Abnormal state road determination method and device, equipment, storage medium and program product

Abstract

The invention provides an abnormal state road determination method and device, electronic equipment, a computer readable storage medium and a computer program product, and relates to the technical field of artificial intelligence such as automatic driving and map navigation. The method comprises the steps of determining a to-be-recognized road area based on track change features; according to the actual trajectory appearing in the to-be-identified road area, obtaining a trajectory map; obtaining a road network map according to the road network information corresponding to the road area to be identified; performing image difference processing on the trajectory map and the road network map to obtain a difference image; and determining a target road in an abnormal state according to the differentiated image. According to the method, the to-be-recognized area where the road in the abnormal state possibly exists is screened out, invalid analysis is reduced, then the overlapping degree of the real-time track and the road is visually reflected through image differential processing, the road in the abnormal state is determined, the abnormal state is added to the corresponding road section in the electronic map subsequently, and the recognition accuracy is improved. The accuracy of the navigation planning path is improved.

Description

Technical Field

[0001] The present disclosure relates to the technical field of data processing, specifically to artificial intelligence technical fields such as autonomous driving and map navigation, and particularly to a method, device, electronic device, computer-readable storage medium, and computer program product for determining a road in an abnormal state. Background Art

[0002] In an electronic map product, "road blockage" is used to represent an impassable state caused by traffic control, bad weather, road construction, or other reasons.

[0003] When a user performs navigation planning, the navigation system will avoid impassable roads based on this blockage information; and when the blockage state is lifted, it is necessary to quickly update to restore the passable state of the road in the navigation system. Summary of the Invention

[0004] Embodiments of the present disclosure propose a method, device, electronic device, computer-readable storage medium, and computer program product for determining a road in an abnormal state.

[0005] In a first aspect, embodiments of the present disclosure propose a method for determining a road in an abnormal state, including: determining a road area to be recognized based on trajectory change features; obtaining a trajectory map according to the actual trajectories that appear in the road area to be recognized; obtaining a road network map according to the road network information corresponding to the road area to be recognized; performing image difference processing on the trajectory map and the road network map to obtain a post-difference image; and determining a target road in an abnormal state according to the post-difference image.

[0006] In a second aspect, embodiments of the present disclosure propose a device for determining a road in an abnormal state, including: a road area to be recognized determination unit configured to determine a road area to be recognized based on trajectory change features; a trajectory map acquisition unit configured to obtain a trajectory map according to the actual trajectories that appear in the road area to be recognized; a road network map acquisition unit configured to obtain a road network map according to the road network information corresponding to the road area to be recognized; an image difference unit configured to perform image difference processing on the trajectory map and the road network map to obtain a post-difference image; and an abnormal state road determination unit configured to determine a target road in an abnormal state according to the post-difference image.

[0007] In a third aspect, embodiments of the present disclosure provide an electronic device, which includes: 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 when the instructions are executed by the at least one processor, the at least one processor is enabled to implement the method for determining a road in an abnormal state described in the first aspect.

[0008] Fourthly, embodiments of the present disclosure provide a non-transitory computer-readable storage medium storing computer instructions, which are used to enable a computer to execute the abnormal state road determination method described in the first aspect when executed.

[0009] Fifthly, embodiments of the present disclosure provide a computer program product including a computer program, which can implement the steps of the abnormal state road determination method described in the first aspect when executed by a processor.

[0010] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it used to limit the scope of the present disclosure. Other features of the present disclosure will become easily understandable through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] By reading the detailed description of the non-limiting embodiments with reference to the following drawings, other features, objectives, and advantages of the present disclosure will become more apparent:

[0012] Figure 1 is an exemplary system architecture to which the present disclosure can be applied;

[0013] Figure 2 is a flowchart of an abnormal state road determination method provided by an embodiment of the present disclosure;

[0014] Figure 3 is a schematic diagram of three parallel schemes for determining a road area to be recognized provided by an embodiment of the present disclosure;

[0015] Figure 4 is a summary schematic diagram of each scheme for specifically determining a road area to be recognized provided by an embodiment of the present disclosure;

[0016] Figure 5 is a flowchart of determining a target road according to a differential image provided by an embodiment of the present disclosure;

[0017] Figure 6 is a flowchart of a secondary verification and correction method based on verification feedback provided by an embodiment of the present disclosure;

[0018] FIG. 7 is a schematic flowchart of an abnormal state road determination method in an application scenario provided by an embodiment of the present disclosure;

[0019] Figure 8 is a structural block diagram of an abnormal state road determination device provided by an embodiment of the present disclosure;

[0020] Figure 9 is a schematic structural diagram of an electronic device suitable for executing the abnormal state road determination method provided by an embodiment of the present disclosure. Detailed Implementation Modes

[0021] The exemplary embodiments of the present disclosure will be described below in conjunction with the accompanying drawings. Various details of the embodiments of the present disclosure are included to facilitate understanding, and they should be considered merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can 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, the descriptions of well-known functions and structures are omitted below. It should be noted that, without conflict, the embodiments in the present disclosure and the features in the embodiments can be combined with each other.

[0022] In the technical solution of the present disclosure, the processing of the collection, storage, use, processing, transmission, provision, and disclosure of the user's personal information complies with the provisions of relevant laws and regulations and does not violate public order and good customs.

[0023] Figure 1 An exemplary system architecture 100 is shown, which can apply the embodiments of the abnormal state road determination method, device, electronic device, and computer-readable storage medium of the present disclosure.

[0024] As Figure 1 shown, the system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 is used to provide a medium for communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, etc.

[0025] Users can use the terminal devices 101, 102, 103 to interact with the server 105 through the network 104 to receive or send messages, etc. Various applications for realizing information communication between the two can be installed on the terminal devices 101, 102, 103 and the server 105, such as electronic map applications, navigation planning applications, map information update applications, etc.

[0026] The terminal devices 101, 102, 103 and the server 105 can be either hardware or software. When the terminal devices 101, 102, 103 are hardware, they can be various electronic devices with a display screen, including but not limited to smartphones, tablets, laptop computers, desktop computers, etc.; when the terminal devices 101, 102, 103 are software, they can be installed in the above-listed electronic devices, and can be implemented as multiple software or software modules, or can be implemented as a single software or software module, which is not specifically limited here. When the server 105 is hardware, it can be implemented as a distributed server cluster composed of multiple servers, or can be implemented as a single server; when the server is software, it can be implemented as multiple software or software modules, or can be implemented as a single software or software module, which is not specifically limited here.

[0027] The server 105 can provide various services through various built-in applications. Taking the map information update application that can provide the abnormal state road determination service as an example, when the server 105 runs this map information update application, the following effects can be achieved: First, receive the historical travel trajectories transmitted by the terminal devices 101, 102, 103 through the network 104, and then determine the road area to be recognized based on the analyzed trajectory change characteristics; then, obtain a trajectory map according to the actual trajectories that appear in the road area to be recognized; and obtain a road network map according to the road network information corresponding to the road area to be recognized; next, perform image difference processing on the trajectory map and the road network map to obtain a difference image; finally, determine the target road in the abnormal state according to the difference image.

