Vehicle splitting method and apparatus

Abstract

The application discloses a vehicle separating method and device, wherein the method comprises: determining a plurality of trajectories according to trigger positions corresponding to each trigger information of a trigger information group when a detection execution condition is satisfied, wherein each trigger information is trigger information of a weighing sensor in a weighing area being triggered; determining at least one trajectory group according to a trajectory feature of each trajectory in the plurality of trajectories, wherein each trajectory group in the at least one trajectory group contains at least one trajectory in the plurality of trajectories; and performing a separating process according to the at least one trajectory group to obtain at least one vehicle, wherein the at least one trajectory group and the at least one vehicle are in one-to-one correspondence. Through the application, the problem that a vehicle separating method in the related art has a large consumption of computing resources in a separating process is solved.

Description

Technical Field

[0001] This application relates to the field of computers, and more specifically, to a method and apparatus for vehicle separation. Background Technology

[0002] To reduce safety hazards caused by overloaded freight vehicles and avoid traffic congestion due to low weighing efficiency during manual on-site vehicle weighing, a non-site enforcement system based on dynamic weighing can be used to dynamically weigh vehicles. This system ensures that vehicle weight measurement, license plate capture, matching, and data uploading are completed during normal vehicle movement. The dynamic weighing system within this system can include: a weighing sensor array installed on the road surface (e.g., strip sensors, wheel spoke sensors), and vehicle identification sensors (e.g., inductive loop detectors).

[0003] Currently, the vehicle allocation algorithms used in off-site law enforcement systems are generally real-time processing, meaning that the logic must be executed every time a sensor is triggered, consuming significant computing resources. Furthermore, real-time processing requires making decisions with potentially insufficient information, resulting in a relatively high error rate; even with error correction mechanisms, it still places a considerable burden on computing resources.

[0004] It is evident that the vehicle allocation methods in related technologies suffer from the problem of high computational resource consumption during vehicle allocation processing. Summary of the Invention

[0005] This application provides a vehicle allocation method and apparatus to at least address the problem of high computational resource consumption in related technologies.

[0006] According to one aspect of the embodiments of this application, a vehicle allocation method is provided, comprising: upon detecting that an execution condition is met, determining multiple trajectories based on the trigger position corresponding to each trigger information in a trigger information group, wherein each trigger information is trigger information indicating that a weighing sensor in a weighing area is triggered; determining at least one trajectory group based on the trajectory characteristics of each trajectory in the multiple trajectories, wherein each trajectory group in the at least one trajectory group contains at least one trajectory in the multiple trajectories; and performing vehicle allocation processing based on the at least one trajectory group to obtain at least one vehicle, wherein the at least one trajectory group corresponds one-to-one with the at least one vehicle.

[0007] According to another aspect of the embodiments of this application, a vehicle allocation device is also provided, comprising: a first determining unit, configured to determine multiple trajectories based on the trigger position corresponding to each trigger information in a trigger information group when an execution condition is detected to be met, wherein each trigger information is trigger information of a weighing sensor in a weighing area being triggered; a second determining unit, configured to determine at least one trajectory group based on the trajectory characteristics of each trajectory in the multiple trajectories, wherein each trajectory group in the at least one trajectory group contains at least one trajectory in the multiple trajectories; and a vehicle allocation unit, configured to perform vehicle allocation processing based on the at least one trajectory group to obtain at least one vehicle, wherein the at least one trajectory group corresponds one-to-one with the at least one vehicle.

[0008] According to another aspect of the embodiments of this application, a computer-readable storage medium is also provided, wherein a computer program is stored in the computer program, and the computer program is configured to execute the above-described vehicle separation method when it is run.

[0009] According to another aspect of the embodiments of this application, an electronic device is also provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the above-described vehicle allocation method through the computer program.

[0010] In this embodiment, a method is adopted to determine vehicle trajectories based on triggering locations according to set execution conditions and to perform vehicle matching based on trajectory features. When the execution conditions are met, multiple trajectories are determined according to the triggering locations corresponding to each triggering information in a triggering information group. Each triggering information is the triggering information of a weighing sensor within the weighing area. At least one trajectory group is determined based on the trajectory features of each of the multiple trajectories, where each trajectory group contains at least one of the multiple trajectories. Vehicle allocation is performed based on the at least one trajectory group to obtain at least one vehicle. Since the vehicle allocation operation is triggered by setting execution conditions, rather than being executed every time triggering information is received, computational resource consumption can be reduced. Dividing vehicle trajectories based on triggering locations when the execution conditions are met improves the rationality of vehicle allocation. Furthermore, vehicle matching based on the trajectory features of the vehicle trajectories ensures the accuracy of vehicle matching, thereby reducing the number of triggers for the vehicle allocation logic and achieving the technical effect of reducing the computational resource consumption of vehicle allocation. This solves the problem of high computational resource consumption in vehicle allocation methods in related technologies. Attached Figure Description

[0011] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0012] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 This is a schematic diagram of the hardware environment of an optional vehicle allocation method according to an embodiment of this application;

[0014] Figure 2 This is a schematic diagram of the overall process of an optional vehicle allocation method according to an embodiment of this application;

[0015] Figure 3 This is a detailed flowchart illustrating an optional vehicle allocation method according to an embodiment of this application;

[0016] Figure 4 This is a schematic diagram of the trajectory matching process according to an embodiment of this application;

[0017] Figure 5 This is a structural block diagram of an optional vehicle separation device according to an embodiment of this application;

[0018] Figure 6 This is a structural block diagram of an optional electronic device according to an embodiment of this application. Detailed Implementation

[0019] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0020] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0021] According to one aspect of the embodiments of this application, a vehicle allocation method is provided. Optionally, in this embodiment, the above-described vehicle allocation method can be applied to, for example... Figure 1 The hardware environment shown consists of a weighing sensor 102 and a server 104. Figure 1 As shown, server 104 is connected to weighing sensor 102 via a network and can be used to provide services (such as application services) to terminals or clients installed on terminals. A database can be set up on the server or independently of the server to provide data storage services for server 104.

[0022] The aforementioned network may include, but is not limited to, at least one of the following: wired network, wireless network. The aforementioned wired network may include, but is not limited to, at least one of the following: wide area network, metropolitan area network, local area network. The aforementioned wireless network may include, but is not limited to, at least one of the following: Wi-Fi (Wireless Fidelity), Bluetooth. The weighing sensor 102 is not limited to PCs, mobile phones, tablets, etc.

[0023] The vehicle allocation method of this application embodiment can be executed by server 104, by weighing sensor 102, or by both server 104 and weighing sensor 102. Alternatively, the weighing sensor 102 can execute the vehicle allocation method of this application embodiment by a client installed on it.

[0024] Taking the vehicle allocation method in this embodiment as an example, which is executed by server 104, Figure 2 This is a schematic diagram of the overall process of an optional vehicle allocation method according to an embodiment of this application, as shown below. Figure 2 As shown, the process of this method may include the following steps:

[0025] Step S202: When the execution conditions are detected to be met, multiple trajectories are determined according to the trigger position corresponding to each trigger information in the trigger information group, wherein each trigger information is the trigger information of the weighing sensor in the weighing area being triggered.

[0026] The vehicle separation method in this embodiment can be applied in the following scenarios: weighing and separating vehicles using weighing sensors deployed along the lanes. These weighing sensors can be located on the highway, and can be bar sensors, spoke sensors, or other sensors or sensor arrays used for vehicle weighing. This embodiment does not impose any limitations on this.

[0027] Within a specific area (e.g., a highway), at least one lane may be provided, and a weighing area may be provided on the at least one lane. Multiple rows of load cells (e.g., two rows of load cells) or an array of load cells may be provided within the weighing area. Each row of load cells may contain multiple load cells (e.g., two load cells). Load cells located in the same row may be arranged side-by-side or not side-by-side, for example, arranged in a crisscross pattern.

