Traveling route prediction method, electronic device, and storage medium
By filtering and calculating historical driving trajectories, a database of commonly used routes is established, which solves the problem of accurate route prediction when the vehicle is not using navigation and improves the user experience.
Patent Information
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- ZHEJIANG GEELY HLDG GRP CO LTD
- Filing Date
- 2025-12-23
- Publication Date
- 2026-07-09
Smart Images
Figure CN2025144842_09072026_PF_FP_ABST
Abstract
Description
Driving route prediction methods, electronic devices and storage media Cross-references to related applications
[0001] This application claims priority to Chinese Patent Application No. 202411995812.4, filed with the Chinese Patent Office on December 31, 2024, the entire contents of which are incorporated herein by reference. Technical Field
[0002] This application relates to, but is not limited to, the field of automotive technology, and particularly to, but is not limited to, a driving route prediction method, electronic device, and storage medium. Background Technology
[0003] By combining vehicle navigation information, we can focus on the research and development of intelligent driving functions. Navigation traffic information has already been widely used, such as using navigation traffic information to optimize the energy management of new energy vehicles. Summary of the Invention
[0004] The following is an overview of the subject matter described in detail herein. This overview is not intended to limit the scope of the claims.
[0005] This application provides a method for predicting driving routes, an electronic device, and a storage medium.
[0006] This application provides a method for predicting driving routes, including: acquiring multiple historical driving trajectories of a target vehicle; filtering the multiple historical driving trajectories according to a preset filtering rule to obtain a target historical driving trajectory, wherein the preset filtering rule at least includes filtering out historical driving trajectories whose mileage is less than a first preset mileage or greater than a second preset mileage; acquiring travel information of the target historical driving trajectory, wherein the travel information at least includes the destination location of the target historical driving trajectory and the vehicle's travel time; calculating the route probability of target historical driving trajectories with the same destination location and the same travel time; establishing a database of the target vehicle's preferred routes based on the route probability and the travel information; and determining a first final predicted driving route of the target vehicle based on the database of preferred routes after detecting that the target vehicle has started.
[0007] Compared with related technologies, the embodiments of this application have at least the following advantages: By filtering multiple historical driving trajectories according to preset filtering rules, abnormal driving trajectories in the historical driving trajectories can be filtered out, thereby reducing the computational load of subsequent steps; since users may reach the same destination through different driving trajectories at the same travel time, by calculating the route probability of target historical driving trajectories with the same destination location and the same vehicle travel time, it is possible to know the probability of different routes used when users reach the same destination at the same travel time, and establish a database of the target vehicle's preferred routes based on the route probability and travel information. Thus, after the target vehicle starts, the cloud can select the first final predicted driving route of the target vehicle from the preferred route database, which not only enables the prediction of the vehicle's future journey when the user is not using the vehicle navigation system, but also improves the accuracy of the prediction, thereby improving the user's travel experience.
[0008] In some possible implementations, before determining the first final predicted driving route of the target vehicle based on the habitual route database, the method further includes: obtaining the target vehicle's identity information, current first location information, and current time; determining the habitual route database matching the target vehicle based on the identity information; the step of determining the first final predicted driving route of the target vehicle based on the habitual route database includes: selecting an initial predicted driving route from the habitual route database that matches the first location information and the current time, and taking the initial predicted driving route with the highest probability among the initial predicted driving routes as the first final predicted driving route.
[0009] In some possible implementations, after selecting the initial predicted driving route with the highest probability from the initial predicted driving routes as the first final predicted driving route for the target vehicle, the process includes: selecting the initial predicted driving route with the highest probability from the initial predicted driving routes as the driving route to be determined; detecting whether the driving route of the target vehicle when the driving time exceeds a second preset time and the driving distance is greater than a preset driving distance matches the driving route to be determined; and when the driving route is detected to match the driving route to be determined, selecting the driving route to be determined as the first final predicted driving route.
[0010] In some possible implementations, after determining the route to be determined as the first final predicted route, the method further includes: detecting whether the target vehicle deviates from its course at preset intervals; when the target vehicle deviates from its course for M consecutive preset intervals, obtaining the current second location information of the target vehicle, where M is an integer greater than 1; and selecting a second final predicted route that matches the second location information from the habitual route database.
[0011] In some possible implementations, filtering the multiple historical driving trajectories according to preset filtering rules includes: detecting whether there is a first historical driving trajectory to be filtered among the multiple historical driving trajectories where the vehicle speed is 0 for a duration exceeding a first preset duration; and when the existence of the first historical driving trajectory to be filtered is detected, filtering the first historical driving trajectory to be filtered among the multiple historical driving trajectories.