[0028] Furthermore, the determined target road can also be used to update the map information of the electronic map used by the electronic map application.

[0029] It should be noted that in addition to obtaining the historical travel trajectories from the terminal devices 101, 102, 103 through the network 104, they can also be pre-stored locally in the server 105 in various ways. Therefore, when the server 105 detects that these data have been stored locally (such as the pending tasks retained before starting the processing), it can choose to directly obtain these data from the local. In this case, the exemplary system architecture 100 may not include the terminal devices 101, 102, 103 and the network 104.

[0030] Since the analysis of a large number of trajectories and image processing require a large amount of computing resources and strong computing power, the method for determining abnormal state roads provided in the subsequent embodiments of the present disclosure is generally executed by the server 105 with strong computing power and a large amount of computing resources. Correspondingly, the abnormal state road determination device is generally also set in the server 105. However, it should also be noted that when the terminal devices 101, 102, and 103 also have computing power and computing resources that meet the requirements, the terminal devices 101, 102, and 103 can also complete the above operations originally performed by the server 105 through the map information update applications installed thereon, and then output the same results as the server 105. Especially in the case where there are multiple terminal devices with different computing capabilities at the same time, when the map information update application determines that the terminal device where it is located has strong computing power and a large amount of remaining computing resources, the terminal device can be allowed to perform the above operations, thereby appropriately reducing the computing pressure on the server 105. Correspondingly, the abnormal state road determination device can also be set in the terminal devices 101, 102, and 103. In this case, the exemplary system architecture 100 may not include the server 105 and the network 104 either.

[0031] It should be understood that Figure 1 the numbers of terminal devices, networks, and servers in

[0032] Please refer to Figure 2 , Figure 2 which is a flowchart of a method for determining abnormal state roads provided by an embodiment of the present disclosure. The process 200 includes the following steps:

[0033] Step 201: Based on the trajectory change characteristics, determine the road area to be recognized;

[0034] This step aims to identify the road area where the road may be in an abnormal state in the full-scale road network information by the execution entity of the abnormal state road determination method (such as Figure 1 the server 105 shown, relying on its powerful computing power and storage capacity to efficiently process and analyze a large amount of trajectory data) at least by analyzing the trajectory change characteristics shown in the vehicle trajectory data. Among them, the abnormal state mainly refers to the situation where the road cannot be normally opened to traffic, such as road blockage or closure caused by accidents, construction, natural disasters, or traffic control.

[0035] Among them, the trajectory change characteristics described in this step refer to the quantifiable change manifestations presented by the vehicle's driving trajectory before and after the occurrence of abnormal road conditions. These characteristics can reflect the change of road traffic conditions and are the key basis for identifying abnormal roads. For example, the reduction in the number of trajectories, the increase in yaw behavior, the abnormal fluctuation of speed, the interruption of trajectories, and the formation of detour paths, etc., are all trajectory change characteristics that can show similar situations.

[0036] Specifically, first, vehicle trajectory data (i.e., raw data) in the entire road network can be collected, including time stamps, position coordinates, speed, direction, etc.; then, the raw data is cleaned and denoised to remove abnormal trajectory points (such as drift points, duplicate points, etc.); next, the trajectory data is matched with the road network to determine the road segments corresponding to each trajectory; in the next step, calculate the characteristics such as the number of trajectories, speed distribution, yaw rate, etc. of each road segment within a specific time window, and compare the characteristic values with historical data or adjacent road segments to identify abnormal road segments that significantly deviate from the normal range; finally, combined with spatio-temporal analysis, capture the spatio-temporal propagation law of trajectory changes, for example, the anomaly gradually spreads from a certain point to the surrounding area, and the specific spread range or included scope can be flexibly determined according to actual needs and is not specifically limited here.

[0037] Step 202: Obtain a trajectory map based on the actual trajectories that appear in the area of the road to be identified;

[0038] Based on step 201, the purpose of this step is for the above-mentioned execution entity to obtain the specific vehicle trajectories that actually appear in the area of the road to be identified, and generate a trajectory map according to the specific vehicle trajectories in the area of the road to be identified. That is, extract the trajectory information of the area of the road to be identified from the massive trajectory data and visually present it.

[0039] Specifically, first, according to the geographical scope of the area of the road to be identified (such as the coordinates of the geographical fence), screen out all vehicle trajectories that appear in this area from the entire trajectory data; then extract the key attributes of the trajectories, including time stamps, position coordinates, speed, direction, vehicle ID, etc. information; next, de-duplicate and complete the screened trajectories to ensure the integrity and accuracy of the data; in the next step, the extracted trajectory data can be mapped onto a digital map, and different types of trajectories (such as normal trajectories, detour trajectories, stagnant trajectories) can be distinguished by different colors, line types or symbols, and then mark the starting point, ending point and key nodes of the trajectories to form an intuitive trajectory path.

[0040] At the same time, considering the situation where actual trajectory points are unstable and thus generate noise data, after obtaining the actual trajectories that appear in the area of the road to be identified, the actual trajectories can also be denoised, and then a trajectory map described in the form of lines can be generated according to the denoised trajectories to improve the accuracy of the generated trajectory map in describing the trajectories.

[0041] Furthermore, the extracted trajectories can be segmented according to the time sequence to identify the complete driving paths of each vehicle within the target area, and the entire process trajectories of the same vehicle entering, passing through, and leaving the target area can be associated to form a continuous behavior chain. Key points in the trajectories, such as entry points, exit points, stop points, and yaw points, can also be marked, and trajectories that do not conform to the characteristics of the target area can be filtered out, such as the trajectories of vehicles that pass by briefly without being affected. At the same time, trajectories highly related to abnormal states, such as detour trajectories, stagnant trajectories, and low-speed trajectories, can be retained.

[0042] Moreover, time-axis information can be added to the trajectory map to display the spatio-temporal evolution process of the trajectories through dynamic playback or segmented display; or in the form of a heat map or density map to show the distribution and aggregation of trajectories in different time periods. Furthermore, road network information, including lane distribution, traffic signs, and signal light positions, can be overlaid on the trajectory map, and even external factors such as weather and events can be added to facilitate subsequent analysis of the reasons for trajectory changes.

[0043] Step 203: Obtain a road network map according to the road network information corresponding to the road area to be recognized;

[0044] Based on Step 201, the purpose of this step is for the above-mentioned execution entity to obtain the road network information corresponding to the road area to be recognized and generate a road network map according to the road network information corresponding to the road area to be recognized. That is, using spatial database and Geographic Information System (GIS) technology, extract the road network information of the target area from the full-scale road network data and visually present it.

