Data processing method and device, electronic equipment, storage medium and program product

Abstract

Embodiments of the present application disclose a data processing method and device, electronic equipment, storage medium and program product. The method comprises: obtaining trajectory data of each vehicle on a target road section for the vehicle on the target road section; a traffic signal lamp is installed at an end point of the target road section; based on the trajectory data, at least one red light waiting behavior of the vehicle on the target road section is identified, and authenticity of the last red light waiting behavior is determined; wherein the real last red light waiting behavior represents that the vehicle stops and waits due to the indication of the traffic signal lamp; if the last red light waiting behavior is real, the red light waiting time corresponding to the last red light waiting behavior is deducted from the total travel time of the vehicle on the target road section to obtain the net travel time of the vehicle, and based on the net travel time and the travel distance of the vehicle on the target road section, the travel speed of the vehicle on the target road section is determined. The vehicle travel speed calculated by the embodiments of the present application can more accurately reflect the real road conditions on the target road section.

Description

Technical Field

[0001] This application relates to the field of electronic map technology, specifically to a data processing method and apparatus, electronic equipment, computer-readable storage medium, and computer program product. Background Technology

[0002] Traffic lights (red and green lights) are an important component of urban transportation infrastructure, playing a crucial role in regulating vehicle movement and maintaining traffic order. When the red light is on, vehicles must obey traffic rules and stop to wait; this waiting behavior is an expected and normal traffic phenomenon.

[0003] Currently, intelligent analysis of traffic conditions typically calculates vehicle speeds based on travel distance and time on a given road segment, using this speed to reflect the overall traffic conditions. However, this approach fails to effectively eliminate the impact of traffic light waiting times. In urban areas with numerous traffic lights, this can lead to consistently low vehicle speeds across almost all road segments, resulting in inaccurate representations of widespread traffic congestion on electronic maps. This poses a significant challenge to real-time traffic management.

[0004] Therefore, how to improve the accuracy of urban traffic management is a technical problem that urgently needs to be solved by technical personnel in this field. Summary of the Invention

[0005] To address the aforementioned technical problems, embodiments of this application provide a data processing method, a data processing apparatus, an electronic device, a computer-readable storage medium, and a computer program product. After identifying the vehicle's actual last stop at a traffic light, embodiments of this application deduct the duration of that last stop from the vehicle's total travel time and calculate the vehicle's travel speed based on the remaining time. This calculated vehicle travel speed more accurately reflects the actual road conditions on the target road segment, thereby improving the precision of urban traffic management.

[0006] One aspect of this application provides a data processing method, the method comprising: acquiring trajectory data of at least one vehicle on a target road segment; wherein a traffic light is installed at the end of the target road segment; based on the trajectory data, identifying at least one waiting-at-the-light behavior of the vehicle on the target road segment, and determining the authenticity of the last waiting-at-the-light behavior; wherein the authentic last waiting-at-the-light behavior indicates that the vehicle stopped and waited due to the instruction of the traffic light; if the last waiting-at-the-light behavior is authentic, subtracting the waiting time corresponding to the last waiting-at-the-light behavior from the total travel time of the vehicle on the target road segment to obtain the net travel time of the vehicle, and determining the travel speed of the vehicle on the target road segment based on the net travel time and the travel distance of the vehicle on the target road segment.

[0007] In another exemplary embodiment, identifying the vehicle's last waiting-at-the-light behavior on the target road segment based on the trajectory data and determining the authenticity of the last waiting-at-the-light behavior includes: determining the trajectory type of the vehicle traveling on the target road segment based on the trajectory data; if the trajectory type indicates that the vehicle has not yet passed the traffic light, determining the authenticity of the last waiting-at-the-light behavior based on the real-time status information of the traffic light; if the trajectory type indicates that the vehicle has passed the traffic light, determining the authenticity of the last waiting-at-the-light behavior based on the historical maximum waiting queue length corresponding to the traffic light.

[0008] In another exemplary embodiment, determining the authenticity of the last waiting behavior based on the real-time status information of the traffic light includes: determining the remaining distance between the end point of the trajectory and the traffic light based on the trajectory data; determining the remaining green light duration based on the real-time status of the traffic light; determining the passable distance of the vehicle within the remaining green light duration; if the passable distance is less than the remaining distance, determining that the last waiting behavior is not authentic; otherwise, determining that the last waiting behavior is authentic.

[0009] In another exemplary embodiment, determining the remaining green light duration based on the real-time status of the traffic light includes: determining the traffic light cycle in which the timestamp of the trajectory's end point is located based on the real-time status of the traffic light; if the traffic light cycle is a red light cycle, using the duration of a single green light cycle of the traffic light as the remaining green light duration; if the traffic light cycle is a green light cycle, using the current remaining green light seconds of the traffic light as the remaining green light duration.

[0010] In another exemplary embodiment, determining the permissible distance of a vehicle within the remaining green light duration includes: determining the average speed of travel on the road segment before the traffic light based on trajectory data of vehicles that have already passed the traffic light; and calculating the product of the average speed and the remaining green light duration to obtain the permissible distance.

[0011] In another exemplary embodiment, determining the authenticity of the last waiting behavior based on the historical maximum waiting queue length corresponding to the traffic light includes: determining the waiting position corresponding to the last waiting behavior based on the trajectory data; if the distance from the waiting position to the traffic light is greater than or equal to the historical maximum waiting queue length corresponding to the traffic light, determining that the last waiting behavior is not authentic; otherwise, determining that the last waiting behavior is authentic.

[0012] In another exemplary embodiment, the method further includes: if the last stop at the traffic light is not real, then directly determining the vehicle's travel speed on the target road segment based on the total travel time and distance of the vehicle on the target road segment.

[0013] In another exemplary embodiment, the method further includes: performing a fusion calculation on the travel speed of each vehicle on the target road segment to obtain a fusion score of travel speed corresponding to the target road segment; determining the road condition state mapped by the fusion score of travel speed based on a preset road condition state mapping rule, and using the determined road condition state as the real-time road condition state of the target road segment.

[0014] In another exemplary embodiment, the step of fusing the travel speeds of each vehicle on the target road segment to obtain a travel speed fusion score corresponding to the target road segment includes: determining a road condition weight factor for each vehicle based on the trajectory data of each vehicle, wherein the road condition weight factor includes at least one of trajectory traffic ratio, trajectory quality score, and trajectory freshness; determining the road condition weight of each vehicle based on the road condition weight factor; and calculating the travel speed fusion score based on the road condition weight and the travel speed of each vehicle on the target road segment.

[0015] In another exemplary embodiment, the method further includes: inputting the travel speed of each vehicle on the target road segment into a trained machine learning model to obtain the real-time traffic status of the target road segment output by the machine learning model.

[0016] In another aspect of this application, a data processing apparatus is provided, comprising: an acquisition module configured to acquire trajectory data of at least one vehicle on a target road segment; wherein a traffic light is installed at the end of the target road segment; an identification module configured to identify at least one waiting-at-a-light behavior of the vehicle on the target road segment based on the trajectory data, and determine the authenticity of the last waiting-at-a-light behavior; wherein the authentic last waiting-at-a-light behavior indicates that the vehicle stopped and waited due to the instruction of the traffic light; and a calculation module configured to, if the last waiting-at-a-light behavior is authentic, subtract the waiting time corresponding to the last waiting-at-a-light behavior from the total travel time of the vehicle on the target road segment to obtain the net travel time of the vehicle, and determine the travel speed of the vehicle on the target road segment based on the net travel time and the travel distance of the vehicle on the target road segment.

