Road condition recognition method and device, path planning method and device, equipment and storage medium

Abstract

The invention provides a road condition recognition method, a path planning method and device, electronic equipment, a storage medium and a program product, and relates to the technical field of intelligent traffic, in particular to the technical field of Internet of Vehicles, the technical field of navigation, the technical field of big data processing and the like. According to the specific implementation scheme, respective lane passing information sets of a plurality of lanes on an abnormal road section are obtained; on the basis of the lane traffic information set, traffic identification indexes used for identifying the abnormal lane are determined, and the traffic identification indexes comprise at least one of a speed index, a distance index and a density index; and determining an abnormal lane from the plurality of lanes based on the respective traffic identification indexes of the plurality of lanes.

Description

Technical Field

[0001] The present disclosure relates to the field of smart transportation technology, in particular to the field of vehicle networking technology, navigation technology, big data processing technology, etc., and specifically to a road condition recognition method, a path planning method, a device, an electronic device, a storage medium, and a program product. Background Art

[0002] With the rapid growth in the number of vehicles, road congestion is becoming increasingly frequent and prominent. Based on the cause of congestion, road congestion can be divided into regular congestion and abnormal congestion. Regular congestion often occurs during peak hours in the morning and evening, such as during rush hour. Abnormal congestion is often caused by incidental events, such as traffic accidents and vehicle breakdowns.

[0003] Related technologies can provide navigation users with early warning information on road congestion, but it is difficult to achieve detailed early warning. Summary of the Invention

[0004] The present disclosure provides a road condition identification method, a path planning method, an apparatus, an electronic device, a storage medium, and a program product.

[0005] According to one aspect of the present disclosure, a road condition identification method is provided, comprising: obtaining a lane traffic information set for each of a plurality of lanes on an abnormal road section; determining a traffic identification index for identifying an abnormal lane based on the lane traffic information set, wherein the traffic identification index comprises at least one of the following: a speed index, a distance index, and a density index; and determining an abnormal lane from a plurality of lanes based on the traffic identification index for each of the plurality of lanes.

[0006] According to another aspect of the present disclosure, a path planning method is provided, comprising: upon determining that a vehicle is located in the abnormal road section, updating navigation information on a navigation interface to lane-level navigation information, and adding identification information for characterizing an abnormal lane in the abnormal road section;

[0007] The abnormal lane is determined by the road condition recognition method described above.

[0008] According to another aspect of the present disclosure, a road condition identification device is provided, including: a set acquisition module for obtaining a lane traffic information set of each of a plurality of lanes on an abnormal road section; an indicator identification module for determining a traffic identification index for identifying an abnormal lane based on the lane traffic information set, wherein the traffic identification index includes at least one of the following: a speed index, a distance index, and a density index; and a first lane identification module for determining an abnormal lane from a plurality of the lanes based on the traffic identification index of each of the plurality of lanes.

[0009] According to another aspect of the present disclosure, a path planning device is provided, comprising: a navigation update module for updating the navigation information of the navigation interface to lane-level navigation information when it is determined that the vehicle is in the above-mentioned abnormal road section; and an identification module for adding identification information for characterizing the abnormal lane in the above-mentioned abnormal road section; wherein the above-mentioned abnormal lane is determined by the road condition recognition device as described above.

[0010] According to another aspect of the present 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, and the instructions are executed by the at least one processor so that the at least one processor can execute the method described above.

[0011] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute the method described above.

[0012] According to another aspect of the present disclosure, a computer program product is provided, comprising a computer program, which implements the method described above when executed by a processor.

[0013] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The accompanying drawings are provided to facilitate a better understanding of the present invention and do not constitute a limitation of the present disclosure.

[0015] Figure 1 Schematically illustrates an exemplary system architecture to which the road condition identification method and apparatus according to an embodiment of the present disclosure may be applied;

[0016] Figure 2 The following schematically shows a flow chart of a road condition identification method according to an embodiment of the present disclosure;

[0017] Figure 3A The following schematically shows a flow chart of identifying abnormal lanes according to an embodiment of the present disclosure;

[0018] Figure 3B The following schematically shows a flow chart of identifying abnormal lanes according to another embodiment of the present disclosure;

[0019] Figure 4 A schematic diagram of generating a road network topology according to an embodiment of the present disclosure is schematically shown;

[0020] Figure 5 The following schematically shows a flow chart of a path planning method according to an embodiment of the present disclosure;

[0021] Figure 6 Schematically shows a state change diagram of an updated navigation interface according to an embodiment of the present disclosure;

[0022] Figure 7 Schematically shows a block diagram of a road condition recognition device according to an embodiment of the present disclosure;

[0023] Figure 8 A block diagram schematically illustrates a path planning device according to an embodiment of the present disclosure; and

[0024] Figure 9 A block diagram of an electronic device suitable for implementing a road condition identification method according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0025] The following description of exemplary embodiments of the present disclosure is made in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding. These details should be considered as merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0026] The current method for determining abnormal lanes is usually to collect vehicle driving trajectories and analyze the vehicle's lane changing behavior to determine whether there are accidents or abnormal obstacles in the lane.

[0027] However, the method of using lane change information to identify abnormal lanes requires determining the lane change trajectory based on vehicle trajectory information collected over a long period of time. This detection method is inefficient and also has certain misjudgment issues.

[0028] In view of this, an embodiment of the present disclosure provides a road condition identification method, comprising: collecting a set of lane traffic information for each of multiple lanes on an abnormal road section; determining a traffic identification index for identifying the abnormal lane based on the lane traffic information; the traffic identification index comprising at least one of the following: a speed index, a distance index, and a vehicle density index; and determining an abnormal lane from the multiple lanes based on the traffic identification index for each of the multiple lanes.

[0029] The above-described road condition identification method can further identify abnormal lanes within a road section, even if the road section is determined to be abnormal. This allows for refined identification of abnormal road conditions and enhanced warning effectiveness. Furthermore, traffic identification indicators can be determined by assembling lane traffic information for each lane. By converting directly collected information into traffic identification indicators, this improves both information utilization and the accuracy of abnormal lane identification. Furthermore, traffic identification indicators include at least one of a speed indicator, a distance indicator, and a vehicle density indicator. These indicators are correlated with lane traffic information such as speed, distance, and traffic volume, enabling the collection of instantaneous information, eliminating the need for long-term data collection for identification, thereby improving processing efficiency.

[0030] Figure 1 An exemplary system architecture to which the road condition identification method and apparatus according to an embodiment of the present disclosure can be applied is schematically shown.

[0031] It should be noted that Figure 1 The examples shown are merely examples of system architectures to which the embodiments of the present disclosure may be applied, to help those skilled in the art understand the technical content of the present disclosure, but do not mean that the embodiments of the present disclosure may not be used in other devices, systems, environments or scenarios.

