Traffic condition identification method and device and computer program product

Abstract

The embodiment of the invention discloses a traffic condition identification method and device and a computer program product. The method comprises the following steps: acquiring trajectory data of a vehicle in a target area; determining vehicle behavior characteristics of each road section unit in the target area based on the trajectory data; performing spatial-temporal clustering on abnormal behaviors in the vehicle behavior characteristics, and determining candidate road section units where traffic events occur in the target area based on a spatial-temporal clustering result; and determining a detection interval based on the candidate road section units, and identifying the traffic condition of the detection interval based on the vehicle behavior characteristics of each road section unit in the detection interval. According to the invention, accurate identification of the traffic condition can be realized, and the timeliness and the coverage degree are significantly improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of dynamic traffic, in particular to a traffic condition identification method, device and computer program product. BACKGROUND

[0002] When a user is traveling or planning to travel, he / she often faces various traffic conditions. For example, bridge collapse, road collapse, major traffic accidents and other events can cause serious damage to road traffic capacity, and vehicles cannot normally pass or appear in a long-stopped state. These will seriously affect the user's travel plan, and even cause serious safety problems. Therefore, there is an urgent need for a way to accurately identify traffic conditions. SUMMARY

[0003] Therefore, the present application provides a traffic condition identification method, device and computer program product to accurately identify traffic conditions.

[0004] The present application provides the following solutions: According to a first aspect, a traffic condition identification method is provided, the method comprising: obtaining trajectory data of vehicles in a target area; determining vehicle behavior features of each road segment unit in the target area based on the trajectory data; spatiotemporal clustering of abnormal behaviors in the vehicle behavior features, and determining candidate road segment units in which traffic events occur in the target area based on the results of the spatiotemporal clustering; determining a detection interval based on the candidate road segment units, and identifying traffic conditions of the detection interval based on vehicle behavior features of each road segment unit in the detection interval.

[0005] According to a second aspect, a traffic condition identification device is provided, the device comprising: a data acquisition unit configured to obtain trajectory data of vehicles in a target area; a feature determination unit configured to determine vehicle behavior features of each road segment unit in the target area based on the trajectory data; a candidate screening unit configured to spatiotemporal cluster abnormal behaviors in the vehicle behavior features, and determine candidate road segment units in which traffic events occur in the target area based on the results of the spatiotemporal clustering; a traffic identification unit configured to determine a detection interval based on the candidate road segment units, and identify traffic conditions of the detection interval based on vehicle behavior features of each road segment unit in the detection interval.

[0006] According to a third aspect, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the steps of the method according to the first aspect.

[0007] According to the embodiments provided in the present application, the following technical effects are disclosed: The present application analyzes the vehicle behavior characteristics through the vehicle trajectory data, and performs the spatio-temporal clustering and the traffic condition identification based on the abnormal behavior, so as to realize the accurate identification of the traffic condition. In addition, this way does not need to rely on the manual reporting and the sensor setting, and can also timely monitor the traffic condition in the remote area, the night, the monitoring blind area and the like, so that the timeliness and the coverage degree of the traffic condition identification are significantly improved.

[0008] Of course, implementing any product of the present application does not necessarily need to achieve all the advantages described above at the same time. BRIEF DESCRIPTION OF DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments will be briefly introduced as follows. Obviously, the drawings in the following description only constitute some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings.

[0010] Figure 1 The system architecture diagram to which the embodiments of the present application are applicable.

[0011] Figure 2 The flowchart of the traffic condition identification method provided by the embodiments of the present application.

[0012] Figure 3a The schematic diagram of determining the detection interval provided by the embodiments of the present application.

[0013] Figure 3b The schematic diagram of determining the detection interval provided by the embodiments of the present application.

[0014] Figure 4 The schematic diagram of the traffic interruption provided by the embodiments of the present application.

[0015] Figure 5 The schematic diagram of the traffic interruption provided by the embodiments of the present application.

[0016] Figure 6 The schematic block diagram of the traffic condition identification device provided by the embodiments of the present application.

[0017] Figure 7 The schematic block diagram of the electronic device provided by the embodiments of the present application. DETAILED DESCRIPTION

[0018] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments of the present application shall fall within the scope of the present application.

[0019] The terms used in the embodiments of the present application are merely for the purpose of describing particular embodiments, and are not intended to limit the present application. The singular forms "a", "said" and "the" used in the embodiments of the present application and the appended claims are also intended to include the plural forms, unless the context clearly indicates otherwise.

[0020] It should be understood that the term "and / or" used herein is merely to describe the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B can represent the three cases of A alone, A and B together, and B alone. In addition, the character " / " herein generally represents an "or" relationship between the front and rear associated objects.

[0021] Depending on the context, the word "if" as used herein can be interpreted as meaning "when" or "upon" or "in response to determining" or "in response to detecting". Similarly, depending on the context, the phrase "if it is determined" or "if (a stated condition or event) is detected" can be interpreted as meaning "when it is determined" or "in response to determining" or "when (a stated condition or event) is detected" or "in response to detecting (a stated condition or event)".

