Signal lamp countdown prediction method and device, equipment and storage medium

By acquiring and grouping historical trajectory data and determining the intersection phase information, the problem of inaccurate prediction of signal light countdown in the prior art is solved, and the prediction accuracy is improved.

CN120148272APending Publication Date: 2025-06-13BEIJING SIWEI TUXIN TECHNOLOGY CO LTD +1
View PDF 0 Cites 2 Cited by

Patent Information

Application Number
CN202510378242.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-03-27
Publication Date
2025-06-13

AI Technical Summary

Technical Problem

In the prior art, by processing real-time trajectory data for the current driving direction of the intersection, when the prediction signal light countdown is missing or insufficient, the prediction will be inaccurate.

Method used

By obtaining the historical trajectory data of the target intersection, determining the correlation relationship between each road based on the road network data, data grouping processing is performed, and the phase information of the target intersection is determined for predicting the countdown of the signal light.

Benefits of technology

Improves prediction accuracy of signal light countdown and reduces prediction errors due to insufficient real-time trajectory data.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120148272A_ABST
    Figure CN120148272A_ABST
Patent Text Reader

Abstract

The embodiment of the invention provides a signal lamp countdown prediction method and device, equipment and a storage medium. The method comprises the following steps: acquiring at least one piece of historical trajectory data of a target intersection; according to the road network data of the target intersection, determining an association relationship between roads corresponding to the historical trajectory data; according to the incidence relation between the roads corresponding to the historical track data, grouping the historical track data to obtain a grouping set; and determining phase information of the target intersection according to the historical trajectory data in each group. The method can improve the prediction accuracy of signal lamp countdown.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of map traffic technology, and in particular to a method, device, equipment and storage medium for predicting a traffic light countdown. Background Art

[0002] While driving, users can use the navigation app to learn about the countdown of traffic lights at intersections, so that they can prepare for vehicle start and route planning in advance, thereby improving traffic efficiency and safety.

[0003] In the prior art, the countdown of the traffic light at the intersection is predicted by processing the real-time trajectory data of the current driving direction of the intersection.

[0004] However, in the above process, if the real-time trajectory data of the current driving direction is missing or insufficient, the traffic light countdown prediction may be inaccurate. Summary of the invention

[0005] The embodiments of the present application provide a method, device, equipment and storage medium for predicting a traffic light countdown, which can improve the prediction accuracy of a traffic light countdown.

[0006] In a first aspect, an embodiment of the present application provides a method for predicting a traffic light countdown, comprising:

[0007] Acquire at least one historical trajectory data of the target intersection; and determine the association relationship between the roads corresponding to each of the historical trajectory data according to the road network data of the target intersection; wherein the historical trajectory data is the trajectory data of the vehicle traveling on each road under the target intersection within the historical time period; and the road network data includes the road information of all roads under the target intersection;

[0008] According to the association relationship between the roads corresponding to the historical trajectory data, each of the historical trajectory data is grouped to obtain a group set; wherein the group set includes at least one group;

[0009] The phase information of the target intersection is determined according to each historical trajectory data in each group; wherein the phase information represents the phase situation between the traffic lights in different road directions of the target intersection; and the phase information is used to predict the countdown information of the traffic lights at the target intersection.

[0010] In a possible implementation, the association relationship is a main-auxiliary road relationship in the same direction, or an opposite relationship, or a straight-through left-turn relationship in the same direction; and according to the association relationship between the roads corresponding to each of the historical trajectory data, each of the historical trajectory data is grouped to obtain a group set, including:

[0011] The historical trajectory data are grouped and processed to obtain at least one main and auxiliary road group, at least one opposite direction group, and at least one straight-through left-turn group; wherein the roads corresponding to the historical trajectory data in the main and auxiliary road group have a main and auxiliary road relationship in the same direction; the road directions corresponding to the historical trajectory data in the opposite direction group have an opposite direction relationship; and the road directions corresponding to the historical trajectory data in the straight-through left-turn group have a straight-through left-turn relationship in the same direction;

[0012] Among them, each of the main and auxiliary road groups, each of the opposite groups, and each of the straight-ahead left-turn groups constitute each of the groups in the group set.

[0013] In a possible implementation, determining the association relationship between the roads corresponding to the historical trajectory data according to the road network data of the target intersection includes:

[0014] Determine the entrance line segment corresponding to the historical trajectory data according to the road network data of the target intersection; wherein the entrance line segment represents the road shape of the road corresponding to the historical trajectory data in the entrance direction of the target intersection;

[0015] According to the import line segments corresponding to the historical trajectory data, the association relationship between the roads corresponding to the historical trajectory data is determined.

[0016] In a possible implementation, the association relationship is a subtending relationship; determining the association relationship between the roads corresponding to each of the historical trajectory data according to the import line segments corresponding to each of the historical trajectory data includes:

[0017] According to the included angle between the import line segments corresponding to each two of the historical trajectory data, the subtending relationship between the roads corresponding to each two of the historical trajectory data is determined.

[0018] In a possible implementation, the association relationship is a subtending relationship; determining the association relationship between the roads corresponding to each of the historical trajectory data according to the import line segments corresponding to each of the historical trajectory data includes:

[0019] According to the text information of the import line segments corresponding to each two of the historical trajectory data, the subtending relationship between the roads corresponding to each two of the historical trajectory data is determined; wherein the text information includes text content representing the road import direction of the import line segment.

[0020] In a possible implementation manner, determining the phase information of the target intersection according to each historical trajectory data in each group includes:

[0021] Determine the time information corresponding to the historical trajectory data according to the driving speed and position information in the historical trajectory data; wherein, the time information represents the time range during which the vehicle to which the historical trajectory data belongs waits for the traffic signal at the target intersection;

[0022] Determine the phase result corresponding to the group according to the time information corresponding to each historical trajectory data in the group; wherein, the phase result represents the phase situation between the traffic signals of the roads corresponding to each historical trajectory data in the group;

[0023] Determine the phase information of the target intersection according to the phase results corresponding to each group.

[0024] In a possible implementation manner, determining the phase result corresponding to the group according to the time information corresponding to each historical trajectory data in the group includes:

[0025] Determine the number of target vehicles and the target vehicle ratio corresponding to the group according to the time information corresponding to each historical trajectory data in the group; wherein, the number of target vehicles is the total number of all target vehicles corresponding to the group; the target vehicle is the vehicle to which two historical trajectory data whose corresponding time information meets the first preset condition belong; the target vehicle ratio is the ratio of the number of target vehicles corresponding to the group in the total number of vehicles to which all historical trajectory data in the group belong.