[0032] like Figure 1 As shown, the system architecture 100 according to this embodiment may include a vehicle 101, a network 102, and a server 103. The network 102 is used to provide a medium for a communication link between the vehicle 101 and the server 105. The network 104 may include various connection types, such as wired and / or wireless communication links, etc.

[0033] Users can use vehicle 101 to interact with server 103 via network 102 to receive or send messages, etc. Vehicle 101 may be installed with various communication client applications, such as knowledge reading applications, web browser applications, search applications, instant messaging tools, email clients, and / or social platform software (for example only). It should be noted that users can also use other terminal devices, such as mobile phones and tablets, to interact with server 103 via network 102 to receive or send messages, as long as the server 103 can obtain driving status information of vehicle 101.

[0034] The vehicle 101 may be a vehicle driven by a person, but is not limited thereto. The vehicle 101 may also be an autonomous driving vehicle, and the type of vehicle is not limited thereto.

[0035] Server 103 may be a server that provides various services, such as a background management server that supports content viewed by users in vehicle 101 (for example only). The background management server may analyze and process received data such as user requests, and provide feedback to vehicle 101 on the processing results (e.g., web pages, information, or data obtained or generated based on user requests).

[0036] It should be noted that the road condition identification method provided in the embodiment of the present disclosure can generally be executed by the server 103. Accordingly, the road condition identification device provided in the embodiment of the present disclosure can also be set in the server 103.

[0037] It should be understood that Figure 1 The number of vehicles, networks and servers in the embodiment is only illustrative. Any number of vehicles, networks and servers may be provided as needed.

[0038] In the technical solution disclosed herein, the collection, storage, use, processing, transmission, provision, disclosure and application of user personal information involved comply with the provisions of relevant laws and regulations, take necessary confidentiality measures, and do not violate public order and good morals.

[0039] In the technical solution disclosed herein, the user's authorization or consent is obtained before obtaining or collecting the user's personal information.

[0040] It should be noted that the sequence numbers of the operations in the following method are only used to indicate the operation for the purpose of description, and should not be regarded as indicating the order in which the operations should be performed. Unless explicitly stated, the method does not need to be performed in the order shown.

[0041] Figure 2 The flowchart of the road condition identification method according to an embodiment of the present disclosure is schematically shown.

[0042] like Figure 2 As shown, the method includes operations S210 to S230.

[0043] In operation S210 , a lane traffic information set of each of a plurality of lanes on an abnormal road section is obtained.

[0044] In operation S220 , a traffic identification index for identifying abnormal lanes is determined based on the lane traffic information set.

[0045] In operation S230 , an abnormal lane is determined from among the plurality of lanes based on the traffic recognition indices of the plurality of lanes.

[0046] An abnormal road section may refer to a road section experiencing abnormal congestion. For example, a traffic accident or vehicle breakdown may have occurred on this road section. For example, in the case of a road section congestion caused by a vehicle breakdown or traffic accident, two of the multiple lanes on the abnormal road section, for example, three lanes, may be normal, while the broken-down vehicle is only parked in one lane, making only one lane abnormal. Based on lane traffic information, the abnormal and normal lanes of the abnormal road section can be identified, and the abnormal lane can be determined from multiple lanes. This provides refined traffic anomaly warnings.

[0047] A lane traffic information set may include lane traffic information for multiple vehicles. Lane traffic information may include vehicle driving status information, such as speed, location, driving direction, acceleration, etc., but is not limited to this. Lane traffic information sets may also include information such as traffic flow in the lane.

[0048] The traffic identification index may include at least one of the following: a speed index, a distance index, and a vehicle density index.

[0049] Alternatively, the speed index may be determined using information related to vehicle speed in the lane traffic information. The distance index may be determined using information related to vehicle travel distance in the lane traffic information. The vehicle density index may be determined using information related to vehicle flow in the lane traffic information.

[0050] By using the lane traffic information set to determine the traffic identification index for identifying abnormal lanes, the lane traffic information set can be further converted and refined, making the traffic identification index clear and effective.

[0051] The above-described road condition identification method can further identify abnormal lanes within a road section, even if the road section is determined to be abnormal. This allows for refined identification of abnormal road conditions and enhanced warning effectiveness. Furthermore, traffic identification indicators can be determined by assembling lane traffic information for each lane. By converting directly collected information into traffic identification indicators, this improves both information utilization and the accuracy of abnormal lane identification. Furthermore, traffic identification indicators include at least one of a speed indicator, a distance indicator, and a vehicle density indicator. These indicators are correlated with lane traffic information such as speed, distance, and traffic volume, enabling the collection of instantaneous information, eliminating the need for long-term data collection for identification, thereby improving processing efficiency.

[0052] The road condition identification method provided by the embodiment of the present disclosure can ensure the effectiveness, accuracy and fine granularity of abnormal lane identification.

[0053] According to the embodiments of the present disclosure, Figure 2Operation S220, shown as determining a traffic identification index for identifying abnormal lanes based on the lane traffic information set, may include determining, based on the lane traffic information set, a first identification index indicating average lane traffic information and a second identification index indicating the degree of dispersion of information in the lane traffic information set. The traffic identification index is obtained based on the first and second identification indicators.

[0054] The first and second identification indicators can refer to different types of identification indicators within the same dimension. For example, taking the speed indicator as an example, the first identification indicator may include the median speed or average speed, which is used to represent the average speed of vehicles in the lane. The second identification indicator may include the speed variance, which is used to represent the degree of dispersion of different vehicle speeds in the lane.

[0055] The first recognition index and the second recognition index may both be used as the pass recognition index, but the present invention is not limited thereto. Alternatively, the first recognition index and the second recognition index may be weighted and summed to obtain the pass recognition index.

[0056] The lane traffic information set includes lane traffic information from multiple vehicles at different times within a preset time period. This combines multiple driving status information across multiple dimensions, including temporal and spatial dimensions, providing comprehensive and effective reference information for screening outlier lanes. Furthermore, determining multiple identification indicators of the same type within the lane traffic information set, with varying content, allows for comprehensive analysis from various perspectives, further improving the accuracy of outlier lane identification based on these indicators.

[0057] According to an embodiment of the present disclosure, the first identification index may include at least one of the following: median speed, average distance between vehicles and the end of an abnormal road section, and the number of vehicles. The second identification index may include at least one of the following: speed variance, variance of distance between vehicles and the end of an abnormal road section, and vehicle density.

[0058] The median speed can be the median of the speeds of multiple vehicles in a single lane. For example, after arranging multiple speeds in descending order, the speed value at the middle position is used. For example, if the speeds are 2km / h, 2.5km / h, and 3km / h, the median speed is 2.5km / h. Using the median speed as the first identification metric can eliminate interference from extreme speeds, such as 20km / h, which are not of the same dimension.

[0059] Speed variance can be the variance of the speeds of multiple vehicles collected on a single lane. As the second identification metric, speed variance measures the degree of dispersion of vehicle speeds on a lane.

