Road traffic state identification method and device

Abstract

The invention provides a road traffic state recognition method and device, and relates to the technical fields of data processing, artificial intelligence, large models and the like. The method comprises the following steps: preprocessing multi-source trajectory data to obtain first trajectory data; wherein the multi-source trajectory data is trajectory data from a plurality of data sources; segmenting a target road of which the road traffic state is to be identified to obtain a plurality of road segments of the target road; wherein the target road is determined based on first road network data matched with the first track data; determining speed information of the plurality of road segments according to second track data matched with the plurality of road segments in the first track data; determining a road traffic state of the target road according to the speed information of the plurality of road segments; wherein the road passing state is used for indicating whether the target road passes normally or not.

Description

Technical Field

[0001] This disclosure relates to the technical fields of data processing, artificial intelligence, and large models, and in particular to a method and apparatus for recognizing road traffic conditions. Background Technology

[0002] Road traffic status (such as smooth or congested) directly reflects the road's capacity and provides a reference for route planning. Incomplete or inaccurate road traffic status can prevent navigation systems from promptly avoiding congested roads, impacting user experience. Summary of the Invention

[0003] This disclosure provides a method and apparatus for identifying road traffic conditions.

[0004] According to one aspect of this disclosure, a method for identifying road traffic status is provided. The method includes: preprocessing multi-source trajectory data to obtain first trajectory data; wherein the multi-source trajectory data is trajectory data from multiple data sources; segmenting a target road whose traffic status needs to be identified to obtain multiple road segments of the target road; wherein the target road is determined based on first road network data matched with the first trajectory data; determining speed information of the multiple road segments based on second trajectory data matching the multiple road segments in the first trajectory data; and determining the road traffic status of the target road based on the speed information of the multiple road segments; wherein the road traffic status is used to indicate whether the target road is open to traffic.

[0005] According to another aspect of this disclosure, a road traffic status identification device is provided. The device includes: a processing module for preprocessing multi-source trajectory data to obtain first trajectory data; wherein the multi-source trajectory data is trajectory data from multiple data sources; a segmentation module for segmenting a target road whose road traffic status needs to be identified to obtain multiple road segments of the target road; wherein the target road is determined based on first road network data matched with the first trajectory data; a first determination module for determining speed information of the multiple road segments based on second trajectory data in the first trajectory data that matches the multiple road segments; and a second determination module for determining the road traffic status of the target road based on the speed information of the multiple road segments; wherein the road traffic status is used to indicate whether the target road is open to traffic normally.

[0006] According to another aspect of this disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the road traffic status recognition method proposed above in this disclosure.

[0007] According to another aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions for causing the computer to execute the road traffic status recognition method proposed above in this disclosure.

[0008] According to another aspect of this disclosure, a computer program product is provided, including a computer program / instructions that, when executed by a processor, implement the road traffic status recognition method proposed above in this disclosure.

[0009] 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

[0010] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein: Figure 1 A schematic flowchart illustrating a road traffic status recognition method provided in this embodiment of the disclosure; Figure 2(a) is a schematic diagram of trajectory matching provided in an embodiment of this disclosure; Figure 2(b) is a schematic diagram of speed information for road segments provided in an embodiment of this disclosure; Figure 3 A flowchart illustrating another road traffic status recognition method provided in this embodiment of the disclosure; Figure 4(a) is a schematic diagram of an abnormal trajectory point determination provided by an embodiment of this disclosure; Figure 4(b) is a schematic diagram of a large model for determining the difficulty of passage according to an embodiment of this disclosure; Figure 5 A flowchart illustrating another road traffic status recognition method provided in this embodiment of the disclosure; Figure 6 A schematic diagram illustrating the principle of a road traffic status recognition method provided in this embodiment of the disclosure; Figure 7 This is a schematic diagram of the structure of a road traffic status recognition device provided in an embodiment of the present disclosure; Figure 8A schematic block diagram of an example electronic device 800 that can be used to implement embodiments of the present disclosure is shown. Detailed Implementation

[0011] 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.

[0012] The road traffic status recognition method and apparatus of this disclosure are described below with reference to the accompanying drawings.

[0013] Figure 1 This is a flowchart illustrating a road traffic status recognition method provided in an embodiment of the present disclosure.

[0014] like Figure 1 As shown, the road traffic status recognition method may include the following steps: Step S101: Preprocess the multi-source trajectory data to obtain the first trajectory data.

[0015] It should be noted that the execution entity of the road traffic status recognition method in this disclosure embodiment can be a hardware device with data processing capabilities and / or the necessary software to drive the hardware device. Optionally, the execution entity may include a server, a user terminal, and other intelligent devices. Optionally, the user terminal includes, but is not limited to, mobile phones, computers, intelligent voice interaction devices, etc. Optionally, the server includes, but is not limited to, a network server, an application server, or a server of a distributed system, or a server combined with blockchain, etc. This disclosure embodiment does not impose specific limitations.

[0016] Multi-source trajectory data refers to trajectory data from multiple data sources.

[0017] The data source may include at least one of the following: user terminal, in-vehicle equipment, IoT (Internet of Things) sensing device (such as a positioning chip on a shared mobility vehicle).

[0018] Trajectory data is a data sequence that records the positional information of a moving object (such as a person or vehicle) over time. Trajectory data includes the time information and positional information of trajectory points, as well as possible additional information (such as the speed, direction of movement, and type of trajectory point (such as stationary point or moving point)), and is used to describe the movement path of the moving object at continuous or discrete points in time.

[0019] As an example, multi-source trajectory data can include crowdsourced trajectory data and intelligent driving high-precision trajectory data. Crowdsourced trajectory data is trajectory data generated unintentionally by a large number of ordinary users or devices, such as trajectory data generated when a user turns on navigation in map software on a user terminal or in-vehicle device. Intelligent driving high-precision trajectory data is trajectory data collected by professionally equipped vehicles with high-precision positioning and multiple types of sensors.

[0020] The first trajectory data can be the trajectory data of the target object. The target object can be any moving object on the road, such as a motor vehicle.

[0021] Due to equipment malfunctions, signal errors, etc., multi-source trajectory data may contain noisy data, such as sampling anomalies (e.g., lost trajectory points) and accuracy anomalies (e.g., trajectory point positions drifting to both sides of the road). At the same time, due to red lights, congestion, etc., multi-source trajectory data may be repeatedly sampled at the same or similar locations. In addition, multi-source trajectory data includes trajectory data collected under various traffic modes, which may contain trajectory data of non-target objects. For example, when the target object is a motor vehicle, the trajectory data in the cycling navigation mode is trajectory data of a non-target object. Therefore, multi-source trajectory data needs to be preprocessed to obtain the first trajectory data.