[0012] In some possible implementations, filtering multiple historical driving trajectories according to preset filtering rules includes: detecting whether there is a second historical driving trajectory to be filtered among the multiple historical driving trajectories whose mileage is greater than a third preset mileage for N consecutive days, where N is an integer greater than 1; when the existence of the second historical driving trajectory to be filtered is detected, filtering the second historical driving trajectory to be filtered among the multiple historical driving trajectories.
[0013] In some possible implementations, after obtaining multiple historical driving trajectories of the target vehicle in its historical driving, the method further includes: marking each historical driving trajectory with feature points, wherein the feature points include the starting point, ending point, and waypoints of the historical driving trajectory; performing route correction on each historical driving trajectory based on the feature points corresponding to each historical driving trajectory; and filtering multiple historical driving trajectories according to a preset filtering rule, which includes: filtering multiple historical driving trajectories after route correction according to a preset filtering rule.
[0014] In some possible implementations, each historical driving trajectory includes multiple road segments. After performing route correction on each historical driving trajectory, the method further includes: obtaining the names of all road segments included in each historical driving trajectory; filtering the multiple historical driving trajectories after route correction according to a preset filtering rule includes: detecting whether there is a third historical driving trajectory to be filtered among the multiple historical driving trajectories after route correction whose road segment name appears more than or equal to a preset number of times; and filtering the third historical driving trajectory to be filtered among the multiple historical driving trajectories after route correction if the existence of the third historical driving trajectory to be filtered is detected.
[0015] A second aspect of this application discloses an electronic device comprising a processor and a memory, the memory being configured to store instructions, and the processor being configured to invoke the instructions in the memory, causing the electronic device to execute the aforementioned driving route prediction method.
[0016] A third aspect of this application discloses a storage medium including computer instructions that, when executed on an electronic device, cause the electronic device to perform the aforementioned route prediction method.
[0017] Understandably, the electronic device of the second aspect and the storage medium of the third aspect provided above correspond to the method of the first aspect. Therefore, the beneficial effects they can achieve can be referred to the beneficial effects of the corresponding methods provided above, and will not be repeated here.
[0018] After reading and understanding the accompanying diagrams and detailed descriptions, other aspects can be understood. Attached Figure Description
[0019] The accompanying drawings are used to provide a further understanding of the technical solutions of this application and constitute a part of the specification. They are used together with the embodiments of this application to explain the technical solutions of this application and do not constitute a limitation on the technical solutions of this application.
[0020] Figure 1 is a schematic flowchart of a driving route prediction method according to an embodiment of this application.
[0021] Figure 2 is a flowchart illustrating a route prediction method according to an embodiment of this application.
[0022] Figure 3 is a flowchart illustrating a route prediction method according to an embodiment of this application.
[0023] Figure 4 is a flowchart illustrating a driving route prediction method according to an embodiment of this application.
[0024] Figure 5 is a flowchart illustrating a route prediction method according to an embodiment of this application.
[0025] Figure 6 is a schematic diagram of the functional modules of an electronic device according to an embodiment of the present application. Detailed Implementation
[0026] To better understand the above-mentioned objectives, features, and advantages of this application, the application will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in these embodiments can be combined with each other.
[0027] The following description sets forth many specific details to provide a full understanding of this application. The described embodiments are only some, not all, of the embodiments of this application.
[0028] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein in the specification of this application is for the purpose of describing particular embodiments only and is not intended to be limiting of this application.
[0029] It should be further noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.
[0030] In this application, "at least one" means one or more, and "more than one" means two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone, where A and B can be singular or plural. The terms "first," "second," "third," "fourth," etc. (if present) in the specification, claims, and drawings of this application are used to distinguish similar objects, not to describe a specific order or sequence.
[0031] In the embodiments of this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design that is described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design. Specifically, the use of the terms "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.
[0032] Obtaining traffic information when users travel without using navigation has become a common challenge in the automotive industry. How to record regular daily travel habits and further obtain traffic information for future trips is a key bottleneck that the automotive industry needs to overcome.
[0033] Please refer to Figure 1, which is a flowchart illustrating the route prediction method provided in this embodiment. This embodiment is applied in the cloud and includes the following steps:
[0034] Step 101: Obtain multiple historical driving trajectories of the target vehicle during its historical driving.
[0035] In some embodiments, the target vehicle uploads its GPS (Global Positioning System) location to the cloud during its historical driving process, enabling the cloud to obtain its historical driving trajectory. In some embodiments, the navigation software may be on or off when the target vehicle uploads its GPS location during its historical driving process.
[0036] In some embodiments, the target vehicle uses navigation software for navigation, and the cloud can also obtain the target vehicle's historical driving trajectory through the navigation software's history records. It is understood that this embodiment does not specifically limit the method of obtaining historical driving trajectories, and can be set according to actual needs.
