is abnormal.

13. A road speed recommendation device, wherein, The device includes: The first acquisition module is used to acquire vehicle trajectory data on roads associated with the map road network; wherein, the road includes at least one road segment, and the vehicle trajectory data includes speed values ​​corresponding to multiple trajectory points; The first determining module is used to determine, for any one of the road segments, a target trajectory point that matches the road segment from the plurality of trajectory points; The second determining module is used to determine the target trajectory speed of the road segment based on the speed value corresponding to the target trajectory point; The processing module is used to fuse the target trajectory speed and target speed limit of the at least one road segment to obtain the recommended speed for each road segment in the road; wherein the recommended speed is used to provide speed recommendations for vehicles.

14. An electronic device, comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1 to 12.

15. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1 to 12.

16. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1 to 12.

Images