[0022] In some embodiments, the trajectory data of the target object can be determined from the multi-source trajectory data based on the speed of the trajectory points in the multi-source trajectory data and the set speed requirement of the target object. The trajectory data of the target object can then be processed by deduplication, deletion of trajectory points drifting on both sides of the road, etc., to obtain the first trajectory data.

[0023] Specifically, the trajectory data of the target object can be determined from the multi-source trajectory data based on whether the maximum speed, average speed, and minimum speed of any trajectory data in its life cycle meet the set speed requirements of the target object.

[0024] As an example, assuming the target object is a motor vehicle, the speed requirements for the target object may include a maximum speed of <150km / h, an average speed of ≥25km / h, and a minimum speed of ≥10km / h.

[0025] Step S102: The target road whose traffic status needs to be identified is segmented to obtain multiple road segments of the target road.

[0026] The target road is determined based on the first road network data matched with the first trajectory data.

[0027] In some embodiments, the location information of the trajectory points in the first trajectory data is represented by latitude and longitude coordinates. Therefore, the first road network data matching the first trajectory data can be determined based on the location information of the trajectory points in the first trajectory data.

[0028] Road network data is geospatial data that digitally describes the structure, attributes, and connectivity of road networks in the real world. Road network data includes nodes, indicating key locations such as the start and end points, intersections, and connection points of roads; road segments (directed road segments connecting two nodes); connectivity relationships, indicating how nodes and road segments are connected (e.g., which road segment connects which two nodes, which road segments are interconnected at nodes), and possible additional information (e.g., road name, road class (e.g., expressway, urban arterial road, secondary road), number of lanes, speed limits, etc.).

[0029] The target road is the road in the first road network data whose traffic status needs to be identified. The target road can be a road segment in the first road network data, or it can be a road segment composed of multiple road segments with the same traffic direction in the first road network data.

[0030] In some embodiments, a suitable segmentation interval can be determined based on the length of the target road, and the target road can be segmented according to the segmentation interval to obtain multiple road segments.

[0031] Step S103: Determine the speed information of multiple road segments based on the second trajectory data that matches the multiple road segments in the first trajectory data.

[0032] In some embodiments, trajectory matching can be performed based on first trajectory data and first road network data to match trajectory points in the first trajectory data to roads in the first road network data. Then, for any road segment, second trajectory data matching that road segment in the first trajectory data is determined based on the matching relationship between trajectory points in the first trajectory data and roads in the first road network data.

[0033] As an example, Hidden Markov Models (HMMs) can be used for trajectory matching. The trajectory points in the first trajectory data are the observed sequence, and the actual roads traversed by the trajectory are the hidden sequence. The Viterbi algorithm is used to match the trajectory points in the first trajectory data to the roads in the first road network data. The input of the Hidden Markov Model is the first trajectory data and the first road network data. The output is the sequence of matching points on the roads in the first road network data. For example, as shown in Figure 2(a), the matching point sequence on the road in the first road network data for trajectory point T1 {1,2,3,4,5,6,7,8} is {1',2',3',4',5',6',7',8'}; the matching point sequence on the road in the first road network data for trajectory point T2 {11,12,13,14,15} is {11',12',13',14',15'}. The location information of each matching point in the matching point sequence can be indicated by the road ID and the offset. The offset can be the distance between the matching point and the start or end point of the road indicated by the road ID.

[0034] In some embodiments, for any road segment, the speed information of that road segment can be determined based on second trajectory data that matches that road segment in the first trajectory data.

[0035] The speed information for road segments includes various speeds, such as the maximum speed, minimum speed, average speed, and 80th percentile speed of the road segment.

[0036] As an example, as shown in Figure 2(b), each graphic represents the corresponding speed of a road segment of the target road. For example, a circle represents the average speed of a road segment of the target road, a square represents the 80th percentile speed of a road segment of the target road, a light gray triangle represents the maximum speed of a road segment of the target road, and a dark gray triangle represents the minimum speed of a road segment of the target road. By analyzing the speed information of multiple road segments of the target road, it is possible to determine whether there is a sudden drop in speed in a section or a situation of low speed throughout or in part of the road.

[0037] Step S104: Determine the traffic status of the target road based on the speed information of multiple road segments.

[0038] Among them, the road traffic status is used to indicate whether the target road is open to traffic.

[0039] In some embodiments, if the target road experiences a sudden drop in speed within a section or low speed throughout / part of the route, the target road is suspected to have poor traffic capacity, meaning the road traffic condition of the target road may be difficult to pass. Otherwise, the target road is determined to have good traffic capacity, meaning the road traffic condition of the target road is easy to pass.

[0040] The road traffic status recognition method provided in this disclosure can ensure the accuracy and reliability of the first trajectory data by preprocessing the multi-source trajectory data. By segmenting the target road and matching the corresponding second trajectory data of multiple road segments from the first trajectory data, the speed characteristics of each road segment can be accurately characterized, thereby achieving a reliable judgment of the road traffic status, which helps to improve the rationality of route planning and enhance the user experience.

[0041] Figure 3 This is a flowchart illustrating another road traffic status recognition method provided in an embodiment of the present disclosure.

[0042] like Figure 3 As shown, the road traffic status recognition method may include the following steps: Step S301: Preprocess the multi-source trajectory data to obtain the first trajectory data.

[0043] Multi-source trajectory data refers to trajectory data from multiple data sources.

[0044] In some embodiments, candidate first trajectory data can be determined from multi-source trajectory data; wherein the candidate first trajectory data is trajectory data of a target object; abnormal trajectory points in the candidate first trajectory data are determined; and the abnormal trajectory points are deleted from the candidate first trajectory data to obtain the first trajectory data. Thus, the first trajectory data is the trajectory data of the target object and the abnormal trajectory points in the first trajectory data have been deleted.

[0045] The target object can be any moving object on the road, such as a motor vehicle.

[0046] Among them, accurately locating and filtering the trajectory data of the target object from multi-source trajectory data can avoid interference from irrelevant trajectory data. By identifying and eliminating abnormal trajectory points in the candidate first trajectory data, trajectory deviations caused by factors such as equipment errors, environmental interference, and equipment failures can be reduced, making the final first trajectory data more consistent with the actual movement state of the target object.

[0047] In some embodiments, for any trajectory data in the multi-source trajectory data, the velocity information of the trajectory data can be determined based on the position and time information carried by the trajectory points in the trajectory data; the probability that the trajectory data is the trajectory data of the target object can be determined based on the velocity information of the trajectory data and the set velocity requirement of the target object; and the trajectory data with a probability not less than a set probability threshold can be determined as the candidate first trajectory data.