[0028] When a vehicle (e.g., a regular truck, an off-road truck, a special-purpose vehicle, etc.) passes through the weighing area of ​​a lane, the wheels on different sides of the vehicle will trigger the weighing sensors multiple times, thus obtaining multiple trigger information. The aforementioned trigger information is sensor-level information, which may include trigger location, trigger time, and, depending on the sensor type, may also include pressure waveform curves, or information obtained from pressure waveform curves, such as waveform maximum value, waveform integral sum, waveform width, etc., which are not limited in this example.

[0029] Each weighing component can upload the trigger information to the server via the network after collecting the trigger information. The trigger information can be uploaded in real time (e.g., directly uploaded to the server after each trigger information is detected) or uploaded with a delay (e.g., the detected trigger information is uploaded to the server only after the number of detected trigger information reaches a target threshold or after a predetermined time). This embodiment does not limit the method of uploading trigger information.

[0030] The server can receive trigger information uploaded by multiple weighing sensors and store the received trigger information in a trigger information group. The server can store trigger information groups containing the trigger information currently uploaded by the weighing sensors. This trigger information can be pending or processed. Processed trigger information refers to trigger information that has already been processed for vehicle allocation when the execution conditions were met in the last instance. Here, the trigger information group contains the weighing information of all vehicles that have not yet departed. After receiving the trigger information sent by the weighing sensors, the server can check whether the conditions for executing the vehicle allocation logic are met. Optionally, vehicle allocation can also be performed when execution conditions unrelated to receiving trigger information are met (e.g., a vehicle allocation signal is detected from the vehicle allocation sensor). This embodiment does not limit this.

[0031] The above execution conditions can be one or more. For example, they can be determined by judging whether the number of pending trigger information received by the server reaches a set threshold, or by detecting whether there are vehicles waiting to be dispatched or vehicles waiting to enter the weighing area within the detection area, or by other conditions. This embodiment does not limit this.

[0032] When the server detects that the execution conditions are met, it can determine multiple trajectories based on the trigger positions corresponding to each trigger information in the trigger information group. Each trigger information in the trigger information group can correspond to a trigger position; different trigger information can correspond to the same or different trigger positions. Multiple trajectories are determined based on the trigger position corresponding to each trigger information, and each trajectory can contain one or more trigger information items that are close to the trigger position in the trigger information group. The trigger position can include at least one of the following: the sensor identifier of the load cell, the actual position of the wheel triggering the load cell (e.g., the actual position based on real-world coordinates), and the relative position of the wheel triggering the load cell (e.g., the position relative to a certain point on the load cell).

[0033] Based on the trigger position corresponding to each trigger information, multiple trajectories can be determined in one or more ways. For example, if each trigger information in a trigger information group is a trigger information to be processed, clustering or other information aggregation operations can be performed on the trigger positions corresponding to each trigger information to obtain multiple trigger information sets, each trigger information set corresponding to one trajectory. Alternatively, if each trigger information in a trigger information group contains processed trigger information (processed trigger information is divided into at least one trigger information set, i.e., at least one existing trajectory) and trigger information to be processed, each trigger information to be processed can be placed into a separate trigger information set based on the similarity between the trigger position corresponding to the trigger information to be processed and the trigger positions corresponding to the trigger information in each trigger information set. If there is any trigger information not placed in the set, the aforementioned clustering operation can be performed on all trigger information to obtain multiple trigger information sets again. Alternatively, existing trigger information sets can be disregarded, and the aforementioned clustering operation can be performed directly on all trigger information to obtain multiple trigger information sets. The obtained multiple trigger information sets can correspond to multiple trajectories. After obtaining multiple trajectories, the server can also record the trigger information contained in each trajectory within each trajectory.

[0034] Step S204: Based on the trajectory characteristics of each trajectory among the multiple trajectories, determine at least one trajectory group, wherein each trajectory group contains at least one trajectory among the multiple trajectories.

[0035] In this embodiment, based on multiple trajectories, a trajectory matching algorithm can be used to identify trajectories belonging to the same vehicle, so as to combine them into a vehicle. After obtaining multiple trajectories, the server can process the trigger information in each trajectory to obtain the trajectory features of each trajectory. The aforementioned trajectory features may include one or more features related to the trigger information, time features related to the time corresponding to the trigger information, spatial features related to the trigger location corresponding to the trigger information, features related to the number of trigger information items, or other features (such as features related to the pressure waveform obtained from the trigger, etc.). This embodiment does not limit these features.

[0036] The server can obtain different trajectory features in different ways. For example, the server can call different program modules to calculate different trajectory features. These trajectory features can be trajectory-level information, including but not limited to at least one of the following: trajectory position, trajectory width, start and end times, trajectory speed, etc. The sensor-level information and the trajectory-level information can be linked by trajectory matching algorithms such as trajectory clustering algorithms; this embodiment does not limit this.

[0037] After obtaining the trajectory features of each trajectory, the server can match multiple trajectories based on these features to determine at least one trajectory group. Each trajectory group can contain one or more matched trajectories; for example, a trajectory group can contain 1, 2, or 3 trajectories. During trajectory matching, the server can determine one or more trajectories that match the trajectory features of each trajectory based on its temporal and spatial features. Here, a trajectory matching a given trajectory can be the same trajectory itself. Whether trajectory features match can be determined based on the difference between trajectory features. For example, the server can determine the feature difference between the trajectory features of one trajectory and the trajectory features of another trajectory among multiple trajectories. If the feature difference is within a preset range, the two trajectories are considered to match and can be placed into a trajectory group containing at least two trajectories. A trajectory can match one or more trajectories; therefore, a single trajectory can belong to multiple trajectory groups.

[0038] Optionally, when obtaining at least one trajectory group, if overlapping trajectories exist, there may be unreasonable matching results or mismatch results. Other information can be used to determine the confidence level of trajectories in the trajectory group belonging to the same vehicle, and trajectory groups with excessively low confidence levels can be removed to obtain an updated at least one trajectory group. This embodiment does not impose limitations on this.

[0039] Step S206: Perform vehicle assignment processing based on at least one trajectory group to obtain at least one vehicle, wherein at least one trajectory group corresponds one-to-one with at least one vehicle.

[0040] After obtaining at least one track group, the server can perform vehicle allocation for each track group, obtaining at least one vehicle corresponding to each track group. If at least one existing vehicle was obtained during the previous vehicle allocation operation, the server can determine whether a track group belongs to an existing vehicle. If so, the existing vehicle is updated; otherwise, a new vehicle is created. If no existing vehicle exists, a new vehicle can be created for each track group, thus obtaining at least one vehicle.

[0041] For each of at least one vehicle, the vehicle level information that can be calculated may include, but is not limited to, at least one of the following: driving direction, lane, speed, number of axles, axle load, axle spacing, etc. Here, the vehicle level information and the aforementioned trajectory level information can be linked by a trajectory matching algorithm. Optionally, for each vehicle, its vehicle level information can also be calculated only when the vehicle is a vehicle waiting to exit. This embodiment does not limit this.

[0042] Optionally, when a vehicle among at least one of the vehicles meets the departure conditions, the vehicle can be charged based on its vehicle level information. The departure conditions may include at least one of the following: the rear coil is off; a three-axle coupling is present in the vehicle; or a following vehicle is detected. This embodiment does not impose any limitations on these conditions.

[0043] Through steps S202 to S206 above, when the execution conditions are detected to be met, multiple trajectories are determined according to the trigger position corresponding to each trigger information in the trigger information group, wherein each trigger information is the trigger information of the weighing sensor in the weighing area being triggered; at least one trajectory group is determined according to the trajectory characteristics of each trajectory in the multiple trajectories, wherein each trajectory group in the at least one trajectory group contains at least one trajectory in the multiple trajectories; vehicle allocation processing is performed according to the at least one trajectory group to obtain at least one vehicle, wherein the at least one trajectory group corresponds one-to-one with at least one vehicle, solving the problem of high computational resource consumption in vehicle allocation methods in related technologies, and reducing the computational resource consumption of vehicle allocation.

