Traffic light control information acquisition method and apparatus, computing device cluster, and storage medium

Abstract

A traffic light control information acquisition method and apparatus, a computing device cluster, and a storage medium. The traffic light control information acquisition method comprises: acquiring driving trajectories of a plurality of sample vehicles passing through a target intersection within a target time period so as to obtain a driving trajectory set (S11); determining, from the driving trajectory set, the numbers of first-type trajectories respectively corresponding to permitted directions at the target intersection, and the total numbers of driving trajectories respectively corresponding to the permitted directions, wherein each first-type trajectory is a driving trajectory in which a stopping behavior occurs (S12); for each permitted direction, calculating a first ratio of the number of the first-type trajectories corresponding to the permitted direction to the total number of the driving trajectories corresponding to the permitted direction (S13); and when the first ratio is greater than a first preset ratio, determining that traffic light control information is present for the permitted direction (S14). According to the traffic light control information acquisition method, traffic light control information can be acquired accurately and efficiently in a timely manner.

Description

Lighting control information acquisition method, device, computing device cluster and storage medium

[0001] This disclosure claims priority to a Chinese patent application filed with the Patent Office of China on March 28, 2024, with application number 202410370603.4 and application name “A method, device, computing device cluster and storage medium for obtaining lighting control information,” the entire contents of which are incorporated herein by reference. Technical Field

[0002] The present disclosure relates to the field of traffic technology, and in particular to a method and apparatus for obtaining light control information, a computing device cluster, and a storage medium. Background Art

[0003] When users are driving, they are accustomed to using navigation applications on their mobile phones or car computers for navigation. Currently, navigation applications can display information about traffic lights on the navigation interface, such as the current status of traffic lights and / or the remaining duration of the current status. In order for navigation applications to present accurate traffic light information to users, it is necessary to comprehensively explore the control information of traffic lights at each intersection. Among them, the control information of traffic lights, hereinafter referred to as light control information, refers to the information on the current outbound direction of traffic flow controlled by traffic lights at intersections with traffic lights. The outbound direction refers to the relative direction between the road that the vehicle arrives at after leaving the intersection and the road that the vehicle was traveling before the intersection. The outbound direction can be a U-turn, left turn, straight ahead, right turn, etc.

[0004] The traditional method of obtaining traffic light control information is to manually collect road image data using mobile devices, and then determine the traffic light control information through manual or image recognition.

[0005] However, due to the large number of roads and the wide coverage of traffic lights, the above methods have long acquisition cycles and high costs. Manual processing of image data is inefficient, while image recognition technology has difficulty detecting small objects and is easily affected by interference from image viewing angles and other directional lights, resulting in low accuracy. Furthermore, these methods have long information update cycles. If a certain outbound direction at an intersection changes from no traffic light information to traffic light information, these methods are unable to capture this change in a timely manner.

[0006] Therefore, a solution is needed to obtain lighting control information in a timely, accurate and efficient manner. Summary of the Invention

[0007] In order to solve the above-mentioned problems existing in the prior art, the present disclosure provides a lighting control information acquisition method, apparatus, computing device cluster and storage medium, which can timely, accurately and efficiently acquire lighting control information.

[0008] In a first aspect, the present disclosure provides a method for obtaining light control information, which can be implemented by a server device. The method includes the following steps: obtaining the driving trajectories of multiple sample vehicles passing through a target intersection within a target time period to obtain a driving trajectory set; from the driving trajectory set, determining the number of first-class trajectories corresponding to each passable direction of the target intersection, and the total number of trajectories corresponding to each passable direction, the first-class trajectory being the driving trajectory in which parking behavior occurs; for each passable direction, calculating a first ratio of the number of first-class trajectories corresponding to the passable direction to the total number of driving trajectories corresponding to the passable direction; when the first ratio is greater than a first preset ratio, determining that light control information exists in the passable direction.

[0009] By collecting the driving trajectories of sample vehicles and rationally selecting the length of the target time period, the above scheme ensures a sufficient amount of trajectory data, improves the reliability of the light control information mining results, and eliminates the need for manual on-site information collection, shortening the data collection cycle and reducing data collection costs. By rationally selecting the time window for the target time period, the timeliness of the light control information mining results can be improved. For example, the time window can be set to the most recent day. Based on the relationship between the first ratio of the number of first-category trajectories corresponding to each passable direction and the total number of driving trajectories corresponding to each passable direction and a first preset ratio, this scheme can determine whether light control information exists for each passable direction, such as for U-turns, left turns, straight ahead, or right turns. This makes it more comprehensive and efficient. Furthermore, this scheme can process the trajectory data using a computing device, enabling large-scale batch mining of light control information, significantly reducing labor costs and possessing high practicality. In summary, this method enables timely, accurate, and efficient acquisition of light control information.

[0010] In the second aspect, the present disclosure also provides a lighting control information acquisition device, which includes: an acquisition unit, a first determination unit and a second determination unit. The acquisition unit is used to acquire the driving trajectories of multiple sample vehicles passing through the target intersection within a target time period to obtain a driving trajectory set. The first determination unit is used to determine the number of first-class trajectories corresponding to each passable direction of the target intersection and the total number of driving trajectories corresponding to each passable direction from the driving trajectory set, and the first-class trajectory is the driving trajectory with parking behavior. The second determination unit is used to calculate, for each passable direction, a first ratio of the number of first-class trajectories corresponding to the passable direction to the total number of driving trajectories corresponding to the passable direction; when the first ratio is greater than the first preset ratio, it is determined that there is lighting control information in the passable direction.

[0011] In a third aspect, the present disclosure further provides a computing device cluster, comprising at least one computing device, the at least one computing device including at least one processor and at least one memory, the at least one memory storing computer-readable instructions, and the at least one processor executing the computer-readable instructions to cause the computing device cluster to perform the lighting control information acquisition method. The computing device cluster may also be referred to as a server cluster, and the computing devices included in the computing device cluster may also be referred to as server devices.

[0012] In a fourth aspect, the present disclosure further provides a storage medium storing computer-readable instructions, which, when executed by a processor of a computing device, are used to implement a method for acquiring lighting control information.

[0013] In a fifth aspect, the present disclosure further provides a computer program product, including a computer program, which implements a method for obtaining lighting control information when executed by at least one computing device. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] FIG1 is a schematic diagram of a scenario provided by an embodiment of the present disclosure;

[0015] FIG2 is a flow chart of a method for acquiring lighting control information provided by an embodiment of the present disclosure;

[0016] FIG3 is a second schematic diagram of a scenario provided by an embodiment of the present disclosure;

[0017] FIG4 is a third schematic diagram of a scenario provided by an embodiment of the present disclosure;

[0018] FIG5 is a flow chart of another method for acquiring lighting control information provided by an embodiment of the present disclosure;

[0019] FIG6 is a schematic diagram of a lighting control information acquisition device provided by an embodiment of the present disclosure;

[0020] FIG7 is a schematic diagram of a computing device provided by an embodiment of the present disclosure;

[0021] FIG8 is a schematic diagram of a computing device cluster provided by an embodiment of the present disclosure;

[0022] FIG9 is a first schematic diagram of a connection method of a computing device cluster provided by an embodiment of the present disclosure;

[0023] FIG10 is a second schematic diagram of the connection method of the computing device cluster provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0024] In order to enable people skilled in the art to more clearly understand the present disclosure, the following first explains the relevant terms in the present disclosure.

[0025] Traffic light: An important infrastructure for traffic management departments to control vehicle traffic order and adjust road traffic flow. The traffic light in the following description of the embodiments of the present disclosure may also be called a traffic light or a traffic signal light.