[0026] Determine the phase result corresponding to the group according to the number of target vehicles and the target vehicle ratio corresponding to the group.

[0027] In a possible implementation manner, determining the phase result corresponding to the group according to the number of target vehicles and the target vehicle ratio corresponding to the group includes:

[0028] If it is determined that the number of target vehicles meets the second preset condition and the target vehicle ratio meets the third preset condition, then determine that the phase result corresponding to the group represents that the traffic signals in each road direction corresponding to the group are in the same phase.

[0029] In a second aspect, an embodiment of the present application provides a prediction device for traffic signal countdown, including:

[0030] An acquisition module, configured to acquire at least one historical trajectory data of a target intersection, and determine the association relationship between the roads corresponding to each historical trajectory data according to the road network data of the target intersection; wherein, the historical trajectory data is the trajectory data of vehicles driving on each road at the target intersection during a historical time period; the road network data includes the road information of all roads at the target intersection.

[0031] A grouping module, configured to perform grouping processing on each of the historical trajectory data according to the association relationship between the roads corresponding to each of the historical trajectory data, so as to obtain a grouping set; wherein, the grouping set includes at least one grouping.

[0032] A determination module, configured to determine the phase information of the target intersection according to each historical trajectory data in each of the groupings; wherein, the phase information characterizes the phase situation between the signal lights in different road directions of the target intersection; the phase information is used to predict the countdown information of the signal lights at the target intersection.

[0033] In a possible implementation manner, the association relationship is a same-direction main and auxiliary road relationship, or an opposite-direction relationship, or a same-direction straight and left-turn relationship; the grouping module is specifically configured to: perform grouping processing on each of the historical trajectory data to obtain at least one main and auxiliary road grouping, at least one opposite-direction grouping, and at least one straight and left-turn grouping; wherein, the roads corresponding to each historical trajectory data in the main and auxiliary road grouping have a same-direction main and auxiliary road relationship; the road directions corresponding to each historical trajectory data in the opposite-direction grouping have an opposite-direction relationship; the road directions corresponding to each historical trajectory data in the straight and left-turn grouping have a same-direction straight and left-turn relationship; wherein, each of the main and auxiliary road groupings, each of the opposite-direction groupings, and each of the straight and left-turn groupings constitute each of the groupings in the grouping set.

[0034] In a possible implementation manner, the obtaining module is specifically configured to: determine the inlet segment corresponding to the historical trajectory data according to the road network data of the target intersection; wherein, the inlet segment represents the road shape of the road corresponding to the historical trajectory data in the inlet direction of the target intersection; determine the association relationship between the roads corresponding to each of the historical trajectory data according to the inlet segments corresponding to each of the historical trajectory data.

[0035] In a possible implementation manner, the association relationship is an opposite-direction relationship; the obtaining module is further specifically configured to: determine the opposite-direction relationship between the roads corresponding to every two historical trajectory data according to the included angle between the inlet segments corresponding to every two historical trajectory data.

[0036] In a possible implementation manner, the association relationship is an opposite-direction relationship; the obtaining module is further specifically configured to: determine the opposite-direction relationship between the roads corresponding to every two historical trajectory data according to the text information of the inlet segments corresponding to every two historical trajectory data; wherein, the text information includes the text content representing the road inlet direction of the inlet segment.

[0037] In a possible implementation manner, the determining module is specifically configured to: determine the time information corresponding to the historical trajectory data according to the driving speed and position information in the historical trajectory data; wherein, the time information represents the time range during which the vehicle to which the historical trajectory data belongs waits for the signal light at the target intersection; determine the phase result corresponding to the group according to the time information corresponding to each piece of historical trajectory data in the group; wherein, the phase result represents the phase situation between the signal lights of the roads corresponding to each piece of historical trajectory data in the group; determine the phase information of the target intersection according to the phase results corresponding to each group.

[0038] In a possible implementation manner, the determining module is specifically configured to: determine the number of target vehicles and the target vehicle ratio corresponding to the group according to the time information corresponding to each piece of historical trajectory data in the group; wherein, the number of target vehicles is the total number of all target vehicles corresponding to the group; the target vehicle is the vehicle to which two pieces of historical trajectory data whose corresponding time information meets the first preset condition belong; the target vehicle ratio is the ratio of the number of target vehicles corresponding to the group to the total number of vehicles to which all historical trajectory data in the group belong; determine the phase result corresponding to the group according to the number of target vehicles and the target vehicle ratio corresponding to the group.

[0039] In a possible implementation manner, the determining module is specifically configured to: if it is determined that the number of target vehicles meets the second preset condition and the target vehicle ratio meets the third preset condition, then determine that the phase result corresponding to the group represents that the signal lights in each road direction corresponding to the group are in the same phase.

[0040] In a third aspect, an embodiment of the present application provides an electronic device, including: a memory, a processor;

[0041] The memory stores computer execution instructions;

[0042] The processor executes the computer execution instructions stored in the memory, so that the processor executes the above first aspect and / or various possible implementation manners of the first aspect.

[0043] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer execution instructions are stored, and when the computer execution instructions are executed by a processor, they are used to implement the above first aspect and / or various possible implementation manners of the first aspect.

[0044] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, and when the computer program is executed by a processor, it implements the above first aspect and / or various possible implementation manners of the first aspect.

[0045] The prediction method, device, equipment and storage medium for signal lamp countdown provided by the embodiments of the present application determine the correlation relationship between the roads corresponding to each historical trajectory data under the target intersection through the road information of all roads under the target intersection, group the multiple historical trajectory data, and determine the phase conditions between the signal lamps in different road directions of the target intersection according to the grouped historical trajectory data, so as to predict the countdown of the signal lamp at the target intersection, which can improve the prediction accuracy of the signal lamp countdown. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The accompanying drawings herein are incorporated into the specification and form a part of the specification, showing embodiments consistent with the present application and used together with the specification to explain the principles of the present application.

[0047] Figure 1 FIG. 9 is a schematic diagram of an application scenario provided by the present application;

[0048] Figure 2 FIG. 13 is a schematic flowchart of a method for predicting signal lamp countdown provided by an embodiment of the present application;

[0049] Figure 3 FIG. 17 is a schematic flowchart of another method for predicting signal lamp countdown provided by an embodiment of the present application;

[0050] Figure 4 FIG. 21 is a schematic flowchart of a phase judgment process provided by an embodiment of the present application;

[0051] Figure 5 FIG. 25 is a schematic diagram of an example of an oncoming relationship provided by an embodiment of the present application;

[0052] Figure 6 FIG. 29 is a schematic diagram of an example of a data grouping scenario provided by an embodiment of the present application;

[0053] Figure 7 FIG. 33 is a schematic structural diagram of a device for predicting signal lamp countdown provided by an embodiment of the present application;

[0054] Figure 8 FIG. 37 is a schematic structural diagram of an electronic device provided by an embodiment of the present application.