[0060] Optionally, the first identification index may further include a speed threshold ratio, for example, the ratio of the number of vehicles in a lane whose speed is lower than a speed threshold, such as 30 km / h, to the total number of vehicles.

[0061] Alternatively, using speed as a traffic identification metric can reveal significant speed differences between vehicles in the abnormal lane ahead and behind the accident point, due to stalled vehicles behind the accident point. Using speed variance, speed threshold ratio, and speed median as speed indicators allows for a combined analysis of the first and second identification metrics, allowing the speed indicator to quickly and significantly reflect lane congestion.

[0062] The distance variance can be the variance of the distances traveled by multiple vehicles within a preset time period, but is not limited to this. It can also be the variance of the distances between multiple vehicles and the end of the abnormal road section at a certain moment. Any distance variance that can characterize the distance distribution caused by vehicle accumulation will suffice.

[0063] The average distance may be the average distance between multiple vehicles and the end of the abnormal road section at a certain moment, but is not limited thereto. It may also be the average distance traveled by multiple vehicles within a preset time period.

[0064] Optionally, the first identification index may further include a distance threshold ratio. For example, the ratio of the number of vehicles whose distance from the end of the abnormal road section falls within the threshold to the total number of vehicles. However, this is not limited to this. The first identification index may further include a distance density, for example, the average distance of the vehicles whose nearest threshold, for example, 10%, accounts for the distance from the end of the abnormal road section.

[0065] Alternatively, using distance as a traffic identification metric can reveal significant differences in the distances traveled by vehicles in the abnormal lane ahead of and behind the accident point due to the accumulation of vehicles behind the accident point and the concentrated distance distribution. Using distance variance, distance threshold ratio, and average distance as distance indicators, the first and second identification indicators can be combined for analysis, allowing the distance indicator to significantly reflect lane congestion.

[0066] The number of vehicles may refer to, but is not limited to, the number of vehicles parked in each lane. It may also refer to the number of data points collected in each lane within a preset time period.

[0067] Vehicle density refers to the number of vehicles collected per unit distance in each lane within a preset time period.

[0068] Alternatively, using vehicle density as a traffic identification metric can reveal significant differences in vehicle distribution in the abnormal lane ahead of and behind the accident site due to the accumulation of vehicles behind the accident site and the concentrated distribution of vehicles. Using both vehicle count and vehicle density as vehicle density indicators allows for a combined analysis of the first and second identification metrics, with the density metric providing a clearer picture of lane congestion.

[0069] For example, the first identification index may include: median speed, average distance from the end of the abnormal road section, and number of vehicles. The second identification index may include: speed variance, variance of distance from the end of the abnormal road section, and vehicle density.

[0070] The first identification index represents the average value of the traffic information in the traffic information set, and the second identification index represents the degree of discreteness of the information in the traffic information set. Combining the first identification index and the second identification index, evaluation can be performed from different dimensions, thereby improving the accuracy of abnormal lane recognition.

[0071] According to an embodiment of the present disclosure, each lane may include multiple traffic identification indicators, such as a vehicle density indicator, a speed indicator, and a distance indicator.

[0072] For example Figure 2 Operation S230 shown, determining an abnormal lane from the multiple lanes based on the traffic identification indicators of the multiple lanes, may include: for each lane, if multiple traffic identification indicators all indicate that the lane is an abnormal lane, determining the lane as an abnormal lane.

[0073] For example, when the vehicle density index, the speed index, and the distance index all indicate that the lane is an abnormal lane, the lane is determined to be an abnormal lane.

[0074] If any of the multiple traffic identification indicators indicates that the lane is a normal lane, the lane identification result is determined to be a sub-fuzzy identification result. If multiple sub-fuzzy identification results are obtained, a fuzzy identification result is obtained indicating that no abnormal lane has been determined from the multiple lanes.

[0075] Preferably, the priorities of a plurality of traffic identification indicators can be preset, and the lanes can be identified in order of priority.

[0076] For example, the speed indicator can be prioritized first, the distance indicator in the middle, and the vehicle density indicator last.

[0077] Optionally, a priority order may be set based on the significance and ease of identification of traffic identification indicators as reference indicators, so that abnormal lane identification can be performed quickly, simply, and effectively using this priority order.

[0078] Optionally, both the first and second recognition indicators can be used as traffic recognition indicators. For the same type of first and second recognition indicators with different contents, they can be used together to determine if both indicate a lane anomaly. If either indicator indicates a normal lane, a sub-fuzzy recognition result is obtained.

[0079] Figure 3A The flowchart of identifying abnormal lanes according to an embodiment of the present disclosure is schematically shown.

[0080] like Figure 3A As shown, identifying an abnormal lane includes the following operations S310 to S350 .

[0081] In operation S310, using the speed index as an example of a traffic identification indicator, a determination is made as to whether the speed index indicates that the lane is an abnormal lane. The median speed may be compared with a predetermined median speed threshold, and the speed variance may be compared with a speed variance threshold. If the median speed is less than the predetermined median speed threshold and the speed variance is greater than the speed variance threshold, the speed index is determined as a traffic identification indicator, indicating that the lane is an abnormal lane, and operation S320 is executed. Otherwise, operation S350 is executed.

[0082] In operation S320, the distance indicator is used as a traffic identification indicator to determine whether the distance indicator indicates that the lane is an abnormal lane. If the average distance is less than a predetermined distance threshold and the distance variance is greater than the distance variance threshold, the distance indicator is determined as a traffic identification indicator, indicating that the lane is an abnormal lane, and operation S330 is executed. Otherwise, operation S350 is executed.

[0083] In operation S330, the density index is used as a traffic identification indicator to determine whether the density index indicates that the lane is an abnormal lane. If the vehicle density is greater than a predetermined vehicle density threshold and the number of vehicles is greater than a distance threshold, the density index is determined as a traffic identification indicator, indicating that the lane is an abnormal lane, and operation S340 is executed. Otherwise, operation S350 is executed.

[0084] In operation S340 , the lane is determined to be an abnormal lane.

[0085] In operation S350, a sub-fuzzy recognition result is determined.

[0086] By using multiple traffic recognition indicators of different types, a first recognition indicator and a second recognition indicator of the same type but different contents are used as a reference in each traffic recognition indicator to identify abnormal lanes, thereby improving recognition accuracy.

[0087] According to an embodiment of the present disclosure, determining an abnormal lane from among the multiple lanes based on traffic identification indicators for each of the multiple lanes may include: upon obtaining a fuzzy recognition result based on the traffic identification indicators for each of the multiple lanes, performing a weighted summation of the multiple traffic identification indicators for each lane to obtain a lane assessment result for each lane. The fuzzy recognition result indicates that an abnormal lane has not been determined from among the multiple lanes. Determining an abnormal lane from among the multiple lanes based on the multiple lane assessment results.