[0037] In some embodiments, the cloud refers to a remote data processing center located outside the vehicle and accessible via a wireless communication network. Specifically, it may include one or more physical or virtual remote servers, which can be deployed in a distributed or centralized architecture to provide data reception, storage, computation, and analysis services. For example, the cloud could be a dedicated V2X (Vehicle-to-Everything) cloud server for vehicle-to-everything (V2X) services, communicating with the vehicle's infotainment system via cellular mobile communication networks (such as 4G or 5G) to receive and process navigation-related data uploaded by the vehicle (such as real-time location, driving trajectory, and road condition awareness information).
[0038] Step 102: Filter multiple historical driving trajectories according to preset filtering rules to obtain the target historical driving trajectory. The preset filtering rules include at least filtering out historical driving trajectories with a mileage less than a first preset mileage or greater than a second preset mileage.
[0039] In some embodiments, the first preset mileage is less than or equal to 2 km (e.g., 1 km, 2 km, etc.), and the second preset mileage is greater than or equal to 200 km (e.g., 200 km, 300 km, etc.). Since a small mileage indicates a nearby destination where the user does not require navigation services or other services derived from the driving route, while a large mileage indicates a destination that is not the user's usual destination or route, setting the first and second preset mileage within this range filters out driving trajectories from historical driving paths that do not require navigation or are not the user's usual routes. This improves the reliability of the driving route prediction method and reduces the computational load of subsequent steps.
[0040] In some embodiments, the first historical driving trajectory to be filtered can be filtered out from the multiple historical driving trajectories if it is detected that there is a first historical driving trajectory to be filtered out when the existence of the first historical driving trajectory to be filtered out is detected.
[0041] Understandably, the first historical driving trajectory to be filtered, where the vehicle speed is 0 for a duration exceeding the first preset duration, is considered an abnormal driving trajectory. This method further reduces the computational load of subsequent steps.
[0042] This embodiment does not specifically limit the size of the first preset duration, which can be set according to actual needs. For example, the value of the first preset duration can be between 10 minutes and 20 minutes. By limiting the size of the first preset duration, the accuracy of detecting the first historical driving trajectory to be filtered can be ensured.
[0043] In some embodiments, it is also possible to detect whether there are multiple second historical driving trajectories to be filtered that are distributed over N consecutive days and have a mileage greater than a third preset mileage, where N is an integer greater than 1; when the existence of the second historical driving trajectory to be filtered is detected, the second historical driving trajectory to be filtered is filtered from the multiple historical driving trajectories.
[0044] It is understandable that if the mileage traveled for N consecutive days is greater than the third preset mileage, it indicates that the target vehicle may be an operational vehicle. Therefore, this embodiment does not establish a database of commonly used routes for operational vehicles.
[0045] In some embodiments, the value of N can range from 15 days to 20 days, and the third preset mileage can range from 150 km to 200 km. This setting ensures the accuracy of detecting the second historical driving trajectory to be filtered.
[0046] Step 103: Obtain the travel information of the target's historical driving trajectory, including the destination location of the target's historical driving trajectory and the vehicle's travel time.
[0047] In some embodiments, after obtaining multiple historical driving trajectories of the target vehicle during its historical driving, the travel information of each historical driving trajectory can be obtained. For example, assuming that the cloud obtains the historical driving trajectory through the GPS location uploaded by the target vehicle during its historical driving, the cloud will record the upload time and the destination of the target vehicle when it uploads the GPS location, thereby obtaining the travel information of the target's historical driving trajectory.
[0048] Step 104: Calculate the route probability of target historical driving trajectories with the same destination location and the same vehicle travel time.
[0049] To make it easier to understand, the following example illustrates how to calculate route probability:
[0050] Assuming the destination is destination A, and there are ten target historical driving trajectories with the vehicle's travel time between 8:00 AM and 9:00 AM. Among these ten target historical driving trajectories, three target historical driving trajectories 1 have the same route, five target historical driving trajectories 2 have the same route, and two target historical driving trajectories 3 have the same route. Then, the probability of target historical driving trajectory 1 is 1 = 3 / 10 = 30%, the probability of target historical driving trajectory 2 is 2 = 5 / 10 = 50%, and the probability of target historical driving trajectory 3 is 3 = 2 / 10 = 20%.
[0051] Find all historical driving trajectories with the same destination and the same travel time, and calculate the route probability of each historical driving trajectory in the same way as above.
[0052] In some embodiments, the route probability can also be calculated using the historical driving trajectory of the target vehicle over the previous P days. In this way, the final predicted route can be more in line with the user's current usage habits.
[0053] In some embodiments, the value of P is between 5 and 7 days. By setting this range, it is possible to ensure that the number of historical driving trajectories is sufficient, and that the subsequently predicted routes are more in line with the user's current usage habits.