[0045] Specifically, first, according to the geographical scope of the road area to be recognized (such as the coordinates of the geographical fence), screen out all road information within the area from the full-scale road network data, and then extract the key attributes of the roads, including road grade (high-speed, main road, secondary road, etc.), number of lanes, direction, speed limit, traffic signs, signal light positions, etc. Next, perform a topological check on the screened road data to ensure the connectivity and integrity of the road network; then, the road topological structure of the target area can also be analyzed to identify key nodes (such as intersections and overpasses) and important sections (such as bridges and tunnels) to finally generate the road network map.

[0046] Furthermore, to enrich the information contained in the road network map, the traffic direction, lane distribution, traffic control information (such as one-way streets and restricted areas) of the roads can also be marked.

[0047] Step 204: Perform image difference processing on the trajectory map and the road network map to obtain the difference image;

[0048] Based on steps 202 and 203, this step aims to enable the above-mentioned execution entity to compare the differences between the trajectory map and the road network map through image difference processing technology, so as to identify the target roads in an abnormal state according to the obtained difference image.

[0049] Image difference technology refers to the technology of extracting the changed areas or target objects by comparing the differences between two or more images at the pixel level. Its core idea is to calculate the difference values of corresponding pixels in the image (such as gray values, color values, etc.) to generate a difference image, thereby highlighting the changed parts between the images. This step is also based on this core idea and is adapted and optimized for the characteristics of traffic trajectory maps and road network maps.

[0050] A specific implementation process of image difference can include the following steps:

[0051] 1) Image alignment and preprocessing: Align the trajectory map and the road network map spatially to ensure that they are in the same geographic coordinate system with the same resolution; denoise the images to eliminate the noise interference introduced during data collection or drawing; convert the images into a unified format (such as binary images or grayscale images) for subsequent difference calculation.

[0052] 2) Difference calculation: Adopt a pixel-level difference algorithm to compare the pixel values at corresponding positions in the trajectory map and the road network map and calculate the differences; for binary images, directly compare whether the pixel values are the same; for grayscale images, calculate the difference or ratio of pixel values; generate a difference image, in which the pixel regions with significant differences (such as missing trajectories, trajectory offsets, etc.) are highlighted.

[0053] Furthermore, the difference results can be optimized in the following way: perform morphological processing (such as dilation, erosion) on the difference image to remove isolated noise points and enhance the significance of continuous difference regions; or set a difference threshold at the same time to filter out the interference caused by minor deviations and retain the significant difference regions.

[0054] Step 205: Determine the target roads in an abnormal state according to the difference image.

[0055] Based on step 204, this step aims to enable the above-mentioned execution entity to determine the target roads in an abnormal state according to the difference image. For example, the difference region can be determined based on the bright and dark distribution in the difference image, and then the specific road corresponding to the difference region can be determined in combination with the road network map. Finally, the determined specific road is determined as the target road in an abnormal state.

[0056] Specifically, according to the differential features, the abnormal states can be classified. For example: missing trajectory: may indicate that the road is completely blocked or closed; trajectory deviation: may indicate that the road is partially closed or the vehicle is detoured; sparse trajectory: may indicate that the road traffic capacity has decreased or the vehicle is avoiding. Then, the trajectory map and the road network map can be combined to further analyze the abnormal reasons, such as accidents, construction, natural disasters, etc.

[0057] Furthermore, the degree of abnormality can also be evaluated. For example, according to the size of the differential area, the amplitude of the trajectory change, and the duration, the severity of the abnormal state can be evaluated, and the abnormal roads can be classified, such as slightly affected, partially blocked, completely closed, etc. Finally, the target roads in the abnormal state can be marked on the road network map to generate a distribution map of abnormal roads, and the detailed information of the abnormal roads can be output, including location, type, severity, possible reasons, etc., so as to update the relevant information of each road in the electronic map for guiding the subsequent generation process of navigation path planning.

[0058] The method for determining abnormal state roads provided by the embodiments of the present disclosure first screens out the to-be-identified areas where roads in abnormal states may exist in the full-scale road network through trajectory change features, thereby reducing ineffective analysis. Then, by performing image difference processing on the road network map and the trajectory map of the to-be-identified area, the coincidence degree between the real-time trajectory and the road can be determined according to the image difference result, that is, the roads in the abnormal state can be accurately determined from the visual level, so as to add the abnormal state to the corresponding road sections in the electronic map subsequently to improve the accuracy of the navigation planning path. And this solution combines image processing algorithms and spatial analysis capabilities, providing a precise means for traffic management to identify abnormal roads, having broad application value and expansion potential, and can significantly improve the intelligent level and emergency response ability of traffic management.

[0059] To deepen the understanding of how to initially screen the to-be-identified road areas where roads in abnormal states may exist from the full-scale road network information, this embodiment also Figure 3 shows three parallel implementation schemes. The parallel schemes are independent of each other and can each be used as a specific implementation method:

[0060] Scheme 1: Determine the to-be-identified road area based on trajectory change features and construction status information.

[0061] That is, in addition to the abnormal road state reflected from the trajectory change level, the construction status information given by the road administration is also combined, in order to more comprehensively determine the to-be-identified road area by simultaneously leveraging the rigid impact of the construction status information on the road traffic status.

[0062] Scheme 2: Determine the to-be-identified road area based on trajectory change features and known abnormal road information.

[0063] That is, in addition to the abnormal road conditions reflected from the aspect of trajectory changes, known abnormal road information is also combined, in order to more comprehensively determine the road area to be identified by means of some known abnormal road information at the same time.

[0064] Solution 3: Determine the road area to be identified according to the trajectory change characteristics, construction status information, and known abnormal road information.

[0065] Solution 3 can actually be regarded as the integration of Solution 1 and Solution 2. That is, in addition to the abnormal road conditions reflected from the aspect of trajectory changes, the construction status information and known abnormal road information that can be determined from the road administration information channel are also combined to supplement and determine the road area to be identified, so that the determined road area to be identified is as comprehensive and accurate as possible, because information from different sources and different dimensions can also corroborate each other.

[0066] In Figure 3 On the basis of the schematic diagram showing the technical key points used by each parallel solution respectively, in order to deepen the understanding of how each technical key point is specifically used to determine the road area to be identified, the following also combines Figure 4 the schematic diagram for a detailed description:

[0067] For the trajectory change characteristics, the road area where the decline rate of the number of trajectories over time exceeds the first preset rate can be specifically determined as the first road area (when an abnormality occurs on a certain road, the number of passing vehicles will decrease significantly, so it will be manifested as a sharp decrease in the trajectory point density); and the road area where the growth rate of the number of yaw behaviors in the trajectory over time exceeds the second preset rate can be determined as the second road area (when a vehicle approaches an abnormal section, it will show behaviors such as detouring or deviating from the original path, forming a new trajectory hot spot). In addition, the road area with abnormal speed fluctuations (the vehicle shows sudden deceleration, stagnation or repeated start-stop phenomena near the abnormal section), trajectory interruption (the vehicle suddenly stops moving at the abnormal section and there are no subsequent trajectory points for a long time), or the formation of a detour path (the vehicle forms a new passing path around the abnormal section, manifested as an obvious change in the spatial distribution of the trajectory) can also be determined as the road area suspected of having abnormal conditions, that is, the road area to be identified, in order to avoid omission as much as possible.