[0017] Another aspect of this application provides an electronic device, including: one or more processors; and a memory for storing one or more computer programs, which, when executed by the one or more processors, cause the electronic device to implement the data processing method as described above.

[0018] Another aspect of this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor of an electronic device, causes the electronic device to perform the data processing method described above.

[0019] Another aspect of this application provides a computer program product, including a computer program that, when executed by a processor of an electronic device, implements the data processing method described above.

[0020] In the technical solution provided in the embodiments of this application, for at least one vehicle on a target road segment where traffic lights are installed at the end point, the trajectory data of each vehicle on the target road segment is acquired, the last waiting behavior of the vehicle on the target road segment is identified based on the trajectory data, and the authenticity of the last waiting behavior is further determined. If the first waiting behavior is authentic, it means that the last waiting behavior is a normal stop waiting caused by the traffic lights on the target road segment. The duration of the last waiting time needs to be deducted from the total travel time of the vehicle. The resulting net travel time can more accurately reflect the real road conditions on the target road segment, thereby making the travel speed calculated based on the net travel time more accurate.

[0021] Furthermore, since the vehicle speed obtained from the embodiments of this application can more accurately reflect the real road conditions on the target road segment, the vehicle speed obtained from the embodiments of this application can also be used to achieve more precise urban traffic management.

[0022] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this application. Attached Figure Description

[0023] Figure 1 This is a schematic diagram of an exemplary implementation environment involved in this application;

[0024] Figure 2 This is a flowchart illustrating a data processing method in an exemplary embodiment of this application;

[0025] Figure 3 This diagram illustrates the effect of an exemplary vehicle trajectory data.

[0026] Figure 4 This is a flowchart illustrating a data processing method in another exemplary embodiment of this application;

[0027] Figure 5 This diagram illustrates the effect of another exemplary vehicle trajectory data;

[0028] Figure 6 This illustrates yet another example of the effect of vehicle trajectory data;

[0029] Figure 7 This is a flowchart illustrating a data processing method in yet another exemplary embodiment of this application;

[0030] Figure 8 This diagram illustrates an exemplary mapping relationship between road condition status and traffic speed fusion score;

[0031] Figure 9 This illustrates a flowchart of the process for obtaining the speed of vehicles on a target road segment in front of a traffic light in an exemplary application scenario.

[0032] Figure 10 This is a block diagram illustrating a data processing apparatus according to an exemplary embodiment of this application;

[0033] Figure 11 A schematic diagram of the structure of a computer system suitable for implementing the electronic device of the present application is shown. Detailed Implementation

[0034] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0035] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0036] The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily have to be performed in the described order. For example, some operations / steps can be broken down, while others can be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0037] In this application, "multiple" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. The character " / " generally indicates that the preceding and following related objects have an "or" relationship.

[0038] The terms "first," "second," "third," and "fourth," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. 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 includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0039] In the embodiments of this application, the terms "module" or "unit" refer to a computer program or part of a computer program that has a predetermined function and works with other related parts to achieve a predetermined goal, and can be implemented wholly or partially using software, hardware (such as processing circuitry or memory), or a combination thereof. Similarly, a processor (or multiple processors or memory) can be used to implement one or more modules or units. Furthermore, each module or unit can be part of an overall module or unit that includes the functionality of that module or unit.

[0040] Please refer to the following first. Figure 1 , Figure 1 This is a schematic diagram of an exemplary implementation environment involved in this application. Specifically, the implementation environment is a vehicle electronic map service system, including multiple vehicles 110 and a server 120 that provides electronic map services to the vehicles 110.

[0041] Electronic maps can be understood as maps stored on computer media. Their content is represented digitally and displayed, read, retrieved, and analyzed using specialized software. Electronic maps are characterized by detailed content, large information volume, rich visualization methods, strong interactivity, high sharing capabilities, and powerful computational and statistical analysis functions. The creation and application of electronic maps involve several key technologies, including map data organization and processing, coordinate system transformation, multi-dimensional information visualization, navigation electronic map technology, and multimedia electronic map technology. Consequently, electronic maps have wide applications in various fields such as transportation, tourism, urban planning, and environmental monitoring. Furthermore, with continuous technological advancements and increasing application demands, electronic maps are gradually exhibiting development trends such as high-precision positioning and navigation, intelligence and personalization, and cross-platform and integrated applications.

[0042] Vehicle 110 obtains electronic map services from server 120 via a wireless communication connection. The electronic map services provided by server 120 include, but are not limited to, navigation, positioning, route planning, and traffic condition analysis. During the process of providing electronic map services to vehicle 110, server 120 needs to collect real-time information of vehicle 110, such as vehicle location information, vehicle driving trajectory, vehicle speed information, vehicle status information, and vehicle identification information, etc., without limitation.

[0043] The display device 130 installed on vehicle 110 can be used to display electronic maps to provide real-time driving services to the driver. For example, electronic map service data obtained by vehicle 110 from server 120 can be visualized on display device 130 to show the driver the vehicle's real-time location and driving route, helping the driver quickly understand the best route between the current location and destination. It can also dynamically update traffic information, such as road conditions, congestion, and accident warnings, allowing the driver to adjust their driving strategy in a timely manner to avoid congestion and dangerous road sections, thereby improving driving efficiency and safety. When the vehicle malfunctions or experiences abnormalities, the electronic map service can also promptly alert the driver and may provide relevant solutions or suggestions to ensure driving safety.

[0044] It should be noted that server 120 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services; there are no restrictions here. Display device 130 can be an in-vehicle infotainment (IVI) display screen, also referred to as a vehicle display screen or navigation display screen. Display device 130 can also be a smart terminal, such as a smartphone or tablet; there are no restrictions here either.

[0045] In order to improve the accuracy of electronic map services for urban traffic management, the embodiments of this application consider that traffic lights, as an important part of urban traffic infrastructure, play a key role in regulating vehicle driving rhythm and maintaining traffic order. When the red light is on, vehicles must stop and wait in accordance with traffic rules. This waiting behavior is an expected and normal traffic phenomenon. However, there are still abnormal factors such as traffic accidents, road construction, and vehicle malfunctions that cause vehicles to stop and wait in front of traffic lights. These abnormal factors that cause vehicles to stop and wait in front of traffic lights will greatly affect the accuracy of electronic map services.

[0046] For example Figure 1 As indicated, electronic map services need to obtain... Figure 1 The system displays real-time traffic conditions for the indicated road segment, providing drivers with relevant services based on these conditions. These services include displaying real-time traffic conditions on an electronic map, showing traffic conditions along the planned navigation route, displaying and playing traffic information during navigation, and identifying congestion points in intelligent transportation scenarios. When a red light is on, vehicles must obey traffic rules and wait; this waiting behavior is a normal traffic phenomenon and should not be mistakenly interpreted as a sign of traffic congestion. However, when traffic congestion is caused by abnormal factors such as traffic accidents, road construction, or vehicle breakdowns, it needs to be interpreted as traffic congestion to provide drivers with more accurate electronic map services.

[0047] Therefore, server 120 uses traffic lights installed on road links to divide urban road segments. For road segments before traffic lights (i.e., segments ending at traffic lights), server 120 acquires vehicle trajectory data on that segment. Based on the trajectory data, it identifies at least one waiting time for the vehicle on that segment, and further determines whether the last waiting time was a normal waiting behavior due to a red light. If so, it subtracts the waiting time of the last waiting time from the total travel time on that segment to obtain the vehicle's net travel time. Then, based on the net travel time and travel distance, it calculates the vehicle's speed on that segment. This speed more accurately reflects the actual road conditions. Based on these more accurate vehicle speeds, server 120 can more precisely obtain the actual road condition status on that segment and provide drivers with more accurate electronic map services based on this road condition status.