[0048] Specifically, for any trajectory point in any trajectory data, the velocity information of the trajectory point can be determined based on the position and time information carried by the trajectory point, as well as the position and time information carried by the previous trajectory point in the direction of motion. Then, based on the velocity information of multiple trajectory points in any trajectory data, the velocity information of the trajectory data can be determined.

[0049] The velocity information in the trajectory data includes various speeds, such as maximum speed, minimum speed, and average speed. Correspondingly, the set speed requirements for the target object include various speed requirements.

[0050] As an example, suppose the speed information of the trajectory data includes the maximum speed, minimum speed, and average speed of the trajectory data. The target object is a motor vehicle, and the set speed requirements for the target object may include a maximum speed < 150 km / h, a minimum speed ≥ 10 km / h, and an average speed ≥ 25 km / h. Then, based on whether the maximum speed of the trajectory data meets the maximum speed requirement of the target object, a probability value p1 can be determined; based on whether the minimum speed of the trajectory data meets the minimum speed requirement of the target object, a probability value p2 can be determined; and based on whether the average speed of the trajectory data meets the average speed requirement of the target object, a probability value p3 can be determined. Based on p1, p2, and p3, the probability that the trajectory data belongs to the target object can be determined.

[0051] For example, we can set p1=1 if the maximum speed is <150km / h, otherwise p1=0; p2=min(1, minimum speed / 10), when the minimum speed is ≥10, p2=1, when the minimum speed is <10, p2=minimum speed / 10 (probability decreases); p3=min(1, average speed / 25), when the average speed is ≥25, p3=1, when the average speed is <25, p3=average speed / 25 (probability decreases).

[0052] For example, we can set p1=0, or p2=0, or p3=0, and directly determine that the probability that the trajectory data is the trajectory data of the target object is 0; otherwise, we calculate the probability that the trajectory data is the trajectory data of the target object according to the weights assigned to p1, p2, and p3.

[0053] Specifically, based on the inherent position and time information of trajectory points, velocity information is derived, extending trajectory data from the basic spatiotemporal dimension to the motion feature dimension. This provides a judgment basis that aligns with the motion essence of the target object's trajectory data for identification. By comparing the velocity information of the trajectory data with the set velocity requirements of the target object, the probability that the trajectory data belongs to the target object is calculated. This makes the correlation judgment between the trajectory data and the target object more consistent with the motion pattern of the target object, improving the accuracy of the target object's trajectory data identification. By setting a probability threshold to filter candidate first trajectory data, irrelevant trajectory data can be quickly filtered out.

[0054] In some embodiments, determining abnormal trajectory points in the candidate first trajectory data may include at least one of the following: Based on the time information carried by the trajectory points in the candidate first trajectory data, at least one trajectory point other than the trajectory point to be retained among multiple trajectory points with the same time information is identified as an abnormal trajectory point. Based on the location information carried by the trajectory points in the candidate first trajectory data, at least one trajectory point other than the trajectory point to be retained among multiple trajectory points with a point spacing less than a set point spacing threshold is identified as an abnormal trajectory point. Based on the trajectory points in the candidate first trajectory data and the second road network data that matches the candidate first trajectory data, trajectory points that are not located in the corresponding road surface area are identified as abnormal trajectory points; Based on the trajectory points in the candidate first trajectory data and the second road network data that matches the candidate first trajectory data, trajectory points located in the corresponding road surface area but whose trajectory point density is not greater than the set point density threshold are identified as abnormal trajectory points.

[0055] If multiple trajectory points have the same time information, it means that these multiple trajectory points are repeatedly sampled trajectory points. In this case, only the first trajectory point that was repeatedly sampled (the trajectory point with the earliest time information) can be retained, and the other redundant trajectory points can be identified as abnormal trajectory points.

[0056] The point spacing is the distance between two trajectory points. The point spacing threshold can be any specified value, such as 3m.

[0057] If the distance between multiple trajectory points is less than the set distance threshold, it indicates that these trajectory points are sampled too closely. Similarly, only the trajectory point with the earliest sampling time among these multiple trajectory points can be retained, while the other trajectory points are identified as abnormal trajectory points.

[0058] As an example, assuming the target object is a motor vehicle, the candidate first trajectory data is the trajectory data of the motor vehicle. Since the motor vehicle will repeatedly or too closely sample a large number of points in a small space when it is stopped or moving at low speed, it is necessary to reasonably thin and smooth the candidate first trajectory data. For example, for the set of trajectory points with the same timestamp (repeated sampling) and the set of trajectory points that are too close (such as the distance between points is less than 3m) in the candidate first trajectory data, the trajectory point with the earliest sampling time can be retained, and the other trajectory points in the trajectory point set can be identified as abnormal trajectory points.

[0059] The road surface area can be determined based on the road location information and lane line information indicated in the second road network data. For example, the cross-sectional width of the road surface area can be determined based on the lane line information, and then the road surface area can be determined based on the road location information and the cross-sectional width of the road surface area.

[0060] Among them, the candidate first trajectory data may contain trajectory points that are not located in the corresponding road surface area. Therefore, the trajectory points in the candidate first trajectory data that are not located in the corresponding road surface area can be identified as abnormal trajectory points.

[0061] Among them, the trajectory points in the candidate first trajectory data may be located in the corresponding road surface area but drift on both sides of the road. Therefore, based on the high aggregation density of trajectory points in the road surface area and the low aggregation density at the road boundary, the trajectory points in the candidate first trajectory data that are located in the corresponding road surface area but whose trajectory point density is not greater than the set point density threshold can be identified as abnormal trajectory points.

[0062] Among these features, time-based filtering eliminates trajectory points with overlapping times, ensuring the rationality of the trajectory data sequence; location-based processing avoids excessive spatial clustering of trajectory points, reducing data noise; combined with road network data matching, it can filter out abnormal points that deviate from the actual road, enhancing the consistency between trajectory data and the real environment; and through point density threshold checking, it can identify and process trajectory points drifting on both sides of the road surface area, improving the accuracy of trajectory data.

[0063] In some embodiments, trajectory matching can be performed based on candidate first trajectory data and second road network data to determine the matching road in the second road network data for trajectory points in the candidate first trajectory data; the road surface area of ​​the matching road is determined according to the location information and lane line information of the matching road indicated in the second road network data; cluster analysis is performed on the trajectory points located in the road surface area in the candidate first trajectory data to obtain the trajectory point density of at least one cluster; wherein, any cluster includes at least one trajectory point located in the road surface area in the candidate first trajectory data; trajectory points included in clusters whose trajectory point density is not greater than a set point density threshold are determined as abnormal trajectory points.

[0064] Hidden Markov Models can be used to perform trajectory matching based on candidate first trajectory data and second road network data to determine the matching roads for trajectory points in the candidate first trajectory data in the second road network data.