[0068] Furthermore, if the distance between the first road area and the second road area is less than the preset distance, the connected area between the first road area and the second road area can also be determined as the third road area, and the third road area can be supplemented into the area range included in the road area to be identified. That is, the probability of there being an abnormal state road in the connected part between two adjacent road areas is significantly higher than that of other road areas, so this part of the road area can also be determined as a part of the road area to be identified.

[0069] For the construction status information, the road construction behavior can be specifically determined according to the road administration information, and then the road area with road construction behavior is determined as the fourth road area.

[0070] For the known abnormal road information, the remaining normal road areas of the roads that are already in a partially closed state or a partially blocked state can be specifically determined as the fifth road area.

[0071] Furthermore, the road area to be recognized can be obtained by summarizing the above-mentioned road areas. It should be noted that in Solution 1, the road area to be recognized should be obtained by summarizing the first road area, the second road area, and the fourth road area. In Solution 2, it should be obtained by summarizing the first road area, the second road area, and the fifth road area. In Solution 3, it should be obtained by summarizing the above various road areas. The third road area can also be used to supplement the road area to be recognized determined by the above three solutions. At the same time, the multiple road areas should also be de-duplicated and supplemented to obtain the road area to be recognized.

[0072] Based on any of the above embodiments, to deepen the understanding of how to determine the target road according to the differential image, this embodiment also provides Figure 5 a specific implementation method, and its process 500 includes the following steps:

[0073] Step 501: Determine the preliminary screening road from the differential image according to the gray-scale information distribution in the differential image;

[0074] Gray scale, also known as color scale or gray level, refers to the brightness and darkness degree. Therefore, the gray-scale information distribution actually represents the distribution of different brightness in the differential image, that is, the part with a higher brightness value represents the part where the trajectory and the road network have a more obvious difference, and is more likely to be an indication of an abnormal state. Relatively, the part with a lower brightness value represents the part where the trajectory and the road network have a higher degree of consistency, and is more likely to be an indication of a normal state. Therefore, the brightness value can be compared with the first preset brightness value, and the road corresponding to the actual brightness value exceeding the first preset brightness value is determined as the preliminary screening road, that is, the actual brightness value corresponding to the preliminary screening road exceeds the first preset brightness value, and the preliminary screening road is usually a set containing multiple roads.

[0075] Furthermore, misleading areas caused by image noise or data errors can be removed, such as isolated bright points (points with an actual brightness exceeding a certain brightness value and thus appearing significantly prominent visually) or bright areas with too small an area (i.e., areas formed by the convergence of multiple bright points), and only the road segments corresponding to the significant bright areas are retained as the preliminary screening roads for subsequent analysis.

[0076] Step 502: Determine the target roads in an abnormal state based on the road feature information and historical trajectory information of the preliminarily screened roads.

[0077] Among them, the road feature information may include: road grade information, road attribute information, etc. The road grade information can be information distinguished by high or low grades. For example, the national road has the highest grade, while the provincial road, highway, city road, and village road gradually decrease in grade; the road attribute information can include various information such as road type (high-speed, main road, auxiliary road, etc.), number of lanes, speed limit, traffic signs, and signal light positions. All kinds of road feature information can be used to analyze the relevance between the road and the abnormal state to a certain extent. For example, the appearance of a bright area on a highway may indicate a serious blockage; the appearance of a bright area on an urban road may indicate local congestion or construction.

[0078] Among them, the historical trajectory information may include: total number of trajectories, average number of trajectories, speed distribution, number of errors (here, the error means that the historical trajectory is mispositioned on a certain road), proportion of the number of errors, traffic direction, etc. Each specific historical trajectory information can be used alone to analyze the relevance between the road and the abnormal state by comparing with the current trajectory. For example, if the total number of trajectories of the current trajectory is significantly less than that of the historical trajectory, it may indicate that the corresponding road is temporarily closed at present, or if the speed distribution of the current trajectory is significantly lower than that of the historical trajectory, it may indicate that the corresponding road is in a traffic congestion state at present.

[0079] Of course, the historical trajectory information can also be used to assist in combining with the road feature information to more accurately determine whether certain specific types of roads among the preliminarily screened roads are target roads in an abnormal state. For example, the historical trajectory information is combined with the road grade information in the road feature information to determine the usage frequency of each preliminarily screened road, and the preliminarily screened road with a higher usage frequency is determined as the target road. That is, compared with the road with a lower usage frequency, identifying whether the road with a higher usage frequency is in an abnormal state can serve more vehicles or pedestrians passing through this road. Another example is that the historical trajectory information can be combined with the road attribute information in the road feature information to distinguish which preliminarily screened roads are complex roads and which are ordinary roads, and then different target road discrimination criteria are provided for complex roads and ordinary roads respectively, thereby improving the rigor and accuracy of the discrimination results.

[0080] Furthermore, the severity can also be evaluated according to the influence range, duration of the abnormal state, and the amplitude of trajectory changes, such as mild, medium, severe, etc.

[0081] This embodiment aims to screen out the roads (preliminarily screened roads) that may be in an abnormal state according to the gray information distribution in the differential image, and then combine the road feature information and historical trajectory information to further confirm the target roads that are indeed in an abnormal state.

[0082] Based on the previous embodiment, this embodiment also provides two different methods to deepen the understanding of determining the target road by specifically combining road feature information and historical trajectory information:

[0083] Method 1: First, the actual road grade of the initially screened roads can be determined according to the road grade information in the road feature information (for example, secondary, assuming that the road grades include first, second, third, and fourth grades in decreasing order), and the actual historical trajectory quantity of the initially screened roads can be determined according to the trajectory quantity information in the historical trajectory information; then, the initially screened roads corresponding to the actual road grade exceeding the preset road grade (for example, third grade) and / or the actual historical trajectory quantity exceeding the preset historical trajectory quantity are determined as the target roads in an abnormal state.

[0084] In this method, the screening condition that the actual road grade is greater than the preset road grade aims to screen out some of the initially screened roads with higher road grades. Generally, a higher road grade reflects a larger number of trajectories, a higher usage frequency, and a higher necessity to identify whether the road is in an abnormal state. Similarly, the screening condition that the actual historical trajectory quantity exceeds the preset historical trajectory quantity is also to screen out some of the initially screened roads with higher usage frequencies and a higher necessity to identify whether they are in an abnormal state. When both screening conditions are met, it indicates a higher necessity. Therefore, this method aims to screen out the part of the initially screened roads that need to be determined whether they are in an abnormal state through this method, so as to improve the pertinence of the solution and avoid useless or inefficient operations.