[0026] Black light: There are traffic lights on the road, but they are not on and have no function in regulating traffic flow.

[0027] Yellow flashing light: There are traffic lights on real roads, but they are only in a flashing yellow state, used to serve as a warning.

[0028] Evergreen light: There is a traffic light on the route, but it is only in the green state.

[0029] Driving trajectory refers to the sequence of global navigation satellite system (GNSS) position data transmitted back by the vehicle navigation device during the driving process.

[0030] Out-degree road: At an intersection, the road that a vehicle reaches after leaving the intersection is called the out-degree road.

[0031] In-degree road: At an intersection, the road that a vehicle travels on before leaving the intersection is an in-degree road.

[0032] Out-degree direction: The out-degree direction can be determined by combining the out-degree road and the in-degree road. The out-degree direction refers to the relative direction between the road a vehicle reaches after leaving the intersection and the road the vehicle was traveling on before the intersection. The out-degree direction can be a U-turn, left turn, straight ahead, or right turn. Specifically, when the road a vehicle reaches after leaving the intersection is to the left of the road the vehicle was traveling on before the intersection, the relative direction is left, and the out-degree direction is a left turn. When the road a vehicle reaches after leaving the intersection does not turn relative to the road the vehicle was traveling on before the intersection, the relative direction is forward, and the out-degree direction is straight ahead. When the road a vehicle reaches after leaving the intersection is to the right of the road the vehicle was traveling on before the intersection, the relative direction is right, and the out-degree direction is a right turn. When the road a vehicle reaches after leaving the intersection does not turn relative to the road the vehicle was traveling on before the intersection, the relative direction is reverse, and the out-degree direction is a U-turn.

[0033] An outgoing direction can represent a possible direction for a vehicle to pass through an intersection, which is explained in detail below.

[0034] See FIG1 , which is a first schematic diagram of a scenario provided by an embodiment of the present disclosure.

[0035] In FIG1 , a sample vehicle passing through an intersection is taken as an example. The possible directions for the sample vehicle at the intersection may include: U-turn L1 , left turn L2 , straight ahead L3 , and right turn L4 .

[0036] The combination of the in-degree and out-degree roads before and after a vehicle passes through an intersection can be used to characterize the vehicle's travel direction. Specifically:

[0037] The incoming road is the road before leaving the intersection and the direction is from south to north. The outgoing road is the road after leaving the intersection and the direction is from north to south. The corresponding drivable direction is: U-turn L1;

[0038] The incoming road is the road before leaving the intersection and the direction is from south to north. The outgoing road is the road after leaving the intersection and the direction is from east to west. The corresponding passable direction is: turn left to L2;

[0039] The in-degree road is the road before leaving the intersection and the direction is from south to north. The out-degree road is the road reached after leaving the intersection and the direction is from south to north. The corresponding passable direction is: straight ahead L3;

[0040] The incoming road is the road before leaving the intersection and the direction is from south to north. The outgoing road is the road reached after leaving the intersection and the direction is from west to east. The corresponding passable direction is: turn right to L4.

[0041] It is understood that when the intersection is a T-junction, the passable directions may include U-turn L1, left turn L2, and straight ahead L3, or U-turn L1, left turn L2, and right turn L4, or U-turn L1, straight ahead L3, and right turn L4. Alternatively, when the intersection is a straight ahead intersection, the passable directions may include U-turn L1 and straight ahead L3, or when the intersection is a left turn intersection, the passable directions may include U-turn L1 and left turn L2, or when the intersection is a right turn intersection, the passable directions may include U-turn L1 and right turn L4.

[0042] The intersection in the following embodiments of the present disclosure includes at least one in-degree road and one out-degree road, that is, includes at least one passable direction.

[0043] In order to enable those skilled in the art to more clearly understand the solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be described below in conjunction with the accompanying drawings in the embodiments of the present disclosure.

[0044] The terms "first", "second", etc. in this disclosure are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features.

[0045] The embodiments of the present disclosure provide a method for obtaining lighting control information, which is described in detail below with reference to the accompanying drawings.

[0046] See FIG. 2 , which is a flow chart of a method for acquiring lighting control information provided by an embodiment of the present disclosure.

[0047] The method comprises the following steps:

[0048] S11: Obtain driving trajectories of multiple sample vehicles passing through a target intersection within a target time period to obtain a driving trajectory set.

[0049] In the embodiment of the present disclosure, in order to accurately confirm whether there is traffic light control information for each passable direction of the intersection, a large number of driving trajectories need to be analyzed, so it is necessary to collect driving trajectories. The more sufficient the number of driving trajectories in the driving trajectory set, the higher the reliability of the mining results.

[0050] It is understood that the acquired driving trajectories of multiple sample vehicles passing through the target intersection during the target time period, i.e., the driving trajectory set itself, do not require the additional operation of constructing a driving trajectory set in the disclosed embodiment. Of course, to facilitate data storage, a new dataset can also be created and the multiple acquired driving trajectories can be stored in this dataset, which is also reasonable.

[0051] Please also refer to Figure 3, which is a second scenario diagram provided by an embodiment of the present disclosure.

[0052] During the in-vehicle navigation process, the in-vehicle navigation device can send trajectory data to the navigation server 10 with the authorization of the user. The trajectory data may include identification information, a sequence of GNSS position data, and time information corresponding to each GNSS position data. The identification information is used to distinguish the sample vehicles that provide the trajectory data. In one possible implementation, the identification information can be a unique identifier of the user of the navigation application. The time information is used to identify the acquisition time of the corresponding GNSS position data. The sample vehicle trajectory data includes a sequence of multiple GNSS position data, so the trajectory data of a group of sample vehicles can represent the driving trajectory of the sample vehicle.

[0053] For example, the driving trajectory of a sample vehicle includes a set of trajectory data, which can be specifically expressed as: [M, (T1, L1), (T2, L2), ..., (T n , L n )].

[0054] M is identification information, L i is the GNSS position data, T i For L i Corresponding time information, i=1, 2, ...n, n is a positive integer.

[0055] By analyzing the driving trajectory, it is possible to determine whether the vehicle has stopped and the average speed of the vehicle within a specified time.

[0056] For example, when L1 and L2 are the same GNSS position data at two different times T1 and T2, it indicates that the vehicle has stopped during the period T1-T2; for another example, the vehicle's moving distance during the period T1-T2 can be determined based on L1 and L2, and the driving time can be determined based on T1 and T2. The average speed of the vehicle during the period T1-T2 can be determined based on the ratio of the moving distance to the driving time.

[0057] It is understandable that the above representation of the driving trajectory is only for the convenience of understanding and does not constitute a limitation on the technical solution of the present disclosure. In actual applications, those skilled in the art may use other methods to represent the driving trajectory.

[0058] GNSS may include the global positioning system (GPS), the global navigation satellite system (GLONASS), the Beidou navigation satellite system (BDS), the quasi-zenith satellite system (QZSS) and / or the satellite-based augmentation system (SBAS), etc., and is not specifically limited in this disclosure.

[0059] The navigation server 10 can store the acquired trajectory data locally, that is, the navigation server 10 stores the driving trajectories of multiple sample vehicles. When the data mining server 20 executes the method of the embodiment of the present disclosure and requests to acquire the driving trajectories of multiple sample vehicles, the navigation server 10 sends the driving trajectories of multiple sample vehicles to the data mining server 20. After the data mining server 20 acquires the driving trajectories of multiple sample vehicles, it also acquires a driving trajectory set.