[0048] Therefore, server 120 can obtain vehicle speed data on a "one light, one policy" basis, rather than a fixed pattern. This "one light, one policy" means that the speed of each vehicle on a road segment is related to the actual condition of the traffic light at the end of that segment. The actual condition of the traffic light specifically helps to verify the authenticity of the vehicle's last waiting time on that segment. The actual last waiting time is caused by a red light. Based on the verified authenticity of the last waiting time, the waiting time corresponding to that last waiting time is deducted, and the final calculated vehicle speed on that segment more accurately reflects the actual road conditions.

[0049] The electronic map service solution proposed in this application will be described in detail below through specific embodiments.

[0050] Please see Figure 2 , Figure 2 This is a flowchart illustrating a data processing method in an exemplary embodiment of this application. This data processing method can be applied to… Figure 1 The implementation environment shown is, for example, executed by server 120. In some other implementation environments, this data processing method can also be executed jointly by the vehicle and the server, and this embodiment does not limit this.

[0051] like Figure 2 As shown, in an exemplary embodiment, the data processing method includes S210-S230, which are described in detail below:

[0052] S210: For at least one vehicle on the target road segment, acquire the vehicle's trajectory data on the target road segment.

[0053] First, it can be understood that the road segment mentioned in the embodiments of this application can refer to a link on an electronic map. A link is one of the basic units constituting a road network. A link typically refers to a road segment between two nodes (usually represented as nodes), indicating a direct connection between the two nodes. Nodes are typically road intersections, endpoints, or key points. On an electronic map, a link can contain segment information. A segment represents the detailed part of the road between two road joints, and can be represented as a more specific road description on the link, such as details like curvature and width.

[0054] In a road network, each link typically also has directional information; the direction of a link is from the starting node (origin) to the ending node (end). The target road segment mentioned in this embodiment refers to the link whose end point is equipped with a traffic light. This can also be understood as the end point of the target road segment being an intersection equipped with a traffic light.

[0055] Typically, only one traffic light is installed at the end of a target road segment because, in road network segmentation, traffic lights are usually treated as nodes within a link. Therefore, the embodiments of this application consider the scenario where a traffic light is installed only at the end of a target road segment.

[0056] This embodiment specifically processes the trajectory data of each vehicle on the target road segment where traffic lights are installed at the end point to determine the travel speed of each vehicle on this target road segment. This travel speed can be used to reflect the impact of the actual traffic light conditions on the road conditions of the target road segment.

[0057] Vehicle trajectory data refers to the recorded information about the routes and position changes of a vehicle during its journey, and is an important data type in the field of intelligent transportation. Vehicle trajectory data can include, for example, location information, time information, speed information, and direction information, without limitation. Each location point in the trajectory data is associated with a specific point in time, recording the vehicle's position at different times. The vehicle's location information can be recorded using the vehicle's GPS (Global Positioning System) positioning device or other equipment.

[0058] S220 identifies at least one traffic light stop by a vehicle on a target road segment based on trajectory data and determines the authenticity of the last traffic light stop.

[0059] As mentioned earlier, the speed of a vehicle on a target road segment can reflect the road conditions on that segment. For target road segments with traffic lights at the end, it is necessary to eliminate the negative impact of the actual traffic light conditions on the vehicle speed so that the obtained vehicle speed can accurately reflect the true road conditions on that target road segment.

[0060] The negative impact of traffic lights on vehicle speed can be understood as follows: when the red light is on, vehicles must obey traffic rules and wait, leading to an increase in the time vehicles spend on a road segment. This, in turn, results in a lower calculated speed for vehicles before the traffic light. In urban road networks with numerous traffic lights, when vehicle speeds are significantly underestimated, it can incorrectly reflect traffic congestion on that segment, creating the misconception among the public and traffic management departments that "everywhere at traffic lights in the city is congested."

[0061] To more accurately determine the vehicle's speed on the target road segment, this embodiment removes the vehicle's last stop at a traffic light from the total travel time on that segment when calculating the vehicle's speed. Since each location point in the trajectory data is associated with a specific time point, recording the vehicle's position at different times, the system can identify at least one stop at a traffic light on the target road segment based on the location and time information contained in the trajectory data. The latest stop at a traffic light is considered the last stop at a traffic light. This can also be understood as the last stop at a traffic light on the target road segment being the vehicle's last stop at the target road segment, during which the vehicle's position remains unchanged or changes only by a short distance.

[0062] For example, before identifying at least one stopping and waiting behavior of a vehicle on a target road segment, the acquired trajectory data can be cleaned and preprocessed to remove noisy, abnormal, and duplicate data, ensuring the accuracy and reliability of the remaining trajectory data.

[0063] There are several ways to identify a vehicle's waiting behavior at a traffic light on a target road segment based on trajectory data. For example, if the vehicle's speed is below a preset speed threshold (e.g., 0.5 m / s or lower) for a period of time (e.g., 5 minutes or longer), it can be determined that the vehicle is in a stopped waiting state. Alternatively, cluster analysis can be performed on the vehicle's trajectory points. If the number of trajectory points in a certain cluster area is large and the speed is low—for example, if the number of trajectory points in a certain cluster area is greater than a preset number threshold and the speed is below the preset speed threshold—then it can be determined that the vehicle is in a stopped waiting state in this cluster area.

[0064] If there are parking areas, such as parking spaces, on the target road segment, the positional relationship between the vehicle's trajectory point and the preset parking area can be compared. If the vehicle is determined to be within the preset parking area based on this positional relationship, then this parking behavior cannot be identified as waiting at a traffic light.

[0065] Furthermore, this embodiment takes into account the need to distinguish between normal stopping and waiting caused by traffic lights and traffic congestion caused by abnormal factors such as traffic accidents, road construction, and vehicle breakdowns, in order to ensure the accuracy of vehicle speed on the target road segment. Therefore, after identifying the vehicle's last stop at a traffic light on the target road segment based on trajectory data, this embodiment also judges the authenticity of the last stop at a traffic light. A genuine last stop at a traffic light indicates that the vehicle stopped and waited due to the instruction of a traffic light at the end of the target road segment, which is an expected and normal traffic phenomenon. An inauthentic last stop at a traffic light is an unexpected and abnormal traffic phenomenon, such as traffic congestion caused by abnormal factors such as traffic accidents, road construction, and vehicle breakdowns.

[0066] Figure 3 This illustration shows an example of the effect of vehicle trajectory data. For example... Figure 3 As shown, the trajectory data of vehicle A indicates that vehicle A has engaged in two waiting-at-the-light actions on the target road segment. The second waiting-at-the-light action is a normal stop-and-wait due to the traffic light turning red, and is the actual last waiting-at-the-light action. The trajectory data of vehicle B indicates that vehicle B has engaged in one waiting-at-the-light action on this target road segment. However, based on vehicle B's current position, it can be deduced that vehicle B will experience one more waiting-at-the-light action before passing through the traffic light. Therefore, in Figure 3 In the trajectory data of vehicle B shown, the last time a vehicle waits at a traffic light is likely due to traffic congestion and queuing, and is not the actual last time a vehicle waits at a traffic light.

[0067] It can be seen that the determination of the authenticity of the last stop behavior of the vehicle based on trajectory data in this embodiment is necessary to ensure the accuracy of the vehicle's passage speed, and is closely related to the actual light conditions of the traffic lights set at the end of the target road segment.

[0068] S230, if the last waiting time at the light is real, the waiting time corresponding to the last waiting time at the light is deducted from the total travel time of the vehicle on the target road segment to obtain the vehicle's net travel time. Based on the net travel time and the vehicle's travel distance on the target road segment, the vehicle's travel speed on the target road segment is determined.