[0044] In an exemplary embodiment, the execution conditions include at least one of the following: obtaining a vehicle allocation signal emitted by the vehicle allocation sensor, the number of pending trigger information reaching a target number threshold, and the pending trigger information being trigger information to be placed into an existing trajectory.

[0045] In this embodiment, vehicle allocation processing can be performed based on the vehicle allocation signal emitted by the vehicle allocation sensor. That is, the execution condition may include: acquiring the vehicle allocation signal emitted by the vehicle allocation sensor. For the vehicle allocation sensor, it can determine whether a vehicle has entered or left the weighing area based on the information it detects. It can be a coil sensor, such as a ground inductive coil.

[0046] Taking a coil sensor as an example, the coil sensor can be installed on the upper and lower sides of the weighing area (i.e., the entrance and exit positions). When a vehicle enters the weighing area, the coil sensor lights up; when a vehicle leaves the weighing area, the coil sensor turns off. At this time, the coil sensor can send a vehicle separation signal to separate the currently weighing vehicle and subsequent vehicles for billing purposes.

[0047] In this embodiment, vehicle allocation can also be performed based on the number of trigger messages detected by the weighing sensor. Specifically, the execution conditions may include: the number of trigger messages to be processed reaching a target threshold, and the trigger messages to be processed being those to be placed into an existing track (which can be empty). The information to be processed here is similar to that in the previous embodiments and will not be elaborated upon further.

[0048] The server can determine the number of trigger messages to be processed each time it receives a trigger message from the weighing sensor. If the target number threshold is not reached, no vehicle allocation is performed, and only the received trigger messages are stored. If the target number threshold is reached, vehicle allocation can be performed on the unprocessed weighing information or a combination of unprocessed and processed weighing information.

[0049] For example, as a vehicle passes through the weighing area, the sensor array comes into contact with the wheels and is triggered successively. Each trigger event forms a record (i.e., trigger information), containing characteristic information of the signal during this triggering process, such as position. As the number of trigger events increases, vehicle segmentation processing is performed when the logical execution conditions are met. The logical execution conditions here may be that the number of triggers of sensors that have not been clustered since the last processing reaches a set threshold, or that the vehicle segmentation sensor (i.e., the vehicle segmentation sensor) provides a vehicle segmentation signal, or other constraints determined according to actual needs.

[0050] This embodiment improves the rationality of vehicle allocation operations by performing vehicle allocation processing based on the number of vehicle allocation signals or pending trigger information emitted by the vehicle allocation sensor.

[0051] In one exemplary embodiment, determining at least one group of trajectories based on the trajectory characteristics of each of the multiple trajectories includes:

[0052] S11, obtain multiple pending trigger information, wherein each pending trigger information is a trigger information to be placed into multiple existing trajectories, and the trigger information group includes multiple pending trigger information and trigger information in multiple existing trajectories;

[0053] S12, based on the trigger position corresponding to each pending trigger information, match each pending trigger information with multiple existing trajectories;

[0054] S13, if each pending trigger information matches a corresponding existing trajectory, obtain the updated multiple existing trajectories and features, wherein the updated multiple existing trajectories are multiple trajectories.

[0055] When determining trajectory groups based on the trajectory characteristics of each trajectory, if clustering and other processing are performed on all weighing trigger information each time, all weighing trigger information will be reprocessed even if there is no new trigger information or no new trajectory, which will result in a waste of computing resources.

[0056] In this embodiment, the server can first obtain trigger information to be processed, resulting in multiple trigger information sets. If existing tracks exist, it can first determine whether all the trigger information to be processed can be placed into an existing track. If not, or if no existing track exists, then all weighing information is clustered. Here, trigger information to be processed refers to trigger information to be placed into multiple existing tracks. The aforementioned trigger information group includes multiple trigger information sets to be processed and trigger information from each of the multiple existing tracks.

[0057] For each pending trigger information, the server can match the pending trigger information with existing trajectories. This matching operation can be a matching operation between the trigger location corresponding to the pending trigger information and the trajectory features of an existing trajectory. For example, it can determine whether the trigger location corresponding to the pending trigger information is within the trajectory range of an existing trajectory; if so, the two are considered a match; otherwise, they are considered a mismatch.

[0058] If each pending trigger information can be matched with a corresponding existing trajectory, these pending trigger information can be used to update the corresponding existing trajectory. For example, update the trigger information contained in the existing trajectory, update the trajectory features of the existing trajectory, etc. The above multiple trajectories are multiple updated existing trajectories.

[0059] In this embodiment, the trigger information to be processed is matched with the existing trajectory, so that the vehicle trajectory in this vehicle allocation process can be obtained through trajectory update, which can improve the efficiency of vehicle allocation and reduce the waste of computing resources.

[0060] In one exemplary embodiment, determining at least one group of trajectories based on the trajectory characteristics of each of the multiple trajectories further includes:

[0061] S21, if there are pending trigger information messages that do not match the existing trajectory, or if there is no existing trajectory, perform a clustering operation on all trigger information messages in the trigger information group to obtain multiple trajectories, where each trajectory in the multiple trajectories corresponds to a first cluster obtained by clustering.

[0062] In this embodiment, if there are pending trigger messages among multiple pending trigger messages that do not match a corresponding existing trajectory, or if there is currently no existing trajectory, in order to improve the rationality of vehicle trajectory determination and avoid vehicle assignment errors caused by unreasonable trajectory determination, the server can perform a clustering operation on all trigger messages. Here, all trigger messages are those that have been acquired but have not yet been processed for vehicle dispatch, that is, all trigger messages in the trigger message group.

[0063] The server can perform clustering operations on all trigger information in the trigger information group to obtain multiple clusters. Each cluster can correspond to a trajectory, resulting in multiple trajectories. The trajectory clustering algorithm on which the above clustering operation is based can be of various types, such as the DBSCAN density clustering algorithm, other density-based clustering algorithms such as OPTICS, or adaptive algorithms optimized based on such algorithms. This embodiment does not limit the specific algorithms used.

[0064] For example, all trigger records are clustered based on the trigger location. The trajectory clustering algorithm used is the DBSCAN density clustering algorithm. This algorithm can group sensor trigger events (i.e., trigger information) with similar trigger locations into one category, and each category is called a trajectory. Each trajectory is obtained by the triggering of a single tire on one side of the same vehicle.

[0065] In this embodiment, when there are trigger information messages in the pending trigger information that do not match existing trajectories, the rationality of vehicle trajectory determination can be improved by performing a clustering operation on all trigger information messages.

[0066] In one exemplary embodiment, determining at least one group of trajectories based on the trajectory characteristics of each of the multiple trajectories includes:

[0067] S31, based on the first trajectory features of each trajectory, determine the first trajectory among multiple trajectories, wherein the first trajectory is the trajectory corresponding to a vehicle with two wheels, each first trajectory is a first trajectory group, and the first trajectory features include at least one of the following: trajectory pressure maximum value, trajectory trigger number, trajectory trigger width;

[0068] S32, perform a double traversal of the other trajectories along the first direction according to the second trajectory features to obtain a second trajectory group, wherein the other trajectories are the other trajectories besides the first trajectory among multiple trajectories, and the second trajectory features include at least one of the following: trajectory width, trajectory position, trajectory direction, trajectory speed, trajectory start and end time, and at least one trajectory group includes all the first trajectory groups and all the second trajectory groups, and the first direction is the direction from one end of the trajectory to the other end of the trajectory.