[0022] The conventional way of identifying traffic conditions mainly relies on manual reporting of traffic events or using cameras installed at the roadside to collect events. However, the manual reporting of traffic events is too dependent on the initiative and timeliness of user reporting, so there are defects such as response delay and limited coverage. The way of installing cameras at the roadside is difficult to monitor traffic events in time in remote areas, at night, in monitoring blind areas and other scenes.

[0023] In view of this, the present application provides a new idea. In order to facilitate the understanding of the present application, first, the system architecture based on the present application is described. Figure 1 An exemplary system architecture to which embodiments of the present application can be applied is shown, as shown in FIG. 1, which can include a user device, a traffic condition identification apparatus located at a server end. Figure 1

[0024] Among them, the user device and the server can communicate. The user device and the server can be directly or indirectly connected through wired or wireless communication, which is not limited by the present application. ​

[0025] The user equipment can include, but is not limited to, a smart mobile terminal, a smart home device, a wearable device, a PC (Personal Computer), and the like. The smart mobile terminal can include a mobile phone, a tablet computer, a notebook computer, a PDA (Personal Digital Assistant), an Internet car, and the like. The smart home device can include a smart television, a smart refrigerator, and the like. The wearable device can include a smart watch, smart glasses, a virtual reality device, an augmented reality device, a mixed reality device (i.e., a device that can support virtual reality and augmented reality), and the like.

[0026] The server can be a stand-alone server, a server group, or a cloud server. The cloud server, also known as a cloud computing server or a cloud host, is a host product in a cloud computing service system, and is used to solve the problems of large management difficulty and weak service scalability in traditional physical hosts and virtual private server (VPS, Virtual Private Server) services.

[0027] The user can send a request through the user equipment. Specifically, the user equipment sends the request to the traffic condition recognition device on the server side through the network. The traffic condition recognition device predicts the traffic condition by using the method provided in the embodiments of the present application, and returns the traffic condition to the user equipment through the network in response to the request of the user. The user equipment displays the received traffic condition to the user. Alternatively, the server side can actively push the traffic condition to the user equipment, and the user equipment displays the traffic condition to the user or performs voice broadcast based on the traffic condition. Alternatively, the server side can perform downstream tasks based on the recognized traffic condition, such as determining a recommended route, recommending a departure time, generating risk warning information, and the like, and then sends the results of the downstream tasks to the user equipment.

[0028] In addition to the architecture shown in Figure 1 , the computer terminal device with strong computing capability can also obtain the traffic condition by using the method provided in the embodiments of the present application.

[0029] It should be understood that Figure 1 the number of user equipment and traffic condition recognition devices is only illustrative. According to the implementation needs, there can be any number of user equipment and traffic condition recognition devices.

[0030] Figure 2 The traffic condition recognition method provided in the embodiments of the present application is shown in the flowchart. The method can be executed by the traffic condition recognition device on the server side in the system shown in Figure 1 . As shown in Figure 2 , the method can include the following steps: Step 201: Obtain trajectory data of vehicles in a target area.

[0031] Step 203: Determine vehicle behavior features of each road segment unit in the target area based on the trajectory data.

[0032] Step 205: Perform spatio-temporal clustering on abnormal behaviors in the vehicle behavior features, and determine candidate road segment units in which traffic events occur in the target area based on the result of the spatio-temporal clustering.

[0033] Step 207: Determine a detection interval based on the candidate road segment units, and identify traffic conditions of the detection interval based on vehicle behavior features of each road segment unit in the detection interval.

[0034] As can be seen from the above process, the application analyzes vehicle behavior features through vehicle trajectory data, and based on abnormal behaviors therein, performs spatio-temporal clustering to obtain candidate road segment units, and based on the candidate road segment units, determines a detection interval, and then identifies traffic conditions based on vehicle behavior features of each road segment unit in the detection interval. This way can not only achieve accurate identification of traffic conditions, but also does not need to rely on manual reporting and sensor settings, and can also timely monitor traffic conditions in remote areas, at night, in monitoring blind areas and other scenarios, so that the timeliness and coverage of traffic condition identification are significantly improved.

[0035] The steps in the above process and the effects that can be further produced will be described in detail below in conjunction with embodiments. It should be noted that the "first", "second", and the like involved in the present disclosure do not have the limitations of size, order, and quantity, and are only used to distinguish in name. For example, "first threshold", "second threshold", "third threshold", and the like are only used to distinguish different thresholds in name.

[0036] First, the above step 201, i.e., "obtaining trajectory data of vehicles in a target area", will be described in detail in conjunction with an embodiment.

[0037] In the embodiments of the present application, trajectory data of vehicles in a target area is obtained. The target area here refers to an area on the road that needs to monitor traffic conditions. The target area can be a pre-designated area, for example, according to the influence degree on the entire road network traffic, areas with greater influence on road network traffic are selected as target areas, and for example, historical data can be used to select areas where traffic events are more likely to occur as target areas. The target area can also be a region selected based on traffic volume, for example, analyzing the traffic volume of each region, and preliminarily screening based on traffic volume, and selecting regions with traffic volume exceeding a traffic threshold as target regions.