[0069] If the last waiting time of the vehicle determined in S220 is real, the waiting time corresponding to the last waiting time is subtracted from the total travel time of the vehicle on the target road segment to obtain the net travel time. The travel speed of the vehicle on the target road segment is obtained by calculating the quotient between the travel distance and the net travel time.

[0070] The total travel time and distance of a vehicle on the target road segment can be obtained from the vehicle's trajectory data on that segment. The waiting time corresponding to the vehicle's last stop at a traffic light can also be determined based on the trajectory data; this determined waiting time is the vehicle's actual waiting time on the target road segment. Therefore, the travel speed determined in this embodiment is calculated after deducting the actual last waiting time, and the deducted time will not exceed the actual red light duration of the traffic light, corresponding to the actual traffic light status. This allows for a more accurate reflection of the vehicle's travel status on the road, and thus a more accurate representation of the actual road conditions on the target road segment.

[0071] If the last stop at a traffic light identified in S220 is not genuine, it indicates an abnormal parking behavior. In this case, the parking duration corresponding to the abnormal parking behavior should be included in the calculation of the vehicle's travel speed, rather than being removed from the total travel time. Therefore, in this situation, the vehicle's travel speed on the target road segment can be calculated directly based on the total travel time and distance on the target road segment.

[0072] If S220 does not detect the vehicle waiting at a traffic light on the target road segment, it means that the vehicle did not stop and wait on the target road segment. The vehicle's speed on the target road segment can be calculated directly based on the total travel time and distance on the target road segment.

[0073] Therefore, this embodiment targets a road segment where traffic lights are installed at the end point. By acquiring the trajectory data of each vehicle on the target road segment, it identifies at least one waiting-at-the-light behavior of the vehicle on the target road segment based on the trajectory data. Furthermore, it determines the authenticity of the last waiting-at-the-light behavior by combining the actual light conditions of the traffic lights. Based on the authenticity result, it decides whether to execute the light-delay logic. Moreover, the specific light-delay duration does not exceed the actual red light duration of the traffic lights. In this way, the vehicle's passage speed on the target road segment can more accurately reflect the real road conditions on this target road segment and correspond to the actual light conditions of the traffic lights, which can serve as a "one light, one policy".

[0074] The aforementioned "one light, one policy" can be understood as follows: under the technological background of intelligent transportation, the red and green light durations of traffic lights on different road links in a road network can usually be intelligently adjusted, for example, according to the time period or actual road conditions, rather than a fixed pattern. If a fixed number of seconds is applied when executing the light-deactivation logic, such as a fixed 150 seconds, it will inevitably have a significant impact on the accuracy of the final calculated vehicle speed. In this embodiment, the travel speed of each vehicle on the target road segment is related to the actual light condition of the traffic light installed at the end of the road segment. The actual light condition of the traffic light is used to identify the authenticity of the last waiting behavior of the vehicle on the road segment. The real last waiting behavior is caused by the red light. Subsequently, based on the authenticity of the identified last waiting behavior, the waiting time corresponding to the last waiting behavior is deducted, and the deducted time does not exceed the actual red light time of the traffic light. The final calculated travel speed of the vehicle on the road segment can more accurately reflect the real road conditions on the road segment.

[0075] Furthermore, since the travel speed of each vehicle on the target road segment obtained by the embodiments of this application can more accurately reflect the real road conditions on the target road segment, it is possible to achieve more precise urban traffic management based on the vehicle travel speed obtained by the embodiments of this application.

[0076] In another exemplary embodiment of this application, such as Figure 4 As shown, in Figure 2 Based on the illustrated embodiment, the process of identifying at least one stop-at-a-light behavior of a vehicle on a target road segment based on trajectory data and determining the authenticity of the last stop-at-a-light behavior includes the following steps:

[0077] S410 determines the trajectory type of the vehicle traveling on the target road segment based on trajectory data.

[0078] In this embodiment, considering that each time trajectory data corresponding to the target road segment is acquired, trajectory data for multiple vehicles will be obtained, these trajectory data can be summarized into two types: those indicating that the vehicle has not yet passed the traffic light and those indicating that the vehicle has passed the traffic light. For example... Figure 3 As shown, the trajectory data of vehicle A represents the trajectory type of the vehicle that has passed the traffic light, while the trajectory data of vehicle B represents the trajectory type of the vehicle that has not passed the traffic light.

[0079] To ensure the accuracy of the calculated vehicle speed, for trajectories where vehicles have not yet passed through traffic lights, it is necessary to analyze whether the vehicles are affected by traffic congestion and queuing, and whether they will continue to stop and wait before passing through traffic lights. For trajectories where vehicles have already passed through traffic lights, it is necessary to analyze whether the vehicle's stop and wait is an abnormal stop, such as an abnormal stop caused by the driver's own reasons or traffic congestion.

[0080] Therefore, after obtaining the trajectory data of each vehicle on the target road segment, the trajectory type of the vehicle on the target road segment can be determined based on the correlation between the vehicle location information and time information contained in the obtained trajectory data. Then, based on the determined trajectory type, different logic for judging the authenticity of the last stop at the traffic light can be executed to ensure the accuracy of the final calculated vehicle speed on the target road segment.

[0081] S420: If the trajectory type indicates that the vehicle has not yet passed the traffic light, the authenticity of the last waiting behavior is determined based on the real-time status information of the traffic light.

[0082] For trajectory data representing a vehicle that has not yet passed a traffic light, this embodiment determines the authenticity of the vehicle's last waiting behavior based on the real-time status information of the traffic lights. The principle for determining the authenticity of the vehicle's last waiting behavior can be understood as judging whether the vehicle will continue to wait before passing the traffic light. If it will, the last waiting behavior on the current trajectory data may be an inauthentic last waiting behavior caused by traffic congestion; otherwise, it is an authentic last waiting behavior. The real-time status information of the traffic lights may include, for example, the current light cycle (including red or green light cycles), the current number of seconds the lights are on, and the current duration of a single cycle (including the duration of a single red light or green light), etc., and is not limited here.

[0083] For example, the authenticity of the last stop-at-the-light behavior determined based on vehicle trajectory data can be determined through the following process:

[0084] S421, Determine the remaining distance between the end point of the trajectory and the traffic light based on the trajectory data;

[0085] S422, determine the remaining green light duration based on the real-time status of the traffic lights;

[0086] S423 determines the permissible distance of the vehicle within the remaining green light duration. If the permissible distance is less than the remaining distance, the last waiting time at the light is determined to be false; otherwise, the last waiting time at the light is determined to be true.

[0087] In the above process, the trajectory endpoint refers to the vehicle's current location at the moment the trajectory data on the target road segment is acquired. The timestamp of the trajectory endpoint is the time information associated with that location. The distance from that location to the traffic light is the remaining distance between the trajectory endpoint and the traffic light. The location information of the traffic light can be determined based on an electronic map. Moreover, for trajectory types that indicate the vehicle has not yet passed the traffic light, the trajectory endpoint usually corresponds to within the green light cycle. Therefore, the remaining green light duration can be determined based on the real-time status of the traffic light. Based on the remaining green light duration, the permissible distance of the vehicle within this remaining green light duration can be further determined. Consequently, based on the remaining distance between the trajectory endpoint and the traffic light and the permissible distance of the vehicle within this remaining green light duration, the authenticity of the vehicle's last stop at the traffic light can be determined.