[0060] The driving trajectory set includes multiple driving trajectories, each driving trajectory includes a set of trajectory data, and each driving trajectory corresponds to a sample vehicle.

[0061] Alternatively, the navigation server 10 may proactively forward the driving trajectories of multiple sample vehicles to the data mining server 20, which will store the driving trajectories. When the data mining server 20 executes the method of the embodiment of the present disclosure, it calls the driving trajectories of multiple sample vehicles stored locally to obtain a driving trajectory set.

[0062] The disclosed embodiments do not impose specific limitations on the length of the target time period or the specific time window. In practical applications, to ensure sufficient trajectory data is obtained, the target time period can be set to a longer period, such as 30 days. Furthermore, to improve the timeliness of the acquired lighting control information, the target time period can be set to the latest 30 days. In other words, the target time period can end on or near the current date.

[0063] S12: Determine, from the set of driving trajectories, the number of first-category trajectories corresponding to each passable direction of the target intersection, and the total number of driving trajectories corresponding to each passable direction.

[0064] The driving trajectories in the embodiments of the present disclosure can be divided into two categories, including the first category of trajectories and the second category of trajectories. The first category of trajectories is the driving trajectories in which the vehicle stops at the target intersection, and the second category of trajectories is the driving trajectories in which the vehicle does not stop at the target intersection.

[0065] In a possible implementation, the number of first-category trajectories corresponding to each passable direction may be determined first, and then the total number of driving trajectories corresponding to each passable direction may be determined.

[0066] In another possible implementation, the total number of driving trajectories corresponding to each passable direction may be determined first, and then the number of first-category trajectories corresponding to each passable direction may be determined.

[0067] In another possible implementation, the total number of driving trajectories corresponding to each passable direction can be determined first, and then the number of second-category trajectories corresponding to each passable direction can be determined. The total number of driving trajectories corresponding to each passable direction can be subtracted from the number of second-category trajectories to determine the number of first-category trajectories corresponding to each passable direction.

[0068] In another possible implementation, the number of first-category trajectories and the number of second-category trajectories corresponding to each passable direction may be determined first, and the number of first-category trajectories and the number of second-category trajectories may be added together to determine the total number of driving trajectories corresponding to each passable direction.

[0069] See FIG4 , which is a third schematic diagram of a scenario provided in an embodiment of the present disclosure.

[0070] FIG4 illustrates the target intersection as an example of a crossroads. When the target intersection is another type of intersection, the implementation method is similar and will not be described in detail here.

[0071] According to the in-degree roads and out-degree roads, the accessible directions of the target intersection can be divided into U-turn, left turn, straight ahead and right turn.

[0072] The trajectory set includes S1 trajectories. S1 = n + m + i + j, where n, m, i, and j are the number of trajectories corresponding to U-turns, left turns, straight ahead, and right turns, respectively. n, m, i, and j are all positive integers. Each trajectory corresponds to a set of trajectory data, which corresponds to a sequence of GNSS position data for a sample vehicle.

[0073] There are n driving trajectories corresponding to the U-turn direction in Figure 4, which are from a1 to a n ; There are m driving trajectories corresponding to the left turn direction, namely b1 to b m ; There are i driving trajectories corresponding to the straight direction, namely c1 to c i ; There are j driving trajectories corresponding to the right turn direction, namely d1 to d j .

[0074] Determine the number of first-category trajectories corresponding to each traversable direction. For example, the number of first-category trajectories corresponding to a U-turn direction is N, the number of first-category trajectories corresponding to a left turn direction is M, the number of first-category trajectories corresponding to a straight direction is I, and the number of first-category trajectories corresponding to a right turn direction is J. N, M, I, and J are all positive integers.

[0075] S13: For each passable direction, calculate a first ratio of the number of first-category trajectories corresponding to the passable direction to the total number of driving trajectories corresponding to the passable direction.

[0076] The first ratio is used to represent the proportion of driving trajectories with parking behaviors before the intersection in each passable direction of the target intersection.

[0077] For example, the number of first-type trajectories corresponding to the U-turn direction is N, and there are n driving trajectories corresponding to the U-turn direction, then the first ratio corresponding to the U-turn direction is N / n;

[0078] The number of the first type of trajectories corresponding to the left turn direction is M, and there are m driving trajectories corresponding to the left turn direction, so the first ratio corresponding to the left turn direction is M / m;

[0079] The number of first-type trajectories corresponding to the straight direction is I, and there are i driving trajectories corresponding to the straight direction, then the first ratio corresponding to the straight direction is I / i;

[0080] The number of first-type trajectories corresponding to the right turn direction is J, and there are j driving trajectories corresponding to the right turn direction, so the first ratio corresponding to the right turn direction is J / j.

[0081] S14: When the first ratio is greater than the first preset ratio, it is determined that light control information exists in the passable direction.

[0082] Ideally, the stopping behavior in the disclosed embodiments is caused by the presence of traffic light control information. For example, when a sample vehicle drives to an intersection, the traffic light at the intersection is red, and the sample vehicle needs to stop at the intersection, causing the corresponding driving trajectory of the sample vehicle to become a first-class trajectory. Therefore, when a first-class trajectory exists in a certain passable direction of the target intersection, it can be indicated that the target intersection has traffic light control information in that passable direction.

[0083] However, in actual applications, there may be other unexpected situations that cause the sample vehicle to stop in a passable direction without light control information. These unexpected situations may include but are not limited to roadside parking, vehicle breakdown, congested parking caused by heavy traffic, traffic accidents, emergency avoidance of obstacles, etc. In this case, the driving trajectory of the sample vehicle will also be judged as the first type of trajectory.

[0084] To overcome the misjudgment caused by the above situation, the solution of the embodiment of the present disclosure determines whether light control information exists in a certain passable direction based on the ratio of the number of first-category tracks corresponding to the passable direction to the total number of driving tracks corresponding to the passable direction. Specifically, in the solution of the embodiment of the present disclosure, the ratio of the number of first-category tracks corresponding to the passable direction to the total number of driving tracks corresponding to the passable direction is determined as a first ratio. When the first ratio is greater than a first preset ratio, it is determined that light control information exists in the passable direction.

[0085] For example, for the intersection shown in FIG4 , the first ratio corresponding to the U-turn direction is N / n. When N / n is greater than the first preset ratio, it is determined that there is light control information in the U-turn direction.

[0086] The embodiments of the present disclosure do not specifically limit the first preset ratio. In actual applications, the first preset ratio may be related to conditions such as the traffic volume at the target intersection, the number of lanes at the target intersection, and the duration of each light state of the signal light at the target intersection. Through extensive testing and verification, the present disclosure provides a recommended value range of 0.05-0.15 for the first preset ratio. For example, a value of 0.1 may be used, but this does not constitute a limitation on the technical solution of the present disclosure. In order to determine the first preset ratio, the driving trajectories of several trafficable directions at several intersections with light control information can be collected and analyzed in advance to obtain the first preset ratio.

[0087] For example, for a certain passable direction at a certain intersection, it is known that there is light control information in the passable direction. Then, the driving trajectories of sample vehicles passing through the target intersection within a target time period, such as the last 30 days, are collected. By processing the trajectory data, the ratio of the number of first-category trajectories corresponding to the passable direction and the total number of driving trajectories corresponding to the passable direction is determined. Similarly, multiple ratios are obtained by performing data analysis on the passable directions with light control information at multiple other intersections. Then, the multiple ratios obtained are appropriately optimized and adjusted in combination with the actual situation, and finally a first preset ratio can be obtained. The first preset ratio can be used as a basis for determining whether there is light control information in the passable direction.