[0085] Method 2: First, the scene type of the initially screened roads can be determined according to the road attribute information in the road feature information (for example, intersection scene, uphill scene, multi-curve scene, etc.), and the actual error trajectory ratio of the initially screened roads can be determined according to the error quantity ratio information in the historical trajectory information, that is, the actual error trajectory ratio is the ratio of the number of historical trajectories erroneously identified as traveling on the initially screened roads to the total number of historical trajectories; then, the initially screened roads with the scene type specifically being an intersection scene and the actual error trajectory ratio exceeding the preset error trajectory ratio are determined as complex intersection roads; finally, if the actual brightness value of the complex intersection road exceeds the second preset brightness value, the complex intersection road is determined as the target road in an abnormal state, and the second preset brightness value is greater than the first preset brightness value.

[0086] In this method, the scenario type is used to filter out intersection scenarios where error trajectories are likely to occur, and the screening condition that the proportion of actual error trajectories is greater than the preset proportion of error trajectories is used to further filter out the partially screened roads with trajectory misjudgment. The combination of the two can determine that this intersection scenario is a complex intersection road where trajectory misjudgment often occurs. Therefore, to improve the accuracy of discrimination, a higher brightness threshold (i.e., the second preset brightness value) is required to determine the correct conclusion of whether the target road is in an abnormal state. It should be understood that the higher the brightness value, the greater the difference between the trajectory and the road network map, and thus the higher the probability of an abnormal state.

[0087] Furthermore, the initially screened roads that do not belong to complex intersection roads and whose actual brightness value is greater than the third preset brightness value can be determined as target roads in an abnormal state. The third preset brightness value is greater than the first preset brightness value but less than the second preset brightness value. That is, for ordinary roads in non-complex intersection scenarios, a relatively smaller brightness threshold compared to the second preset brightness value can be used to obtain the discrimination result.

[0088] Based on any of the above embodiments, regarding how to effectively use the determined target roads, this embodiment also Figure 6 provides a specific implementation method, and its process 600 includes the following steps:

[0089] Step 601: Generate verification intelligence based on the target road and push the verification intelligence to an execution object with verification capabilities;

[0090] Among them, the verification intelligence may include the following content: key information of the target road, including location, abnormal type (such as blockage, closure, congestion), abnormal severity, possible reasons (such as accidents, construction, natural disasters), etc., as well as additional relevant data support, such as differential images, trajectory maps, road network maps, historical trajectory comparisons, etc., to provide a basis for verification. And the verification intelligence can be encapsulated in a standardized format (such as JSON, XML) to facilitate parsing and processing by different execution objects. Furthermore, metadata such as timestamps and unique identifiers can be added to ensure the traceability and uniqueness of the intelligence.

[0091] Even further, the verification intelligence can be prioritized according to the abnormal severity and the affected range. For example: High priority: Main roads that are completely blocked; Medium priority: Sub-roads that are partially closed; Low priority: Minor roads with slight congestion.

[0092] For the process of pushing the information to be verified, the execution objects with verification capabilities can be matched according to the type and priority of the information. For example: traffic management personnel are responsible for handling major anomalies with high priority; inspection personnel are responsible for on-site verification of medium and low priority anomalies; intelligent devices (such as drones, patrol vehicles) automatically collect real-time data of the target road.

[0093] The information can be pushed through multiple channels to ensure that the execution objects receive it in a timely manner. For example: mobile terminals push information through APPs or text messages; email systems send detailed information reports; command centers display information on monitoring large screens.

[0094] Step 602: In response to receiving the verification feedback result of the execution object, correct the road coverage of the target road according to the verification feedback result.

[0095] The solution provided in this step is actually based on the following feedback mechanism: first, the execution object is required to send a confirmation receipt after receiving the information to ensure the successful delivery of the information; then, a timeout mechanism is also set up. For execution objects that do not confirm in a timely manner, the information is pushed again or assigned to other objects.

[0096] The received feedback results can be required to include: anomaly status confirmation: whether it is true, specific reasons, scope of influence, etc.; additional information: on-site photos, videos, sensor data, etc.; correction suggestions: such as adjusting the anomaly scope, updating the anomaly type, etc.

[0097] On this basis, by parsing and classifying the feedback results, key information can be extracted for correcting the target road, and conflict detection and processing can be performed on inconsistent feedback results, such as through multi-source data comparison or re-verification. Then, according to the feedback results, correct the road coverage of the target road. For example: expand the scope: the feedback result indicates that the anomaly impact area is larger; narrow the scope: the feedback result indicates that the anomaly impact area is smaller.

[0098] After determining the target road in an abnormal state, this embodiment aims to generate information to be verified and push it to execution objects with verification capabilities (such as traffic management personnel, inspection personnel, intelligent devices, etc.), and then correct the road coverage of the target road according to the verification feedback results of the execution objects to ensure the accuracy and reliability of anomaly detection.

[0099] It should be noted that step 602 is only a possible implementation method after step 601 is executed, that is, step 601 does not depend on the existence of step 602. Step 601 can be completely combined with other subsequent implementation methods to form another separate embodiment. This embodiment only exists as a preferred implementation method.

[0100] Based on this embodiment, to reduce the workload of manual verification, real-time data of the target road can also be automatically collected by intelligent devices (such as drones and patrol vehicles) for automatic verification; for complex or uncertain abnormal states, the determination accuracy can also be gradually improved by conducting multiple rounds of verification. At the same time, an incentive mechanism can also be provided for the verification feedback of the execution object to encourage the timely and accurate completion of the verification task.

[0101] Furthermore, during the visualization process, the correction process of the target road can also be dynamically displayed in the road network map to provide intuitive decision-making support for traffic management personnel. And dynamic effects, such as flashing markings and color gradients, can be added to the difference image to further enhance the intuitiveness and expressiveness of the visualization.

[0102] To deepen the understanding, the present disclosure also gives a specific implementation solution in combination with a specific application scenario, as shown in Figure 7:

[0103] The abnormal state road recognition scheme provided in this embodiment specifically takes the blocked road as an example. By retrieving the trajectory of the road and then based on the changes in the road network and the real-time trajectory of the road, the image difference strategy is used to identify the road blockage to more accurately verify the road blockage situation.

[0104] The implementation solution provided in this embodiment mainly includes the following three parts, as shown in Figure 7-1 :

[0105] 1. Trigger layer: Since the national road network is very large, it is impossible to perform all trajectory and road network differences on all roads. Therefore, it is considered to trigger based on the information of sudden drops in yaw of the trajectory and the roads under construction or blocked in the vicinity, and then perform trajectory retrieval within this range.