[0088] Taking an abnormal road section consisting of three lanes as an example, based on the traffic identification index, if at least one lane is determined to be an abnormal lane, the abnormal lane is determined from multiple lanes. When determining the fuzzy identification results, the multiple traffic identification indicators for each lane can be weighted summed to obtain a lane assessment result for each lane. Based on the lane assessment results of each lane, the abnormal lane is determined from the multiple lanes. For example, the lane with the smallest lane assessment result value is determined as the abnormal lane. However, this is not limited to this. Alternatively, a lane with a lane assessment result less than an assessment result threshold can be determined as an abnormal lane.

[0089] Figure 3B The figure schematically shows a schematic diagram of identifying abnormal lanes according to another embodiment of the present disclosure.

[0090] like Figure 3B The operation shown is as follows Figure 3A Executed after the operation shown.

[0091] like Figure 3B As shown, when multiple sub-fuzzy recognition results 320 corresponding to multiple lanes 310 of the abnormal road section are obtained based on multiple traffic identification indicators, a fuzzy recognition result is determined. For example, the multiple lanes include lane 1, ..., and lane L, where L is greater than or equal to 1. The multiple sub-fuzzy recognition results include the first sub-fuzzy recognition result, ..., and the Lth sub-fuzzy recognition result. The multiple traffic identification indicators for each lane can be weighted and summed to obtain a lane assessment result for each lane. The multiple lane assessment results 330 can include the first lane assessment result, ..., and the Lth lane assessment result.

[0092] Based on the plurality of lane evaluation results 330 , an abnormal lane 311 is determined from among the plurality of lanes.

[0093] According to the embodiments of the present disclosure, the traffic recognition index and lane assessment results are combined to realize the joint analysis of three different types of indicators, namely speed index, distance index and density index, and construct a dynamic weighted evaluation function, thereby highlighting the dual-channel decision-making mechanism, thereby improving the timeliness, accuracy and real-time warning effect of recognition.

[0094] According to an embodiment of the present disclosure, weighted summing of multiple traffic identification indicators for each lane to obtain a lane assessment result for each lane may include: performing normalization operations on the multiple traffic identification indicators to obtain multiple normalized traffic parameters; and performing weighted summing of the multiple normalized traffic parameters to obtain a lane assessment result for each lane.

[0095] The normalization operation may include, for example, a Z-score normalization operation as shown in the following formula (1), but is not limited thereto. Other calculation methods may also be used as long as the normalized traffic parameters can be made to belong to the same dimension.

[0096] For example, within a preset time period, lane access information is collected for each vehicle at N times. The N lane access information for each of the M vehicles is combined into a lane access information set. For example, the lane access information set includes: lane access information A-T1, ..., lane access information A-TN of vehicle A; lane access information B-T1, ..., lane access information B-TN, ... of vehicle B; and lane access information M-T1, ..., lane access information M-TN of vehicle M.

[0097] Based on the lane traffic information set, the mean and standard deviation of each different type of identification indicator can be determined.

[0098] ;Formula (1)

[0099] Wherein, X represents the traffic identification index. Represents the mean value of the traffic identification index. Indicates the standard deviation of the traffic identification index. Represents the normalized traffic parameter.

[0100] Optionally, each lane identification indicator can include a first identification indicator and a second identification indicator. These two different identification indicators may have significantly different dimensions. Using normalization, the normalized lane parameters can be set between 0 and 1. This eliminates the effects of misidentification caused by different dimensions, thereby improving the accuracy of lane assessment results.

[0101] According to an optional embodiment of the present disclosure, before performing the weighted summation operation, the road condition identification method may further include an operation of updating the weights of multiple traffic identification indicators based on environmental information so as to perform the weighted summation operation using the updated weights.

[0102] Environmental information may include weather information such as visibility, rainfall, etc., but is not limited thereto, and may also include time information such as holidays, morning and evening commuting time, etc.

[0103] The weights of different types of traffic identification indicators can be adjusted according to different environmental information to obtain weights that match the environmental information.

[0104] For example, in weather with visibility less than 50m, the weight of vehicle density can be adjusted from W density to 1.4W density. This reinforces the importance of vehicle density as a traffic identification indicator in low visibility environments.

[0105] For another example, in weather with rainfall greater than 30 mm / h, the weight of the speed variance may be adjusted from W speed variance to 0.6W speed variance, thereby suppressing interference caused by speed fluctuations.

[0106] For example, during the evening rush hour, the weight of the speed threshold ratio can be adjusted from W speed threshold ratio update to (0.15 + W speed threshold ratio update), thereby improving the sensitivity of slow-moving scenarios.

[0107] The weights of the corresponding traffic recognition indicators are reasonably adjusted according to the environmental information, thereby improving the lane assessment results obtained after weighted summation to match the actual situation, thereby improving the recognition accuracy of the lane assessment results.

[0108] For example, an environmental index may be determined based on the environmental information, and a weighted sum of the environmental index and the traffic recognition index may be performed to obtain a lane assessment result.

[0109] The lane assessment result can be determined by combining the environmental index and the traffic recognition index using the following formula (2).

[0110] ;Formula (2)

[0111] Where S represents the lane assessment result, k and j represent the sequence numbers, and K and J represent the total number of sequence numbers. represents the weight of the traffic identification index, Indicates the traffic identification index, represents the mean value of the traffic identification index, represents the standard deviation of the traffic identification index, represents the weight of the result after weighted summation of environmental indicators, represents the weight of environmental indicators, Indicates environmental indicators.

[0112] Lane assessment results are determined by combining environmental indicators with traffic recognition metrics. Traffic recognition metrics can reflect long-term accumulated driving patterns, while environmental information can fully reflect the dynamic impact of current traffic conditions. Combining environmental and traffic recognition metrics provides comprehensive, dynamic, and effective lane assessment results.

[0113] According to an embodiment of the present disclosure, when executing Figure 2 Before the operation S210 shown, the road condition identification method may further include an operation of determining whether the congested road section is an abnormal road section based on the road network topology of the congested road section and the traffic timing information of each of the multiple road sections on the road network topology within a preset time period.

[0114] Traffic sequence information can include multiple traffic information at different times within a preset time period. Unlike lane traffic information, traffic information refers to section traffic information, which is the sum of traffic information of multiple lanes on the same section.

[0115] Optionally, the road network topology may include edges and connection points between multiple edges. Edges represent road segments, and connection points represent the connectivity between each road segment.

[0116] Traffic timing information can be used as the attribute information of the road network edge and combined with the road network topology to encode a traffic feature matrix that represents the road network topology and traffic timing information. The traffic feature matrix is input into the Spatial Temporal Graph Convolutional Network (ST-GCN) to obtain the recognition result used to determine whether the congested road section is an abnormal section.