[0088] In summary, through the solution provided by the embodiment of the present disclosure, the driving trajectory of the sample vehicle is used to mine the lighting control information of the target intersection, which can obtain the lighting control information in a timely, accurate and efficient manner. Since the solution does not require manual information collection, the labor cost is significantly reduced. Continuing to refer to Figure 3, when the data mining server 20 uses the solution of the present disclosure to obtain the lighting control information of the target intersection, or updates the lighting control information of the target intersection, the data mining results can be sent to the navigation server 10. The navigation server 10 can update the road network database based on the data mining results, and when performing subsequent in-vehicle navigation, the previous data mining results can be used to enable the navigation interface of the navigation device to be displayed accordingly, thereby providing prompts to the user.

[0089] The following describes the specific implementation method.

[0090] Refer to FIG5 , which is a flow chart of another method for acquiring lighting control information provided by an embodiment of the present disclosure.

[0091] The method comprises the following steps:

[0092] S21: Obtain the initial trajectory set within the target time period.

[0093] The initial trajectory set includes the driving trajectories of multiple sample vehicles within the target time period.

[0094] The disclosed embodiments do not impose specific limitations on the length of the target time period or the specific time window. For example, the driving trajectories of each sample vehicle over a 30-day period can be obtained to form an initial trajectory set. This initial trajectory set can include driving trajectories on different roads, from which it is necessary to filter out usable driving trajectories, specifically those that pass through the target intersection.

[0095] S22: Match the driving trajectory passing through the target intersection from the initial trajectory set to obtain a driving trajectory set.

[0096] The target intersection in the embodiment of the present disclosure may be an intersection where it is currently being determined whether or not there is traffic light control information, or an intersection where traffic light control information is to be updated, and the embodiment of the present disclosure does not make any specific limitation.

[0097] In one possible implementation, static road data can be combined to select an intersection with traffic lights and use the intersection as the target intersection to determine whether there is traffic light information in each passable direction at the intersection or to update the traffic light information in each passable direction at the intersection.

[0098] In another possible implementation, when selecting an intersection, it is not known whether there is a traffic light at the intersection. The method of the embodiment of the present disclosure is used to determine whether there is light control information in each passable direction at the intersection. After determining that there is light control information in at least one passable direction, it can also be determined that there is a traffic light at the intersection.

[0099] In order to obtain the driving trajectory set, in one possible implementation, the roads connected to the target intersection can be determined, and then the multiple initial trajectories included in the initial trajectory set are matched using a road matching algorithm to obtain the driving trajectory passing through the target intersection.

[0100] Among them, the road matching algorithm can calculate the degree of matching between the coordinate position sequence of the road (the coordinate position sequence may include the coordinate position sequence of the target intersection) and the coordinate position sequence in the trajectory data. When the degree of matching between the two meets the matching degree requirements, it indicates that the driving trajectory and the road can basically fit, and the driving trajectory passes through the road.

[0101] S23: Obtaining trajectory data of each driving trajectory in the driving trajectory set within a first preset distance before the target intersection.

[0102] The trajectory data corresponding to each driving trajectory includes the trajectory data of the vehicle on the in-degree road before the target intersection, and the trajectory data of the vehicle on the out-degree road after passing the target intersection. When determining whether there is parking behavior at the intersection, the present disclosure only uses the trajectory data of the vehicle before the target intersection.

[0103] The embodiments of this disclosure do not impose specific limitations on the first preset distance. In practical applications, this first preset distance should be reasonably set. A longer setting will increase the computational effort, while a shorter setting may reduce the accuracy of the lighting control information mining results. Through extensive testing and verification, this disclosure recommends a first preset distance range of 50 to 120 meters, but this does not constitute a limitation on the solution.

[0104] S24: Determine a first type of trajectory according to the trajectory data corresponding to each driving trajectory.

[0105] The driving trajectories in the embodiments of this disclosure can be divided into two categories: the first category is the driving trajectories that have stopped at the target intersection, and the second category is the driving trajectories that have not stopped at the target intersection. In the embodiments of this disclosure, each driving trajectory can only belong to one of the first and second categories.

[0106] In the solution of the embodiment of the present disclosure, when the driving trajectory meets one or more of the preset conditions, the driving trajectory is determined to be a first-category trajectory. The preset conditions may be:

[0107] There is trajectory data in the driving trajectory with a speed of zero and a duration greater than a first preset time period;

[0108] The driving trajectory contains trajectory data in which the moving distance within the second preset time is less than the second preset distance.

[0109] The following example illustrates that the trajectory data in the driving trajectory is represented as: [M, (T1, L1), (T2, L2), ..., (T n , L n )].

[0110] M is identification information, L i is the GNSS position data, T i is the time information corresponding to Li, i=1, 2,…n, and n is a positive integer.

[0111] When there is GNSS position data in the trajectory data that is fixed and lasts for more than the first preset time, it is determined that there is trajectory data in the driving trajectory with a speed of zero and lasting for more than the first preset time period. For example, L1=L2=…=L 20 , and T 20 If the time length between T1 and T2 is greater than the first preset time, the current driving trajectory can be determined as a first type of trajectory.

[0112] Similarly, the second preset time is 10 seconds, and the two adjacent time information T i and T i+1 The time interval is 1 second. j and L j+10 When the determined moving distance is less than the second preset distance, it is determined that there is trajectory data in the driving trajectory at this time in which the moving distance within the second preset time is less than the second preset distance.

[0113] In the embodiments of the present disclosure, there is no specific limitation on the first preset time, the second preset time, the second preset distance, etc., and those skilled in the art may determine them according to actual circumstances.

[0114] Among them, if the first preset time and the second preset time are set too short, or the second preset distance is set too long, the error caused by accidental situations may increase. Through a large number of tests and verifications, the present disclosure gives a recommended value range of 5-15 seconds for the first preset time, a recommended value range of 5-15 seconds for the second preset time, and a recommended value range of 0.2 meters to 2 meters for the second preset distance, but this does not constitute a limitation on the solution.

[0115] For example, based on the GNSS position information and time information in the trajectory data, a driving trajectory with a speed of 0 and a duration greater than 10 seconds, and a driving trajectory with a moving distance of less than 1 meter within 10 seconds, are determined to be the first type of trajectory. The first type of trajectory is a driving trajectory with parking behavior.

[0116] In practical applications, for a certain passable direction at a certain intersection, it is known that traffic light control information exists in that passable direction. Then, the driving trajectories of sample vehicles in that passable direction within a target time period, such as the last 30 days, are collected. By processing the trajectory data in the driving trajectories, it is possible to determine the duration of the sample vehicles' stops in that passable direction, or the duration and distance of their extremely slow driving. Similarly, the same data analysis can be performed on multiple other passable directions at other intersections with traffic light control information. After combining the driving trajectories of a large number of sample vehicles, the values ​​of the first preset time, the second preset time, and the second preset distance can be determined.

[0117] In one possible implementation, each driving trajectory in the driving trajectory set may be classified according to the passable direction to obtain a driving trajectory corresponding to each passable direction. Then, trajectory data for each driving trajectory corresponding to each passable direction within a first preset distance before the target intersection is determined.

[0118] For example, referring to FIG4 , it is determined that there are n driving trajectories corresponding to U-turn directions, m driving trajectories corresponding to left turns, i driving trajectories corresponding to straight travel, and j driving trajectories corresponding to right turns. Trajectory data for the n driving trajectories in the U-turn direction within a first preset distance before the target intersection is then obtained; trajectory data for the m driving trajectories in the left turn direction within a first preset distance before the target intersection is obtained; trajectory data for the i driving trajectories in the straight travel direction within a first preset distance before the target intersection is obtained; and trajectory data for the j driving trajectories in the right turn direction within a first preset distance before the target intersection is obtained.