[0088] For example Figure 5 As shown, if the remaining distance L1 between the end of the trajectory and the traffic light is greater than or equal to the vehicle's passable distance L2 within the remaining green light duration, it indicates that the vehicle has not yet passed the traffic light when the next red light appears, or has just arrived at the traffic light. Therefore, the vehicle will likely wait at the light again on this target road segment in the future, and the last waiting behavior determined by the currently acquired trajectory data is not the actual last waiting behavior. If the remaining distance L1 between the end of the trajectory and the traffic light is less than the vehicle's passable distance L2 within the remaining green light duration, it indicates that the vehicle has already passed the traffic light when the next red light appears. Therefore, the vehicle will not wait at the light again on this target road segment in the future, and the last waiting behavior determined by the currently acquired trajectory data is the actual last waiting behavior. Thus, this embodiment can more accurately determine the authenticity of the last waiting behavior identified based on the vehicle's trajectory data.

[0089] In some exemplary embodiments, the traffic light cycle in which the timestamp of the trajectory's end point falls can be determined based on the real-time status of the traffic lights. For example, at the moment indicated by the timestamp of the trajectory's end point, if the traffic light is green, it means that the timestamp is in a green light cycle; if the traffic light is red, it means that the timestamp is in a red light cycle. If the traffic light cycle is determined to be a red light cycle, the duration of a single green light is taken as the remaining green light duration. If the traffic light cycle is determined to be a green light cycle, the remaining seconds of the current green light are taken as the remaining green light duration. Thus, the remaining green light duration determined based on the real-time status of the traffic lights can accurately reflect the actual traffic conditions on the target road segment under the guidance of the traffic lights, ensuring that the subsequently determined travel distance of vehicles within the remaining green light duration is also accurate.

[0090] In some exemplary embodiments, the average speed of vehicles traveling on the road segment before the traffic light can be determined based on trajectory data of vehicles that have already passed the traffic light. The permissible distance for vehicles within the remaining green light duration is obtained by multiplying this average speed by the remaining green light duration. The road segment before the traffic light can refer to the target road segment, a predetermined distance from the traffic light. The speed of vehicles that have already passed the traffic light on this road segment can be calculated based on their travel time and the length of this road segment. The average speed of vehicles that have already passed the traffic light on this road segment is obtained by averaging the speeds of multiple vehicles that have passed the traffic light. This average speed reflects the actual speed of vehicles when the traffic light is green, thus ensuring the accuracy of the calculated permissible distance for vehicles within the remaining green light duration.

[0091] In other exemplary embodiments, the average speed of a vehicle on the road segment before a traffic light can also be obtained in other ways. For example, the average speed can be set to a preset speed value, which can be obtained by analyzing the average speed of vehicles when the traffic light is in a historical green light state.

[0092] S430, if the trajectory type indicates that the vehicle has passed the traffic light, determine the authenticity of the last waiting behavior based on the historical maximum waiting queue length corresponding to the traffic light.

[0093] For trajectory data representing a vehicle's passage through a traffic light, this embodiment determines the authenticity of the vehicle's last waiting-at-the-light behavior based on its location. For example, the waiting position corresponding to the last waiting-at-the-light behavior is determined based on the trajectory data. If the distance from the waiting position to the traffic light is greater than the historical maximum queue length corresponding to the traffic light, the last waiting-at-the-light behavior is determined to be authentic; otherwise, the last waiting-at-the-light behavior is determined to be authentic.

[0094] like Figure 6As shown, when the distance L3 from the vehicle's last waiting position to the traffic light is greater than the historical maximum waiting queue length L4, it indicates that the vehicle's last waiting behavior, determined based on trajectory data, is not a normal vehicle stop due to the traffic light turning red, but rather an abnormal stopping behavior, thus identified as an untrue last waiting behavior. The historical maximum waiting queue length corresponding to the traffic light can be a preset value or obtained by mining historical trajectory data in front of that traffic light. Therefore, this embodiment, by combining the real-time status of the traffic light and mining the maximum waiting queue length in front of the traffic light based on historical trajectory data, can achieve a "one light, one policy" approach, accurately matching the characteristics of the traffic light and thus accurately calculating the passage speed of each vehicle in front of the traffic light.

[0095] In another exemplary embodiment, such as Figure 7 As shown, Figure 7 This is a flowchart illustrating a data processing method in another exemplary embodiment of this application, the method being... Figure 2 Based on the illustrated embodiment, it further includes S710-S720, which are described in detail below:

[0096] S710 calculates the combined speed of each vehicle on the target road segment to obtain the combined speed score for the target road segment.

[0097] This embodiment calculates the combined speed of vehicles on a target road segment, resulting in a combined speed score that reflects the overall traffic flow on that segment. This score allows for the determination of the road condition status of the target road segment. After determining the road condition status, this status can be sent to each vehicle on the target road segment, allowing them to update their electronic map displays. This enables precise data acquisition of each vehicle's speed on the target road segment, based on a "one light, one policy" approach, allowing the electronic map's user interface to update the traffic information in real time. Alternatively, each vehicle's electronic map can provide voice announcements for different road conditions, such as every 2 kilometers for light congestion and every 500 meters for severe congestion, significantly improving the user experience. In some exemplary embodiments, the average speed of each vehicle on the target road segment can be calculated to obtain the combined speed score for that segment.

[0098] In other exemplary embodiments, road condition weight factors for each vehicle can be determined based on the trajectory data of each vehicle, and road condition weights for each vehicle can be determined based on the road condition weight factors of each vehicle. Thus, based on the road condition weights of each vehicle and the travel speed of each vehicle on the target road segment, a travel speed fusion score can be calculated.

[0099] Traffic condition weighting factors represent information that may affect the assessment of traffic conditions. For example, traffic condition weighting factors may include at least one of the following: track traffic share, track quality score, and track freshness.

[0100] The trajectory travel ratio represents the ratio of the distance a vehicle travels on the target road segment to the total length of that target road segment, and can be calculated using the following formula:

[0101]

[0102] Among them, w percentage,i d represents the percentage of traffic on the trajectory of the i-th vehicle. i Let represent the distance traveled by the i-th vehicle on the target road segment, and D represent the total length of the target road segment.

[0103] The trajectory quality score can include either a matching quality score or a collection quality score, both of which can be represented as values ​​between 0 and 1. The collection quality score characterizes the quality of the trajectory data during the collection process and can be related to sensor accuracy, sampling frequency, and equipment calibration. The matching quality score characterizes the degree of matching between the collected trajectory data and the road network in the electronic map, and can be related to map data accuracy, matching algorithm accuracy, and trajectory point density.

[0104] In some exemplary embodiments, the trajectory quality score can also be obtained by weighting and summing the matching quality score and the acquisition quality score, as shown in the following formula:

[0105] w quality,i =α·w match,i +(1-α)·w collection,i

[0106] Among them, w quality,i w represents the trajectory quality score of the i-th vehicle. match,i w represents the matching quality score of the i-th vehicle. collection,i Let represent the quality score of the i-th vehicle, α represent the weighting coefficient of the matching quality score, and 1-α represent the weighting coefficient of the acquisition quality score. The weighting coefficients corresponding to the matching quality score and the acquisition quality score can both be 0.5, or other weighting coefficient ratios; there are no restrictions here.

[0107] Track freshness can be determined based on the timestamps of the track data, with newer track data receiving higher weights. For example, an exponential decay function can be used to calculate the freshness score for each track point in the track data, as shown below:

[0108]

[0109] Where, w freshness,j Let represent the freshness score of the j-th trajectory point, λ represent the decay coefficient, which determines the rate at which the freshness of the trajectory point decreases over time and can be adjusted according to actual needs, and t represent the current time. j This indicates the time when the j-th trajectory point was recorded.