[0055] Through the above accompanying drawings, the clear embodiments of the present application have been shown, and there will be more detailed descriptions hereinafter. These drawings and text descriptions are not intended to limit the scope of the concept of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0056] Exemplary embodiments will be described in detail herein, and examples thereof are shown in the accompanying drawings. When the following description refers to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0057] First, the terms involved in the present application will be explained:

[0058] Phase: For a signal display state corresponding to the simultaneous acquisition of the right of way for a group of non-conflicting traffic flows, we refer to it as the signal phase, simply called the phase.

[0059] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or fully authorized by all parties. Moreover, the processing of relevant data, such as collection, use, processing, transmission, provision, disclosure, and application, complies with relevant laws, regulations, and standards, takes necessary confidentiality measures, does not violate public order and good customs, and provides corresponding operation entrances for users to choose to authorize or refuse.

[0060] In addition, the present application involves big data analysis of user information (including but not limited to personal biometric characteristics, identity data, consumption data, asset data, electronic terminal operation data, etc.), and uses artificial intelligence technology for automated decision-making. For technical solutions that make decisions having a significant impact on personal rights and interests based on the results of automated decision-making, corresponding operation entrances are provided for users to choose to agree or refuse the results of automated decision-making; if the user chooses to refuse, the expert decision-making process will be entered.

[0061] It should be noted that the present application can be used in the field of map traffic technology, and can also be used in any field other than map traffic technology. The application field of the present application is not limited.

[0062] Figure 1 FIG. is a schematic diagram of an application scenario provided for the present application. As Figure 1 shown, the specific application scenario of the present application is as follows: When user 101 is driving, he can obtain the countdown of the traffic lights at the intersection through a navigation application in an electronic device 102 such as a vehicle or a mobile phone, so as to prepare in advance for vehicle startup and route planning, and improve traffic efficiency and traffic safety.

[0063] Combined with the above scenarios, in the prior art, by processing the real-time trajectory data of the current driving direction at an intersection, the countdown of the traffic lights at the intersection is predicted. There is a technical problem that if the real-time trajectory data of the current driving direction is missing or insufficient, it may lead to inaccurate prediction of the traffic light countdown.

[0064] The prediction method of the traffic light countdown provided by this application determines the association relationship between the roads corresponding to each historical trajectory data under the target intersection according to the road information of all roads under the target intersection, groups multiple historical trajectory data, and determines the phase situation between the traffic lights in different road directions of the target intersection based on the grouped historical trajectory data, so as to predict the countdown of the traffic lights at the target intersection, and solves the technical problem of inaccurate prediction of the traffic light countdown.

[0065] The following uses specific embodiments to elaborate in detail on the technical solution of this application and how the technical solution of this application solves the above technical problems. These several specific embodiments below can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of this application will be described below in conjunction with the accompanying drawings.

[0066] Figure 2 It is a schematic flowchart of a prediction method for the traffic light countdown provided by an embodiment of this application. As Figure 2 shown, the method includes:

[0067] 201. Obtain at least one historical trajectory data of the target intersection, and determine the association relationship between the roads corresponding to each historical trajectory data according to the road network data of the target intersection; wherein, the historical trajectory data is the trajectory data of vehicles driving on each road under the target intersection during a historical time period; the road network data includes the road information of all roads under the target intersection.

[0068] Exemplarily, the execution subject of this embodiment can be an electronic device. The electronic device can hereinafter be simply referred to as a device, and the device can be a physical device or a virtual device for executing the prediction method of the traffic light countdown. For each intersection among all intersections within a certain target geographical area, that is, the target intersection, the device can obtain the trajectory data of vehicles driving on each road under each target intersection during a historical time period by calling a data transmission interface or the like, and obtain at least one historical trajectory data. For example, multiple historical trajectory data of each target intersection can be obtained through a high-frequency data collection method (time interval is 1 second or 0.5 second) by a data collection device for subsequent processing.

[0069] After obtaining multiple historical trajectory data, the device can obtain the road information of all roads under the target intersection, that is, road network data, such as road shapes and road attributes, through methods such as calling data transmission interfaces. Road attributes include arterial roads, secondary arterial roads, branch roads, ramps, straight lanes, left-turn lanes, right-turn lanes, etc. It can analyze all historical trajectory data and the road information of the road corresponding to each historical trajectory data based on a preset trajectory data analysis method, perform trajectory-road network matching processing on each historical trajectory data and the road network data, obtain the road information of the road corresponding to each historical trajectory data, and then determine the association relationship between the roads corresponding to each historical trajectory data based on the road information of the road corresponding to each historical trajectory data. The association relationship can be an intersection relationship such as a crossroads or a T-junction, or a connection relationship connected by a ramp, or a parallel relationship, or a hierarchical relationship between an arterial road and a branch road.

[0070] For example, if the road shapes of the roads corresponding to two historical trajectory data are parallel and are an arterial road and a secondary arterial road in the same road direction respectively, it can be determined that there is a hierarchical relationship between the two roads. Or, if the road shapes of the roads corresponding to two historical trajectory data intersect on a plane, it can be determined that there is an intersection relationship between the two roads.

[0071] 202. Group the historical trajectory data according to the association relationship between the roads corresponding to each historical trajectory data to obtain a grouping set; where the grouping set includes at least one group.

[0072] Exemplarily, after obtaining multiple historical trajectory data, the device can analyze all historical trajectory data based on a preset trajectory data analysis method, determine the association relationship between the roads corresponding to each historical trajectory data, and group the historical trajectory data with an association relationship between the corresponding roads into one group to obtain multiple groups in the grouping set.

[0073] For example, the device can obtain the road information corresponding to each historical trajectory data through a trajectory data extraction technology combined with a road map. For example, historical trajectory data 1 corresponds to road 1, historical trajectory data 2 corresponds to road 2, historical trajectory data 3 corresponds to road 1, and historical trajectory data 4 corresponds to road 3. Then it can be determined that there is an association relationship between the road corresponding to historical trajectory data 1 and the road corresponding to historical trajectory data 3, and roads 2 and 3 are roads traveling in the same direction. Then it can be determined that there is an association relationship between the road corresponding to historical trajectory data 2 and the road corresponding to historical trajectory data 4. Group historical trajectory data 2 and historical trajectory data 4 into one group, and at the same time group historical trajectory data 1 and historical trajectory data 3 into one group.