[0117] Furthermore, based on the road network topology and the traffic sequence information of each of the multiple road sections, the changes in the vehicle driving status of each road section within a preset time period can be determined to determine whether the congested road section is normal. For example, the traffic information of the congested road section at time T1 indicates that the vehicle is moving forward and the average vehicle speed is V1. In addition, the traffic information of the adjacent road section connected to the congested road section at time T1 indicates that the vehicle is in a normal traffic state. The traffic information of the congested road section at time T2 indicates that the vehicle's driving direction is turned to the adjacent road section, and the average vehicle speed has dropped below V1. In addition, the traffic information of the adjacent road section connected to the congested road section at time T2 indicates that the average vehicle speed is lower than the speed of the normal traffic state. In this case, the congested road section can be determined to be an abnormal road section.

[0118] According to the embodiments of the present disclosure, based on the road network topology and traffic sequence information of a congested road section, information from different dimensions, both temporal and spatial, can be combined for analysis. This not only improves the ability to determine whether the congested road section is abnormal, but also allows analysis of whether the congestion status of the congested road section will spread to other connected roads, thereby improving the comprehensiveness and accuracy of the analysis.

[0119] According to an embodiment of the present disclosure, before performing the operation of determining whether a congested road section is an abnormal road section as described above, the road condition identification method may further include the operations of generating a road network topology and acquiring traffic timing information.

[0120] According to embodiments of the present disclosure, a road network topology can be generated by, for example, generating an initial road network topology centered on a congested road section based on a map of the area where the congested road section is located and the relationships between multiple road sections. The initial road network topology is then updated based on real-time traffic notification information to obtain a road network topology.

[0121] The map includes information such as the geographic locations and relationships of multiple road segments. A map of the area where the congested road segment is located can be created by drawing a circle with a predetermined radius R, centered on the congested road segment. Information such as the length of each road segment, the relationships between multiple road segments, and the locations of connections can be extracted from the map to generate an initial road network topology centered on the congested road segment, with edges representing the road segments and connection points representing the connections.

[0122] Figure 4 A schematic diagram of generating a road network topology according to an embodiment of the present disclosure is schematically shown.

[0123] like Figure 4 As shown in FIG, based on the vehicle status information on the road section, the road section is determined to be a congested road section. With the congested road section as the center and the connected road sections, an initial road network topology 400 is generated, in which the road sections are represented by edges and the connection relationships are represented by connection points 420. For example, the edge 410 represents the congested road section, as shown in FIG. Figure 4 The two arrow end points of the arrow line shown represent the two ends of the congested road section.

[0124] The edges or connection points on the initial road network topology can be updated in combination with the real-time traffic notification information. Traffic notification information can include temporary information related to road traffic, such as road construction information and temporary road closure information.

[0125] like Figure 4 As shown, based on the traffic notification information, it is determined that the road section is blocked and cannot be passed. Then, in the initial road network topology 400, the edge 430 corresponding to the road section and the edge 440 corresponding to the road section adjacent to the road section can be deleted to obtain the road network topology 400'.

[0126] According to the embodiments of the present disclosure, using a map to generate an initial road network topology can improve the utilization rate of existing maps and simplify the difficulty of generating the road network topology. In addition, combined with real-time changing traffic notification information, the initial road network topology can be dynamically updated in real time, thereby improving the accuracy and flexibility of the road network topology.

[0127] For example, identification information can be added to the edges representing road segments in the road network topology to highlight the fine-grained connection relationship between congested road segments and other connected road segments. For example, the congested road segment is assigned identification information 0, the directly connected road segment is assigned identification information 1, and so on. The road segments connected through the road segment with identification information 1 are assigned identification information 2, and so on, until identification information is added to X, where X is an integer greater than or equal to 3.

[0128] By utilizing identification information, the association between multiple road sections and congested road sections in the road network topology can be improved, and the granularity of the road network topology in the spatial dimension can be improved.

[0129] According to an embodiment of the present disclosure, the traffic sequence information can be obtained in the following manner: For example, a plurality of traffic information of each road section in the road network topology at different times within a preset time period is obtained, and the traffic sequence information is obtained by arranging them in time sequence.

[0130] There are no restrictions on the preset time period. For example, it can include 5 minutes or 6 minutes. Furthermore, there are no restrictions on how the multiple collection moments within the preset time period are divided. For example, the collection moments can be divided at equal intervals or randomly. As long as multiple traffic information is collected at different times within the preset time period, it is sufficient.

[0131] For example, the longer the preset time period, the higher the reference value and the higher the accuracy of identifying abnormal road sections. Conversely, the lower the recognition efficiency. To balance recognition accuracy and processing efficiency, the preset time period can be set to 5 minutes.

[0132] Optionally, the traffic information includes at least one of the following: vehicle speed, traffic volume, lane occupancy, and vehicle driving direction.

[0133] Preferably, the traffic information may include vehicle speed, traffic volume, lane occupancy, and vehicle travel direction. The more information referenced in the traffic information, the higher the accuracy of abnormal road section identification.

[0134] In addition, arranging multiple traffic information in time sequence to obtain traffic time sequence information can significantly improve the changing trend of the vehicle's driving status over time in the time dimension and improve the accuracy of identifying abnormal road sections.

[0135] According to an embodiment of the present disclosure, multiple traffic information of each road section on the road network topology at different times within a preset time period is obtained, including: when it is determined that there is a moment of missing information, the information of the moment of missing information is supplemented based on the historical traffic information of the historical moments of the road section.

[0136] The traffic sequence information within a preset time period, for example, from 15:00 to 15:05 on March 4, may include traffic information 1 at time T1, traffic information 2 at time T2, ..., traffic information TN at time TN.

[0137] If it's determined that the traffic information 3 at time T3 is missing, the historical traffic information for time T3 between 15:00 and 15:00 5 minutes on February 4th can be used as the traffic information 3 for time T3 between 15:00 and 15:00 5 minutes on March 4th. However, this is not limiting. The average historical traffic information for times T1-T3 between 15:00 and 15:00 5 minutes on February 4th can also be used as the traffic information 3 for time T3 between 15:00 and 15:00 5 minutes on March 4th. Any method that can supplement the missing time information with historical traffic information will suffice.

[0138] By using the historical traffic information of historical moments to complete the information of the moments with missing information, the referenceability of the traffic timing information can be improved, thereby improving the recognition accuracy of abnormal road sections.

[0139] According to another embodiment of the present disclosure, the road condition identification method may further include the following operation for identifying whether the congested road section is an abnormal road section.

[0140] For example, based on the current traffic information and reference traffic information of the congested road section, the road condition of the congested road section is identified to obtain an identification result for characterizing whether the congested road section is abnormal.

[0141] The current traffic information is the traffic information at the current moment.

[0142] The reference traffic information can be the reference information under normal traffic status. The reference traffic information has the same information type as the current traffic information.