[0065] As an example, as shown in Figure 4(a), assuming that the rectangular area in Figure 4(a) represents the road surface area of ​​the matching road, the point density of the clusters shown by the black circles is not greater than the set point density threshold, and the point density of the clusters shown by the gray circles is greater than the set point density threshold, then the trajectory points included in the clusters shown by the black circles can be identified as abnormal trajectory points.

[0066] One approach is to use the DBSCAN (Density-Based Spatial Clustering of Applications with Noise) clustering algorithm to perform clustering analysis on trajectory points located within the road surface area in the candidate first trajectory data.

[0067] To improve processing efficiency, the matching road can be segmented, and the above-mentioned process of determining abnormal trajectory points can be performed on multiple segments.

[0068] Specifically, by accurately matching candidate first trajectory data with second road network data, and clarifying the road surface area based on the location information and lane line information in the second road network data, a spatial benchmark that fits the actual road scenario can be provided for the identification of abnormal trajectory points. Abnormal trajectory points are determined based on the density of trajectory points located within the road network area. Clustering can be used to accurately capture the spatial distribution characteristics of trajectory points. Furthermore, based on the high clustering density of trajectory points within the road surface and the low clustering density at the road boundary, a set point density threshold can be used to accurately locate trajectory points drifting on both sides of the road.

[0069] In order to improve the accuracy of road traffic status recognition, the determined first trajectory data can be filtered to remove low-quality first trajectory data.

[0070] In some embodiments, the matching relationship between trajectory points in the first trajectory data and roads in the first road network data, as well as the matching points corresponding to the trajectory points, can be determined based on the first trajectory data and the first road network data; wherein, the matching point is the projection point of the corresponding trajectory point on the matching road indicated by the matching relationship; and the first trajectory data is filtered based on the confidence between the trajectory points in the first trajectory data and the matching points corresponding to the trajectory points.

[0071] Hidden Markov Models can be used to determine the matching relationship between trajectory points in the first trajectory data and roads in the first road network data, as well as the matching points corresponding to the trajectory points, based on the first trajectory data and the first road network data.

[0072] Specifically, for any given first trajectory data, it can be determined whether the confidence level between each trajectory point and its corresponding matching point is greater than a set confidence threshold. In response to a situation where the confidence level between at least one trajectory point and its corresponding matching point is not greater than the set confidence threshold, the first trajectory data is filtered. Thus, in the retained first trajectory data, the confidence level between each trajectory point and its corresponding matching point in each first trajectory data is greater than the set confidence threshold.

[0073] Specifically, by accurately associating the first trajectory data with the first road network data, the matching relationship between the trajectory points in the first trajectory data and the roads in the first road network data is clarified, as well as the matching points corresponding to the trajectory points. This gives the first trajectory data a real geospatial attribute. Then, filtering is performed based on the confidence between the trajectory points and the corresponding matching points, which can selectively remove low-quality first trajectory data. This makes the filtered first trajectory data more reliable in subsequent road traffic status identification, thereby improving the accuracy of subsequent road traffic status identification.

[0074] The explanation of step S301 can be found in the relevant description in any embodiment of this disclosure, and will not be repeated here.

[0075] Step S302: The target road whose traffic status needs to be identified is segmented to obtain multiple road segments of the target road.

[0076] The target road is determined based on the first road network data matched with the first trajectory data.

[0077] In some embodiments, the target road can be segmented along a target direction to obtain multiple road segments; wherein, no road segment overlaps with another, and the sum of the road lengths of the multiple road segments is the same as the road length of the target road; wherein, the target direction is perpendicular to the travel direction of the target road.

[0078] The lengths of multiple road segments can be the same or different.

[0079] In cases where multiple road segments have the same length, the segment spacing can be determined based on the length of the target road. For example, if the target road is 200m long, it can be segmented every 10m.

[0080] The system segments the target road based on the target direction (perpendicular to the road traffic direction), ensuring that each road segment does not overlap and the sum of its length is consistent with the original road length. This accurately depicts the attribute distribution and structural features of the road in the horizontal dimension.

[0081] The explanation of step S302 can be found in the relevant description in any embodiment of this disclosure, and will not be repeated here.

[0082] Step S303: Determine the speed information of multiple road segments based on the second trajectory data that matches the multiple road segments in the first trajectory data.

[0083] In some embodiments, for any road segment, second trajectory data matching the road segment in the first trajectory data can be determined based on the matching relationship between trajectory points in the first trajectory data and roads in the first road network data; for any trajectory point in the second trajectory data, the velocity information of the trajectory point can be determined based on the position and time information carried by the trajectory point, as well as the position and time information carried by the previous trajectory point in the direction of movement; and the velocity information of the road segment can be determined based on the velocity information of the trajectory points in the second trajectory data.

[0084] The matching relationship between trajectory points in the first trajectory data and roads in the first road network data can be determined using a hidden Markov model based on the first trajectory data and the first road network data.

[0085] For any road segment, the second trajectory data matching that road segment includes multiple trajectory points. For any trajectory point, the speed of that trajectory point can be determined based on the position and time of the previous trajectory point in the direction of movement. Then, statistical analysis can be performed based on the speeds of these multiple trajectory points to obtain the speed information of the road segment. The speed information of the road segment includes various different speeds, such as the maximum speed, minimum speed, average speed, and 80th percentile speed of the road segment.

[0086] Specifically, by matching the trajectory points in the first trajectory data with the roads in the first road network data, valid trajectory data is filtered out. Based on the location and time information of continuous trajectory points, the speed information of a single trajectory point is calculated, thereby aggregating the speed information of road segments. This ensures the accuracy of speed calculation and can truly reflect the actual traffic conditions of road segments.

[0087] In some embodiments, to avoid the accuracy of speed information being affected by the missing second trajectory data of some road segments, linear interpolation can be performed based on the second trajectory data of multiple road segments to fill in the missing second trajectory data.

[0088] In response to the existence of target road segments, linear interpolation can be performed on the second trajectory data matched by multiple road segments of the target road to supplement the second trajectory data matched by the target road segments; wherein the number of trajectory points in the second trajectory data matched by the target road segments does not meet the set number requirement.

[0089] Among them, linear interpolation based on the second trajectory data matched by multiple road segments can achieve accurate matching relationship based on road segments, perform linear interpolation that conforms to the actual road topology, ensure that the filled second trajectory data is highly consistent with the actual traffic conditions, and thus ensure the accuracy of the speed information of road segments.

[0090] The explanation of step S303 can be found in the relevant description in any embodiment of this disclosure, and will not be repeated here.

[0091] Step S304: Based on the speed information of multiple road segments, determine whether the target road is a candidate road with abnormal traffic.