[0038] The trajectory data is a collection of spatial position information of a moving object (such as a car, a two-wheeled vehicle, etc.) changing over time, and is widely used in traffic management, urban planning, logistics optimization, environmental monitoring, etc. The vehicle involved in the embodiments of the present application mainly includes a car, and in some scenarios can also include a two-wheeled vehicle, etc. The trajectory data is composed of a series of spatial coordinate points arranged in time sequence, and each coordinate point (i.e. a trajectory point) contains position information (such as latitude and longitude, address) and a timestamp.

[0039] The trajectory data described above can be obtained by reporting position information on a positioning device on the vehicle or a user device bound to the vehicle, or can be obtained from navigation data used by a user device on the vehicle, or can be obtained in other ways.

[0040] The step 203, i.e. "determining the vehicle behavior characteristics of each road segment unit in the target area based on the trajectory data", will be described in detail below in conjunction with an embodiment.

[0041] A road segment refers to a section of road in a road system with specific range and functional attributes, and is usually taken as the starting point and ending point of a road segment, such as the road part between two intersections, between the entrances and exits of a highway, etc. The road grade, purpose and management rules of the same road segment are usually consistent, such as a road segment being a city trunk road throughout or a speed limit of 60 kilometers per hour throughout. The road segment unit involved in the embodiments of the present application is a further division of the road segments in the target area, i.e. the road segments are divided into finer-grained road segment units of a preset length (such as 20 meters), thereby obtaining a high-resolution road network model of the target area.

[0042] The trajectory data of the vehicles in the target area is then mapped to each road segment unit of the target area, and the trajectory data of the vehicles on each road segment unit is analyzed, thereby obtaining the vehicle behavior characteristics of each road segment unit. The vehicle behavior characteristics can include normal behavior such as a vehicle driving from the starting point of a road segment unit to the ending point of the road segment unit, and can also include abnormal behavior such as sudden braking behavior, temporary parking behavior, etc.

[0043] Since the time interval of the position information reported by the positioning device is usually slightly longer, such as reporting once every 1 second, in order to improve the timeliness of monitoring abnormal behavior, the user end can obtain the data collected by the sensor, and analyze the vehicle behavior characteristics and report abnormal behavior based on the data collected by the sensor. For example, based on the data collected by the mobile phone accelerometer, gyroscope, etc., whether the vehicle has sudden braking behavior is analyzed. Since the sensor can achieve millisecond-level collection, the analysis of the vehicle behavior characteristics can be more timely.

[0044] The emergency braking behavior is mainly determined by calculating the acceleration of the vehicle, and analyzing whether the acceleration is negative and the absolute value exceeds a preset acceleration threshold. If so, it can be considered that the emergency braking behavior exists. The temporary stop behavior is mainly determined by calculating the speed of the vehicle. If the speed of the vehicle is lower than a parking speed threshold (for example, 0.5 km / h) and the duration is within a temporary stop duration interval, it is considered that the temporary stop behavior exists. The application does not make specific limitations on the determination method of abnormal behavior, and other determination methods can also be used.

[0045] The above step 205, i.e., "spatiotemporal clustering of abnormal behaviors in vehicle behavior features, and determining candidate road section units in which traffic events occur in the target area based on the results of spatiotemporal clustering", will be described in detail below in combination with embodiments.

[0046] Spatiotemporal clustering is an algorithm that groups abnormal behaviors by combining time and space dimensions. The core is to group abnormal behaviors with close spatial positions and close occurrence times into a cluster, and each cluster is called an abnormal behavior cluster. That is, the abnormal behaviors are clustered based on their occurrence time and occurrence position, and at least one abnormal behavior cluster is obtained.

[0047] The spatiotemporal clustering method used can include but is not limited to ST-DBSCAN (Spatial-Temporal Density-Based Spatial Clustering of Applications with Noise, Spatial-Temporal Density-Based Spatial Clustering of Applications with Noise), STING (Spatial-Temporal Information Grid, Spatial-Temporal Information Grid Clustering), ST-Graph (Spatial-Temporal Graph Clustering, Spatial-Temporal Graph Clustering) algorithm, etc.

[0048] Since the abnormal behavior cluster reflects that abnormal behaviors have occurred in a specific position range, it is highly probable that a traffic event has occurred near the specific range. Therefore, the road section unit corresponding to the abnormal behavior cluster can be determined as a candidate road section unit in which a traffic event occurs in the target area. For example, the road section unit to which the cluster center position of the abnormal behavior cluster belongs can be determined as a candidate road section unit. For another example, all road section units covered by the abnormal behavior cluster can be determined as candidate road section units.

[0049] As can be seen from the above, the spatiotemporal clustering method can determine the abnormal behaviors that have occurred in a cluster and their corresponding positions, thereby serving as a basis for subsequent identification of traffic conditions. This method can focus on key positions from massive unordered data, exclude the influence of invalid data, thereby accelerating the identification efficiency and improving the accuracy of determination.

[0050] The candidate road segment units identified in this step can be one or more, and can be discrete candidate road segment units or continuous candidate road segment units. That is, multiple consecutive road segment units may be identified as candidate road segment units.

[0051] The following describes in detail step 207, namely "determining the detection interval based on candidate road segment units and identifying the traffic conditions of the detection interval based on the vehicle behavior characteristics of each road segment unit in the detection interval", with reference to the embodiments.