[0143] The current traffic information is compared with the reference traffic information. If there is a significant difference between the current traffic information and the reference traffic information, for example, the difference between the current traffic information and the reference traffic information is greater than a preset difference threshold, the recognition result is determined to indicate that the congested road section is abnormal. If the difference between the current traffic information and the reference traffic information is less than the preset difference threshold, the congested road section is determined to be normal.

[0144] For example, a congested road section is a major traffic section that experiences congestion during rush hour. The average vehicle speed of the reference traffic information is A km / h. The average vehicle speed of the current traffic information is B km / h. Although B km / h is relatively low, it indicates congestion on this road section. However, if the difference between the current traffic information B km / h and the reference traffic information A km / h is less than a preset difference threshold, the congested road section is determined to be normal.

[0145] By comparing the reference traffic information provided by the embodiment of the present disclosure with the current traffic information to determine whether the congested road section is abnormal, it is possible to improve recognition accuracy while simplifying processing methods and improving processing efficiency by referring to the traffic information.

[0146] According to an embodiment of the present disclosure, the road condition identification method may further include: generating reference traffic information.

[0147] Alternatively, the reference traffic information can be generated based on historical traffic information corresponding to the same time point in different periods relative to the current moment. For example, the historical traffic information corresponding to the same time point in different periods can be used as the reference traffic information for the current moment. Alternatively, the historical traffic information from multiple historical moments at the same time point in different periods can be averaged to obtain the reference traffic information for the current moment.

[0148] For example, the historical moments of the same time point in different periods of the current moment may be: if the current moment is 15:00 on March 4, the historical moments of the same time point in different periods may include 15:00 on March 3 or 15:00 on March 2.

[0149] In another embodiment, the reference pass information may be generated in the following manner.

[0150] For example, the reference traffic information at the current moment is determined based on the historical traffic sequence information of the congested road section in the historical period adjacent to the current moment and the environmental information at the current moment.

[0151] For example, the historical time period adjacent to the current time may be: the current time is 15:00 on March 4, and the historical time period adjacent to the current time may include any time period between 9:00 and 15:00 on March 4.

[0152] By utilizing historical traffic time series information from historical periods adjacent to the current moment, the current moment's traffic information can be predicted and used as reference traffic information. For example, the historical traffic time series information can be input into a traffic prediction model to obtain reference traffic information. However, this is not a limitation. Alternatively, the historical traffic time series information can be combined with the current moment's environmental information and input into the traffic prediction model to obtain reference traffic information.

[0153] Common prediction models may include Long Short-Term Memory (LSTM) networks, but are not limited thereto and may also include statistical models for time series analysis and prediction (Auto Regressive Integrated Moving Average Model, ARIMA).

[0154] As explained above, environmental information can include weather information such as rainfall and visibility, as well as time information such as holidays or peak traffic periods. By using environmental information as a reference, we can consider the impact of factors such as unusual weather conditions, traffic control measures, and road construction on congestion.

[0155] The generation of reference traffic information provided by the embodiments of the present disclosure utilizes historical traffic time series information to reflect periodic patterns and potential nonlinear relationships, generating benchmark traffic information that closely reflects current conditions. Furthermore, the use of environmental information can fully reflect the dynamic changes in current traffic conditions, embodying real-time capabilities. Combining historical traffic time series information with environmental information provides comprehensive, dynamic, and accurate reference traffic information, thereby improving the accuracy and efficiency of identifying abnormal road sections.

[0156] Alternatively, one of the two aforementioned methods can be used to determine whether a congested road section is an abnormal road section. However, this is not a limitation. The two methods can also be combined to determine whether a congested road section is an abnormal road section. The combined method can include parallel determination or sequential determination. With parallel determination, two results can be calculated simultaneously. If either of the two results indicates an abnormality, the congested road section is determined to be abnormal. With sequential determination, there is no restriction on the execution order; as long as either of the two results indicates an abnormality, the congested road section is determined to be abnormal.

[0157] The above two embodiments are both explanations of how to determine whether a congested road section is an abnormal road section. In the case of determining that the congested road section is an abnormal road section, an abnormal lane is determined from multiple lanes in the abnormal road section.

[0158] The embodiment of the present disclosure also provides a method for determining an abnormal lane, which directly determines whether there is an abnormal lane among multiple lanes.

[0159] For example, when executing Figure 2 Before operation S210 of the road condition identification method shown, the following operation may be performed: in response to receiving abnormal lane feedback information sent through the navigation interface, if multiple abnormal lane feedback information all indicate that the lane is an abnormal lane, determining that the lane is an abnormal lane.

[0160] Abnormal lane feedback information may include lane position, lane abnormality indication, and abnormality cause, etc.

[0161] The server can receive lane abnormality feedback information sent by the user through the navigation interface through the navigation application. If multiple lane abnormality feedback information is received for the same lane, and all of them indicate that the lane is an abnormal lane, the lane can be directly determined to be an abnormal lane.

[0162] By utilizing the abnormal lane feedback information provided by users, it is possible to directly determine whether a lane is an abnormal lane, which is direct, effective, fast and accurate.

[0163] Optionally, when a single abnormal lane feedback information is received, the road condition of the lane may be identified based on the position information of the abnormal lane in the abnormal lane feedback information, so as to reduce the amount of data processing.

[0164] Figure 5 The flowchart of the path planning method according to the embodiment of the present disclosure is schematically shown.

[0165] like Figure 5 As shown, the method includes operations S510 to S520.

[0166] In operation S510 , when it is determined that the vehicle is located in an abnormal road section, navigation information of the navigation interface is updated to lane-level navigation information.

[0167] In operation S520 , identification information for characterizing an abnormal lane in the abnormal road section is added.

[0168] Exemplarily, the abnormal lane is determined by the road condition recognition method as described above.

[0169] Navigation information can include road segment lines and driving directions marked on the map. Lane-level navigation information can refine the map on the navigation interface to the lane level, displaying lane widths and lane markings. Using lane-level navigation information for navigation, drivers can be alerted to avoid unusual lanes on unusual road sections by identifying them and detouring around obstacles that may be causing congestion.

[0170] Timely and accurate identification of abnormal lanes and updating them to the navigation interface can provide users with timely and reliable lane-level navigation information, help users plan the best driving route, enable drivers to avoid abnormal lanes in advance, reduce the probability of rear-end collisions due to obstructed vision or delayed reaction, and ensure traffic safety.

[0171] Figure 6 A state change diagram of an updated navigation interface according to an embodiment of the present disclosure is schematically shown.

[0172] like Figure 6 As shown, when driving on a normal road section, the navigation interface 600 displays navigation information 610, which can identify the driving direction and the road section line. When it is determined that the vehicle is on an abnormal road section, the navigation information of the navigation interface can be updated to lane-level navigation information 620, which can display multiple lanes of the road section, the width of each lane, the lane dividing line, etc. In addition, the lane in which the vehicle is located can also be displayed. In addition, identification information 630 for representing abnormal lanes and normal lanes can be added to the navigation interface. The normal lane can be identified by the identification information of the "check mark". The abnormal lane can be identified by the identification information of the "cross mark". This improves the early warning capability of the abnormal lane and reminds the driver to change lanes in time.