[0110] Since a trajectory typically contains multiple trajectory points, the freshness score of each trajectory point can be determined using the formula above. By merging the freshness scores of these individual trajectory points, the freshness of the entire trajectory can be obtained. For example, the arithmetic mean of the freshness scores of all trajectory points can be calculated to obtain the freshness of the entire trajectory. Alternatively, a weighted average of the freshness scores of all trajectory points can be calculated to obtain the freshness of the entire trajectory. Furthermore, the temporal order of the trajectory points can be considered, and a cumulative decay function can be applied to calculate the freshness of the entire trajectory. The calculation formula is shown below:

[0111]

[0112] Among them, C j C represents the cumulative freshness from the starting point of the trajectory to the j-th trajectory point, and μ represents the decay coefficient, used to control the influence of earlier trajectory points on freshness during the accumulation process. If we assume the entire trajectory contains m trajectory points, then C... m The freshness of the entire trajectory.

[0113] For example, the road condition weighting factors for each vehicle can be weighted and summed to obtain the road condition weight for that vehicle. The weighting coefficients corresponding to each road condition weighting factor can be adjusted to the same coefficient or different coefficients according to actual application needs, and there is no restriction here.

[0114] In other exemplary embodiments, the traffic speed fusion score can also be calculated based on the following formula:

[0115]

[0116] Among them, w avg The sum of traffic speeds represents the combined score, where n represents the number of vehicles, and w represents the combined score. total,i v represents the road condition weight of the i-th vehicle. iThis represents the travel speed of the i-th vehicle on the target road segment.

[0117] As can be seen, the traffic speed fusion score represents the ratio of the weighted total communication speed on the target road segment to the sum of the road condition weights of all vehicles on the target road segment. In other words, it is a normalization process for the traffic speed of each vehicle on the target road segment. The traffic speed fusion score can also be represented as a value between 0 and 1.

[0118] S720 determines the road condition status based on the preset road condition status mapping rules, and uses the determined road condition status as the real-time road condition status of the target road segment.

[0119] Road condition mapping rules are used to characterize the mapping relationship between different road condition states and the combined traffic speed score. Moreover, the mapping relationship between road condition states and the combined traffic speed score can be different for different road types.

[0120] Figure 8 This diagram illustrates an exemplary mapping relationship between road condition status and traffic speed fusion score, as shown below. Figure 8 As shown, roads can be categorized into three types: expressways and urban expressways, national highways, provincial highways, and county roads, and other small roads. For each road type, corresponding score thresholds are set to distinguish different road condition states. For example, for expressways and urban expressways, if the combined speed score is greater than 0.55, the road condition is determined to be "smooth"; if the combined speed score is less than or equal to 0.55 but greater than 0.30, the road condition is determined to be "slow"; if the combined speed score is less than or equal to 0.30 but greater than 0.15, the road condition is determined to be "congested"; and if the combined speed score is less than or equal to 0.15, the road condition is determined to be "extremely congested". For national highways, provincial highways, and county roads, if the combined speed score is greater than 0.50, the road condition is determined to be "smooth"; if the combined speed score is less than or equal to 0.50 but greater than 0.30, the road condition is determined to be "slow"; if the combined speed score is less than or equal to 0.30 but greater than 0.10, the road condition is determined to be "congested"; and if the combined speed score is less than or equal to 0.10, the road condition is determined to be "extremely congested".

[0121] Therefore, based on this road condition mapping rule, the road condition status mapped by the traffic speed fusion score can be determined, and this road condition status is the real-time road condition status of the target road segment.

[0122] It should be noted that, Figure 8The road condition mapping rules shown are for illustrative purposes only. In actual application scenarios, various road types and the thresholds used to distinguish different road conditions under each road type can be set according to actual needs.

[0123] Since the traffic speed fusion score is based on the traffic speed of each vehicle on the target road segment and is obtained by fusion based on the corresponding road condition weights, the real-time road condition status of the target road segment obtained in this embodiment based on the road condition mapping rules and the traffic speed fusion score is closer to the actual road condition status of the target road segment, which meets the accuracy requirements of road condition status in actual application scenarios.

[0124] In other exemplary embodiments, the travel speed of each vehicle on the target road segment can be input into a trained machine learning model to obtain the real-time traffic status of the target road segment output by the machine learning model. The machine learning model can be an LR (Logistic Regression) model, a decision tree-based XGBoost model, a DNN (Deep Neural Network) model, etc., and is not limited thereto.

[0125] Figure 9 This diagram illustrates the process of obtaining the speed of vehicles on a target road segment in front of a traffic light in an exemplary application scenario.

[0126] like Figure 9As shown, the system first needs to periodically acquire the trajectory data of N vehicles in front of the traffic light; that is, it periodically acquires the trajectory data of each vehicle on the target road segment where the traffic light is located. Then, it iterates through the trajectory data of each vehicle and identifies the waiting behavior at the traffic light. If no waiting behavior at the traffic light is identified, the light-deactivation logic is not executed. Instead, the system directly determines the vehicle's travel distance and total travel time on the target road segment based on the trajectory data, and calculates the vehicle's travel speed on the target road segment based on the travel distance and total travel time. If a vehicle is detected waiting at a traffic light, the system further determines whether the vehicle has passed the traffic light. If not, it means the vehicle has not yet completed its journey along the target road segment. The remaining green light duration is then determined based on the real-time traffic light status. The authenticity of the vehicle's last waiting time is then verified based on the remaining green light duration. If authentic, the duration of the vehicle's last waiting time is determined based on trajectory data. This waiting time is subtracted from the total travel time to obtain the vehicle's net travel time on the target road segment. Finally, the vehicle's speed on the target road segment is calculated based on the net travel time and travel distance. If the vehicle's last waiting time is not authentic, the waiting time deduction logic is not executed, and the vehicle's speed on the target road segment is directly calculated based on the travel distance and total travel time. If a vehicle fails to pass a traffic light, the location of the vehicle's last waiting behavior on the target road segment is obtained, and the distance La from the waiting location to the traffic light is calculated. The historical maximum queue length Lc in front of the traffic light is also extracted from the historical trajectory data. If La ≥ Lc, it means that the vehicle's last waiting behavior is not real, and the light-delaying logic is not executed. Otherwise, it means that the vehicle's last waiting behavior is real, and the light-delaying logic needs to be executed.

[0127] As can be seen from the above, the embodiments of this application mainly focus on three aspects in detail regarding the processing logic. The first aspect is whether the last waiting behavior for a trajectory data point that did not pass a traffic light was normally influenced by traffic light regulations, or whether it was caused by traffic congestion leading to a stop and wait. The second aspect is whether the last waiting behavior for a trajectory data point that did not pass a traffic light was normally influenced by traffic light regulations, or whether it was caused by traffic congestion leading to a stop and wait. The third aspect is how to make the light-deactivation duration more reasonable when calculating vehicle speed. Based on addressing these three questions, the embodiments of this application innovatively combine with the real-time status of traffic lights to achieve a "one light, one policy" approach, accurately matching the characteristics of traffic lights and calculating the speed of each vehicle before the traffic light with sufficient precision. This allows the speed calculation based on multi-vehicle fusion to most accurately reflect the real state of the road conditions, reflect the user's real feelings, and improve user experience and reputation.

[0128] It should also be noted that the real-time traffic status of the target road segment obtained in this application embodiment can be applied to the base map traffic display in electronic maps to achieve visualization of basic information. For example, historical congestion heat maps can be used to display frequently congested road segments in the city, and road level data (such as highways / national roads / urban branch roads) can be combined for hierarchical rendering to help users predict road capacity. Historical traffic data can also be used to predict highway congestion periods during holidays, etc.