[0074] 203. Determine the phase information of the target intersection according to each historical trajectory data in each group; wherein, the phase information characterizes the phase situation between the signal lights in different road directions of the target intersection; the phase information is used to predict the countdown information of the signal lights at the target intersection.

[0075] Exemplarily, the device analyzes and processes each historical trajectory data in each group to obtain the vehicle passing situation of each road or each road direction corresponding to each group, and then conducts a combined analysis of the vehicle passing situations corresponding to all groups to obtain the phase situation between the signal lights in different road directions of all target intersections, that is, the phase information; for example, it can be obtained that the signal lights in the road direction corresponding to group 1 and the signal lights in the road direction corresponding to group 2 are in the same phase. The device can calculate based on the signal light, such as the red and green light countdown processing program, the phase information of each target intersection obtained, the position and driving speed of the current vehicle at the target intersection, and can predict the countdown information of the signal lights at the target intersection where the current vehicle is located.

[0076] In this embodiment, a method for predicting the signal light countdown is provided. By according to the association relationship between the roads corresponding to each historical trajectory data under the target intersection, including the main and auxiliary road relationship in the same direction, or the opposite direction relationship, or the straight and left turn relationship in the same direction, multiple historical trajectory data are grouped, and according to the historical trajectory data after grouping, the phase situation between the signal lights in different road directions of the target intersection is determined to be used for predicting the countdown of the signal lights at the target intersection, which can improve the prediction accuracy of the signal light countdown; in addition, by processing a large amount of historical trajectory data, increasing the amount of trajectories to be processed and enhancing the timeliness of variable cycle recognition, the countdown prediction accuracy can be further improved.

[0077] Figure 3 For another flow chart of the method for predicting the signal light countdown provided by the embodiment of the present application, as Figure 3 shown, the method includes:

[0078] 301. Obtain at least one historical trajectory data of the target intersection, and determine the association relationship between the roads corresponding to each historical trajectory data according to the road network data of the target intersection; wherein, the historical trajectory data is the trajectory data of the vehicles driving on each road under the target intersection during the historical time period, and the road network data includes the road information of all roads under the target intersection.

[0079] Exemplarily, this step can refer to step 201, which will not be elaborated here.

[0080] In one example, determining the association relationship between the roads corresponding to each historical trajectory data according to the road network data of the target intersection in step 301 includes:

[0081] The first step is to determine the entrance segment corresponding to the historical trajectory data according to the road network data of the target intersection; wherein the entrance segment represents the road shape of the road corresponding to the historical trajectory data in the entrance direction of the target intersection.

[0082] The second step is to determine the association relationship between the roads corresponding to the historical trajectory data according to the import line segments corresponding to the historical trajectory data.

[0083] For example, Figure 4 A flow chart of a phase determination process provided in an embodiment of the present application is shown as follows: Figure 4 As shown, when the device obtains each historical trajectory data, it can also obtain the road network data corresponding to the target intersection, that is, the map road network under the target intersection, including the road shapes of all roads under the target intersection, and perform trajectory-road-network matching processing on each historical trajectory data and the road network data to obtain the road shape of the road corresponding to the historical trajectory data in the entrance direction of the target intersection, that is, the entrance segment, and determine the association relationship between the roads corresponding to each historical trajectory data according to the entrance segments corresponding to all historical trajectory data.

[0084] For example, if the road shapes represented by the two entrance line segments are parallel and have the same road direction, it can be determined that the roads corresponding to the two entrance line segments have a main-auxiliary road relationship; or, if the road shapes represented by the two entrance line segments are parallel and have different entrance directions, it can be determined that the roads corresponding to the two entrance line segments have a subtending relationship.

[0085] It is worth adding that Figure 4 Before data grouping, all historical trajectory data can be cleaned. For example, based on the historical trajectory data of vehicles at traffic lights, the number of times the vehicle stops on the road corresponding to the traffic light intersection, the duration of each stop, the parking location, and the parking start time can be calculated. Then, the vehicle trajectory data with too short parking time, too far parking location, multiple stops, and abnormal speed can be filtered according to a certain empirical threshold to obtain the cleaned historical trajectory data for subsequent data grouping processing.

[0086] In one example, the association relationship is a subtending relationship; the second step of step 301 includes: determining the subtending relationship between the roads corresponding to each two historical trajectory data according to the included angle between the import line segments corresponding to each two historical trajectory data.

[0087] Specifically, when it is determined that the association relationship between the roads corresponding to the historical trajectory data is an oncoming relationship, an angle can be formed between the import segments corresponding to every two historical trajectory data in each historical trajectory data, and the angle can be calculated. By judging the magnitude of the angle, the oncoming relationship between the roads corresponding to every two historical trajectory data can be determined. Furthermore, by judging the oncoming relationship through the angle, more missed judgments in irregular road scenarios can be reduced, and the prediction coverage rate of the intersection signal countdown can be improved.

[0088] For example, Figure 5 is a schematic diagram of an oncoming relationship example provided by an embodiment of the present application. As Figure 5 shown, every two line segments are combined to obtain multiple angles, and then it is judged which threshold condition each angle meets. Then, the two line segments corresponding to this angle are the oncoming relationship corresponding to that threshold condition. For example, when the angle is 180°, it is oncoming 1, or when the angle judgment satisfies 160° - 180°, it is a group of oncoming, such as oncoming 2. For example, the south import and the northeast import are a group of oncoming.

[0089] In one example, the association relationship is an oncoming relationship; the second step of step 301 includes: determining the oncoming relationship between the roads corresponding to every two historical trajectory data according to the text information of the import segments corresponding to every two historical trajectory data; wherein, the text information includes the text content representing the road import direction of the import segment.

[0090] Specifically, in combination with Figure 5 , when it is determined that the association relationship between the roads corresponding to the historical trajectory data is an oncoming relationship, the text information of the import segment corresponding to each historical trajectory data can be determined first, that is, the text content representing the road import direction of the import segment. The oncoming relationship can be judged according to the import directions represented by the text information corresponding to every two import segments; for example, the text information includes east import, or west import, or southeast import, or northwest import. The east import and the west import are a group of oncoming, and the southeast import and the northwest import are a group of oncoming.