[0173] Figure 7 A block diagram of a road condition recognition device according to an embodiment of the present disclosure is schematically shown.

[0174] like Figure 7 As shown, the road condition recognition device 700 may include a set acquisition module 710 , an indicator recognition module 720 and a first lane recognition module 730 .

[0175] The set acquisition module 710 is used to obtain lane traffic information sets of multiple lanes on the abnormal road section.

[0176] The indicator identification module 720 is used to determine a traffic identification indicator for identifying abnormal lanes based on the lane traffic information set, wherein the traffic identification indicator includes at least one of the following: a speed indicator, a distance indicator, and a density indicator.

[0177] The first lane identification module 730 is configured to identify an abnormal lane from the plurality of lanes based on the traffic identification indicators of the plurality of lanes.

[0178] According to an embodiment of the present disclosure, the indicator identification module includes: a first indicator identification submodule and a second indicator identification submodule.

[0179] The first indicator identification submodule is used to determine, based on the lane traffic information set, a first identification indicator for indicating average lane traffic information and a second identification indicator for indicating a degree of discreteness of information in the lane traffic information set.

[0180] The second indicator recognition submodule is configured to obtain a passage recognition indicator based on the first recognition indicator and the second recognition indicator.

[0181] According to an embodiment of the present disclosure, the first identification index includes at least one of the following: median speed, average distance between vehicles and the end of the abnormal road section, and the number of vehicles. The second identification index includes at least one of the following: speed variance, variance of distance between vehicles and the end of the abnormal road section, and vehicle density.

[0182] According to an embodiment of the present disclosure, each lane includes multiple traffic identification indicators.

[0183] According to an embodiment of the present disclosure, the first lane recognition module includes: a first lane recognition sub-module.

[0184] The first lane identification submodule is configured to determine, for each lane, if multiple traffic identification indicators all indicate that the lane is an abnormal lane, that the lane is an abnormal lane.

[0185] According to an embodiment of the present disclosure, the first lane recognition module includes: a second lane recognition submodule and a third lane recognition submodule.

[0186] The second lane identification submodule is configured to, based on fuzzy identification results obtained based on the multiple traffic identification indicators for each of the multiple lanes, perform a weighted summation of the multiple traffic identification indicators for each lane to obtain a lane assessment result for each lane. The fuzzy identification result indicates that no abnormal lane has been identified from the multiple lanes.

[0187] The third lane identification submodule is configured to determine an abnormal lane from the multiple lanes based on the multiple lane evaluation results.

[0188] According to an embodiment of the present disclosure, the second lane recognition submodule includes: a normalization unit and a summing unit.

[0189] A normalization unit, configured to perform normalization operations on a plurality of traffic identification indicators to obtain a plurality of normalized traffic parameters;

[0190] The summing unit is used to perform weighted summation on multiple normalized traffic parameters to obtain a lane assessment result for each lane.

[0191] According to an embodiment of the present disclosure, the road condition identification device further includes: a weight updating module.

[0192] The environment update module is used to update the weights of multiple traffic identification indicators based on environmental information so as to perform a weighted sum operation using the updated weights.

[0193] According to an embodiment of the present disclosure, the road condition identification device further includes: a first road section identification module.

[0194] The first road section identification module is used to determine whether the congested road section is an abnormal road section based on the road network topology of the congested road section and the traffic timing information of multiple road sections on the road network topology within a preset time period.

[0195] According to an embodiment of the present disclosure, the road condition identification device further includes: a first topology generation module and a second topology generation module.

[0196] The first topology generation module is used to generate an initial road network topology centered on the congested road section based on a map of the area where the congested road section is located and the association relationship between multiple road sections.

[0197] The second topology generation module is used to update the initial road network topology based on the traffic notification information obtained in real time to obtain the road network topology.

[0198] According to an embodiment of the present disclosure, the road condition identification device further includes: an information acquisition module and a sorting module.

[0199] The information acquisition module is used to obtain multiple traffic information of each road section in the road network topology at different times within a preset time period.

[0200] The sorting module is used to obtain traffic sequence information according to the time sequence. The traffic sequence information includes at least one of the following: vehicle speed, traffic volume, lane occupancy, and vehicle driving direction.

[0201] According to an embodiment of the present disclosure, the information acquisition module includes: a completion submodule.

[0202] The completion submodule is used to complete the information of the missing time based on the historical traffic information of the historical time of the road section when it is determined that there is a time when the missing information exists.

[0203] According to an embodiment of the present disclosure, the road condition identification device further includes: a second road section identification module.

[0204] The second road section identification module is used to identify the road condition of the congested road section based on the current traffic information and reference traffic information of the congested road section, and obtain an identification result for indicating whether the congested road section is abnormal.

[0205] According to an embodiment of the present disclosure, the road condition identification device further includes: a reference determination module.

[0206] The reference determination module is used to determine the reference traffic information at the current moment based on the historical traffic sequence information of the congested road section in the historical time period adjacent to the current moment and the environmental information at the current moment.

[0207] According to an embodiment of the present disclosure, the road condition recognition device further includes: a response module and a second lane recognition module.

[0208] The response module is used to respond to abnormal lane feedback information received through the navigation interface.

[0209] The second lane recognition module is configured to determine that a lane is an abnormal lane when multiple pieces of abnormal lane feedback information all indicate that the lane is an abnormal lane.

[0210] Figure 8 The block diagram of the path planning device according to an embodiment of the present disclosure is schematically shown.

[0211] like Figure 8 As shown, the path planning device 800 includes: a navigation refinement module 810 and an identification module 820 .

[0212] The navigation update module 810 is used to update the navigation information of the navigation interface to lane-level navigation information when it is determined that the vehicle is in an abnormal road section.

[0213] The identification module 820 is used to add identification information for characterizing abnormal lanes in abnormal road sections.

[0214] Abnormal lanes are determined by a road condition recognition device.

[0215] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0216] According to an embodiment of the present disclosure, an electronic device includes: at least one processor; and 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, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method described above.

[0217] According to an embodiment of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause a computer to execute the method described above.

[0218] According to an embodiment of the present disclosure, a computer program product includes a computer program, and when the computer program is executed by a processor, the computer program implements the method described above.

[0219] 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 can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are provided as examples only and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0220] like Figure 9 As shown, device 900 includes a computing unit 901, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 902 or a computer program loaded from a storage unit 908 into a random access memory (RAM) 903. RAM 903 may also store various programs and data required for the operation of device 900. Computing unit 901, ROM 902, and RAM 903 are connected to each other via a bus 904. An input / output (I / O) interface 905 is also connected to bus 904.