[0129] The real-time traffic status of the target road segment obtained in this application embodiment can also be applied to the traffic status display on the navigation planning route to achieve dynamic route planning and improve the spatiotemporal efficiency of the navigation system. For example, a cost function can be constructed by combining real-time traffic conditions, road grade, and historical congestion probability to achieve automatic recommendation of navigation routes. Congestion spread can also be predicted based on the traffic flow wave propagation model to achieve predictive route adjustment.

[0130] The real-time traffic conditions of the target road segment obtained in this application embodiment can also be applied to traffic condition display and broadcast during navigation to improve driving safety and navigation experience. For example, a tiered voice prompt strategy can be adopted to achieve context-aware playback; for instance, a broadcast can be given every 2 kilometers for lightly congested road segments, every 500 meters for severely congested road segments, and immediately in the event of an emergency. Real-time traffic holographic projection can also be overlaid on the vehicle's HUD (Head-Up Display) to achieve immersive AR (Augmented Reality) navigation.

[0131] The real-time traffic conditions of the target road segment obtained in this application embodiment can also be applied to congestion point identification in the field of intelligent transportation to empower traffic management. For example, by clustering the full amount of GPS trajectory data, frequently occurring congestion bottlenecks can be identified, or a congestion duration-impact range matrix can be established to distinguish between occasional accidents and structural congestion, thereby achieving spatiotemporal clustering analysis. Correlation analysis can also be performed on multiple dimensions such as traffic flow, road facilities, and signal control to achieve root cause diagnosis of traffic problems. Simulation of traffic management solutions such as lane expansion and signal optimization can also be implemented, which will not be listed here.

[0132] Figure 10 This is a block diagram illustrating a data processing apparatus according to an exemplary embodiment of this application. This data processing apparatus can be applied to... Figure 1 The implementation environment shown is, for example, specifically configured on server 120. In some other implementation environments, the data processing device can also be configured on both the vehicle and the server; this embodiment does not limit this.

[0133] like Figure 10 As shown, in an exemplary embodiment, the data processing apparatus includes:

[0134] The acquisition module 1010 is configured to acquire the trajectory data of at least one vehicle on the target road segment; wherein a traffic light is installed at the end of the target road segment.

[0135] The identification module 1020 is configured to identify at least one traffic light waiting behavior of a vehicle on a target road segment based on trajectory data, and determine the authenticity of the last traffic light waiting behavior; wherein, the authentic last traffic light waiting behavior indicates that the vehicle stopped and waited due to the instruction of the traffic signal light.

[0136] The calculation module 1030 is configured to, if the last waiting time at a traffic light is real, subtract the waiting time corresponding to the last waiting time at a traffic light from the total travel time of the vehicle on the target road segment to obtain the vehicle's net travel time, and determine the vehicle's travel speed on the target road segment based on the net travel time and the vehicle's travel distance on the target road segment.

[0137] In another exemplary embodiment, the identification module 1020 includes:

[0138] The type determination submodule is configured to determine the trajectory type of the vehicle traveling on the target road segment based on trajectory data;

[0139] The authenticity determination submodule is configured to determine the authenticity of the last waiting behavior based on the real-time status information of the traffic light if the trajectory type indicates that the vehicle has not yet passed the traffic light; and to determine the authenticity of the last waiting behavior based on the historical maximum waiting queue length corresponding to the traffic light if the trajectory type indicates that the vehicle has passed the traffic light.

[0140] In another exemplary embodiment, the authenticity determination submodule includes:

[0141] The distance determination unit is configured to determine the remaining distance between the end point of the trajectory and the traffic light based on the trajectory data.

[0142] The duration determination unit is configured to determine the remaining green light duration based on the real-time status of the traffic lights;

[0143] The distance comparison unit is configured to determine the passable distance of a vehicle within the remaining green light duration. If the passable distance is less than the remaining distance, the last waiting time at the light is determined to be false; otherwise, the last waiting time at the light is determined to be true.

[0144] In another exemplary embodiment, the duration determination unit is further configured to perform the following steps:

[0145] Based on the real-time status of the traffic lights, determine the traffic light cycle in which the timestamp of the trajectory's end point falls;

[0146] If the traffic light cycle is a red light cycle, the duration of a single green light cycle will be used as the remaining green light duration.

[0147] If the traffic light cycle is a green light cycle, the remaining number of seconds of the current green light is taken as the remaining green light duration.

[0148] In another exemplary embodiment, the comparison unit is further configured to perform the following steps:

[0149] Based on the trajectory data of the traffic lights that have been passed, determine the average speed of travel on the road segment before the traffic lights;

[0150] Calculate the product of the average speed and the remaining green light duration to obtain the passable distance.

[0151] In another exemplary embodiment, the authenticity determination submodule includes:

[0152] The location determination unit is configured to determine the waiting position corresponding to the last waiting behavior based on trajectory data;

[0153] The location comparison unit is configured to determine that the last waiting behavior is not real if the distance from the waiting position to the traffic light is greater than or equal to the historical maximum waiting queue length corresponding to the traffic light; otherwise, it determines that the last waiting behavior is real.

[0154] In another exemplary embodiment, the calculation module 1030 is further configured to: if the last stop at the traffic light is not real, determine the vehicle's travel speed on the target road segment directly based on the total travel time and distance of the vehicle on the target road segment.

[0155] In another exemplary embodiment, the data processing apparatus further includes:

[0156] The score fusion module is configured to perform fusion calculations on the travel speed of each vehicle on the target road segment to obtain the fusion score of the travel speed corresponding to the target road segment;

[0157] The traffic condition determination module is configured to determine the traffic condition status based on the preset traffic condition status mapping rules, and use the determined traffic condition status as the real-time traffic condition status of the target road segment.

[0158] In another exemplary embodiment, the score fusion module includes:

[0159] The weighting factor determination submodule is configured to determine the road condition weighting factor for each vehicle based on the trajectory data of each vehicle. The road condition weighting factor includes at least one of trajectory traffic ratio, trajectory quality score, and trajectory freshness.

[0160] The road condition weight determination submodule is configured to determine the road condition weight of each vehicle based on the road condition weight factor.

[0161] The fusion calculation submodule is configured to calculate the fusion score of traffic speed based on road condition weights and the traffic speed of each vehicle on the target road segment.

[0162] In another exemplary embodiment, the data processing device further includes a model prediction module, which is configured to input the travel speed of each vehicle on the target road segment into a trained machine learning model to obtain the real-time traffic status of the target road segment output by the machine learning model.

[0163] It should be noted that the apparatus and method provided in the above embodiments belong to the same concept, and the specific manner in which each module and unit performs its operation has been described in detail in the method embodiments, and will not be repeated here. In practical applications, the data processing apparatus provided in the above embodiments can be assigned to different functional modules as needed, that is, the internal structure of the apparatus can be divided into different functional modules to complete all or part of the functions described above, and this is not a limitation here.

[0164] Embodiments of this application also provide an electronic device, including: one or more processors; and a memory for storing one or more computer programs, which, when executed by the one or more processors, cause the electronic device to implement the data processing methods provided in the above embodiments.

[0165] Figure 11 A schematic diagram of a computer system suitable for implementing an electronic device according to embodiments of this application is shown. It should be noted that the electronic device can be... Figure 1 The server 120 in the implementation environment shown can also be a terminal or server in other implementation environments; there are no restrictions here. It should also be noted that... Figure 11 The computer system 1100 of the electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0166] like Figure 11As shown, the computer system 1100 includes a Central Processing Unit (CPU) 1101, which can perform various appropriate actions and processes based on a computer program stored in Read-Only Memory (ROM) 1102 or a computer program loaded from storage portion 1108 into Random Access Memory (RAM) 1103, such as performing the methods described in the above embodiments. Various computer programs and data required for system operation are also stored in RAM 1103. The CPU 1101, ROM 1102, and RAM 1103 are interconnected via bus 1104. An Input / Output (I / O) interface 1105 is also connected to bus 1104.