[0119] S25: Classify according to the passable directions to obtain the number of first-category trajectories corresponding to each passable direction and the total number of driving trajectories.

[0120] Classify each first-category trajectory according to the passable direction to obtain the number of first-category trajectories corresponding to each passable direction, and classify each driving trajectory in the driving trajectory set according to the passable direction to obtain the total number of driving trajectories corresponding to each passable direction.

[0121] In a possible implementation, each first-category trajectory is classified using the in-degree road and the out-degree road as key values ​​to determine the traversable direction corresponding to each first-category trajectory.

[0122] Continuing with the scenario diagram shown in FIG4 , the description is given.

[0123] The driving trajectory set includes S1 driving trajectories, each of which corresponds to a set of trajectory data. That is, the driving trajectory set includes S1 sets of trajectory data. In step S24, the total number S2 of first-category trajectories included in the S1 set of trajectory data is determined. Then, the traversable directions corresponding to the S2 first-category trajectories are determined.

[0124] Each set of trajectory data includes a sequence of GNSS position data for multiple trajectory points. Based on the positions of the trajectory points, the corresponding traversable direction of the driving trajectory can be determined. For example, in Figure 4, if the in-degree road is a south-to-north road, and after passing the target intersection, the trajectory point is located on the out-degree road after turning left, then the corresponding traversable direction of the driving trajectory can be determined to be a left turn. For another example, if the trajectory point is located on the out-degree road after going straight after passing the target intersection, then the corresponding traversable direction of the driving trajectory can be determined to be straight ahead.

[0125] S26: Determine a first ratio as the ratio of the number of the first type of trajectories in the first traveling direction to the total number of the driving trajectories in the first traveling direction.

[0126] In the embodiment of the present disclosure, the passable directions of the target intersection can be a U-turn, a left turn, a straight ahead, or a right turn, and the first passable direction is any one of the passable directions.

[0127] For the first traveling direction, a ratio of the number of first-type trajectories in the first traveling direction to the total number of driving trajectories in the first traveling direction is determined as a first ratio.

[0128] Continuing with the above example, for example, when the first traveling direction is a U-turn, the number of first-type trajectories corresponding to the U-turn is N, and the total number of driving trajectories corresponding to the U-turn is n, then the first ratio corresponding to the U-turn is N / n.

[0129] S27: Whether the first ratio is smaller than the second preset ratio.

[0130] If not, execute S28; if so, execute S33.

[0131] The embodiment of the present disclosure does not specifically limit the second preset ratio. In actual applications, the second preset ratio may be related to conditions such as the traffic volume at the target intersection, the number of lanes at the target intersection, and the duration of each light state of the signal light at the target intersection. Through a large number of tests and verifications, the present disclosure provides a recommended value range of 0.005-0.02 for the second preset ratio, for example, a value of 0.01, but this does not constitute a limitation on the technical solution of the present disclosure. When the first ratio is less than the second preset ratio, it can be determined that the vehicle does not need to stop in the direction of travel at the target intersection. Even if a stop occurs occasionally, it is due to an unexpected situation, not due to the existence of light control information.

[0132] S28: Whether the first ratio is greater than a first preset ratio.

[0133] If not, execute S29; if so, execute S34.

[0134] The embodiment of the present disclosure does not make any specific limitation on the first preset ratio. In actual applications, the first preset ratio may be related to conditions such as the traffic volume at the target intersection, the number of lanes at the target intersection, and the duration of each light state of the signal light at the target intersection. Through a large number of tests and verifications, the present disclosure provides a recommended value range of 0.05-0.15 for the first preset ratio, for example, a value of 0.1, but this does not constitute a limitation on the technical solution of the present disclosure. When the first ratio is greater than the first preset ratio, it can be determined that more vehicles need to stop in the direction of travel of the target intersection, and the parking behavior is not due to an unexpected situation, but is caused by the existence of light control information in the direction of travel at the target intersection.

[0135] S29: Divide each first-category trajectory in the first traffic direction into different preset time periods according to the time when the sample vehicles corresponding to each first-category trajectory in the first traffic direction pass through the target intersection.

[0136] When the first ratio is greater than or equal to the second preset ratio and less than or equal to the first preset ratio, it indicates that the target intersection may have time-sharing traffic light control information in the first direction of travel, that is, there may be traffic light control information in some preset time periods and no traffic light control information in other preset time periods.

[0137] For example, if the road is near a school, there is traffic light control information in the first direction of traffic during the school hours and the school dismissal hours, but no traffic light control information in the first direction of traffic during other time periods. The reasons for the occurrence of time-sharing traffic light control information may also be other reasons, which will not be elaborated in detail in the present embodiment.

[0138] Due to the existence of time-sharing light control information, the proportion of the first type of trajectory may be relatively high, but not enough to reach the first preset ratio. Therefore, the solution implemented in the present disclosure classifies the first type of trajectories in the first traffic direction according to time for further judgment.

[0139] According to the data of each first-category trajectory in the first travel direction, the time when the vehicle passes the target intersection can be determined, and the time is used as the basis for classification, and classification is performed in units of hours.

[0140] Each preset time period is the result of dividing the entire day. In one possible implementation, the number of first-category trajectories in the first traffic direction within each hour can be determined by dividing the entire day into (0:00, 1:00), [1:00, 2:00), ..., [23:00, 24:00], with each hour as a preset time period.

[0141] In another possible implementation, the division method can be adjusted. For example, the division method can be (0:30, 1:30), [1:30, 2:30), ..., [23:30, 0:30 (next day)], with each hour as a preset time period, to determine the number of first-category trajectories in the first traffic direction within each hour.

[0142] In addition, other methods may be used to divide the time into multiple preset time periods, for example, dividing the time into two hours as a preset time period, which will not be described in detail in the embodiment of the present disclosure.

[0143] In a possible implementation, the embodiment of the present disclosure may adopt a plurality of different preset time period division methods to perform the calculation process of S30-S31 multiple times to determine more accurate lighting control information. The embodiment of the present disclosure only describes the process once.

[0144] S30: Determine a second ratio of the number of first-type trajectories corresponding to the first traveling direction to the total number of driving trajectories corresponding to the first traveling direction within each preset time period.

[0145] For example, in the preset time period [11:00, 12:00), the number of first-type trajectories corresponding to the first traffic direction is N1, and the total number of driving trajectories corresponding to the first traffic direction is N0. The second ratio at this time is N1 / N0.

[0146] Calculation is performed for each preset time period to determine the second ratio corresponding to each preset time period.

[0147] S31: Is there at least one preset time period in which the second ratio corresponding to the second ratio is greater than the third preset ratio?

[0148] If so, execute S32; otherwise, execute S33.

[0149] For each preset time period, when the second ratio of the preset time period is greater than the third preset ratio, it is determined that there is light control information in the passable direction within the preset time period; when the second ratio is less than or equal to the third preset ratio, it is determined that there is no light control information in the passable direction within the preset time period.

[0150] The third preset ratio is not specifically limited in the embodiment of the present disclosure. Through a large number of tests and verifications, the recommended range of the third preset ratio is 0.10-0.20, for example, 0.15, but this does not constitute a limitation on the technical solution of the present disclosure.

[0151] When the second ratio corresponding to a certain preset time period is greater than the third preset ratio, it can be determined that within the preset time period, more vehicles need to stop in the direction of travel of the target intersection, and the parking behavior is not due to an accident, but because the target intersection has traffic control information in the first direction of travel within the preset time period.