[0221] Various components in device 900 are connected to an input / output (I / O) interface 905, including an input unit 906, such as a keyboard and mouse; an output unit 907, such as various types of displays and speakers; a storage unit 908, such as a magnetic disk and optical disk; and a communication unit 909, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 909 allows device 900 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0222] The computing unit 901 can be any general-purpose and / or specialized processing component 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 specialized 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 condition identification and path planning methods. For example, in some embodiments, the road condition identification and path planning methods may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 908. In some embodiments, part or all of the computer program may be loaded and / or installed onto the device 900 via the ROM 902 and / or the communication unit 909. When the computer program is loaded into the RAM 903 and executed by the computing unit 901, one or more steps of the road condition identification and path planning methods described above may be performed. Alternatively, in other embodiments, the computing unit 901 may be configured to execute the road condition recognition and path planning method in any other appropriate manner (eg, by means of firmware).

[0223] Various embodiments of the systems and techniques described above 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), system-on-a-chip systems (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0224] The program code for implementing the method of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0225] In the context of the present disclosure, a machine-readable medium may 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 may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of machine-readable storage media may include an electrical connection based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), optical fibers, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0226] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the 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 acoustic input, voice input, or tactile input).

[0227] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0228] A computer system may include a client and a server. The client and server are generally remote from each other and typically interact through a communication network. The client-server relationship arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server may be a cloud server, a server in a distributed system, or a server integrated with a blockchain.

[0229] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved. This is not a limitation herein.

[0230] The above specific embodiments do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the scope of protection of this disclosure.

Claims

1. A road condition recognition method, comprising: Obtain lane traffic information sets for multiple lanes on abnormal road sections; Determining a traffic identification index for identifying abnormal lanes based on the lane traffic information set, wherein the traffic identification index includes at least one of the following: a speed index, a distance index, and a density index; and An abnormal lane is determined from the plurality of lanes based on the traffic recognition index of each of the plurality of lanes.

2. The method according to claim 1, wherein The determining of a traffic identification index for identifying an abnormal lane based on the lane traffic information set includes: determining, based on the lane passage information set, a first identification index for indicating average lane passage information and a second identification index for indicating a degree of dispersion of information in the lane passage information set; The passage identification index is obtained based on the first identification index and the second identification index.

3. The method according to claim 2, wherein: The first identification index includes at least one of the following: median speed, average distance between vehicles and the end of the abnormal road section, and number of vehicles; The second identification index includes at least one of the following: speed variance, distance variance of the vehicle from the end of the abnormal road section, and vehicle density.

4. The method according to any one of claims 1 to 3, wherein The traffic identification indicators of each lane include multiple ones; The determining an abnormal lane from the plurality of lanes based on the respective traffic identification indicators of the plurality of lanes includes: For each lane, if a plurality of the traffic identification indicators all indicate that the lane is an abnormal lane, the lane is determined to be an abnormal lane.

5. The method according to claim 4, wherein The determining an abnormal lane from the plurality of lanes based on the respective traffic identification indicators of the plurality of lanes includes: When fuzzy recognition results are obtained based on the plurality of traffic recognition indicators for each of the plurality of lanes, weighted summing the plurality of traffic recognition indicators for each lane to obtain a lane assessment result for each lane, wherein the fuzzy recognition result indicates that the abnormal lane is not determined from the plurality of lanes; and Based on the plurality of lane evaluation results, the abnormal lane is determined from the plurality of lanes.

6. The method according to claim 5, wherein: The weighted summation of the plurality of traffic identification indicators for each lane to obtain a lane assessment result for each lane includes: Normalizing the plurality of traffic identification indicators to obtain a plurality of normalized traffic parameters; A weighted sum is performed on the multiple normalized traffic parameters to obtain a lane assessment result for each lane.

7. The method according to claim 5 or 6, further comprising: Based on the environmental information, the weights of the plurality of traffic identification indicators are updated so as to perform a weighted summation operation using the updated weights.

8. The method according to any one of claims 1 to 7, further comprising: Based on the road network topology of the congested road section and the traffic sequence information of each of the multiple road sections on the road network topology within a preset time period, it is determined whether the congested road section is the abnormal road section.

9. The method according to claim 8, further comprising: generating an initial road network topology centered on the congested road section based on a map of the area where the congested road section is located and associations between multiple road sections; as well as Based on the traffic notification information obtained in real time, the initial road network topology is updated to obtain the road network topology.

10. The method according to claim 8 or 9, further comprising: Acquire multiple traffic information of each road section on the road network topology at different times within a preset time period; as well as Arrange the passage timing information in time sequence to obtain the passage timing information; The traffic information includes at least one of the following: Vehicle speed, traffic volume, lane occupancy, and vehicle direction.

11. The method according to claim 10, wherein: The obtaining of a plurality of traffic information of each road section on the road network topology at different times within a preset time period includes: When it is determined that there is a time at which missing information exists, information of the time at which the missing information exists is supplemented based on historical traffic information of the historical time at the road section.

12. The method according to any one of claims 1 to 7, further comprising: Based on the current traffic information and reference traffic information of the congested road section, the road condition of the congested road section is identified to obtain an identification result for characterizing whether the congested road section is abnormal.

13. The method according to claim 12, further comprising: The reference traffic information at the current moment is determined based on the historical traffic sequence information of the congested road section in a historical period adjacent to the current moment and the environmental information at the current moment.

14. The method according to any one of claims 1 to 11, further comprising: In response to receiving abnormal lane feedback information sent through the navigation interface; as well as In a case where the plurality of abnormal lane feedback information all indicate that the lane is an abnormal lane, the lane is determined to be the abnormal lane.

15. A path planning method, comprising: When it is determined that the vehicle is in the abnormal road section, updating the navigation information of the navigation interface to lane-level navigation information, and adding identification information for characterizing the abnormal lane in the abnormal road section; The abnormal lane is determined by the road condition recognition method according to any one of claims 1 to 14.

16. A road condition recognition device, comprising: A collection acquisition module is used to obtain lane traffic information collection of multiple lanes on the abnormal road section; an indicator identification module, configured to determine a traffic identification indicator for identifying an abnormal lane based on the lane traffic information set, wherein the traffic identification indicator includes at least one of the following: a speed indicator, a distance indicator, and a density indicator; and The first lane recognition module is configured to determine an abnormal lane from the plurality of lanes based on the traffic recognition indicators of each of the plurality of lanes.

17. A path planning device, comprising: A navigation update module, configured to update the navigation information on the navigation interface to lane-level navigation information when determining that the vehicle is located in the abnormal road section; as well as an identification module, configured to add identification information for characterizing an abnormal lane in the abnormal road section; Wherein, the abnormal lane is determined by the road condition recognition device according to claim 16.

18. 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, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 15.

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

20. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1 to 15.

Images