[0052] As described in the above embodiments, since abnormal behavior clusters reflect the occurrence of abnormal behavior within a specific location range, a traffic incident is likely to have occurred in the vicinity of that specific range. Therefore, after determining candidate road segment units based on abnormal behavior clusters, it is necessary to search the preceding and following road segment units based on the candidate road segment units, and then combine the search results to comprehensively identify the traffic situation. Therefore, in order to facilitate identification, the "search" interval can be determined first, which is referred to as the detection interval in this embodiment.

[0053] For discrete candidate road segment units (i.e., non-continuous candidate road segment units), a detection interval can be formed by a first preset number of road segment units upstream of the candidate road segment unit, the candidate road segment unit itself, and a second preset number of road segment units downstream of the candidate road segment unit. In this embodiment, the driving direction of the vehicle trajectory is taken as the forward direction. The upstream of the candidate road segment unit refers to the road segment unit before the candidate road segment unit, that is, the road segment unit extending upward in front; the downstream of the candidate road segment unit refers to the road segment unit after the candidate road segment unit, that is, the road segment unit extending upward in back.

[0054] like Figure 3a As shown in the figure, the road segment units shown in purple are candidate road segment units. Since the candidate road segment units are discrete, they can be used together with the first preset number of upstream road segment units and the second preset number of downstream road segment units to form a detection interval.

[0055] In this embodiment, a discrete candidate road segment unit refers to a state where none of the preceding and following road segment units are candidate road segment units, thus forming a discontinuous state of candidate road segment units. For each discrete candidate road segment unit, a detection interval is formed by combining a first predetermined number of upstream road segment units, the candidate road segment unit itself, and a second predetermined number of downstream road segment units, as described above. For example, suppose that among sequentially adjacent road segment units a, b, c, d, and e, only road segment units b and d are candidate road segment units, while road segment units a, c, and e are not. Then, road segment units b and d are discrete candidate road segment units. A detection interval is determined for road segment unit b and its upstream and downstream road segments, and a detection interval is determined for road segment unit d and its upstream and downstream road segments.

[0056] For the continuous multiple candidate road section units, the upstream third preset number of road section units of the candidate road section unit ranked first in the continuous multiple candidate road section units, the candidate road section unit ranked first and the downstream fourth preset number of road section units thereof can be combined to form a detection interval. The first preset number, the second preset number, the third preset number and the fourth preset number can be the same or different.

[0057] As shown in FIG. 6, the road section units shown in purple are three continuous candidate road section units, and the candidate road section unit ranked first and the upstream third preset number and the downstream fourth preset number of road section units thereof can be combined to form a detection interval. Since the continuous candidate road section units all have abnormal behaviors, such as sudden braking and temporary stopping, the abnormal position of the traffic condition, such as traffic interruption, is most likely to be before the candidate road section unit ranked first. Therefore, the candidate road section unit ranked first and the upstream and downstream road section units thereof are selected to form a detection interval, which can more effectively include the abnormal position of the traffic condition, thereby improving the detection success rate. It should be noted that in the case of multiple continuous candidate road section units, the downstream road section of the candidate road section unit ranked first also includes all or part of the continuous candidate road section units. Figure 3b

[0058] In addition, it should be noted that in the embodiments of the present application, "front" is consistent with the driving direction of the vehicle, and "rear" is opposite to the driving direction of the vehicle.

[0059] As can be seen from the above, the present application can effectively improve the accuracy of traffic condition recognition by including the candidate road section unit and its upstream and downstream road section units in the detection interval based on the characteristics of the traffic flow conducted upstream and downstream by the influence of the traffic event. The multiple continuous candidate road section units are most likely to be affected by the same traffic event, so the detection interval is determined as a whole to avoid wasting computing power.

[0060] In the embodiments of the present application, the traffic condition of the detection interval can include a traffic abnormality type and a traffic abnormality position. The traffic abnormality type of the detection interval can be determined based on the vehicle behavior characteristics of each road section unit in the detection interval and the behavior characteristic conditions corresponding to at least one traffic abnormality type. As one of the implementable ways, in response to the vehicle behavior characteristics of each road section unit in the detection interval satisfying the preset behavior characteristic conditions corresponding to the traffic abnormality type, the traffic abnormality type is determined as the traffic abnormality type of the detection interval. This way can simply and efficiently judge the traffic abnormality type, and can improve or expand the judgment of the traffic abnormality type by flexibly adjusting the behavior characteristic conditions.

[0061] ​Specifically, pre-configured behavioral characteristic conditions can be set for each type of traffic anomaly. This application embodiment mainly addresses the situation of traffic flow interruption. Traffic flow interruption refers to a state in which road traffic capacity is severely damaged due to major traffic accidents, bridge collapses, road collapses, natural disasters, or other emergencies, resulting in vehicles being unable to pass normally or experiencing prolonged stagnation. Traffic flow interruption corresponds to different traffic states at different stages of development: for example, an event causing traffic flow interruption has just occurred, but the interruption characteristics are not yet obvious, and the traffic anomaly type at this time can be multi-vehicle behavior anomaly; after a period of time, the interruption characteristics gradually become obvious, and the traffic anomaly type at this time can be traffic obstruction; after a period of time, the interruption characteristics are more obvious, and a large-scale traffic interruption occurs, and the traffic anomaly type at this time can be traffic interruption.