[0091] It is worth adding that when it is determined that the association relationship between the roads corresponding to the historical trajectory data is an oncoming relationship, either one of the above two methods can be selected; or, both of the above two methods can be selected simultaneously, and one of the results can be selected.

[0092] 302. Group the historical trajectory data to obtain at least one main - auxiliary road group, at least one oncoming group, and at least one straight - turn group; wherein, there is a same - direction main - auxiliary road relationship between the roads corresponding to the historical trajectory data in the main - auxiliary road group; there is an oncoming relationship between the road directions corresponding to the historical trajectory data in the oncoming group; and there is a same - direction straight - turn relationship between the road directions corresponding to the historical trajectory data in the straight - turn group.

[0093] Among them, the association relationship is the relationship between main and auxiliary roads in the same direction, or the relationship between opposite directions, or the relationship between going straight and turning left in the same direction.

[0094] Among them, each main and auxiliary road group, each opposite group and each straight-ahead left-turn group constitute each group in the group set.

[0095] For example, Figure 6 A schematic diagram of an example of a data grouping scenario provided in an embodiment of the present application, such as Figure 6 As shown, combined with the actual scenario, the association relationship between the various roads at the intersection can be set as a main and auxiliary road relationship in the same direction, that is, the road corresponding to the same direction is the main road or the auxiliary road, or the association relationship can also be an opposite relationship, such as a road heading south and a road heading north, or the association relationship can also be a straight-through left-turn relationship in the same direction, such as a straight road or a left-turn road corresponding to the road heading in the same direction. The device can determine whether the road corresponding to each historical trajectory data is a main road or an auxiliary road, whether the road direction is south or north, and whether the road direction is a straight road or a left-turn road by analyzing each historical trajectory data, and merge the various historical trajectory data groups with the main and auxiliary road relationship in the same direction of the corresponding road to obtain the main and auxiliary road group corresponding to each road direction; merge the various historical trajectory data groups with the opposite relationship between the corresponding road directions to obtain the opposite group corresponding to each road direction; merge the various historical trajectory data groups with the same direction straight-through left-turn relationship between the corresponding road directions to obtain the straight-through left-turn group corresponding to each road direction, and then all the main and auxiliary road groups, all the opposite groups and all the straight-through left-turn groups obtained constitute all the groups in the group set.

[0096] For example, if the road shapes of two roads are parallel and they are respectively the main road and the secondary road in the same road direction, then it can be determined that the two roads have a main-auxiliary road relationship; or, if the road shapes of two roads are parallel and they are in different road directions, then it can be determined that the two roads have a subtending relationship; or, if the road shapes of two roads are partially parallel and one of the roads is a turning shape, or if the road shapes of two roads are partially parallel and they are respectively the straight road and the left turn road in the same road direction, then it can be determined that the two roads have a straight-ahead left turn relationship in the same direction.

[0097] 303. Determine time information corresponding to the historical trajectory data according to the driving speed and position information in the historical trajectory data; wherein the time information represents a time range in which the vehicle to which the historical trajectory data belongs waits for the traffic light at the target intersection.

[0098] Exemplarily, based on each piece of historical trajectory data, the device extracts the driving speed and location information of the vehicle in each piece of historical trajectory data, calculates the driving speed and location information of the vehicle in each piece of historical trajectory data, and then determines the time range during which the vehicle corresponding to each piece of historical trajectory data waits for the signal at the target intersection, that is, the time information corresponding to each piece of historical trajectory data, such as the time range between the time point when the vehicle changes from the driving state to the stopping state at the traffic light intersection and the time point when the vehicle changes from the stationary state to the start of the green light.

[0099] 304. Determine the phase result corresponding to the group according to the time information corresponding to each piece of historical trajectory data in the group; wherein, the phase result characterizes the phase situation between the signals of the roads corresponding to each piece of historical trajectory data in the group.

[0100] Exemplarily, in combination with Figure 4 , the device analyzes and processes the time range during which the vehicles corresponding to each piece of historical trajectory data in each group wait for the signal at the target intersection through a preset phase judgment rule, and determines the phase result corresponding to each group, that is, the phase situation between the signals of the roads corresponding to each piece of historical trajectory data in each group can be determined.

[0101] For example, for a certain group, the group contains multiple pieces of historical trajectory data corresponding to the opposite relationship between the south entrance and the north entrance of the corresponding road. Analyze and process the time range during which the vehicles corresponding to each piece of historical trajectory data in the group wait for the signal at the target intersection. If there are pieces of historical trajectory data with consistent time ranges, the pieces of historical trajectory data with consistent time ranges can be analyzed and processed. For example, input them into a preset deep learning model for processing, and output the phase situation between the signals of the south entrance and the north entrance corresponding to the group, such as whether the signals of the south entrance and the north entrance are in the same phase.

[0102] For another example, for a certain group, the group contains both multiple pieces of historical trajectory data corresponding to the opposite relationship between the south entrance and the north entrance of the corresponding road and multiple pieces of historical trajectory data corresponding to the opposite relationship between the main road and the side road of the corresponding road. Then, analyze the multiple pieces of historical trajectory data corresponding to the south entrance and the north entrance, and at the same time, analyze the multiple pieces of historical trajectory data corresponding to the main road and the side road relationship, and the phase situation between the signals of the south entrance and the north entrance of the intersection and the phase situation between the signals of the main road and the side road can be obtained simultaneously. In one example, step 304 includes the following steps:

[0103] First step: Determine the number of target vehicles and the target vehicle ratio corresponding to the group according to the time information corresponding to each historical trajectory data in the group; where the number of target vehicles is the total number of all target vehicles corresponding to the group; the target vehicle is the vehicle to which two historical trajectory data with corresponding time information meeting the first preset condition belong; the target vehicle ratio is the ratio of the number of target vehicles corresponding to the group in the total number of vehicles to which all historical trajectory data corresponding to the group belong.

[0104] Second step: Determine the phase result corresponding to the group according to the number of target vehicles and the target vehicle ratio corresponding to the group.

[0105] Exemplarily, for each group, first determine whether the time information corresponding to every two historical trajectory data meets the first preset condition according to the road direction and time information corresponding to each historical trajectory data. If it meets the first preset condition, for example, the difference in the parking time in the time information corresponding to every two historical trajectory data is within the preset range, then determine the vehicle to which the two historical trajectory data belong as the target vehicle, determine the total number of all target vehicles corresponding to each group, that is, the number of target vehicles, and determine the ratio of the number of target vehicles corresponding to each group in the total number of vehicles to which all historical trajectory data corresponding to the group belong, that is, the target vehicle ratio; according to the preset judgment rule, judge and analyze the number of target vehicles and the target vehicle ratio corresponding to each group, and then it can be obtained whether the traffic lights are in the same phase in the road direction corresponding to the association relationship corresponding to the group.