[0054] Step 105: Establish a database of the target vehicle's preferred routes based on route probability and trip information.
[0055] In some embodiments, the habitual route database stores the target vehicle's VIN (Vehicle Identification Number), route probability, corrected GPS trajectory point set, road segment name, total mileage, and travel time.
[0056] Step 106: After detecting the start of the target vehicle, determine the first final predicted driving route of the target vehicle based on the habitual route database.
[0057] It should be noted that the method for determining the first final predicted driving route is described in detail in subsequent embodiments, and will not be repeated here to avoid repetition.
[0058] Compared with related technologies, the embodiments of this application have at least the following advantages: By filtering multiple historical driving trajectories according to preset filtering rules, abnormal driving trajectories in the historical driving trajectories can be filtered out, thereby reducing the computational load of subsequent steps; since users may reach the same destination through different driving trajectories at the same travel time, by calculating the route probability of target historical driving trajectories with the same destination location and the same vehicle travel time, it is possible to know the probability of different routes used by users when reaching the same destination at the same travel time, and establish a database of the target vehicle's preferred routes based on route probabilities and travel information. Thus, after the target vehicle starts, the cloud can determine the first final predicted driving route of the target vehicle, which not only enables the prediction of the vehicle's future journey when the user is not using the vehicle navigation system, but also improves the accuracy of the prediction, thereby improving the user's travel experience.
[0059] Please refer to Figure 2, which is a flowchart of a route prediction method provided in an embodiment of this application. This embodiment is based on the foregoing embodiment and specifically illustrates how to determine the first final predicted route based on a commonly used route database.
[0060] This embodiment is applied in the cloud, and the specific process is shown in Figure 2, including the following steps:
[0061] Step 201: Obtain multiple historical driving trajectories of the target vehicle during its historical driving.
[0062] Step 202: Filter multiple historical driving trajectories according to preset filtering rules to obtain the target historical driving trajectory. The preset filtering rules include at least filtering out historical driving trajectories with a mileage less than a first preset mileage or greater than a second preset mileage.
[0063] Step 203: Obtain the travel information of the target's historical driving trajectory, including the destination of the target's historical driving trajectory and the vehicle's travel time.
[0064] Step 204: Calculate the route probability of target historical driving trajectories with the same destination location and the same vehicle travel time.
[0065] Step 205: Establish a database of the target vehicle's preferred routes based on route probability and trip information.
[0066] Steps 101 to 105 in the foregoing embodiment are similar to steps 201 to 205 in this embodiment. To avoid repetition, they will not be described again here.
[0067] Step 206: After detecting that the target vehicle has started, obtain the target vehicle's identity information, current first location information, and current time.
[0068] In some embodiments, after the vehicle is started, the vehicle controller uploads the vehicle's identity information, current location information, and current time to the cloud.
[0069] In some embodiments, the identity information is the vehicle VIN (Vehicle Identification Number), and the first location information is the GPS location.
[0070] Step 207: Determine the database of habitual routes that match the target vehicle based on the identity information, select the initial predicted driving route that matches the first location information and the current time from the database of habitual routes, and take the initial predicted driving route with the highest probability among the initial predicted driving routes as the first final predicted driving route.
[0071] To facilitate understanding, the following is a specific example illustrating how the first final predicted driving route is obtained in this embodiment:
[0072] The cloud stores a database of habitual routes for multiple vehicles, with each vehicle corresponding to a specific database. After obtaining vehicle identification information, let's say vehicle A's identification information 'a' is obtained. The cloud uses identification information 'a' to determine the habitual route database 1 that matches vehicle A. Assuming habitual route database 1 contains 200 historical driving trajectories of vehicle A, and assuming the current time is 8:30 AM and the current GPS location is location 1, based on vehicle A's current GPS location and time, ten initial predicted routes are determined from the 200 historical driving trajectories that pass through location 1 and fall between 8:00 AM and 9:00 AM. Assuming that among these ten initial predicted routes, initial predicted route 1 has the highest probability (e.g., 60%), then initial predicted route 1 is taken as vehicle A's first final predicted route.
[0073] Compared with related technologies, the embodiments of this application have at least the following advantages: By filtering multiple historical driving trajectories according to preset filtering rules, abnormal driving trajectories in the historical driving trajectories can be filtered out, thereby reducing the computational load of subsequent steps; since users may reach the same destination through different driving trajectories at the same travel time, by calculating the route probability of target historical driving trajectories with the same destination location and the same vehicle travel time, it is possible to know the probability of different routes used when users reach the same destination at the same travel time, and establish a database of the target vehicle's preferred routes based on the route probability and travel information. Thus, after the target vehicle starts, the cloud can determine the preferred route database based on the target vehicle's identity information, and select the initial predicted driving route with the highest route probability from the preferred route database as the target vehicle's first final predicted driving route. This not only enables the prediction of the vehicle's future journey even when the user is not using the in-vehicle navigation system, but also improves the accuracy of the prediction, thereby improving the user's travel experience.