[0167] The following components are connected to I / O interface 1105: an input section 1106 including a keyboard, mouse, etc.; an output section 1107 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 1108 including a hard disk, etc.; and a communication section 1109 including a network interface card such as a LAN (Local Area Network) card, modem, etc. The communication section 1109 performs communication processing via a network such as the Internet. A drive 1110 is also connected to I / O interface 1105 as needed. Removable media 1111, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., are installed on drive 1110 as needed so that computer programs read from them can be installed into storage section 1108 as needed.

[0168] Specifically, according to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program including a computer program for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 1109, and / or installed from removable medium 1111. When the computer program is executed by central processing unit (CPU) 1101, it performs various functions defined in the system of this application.

[0169] It should be noted that the computer-readable medium shown in the embodiments of this application can be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. The computer program contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0170] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. Each block in a flowchart or block diagram may represent a module, segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0171] The units described in the embodiments of this application can be implemented in software or hardware, and the described units can also be located in a processor. The names of these units do not necessarily limit the specific unit itself.

[0172] Another aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor of an electronic device, implements the data processing method as described above. This computer-readable storage medium may be included in the electronic device described in the above embodiments, or it may exist independently and not assembled into the electronic device.

[0173] Another aspect of this application provides a computer program product comprising a computer program stored in a computer-readable storage medium. A processor of an electronic device reads the computer program from the computer-readable storage medium and executes the computer program, causing the electronic device to perform the data processing methods provided in the various embodiments described above.

[0174] The above description is merely a preferred exemplary embodiment of this application and is not intended to limit the implementation of this application. Those skilled in the art can easily make corresponding modifications or alterations based on the main concept and spirit of this application. Therefore, the scope of protection of this application should be determined by the scope of protection claimed in the claims.

[0175] It is understood that in the specific embodiments of this application, data such as trajectory data and real-time status of traffic lights are involved. When the above embodiments of this application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of related data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

Claims

1. A data processing method, characterized in that, The method includes: For at least one vehicle on a target road segment, acquire the vehicle's trajectory data on the target road segment; wherein a traffic light is installed at the end of the target road segment; Based on the trajectory data, at least one traffic light waiting behavior of the vehicle on the target road segment is identified, and the authenticity of the last traffic light waiting behavior is determined; wherein, the authentic last traffic light waiting behavior indicates that the vehicle stopped and waited due to the instruction of the traffic light. If the last waiting time at a traffic light is real, the waiting time corresponding to the last waiting time at a traffic light is subtracted from the total travel time of the vehicle on the target road segment to obtain the vehicle's net travel time. Based on the net travel time and the distance traveled by the vehicle on the target road segment, the vehicle's travel speed on the target road segment is determined.

2. The method according to claim 1, characterized in that, The step of identifying the vehicle's last stop at a traffic light on the target road segment based on the trajectory data, and determining the authenticity of the last stop at a traffic light, includes: Based on the trajectory data, the trajectory type of the vehicle traveling on the target road segment is determined; If the trajectory type indicates that the vehicle has not yet passed the traffic light, the authenticity of the last waiting behavior is determined based on the real-time status information of the traffic light. If the trajectory type indicates that the vehicle has passed the traffic light, the authenticity of the last waiting behavior is determined based on the historical maximum waiting queue length corresponding to the traffic light.

3. The method according to claim 2, characterized in that, The step of determining the authenticity of the last waiting behavior based on the real-time status information of the traffic lights includes: Based on the trajectory data, determine the remaining distance between the end point of the trajectory and the traffic light; The remaining green light duration is determined based on the real-time status of the traffic lights; The permissible distance for a vehicle within the remaining green light duration is determined. If the permissible distance is less than the remaining distance, the last waiting time at the green light is determined to be false; otherwise, the last waiting time at the green light is determined to be true.

4. The method according to claim 3, characterized in that, Determining the remaining green light duration based on the real-time status of the traffic lights includes: Based on the real-time status of the traffic lights, the traffic light cycle in which the timestamp of the trajectory's end point is located is determined; If the traffic light cycle is a red light cycle, the duration of a single green light of the traffic light is taken as the remaining green light duration. If the traffic light cycle is a green light cycle, the remaining green light time of the current traffic light is taken as the remaining green light duration.

5. The method according to claim 3, characterized in that, Determining the permissible distance for vehicles during the remaining green light duration includes: Based on the trajectory data of the traffic lights, determine the average speed of traffic on the road section before the traffic lights; The product of the average traffic speed and the remaining green light duration is calculated to obtain the passable distance.

6. The method according to claim 2, characterized in that, Determining the authenticity of the last waiting time based on the historical maximum waiting queue length corresponding to the traffic light includes: The waiting position corresponding to the last waiting behavior is determined based on the trajectory data; If the distance from the waiting position to the traffic light is greater than or equal to the historical maximum waiting queue length corresponding to the traffic light, the last waiting behavior is determined to be untrue; otherwise, the last waiting behavior is determined to be true.

7. The method according to any one of claims 1-6, characterized in that, The method further includes: If the last stop at the traffic light is not real, the vehicle's speed on the target road segment is determined directly based on the total travel time and distance on the target road segment.

8. The method according to any one of claims 1-6, characterized in that, The method further includes: The speed of each vehicle on the target road segment is fused and calculated to obtain the fused speed score corresponding to the target road segment; Based on preset road condition mapping rules, the road condition status of the traffic speed fusion score mapping is determined, and the determined road condition status is used as the real-time road condition status of the target road segment.

9. The method according to claim 8, characterized in that, The process of fusing the travel speeds of each vehicle on the target road segment to obtain a fused travel speed score for the target road segment includes: Based on the trajectory data of each vehicle, a road condition weighting factor is determined for each vehicle. The road condition weighting factor includes at least one of trajectory traffic ratio, trajectory quality score, and trajectory freshness. The road condition weight of each vehicle is determined based on the road condition weight factor. Based on the road condition weights and the travel speed of each vehicle on the target road segment, the travel speed fusion score is calculated.

10. The method according to any one of claims 1-6, characterized in that, The method further includes: The travel speed of each vehicle on the target road segment is input into a trained machine learning model to obtain the real-time traffic status of the target road segment output by the machine learning model.

11. A data processing apparatus, characterized in that, The device includes: The acquisition module is configured to acquire trajectory data of at least one vehicle on a target road segment; wherein a traffic light is installed at the end of the target road segment. The identification module is configured to identify at least one traffic light waiting behavior of a vehicle on the target road segment based on the trajectory data, and determine the authenticity of the last traffic light waiting behavior; wherein, the authentic last traffic light waiting behavior indicates that the vehicle stopped and waited due to the instruction of the traffic light. The calculation module is configured to, if the last waiting time at a traffic light is real, subtract the waiting time corresponding to the last waiting time at a traffic light from the total travel time of the vehicle on the target road segment to obtain the vehicle's net travel time, and determine the vehicle's travel speed on the target road segment based on the net travel time and the vehicle's travel distance on the target road segment.

12. An electronic device, characterized in that, include: One or more processors; A memory for storing one or more computer programs that, when executed by one or more processors, cause the electronic device to perform the method as described in any one of claims 1-10.

13. A computer-readable storage medium, characterized in that, It stores a computer program that, when executed by the processor of the electronic device, causes the electronic device to perform the method of any one of claims 1-10.

14. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor of the electronic device, it implements the method as described in any one of claims 1-10.

Images