[0092] In some embodiments, based on the speed information of any two adjacent road segments in a plurality of road segments, it can be determined whether there is speed difference information between two adjacent road segments in the target road that meets a set speed difference requirement; if so, the target road is determined as a candidate abnormal traffic road; or, in response to the speed information of multiple road segments not meeting the set minimum speed requirement, the target road is determined as a candidate abnormal traffic road.

[0093] The set speed difference requirement indicates that the speed difference meets the requirement of a sudden decrease in speed. For example, the set speed difference requirement may include at least one of the following: The speed difference between the maximum speeds meets the set maximum speed difference threshold. The speed difference between the minimum speeds meets the set minimum speed difference threshold. The speed difference between the average speeds meets the set average speed difference threshold.

[0094] If the speed difference information between two adjacent road segments in the target road meets the set speed difference requirement, it indicates that there is a sudden drop in speed in the target road section. In this case, the target road can be considered to have poor traffic capacity and the target road can be identified as a candidate road with abnormal traffic.

[0095] As an example, if the maximum speed of two adjacent road segments in a target road drops from 90 km / h to 30 km / h, the average speed drops from 55 km / h to 35 km / h, and the minimum speed drops from 40 km / h to 20 km / h, then the target road can be considered to have a sudden drop in speed within a section, and the target road can be identified as a candidate road with abnormal traffic.

[0096] The speed information for road segments includes various speeds. Similarly, the minimum speed requirement can also include various minimum speed requirements, such as minimum speed requirements for maximum speed, minimum speed, average speed, and 80th percentile speed.

[0097] If the speed information of multiple road segments in the target road does not meet the set minimum speed requirement, it indicates that the target road is at low speed throughout. In this case, the target road can be considered to have poor traffic capacity and the target road can be identified as a candidate road with abnormal traffic.

[0098] Specifically, based on the speed difference detection between two adjacent road segments within the target road, it can sensitively capture sudden changes in local traffic flow (such as a sudden drop in speed due to congestion or an accident); based on the minimum speed detection of all road segments within the target road, it can achieve coverage of all slow-moving roads. This enables efficient identification of roads with potential traffic anomalies.

[0099] Step S305: If not, then determine that the road traffic status of the target road is normal.

[0100] If, based on the speed information of multiple road segments, it is determined that the target road is not a candidate road with abnormal traffic, then the traffic status of the target road can be determined as normal.

[0101] The target road is in normal traffic condition, meaning that the target road is easy to pass through and there are no obvious obstacles.

[0102] Step S306: If yes, then use the large model based on the acquired images and prompt text templates of the target road to generate information on the difficulty of passing through the target road.

[0103] The prompt text template is used to generate information to determine the difficulty of passage.

[0104] If the target road is determined to be a candidate road with abnormal traffic based on the speed information of multiple road segments, then in order to improve the accuracy of road traffic status recognition, a large model can be used to combine the collected images of the target road with the prompt text template for further judgment.

[0105] In some embodiments, images of the target road can be acquired, and a large model can be used to generate information on the difficulty of passing the target road based on the acquired images of the target road and the prompt text template.

[0106] Among them, the large model can be VLM (Vision-Language Model).

[0107] As an example, a large model can include a perception layer, an inference layer, and a decision layer. The perception layer extracts key elements from the input image to generate perceptual information. For example, the perception layer extracts key elements such as "overall road width," "ground material," "presence or absence of roadblocks," and "roadblock shape" from the input image to form a structured environmental description. The inference layer performs traffic inference based on the perceptual information output by the perception layer and the domain knowledge base to generate inference results. For example, the domain knowledge base includes rules such as "width-restricted stone blocks usually result in single-lane traffic" and "construction barriers are often accompanied by temporary passages." The inference layer infers whether smooth passage is possible. The decision layer generates information to judge the difficulty of passage based on the inference results output by the inference layer.

[0108] The information on the difficulty of passage includes the judgment result (such as "difficult / easy to pass") and the judgment basis (such as "narrow road surface, difficult to pass"), in order to enhance the interpretability of the information on the difficulty of passage.

[0109] As an example, as shown in Figure 4(b), the large model, based on the sampled image of the target road and the prompt text template, can generate the following information indicating the ease of passage, as shown in Figure 4(b): The image shows a vehicle stopped at an intersection with width-restricting bollards. The bollards occupy most of the road surface, making the road too narrow for a single vehicle to pass through. The vehicle in the image is traveling at a speed of 6 km / h. Based on this situation, it can be determined that the road is difficult to pass through.

[0110] Step S307: Determine the road traffic status of the target road based on the information on the difficulty of passing through the target road.

[0111] In some embodiments, in response to the difficulty of passage of the target road indicating that passage is difficult, the road traffic status of the target road is determined to be abnormal; in response to the difficulty of passage of the target road indicating that passage is easy, the road traffic status of the target road is determined to be normal.

[0112] The target road is in normal traffic condition, meaning that the target road is easy to pass through and there are no obvious obstacles.

[0113] Among them, the road traffic status of the target road is abnormal, that is, the target road is difficult to pass and there are corresponding traffic obstacles (such as narrow roads, dirt roads, width-limiting stone blocks, construction, etc.).

[0114] In particular, when the speed information of multiple road segments in the target road is used to determine that the target road is suspected to have poor traffic capacity, the road traffic status of the target road is determined to be abnormal only when the output of the large model also indicates that the target road is difficult to pass. This can avoid the misjudgment of road traffic abnormality based solely on speed information and ensure the accuracy of target road traffic abnormality identification.

[0115] The road traffic status recognition method provided in this disclosure performs rapid and extensive preliminary screening based on the speed information of multiple road segments in the target road, accurately identifying roads suspected of having poor traffic capacity, thereby avoiding the resource consumption of large-scale image analysis of all roads by a large model. Subsequently, when it is determined that the target road is suspected of having poor traffic capacity based on the speed information of multiple road segments in the target road, a large model is specifically introduced to perform deep visual understanding of the target road. By combining image and text prompts, the road traffic status of the target road is determined, which further realizes the accurate recognition and confirmation of road traffic status. Thus, through data filtering and fine-grained perception by artificial intelligence, the accuracy of road traffic status recognition can be improved.

[0116] Figure 5 This is a flowchart illustrating another road traffic status recognition method provided in an embodiment of the present disclosure.

[0117] like Figure 5 As shown, the road traffic status recognition method may include the following steps: Step S501: Preprocess the multi-source trajectory data to obtain the first trajectory data.

[0118] Multi-source trajectory data refers to trajectory data from multiple data sources.

[0119] Step S502: The target road whose traffic status needs to be identified is segmented to obtain multiple road segments of the target road.

[0120] The target road is determined based on the first road network data matched with the first trajectory data.