[0069] In this embodiment, after obtaining multiple trajectories, the server can first determine, based on the first trajectory feature of each trajectory, the trajectory triggered by the wheels of a two-wheeled vehicle (e.g., a motorcycle, an electric bicycle). The aforementioned first trajectory feature may include one or more trajectory information, including but not limited to at least one of the following: maximum trajectory pressure, number of trajectory triggers, and trajectory trigger width.

[0070] Among multiple trajectories, if the first trajectory of the first trajectory has the characteristics of the trajectory of a two-wheeled vehicle, such as the trajectory pressure maximum value being less than or equal to the pressure threshold, the trajectory trigger count being less than or equal to the trigger count threshold, and the trajectory trigger width being less than or equal to the trigger width threshold, then this part of the trajectory can be filtered out and directly determined as a trajectory group, namely, the first trajectory group.

[0071] For example, the width, speed, start / end time, and center position of each trajectory within the current cross-section can be calculated. Based on the maximum pressure, trigger count, and trigger width of each trajectory, it can be determined whether the current trajectory is triggered by a motorcycle. If so, the current trajectory matching scheme is recorded.

[0072] For trajectories other than the first one among multiple trajectories, trajectory matching algorithms can be used to match them. A trajectory matching algorithm involves evaluating multiple given trajectories based on dimensions such as trajectory width, trajectory spacing, start and end time range, and trajectory speed, and selecting the trajectory belonging to the same vehicle based on spatial location and rationality. A vehicle under normal driving conditions has two trajectories, while a vehicle driving abnormally, such as swerving in an S-shape or at an angle, may have one, two, or three trajectories.

[0073] The server can perform a double traversal of other trajectories based on the second trajectory features to determine the relationships between the second trajectory features and identify the trajectory that meets the matching conditions, i.e., the second trajectory. The aforementioned second trajectory features may include, but are not limited to, at least one of the following: trajectory width, trajectory position, trajectory direction, trajectory speed, and trajectory start and end time.

[0074] During the double traversal of the trajectory, starting from the first end (e.g., the left end) of another trajectory based on its estimated position, and following a first direction (e.g., from left to right) from the first end to the second end, it is determined whether the second trajectory features of the current trajectory and its subsequent trajectories (based on the direction before and after the target direction) satisfy the trajectory matching condition. If they do, the current trajectory and the matching trajectory are placed into a trajectory group, resulting in a second trajectory group. After performing the double traversal, multiple second trajectory groups can be obtained. At least one of the aforementioned trajectory groups may include a first trajectory group and a second trajectory group.

[0075] There can be various trajectory matching conditions. For example, they can be: the width difference of the trajectory width is within a preset width difference range, the position difference of the trajectory position is within a preset position difference range, the trajectory directions are consistent, the velocity value of the trajectory speed is within a preset velocity difference range, the time difference of the start and end time of the trajectory trigger is within a preset time difference range, or other trajectory matching conditions. This embodiment does not limit these conditions.

[0076] For example, suppose there are N trajectories in the current spatiotemporal cross-section, numbered from 1 to N from left to right. For any vehicle, suppose the leftmost trajectory triggered by the vehicle is numbered i, and the rightmost trajectory is numbered j (j>=i). A double traversal is performed on either the leftmost or rightmost trajectory of the vehicle, and the vehicle's suitability is determined based on trajectory spacing, width information, and trajectory time overlap. When performing a double traversal on i and j, among all possibilities, a reasonable trajectory matching scheme must satisfy the following conditions:

[0077] 1) The spacing between trajectories i and j is reasonable;

[0078] 2) The velocities of trajectories i and j are in the same direction;

[0079] 3) Trajectories i and j overlap in time;

[0080] The combination of (i, j) that satisfies the above conditions can be identified as a trajectory group.

[0081] If the conditions are met and there is no overlap with the existing scheme, record the current scheme (the existing trajectory group). If the existing scheme is included by the latest scheme, update the existing scheme. If the latest scheme is already included by the existing scheme, do not record the current scheme.

[0082] In this embodiment, the trajectory triggered by a vehicle with two wheels is first identified based on the first trajectory feature, and the trajectory matching the second trajectory feature is determined by a double traversal method, which can improve the accuracy and rationality of trajectory matching.

[0083] In one exemplary embodiment, determining at least one group of trajectories based on the trajectory characteristics of each of the multiple trajectories includes:

[0084] S41, perform a double traversal of multiple trajectories along the second direction according to the second trajectory features to obtain at least one trajectory group, wherein the second trajectory features include at least one of the following: trajectory width, trajectory position, trajectory direction, trajectory speed, trajectory start and end time, and the second direction is the direction from one end of the trajectory to the other end of the trajectory.

[0085] In this embodiment, for multiple trajectories, direct matching between trajectories can also be performed. The server can perform a double traversal of multiple trajectories along the second direction according to the second trajectory features to obtain at least one trajectory group. Here, the method of performing a double traversal of multiple trajectories is similar to the method of performing a double traversal of other trajectories in the previous embodiment. The second direction can be the same as the first direction in the previous embodiment, or it can be the opposite direction, which will not be elaborated here.

[0086] This embodiment improves the completeness of trajectory matching by performing double traversal along a specific direction on multiple trajectories, thereby enhancing the accuracy of vehicle identification.

[0087] In one exemplary embodiment, multiple trajectories are double-traversed along a second direction according to the second trajectory features to obtain at least one group of trajectories, including:

[0088] S51, Based on the trajectory positions of the second trajectory and the third trajectory, determine the horizontal spacing between the second trajectory and the third trajectory, where the second trajectory and the third trajectory are the currently traversed trajectories;

[0089] S52, Based on the start and end times of the second trajectory and the start and end times of the third trajectory, determine the overlap time of the second trajectory and the third trajectory;

[0090] S53, when the horizontal spacing is within the first spacing range, the trajectory width of the second trajectory and the trajectory width of the third trajectory are both within the first width range, and the overlap time is greater than or equal to the first time threshold, the second trajectory and the third trajectory are determined as the first sub-trajectory group;

[0091] S54, if the second trajectory and the third trajectory are the same trajectory and the trajectory width of the second trajectory is within the range of the second width, the second trajectory is determined as the second sub-trajectory group;

[0092] S55, if the trajectory width of the second trajectory and the trajectory width of the third trajectory are both within the range of the third width, the second trajectory and the third trajectory are determined as the third sub-trajectory group;

[0093] S56, if the trajectory widths of the second trajectory and the third trajectory are both within the range of the fourth width and the lateral spacing is within the range of the second spacing, the second trajectory and the third trajectory are determined as the fourth sub-trajectory group.

[0094] In this embodiment, the vehicle trajectories triggered by different vehicles are correlated in different dimensions. Therefore, trajectory matching can be performed through different combinations of the second trajectory features. When performing a double traversal on multiple trajectories, the currently traversed trajectories are the second trajectory and the third trajectory (the second trajectory and the third trajectory can be the same trajectory or different trajectories). The matching of the two trajectories can be determined based on different combinations of the second trajectory features.

[0095] When performing trajectory matching, if there are one or more trajectories in the current section, based on features such as trajectory spacing, trajectory width, and trajectory speed, it can not only complete the trajectory matching of regular vehicles, but also identify special vehicle types (such as tricycles / motorcycles) and abnormal driving modes (such as driving in an S-shape or diagonally).

[0096] The server can first determine the lateral spacing between the second and third trajectories based on their positions, and then determine the overlap time between them based on the start and end times of the second and third trajectories.

[0097] For a normally moving vehicle, its lateral spacing is within a certain spacing range (i.e., the first spacing range), its trajectory width is within a certain width range (i.e., the first width range), and its overlap time (or overlap ratio) is greater than or equal to a certain time threshold (i.e., the first time threshold, or the first ratio threshold). If the lateral spacing, trajectory width, and trajectory overlap time of the second and third trajectories meet the above conditions, the second and third trajectories can be determined as the first sub-trajectory group, that is, the first sub-trajectory group contains two trajectories triggered by a normally moving vehicle.