[0106] 2. Rendering layer: mainly perform noise reduction processing on the retrieved trajectory data within the range, then draw a trajectory map in the form of trajectory points, and obtain a road network map by drawing the regional acquisition of the road network data. Figure 7-1 The LD (Lane Detection Data) data in

[0107] is mainly used to describe the detection results of lane lines or lane boundaries during vehicle driving, and usually includes information such as the position, shape, and type (such as solid lines and dashed lines) of the lane lines.

[0108] Based on the above three parts, it is designed into four major modules at the product design level: Task Trigger Module; Trajectory Retrieval and Rendering Module; Differential Strategy Module; Intelligence Push Module. The following is an introduction to each major module in turn:

[0109] I. Task Trigger Module

[0110] 1) Trajectory information: Due to a large number of trajectories on a certain road in the past few days, but there has been a significant decrease in the amount of trajectories in recent days, resulting in a sudden drop in trajectories. Or there is a big difference between the navigation plan and the actual driving trajectory of users, that is, the phenomenon of deviation. In addition, there are a large number of U-turns at some intersections. Therefore, this part of the road needs to be recalled as a trigger.

[0111] 2) Construction integration data: mainly for the roads that are recalled due to construction, and there may be differences in these roads that affect the driving conditions of users. Therefore, this part of the road needs to be recalled as a trigger source.

[0112] 3) Blocking data: that is, there are some blocked roads in the current area, but the blocking may be incomplete. As a result, the planned road from the starting point to the end point for users is still inaccessible. Therefore, it is also necessary to recall and trigger the roads with partial blockages in the area.

[0113] In summary: The roads that meet the above conditions will be selected as trigger sources, and then the area will be framed to retrieve the trajectory and obtain the time trajectory point status of the current area.

[0114] II. Trajectory Retrieval and Rendering Module

[0115] 1) Based on the area delimited by the trigger module, retrieve the trajectory data of this area in the past day. Since there are unstable actual trajectory points, noise data will be generated, and this part of the data will be denoised.

[0116] 2) Road network map. After obtaining this part of the area, the road lines on both sides of the current road and the width between the two lines can be obtained. Therefore, this part of the road network map can be drawn based on this, and the road network map can be obtained. Further, the trajectory lines that should exist can also be filled inside the road network map to obtain a road network map containing trajectory lines, and the differential result with a similar effect can also be obtained by differentiating with the trajectory map.

[0117] 3) Trajectory map. According to the denoised trajectory data, draw the trajectory lines of this area based on the trajectory points.

[0118] III. Differential Strategy Module

[0119] 1) According to the trajectory map and the road network map (see Figure 7-2)Perform image differencing to obtain how many trajectory points pass through the road in this area. The more white the area is, the more likely the road is different. On the contrary, the less white area indicates that more trajectory points pass through (see Figure 7-3 the central part of Figure 7-2 . By comparing the central parts of

[0120] it can be seen that: due to the existence of more trajectory points in the central section of the road, the color of the result after differencing is darker (black), while the longitudinal roads on both sides appear brighter (white) due to the existence of fewer trajectory points).

[0121] IV. Intelligence Push Module

[0122] It is mainly divided into automatic blocking intelligence push and manual review blocking intelligence push. This module mainly needs to determine which are the intelligence sources to be pushed and the relevant content to be provided for pushing the intelligence. This is conducive to subsequent viewing of the road blocking situation and subsequent manual review.

[0123] The solution provided in this embodiment, by performing trajectory retrieval on the road and using the image differencing strategy for road blocking, has made remarkable progress in improving the accuracy and timeliness of road blocking. And compared with the traditional trajectory portrait statistical data method, this solution can more accurately verify the road blocking situation and avoid the problem of incomplete road blocking in the past. In addition, accurate blocking processing also reduces the troubles and inconveniences that users may encounter during navigation, thereby improving the overall navigation experience, effectively improving the quality of road navigation services, and providing users with a more convenient and accurate travel experience.

[0124] Further referring to Figure 8 , as an implementation of the methods shown in the above figures, the present disclosure provides an embodiment of an abnormal state road determination device. This device embodiment corresponds to Figure 2 the method embodiment shown, and this device can be specifically applied to various electronic devices.

[0125] As shown in Figure 8As shown in the figure, the abnormal state road determination device 800 of this embodiment may include: a road area to be recognized determination unit 801, a trajectory map acquisition unit 802, a road network map acquisition unit 803, an image difference unit 804, and an abnormal state road determination unit 805. Among them, the road area to be recognized determination unit 801 is configured to determine the road area to be recognized based on the trajectory change characteristics; the trajectory map acquisition unit 802 is configured to obtain a trajectory map according to the actual trajectories that appear in the road area to be recognized; the road network map acquisition unit 803 is configured to obtain a road network map according to the road network information corresponding to the road area to be recognized; the image difference unit 804 is configured to perform image difference processing on the trajectory map and the road network map to obtain a difference image; the abnormal state road determination unit 805 is configured to determine the target road in the abnormal state according to the difference image.

[0126] In this embodiment, in the abnormal state road determination device 800: the specific processing of the road area to be recognized determination unit 801, the trajectory map acquisition unit 802, the road network map acquisition unit 803, the image difference unit 804, and the abnormal state road determination unit 805 and the technical effects brought by them can be respectively referred to Figure 2 the relevant descriptions of steps 201-205 in the corresponding embodiment, which will not be elaborated here.

[0127] In some other implementation manners of this embodiment, the road area to be recognized determination unit 801 includes:

[0128] A first determination subunit, configured to determine the road area to be recognized based on the trajectory change characteristics and the construction state information.

[0129] In some other implementation manners of this embodiment, the road area to be recognized determination unit 801 includes:

[0130] A second determination subunit, configured to determine the road area to be recognized based on the trajectory change characteristics and the known abnormal road information.

[0131] In some other implementation manners of this embodiment, the road area to be recognized determination unit 801 includes:

[0132] A third determination subunit, configured to determine the road area to be recognized according to the trajectory change characteristics, the construction state information, and the known abnormal road information.

[0133] In some other implementation manners of this embodiment, determining the road area to be recognized based on the trajectory change characteristics includes:

[0134] Determining the road area where the decline rate of the number of trajectories changing with time exceeds a first preset rate as the first road area;

[0135] Determine a road area where the growth rate of the number of yaw behaviors in the trajectory over time exceeds a second preset amplitude as the second road area; wherein, the road area to be recognized includes the first road area and the second road area.

[0136] In some other implementation manners of this embodiment, the abnormal state road determination device 800 may further include:

[0137] A connected domain construction unit, configured to determine the connected domain between the first road area and the second road area as the third road area in response to the distance between the first road area and the second road area being less than a preset distance;

[0138] An area range supplement unit, configured to supplement the third road area into the area range included in the road area to be recognized.