[0074] Please refer to Figure 3, which is a flowchart illustrating a route prediction method according to an embodiment of this application. This embodiment is a further improvement upon the aforementioned embodiments, primarily in that it also performs route correction on historical driving trajectories. This approach further enhances the accuracy of route prediction.
[0075] This embodiment is applied in the cloud, and the specific process is shown in Figure 3, including the following steps:
[0076] Step 301: Obtain multiple historical driving trajectories of the target vehicle during its historical driving.
[0077] Step 302: Mark feature points for each historical driving trajectory, where feature points include the starting point, ending point, and points along the way of the historical driving trajectory.
[0078] In some embodiments, the feature points are represented as a GPS array, meaning that each feature point includes the longitude and latitude of the vehicle's location.
[0079] In some embodiments, waypoints are obtained by dividing the total number of frames in the historical driving trajectory into b equal parts as waypoints. For example, if the total number of frames in the historical driving trajectory is 1000, and a waypoint is extracted every 100 frames, then the historical driving trajectory includes a total of 9 waypoints.
[0080] Step 303: Based on the feature points corresponding to each historical driving trajectory, perform route correction for each historical driving trajectory.
[0081] In some embodiments, the cloud inputs the feature points corresponding to each historical driving trajectory into the navigation software's API (Application Programming Interface) so that the navigation software outputs a corrected set of GPS trajectory points and the names of all road segments.
[0082] As described in the preceding steps, the feature points of the historical driving trajectory constitute the GPS location point set. Since GPS location points may be offset, the navigation software corrects for these offset GPS location points by inputting the feature points, resulting in a corrected set of GPS trajectory points. Because each historical driving trajectory includes multiple road segments, the navigation software can also simultaneously input the name of each road segment after inputting the feature points.
[0083] Step 304: Filter multiple historical driving trajectories after route correction according to preset filtering rules to obtain the target historical driving trajectory.
[0084] In some embodiments, it is also possible to detect whether there is a third historical driving trajectory to be filtered among multiple historical driving trajectories after route correction, in which the number of occurrences of the road segment name is greater than or equal to a preset number; if the existence of a third historical driving trajectory to be filtered is detected, the third historical driving trajectory to be filtered among multiple historical driving trajectories after route correction is filtered.
[0085] In some embodiments, the preset number of times can be 2 or 3 times. By setting this preset number of times, it is possible to ensure that circling driving trajectories are filtered out.
[0086] Step 305: Obtain the travel information of the target's historical driving trajectory, wherein the travel information includes at least the destination of the target's historical driving trajectory and the time period of vehicle travel.
[0087] In some embodiments, the trip information may also include a set of GPS track points corrected to the target’s historical trajectory, road segment names, and total mileage.
[0088] Step 306: Calculate the route probability of target historical driving trajectories with the same destination location and the same vehicle travel time.
[0089] Step 307: Establish a database of the target vehicle's preferred routes based on route probability and trip information.
[0090] Step 308: After detecting that the target vehicle has started, obtain the target vehicle's identity information, current first location information, and current time.
[0091] Step 309: Determine the database of habitual routes that match the target vehicle based on the identity information, select the initial predicted driving route that matches the first location information and the current time from the database of habitual routes, and take the initial predicted driving route with the highest probability among the initial predicted driving routes as the first final predicted driving route of the target vehicle.
[0092] Steps 301, 305 to 309 in this embodiment are similar to steps 201, 203 to 207 in the previous embodiment. To avoid repetition, they will not be described again here.
[0093] Compared with related technologies, the embodiments of this application have at least the following advantages: By filtering multiple historical driving trajectories according to preset filtering rules, abnormal driving trajectories in the historical driving trajectories can be filtered out, thereby reducing the computational load of subsequent steps; since users may reach the same destination through different driving trajectories at the same travel time, by calculating the route probability of target historical driving trajectories with the same destination location and the same vehicle travel time, it is possible to know the probability of different routes used when users reach the same destination at the same travel time, and establish a database of the target vehicle's preferred routes based on the route probability and travel information. Thus, after the target vehicle starts, the cloud can determine the preferred route database based on the target vehicle's identity information, and select the initial predicted driving route with the highest route probability from the preferred route database as the target vehicle's first final predicted driving route. This not only enables the prediction of the vehicle's future journey even when the user is not using the in-vehicle navigation system, but also improves the accuracy of the prediction, thereby improving the user's travel experience.