[0098] For vehicles exhibiting abnormal driving patterns (or abnormal driving), such as S-curves or diagonal driving, their two tracks may overlap, resulting in a relatively wide track width. If the second and third tracks are the same track (traversing to the same track) and the track width falls within the second width range, then this track is directly defined as a track group, i.e., the second sub-track group. The second sub-track group is a track triggered by a vehicle exhibiting abnormal driving.

[0099] For vehicles in abnormal driving modes (e.g., S / diagonal), their two tracks may not overlap, but each track triggered by the vehicle will be wider than the track width triggered by a normally driving vehicle. If the track widths of both the second and third tracks are within the third width range, then the second and third tracks can be identified as a third sub-track group, that is, the third sub-track group contains the two tracks triggered by a vehicle in abnormal driving mode.

[0100] For vehicles of a specific type (e.g., tricycles), the lateral spacing between the two tracks is within a certain range (i.e., the second spacing range), and the track width is within a certain width range (i.e., the fourth width range). If the lateral spacing, track width, and overlap time of the second and third tracks meet the above conditions, the second and third tracks can be identified as a fourth sub-track group. That is, the fourth sub-track group contains two tracks triggered by a vehicle of a specific type.

[0101] Optionally, for vehicles of a specific type, if there are more than two trajectories, there can be multiple trajectory groups corresponding to that vehicle. The server can also match trajectory groups containing overlapping trajectories to determine whether they are trajectory groups triggered by the same vehicle, and perform a merging operation on trajectory groups triggered by the same vehicle to obtain trajectory groups containing multiple trajectories.

[0102] This embodiment improves the accuracy of trajectory group identification by identifying normally driving vehicles, abnormally driving vehicles, and special vehicle types based on trajectory width, lateral spacing of the trajectory, and trajectory overlap time.

[0103] In one exemplary embodiment, after determining at least one group of trajectories based on the trajectory characteristics of each of the multiple trajectories, the method further includes:

[0104] S61, Remove the abnormal trajectory group from at least one trajectory group to obtain at least one updated trajectory group.

[0105] In this embodiment, after obtaining at least one trajectory group (e.g., after completing a double traversal), there may be overlapping trajectory patterns. Therefore, the obtained at least one trajectory group is not the final output and deduplication processing needs to be performed. For example, abnormal trajectory groups can be removed from the at least one trajectory group to obtain an updated at least one trajectory group. Here, abnormal trajectory groups can be mismatched trajectory groups. There can be one or more ways to identify abnormal trajectory groups. For example, density clustering can be performed based on the trajectory center position to identify and delete erroneous matches caused by parallel vehicles within each cluster, thereby obtaining an updated at least one trajectory group.

[0106] When performing density clustering based on the center position of a trajectory, multiple trajectories can be clustered using the center position of each trajectory as the core object, resulting in multiple secondary clusters. Each secondary cluster can contain one or more trajectories. Based on the secondary clusters in which the trajectories within each trajectory group belong, abnormal trajectory groups can be identified. For example, if the trajectories in a trajectory group belong to different secondary clusters or are located within their own secondary cluster, then that trajectory group can be considered an abnormal trajectory group. Abnormal trajectory groups can be removed from at least one trajectory group, resulting in at least one updated trajectory group.

[0107] Optionally, for trajectory matching results with appropriate spacing but belonging to parallel vehicles on both sides, the trajectory deduplication method described above may not be effective. Therefore, if duplicate trajectories still exist, a scoring system can be used to identify and remove unreasonable schemes based on speed and time overlap. This embodiment does not impose any limitations on this.

[0108] Optionally, the server can also identify a first sub-track group with overlapping trajectories from at least one track group. Then, it iterates through each track in a predetermined direction, and the track encountered becomes the current track. If the current track is an overlapping track, it is skipped, and the current track is searched again. If the current track is not an overlapping track, the matching track in the track group to which the current track belongs is determined. If the matching track is an overlapping track, other track groups to which the matching track in the first sub-track group belongs are removed, and the current track is searched again until there are no overlapping tracks in the first sub-track group, or the first sub-track group remains unchanged after one round of traversal. The result after traversal can be at least one updated track group.

[0109] Optionally, for vehicles of a specific model triggering multiple trajectories (e.g., more than two), these trajectories may be assigned to multiple trajectory groups. The server can also identify a second sub-trajectory group with overlapping trajectories from at least one trajectory group, and perform trajectory combination and operation on this second sub-trajectory group. This can be done by iterating through each trajectory group in a predetermined direction, with the trajectories being the current trajectory group. Based on the trajectory characteristics of the multiple trajectories contained in the current trajectory group and the trajectory group with overlapping trajectories, it is determined whether the two trajectories were triggered by the same vehicle. If so, the trajectory groups are merged, and one overlapping trajectory is retained; otherwise, the next trajectory group is traversed until the second sub-trajectory group has no overlapping trajectories, or the second sub-trajectory group remains unchanged after one round of traversal. The result after traversal can be at least one updated trajectory group.

[0110] After combining and operating the trajectories, the aforementioned method for identifying incorrectly constructed vehicles can also be used to identify erroneous trajectory groups. This embodiment does not limit this approach.

[0111] In this embodiment, by performing clustering operations on the center position of the trajectory, abnormal trajectory groups caused by parallel vehicles and trajectory overlap can be excluded, which can improve the accuracy of vehicle allocation and reduce vehicle dispatch anomalies caused by incorrect matching or trajectory overlap.

[0112] In one exemplary embodiment, the above method further includes:

[0113] S71, when the vehicle meets the departure conditions, determines the vehicle information based on the correspondence between the vehicle and the trajectory, and between the trajectory and the sensor trigger information.

[0114] In this embodiment, when a vehicle meets the departure conditions, a vehicle allocation signal can be given based on the correspondence between the vehicle and the trajectory, and the correspondence between the trajectory and sensor trigger information. Based on the allocation signal, a vehicle allocation operation can be performed. For example, based on the correspondence between the vehicle and the trajectory, the trajectory (or trajectory group) corresponding to the vehicle is determined. Then, based on the correspondence between the trajectory and the sensor trigger information, the sensor trigger information contained in the trajectory corresponding to the vehicle is determined; that is, the sensor trigger information belonging to the vehicle is determined, thereby determining the vehicle information.

[0115] In this embodiment, when a vehicle is dispatched, a vehicle dispatch signal is given based on the correspondence between the vehicle and the trajectory, and between the trajectory and the sensor trigger information, which can improve the accuracy of vehicle dispatch.

[0116] The vehicle segmentation method in this application embodiment will be explained below with reference to optional examples. In this optional example, a vehicle trajectory clustering algorithm based on trigger location is used to determine the vehicle trajectory, and a vehicle matching algorithm based on trajectory features is used for vehicle matching.

[0117] In related technologies, most vehicle sorting algorithms are real-time processes, meaning the logic must be executed every time a sensor triggers. In most cases, dynamic weighing systems do not have high timeliness requirements, so real-time processing consumes significantly more computational resources. Furthermore, real-time processing requires making decisions with potentially insufficient information, leading to a relatively high error rate. Even with error correction mechanisms, it still places a significant burden on computational resources.

[0118] In this optional example, a non-real-time processing mechanism is used. When making decisions, the sensor trigger information is richer than that of a real-time system, the probability of error is lower, and the consumption of computing resources is also lower.

[0119] Furthermore, most vehicle allocation algorithms in related technologies are often applicable to specific sensor layouts or sensor types. For example, in a certain sensor arrangement, a certain characteristic of the triggering order of the sensor array is used to assist decision-making, or the logic itself uses signal characteristics that can only be provided by a specific sensor. This results in poor applicability of the vehicle allocation scheme.