[0139] In some other implementation manners of this embodiment, determining the road area to be recognized based on the construction state information includes:

[0140] Determine road construction behaviors according to road administration information;

[0141] Determine the road area with road construction behaviors as the fourth road area; wherein, the road area to be recognized includes the fourth road area.

[0142] In some other implementation manners of this embodiment, determining the road area to be recognized based on known abnormal road information includes:

[0143] Determine the remaining normal road areas of the roads that are already in a partially closed state or a partially blocked state as the fifth road area; wherein, the road area to be recognized includes the fifth road area.

[0144] In some other implementation manners of this embodiment, the trajectory map acquisition unit 802 is further configured to:

[0145] Acquire the actual trajectories that appear in the road area to be recognized;

[0146] Perform denoising processing on the actual trajectories to obtain denoised trajectories;

[0147] Generate a trajectory map described in the form of lines according to the denoised trajectories.

[0148] In some other implementation manners of this embodiment, the image difference unit 804 includes:

[0149] An image difference sub-unit, configured to determine the target road in an abnormal state based on the bright-dark distribution in the difference image; wherein, the abnormal state includes: a blocked state or a closed state.

[0150] In some other implementation manners of this embodiment, the image difference sub-unit includes:

[0151] A primary screening module, configured to determine a primary screening road from the difference image according to the distribution of gray information in the difference image, and the actual brightness value corresponding to the primary screening road exceeds a first preset brightness value;

[0152] A target road determination module, configured to determine a target road in the abnormal state based on the road feature information and historical trajectory information of the primary screening road; wherein, the abnormal state includes: a blocked state or a closed state.

[0153] In some other implementation manners of this embodiment, the target road determination module is further configured to:

[0154] Determine the actual road level of the primary screening road according to the road feature information;

[0155] Determine the actual number of historical trajectories of the primary screening road according to the historical trajectory information;

[0156] Determine the primary screening road corresponding to the actual road level exceeding the preset road level and / or the actual number of historical trajectories exceeding the preset number of historical trajectories as the target road in the abnormal state.

[0157] In some other implementation manners of this embodiment, the target road determination module is further configured to:

[0158] Determine the scene type of the primary screening road according to the road attribute in the road feature information;

[0159] Determine the actual proportion of incorrect trajectories of the primary screening road according to the historical trajectory information; wherein, the actual proportion of incorrect trajectories is the proportion of the number of historical trajectories misjudged as traveling on the primary screening road to the total number of historical trajectories;

[0160] Determine the primary screening road corresponding to the scene type being a road intersection scene and the actual proportion of incorrect trajectories exceeding the preset proportion of incorrect trajectories as a complex intersection road;

[0161] In response to the actual brightness value of the complex intersection road exceeding a second preset brightness value, determine the complex intersection road as the target road in the abnormal state; wherein, the second preset brightness value is greater than the first preset brightness value.

[0162] In some other implementation manners of this embodiment, the target road determination module may further include:

[0163] A target road determination sub-module, configured to determine a preliminary screening road that does not belong to the complex intersection road and whose actual brightness value is greater than a third preset brightness value as a target road in the abnormal state; wherein, the third preset brightness value is greater than the first preset brightness value but less than the second preset brightness value.

[0164] In some other implementation manners of this embodiment, the abnormal state road determination device 800 may further include:

[0165] A verification information generation and push unit, configured to generate verification information to be verified according to the target road and push the verification information to an execution object with verification capabilities, so that the execution object verifies whether the target road is in the corresponding abnormal state.

[0166] This embodiment exists as a device embodiment corresponding to the above method embodiment. The abnormal state road determination device provided in this embodiment first screens out an area to be recognized where there may be roads in an abnormal state in the full-scale road network through trajectory change features, thereby reducing ineffective analysis. Then, image difference processing is performed on the road network map and trajectory map of the area to be recognized, and further, the coincidence degree between the real-time trajectory and the road can be determined according to the image difference result, that is, the roads in the abnormal state can be accurately determined from the visual level, so as to add the abnormal state to the corresponding road sections in the electronic map subsequently to improve the accuracy of the navigation planning path.

[0167] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, which includes: 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 when the instructions are executed by the at least one processor, the at least one processor is enabled to implement the abnormal state road determination method described in any of the above embodiments.

[0168] According to an embodiment of the present disclosure, the present disclosure also provides a readable storage medium, which stores computer instructions for enabling a computer to implement the abnormal state road determination method described in any of the above embodiments when executed.

[0169] According to an embodiment of the present disclosure, the present disclosure also provides a computer program product, which can implement the abnormal state road determination method described in any of the above embodiments when executed by a processor.

[0170] Figure 9FIG. shows a schematic block diagram of an exemplary electronic device 900 that can be used to implement embodiments of the present disclosure. The electronic device is intended to represent various forms of digital computers, such as, for example, 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 processors, cellular telephones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely exemplary and are not intended to limit the implementations of the present disclosure described and / or claimed herein.

[0171] As Figure 9 shown, the device 900 includes a computing unit 901 that 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. In the RAM 903, various programs and data required for the operation of the device 900 can also be stored. The computing unit 901, the ROM 902, and the RAM 903 are connected to each other via a bus 904. An input / output (I / O) interface 905 is also connected to the bus 904.

[0172] A plurality of components in the device 900 are connected to the I / O interface 905, including: an input unit 906, such as a keyboard, a mouse, etc.; an output unit 907, such as various types of displays, speakers, etc.; a storage unit 908, such as a magnetic disk, an optical disk, etc.; and a communication unit 909, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 909 allows the device 900 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0173] The computing unit 901 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 901 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated 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 executes the various methods and processes described above, such as the abnormal state road determination method. For example, in some embodiments, the abnormal state road determination method can be implemented as a computer software program that is tangibly contained in a machine-readable medium, such as the storage unit 908. In some embodiments, part or all of the computer program can 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 abnormal state road determination method described above can be executed. Alternatively, in other embodiments, the computing unit 901 can be configured to execute the abnormal state road determination method by any other suitable means (e.g., by means of firmware).

[0174] Various embodiments of the systems and techniques described above in this document can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGA), application-specific integrated circuits (ASIC), application-specific standard products (ASSP), system-on-chip systems (SOC), complex programmable logic devices (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a dedicated or general-purpose programmable processor, and can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0175] The program code for implementing the methods of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to the processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the program codes are executed by the processor or controller, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The program codes can be executed entirely on the machine, partially on the machine, as an independent software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0176] In the context of this disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in connection 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 include, 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 a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0177] In order 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 a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds 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, speech input, or tactile input).

[0178] The systems and techniques described herein can be implemented in a computing system that includes backend 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 frontend components (e.g., a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend 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.

[0179] A computer system may include a client and a server. The client and the server are generally far from each other and usually interact via a communication network. The relationship between the client and the server is generated by computer programs running on the respective computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system to solve the defects of high management difficulty and weak business scalability existing in traditional physical hosts and virtual private server (VPS) services.