[0106] In one example, the first step of step 304 includes:

[0107] Step 1: Determine every two historical trajectory data in the group with different corresponding road directions and intersecting time information as associated data.

[0108] Step 2: Determine the difference between the parking start times corresponding to the two historical trajectory data in the associated data; where the parking start time is the time when the vehicle to which the historical trajectory data belongs starts from the parking state to after the traffic light conversion at the target intersection.

[0109] Step 3: Determine the number of target vehicles and the target vehicle ratio corresponding to the group; where the number of target vehicles is the total number of all target vehicles corresponding to the group; the target vehicle is the vehicle to which two historical trajectory data with the difference meeting the preset threshold range belong; the target vehicle ratio is the ratio of the number of target vehicles corresponding to the group in the total number of vehicles to which all historical trajectory data corresponding to the group belong.

[0110] Exemplarily, for each group, first, according to the road direction and time information corresponding to each historical trajectory data, determine historical trajectory data where every two corresponding road directions are different and the time information has an intersection as associated data pairs. Among them, the time range represented by the time information can be appropriately expanded to increase the matching hit probability. The device determines the parking start time corresponding to each historical trajectory data, that is, the time when the vehicle to which the historical trajectory data belongs starts after the signal light conversion from the parking state at the target intersection; then, calculate the difference between the parking start times corresponding to the two historical trajectory data in each associated data pair. According to each difference, determine the vehicles to which the two historical trajectory data corresponding to each difference that meets the preset threshold range belong as the target vehicles corresponding to each group, calculate the total number of all target vehicles corresponding to each group to obtain the number of target vehicles corresponding to each group, and calculate the proportion of the number of target vehicles corresponding to each group in the total number of vehicles to which all historical trajectory data corresponding to this group belong to obtain the target vehicle proportion corresponding to each group; according to the preset judgment rule, perform judgment and analysis on the number of target vehicles and the target vehicle proportion corresponding to each group, and then it can be obtained whether the signal lights in the road directions corresponding to the association relationship corresponding to this group are in the same phase.

[0111] For example, for the main and auxiliary road group, there are historical trajectory data of 4 vehicles. After pairwise association, two associated data pairs are obtained. Each associated data pair has historical trajectory data of 2 vehicles. Calculate the difference between the parking start times in the 2 historical trajectory data of each associated data pair respectively. If one difference meets the condition, then 2 vehicles meet the condition and the proportion is 50%. According to the preset rule, analyze these 2 vehicles and the proportion of 50%, and it can be determined whether the main road signal light and the auxiliary road signal light where these 2 vehicles that meet the condition are located are in the same signal phase.

[0112] In one example, the second step of step 304 includes: if it is determined that the number of target vehicles meets the second preset condition and the target vehicle proportion meets the third preset condition, then determine that the phase result corresponding to the group represents that the signal lights in each road direction corresponding to the group are in the same phase.

[0113] Specifically, the device judges the number of target vehicles and the target vehicle proportion corresponding to each group based on the second preset condition and the third preset condition in the preset rule. If it is determined that the number of target vehicles in this group meets the second preset condition and the target vehicle proportion in this group meets the third preset condition, then determine that the signal lights in each road direction where the target vehicles in this group are located are in the same phase.

[0114] For example, for the historical trajectory data of 4 vehicles in the main and auxiliary road groups, after pairwise association, two associated data pairs are obtained. Each associated data pair has the historical trajectory data of 2 vehicles. Calculate the difference between the parking start times of the 2 historical trajectory data in each associated data pair. If one difference meets the condition, then 2 vehicles meet the condition and the proportion is 50%. According to the preset rules, assuming that both the quantity and the proportion meet the conditions, it means that the main road signal light and the auxiliary road signal light where the 2 vehicles that meet the conditions are located are in the same signal phase.

[0115] It is worth adding that in the case where the number of vehicles meeting the comparison conditions is insufficient, a large time range can be selected and reasoning can be carried out according to the traffic light cycle based on the starting time of the vehicle at an earlier time, so as to reach a relatively close time range, and then compare again according to the above process; for example, according to the signal light display cycle of 1 minute, the starting time of vehicle 1 at 14:00:12 is pushed forward, for example, pushed forward by 10 one-minute intervals, which is 14:10:12, then the difference calculation comparison can be carried out with the starting time of vehicle 2 at 14:10:10. Among them, the traffic light cycle calculation method mainly analyzes the periodicity of the vehicle starting time to find out the cycle of each intersection traffic light at different times. Because the turning lights (except for right turns and U-turns) in different directions at the same intersection at the same time are generally in the same cycle, the historical trajectory data in all directions of the same intersection can be combined and analyzed, so as to improve the accuracy of cycle calculation.

[0116] Finally, if the vehicle number requirement still cannot be met, the judgment results of the oncoming direction and the main and auxiliary roads will be defaulted to the same phase, because in the case of very few vehicles at the intersection, the phase relationship at the intersection is often relatively simple and can also meet the traffic flow control effect. Furthermore, for a simple intersection, the countdown of the signal light can be predicted directly by calculating the starting time difference between the connected phases, which is helpful for predicting the signal light countdown at a simple intersection.

[0117] 305. Determine the phase information of the target intersection according to the phase results corresponding to each group.

[0118] Exemplarily, in combination with Figure 4 , the phase results corresponding to all groups under the target intersection are subjected to result merging processing, such as logically merging the results that meet the oncoming direction merging, main and auxiliary road merging, and straight and left turn merging at the same intersection, and then the complete phase judgment result of the intersection can be obtained, that is, the phase information of the signal lights in different road directions under the target intersection can be obtained.

[0119] For example, the east-west direction and the west-east direction at intersection A are in the same phase, and the straight and left turns in the east-west or west-east direction are in the same phase. Then the four directions of straight and left turns in the east-west and west-east directions at this intersection are all in the same phase.