[0120] In this optional example, compared to other solutions, it is applicable to any sensor type and array layout (provided it can achieve full lane coverage). That is, it is applicable to any type of load cell or load cell array, such as single-row / multi-row multi-channel narrow strips, laterally spaced stress / strain sensor arrays, and other types of sensor arrays that can provide trigger positions perpendicular to the driving direction and have sufficient spatial resolution. Due to this characteristic, the vehicle segmentation method in this optional example is applicable to different sensor subsystems in dynamic weighing scenarios involving multi-sensor fusion.

[0121] The dynamic weighing system in this optional example may include the following components: a weighing sensor array; vehicle segmentation sensors (i.e., vehicle identification sensors); a data transmission system; and an industrial control computer. Based on the above dynamic weighing system (or other dynamic weighing systems), this optional example provides a vehicle identification scheme based on trajectory clustering using a weighing sensor array. By utilizing trajectory clustering and trajectory matching algorithms, trajectories belonging to the same vehicle can be selected based on the rationality of spatial location, thus achieving accurate vehicle identification.

[0122] Combination Figure 3 As shown, the vehicle allocation method in this optional example may include the following steps:

[0123] Step S302: Receive the waveform signal from the weighing sensor.

[0124] Step S304: Calculate the characteristic attributes triggered by the weighing sensor (e.g., the information at the aforementioned sensor level).

[0125] Step S306: Determine whether to execute the vehicle allocation logic (the basis for determination is similar to that in the previous embodiment). If yes, execute step S308; otherwise, execute step S302.

[0126] Step S308: Determine whether all weighing sensors can be placed in the existing trajectory. If yes, proceed to step S312; otherwise, proceed to step S310.

[0127] Step S310: Re-cluster the weighing sensors.

[0128] The weighing sensors corresponding to the position information in all the trigger information are re-clustered to obtain new trajectories.

[0129] Step S312: Update trajectory features (e.g., the information of the aforementioned trajectory level).

[0130] If all the triggering information can be placed into the existing trajectory, then the existing trajectory is used as the current trajectory, and the trajectory features are updated; otherwise, the re-clustered trajectory is used as the current trajectory, and the trajectory features are updated.

[0131] Step S314: Determine whether the trajectory matching algorithm can match new vehicles. If yes, proceed to step S316; otherwise, proceed to step S318.

[0132] Step S316: Create a new car in the cache.

[0133] Step S318, update the existing vehicle.

[0134] Step S320: Determine whether the vehicle meets the departure conditions. If yes, proceed to step S322; otherwise, proceed to step S302.

[0135] Step S322: Calculate vehicle information such as axle speed and axle load, and then dispatch the vehicle.

[0136] When a vehicle meets the dispatch conditions (e.g., the rear coil is off, there is a 3-axle connection at the end of the vehicle, the following vehicle is identified and the cutting is completed), the vehicle information is checked, the number of axles and axle weight are calculated, the vehicle model is determined, and the vehicle is dispatched.

[0137] When performing trajectory matching, such as Figure 4 As shown, combined with Figure 4 As shown, the vehicle trajectory matching method in this optional example may include the following steps:

[0138] Step S402: Traverse each trajectory within the cross section and calculate the information of each trajectory, including trajectory width, initiation time, number of triggers, maximum pressure, and direction / speed of travel.

[0139] Step S404: Determine if the maximum or minimum value of the trajectory pressure, trigger width, or number of triggers meets the set conditions. If so, determine that the trajectory is triggered by a special type of vehicle such as a motorcycle, and proceed to step S416. Otherwise, proceed to step S406.

[0140] The leftmost and rightmost trajectories (i, j) of the assumed vehicle are double-traversed. The rationality of the vehicle is judged based on the trajectory spacing and width information. If the conditions are met and there is no overlap with the existing scheme, the data is recorded in the alternative scheme. For the i-th and j-th trajectories traversed, trajectory matching can be performed through steps S406 to S414.

[0141] Step S406: Calculate the lateral interval, time overlap, or maximum width of trajectories i and j.

[0142] Step S408: Determine whether the spacing, width, and time overlap of trajectories i and j meet the set conditions. If yes, proceed to step S416; otherwise, proceed to step S410. This step can determine whether the vehicle is driving normally.

[0143] Step S410: Determine if trajectories i and j overlap and the overlap width meets the set conditions. If yes, proceed to step S416; otherwise, proceed to step S412. This step can determine if the vehicle is driving abnormally, such as if the vehicle is driving in an S-shape or diagonally.

[0144] Step S412: Determine whether the widths of trajectory i and j meet the set conditions. If yes, proceed to step S416; otherwise, proceed to step S414. This step can determine if the vehicle is driving abnormally, such as if the vehicle is driving in an S-shape or diagonally.

[0145] Step S414: Determine whether the width and spacing of trajectory i and j meet the set conditions. If so, proceed to step S416. The direction of travel can determine whether the vehicle is a tricycle.

[0146] Step S416: Compare with existing alternatives and update existing records based on the inclusion / being-inclusion relationship of the starting trajectory.

[0147] Step S418: The center positions of the trajectories are clustered according to density, and divided into N clusters.

[0148] Step S420: Iterate through each candidate matching scheme and eliminate schemes that belong to different clusters or are within the same cluster.

[0149] After completing the double traversal, density clustering is performed based on the trajectory center position to identify and remove erroneous matches caused by parallel vehicles within each cluster.

[0150] Step S422: Determine whether there are still overlapping trajectories. If yes, proceed to step S424; otherwise, proceed to step S426.

[0151] Step S424: Score the combinations of overlapping trajectories from the perspective of trajectory velocity and time overlap, and delete the combinations with lower scores.

[0152] Step S426, end, output matching results.

[0153] This optional example demonstrates how location-based trajectory clustering and trajectory matching based on trajectory features can reduce the probability of vehicle assignment errors, while also reducing the consumption of computing resources. It is applicable to any sensor type and array layout.

[0154] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0155] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. 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 software product. This computer software product is stored in a storage medium (such as ROM (Read-Only Memory) / RAM (Random Access Memory), magnetic disk, optical disk), and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0156] According to another aspect of the embodiments of this application, a vehicle separation device for implementing the above-described vehicle separation method is also provided. Figure 5 This is a structural block diagram of an optional vehicle separation device according to an embodiment of this application, such as... Figure 5 As shown, the device may include:

[0157] The first determining unit 502 is used to determine multiple trajectories based on the trigger position corresponding to each trigger information in the trigger information group when the execution conditions are detected to be met. Each trigger information is the trigger information of the weighing sensor in the weighing area being triggered.

[0158] The second determining unit 504 is connected to the first determining unit 502 and is used to determine at least one trajectory group based on the trajectory characteristics of each trajectory among multiple trajectories, wherein each trajectory group in the at least one trajectory group contains at least one trajectory among multiple trajectories.

[0159] The vehicle allocation unit 506 is connected to the second determination unit 504 and is used to perform vehicle allocation processing according to at least one trajectory group to obtain at least one vehicle, wherein at least one trajectory group corresponds one-to-one with at least one vehicle.

[0160] It should be noted that the first determining unit 502 in this embodiment can be used to execute the above step S202, the second determining unit 504 in this embodiment can be used to execute the above step S204, and the vehicle separation unit 506 in this embodiment can be used to execute the above step S206.

[0161] Through the above modules, when the execution conditions are met, multiple trajectories are determined based on the trigger position corresponding to each trigger information in the trigger information group. Each trigger information is the trigger information for the weighing sensor within the weighing area. Based on the trajectory characteristics of each trajectory, at least one trajectory group is determined, where each trajectory group contains at least one trajectory from the multiple trajectories. Vehicle allocation is then performed based on the at least one trajectory group to obtain at least one vehicle, where each trajectory group corresponds one-to-one with at least one vehicle. This application solves the problem of high computational resource consumption in vehicle allocation methods in related technologies, achieving the technical effect of saving vehicle allocation resources.