[0121] Step S503: Determine the speed information of multiple road segments based on the second trajectory data that matches the multiple road segments in the first trajectory data.

[0122] Step S504: Determine the traffic status of the target road based on the speed information of multiple road segments.

[0123] The explanation of steps S501-S504 can be found in the relevant descriptions in any embodiment of this disclosure, and will not be repeated here.

[0124] Step S505: Based on the matching relationship between the trajectory points in the first trajectory data and the roads in the first road network data, determine the number of first trajectory data matching the roads in the road network topology relationship indicated by the first road network data.

[0125] The matching relationship between trajectory points in the first trajectory data and roads in the first road network data can be determined using a hidden Markov model based on the first trajectory data and the first road network data.

[0126] Step S506: Determine the trajectory flow of the road in the road network topology relationship based on the number of first trajectory data matched by the road in the road network topology relationship indicated by the first road network data.

[0127] In some embodiments, the number of first trajectory data matching roads in the road network topology relationship indicated by the first road network data can be used as the trajectory flow of that road.

[0128] Step S507: Aggregate roads with the same trajectory flow in the road network topology to obtain at least one road chain.

[0129] In some embodiments, multiple road segments with the same trajectory flow and interconnectedness in the road network topology can be identified as a road chain.

[0130] Step S508: In response to the fact that at least one road segment in any road chain has a road traffic status of abnormal, update the road traffic status of the road chain to abnormal.

[0131] In some embodiments, if at least one road in any road chain has a road traffic status of abnormal, the road notification status of all roads in that road chain can be updated to abnormal.

[0132] The road traffic status recognition method provided in this disclosure aggregates roads with similar trajectory traffic into road chains, and realizes rapid linkage update of the traffic status of the entire road chain based on the abnormal traffic status of local road segments within the road chain. This helps to improve the rationality of route planning and enhance user experience.

[0133] To clearly illustrate the above embodiments, examples are given below.

[0134] Figure 6 This is a schematic diagram illustrating the principle of a road traffic status recognition method provided in an embodiment of this disclosure.

[0135] like Figure 6 As shown, the road traffic status recognition method includes: First, determine the speed information of multiple road segments of the target road.

[0136] The process involves preprocessing multi-source trajectory data to obtain first trajectory data; segmenting the target road whose traffic status needs to be identified to obtain multiple road segments of the target road (wherein, the target road is determined based on first road network data matched with the first trajectory data); and determining the speed information of multiple road segments based on second trajectory data that matches the multiple road segments in the first trajectory data.

[0137] The specific implementation process is described above and will not be repeated here.

[0138] Next, the speed information of multiple road segments of the target road is analyzed. If there is a sudden drop in speed in a local area, the target road is considered to have poor traffic capacity. At this time, one or more images of the target road can be acquired. The large model outputs the traffic difficulty judgment information of the target road based on the acquired images of the target road and the prompt text template.

[0139] Alternatively, if the target road is traveled at low speeds throughout, it may be considered to have poor traffic capacity, and a large model may be used for further assessment.

[0140] In related technologies, road-level speed data is often affected by the high speeds in certain road segments, significantly impacting the overall speed and failing to accurately represent local traffic capacity. This disclosure, however, analyzes speed information from multiple road segments to initially determine the road's traffic status. Furthermore, when a road is suspected of having poor traffic capacity, a large model is used based on collected road images and prompt text templates to generate information assessing the difficulty of traffic flow. This further clarifies whether the road is indeed difficult to navigate, enabling precise identification and confirmation of road traffic status and improving the accuracy of traffic status recognition.

[0141] Figure 7 This is a schematic diagram of the structure of a road traffic status recognition device provided in an embodiment of this disclosure.

[0142] like Figure 7 As shown, the road traffic status recognition device 700 of this embodiment includes a processing module 701, a segmentation module 702, a first determination module 703, and a second determination module 704.

[0143] The processing module 701 is used to preprocess the multi-source trajectory data to obtain the first trajectory data; wherein, the multi-source trajectory data is trajectory data from multiple data sources; The segmentation module 702 is used to segment the target road whose traffic status needs to be identified into multiple road segments; wherein the target road is determined based on the first road network data matched with the first trajectory data. The first determining module 703 is used to determine the speed information of multiple road segments based on the second trajectory data that matches the multiple road segments in the first trajectory data; The second determining module 704 is used to determine the road traffic status of the target road based on the speed information of multiple road segments; wherein, the road traffic status is used to indicate whether the target road is open to traffic.

[0144] In one embodiment of this disclosure, the second determining module 704 is further configured to: determine whether the target road is a candidate abnormal traffic road based on the speed information of multiple road segments; if not, determine that the traffic status of the target road is normal; if so, use a large model based on the acquired image of the target road and the prompt text template to generate traffic difficulty judgment information of the target road; wherein, the prompt text template is used for generating traffic difficulty judgment information; and determine the traffic status of the target road based on the traffic difficulty judgment information of the target road.

[0145] In one embodiment of this disclosure, the second determining module 704 is further configured to: determine whether there is speed difference information between two adjacent road segments in the target road that meets the set speed difference requirement based on the speed information of any two adjacent road segments in the plurality of road segments; if so, determine the target road as a candidate abnormal traffic road; or, in response to the speed information of the plurality of road segments not meeting the set minimum speed requirement, determine the target road as a candidate abnormal traffic road.

[0146] In one embodiment of this disclosure, the second determining module 704 is further configured to: determine the road traffic status of the target road as abnormal in response to the difficulty of traffic assessment information of the target road indicating difficulty of traffic; and determine the road traffic status of the target road as normal in response to the difficulty of traffic assessment information of the target road indicating ease of traffic.

[0147] In one embodiment of this disclosure, the first determining module 703 is further configured to: for any road segment, determine second trajectory data in the first trajectory data that matches the road segment based on the matching relationship between trajectory points in the first trajectory data and roads in the first road network data; for any trajectory point in the second trajectory data, determine the speed information of the trajectory point based on the position and time information carried by the trajectory point, and the position and time information carried by the previous trajectory point in the direction of movement; and determine the speed information of the road segment based on the speed information of the trajectory points in the second trajectory data.

[0148] In one embodiment of this disclosure, the apparatus further includes a filling module for performing linear interpolation based on second trajectory data matched from multiple road segments to fill in missing second trajectory data.

[0149] In one embodiment of this disclosure, the segmentation module 702 is further configured to: segment the target road in a target direction to obtain multiple road segments; wherein, any road segment does not overlap with each other, and the sum of the road lengths of the multiple road segments is the same as the road length of the target road; wherein, the target direction is perpendicular to the traffic direction of the target road.