[0120] In this embodiment, based on the above embodiment, on the one hand, by calculating the starting time differences of vehicles in opposite directions, going straight and turning left in the same direction, and on the main and auxiliary roads respectively to determine the trajectory mining method with consistent phases, and using the corresponding period inference method in the scenario with less historical trajectory data to increase the amount of data participating in the calculation, the timeliness of variable cycle recognition can be improved, the countdown prediction accuracy can be enhanced, and the coverage rate of the red light countdown release result can be increased; on the other hand, for simple intersections, the red light duration of the corresponding phase can be directly predicted by calculating the starting time difference of the connected phases. For example, in a simplest crossroads without left-turn dedicated signal lights, the signal lights of the east-west direction and the north-south direction alternate to display the signal light states to indicate vehicle passage respectively. Therefore, to predict and calculate the red light duration of the east-west phase group, it is the starting moment when the vehicles in the east-west direction change from red to green minus the starting moment when the vehicles in the north-south direction change from red to green minus a transition time for signal light switching (such as about 3 s), which is helpful for predicting the red light duration at simple intersections.

[0121] Figure 7 The following is a schematic structural diagram of a device for predicting the signal light countdown provided by an embodiment of the present application, as Figure 7 shown. The device includes:

[0122] An acquisition module 401, configured to acquire at least one historical trajectory data of a target intersection, and determine the association relationship between the roads corresponding to each historical trajectory data according to the road network data of the target intersection; wherein, the historical trajectory data is the trajectory data of vehicles traveling on each road under the target intersection during a historical time period; the road network data includes the road information of all roads under the target intersection.

[0123] A grouping module 402, configured to perform grouping processing on each historical trajectory data according to the association relationship between the roads corresponding to each historical trajectory data, to obtain a grouping set; wherein, the grouping set includes at least one group.

[0124] A determination module 403, configured to determine the phase information of the target intersection according to each historical trajectory data in each group; wherein, the phase information represents the phase situation between the signal lights in different road directions of the target intersection; the phase information is used to predict the countdown information of the signal lights of the target intersection.

[0125] In a possible implementation, the association relationship is a main-auxiliary road relationship in the same direction, or an opposite relationship, or a straight-through left turn relationship in the same direction; the grouping module 402 is specifically used to: group each historical trajectory data to obtain at least one main-auxiliary road group, at least one opposite group and at least one straight-through left turn group; wherein, the roads corresponding to each historical trajectory data in the main-auxiliary road group have a main-auxiliary road relationship in the same direction; there is an opposite relationship between the road directions corresponding to each historical trajectory data in the opposite group; there is a straight-through left turn relationship in the same direction corresponding to each historical trajectory data in the straight-through left turn group; wherein each main-auxiliary road group, each opposite group and each straight-through left turn group constitute each group in the group set.

[0126] In a possible implementation, the acquisition module 401 is specifically used to: determine the import segment corresponding to the historical trajectory data according to the road network data of the target intersection; wherein the import segment represents the road shape of the road corresponding to the historical trajectory data in the import direction of the target intersection; and determine the association relationship between the roads corresponding to each historical trajectory data according to the import segment corresponding to each historical trajectory data.

[0127] In a possible implementation, the association relationship is a subtending relationship; the acquisition module 401 is further specifically used to determine the subtending relationship between the roads corresponding to each two historical trajectory data according to the angle between the import line segments corresponding to each two historical trajectory data.

[0128] In a possible implementation, the association relationship is a subtending relationship; the acquisition module 401 is further specifically used to: determine the subtending relationship between the roads corresponding to each two historical trajectory data according to the text information of the import segments corresponding to each two historical trajectory data; wherein the text information includes text content representing the road import direction of the import segment.

[0129] In a possible implementation, the determination module 403 is specifically used to: determine the time information corresponding to the historical trajectory data according to the driving speed and position information in the historical trajectory data; wherein the time information represents the time range of the vehicle to which the historical trajectory data belongs waiting for the traffic light at the target intersection; determine the phase result corresponding to the group according to the time information corresponding to each historical trajectory data in the group; wherein the phase result represents the phase situation between the traffic lights of the roads corresponding to each historical trajectory data in the group; and determine the phase information of the target intersection according to the phase results corresponding to each group.

[0130] In a possible implementation, the determining module 403 is specifically configured to: determine the number of target vehicles and the target vehicle ratio corresponding to the group according to the time information corresponding to each historical trajectory data in the group; wherein, the number of target vehicles is the total number of all target vehicles corresponding to the group; a target vehicle is a vehicle to which two historical trajectory data with corresponding time information meeting the first preset condition belong; the target vehicle ratio is the ratio of the number of target vehicles corresponding to the group to the total number of vehicles to which all historical trajectory data corresponding to the group belong; determine the phase result corresponding to the group according to the number of target vehicles and the target vehicle ratio corresponding to the group.

[0131] In a possible implementation, the determining module 403 is specifically configured to: if it is determined that the number of target vehicles meets the second preset condition and the target vehicle ratio meets the third preset condition, determine that the phase result corresponding to the group indicates that the signal lights in each road direction corresponding to the group are in the same phase.

[0132] The device in this embodiment can execute the technical solutions in the above method, and its specific implementation process and technical principle are the same, which will not be elaborated here.

[0133] Figure 8 The structural schematic diagram of an electronic device provided by an embodiment of the present application is as Figure 8 shown. The electronic device includes: a memory 501 and a processor 502; the memory 501 is a memory for storing executable instructions of the processor 502.

[0134] Wherein, the processor 502 is configured to execute the method provided in the above embodiment.

[0135] The electronic device further includes a receiver 503 and a transmitter 504. The receiver 503 is used to receive instructions and data sent by other devices, and the transmitter 504 is used to send instructions and data to external devices.

[0136] The specific implementation process of the processor can refer to the above method embodiment, and its implementation principle and technical effect are similar, which will not be elaborated here in this embodiment.

[0137] In the above embodiments, it should be understood that the processor may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The steps of the method disclosed in combination with the invention can be directly embodied as being executed and completed by a hardware processor, or executed and completed by a combination of hardware and software modules in the processor.

[0138] The embodiments of the present application also provide a chip for running instructions, and this chip is used to execute the technical solution of the processing method in the above embodiments.

[0139] The embodiments of the present application also provide a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions run on a computer, the computer is enabled to execute the technical solution of the processing method in the above embodiments.

[0140] The above-readable storage medium may be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory, electrically erasable programmable read-only memory, erasable programmable read-only memory, programmable read-only memory, read-only memory, magnetic memory, flash memory, magnetic disk or optical disk. The readable storage medium may be any available medium accessible by a general-purpose or special-purpose computer.

[0141] An exemplary readable storage medium is coupled to the processor, so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium may also be a component of the processor. The processor and the readable storage medium may be located in an application specific integrated circuit. Of course, the processor and the readable storage medium may also exist as discrete components in a device.