[0152] When there is no second ratio corresponding to a preset time period greater than the third preset ratio, that is, when the corresponding ratios in all preset time periods are less than the third preset ratio, it can be determined that there is no light control information for the vehicle in the first travel direction of the target intersection.

[0153] S32: Light control information exists in the first traffic direction within at least one preset time period.

[0154] S33: There is no traffic light control information in the first traffic direction.

[0155] In one possible implementation, when selecting the target intersection in S22, an intersection with a traffic light is selected based on the static data of the road, but at this time it is determined that there is no light control information in the first direction of travel, then it can be determined that the traffic light at the current intersection in the first direction of travel is a black light or a flashing yellow light or is in a stopped state.

[0156] S34: There is traffic light control information in the first traffic direction.

[0157] The solution of the disclosed embodiment can determine whether traffic light information exists for different traversable directions and is applicable to both left-hand drive and right-hand drive areas. For example, if the target intersection is in a left-hand drive area, the above solution can be used to determine whether traffic light information exists for a left turn at the target intersection; for another example, if the target intersection is in a right-hand drive area, the above solution can be used to determine whether traffic light information exists for a right turn at the target intersection.

[0158] The order of the steps in the embodiment of the present disclosure is for the convenience of explanation and does not constitute a limitation on the technical solution of the present disclosure. In actual application, those skilled in the art can adjust the order of the steps, which is described in detail below.

[0159] For example, the order of steps S27 and S28 can be swapped, that is, first determine whether the first ratio is greater than the first preset ratio, and when the first ratio is less than or equal to the first preset ratio, then determine whether the first ratio is less than the second preset ratio.

[0160] For another example, the step of determining the total number of driving trajectories corresponding to each passable direction in S25 can be performed in any order after S24 and before S26.

[0161] For another example, in S24-S25 above, all first-category trajectories are first determined from the set of driving trajectories, and then the first-category trajectories corresponding to each passable direction are obtained by classifying them according to the passable direction. In another possible implementation, the passable direction corresponding to each driving trajectory in the set of driving trajectories can be first determined, that is, the total number of driving trajectories corresponding to each passable direction is determined, and then the first-category trajectories among all driving trajectories corresponding to each passable direction are determined. In this case, S24-S25 can be replaced by:

[0162] S24A: Classify each driving trajectory in the driving trajectory set according to the passable direction to obtain the total number of driving trajectories corresponding to each passable direction.

[0163] S25A: Obtaining trajectory data of each driving trajectory corresponding to each passable direction within a first preset distance before the target intersection.

[0164] S25B: Based on the trajectory data corresponding to each driving trajectory, a driving trajectory having a zero speed for a duration greater than a first preset time and a driving trajectory having a moving distance less than a second preset distance within a second preset time are determined as first-category trajectories in the corresponding passable direction, so as to obtain the number of first-category trajectories corresponding to each passable direction.

[0165] For the description of the first preset distance, the second preset distance, the first preset time and the second preset time, please refer to the above steps and will not be repeated here.

[0166] For another example, when determining whether time-sharing traffic light control information exists at the target intersection in S30 above, the ratio of the number of first-type trajectories in the first traffic direction within each preset time period to the total number of vehicle trajectories in the first traffic direction is obtained. In another possible implementation, the following method can also be used:

[0167] S30B: Determine a third ratio of the number of first-category trajectories corresponding to the first traffic direction to the total number of first-category trajectories corresponding to the first traffic direction within each preset time period.

[0168] S31B: Is there at least one preset time period in which the third ratio corresponding to the third ratio is greater than the fourth preset ratio?

[0169] If so, execute S32; otherwise, execute S33.

[0170] The embodiment of the present disclosure does not specifically limit the fourth preset ratio.

[0171] The total number of driving trajectories corresponding to the passable directions may be large, for example, reaching tens of thousands of driving trajectories. When determining the third ratio of the number of first-category trajectories corresponding to the first passable direction to the total number of first-category trajectories corresponding to the first passable direction within each preset time period in S30B, in scenarios where time-sharing traffic light control information is present, the total number of first-category trajectories corresponding to the first passable direction will be significantly reduced relative to the total number of driving trajectories corresponding to the first passable direction, typically by at least an order of magnitude. In this scenario, the computational effort required to calculate the third ratio will be significantly reduced. This can reduce the required computing resources in scenarios where large-scale mining of road light control information is being performed.

[0172] In summary, the method provided by the embodiment of the present disclosure can obtain lighting control information in a timely, accurate, and efficient manner. Since this solution does not require manual information collection, it significantly reduces labor costs. In addition, this method can further determine whether there is time-sharing lighting control information at the target intersection, and further determine the preset time period for the existence of the lighting control information, which has good guiding significance. For example, the data mining server 20 can send the data mining results to the navigation server 10. The navigation server 10 can update the road network database based on the data mining results, and when performing subsequent in-vehicle navigation, it can use the previous data mining results and the current time to determine whether the current time is within the preset time period of time-sharing control, thereby providing users with more detailed prompt services.

[0173] Based on the lighting control information acquisition method provided in the above embodiments, the present disclosure further provides a lighting control information acquisition device, which is described in detail below with reference to the accompanying drawings.

[0174] See FIG6 , which is a schematic diagram of a lighting control information acquisition device provided by an embodiment of the present disclosure.

[0175] The illustrated device includes: an acquisition unit 61 , a first determination unit 62 and a second determination unit 63 .

[0176] The acquisition unit 61 is used to acquire the driving trajectories of multiple sample vehicles passing through the target intersection within a target time period to obtain a driving trajectory set.

[0177] The first determining unit 62 is configured to determine, from the set of driving trajectories, the number of first-category trajectories corresponding to each passable direction of the target intersection and the total number of driving trajectories corresponding to each passable direction.

[0178] In a possible implementation, the trajectory data of each driving trajectory in the driving trajectory set includes a plurality of GNSS position data and time information corresponding to each GNSS position data.

[0179] In a possible implementation, each passable direction at the target intersection may include one or more of a U-turn, a left turn, a straight ahead, or a right turn.

[0180] The first type of trajectory is the driving trajectory with parking behavior.

[0181] The second determination unit 63 is configured to calculate, for each passable direction, a first ratio of the number of first-category trajectories corresponding to the passable direction to the total number of driving trajectories corresponding to the passable direction; and when the first ratio is greater than a first preset ratio, determine that light control information exists in the passable direction.

[0182] In one possible implementation, the acquisition unit 61 is specifically configured to acquire an initial trajectory set within a target time period, where the initial trajectory set includes driving trajectories of multiple sample vehicles within the target time period, and the driving trajectories passing through the target intersection are matched from the initial trajectory set to acquire the driving trajectory set.

[0183] In one possible implementation, the first determination unit 62 includes a trajectory data acquisition module and a first-category trajectory quantity determination module. The trajectory data acquisition module is configured to acquire trajectory data for each driving trajectory in the driving trajectory set within a first preset distance before the target intersection. The first-category trajectory quantity determination module is configured to determine that a driving trajectory is a first-category trajectory when a preset condition is met, and determine the number of first-category trajectories corresponding to each traversable direction of the target intersection based on the trajectory point position of each first-category trajectory in the driving trajectory set.

[0184] Among them, the preset conditions include one or more of the following: there is trajectory data in the driving trajectory with a speed of zero and a duration greater than a first preset time period; there is trajectory data in the driving trajectory with a moving distance less than a second preset distance within a second preset time.