[0180] According to the technical solution of the embodiment of the present disclosure, first, a region to be identified where roads in an abnormal state may exist is screened out from the full-scale road network through trajectory change features, thereby reducing ineffective analysis. Then, image difference processing is performed on the road network map and the trajectory map of the region to be identified, and further, the coincidence degree between the real-time trajectory and the road can be determined according to the image difference result, that is, the roads in an abnormal state can be accurately determined from the visual level, so as to attach the abnormal state to the corresponding road sections in the electronic map subsequently to improve the accuracy of the navigation planning path.

[0181] It should be understood that various forms of the processes shown above can be used, steps can be reordered, added, or deleted. For example, the steps described in the present disclosure can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution disclosed in the present disclosure can be achieved, and no limitation is made herein.

[0182] The above specific embodiments do not constitute a limitation to the protection scope of the present 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 principle of the present disclosure shall be included within the protection scope of the present disclosure.

Claims

1. An abnormal state road determination method, comprising: Determining a road area to be recognized based on trajectory change characteristics; Obtaining a trajectory map according to the actual trajectories appearing in the road area to be recognized; Obtaining a road network map according to the road network information corresponding to the road area to be recognized; Performing image difference processing on the trajectory map and the road network map to obtain a post-difference image; Determining a target road in an abnormal state according to the post-difference image.

2. The method according to claim 1, wherein The determining the road area to be recognized based on trajectory change characteristics includes: Determining the road area to be recognized based on trajectory change characteristics and construction status information.

3. The method according to claim 1, wherein The determining the road area to be recognized based on trajectory change characteristics includes: Determining the road area to be recognized based on the trajectory change characteristics and known abnormal road information.

4. The method according to claim 1, wherein The determining the road area to be recognized based on trajectory change characteristics includes: Determining the road area to be recognized according to the trajectory change characteristics, construction status information, and known abnormal road information.

5. The method according to any one of claims 1-4, wherein, Determining the road area to be recognized based on trajectory change characteristics includes: Determining a first road area as a road area where the decline rate of the number of trajectories over time exceeds a first preset rate; Determining a second road area as a road area where the growth rate of the number of yaw behaviors in the trajectories over time exceeds a second preset rate; wherein, the road area to be recognized includes the first road area and the second road area.

6. The method according to claim 5, further comprising: In response to the distance between the first road area and the second road area being less than a preset distance, determining a connected domain between the first road area and the second road area as a third road area; Supplementing the third road area into the area range included in the road area to be recognized.

7. The method according to claim 2 or 4, wherein Determining the road area to be recognized based on construction status information includes: Determining road construction behaviors according to road administration information; Determining a fourth road area as a road area where the road construction behaviors exist; wherein, the road area to be recognized includes the fourth road area.

8. The method according to claim 3 or 4, wherein Determining the road area to be recognized based on known abnormal road information includes: Determining a fifth road area as the remaining normal road areas of the roads that are already in a partially closed state or a partially blocked state; wherein, the road area to be recognized includes the fifth road area.

9. The method according to claim 1, wherein The obtaining a trajectory map according to the actual trajectories appearing in the road area to be recognized includes: Obtaining the actual trajectories appearing in the road area to be recognized; Performing denoising processing on the actual trajectories to obtain denoised trajectories; Generating a trajectory map described in the form of lines according to the denoised trajectories.

10. The method according to claim 1, wherein The determining a target road in an abnormal state according to the post-difference image includes: Determining a target road in the abnormal state based on the light and dark distribution in the post-difference image; wherein, the abnormal state includes: a blocked state or a closed state.

11. The method according to claim 10, wherein, The determining a target road in the abnormal state based on the light and dark distribution in the post-difference image includes: Determine a preliminarily screened road from the difference image according to the gray information distribution in the difference image; wherein, the actual brightness value corresponding to the preliminarily screened road exceeds a first preset brightness value. Based on the road feature information and historical trajectory information of the preliminarily screened road, determine a target road in the abnormal state; wherein, the abnormal state includes: a blocked state or a closed state.

12. The method according to claim 11, wherein, The determining the target road in the abnormal state based on the road feature information and historical trajectory information of the preliminarily screened road includes: According to the road feature information, determine the actual road grade of the preliminarily screened road. According to the historical trajectory information, determine the actual number of historical trajectories of the preliminarily screened road. Determine the preliminarily screened road corresponding to the actual road grade exceeding the preset road grade and / or the actual number of historical trajectories exceeding the preset number of historical trajectories as the target road in the abnormal state.

13. The method according to claim 11, wherein, The determining the target road in the abnormal state based on the road feature information and historical trajectory information of the preliminarily screened road includes: Determine the scene type of the preliminarily screened road according to the road attribute in the road feature information. According to the historical trajectory information, determine the actual proportion of incorrect trajectories of the preliminarily screened road; wherein, the actual proportion of incorrect trajectories is the proportion of the number of historical trajectories incorrectly recognized as traveling on the preliminarily screened road to the total number of historical trajectories. Determine the preliminarily screened road with the scene type being a road intersection scene and the actual proportion of incorrect trajectories exceeding the preset proportion of incorrect trajectories as a complex road intersection road. In response to the actual brightness value of the complex road intersection road exceeding a second preset brightness value, determine the complex road intersection road as the target road in the abnormal state; wherein, the second preset brightness value is greater than the first preset brightness value.

14. The method according to claim 13, further comprising: Determine the preliminarily screened road that does not belong to the complex road intersection road and has an actual brightness value greater than a third preset brightness value as the target road in the abnormal state; wherein, the third preset brightness value is greater than the first preset brightness value but less than the second preset brightness value.

15. The method according to claim 1, further comprising: Generate a to-be-verified intelligence according to the target road, and push the to-be-verified intelligence to an execution object with verification ability, so that the execution object verifies whether the target road is in the corresponding abnormal state.

16. An abnormal state road determination device, comprising: A to-be-identified road area determination unit configured to determine a to-be-identified road area based on trajectory change characteristics. A trajectory map acquisition unit configured to obtain a trajectory map according to the actual trajectories appearing in the to-be-identified road area. A road network map acquisition unit configured to obtain a road network map according to the road network information corresponding to the to-be-identified road area. An image difference unit configured to perform image difference processing on the trajectory map and the road network map to obtain a difference image. An abnormal state road determination unit configured to determine a target road in an abnormal state according to the difference image.

17. An electronic device, 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 to enable the at least one processor to execute the abnormal state road determination method according to any one of claims 1-15.

18. A non-transitory computer-readable storage medium storing computer instructions for causing the computer to execute the abnormal state road determination method according to any one of claims 1-15.

19. A computer program product comprising a computer program, wherein the steps of the abnormal state road determination method according to any one of claims 1-15 are implemented when the computer program is executed by a processor.

Images