[0142] The embodiments of the present application also provide a computer program product, which includes a computer program stored in a computer-readable storage medium. At least one processor can read the computer program from the computer-readable storage medium, and when at least one processor executes the computer program, the technical solution of the processing method in the above embodiments can be implemented.

[0143] The present application also provides a computer program product, including a computer program, and when the computer program is executed by a processor, the above method is implemented.

[0144] The present application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0145] The above-readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, a magnetic disk, or an optical disk. The readable storage medium can be any available medium accessible by a general-purpose or special-purpose computer.

[0146] An exemplary readable storage medium is coupled to the processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be part of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (ASIC). Of course, the processor and the readable storage medium can also exist as discrete components in a device.

[0147] In addition, in each embodiment of the present invention, the functional units can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit.

[0148] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present invention. The aforementioned storage medium includes: various media such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk that can store program codes.

[0149] Those of ordinary skill in the art will understand that all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments; and the aforementioned storage medium includes: various media such as ROM, RAM, magnetic disks, or optical discs that can store program codes.

[0150] Finally, it should be noted that those skilled in the art will readily conceive of other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses, or adaptations of the present invention, which follow the general principles of the present invention and include known common knowledge or conventional technical means in the technical field not disclosed in the present invention. It is not limited to the exact structures described above and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present invention is only limited by the appended claims.

Claims

1. A method for predicting a traffic light countdown, characterized in that: include: Acquire at least one historical trajectory data of a target intersection, and determine the association relationship between the roads corresponding to each historical trajectory data according to the road network data of the target intersection; wherein the historical trajectory data is the trajectory data of vehicles traveling on each road under the target intersection within a historical time period; According to the association relationship between the roads corresponding to the historical trajectory data, each of the historical trajectory data is grouped to obtain a group set; wherein the group set includes at least one group; The phase information of the target intersection is determined according to each historical trajectory data in each group; wherein the phase information represents the phase situation between the traffic lights in different road directions of the target intersection; and the phase information is used to predict the countdown information of the traffic lights at the target intersection.

2. The method according to claim 1, characterized in that The association relationship is a main-auxiliary road relationship in the same direction, or an opposite relationship, or a straight-through left-turn relationship in the same direction; and the historical trajectory data are grouped according to the association relationship between the roads corresponding to the historical trajectory data to obtain a grouping set, including: The historical trajectory data are grouped to obtain at least one main and auxiliary road group, at least one opposite direction group, and at least one straight left turn group; wherein the roads corresponding to the historical trajectory data in the main and auxiliary road group have a main and auxiliary road relationship in the same direction; the road directions corresponding to the historical trajectory data in the opposite direction group have an opposite direction relationship; and the road directions corresponding to the historical trajectory data in the straight left turn group have a straight left turn relationship in the same direction; Among them, each of the main and auxiliary road groups, each of the opposite groups, and each of the straight-ahead left-turn groups constitute each of the groups in the group set.

3. The method according to claim 1, characterized in that: The determining, based on the road network data of the target intersection, the association relationship between the roads corresponding to the historical trajectory data includes: Determine the entrance line segment corresponding to the historical trajectory data according to the road network data of the target intersection; wherein the entrance line segment represents the road shape of the road corresponding to the historical trajectory data in the entrance direction of the target intersection; According to the import line segments corresponding to the historical trajectory data, the association relationship between the roads corresponding to the historical trajectory data is determined.

4. The method according to claim 3, characterized in that The association relationship is a subtending relationship; the determining the association relationship between the roads corresponding to each of the historical trajectory data according to the import line segments corresponding to each of the historical trajectory data includes: According to the included angle between the import line segments corresponding to each two of the historical trajectory data, the subtending relationship between the roads corresponding to each two of the historical trajectory data is determined.

5. The method according to claim 3, characterized in that: The association relationship is a subtending relationship; the determining the association relationship between the roads corresponding to each of the historical trajectory data according to the import line segments corresponding to each of the historical trajectory data includes: According to the text information of the import line segments corresponding to each two of the historical trajectory data, the subtending relationship between the roads corresponding to each two of the historical trajectory data is determined; wherein the text information includes text content representing the road import direction of the import line segment.

6. The method according to any one of claims 1 to 5, characterized in that The determining the phase information of the target intersection according to each historical trajectory data in each group includes: Determine the time information corresponding to the historical trajectory data according to the driving speed and position information in the historical trajectory data; wherein the time information represents the time range of the vehicle to which the historical trajectory data belongs waiting for the traffic light at the target intersection; Determine a phase result corresponding to the group according to time information corresponding to each historical trajectory data in the group; wherein the phase result represents the phase situation between the traffic lights of the road corresponding to each historical trajectory data in the group; The phase information of the target intersection is determined according to the phase results corresponding to each of the groups.

7. The method according to claim 6, characterized in that The determining, according to the time information corresponding to each historical trajectory data in the group, a phase result corresponding to the group includes: According to the time information corresponding to each historical trajectory data in the group, the number of target vehicles and the target vehicle ratio corresponding to the group are determined; wherein the number of target vehicles is the total number of all target vehicles corresponding to the group; the target vehicle is a vehicle to which two historical trajectory data whose corresponding time information meets the first preset condition belong; the target vehicle ratio is the ratio of the number of target vehicles corresponding to the group to the total number of vehicles to which all historical trajectory data corresponding to the group belong; According to the number of target vehicles and the ratio of target vehicles corresponding to the group, the phase result corresponding to the group is determined.

8. A prediction device for a traffic light countdown, characterized in that: include: An acquisition module, used to acquire at least one historical trajectory data of a target intersection, and determine the association relationship between the roads corresponding to each of the historical trajectory data according to the road network data of the target intersection; wherein the historical trajectory data is the trajectory data of the vehicle traveling on each road under the target intersection within a historical time period; A grouping module, used for grouping the historical trajectory data according to the association relationship between the roads corresponding to the historical trajectory data to obtain a grouping set; wherein the grouping set includes at least one group; A determination module is used to determine the phase information of the target intersection according to each historical trajectory data in each group; wherein the phase information represents the phase situation between the traffic lights in different road directions of the target intersection; and the phase information is used to predict the countdown information of the traffic lights at the target intersection.

9. An electronic device, characterized in that: include: Memory, processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor performs the method according to any one of claims 1 to 7.

10. A computer-readable storage medium / computer program product, characterized in that: The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method according to any one of claims 1 to 7; and / or the computer program product includes a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 7.

Citation Information

Cited By

  • Traffic data processing method and device, electronic equipment and medium

    CN122067419A

  • Traffic data processing method and device, electronic equipment and medium

    CN122067419B