[0062] One possible approach is to define the preset behavioral characteristics for traffic interruption as follows: the number of vehicles crossing and the number of vehicles exhibiting abnormal behavior in the first M road segment units of the detection interval are both 0, and the number of vehicles exhibiting abnormal behavior in the last N road segment units is greater than or equal to a first threshold, where M and N are positive integers. In other words, if the vehicle behavior characteristics of the road segment units in the detection interval meet the behavioral characteristics for traffic interruption, the traffic condition in the detection interval can be determined as traffic interruption. When determining the location of the traffic anomaly, the last road segment unit among the aforementioned first M road segment units can be identified as the location of the traffic anomaly.

[0063] like Figure 4 As shown in the diagram, assuming there is a bridge in the detection interval, if the bridge collapses, the number of vehicles passing through and the number of vehicles exhibiting abnormal behavior in the first M road segment units consisting of the road segment unit where the bridge is located and its upstream road segment units are both 0. That is, no vehicles pass through these road segment units, and no vehicles brake suddenly or stop temporarily in these road segment units. Furthermore, the number of vehicles exhibiting abnormal behavior in the last N road segments is greater than or equal to the first threshold. For example, the number of vehicles that stop temporarily (represented by red dots in the diagram) and / or brake suddenly (represented by purple dots in the diagram) is greater than the first threshold. In this case, it can be determined that the traffic condition in the detection interval is a traffic interruption.

[0064] It should be noted that M and N in this embodiment are not fixed values. Taking traffic interruption as an example, as long as the number of vehicles passing through the preceding road segment unit and the number of vehicles with abnormal behavior are 0 in the detection interval, and then the number of vehicles with abnormal behavior in several road segment units is greater than or equal to the first threshold, the behavioral characteristic condition of traffic interruption is met, and the traffic condition of the detection interval is considered to be traffic interruption.

[0065] As another implementable manner, the preset behavior characteristic condition corresponding to the traffic obstruction includes that the number of passing vehicles and the number of abnormal behavior vehicles of the first M road section units in the detection interval are both 0, and the number of abnormal behavior vehicles of the last N road section units is greater than or equal to the second threshold. In this case, the event of traffic interruption has occurred in front, and the abnormal behavior vehicles have gathered to a certain extent, but have not reached the degree of traffic interruption. When determining the traffic abnormal position, the last road section unit of the first M road section units can be determined as the traffic abnormal position.

[0066] As still another implementable manner, the preset behavior characteristic condition corresponding to the multi-vehicle abnormal behavior includes that the number of passing vehicles and the number of abnormal behavior vehicles of the first M road section units in the detection interval are both 0, and the number of abnormal behavior vehicles of the last N road section units is greater than or equal to the third threshold. In this case, the event of traffic interruption has occurred in front, and the abnormal behavior vehicles have just begun to gather. When determining the traffic abnormal position, the last road section unit of the first M road section units can be determined as the traffic abnormal position.

[0067] Since the multi-vehicle abnormal behavior, the traffic obstruction and the traffic interruption correspond to different development stages of the traffic interruption, in the above behavior characteristic conditions, the first threshold is greater than the second threshold, and the second threshold is greater than the third threshold. That is, as the degree of traffic interruption represented by the traffic abnormal type gradually deepens, the number of abnormal behavior vehicles on the last N road section units gradually increases. In addition, it should be noted that the implementable manners corresponding to the different development stages can be executed alternatively or sequentially. For example, first, the traffic condition of the detection interval is determined as the multi-vehicle abnormal behavior based on the behavior characteristic condition corresponding to the multi-vehicle abnormal behavior; after a period of time, the traffic condition of the detection interval is determined as the traffic obstruction based on the behavior characteristic condition corresponding to the traffic obstruction; and after another period of time, the traffic condition of the detection interval is determined as the traffic interruption based on the behavior characteristic condition corresponding to the traffic interruption.

[0068] In addition, when the last road section unit of the first M road section units is determined as the traffic abnormal position in the above process, one of the start position, the end position, the middle position and the like of the last road section unit can be more specifically determined as the traffic abnormal position. For example, assuming that a road section unit is 20 meters, the rear end point of the road section unit can be determined as the traffic abnormal position, and the determination of the specific traffic abnormal position can facilitate the generation of relatively accurate information when generating the prompt information and the broadcast content subsequently.

[0069] The different development stages of the traffic flow interruption can be simply and efficiently identified as the passing abnormal type corresponding to the traffic abnormal position by the above specific behavior characteristic condition, thereby providing a basis for subsequent reminding and broadcasting for the target user. In addition to the above behavior characteristic condition, the deformation of the above behavior characteristic condition based on the same idea and principle is within the protection scope of the present application, and all possible cases are not listed here.

[0070] In addition to determining the passing abnormal type of the detection interval by the vehicle behavior characteristic of each road segment unit in the detection interval and the behavior characteristic condition corresponding to each passing abnormal type, other ways can also be used, such as providing the vehicle behavior characteristic of the road segment unit in the detection interval to the detection model, and determining the passing abnormal type of the detection interval by the detection model.