[0185] In one possible implementation, the trajectory data acquisition module is specifically configured to classify each driving trajectory in the driving trajectory set according to the passable direction to obtain a driving trajectory corresponding to each passable direction; and obtain trajectory data of each driving trajectory corresponding to each passable direction within a first preset distance before a target intersection.

[0186] In one possible implementation, the second determination unit 63 is also used to determine that there is no light control information in the passable direction when the first ratio is less than the second preset ratio; when the first ratio is less than or equal to the first preset ratio and greater than or equal to the second preset ratio, determine the second ratio of the number of first-type trajectories corresponding to the passable direction to the total number of driving trajectories corresponding to the passable direction within each preset time period; when the second ratio is greater than the third preset ratio, determine that there is light control information in the passable direction within the preset time period; when the second ratio is less than or equal to the third preset ratio, determine that there is no light control information in the passable direction within the preset time period; the first preset ratio is greater than the second preset ratio.

[0187] In a possible implementation, when it is determined that there is no light control information in the first traffic direction, the second determining unit 63 is further configured to determine whether the traffic light is a flashing yellow light or a permanent green light or has stopped working when there is a traffic light at the target intersection.

[0188] In a possible implementation, the target intersection is an intersection with a traffic light.

[0189] To sum up, by using the device provided by the embodiment of the present disclosure and utilizing the driving trajectory of sample vehicles to mine the light control information of the target intersection, the light control information can be obtained in a timely, accurate and efficient manner. Since this solution does not require manual information collection, it significantly reduces labor costs.

[0190] Exemplarily, the acquisition unit 61 , the first determination unit 62 , the second determination unit 63 , etc., may be implemented by hardware or software.

[0191] When implemented via software, each of the above units is an application running on a computing device, such as a computing engine. Applications can be provided as virtualization services. Virtualization services can include virtual machine (VM) services, bare metal server (BMS) services, and container services. VM services can use virtualization technology to create a virtual machine resource pool across multiple physical hosts, providing users with VMs on demand. BMS services use virtualized BMS resource pools across multiple physical hosts, providing users with BMSs on demand. Container services use virtualized container resource pools across multiple physical hosts, providing users with containers on demand. A VM is a simulated virtual computer, or logically a single computer. BMS is a scalable, high-performance computing service with computing performance comparable to traditional physical machines and secure physical isolation. Containers are a kernel virtualization technology that provides lightweight virtualization to isolate user space, processes, and resources. It should be understood that the VM service, BMS service and container service in the above-mentioned virtualization services are only specific examples. In actual applications, virtualization services can also be other lightweight or heavyweight virtualization services, which are not specifically limited here.

[0192] When implemented through hardware, the above units may include at least one computing device, such as a server. Alternatively, the above units may be implemented using an application-specific integrated circuit (ASIC) or a programmable logic device (PLD). The PLD may be a complex programmable logical device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof.

[0193] The present disclosure also provides a computing device, which is described in detail below with reference to the accompanying drawings.

[0194] See FIG7 , which is a schematic diagram of a computing device provided in an embodiment of the present disclosure.

[0195] Computing device 1000 includes a bus 1002 , a processor 1004 , a memory 1006 , and a communication interface 1008 .

[0196] The processor 1004, the memory 1006, and the communication interface 1008 communicate with each other via the bus 1002. The computing device 1000 may be a server or a terminal device. It should be understood that the present disclosure does not limit the number of processors and memories in the computing device 1000.

[0197] Bus 1002 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, among others. Buses may be classified as address buses, data buses, control buses, and the like. FIG8 illustrates a single bus line, but this does not imply a single bus or type of bus. Bus 1002 may include a path for transmitting information between various components of computing device 1000 (e.g., memory 1006, processor 1004, and communication interface 1008).

[0198] The processor 1004 may include any one or more processors such as a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (MP), or a digital signal processor (DSP).

[0199] The memory 1006 may include volatile memory, such as random access memory (RAM). The memory 1006 may also include non-volatile memory, such as read-only memory (ROM), flash memory, hard disk drive (HDD), or solid state drive (SSD).

[0200] The memory 1006 stores executable program codes, and the processor 1004 executes the executable program codes to implement the aforementioned method for acquiring lighting control information. Specifically, the memory 1006 stores instructions for executing the method for acquiring lighting control information.

[0201] The communication interface 1008 uses a transceiver module such as, but not limited to, a network interface card or a transceiver to implement communication between the computing device 1000 and other devices or a communication network.

[0202] The embodiment of the present disclosure further provides a computing device cluster, which is described in detail below with reference to the accompanying drawings.

[0203] See FIG8 , which is a schematic diagram of a computing device cluster provided in an embodiment of the present disclosure.

[0204] The computing device cluster includes at least one computing device. The computing device can be a server, such as a central server, an edge server, or a local server in a local data center. In some embodiments, the computing device can also be a terminal device such as a desktop computer, a laptop computer, or a smartphone.

[0205] As shown in Figure 8, the computing device cluster includes multiple computing devices 1000. The memory 1006 in the computing device 1000 in the computing device cluster may store the same instructions for executing the lighting control information acquisition method.

[0206] In some possible implementations, one or more computing devices 1000 in the computing device cluster may also be used to execute some instructions of the lighting control information acquisition method. In other words, a combination of one or more computing devices 1000 may jointly execute the instructions of the lighting control information acquisition method.

[0207] Figure 9 illustrates a possible implementation. As shown in Figure 9, two computing devices 1000A and 1000B are connected via a communication interface 1008. The memory in computing device 1000A stores instructions for executing the functions of acquisition unit 61. Specifically, computing device 1000A is configured to acquire the driving trajectories of multiple sample vehicles passing through a target intersection within a target time period, thereby obtaining a set of driving trajectories.

[0208] The memory in the computing device 1000B stores instructions for executing the functions of the first determining unit 62 and the second determining unit 63. In other words, the memories 1006 of the computing devices 1000A and 1000B jointly store instructions for executing the lighting control information acquisition method.

[0209] Furthermore, the computing device 1000A may also store instructions for the functions of the first determining unit 62 and the second determining unit 63 , and the computing device 1000B may also store instructions for the functions of the obtaining unit 61 .

[0210] The connection method between the computing device clusters shown in Figure 9 can be considered to be based on the fact that the lighting control information acquisition device provided by the present disclosure may involve a large number of sample vehicle driving trajectories, which may require a large amount of computing power as support, and thus may involve a large number of computing device nodes. Therefore, the functions implemented by the acquisition unit 61, the first determination unit 62, and the second determination unit 63 can be assigned to different computing devices for execution.

[0211] It should be understood that the functions of the computing device 1000A shown in FIG9 may also be completed by multiple computing devices 1000. Similarly, the functions of the computing device 1000B may also be completed by multiple computing devices 1000.

[0212] In some possible implementations, one or more computing devices in a computing device cluster may be connected via a network. The network may be a wide area network or a local area network, etc. FIG10 shows a possible implementation. As shown in FIG10 , two computing devices 1000C and 1000D are connected via a network. Specifically, the connection to the network is made via a communication interface in each computing device. In this type of possible implementation, the memory 1006 in the computing device 1000C stores instructions for executing the functions of the acquisition unit 61. At the same time, the memory 1006 in the computing device 1000D stores instructions for executing the functions of the first determination unit 62 and the second determination unit 63.

[0213] It should be understood that the functions of the computing device 1000C shown in FIG10 may also be completed by multiple computing devices 1000. Similarly, the functions of the computing device 1000D may also be completed by multiple computing devices 1000.