[0094] Please refer to Figure 4, which is a flowchart illustrating a route prediction method according to an embodiment of this application. This embodiment is a further improvement upon the aforementioned embodiments, with the main improvement being that the accuracy of the first final predicted route is further confirmed. This approach further improves the accuracy of route prediction, thereby enhancing the user experience.
[0095] This embodiment is applied in the cloud, and the specific process is shown in Figure 4, including the following steps:
[0096] Step 401: Obtain multiple historical driving trajectories of the target vehicle during its historical driving.
[0097] Step 402: Filter multiple historical driving trajectories according to preset filtering rules to obtain the target historical driving trajectory. The preset filtering rules include at least filtering out historical driving trajectories with a mileage less than a first preset mileage or greater than a second preset mileage.
[0098] Step 403: Obtain the travel information of the target's historical driving trajectory, including the destination location of the target's historical driving trajectory and the vehicle's travel time.
[0099] Step 404: Calculate the route probability of target historical driving trajectories with the same destination location and the same vehicle travel time.
[0100] Step 405: Establish a database of the target vehicle's preferred routes based on route probability and trip information.
[0101] Step 406: After detecting that the target vehicle has started, obtain the target vehicle's identity information, current first location information, and current time.
[0102] Step 407: Determine the database of habitual routes that match the target vehicle based on the identity information, select the initial predicted driving route that matches the first location information and the current time from the database of habitual routes, and select the initial predicted driving route with the highest probability from the initial predicted driving routes as the driving route to be determined.
[0103] Steps 401 to 407 in this embodiment are similar to steps 201 to 207 in the previous embodiment. To avoid repetition, they will not be described again here.
[0104] Step 408: Detect whether the driving route of the target vehicle when the driving time exceeds the second preset time and the driving distance is greater than the preset driving distance matches the driving route to be determined, and when the driving route is detected to match the driving route to be determined, take the driving route to be determined as the first final predicted driving route.
[0105] In some embodiments, the second preset duration ranges from 1 minute to 2 minutes, and the preset travel distance ranges from 500M to 1KM. By setting this range, it is possible to achieve rapid route prediction for the target vehicle while ensuring the accuracy of the predicted route, thus avoiding negative impacts on the user experience due to excessively long prediction times.
[0106] In some embodiments, it can also be detected whether the remaining mileage of the route to be determined is within a preset range. For example, if it is detected that the remaining mileage of the route to be determined is greater than or equal to a first preset mileage and less than or equal to a second preset mileage, then the route to be determined is used as the first final predicted route. In this way, the validity of the predicted first final predicted route can be ensured.
[0107] Compared with related technologies, the embodiments of this application have at least the following advantages: By filtering multiple historical driving trajectories according to preset filtering rules, abnormal driving trajectories in the historical driving trajectories can be filtered out, thereby reducing the computational load of subsequent steps; since users may reach the same destination through different driving trajectories at the same travel time, by calculating the route probability of target historical driving trajectories with the same destination location and the same vehicle travel time, it is possible to know the probability of different routes used when users reach the same destination at the same travel time, and establish a database of the target vehicle's preferred routes based on the route probability and travel information. Thus, after the target vehicle starts, the cloud can determine the preferred route database based on the target vehicle's identity information, and select the initial predicted driving route with the highest route probability from the preferred route database as the target vehicle's first final predicted driving route. This not only enables the prediction of the vehicle's future journey even when the user is not using the in-vehicle navigation system, but also improves the accuracy of the prediction, thereby improving the user's travel experience.
[0108] Please refer to Figure 5, which is a flowchart illustrating a driving route prediction method according to an embodiment of this application. This embodiment is a further improvement based on the aforementioned embodiments. The main improvement is that, in this embodiment, the vehicle's yaw is detected during driving, and the driving route is re-predicted after yaw is detected. This approach can further improve the user's driving experience.
[0109] This embodiment is applied in the cloud, and the specific process is shown in Figure 5, including the following steps:
[0110] Step 501: Obtain multiple historical driving trajectories of the target vehicle during its historical driving.
[0111] Step 502: Filter multiple historical driving trajectories according to preset filtering rules to obtain the target historical driving trajectory. The preset filtering rules include at least filtering out historical driving trajectories with a mileage less than a first preset mileage or greater than a second preset mileage.
[0112] Step 503: Obtain the travel information of the target's historical driving trajectory, including the destination location of the target's historical driving trajectory and the vehicle's travel time.
[0113] Step 504: Calculate the route probability of target historical driving trajectories with the same destination location and the same vehicle travel time.
[0114] Step 505: Establish a database of the target vehicle's preferred routes based on route probability and trip information.
[0115] Step 506: After detecting that the target vehicle has started, obtain the target vehicle's identity information, current first location information, and current time.
[0116] Step 507: Determine the database of habitual routes that match the target vehicle based on the identity information, select the initial predicted driving route that matches the first location information and the current time from the database of habitual routes, and take the initial predicted driving route with the highest probability among the initial predicted driving routes as the first final predicted driving route of the target vehicle.