[0071] Further, after determining the passing abnormal type, the vehicle behavior characteristic of the road segment unit in the detection interval is continuously monitored; and the detection interval is determined to resume passing in response to the vehicle behavior characteristic of each road segment unit in the detection interval satisfying the abnormal dissipation condition.

[0072] As one of the implementable ways, the abnormal dissipation condition can include that the number of passing vehicles of the first M road segment units in the detection interval is greater than a fourth threshold value, and M is a preset positive integer. As shown in Figure 5 If the bridge is repaired, vehicles will pass through the first M road segment units, that is, passing vehicles (represented by blue dots in the figure) will appear, and when the number of passing vehicles is greater than the fourth threshold value, it can be considered that the passing is resumed.

[0073] It can be seen that the present application establishes a closed-loop monitoring mechanism, which can continuously and timely track the traffic condition changes of traffic flow interruption and recovery, and realize the whole life cycle management from discovery to recovery.

[0074] Further, in the embodiments of the present application, the prompt information or the broadcast content can be generated based on the traffic condition of the detection interval; and then the prompt information or the broadcast content is sent to the user terminal of the target user.

[0075] The template corresponding to the prompt information or the broadcast content can be preconfigured, and the template includes a slot of the traffic condition type and a slot of the passing abnormal position. The corresponding slots in the template are filled based on the traffic condition type and the passing abnormal position included in the traffic condition of the detection interval, to generate the prompt information or the broadcast content.

[0076] Taking the broadcast content as an example, the template can be: the front

road where the detection interval is located

traffic condition type

distance between the abnormal traffic location and the current location of the target user

[0077] After the traffic resumes, prompt information or broadcast content can also be generated; and then the prompt information or the broadcast content is sent to the user terminal of the target user.

[0078] Taking the broadcast content as an example, the template after the traffic resumes can be: the front

road where the detection interval is located

[0079] In the embodiment of the application, the navigation route of the target user passes through the abnormal traffic location, the location of the user terminal of the target user has not reached the abnormal traffic location, and the distance between the target user and the abnormal traffic location is less than or equal to a preset distance threshold. That is, the user who will pass through the abnormal traffic location in a short time is taken as the target user. In addition, other ways can also be used to determine the target user, for example, the user within a preset distance range from the abnormal traffic location is taken as the target user, and the like.

[0080] After receiving the prompt information, the user terminal of the target user can display the prompt information on the user interface. For example, the abnormal traffic location is labeled by using text or visual elements on the navigation interface; for another example, the prompt information is displayed on the navigation interface by using the pop-up message.

[0081] After receiving the broadcast content, the user terminal of the target user can synthesize the broadcast content into a broadcast voice, and play the broadcast voice.

[0082] In addition to the prompt and the broadcast, other ways such as early warning can also be used to send to the target user.

[0083] Through the above-mentioned manner, the traffic condition can be actively reminded and broadcast to the user who will pass through and be affected, so as to improve the user experience of the user in the navigation process.

[0084] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0085] According to another embodiment, a traffic condition identification device is provided. Figure 6 A schematic block diagram of a traffic condition recognition device provided in an embodiment of this application, such as... Figure 6 As shown, the device 600 includes: a data acquisition unit 601, a feature determination unit 602, a candidate filtering unit 603, and a traffic identification unit 604, and may also include a content transmission unit 605. The main functions of each component are as follows: The data acquisition unit 601 is configured to acquire trajectory data of vehicles within the target area.

[0086] The feature determination unit 602 is configured to determine the vehicle behavior characteristics of each road segment unit within the target area based on trajectory data.

[0087] The candidate screening unit 603 is configured to perform spatiotemporal clustering of abnormal behaviors in vehicle behavior characteristics, and determine candidate road segment units in the target area where traffic events occur based on the spatiotemporal clustering results.

[0088] Traffic identification unit 604 is configured to determine the detection interval based on candidate road segment units and to identify the traffic conditions of the detection interval based on the vehicle behavior characteristics of each road segment unit in the detection interval.

[0089] As one possible implementation method, the candidate screening unit 603 can be specifically configured to: cluster abnormal behaviors based on the occurrence time and location of the abnormal behaviors to obtain at least one abnormal behavior cluster; and determine the road segment unit corresponding to the abnormal behavior cluster as a candidate road segment unit for traffic events occurring in the target area.

[0090] As one possible implementation, when determining the detection interval based on the candidate road segment unit and its upstream and downstream road segment units, the traffic identification unit 604 can be specifically configured as follows: for discrete candidate road segment units, a detection interval is formed by a first preset number of road segment units upstream of the candidate road segment unit, the candidate road segment unit and its downstream second preset number of road segment units; for multiple consecutive candidate road segment units, a detection interval is formed by a third preset number of road segment units upstream of the first candidate road segment unit in the multiple consecutive candidate road segment units, the first candidate road segment unit and its downstream fourth preset number of road segment units.

[0091] As one possible implementation method, when the traffic identification unit 604 identifies the traffic conditions of the detection interval based on the vehicle behavior characteristics of each road segment unit in the detection interval, it can be specifically configured to: in response to the vehicle behavior characteristics of each road segment unit in the detection interval satisfying the preset behavior characteristic conditions of the traffic anomaly type, determine that the traffic anomaly type is the traffic anomaly type of the detection interval.