[0150] In one embodiment of this disclosure, the processing module 701 includes: a first determining unit, configured to determine candidate first trajectory data from multi-source trajectory data; wherein the candidate first trajectory data is trajectory data of a target object; a second determining unit, configured to determine abnormal trajectory points in the candidate first trajectory data; and a deletion unit, configured to delete the abnormal trajectory points from the candidate first trajectory data to obtain the first trajectory data.

[0151] In one embodiment of this disclosure, the first determining unit is further configured to: determine the speed information of any trajectory data in the multi-source trajectory data based on the position information and time information carried by the trajectory points in the trajectory data; determine the probability that the trajectory data is the trajectory data of the target object based on the speed information of the trajectory data and the set speed requirement of the target object; and determine the trajectory data with a probability not less than a set probability threshold as candidate first trajectory data.

[0152] In one embodiment of this disclosure, the second determining unit is further configured to perform at least one of the following: determining at least one trajectory point other than the trajectory point to be retained from a plurality of trajectory points with the same time information as abnormal trajectory points based on the time information carried by the trajectory points in the candidate first trajectory data; determining at least one trajectory point other than the trajectory point to be retained from a plurality of trajectory points with a point spacing less than a set point spacing threshold as abnormal trajectory points based on the position information carried by the trajectory points in the candidate first trajectory data; determining trajectory points not located in the corresponding road surface area as abnormal trajectory points based on the second road network data matching the trajectory points in the candidate first trajectory data and the candidate first trajectory data; and determining trajectory points located in the corresponding road surface area but with a trajectory point density not greater than a set point density threshold as abnormal trajectory points based on the trajectory points in the candidate first trajectory data and the second road network data matching the candidate first trajectory data.

[0153] In one embodiment of this disclosure, the second determining unit is further configured to: perform trajectory matching based on candidate first trajectory data and second road network data to determine the matching road in the second road network data for trajectory points in the candidate first trajectory data; determine the road surface area of ​​the matching road according to the location information and lane line information of the matching road indicated in the second road network data; perform cluster analysis on the trajectory points located in the road surface area in the candidate first trajectory data to obtain the trajectory point density of at least one cluster; wherein any cluster includes at least one trajectory point located in the road surface area in the candidate first trajectory data; and determine the trajectory points included in the clusters whose trajectory point density is not greater than a set point density threshold as abnormal trajectory points.

[0154] In one embodiment of this disclosure, the apparatus further includes: a third determining module, configured to determine the number of first trajectory data matching roads in the road network topology relationship indicated by the first road network data based on the matching relationship between trajectory points in the first trajectory data and roads in the first road network data; a fourth determining module, configured to determine the trajectory traffic of roads in the road network topology relationship based on the number of first trajectory data matching roads in the road network topology relationship indicated by the first road network data; an aggregation module, configured to aggregate roads with the same trajectory traffic in the road network topology relationship to obtain at least one road chain; and an updating module, configured to update the road traffic status of the road chain to "traffic abnormal" in response to the existence of at least one road segment in any road chain having a traffic abnormality.

[0155] In one embodiment of this disclosure, the above-mentioned apparatus further includes: a fifth determining module, configured to determine, based on the first trajectory data and the first road network data, the matching relationship between the trajectory points in the first trajectory data and the roads in the first road network data, and the matching points corresponding to the trajectory points; wherein, the matching point is the projection point of the corresponding trajectory point on the matching road indicated by the matching relationship; and a filtering module, configured to filter the first trajectory data based on the confidence level between the trajectory points in the first trajectory data and the matching points corresponding to the trajectory points.

[0156] The road traffic status recognition device provided in this embodiment can ensure the accuracy and reliability of the first trajectory data by preprocessing the multi-source trajectory data. By segmenting the target road and matching the corresponding second trajectory data of multiple road segments from the first trajectory data, the speed characteristics of each road segment can be accurately characterized, thereby achieving a reliable judgment of the road traffic status, which helps to improve the rationality of route planning and enhance the user experience.

[0157] The acquisition, storage, and application of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0158] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0159] Figure 8 A schematic block diagram of an example electronic device 800 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.

[0160] like Figure 8 As shown, device 800 includes a computing unit 801, which can perform various appropriate actions and processes based on computer programs / instructions stored in read-only memory (ROM) 802 or loaded from storage unit 808 into random access memory (RAM) 803. RAM 803 may also store various programs and data required for the operation of device 800. The computing unit 801, ROM 802, and RAM 803 are interconnected via bus 804. Input / output (I / O) interface 805 is also connected to bus 804.

[0161] Multiple components in device 800 are connected to I / O interface 805, including: input units 806 such as keyboard, mouse, etc.; output units 807 such as various types of displays, speakers, etc.; storage units 808 such as disks, optical disks, etc.; and communication units 809 such as network cards, modems, wireless transceivers, etc. Communication unit 809 allows device 800 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0162] The computing unit 801 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 801 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 801 performs the various methods and processes described above, such as the road traffic condition recognition method. For example, in some embodiments, the road traffic condition recognition method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 808. In some embodiments, part or all of the computer program / instructions may be loaded and / or installed on device 800 via ROM 802 and / or communication unit 809. When the computer program / instructions are loaded into RAM 803 and executed by the computing unit 801, one or more steps of the road traffic condition recognition method described above may be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to perform a road traffic status recognition method by any other suitable means (e.g., by means of firmware).

[0163] Various implementations 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 implementations may include: implementations in one or more computer programs / instructions 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 transferring data and instructions to the storage system, the at least one input device, and the at least one output device.

[0164] 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.

[0165] 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.

[0166] 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).

[0167] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users 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., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), the Internet, and blockchain networks.

[0168] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. The client-server relationship is created by computer programs / instructions 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.

[0169] 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 the 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 document does not impose any restrictions.

[0170] 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 method for identifying road traffic status, the method comprising: The multi-source trajectory data is preprocessed to obtain the first trajectory data; wherein, the multi-source trajectory data is trajectory data from multiple data sources; The target road whose traffic status needs to be identified is segmented to obtain multiple road segments of the target road; wherein, the target road is determined based on the first road network data matched with the first trajectory data; Based on the second trajectory data that matches the multiple road segments in the first trajectory data, the speed information of the multiple road segments is determined; Based on the speed information of the multiple road segments, the road traffic status of the target road is determined; wherein, the road traffic status is used to indicate whether the target road is open to traffic.

2. The method according to claim 1, wherein, Determining the road traffic status of the target road based on the speed information of the multiple road segments includes: Based on the speed information of the multiple road segments, determine whether the target road is a candidate road with abnormal traffic. If not, then the road traffic status of the target road is determined to be normal. If so, a large model is used to generate information on the difficulty of passage of the target road based on the acquired images and prompt text templates of the target road; wherein, the prompt text templates are used to generate information on the difficulty of passage. Based on the information regarding the difficulty of passage of the target road, the road traffic status of the target road is determined.