[0162] In an exemplary embodiment, the execution conditions include at least one of the following: obtaining a vehicle allocation signal emitted by the vehicle allocation sensor, the number of pending trigger information reaching a target number threshold, and the pending trigger information being trigger information to be placed into an existing trajectory.

[0163] In one exemplary embodiment, the second determining unit includes:

[0164] The first acquisition module is used to acquire multiple pending trigger information, wherein each pending trigger information is a trigger information to be placed into multiple existing trajectories, and the trigger information group includes multiple pending trigger information and trigger information in multiple existing trajectories;

[0165] The matching module is used to match each pending trigger information with multiple existing trajectories based on the trigger position corresponding to each pending trigger information;

[0166] If each pending trigger information matches a corresponding existing trajectory, obtain the updated multiple existing trajectories and features, where the updated multiple existing trajectories are multiple trajectories.

[0167] In one exemplary embodiment, the second determining unit further includes:

[0168] The execution module is used to perform clustering operations on all trigger information in the trigger information group when there are trigger information that has not been matched with an existing trajectory among multiple trigger information to be processed, or when there is no existing trajectory at present, to obtain multiple trajectories. Each of the multiple trajectories corresponds to a first cluster obtained by clustering.

[0169] In one exemplary embodiment, the second determining unit includes:

[0170] The second determining module is used to determine the first trajectory among multiple trajectories based on the first trajectory features of each trajectory. The first trajectory is the trajectory corresponding to a vehicle with two wheels. Each first trajectory is a first trajectory group. The first trajectory features include at least one of the following: maximum trajectory pressure, number of trajectory triggers, and trajectory trigger width.

[0171] The first traversal module is used to perform a double traversal of other trajectories along the first direction according to the second trajectory features to obtain a second trajectory group. The other trajectories are the trajectories other than the first trajectory among multiple trajectories. The second trajectory features include at least one of the following: trajectory width, trajectory position, trajectory direction, trajectory speed, trajectory start and end time. At least one trajectory group contains all the first trajectory groups and all the second trajectory groups. The first direction is the direction from one end of the other trajectory to the other end of the other trajectory.

[0172] In one exemplary embodiment, the second determining unit includes:

[0173] The second traversal module is used to perform a double traversal of multiple trajectories along a second direction according to the second trajectory features to obtain at least one trajectory group. The second trajectory features include at least one of the following: trajectory width, trajectory position, trajectory direction, trajectory speed, trajectory start and end time, and the second direction is the direction from one end of the trajectory to the other end of the trajectory.

[0174] In one exemplary embodiment, the second traversal module includes:

[0175] The first determining submodule is used to determine the horizontal spacing between the second trajectory and the third trajectory based on the trajectory positions of the second trajectory and the third trajectory, wherein the second trajectory and the third trajectory are the currently traversed trajectories;

[0176] The second determining submodule is used to determine the overlap time of the second trajectory and the third trajectory based on the trajectory start and end time of the second trajectory and the trajectory start and end time of the third trajectory.

[0177] The third determining submodule is used to determine the second trajectory and the third trajectory as the first sub-trajectory group when the horizontal spacing is within the first spacing range, the trajectory width of the second trajectory and the trajectory width of the third trajectory are both within the first width range, and the overlap time is greater than or equal to the first time threshold.

[0178] The fourth determination submodule is used to determine the second trajectory as the second sub-trajectory group when the second trajectory and the third trajectory are the same trajectory and the trajectory width of the second trajectory is within the range of the second width.

[0179] The fifth determination submodule is used to determine the second trajectory and the third trajectory as a third sub-trajectory group when both the trajectory width of the second trajectory and the trajectory width of the third trajectory are within the range of the third width.

[0180] The sixth determining submodule is used to determine the second trajectory and the third trajectory as the fourth sub-trajectory group when the trajectory width of the second trajectory and the trajectory width of the third trajectory are both within the fourth width range and the lateral spacing is within the second spacing range.

[0181] In one exemplary embodiment, the above-described apparatus further includes:

[0182] A removal unit is used to remove abnormal trajectory groups from at least one trajectory group to obtain at least one updated trajectory group.

[0183] In one exemplary embodiment, the above-described apparatus further includes:

[0184] The triggering unit is used to give a vehicle assignment signal when the vehicle meets the departure conditions, based on the correspondence between the vehicle and the trajectory, and between the trajectory and the sensor triggering information.

[0185] It should be noted that the examples and application scenarios implemented by the above modules and corresponding steps are the same, but are not limited to the content disclosed in the above embodiments. It should also be noted that the above modules, as part of a device, can operate in environments such as... Figure 1 The hardware environment shown can be implemented through software or hardware, and the hardware environment includes the network environment.

[0186] According to another aspect of the embodiments of this application, a storage medium is also provided. Optionally, in this embodiment, the storage medium can be used to execute the program code of any of the vehicle separation methods described above in the embodiments of this application.

[0187] Optionally, in this embodiment, the storage medium may be located on at least one of the network devices in the network shown in the above embodiment.

[0188] Optionally, in this embodiment, the storage medium is configured to store program code for performing the following steps:

[0189] S1, when the execution conditions are met, multiple trajectories are determined according to the trigger position corresponding to each trigger information in the trigger information group, wherein each trigger information is the trigger information of the weighing sensor in the weighing area being triggered;

[0190] S2, based on the trajectory characteristics of each trajectory among the multiple trajectories, determine at least one trajectory group, wherein each trajectory group contains at least one trajectory from the multiple trajectories.

[0191] S3, perform vehicle sorting based on at least one trajectory group to obtain at least one vehicle, wherein at least one trajectory group corresponds one-to-one with at least one vehicle.

[0192] Optionally, specific examples in this embodiment can refer to the examples described in the above embodiments, and will not be repeated in this embodiment.

[0193] Optionally, in this embodiment, the storage medium may include, but is not limited to, various media capable of storing program code, such as USB flash drives, ROMs, RAMs, portable hard drives, magnetic disks, or optical disks.

[0194] According to another aspect of the embodiments of this application, an electronic device for implementing the above-described vehicle allocation method is also provided. The electronic device may be a server, a terminal, or a combination thereof.

[0195] Figure 6 This is a structural block diagram of an optional electronic device according to an embodiment of this application, such as... Figure 6 As shown, it includes a processor 602, a communication interface 604, a memory 606, and a communication bus 608. The processor 602, communication interface 604, and memory 606 communicate with each other via the communication bus 608.

[0196] Memory 606 is used to store computer programs;

[0197] When processor 602 executes a computer program stored in memory 606, it performs the following steps:

[0198] S1, when the execution conditions are met, multiple trajectories are determined according to the trigger position corresponding to each trigger information in the trigger information group, wherein each trigger information is the trigger information of the weighing sensor in the weighing area being triggered;

[0199] S2, based on the trajectory characteristics of each trajectory among the multiple trajectories, determine at least one trajectory group, wherein each trajectory group contains at least one trajectory from the multiple trajectories.

[0200] S3, perform vehicle sorting based on at least one trajectory group to obtain at least one vehicle, wherein at least one trajectory group corresponds one-to-one with at least one vehicle.

[0201] Optionally, the communication bus can be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. This communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 6 The symbol is represented by a single thick line, but this does not indicate that there is only one bus or one type of bus. The communication interface is used for communication between the aforementioned electronic device and other devices.

[0202] The memory may include RAM, or non-volatile memory, such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.

[0203] As an example, the memory 606 described above may include, but is not limited to, the first determining unit 502, the second determining unit 504, and the vehicle sharing unit 506 in the vehicle sharing device described above. Furthermore, it may include, but is not limited to, other module units in the vehicle sharing device described above, which will not be elaborated upon in this example.