[0092] As one possible implementation method, the traffic anomaly type includes traffic interruption. The preset behavioral characteristic conditions corresponding to traffic interruption include: the number of passing vehicles and the number of vehicles with abnormal behavior in the first M road segment units of the detection interval are both 0, and the number of vehicles with abnormal behavior in the last N road segment units is greater than or equal to a first threshold; and / or, Traffic anomaly types include traffic obstruction. The preset behavioral characteristic conditions corresponding to traffic obstruction include: the number of vehicles crossing and the number of vehicles exhibiting abnormal behavior in the first M road segment units of the detection interval are both 0, and the number of vehicles exhibiting abnormal behavior in the last N road segment units is greater than or equal to a second threshold; and / or, Traffic anomaly types include multi-vehicle behavior anomalies. The preset behavioral characteristic conditions for multi-vehicle behavior anomalies include: the number of passing vehicles and the number of vehicles with abnormal behavior in the first M road segment units of the detection interval are both 0, and the number of vehicles with abnormal behavior in the last N road segment units is greater than or equal to the third threshold. Where M and N are positive integers, the first threshold is greater than the second threshold, and the second threshold is greater than the third threshold.

[0093] Furthermore, the traffic identification unit 604 can also be specifically configured to identify the last road segment unit among the first M road segment units as the location of traffic anomalies.

[0094] Furthermore, the traffic identification unit 604 can also be configured to: after determining that the traffic anomaly type is the traffic anomaly type of the detection interval, monitor the vehicle behavior characteristics of road segment units in the detection interval; in response to the vehicle behavior characteristics of each road segment unit in the detection interval satisfying the anomaly dissipation condition, determine that the detection interval has resumed traffic; wherein, the anomaly dissipation condition includes: the number of vehicles passing through the first M road segment units in the detection interval is greater than a fourth threshold, where M is a preset positive integer.

[0095] Furthermore, the content sending unit 605 can be configured to: generate prompt information or broadcast content based on the traffic conditions of the detection interval; send the prompt information or broadcast content to the target user's terminal, where the target user's navigation route passes through the traffic abnormality location, the target user's terminal location has not yet reached the traffic abnormality location, and the distance between the target user's terminal location and the traffic abnormality location is less than or equal to a preset distance threshold.

[0096] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, for system or device embodiments, since they are basically similar to method embodiments, the description is relatively simple, and relevant parts can be referred to the description of the method embodiments. The system and device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0097] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and corresponding operation entry points are provided for users to choose to authorize or refuse.

[0098] In addition, embodiments of this application also provide a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the method described in any of the foregoing method embodiments.

[0099] And an electronic device, comprising: One or more processors; and A memory associated with the one or more processors, the memory being used to store program instructions that, when read and executed by the one or more processors, perform the steps of the method described in any of the foregoing method embodiments.

[0100] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the method described in any of the foregoing method embodiments.

[0101] in, Figure 7 An exemplary architecture of an electronic device is shown, which may include a processor 710, a video display adapter 711, a disk drive 712, an input / output interface 713, a network interface 714, and a memory 720. The processor 710, video display adapter 711, disk drive 712, input / output interface 713, network interface 714, and memory 720 can communicate with each other via a communication bus 730.

[0102] The processor 710 can be implemented using a general-purpose CPU, microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits to execute relevant programs and implement the technical solution provided in this application.

[0103] The memory 720 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 720 can store the operating system 721 for controlling the operation of the electronic device 700, and the basic input / output system (BIOS) 722 for controlling the low-level operations of the electronic device 700. Additionally, it can store a web browser 723, a data storage management system 724, and a traffic condition recognition device 600, etc. The aforementioned traffic condition recognition device 600 can be the application program that specifically implements the aforementioned steps in this embodiment. In summary, when the technical solution provided in this application is implemented through software or firmware, the relevant program code is stored in the memory 720 and is called and executed by the processor 710.

[0104] Input / output interface 713 is used to connect input / output modules to realize information input and output. Input / output modules can be configured as components in the device (not shown in the figure) or externally connected to the device to provide corresponding functions. Input devices may include keyboards, mice, touch screens, microphones, various sensors, etc., and output devices may include displays, speakers, vibrators, indicator lights, etc.

[0105] Network interface 714 is used to connect a communication module (not shown in the figure) to enable communication between this device and other devices. The communication module can communicate via wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0106] Bus 730 includes a pathway for transmitting information between various components of the device, such as processor 710, video display adapter 711, disk drive 712, input / output interface 713, network interface 714, and memory 720.

[0107] It should be noted that although the above-described device only shows the processor 710, video display adapter 711, disk drive 712, input / output interface 713, network interface 714, memory 720, bus 730, etc., in specific implementations, the device may also include other components necessary for normal operation. Furthermore, those skilled in the art will understand that the above-described device may only include the components necessary for implementing the solution of this application, and does not necessarily include all the components shown in the figures.

[0108] As can be seen from the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a computer program product. This computer program product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in various embodiments or some parts of the embodiments of this application.