3. The method of claim 2, wherein, The step of determining whether the target road is a candidate road with abnormal traffic based on the speed information of the multiple road segments includes: Based on the speed information of any two adjacent road segments in the plurality of road segments, determine whether there is speed difference information between two adjacent road segments in the target road that meets the set speed difference requirement; If it exists, then the target road is determined to be the candidate road with abnormal traffic. or, In response to the speed information of the multiple road segments not meeting the set minimum speed requirement, the target road is determined as the candidate abnormal traffic road.

4. The method of claim 2, wherein, The step of determining the road traffic status of the target road based on the traffic difficulty assessment information of the target road includes: In response to the difficulty of passage of the target road indicating that passage is difficult, the road traffic status of the target road is determined to be abnormal. In response to the difficulty of passage information of the target road indicating that passage is easy, the road traffic status of the target road is determined to be normal.

5. The method of claim 1, wherein, The step of determining the speed information of the plurality of road segments based on the second trajectory data that matches the plurality of road segments in the first trajectory data includes: For any of the road segments, based on the matching relationship between the trajectory points in the first trajectory data and the roads in the first road network data, determine the second trajectory data that matches the road segment in the first trajectory data; For any of the trajectory points in the second trajectory data, the velocity information of the trajectory point is determined based on the position and time information carried by the trajectory point, and the position and time information carried by the previous trajectory point in the direction of motion. Based on the speed information of the trajectory points in the second trajectory data, the speed information of the road segment is determined.

6. The method of claim 5, wherein, The method further includes: Linear interpolation is performed based on the second trajectory data matched by the multiple road segments to fill in the missing second trajectory data.

7. The method of claim 1, wherein, The target road whose traffic status needs to be identified is segmented to obtain multiple road segments of the target road, including: The target road is divided into segments along the target direction to obtain multiple road segments; wherein, no two road segments overlap, and the sum of the lengths of the multiple road segments is the same as the length of the target road; The target direction is perpendicular to the travel direction of the target road.

8. The method of claim 1, wherein, The preprocessing of multi-source trajectory data to obtain the first trajectory data includes: Candidate first trajectory data is determined from the multi-source trajectory data; wherein, the candidate first trajectory data is the trajectory data of the target object; Identify the abnormal trajectory points in the candidate first trajectory data; The abnormal trajectory points are deleted from the candidate first trajectory data to obtain the first trajectory data.

9. The method of claim 8, wherein, The step of determining candidate first trajectory data from the multi-source trajectory data includes: For any of the trajectory data in the multi-source trajectory data, the velocity information of the trajectory data is determined based on the position information and time information carried by the trajectory points in the trajectory data; Based on the speed information of the trajectory data and the set speed requirement of the target object, determine the probability that the trajectory data is the trajectory data of the target object; The trajectory data with a probability not less than a set probability threshold are determined as the candidate first trajectory data.

10. The method of claim 8, wherein, Determining abnormal trajectory points in the candidate first trajectory data includes at least one of the following: Based on the time information carried by the trajectory points in the candidate first trajectory data, at least one trajectory point other than the trajectory point to be retained among multiple trajectory points with the same time information is determined as the abnormal trajectory point. Based on the position information carried by the trajectory points in the candidate first trajectory data, at least one trajectory point other than the trajectory point to be retained among multiple trajectory points with a point spacing less than a set point spacing threshold is determined as the abnormal trajectory point. Based on the trajectory points in the candidate first trajectory data and the second road network data that matches the candidate first trajectory data, the trajectory points that are not located in the corresponding road surface area are determined as the abnormal trajectory points; Based on the trajectory points in the candidate first trajectory data and the second road network data that matches the candidate first trajectory data, the trajectory points located in the corresponding road surface area but whose trajectory point density is not greater than a set point density threshold are determined as the abnormal trajectory points.

11. The method of claim 10, wherein, The step of determining the abnormal trajectory points as those located in the corresponding road surface area but with a trajectory point density not greater than a set point density threshold, based on the trajectory points in the candidate first trajectory data and the second road network data matched with the candidate first trajectory data, includes: Based on the candidate first trajectory data and the second road network data, trajectory matching is performed to determine the matching road in the second road network data for the trajectory points in the candidate first trajectory data. Based on the location information and lane line information of the matching road indicated in the second road network data, the road surface area of ​​the matching road is determined; Cluster analysis is performed on the trajectory points located within the road surface area in the candidate first trajectory data to obtain the trajectory point density of at least one cluster; wherein, any one of the clusters includes at least one trajectory point located within the road surface area in the candidate first trajectory data; Trajectory points included in clusters whose trajectory point density is not greater than the set point density threshold are identified as abnormal trajectory points.

12. The method of claim 1, wherein, The method further includes: Based on the matching relationship between the trajectory points in the first trajectory data and the roads in the first road network data, determine the number of first trajectory data matching the roads in the road network topology relationship indicated by the first road network data; Based on the number of first trajectory data matching roads in the road network topology relationship indicated by the first road network data, determine the trajectory flow of roads in the road network topology relationship; Aggregate roads with the same trajectory flow in the road network topology to obtain at least one road chain; In response to the existence of at least one road segment in any of the road chains having a traffic abnormality, the traffic abnormality of the road chain is updated to traffic abnormality.

13. The method according to any one of claims 1-12, wherein, The method further includes: Based on the first trajectory data and the first road network data, determine the matching relationship between the trajectory points in the first trajectory data and the roads in the first road network data, as well as the matching point corresponding to the trajectory point; wherein, the matching point is the projection point of the corresponding trajectory point on the matching road indicated by the matching relationship; The first trajectory data is filtered based on the confidence level between the trajectory points in the first trajectory data and the matching points corresponding to the trajectory points.

14. A road traffic status recognition device, the device comprising: The processing module is used to preprocess the multi-source trajectory data to obtain the first trajectory data; wherein the multi-source trajectory data is trajectory data from multiple data sources; The segmentation module is used to segment the target road whose traffic status needs to be identified into multiple road segments; wherein the target road is determined based on the first road network data matched with the first trajectory data. The first determining module is used to determine the speed information of the plurality of road segments based on the second trajectory data that matches the plurality of road segments in the first trajectory data; The second determining module is used to determine the road traffic status of the target road based on the speed information of the multiple road segments; wherein the road traffic status is used to indicate whether the target road is open to traffic.

15. 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 as described in any one of claims 1-13.

16. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method as described in any one of claims 1-13.

17. A computer program product comprising computer programs / instructions, wherein, The computer program / instructions, when executed by the processor, implement the method according to any one of claims 1-13.

Images