[0214] The embodiments of the present disclosure also provide a computer-readable storage medium. The computer-readable storage medium can be any available medium that can be stored by a computing device or a data storage device such as a data center that contains one or more available media. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a DVD (digital video disk)), or a semiconductor medium (for example, a solid-state hard disk), etc. The computer-readable storage medium includes instructions that instruct the computing device to execute the above-mentioned method for obtaining lighting control information. The embodiments of the present disclosure also provide another computer-readable storage medium. The computer-readable storage medium includes instructions that instruct the computing device to execute the above-mentioned method for obtaining lighting control information.

[0215] The present disclosure also provides a computer program product containing instructions. This computer program product can be software or a program product containing instructions that can be run on a computing device or stored on any available medium. When the computer program product is executed on at least one computing device, it causes the at least one computing device to execute the aforementioned method for acquiring lighting control information. The present disclosure also provides a computer program product containing instructions. When the computer program product is executed on at least one computing device, it causes the at least one computing device to execute the aforementioned method for acquiring lighting control information.

[0216] It should be understood that in the present disclosure, "at least one (item)" refers to one or more, and "plurality" refers to two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0217] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. The device embodiments described above are merely illustrative, wherein the units and modules described as separate components may or may not be physically separated. In addition, some or all of the units and modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art can understand and implement it without paying any creative work.

[0218] The above description is only a specific embodiment of the present disclosure. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present disclosure. These improvements and modifications should also be regarded as within the scope of protection of the present disclosure.

Claims

1. A method for obtaining lighting control information, wherein: The method comprises: Obtain the driving trajectories of multiple sample vehicles passing through the target intersection within the target time period to obtain a set of driving trajectories; Determining, from the set of driving trajectories, the number of first-category trajectories corresponding to each passable direction of the target intersection, and the total number of driving trajectories corresponding to each passable direction, wherein the first-category trajectories are driving trajectories in which parking occurs; For each passable direction, calculating a first ratio of the number of first-category trajectories corresponding to the passable direction to the total number of driving trajectories corresponding to the passable direction; When the first ratio is greater than a first preset ratio, it is determined that light control information exists in the passable direction.

2. The method according to claim 1, wherein Determining the number of first-category trajectories corresponding to each drivable direction of the target intersection from the set of driving trajectories includes: Acquire trajectory data of each driving trajectory in the driving trajectory set within a first preset distance before the target intersection; When the driving trajectory meets the preset conditions, the driving trajectory is determined to be the first type of trajectory; the preset conditions include one or more of the following: the driving trajectory contains trajectory data with a zero speed and a duration greater than a first preset time period; the driving trajectory contains trajectory data with a moving distance less than a second preset distance within a second preset time period; The number of first-category trajectories corresponding to each drivable direction of the target intersection is determined according to the trajectory point position of each first-category trajectory in the driving trajectory set.

3. The method according to claim 2, wherein: The obtaining of trajectory data of each driving trajectory in the driving trajectory set within a first preset distance before the target intersection includes: Classifying each driving trajectory in the driving trajectory set according to the passable direction to obtain a driving trajectory corresponding to each passable direction; Acquire trajectory data of each driving trajectory corresponding to each of the passable directions within a first preset distance before the target intersection.

4. The method according to any one of claims 1 to 3, wherein After calculating, for each passable direction, a first ratio of the number of first-type trajectories corresponding to the passable direction to the total number of driving trajectories corresponding to the passable direction, the method further includes: When the first ratio is less than a second preset ratio, determining that there is no light control information in the passable direction; When the first ratio is less than or equal to the first preset ratio and greater than or equal to the second preset ratio, determining a second ratio of the number of first-type trajectories corresponding to the passable direction to the total number of driving trajectories corresponding to the passable direction within each preset time period; When the second ratio is greater than a third preset ratio, it is determined that there is light control information in the passable direction within the preset time period; When the second ratio is less than or equal to a third preset ratio, determining that there is no light control information in the passable direction within the preset time period; The first preset ratio is greater than the second preset ratio.

5. The method according to any one of claims 1 to 3, wherein After calculating, for each passable direction, a first ratio of the number of first-type trajectories corresponding to the passable direction to the total number of driving trajectories corresponding to the passable direction, the method further includes: When the first ratio is less than a second preset ratio, determining that there is no light control information in the passable direction; When the first ratio is less than or equal to the first preset ratio and greater than or equal to the second preset ratio, determining a third ratio of the number of first-category trajectories corresponding to the passable direction to the total number of first-category trajectories corresponding to the passable direction within each preset time period; When the third ratio is greater than a fourth preset ratio, it is determined that there is light control information in the passable direction within the preset time period; When the third ratio is less than or equal to a fourth preset ratio, it is determined that no light control information exists in the passable direction within the preset time period.

6. The method according to claim 4 or 5, wherein: When it is determined that there is no light control information in the passable direction, or when it is determined that there is no light control information in the passable direction within each preset time period, the method further includes: When there is a traffic light at the target intersection, it is determined that the traffic light is a flashing yellow light or a permanent green light or stops working.

7. A lighting control information acquisition device, wherein: The device includes: an acquisition unit, a first determination unit and a second determination unit; The acquisition unit is used to acquire the driving trajectories of multiple sample vehicles passing through the target intersection within a target time period to obtain a set of driving trajectories; The first determining unit is configured to determine, from the set of driving trajectories, the number of first-category trajectories corresponding to each passable direction of the target intersection, and the total number of driving trajectories corresponding to each passable direction, wherein the first-category trajectories are driving trajectories in which parking behavior occurs; The second determination unit is configured to calculate, for each passable direction, a first ratio of the number of first-type trajectories corresponding to the passable direction to the total number of driving trajectories corresponding to the passable direction; and when the first ratio is greater than a first preset ratio, determine that light control information exists in the passable direction.

8. The device according to claim 7, wherein The first determining unit is configured to obtain trajectory data of each driving trajectory in the driving trajectory set within a first preset distance before the target intersection; when the driving trajectory meets a preset condition, determine that the driving trajectory is a first-category trajectory; the preset condition includes one or more of the following: the presence of trajectory data in the driving trajectory with a speed of zero and a duration greater than a first preset time period; the presence of trajectory data in the driving trajectory with a moving distance less than a second preset distance within a second preset time period; and determine the number of first-category trajectories corresponding to each passable direction of the target intersection based on the trajectory point position of each first-category trajectory in the driving trajectory set.

9. The device according to claim 7 or 8, wherein The second determining unit is further configured to: When the first ratio is less than a second preset ratio, determining that there is no light control information in the passable direction; When the first ratio is less than or equal to the first preset ratio and greater than or equal to the second preset ratio, determining a second ratio of the number of first-type trajectories corresponding to the passable direction to the total number of driving trajectories corresponding to the passable direction within each preset time period; When the second ratio is greater than a third preset ratio, it is determined that there is light control information in the passable direction within the preset time period; When the second ratio is less than or equal to a third preset ratio, determining that there is no light control information in the passable direction within the preset time period; The first preset ratio is greater than the second preset ratio.

10. A computing device cluster, wherein: The computing device cluster includes at least one computing device; The at least one computing device includes at least one processor and at least one memory, wherein the at least one memory has computer-readable instructions stored therein; The at least one processor executes the computer-readable instructions to enable the computing device cluster to execute the lighting control information acquisition method according to any one of claims 1 to 6.

11. A storage medium, wherein: The storage medium stores computer-readable instructions; The computer-readable instructions are used to implement the lighting control information acquisition method according to any one of claims 1 to 6.

12. A computer program product, wherein: The method comprises a computer program, which, when executed by at least one computing device, implements the lighting control information acquisition method according to any one of claims 1 to 6.

Images