[0204] The processors mentioned above can be general-purpose processors, including but not limited to: CPU (Central Processing Unit), NP (Network Processor), etc.; they can also be DSP (Digital Signal Processor), ASIC (Application Specific Integrated Circuit), FPGA (Field-Programmable Gate Array), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0205] Optionally, specific examples in this embodiment can refer to the examples described in the above embodiments, and will not be repeated here.

[0206] Those skilled in the art will understand that Figure 6 The structure shown is for illustrative purposes only. The device that implements the above vehicle allocation method can be a terminal device, such as a smartphone (e.g., Android phone, iOS phone), tablet computer, PDA, mobile Internet device (MID), PAD, etc. Figure 6This does not limit the structure of the aforementioned electronic device. For example, the electronic device may also include components that are more... Figure 6 The more or fewer components shown (such as network interfaces, display devices, etc.), or having the same Figure 6 The different configurations shown.

[0207] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing the hardware related to the terminal device. The program can be stored in a computer-readable storage medium, which may include: flash drive, ROM, RAM, disk or optical disk, etc.

[0208] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0209] If the integrated units in the above embodiments are implemented as software functional units and sold or used as independent products, they can be stored in the aforementioned computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause one or more computer devices (which may be personal computers, servers, or network devices, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application.

[0210] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method of separating vehicles, characterized by, Comprise: In the case of detecting that the execution condition is met, according to the trigger position corresponding to each trigger information of the trigger information group, a plurality of tracks are determined, wherein the trigger information is the trigger information of the weighing sensor in the weighing area; The execution condition includes at least one of the following: obtaining the vehicle separation sensor signal, the number of the to-be-processed trigger information reaches the target number threshold, and the to-be-processed trigger information is the trigger information to be put into the existing track; According to the track characteristics of each track in the plurality of tracks, at least one track group is determined, wherein each track group in the at least one track group comprises at least one track in the plurality of tracks, comprising: obtaining a plurality of to-be-processed trigger information, wherein each to-be-processed trigger information in the plurality of to-be-processed trigger information is to-be-processed trigger information to be put into a plurality of existing tracks, and the trigger information group comprises the plurality of to-be-processed trigger information and the trigger information in the plurality of existing tracks; According to the trigger position corresponding to each to-be-processed trigger information, each to-be-processed trigger information is matched with the plurality of existing tracks; In the case that each to-be-processed trigger information is matched to the corresponding existing track, the updated plurality of existing tracks and characteristics are obtained, wherein the updated plurality of existing tracks are the plurality of tracks; Remove the abnormal track group from the at least one track group to obtain the updated at least one track group; According to the at least one track group, at least one vehicle is obtained, wherein the at least one track group and the at least one vehicle correspond one by one; Wherein, the method further comprises: when the vehicle meets the vehicle output condition, according to the correspondence between the vehicle and the track, the track and the sensor trigger information, the vehicle separation signal of the vehicle is given.

2. The method of claim 1, wherein, According to the track characteristics of each track in the plurality of tracks, at least one track group is determined, further comprising: In the case that there is a to-be-processed trigger information that is not matched to the corresponding existing track in the plurality of to-be-processed trigger information, or there is no existing track, a clustering operation is performed on all trigger information in the trigger information group to obtain the plurality of tracks, wherein each track in the plurality of tracks corresponds to a first cluster obtained by clustering.

3. The method of claim 1, wherein, According to the track characteristics of each track in the plurality of tracks, at least one track group is determined, comprising: According to the first track characteristics of each track, a first track in the plurality of tracks is determined, wherein the first track is a track corresponding to a vehicle with two wheels, each first track is a first track group, and the first track characteristics include at least one of the following: track pressure maximum value, track trigger times, and track trigger width; The other trajectories are other trajectories in the plurality of trajectories except the first trajectory, the second trajectory feature comprises at least one of the following: trajectory width, trajectory position, trajectory direction, trajectory speed, trajectory start and end time, the first direction is a direction from one end of the other trajectories to the other end of the other trajectories.

4. The method of claim 1, wherein, The determining at least one trajectory group according to the trajectory feature of each trajectory in the plurality of trajectories comprises: The plurality of trajectories are traversed according to the second trajectory feature along the second direction to obtain the at least one trajectory group, wherein the second trajectory feature comprises at least one of the following: trajectory width, trajectory position, trajectory direction, trajectory speed, trajectory start and end time, and the second direction is a direction from one end of the plurality of trajectories to the other end of the plurality of trajectories.

5. The method of claim 4, wherein, The plurality of trajectories are traversed according to the second trajectory feature along the second direction to obtain the at least one trajectory group, wherein the second trajectory feature comprises at least one of the following: trajectory width, trajectory position, trajectory direction, trajectory speed, trajectory start and end time, and the second direction is a direction from one end of the plurality of trajectories to the other end of the plurality of trajectories. The transverse distance between the second trajectory and the third trajectory is determined according to the trajectory position of the second trajectory and the trajectory position of the third trajectory, wherein the second trajectory and the third trajectory are the trajectories currently traversed; The overlap time of the second trajectory and the third trajectory is determined according to the trajectory start and end time of the second trajectory and the trajectory start and end time of the third trajectory; In a case where the transverse distance is within a first distance range, the trajectory width of the second trajectory and the trajectory width of the third trajectory are both within a first width range, and the overlap time is greater than or equal to a first time threshold, the second trajectory and the third trajectory are determined as a first sub-trajectory group; In a case where the second trajectory and the third trajectory are the same trajectory, and the trajectory width of the second trajectory is within a second width range, the second trajectory is determined as a second sub-trajectory group; In a case where the trajectory width of the second trajectory and the trajectory width of the third trajectory are both within a third width range, the second trajectory and the third trajectory are determined as a third sub-trajectory group; In a case where the trajectory width of the second trajectory and the trajectory width of the third trajectory are both within a fourth width range, and the transverse distance is within a second distance range, the second trajectory and the third trajectory are determined as a fourth sub-trajectory group.

6. A vehicle dividing device characterized by comprising: The first determining unit is configured to, in a case where an execution condition is detected to be met, determine a plurality of trajectories according to a trigger position corresponding to each trigger information of a trigger information group, wherein the each trigger information is trigger information in which a weighing sensor in a weighing area is triggered; and the execution condition comprises at least one of the following: a vehicle separation signal sent by a vehicle separation sensor is acquired, a quantity of to-be-processed trigger information reaches a target quantity threshold, and the to-be-processed trigger information is trigger information to be put into an existing trajectory. ​ The second determining unit is configured to determine at least one trajectory group according to a trajectory feature of each trajectory in the plurality of trajectories, wherein each trajectory group in the at least one trajectory group comprises at least one trajectory in the plurality of trajectories, and the second determining unit comprises: a first obtaining module configured to obtain a plurality of to-be-processed trigger information, wherein each to-be-processed trigger information in the plurality of to-be-processed trigger information is trigger information to be put into a plurality of existing trajectories, and a trigger information group comprises the plurality of to-be-processed trigger information and trigger information in the plurality of existing trajectories; a matching module configured to match each to-be-processed trigger information with the plurality of existing trajectories according to a trigger position corresponding to the each to-be-processed trigger information; and in a case where the each to-be-processed trigger information is matched to a corresponding existing trajectory, obtain updated plurality of existing trajectories and features, wherein the updated plurality of existing trajectories are the plurality of trajectories; The vehicle dividing unit is configured to perform vehicle dividing processing according to the at least one trajectory group to obtain at least one vehicle, wherein the at least one trajectory group and the at least one vehicle correspond to each other; The removing unit is configured to remove an abnormal trajectory group from the at least one trajectory group to obtain updated at least one trajectory group; The device further comprises a triggering unit configured to, when a vehicle meets an out-vehicle condition, give a vehicle dividing signal of the vehicle according to a corresponding relationship between the vehicle, a trajectory, and sensor trigger information.

Images