[0117] Step 508: Detect whether the target vehicle deviates from its course at preset intervals.
[0118] In some embodiments, the size of the preset period is not specifically limited and can be set according to the actual situation.
[0119] In some embodiments, the target vehicle is considered to be veerging when the deviation between its real-time position and the road centerline of the first final predicted driving route exceeds a certain threshold. The threshold value is between 20M and 30M.
[0120] Step 509: When the target vehicle is detected to veer off course for M consecutive preset periods, obtain the current second position information of the target vehicle, where M is an integer greater than 1.
[0121] In some embodiments, considering the possibility of misjudgment or temporary detours caused by GPS position offset, in order to avoid frequent entry and exit of the route prediction function, the target vehicle will only be confirmed as deviating when there are continuous deviations for M preset periods.
[0122] Step 510: Select the second final predicted driving route from the habitual route database that matches the second location information.
[0123] In some embodiments, the selection method of the second final predicted driving route is similar to that of the first final predicted driving route, and will not be repeated here to avoid repetition.
[0124] In some embodiments, if no second final predicted driving route matching the second location information is found from the habitual route database, the cloud exits the route prediction function for the target vehicle.
[0125] Please refer to Figure 6, which is a schematic diagram of the hardware structure of the electronic device 1000 provided in this embodiment of the application. As shown in Figure 6, the electronic device 1000 may include a processor 1001 and a memory 1002. The memory 1002 is configured to store one or more computer programs 1003. The one or more computer programs 1003 are configured to be executed by the processor 1001. The one or more computer programs 1003 include instructions that can be used to implement the above-described driving route prediction method in the electronic device 1000.
[0126] It is understood that the structure illustrated in this embodiment does not constitute a specific limitation on the electronic device 1000. In other embodiments, the electronic device 1000 may include more or fewer components than illustrated, or combine some components, or split some components, or have different component arrangements.
[0127] Processor 1001 may include one or more processing units, such as application processors (APs), modems, graphics processing units (GPUs), image signal processors (ISPs), controllers, video codecs, digital signal processors (DSPs), baseband processors, and / or neural network processing units (NPUs). These different processing units may be independent devices or integrated into one or more processors.
[0128] The processor 1001 may also include a memory configured to store instructions and data. In some embodiments, the memory in the processor 1001 is a cache memory. This memory can store instructions or data that the processor 1001 has just used or is recurring. If the processor 1001 needs to use the instruction or data again, it can retrieve it directly from this memory. This avoids repeated accesses, reduces the waiting time of the processor 1001, and thus improves the efficiency of the system.
[0129] In some embodiments, the processor 1001 may include one or more interfaces. Interfaces may include an inter-integrated circuit (I2C) interface, an inter-integrated circuit sound (I2S) interface, a pulse code modulation (PCM) interface, a universal asynchronous receiver / transmitter (UART) interface, a mobile industry processor interface (MIPI), a general-purpose input / output (GPIO) interface, a SIM interface, and / or a USB interface, etc.
[0130] In some embodiments, the processor 1001 is configured to execute acceleration schemes such as Single Instruction Multiple Data (SIMD) and Very Long Instruction Word (VLIW).
[0131] In some embodiments, memory 1002 may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.
[0132] This embodiment also provides a storage medium storing computer instructions. When the instructions are executed on an electronic device, the electronic device performs the aforementioned method steps to implement the driving route prediction method in the above embodiment.
[0133] In this embodiment, the electronic device and storage medium are used to execute the corresponding methods provided above. Therefore, the beneficial effects they can achieve can be referred to the beneficial effects of the corresponding methods provided above, and will not be repeated here.
[0134] In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.
[0135] In the several embodiments provided in this application, the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are illustrative. For instance, the division of modules or units is a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.
[0136] The unit described as a separate component may or may not be physically separate. The component shown as a unit can be one physical unit or multiple physical units, that is, it can be located in one place or distributed in multiple different places. Some or all of the units can be selected to achieve the purpose of the solution in this embodiment according to actual needs.
[0137] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.
[0138] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solutions of the embodiments of this application, essentially or in other words, the parts that contribute to the prior art, or all or part of the technical solutions, can be embodied in the form of a software product. This software product is stored in a storage medium and includes several instructions to cause a device (which may be a microcontroller, chip, etc.) or processor to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0139] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions within the technical scope disclosed in this application should be covered within the scope of protection of this application.