[0109] The technical solutions provided in this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for identifying traffic conditions, characterized in that, The method includes: Obtain vehicle trajectory data within the target area; Based on the trajectory data, the vehicle behavior characteristics of each road segment unit within the target area are determined; Spatiotemporal clustering is performed on the abnormal behaviors in the vehicle behavior characteristics, and candidate road segment units in the target area are determined based on the results of the spatiotemporal clustering. The detection interval is determined based on the candidate road segment units, and the traffic conditions of the detection interval are identified based on the vehicle behavior characteristics of each road segment unit in the detection interval.

2. The method according to claim 1, characterized in that, The step of performing spatiotemporal clustering on abnormal behaviors in the vehicle behavior characteristics, and determining candidate road segment units where traffic events have occurred within the target area based on the results of the spatiotemporal clustering, includes: The abnormal behaviors are clustered based on their occurrence time and location to obtain at least one cluster of abnormal behaviors; The road segment units corresponding to the abnormal behavior clusters are identified as candidate road segment units for traffic incidents occurring within the target area.

3. The method according to claim 1, characterized in that, The step of determining the detection interval based on the candidate road segment units includes: For a discrete candidate road segment unit, a detection interval is formed by the first preset number of road segment units upstream of the candidate road segment unit, the candidate road segment unit and the second preset number of road segment units downstream of the candidate road segment unit; For a series of consecutive candidate road segment units, the detection interval is formed by the third preset number of road segment units upstream of the first candidate road segment unit, the first candidate road segment unit and the fourth preset number of road segment units downstream of it.

4. The method according to claim 1, characterized in that, The method of identifying the traffic conditions of the detection interval based on the vehicle behavior characteristics of each road segment unit in the detection interval includes: If the vehicle behavior characteristics of each road segment unit in the detection interval meet the preset behavior characteristic conditions corresponding to the traffic anomaly type, then the traffic anomaly type is determined to be the traffic anomaly type of the detection interval.

5. The method according to claim 4, characterized in that, The traffic anomaly types include traffic interruption, and the preset behavioral characteristic conditions corresponding to the traffic interruption include: the number of vehicles passing through and the number of vehicles exhibiting abnormal behavior in the first M road segment units of the detection interval are both 0, and the number of vehicles exhibiting abnormal behavior in the last N road segment units is greater than or equal to a first threshold; and / or, The traffic anomaly types include traffic obstruction, and the preset behavioral characteristic conditions corresponding to traffic obstruction include: the number of vehicles passing through and the number of vehicles exhibiting abnormal behavior in the first M road segment units of the detection interval are both 0, and the number of vehicles exhibiting abnormal behavior in the last N road segment units is greater than or equal to a second threshold; and / or, The traffic anomaly type includes multi-vehicle behavior anomaly. The preset behavioral characteristic conditions for multi-vehicle behavior anomaly include: the number of passing vehicles and the number of vehicles with abnormal behavior in the first M road segment units of the detection interval are both 0, and the number of vehicles with abnormal behavior in the last N road segment units is greater than or equal to the third threshold. Wherein, M and N are positive integers, the first threshold is greater than the second threshold, and the second threshold is greater than the third threshold.

6. The method according to claim 5, characterized in that, The method of identifying the traffic conditions of the detection interval based on the vehicle behavior characteristics of each road segment unit in the detection interval also includes: The last road segment unit among the first M road segment units is identified as the location of the traffic anomaly.

7. The method according to claim 4, characterized in that, After determining that the traffic anomaly type is the traffic anomaly type of the detection interval, the method further includes: Monitor the vehicle behavior characteristics of road segment units within the detection interval; In response to the vehicle behavior characteristics of each road segment unit in the detection interval meeting the anomaly dissipation condition, it is determined that the detection interval has resumed traffic. The anomaly dissipation condition includes: the number of vehicles passing through the first M road segment units in the detection interval is greater than a fourth threshold, where M is a preset positive integer.

8. The method according to any one of claims 1 to 7, characterized in that, The traffic conditions include locations of traffic disruptions, and the method further includes: Based on the traffic conditions in the detection zone, generate prompts or broadcast content; The prompt message or broadcast content is sent to the target user's terminal. The target user's navigation route passes through the abnormal traffic location. The target user's terminal location has not yet reached the abnormal traffic location, and the distance between the target user and the abnormal traffic location is less than or equal to a preset distance threshold.

9. A traffic condition recognition device, characterized in that, The device includes: The data acquisition unit is configured to acquire trajectory data of vehicles within the target area; The feature determination unit is configured to determine the vehicle behavior characteristics of each road segment unit within the target area based on the trajectory data. The candidate screening unit is configured to perform spatiotemporal clustering on abnormal behaviors in the vehicle behavior features, and determine candidate road segment units in the target area where traffic events have occurred based on the spatiotemporal clustering results. The traffic identification unit is configured to determine a detection interval based on the candidate road segment units, and to identify the traffic conditions of the detection interval based on the vehicle behavior characteristics of each road segment unit in the detection interval.

10. A computer program product, comprising a computer program, characterized in that, When executed by a processor, the computer program implements the steps of the method according to any one of claims 1 to 8.

Images