Claims
1. A route prediction method, applied in the cloud, comprising: Obtain multiple historical driving trajectories of the target vehicle during its historical driving process; Multiple historical driving trajectories are filtered according to preset filtering rules to obtain a target historical driving trajectory. The preset filtering rules include filtering out historical driving trajectories whose mileage is less than a first preset mileage or greater than a second preset mileage. Obtain the travel information of the target's historical driving trajectory, wherein the travel information includes the destination location of the target's historical driving trajectory and the vehicle's travel time. Calculate the route probability of the target historical driving trajectory where the destination position is the same and the vehicle travel time is the same; A database of the target vehicle's preferred routes is established based on the route probability and the trip information. After the target vehicle is detected to have started, the first final predicted route of the target vehicle is determined based on the habitual route database.
2. The driving route prediction method according to claim 1, wherein, Before determining the first final predicted route for the target vehicle based on the habitual route database, the method further includes: Obtain the target vehicle's identity information, current first location information, and current time; The database of habitual routes matching the target vehicle is determined based on the identity information; Determining the first final predicted route for the target vehicle based on the habitual route database includes: Select an initial predicted driving route from the habitual route database that matches the first location information and the current time, and take the initial predicted driving route with the highest probability among the initial predicted driving routes as the first final predicted driving route.
3. The driving route prediction method according to claim 2, wherein, The step of selecting the initial predicted route with the highest probability from the initial predicted routes as the first final predicted route includes: Select the initial predicted driving route with the highest probability from the initial predicted driving routes as the driving route to be determined; The system detects whether the travel route of the target vehicle when its travel time exceeds a second preset time and its travel distance exceeds a preset travel distance matches the travel route to be determined. When a match is detected between the driving route and the driving route to be determined, the driving route to be determined is taken as the first final predicted driving route.
4. The driving route prediction method according to claim 3, wherein, After determining the route to be determined as the first final predicted route, the method further includes: The target vehicle is checked for deviation at preset intervals. When the target vehicle is detected to veer off course for M consecutive preset periods, the current second position information of the target vehicle is obtained, where M is an integer greater than 1; Select a second final predicted driving route from the habitual route database that matches the second location information.
5. The route prediction method according to claim 1 or 2, wherein, After determining the first final predicted driving route of the target vehicle based on the habitual route database, the method further includes: The target vehicle is checked for deviation at preset intervals. When the target vehicle is detected to veer off course for M consecutive preset periods, the current second position information of the target vehicle is obtained, where M is an integer greater than 1; Select a second final predicted driving route from the habitual route database that matches the second location information.
6. The route prediction method according to any one of claims 1 to 5, wherein, The filtering of multiple historical driving trajectories according to preset filtering rules includes: Detect whether there is a first historical driving trajectory to be filtered among the multiple historical driving trajectories where the vehicle speed is 0 for a duration exceeding a first preset duration; When the existence of the first historical driving trajectory to be filtered is detected, the first historical driving trajectory to be filtered is filtered out from the plurality of historical driving trajectories.
7. The route prediction method according to any one of claims 1 to 5, wherein, The filtering of multiple historical driving trajectories according to preset filtering rules includes: Detect whether there exists a second historical driving trajectory to be filtered among the multiple historical driving trajectories that is distributed over N consecutive days and has a mileage greater than a third preset mileage, where N is an integer greater than 1; When the existence of the second historical driving trajectory to be filtered is detected, the second historical driving trajectory to be filtered is filtered out from the plurality of historical driving trajectories.
8. The route prediction method according to any one of claims 1 to 7, wherein, After obtaining multiple historical driving trajectories of the target vehicle in its historical driving history, the method further includes: Each of the historical driving trajectories is marked with feature points, wherein the feature points include the starting point, ending point, and points along the way of the historical driving trajectory; Based on the feature points corresponding to each historical driving trajectory, route correction is performed on each historical driving trajectory; The filtering of multiple historical driving trajectories according to preset filtering rules includes: The historical driving trajectories after route correction are filtered according to preset filtering rules.
9. The driving route prediction method according to claim 8, wherein, Each of the historical driving trajectories includes multiple road segments. After performing route correction on each of the historical driving trajectories, the following is also included: Obtain the names of all road segments included in each of the historical driving trajectories; The step of filtering multiple historical driving trajectories after route correction according to preset filtering rules includes: Detect whether there is a third historical driving trajectory to be filtered among multiple historical driving trajectories after the route correction, in which the number of occurrences of the road segment name is greater than or equal to a preset number; Upon detecting the existence of the third historical driving trajectory to be filtered, the third historical driving trajectory to be filtered is selected from among the multiple historical driving trajectories after route correction.
10. An electronic device comprising a processor and a memory, the memory being configured to store instructions, the processor being configured to invoke the instructions in the memory, causing the electronic device to perform the driving route prediction method according to any one of claims 1 to 9.
11. A storage medium comprising computer instructions that, when executed on an electronic device, cause the electronic device to perform the route prediction method as described in any one of claims 1 to 9.