A driving route prediction method and device, a vehicle terminal, and a medium

Abstract

The application is suitable for the field of automobile technology, and provides a driving route prediction method and device, a vehicle-mounted terminal and a computer readable storage medium. The method comprises the following steps: acquiring a first departure time, a first departure location and a position coordinate set of a vehicle in a driving process; determining a driven route of the vehicle according to the position coordinate set; inputting the first departure time, the first departure location, the position coordinate set and the driven route into a route prediction model for processing to obtain a target driving route of the vehicle; wherein the route prediction model is a pre-trained neural network model. Compared with the prior art which only predicts the future driving route of the vehicle according to the departure time and the departure location of the vehicle, the method provided by the application needs to combine the departure time, the departure location, the position coordinate set of the vehicle in the driving process and the driven route of the vehicle to predict the driving route of the vehicle, thereby improving the prediction accuracy of the driving route.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of automobiles, and particularly relates to a driving route prediction method and device, a vehicle terminal, and a computer readable storage medium. BACKGROUND

[0002] With the increasing intelligence of vehicles, many intelligent functions need to be based on navigation data (such as the route taken by the vehicle to reach the destination) to be used. At present, most vehicle owners do not use the car navigation system to navigate the route when driving the vehicle. Some vehicle owners choose to use mobile phone navigation, and some vehicle owners do not need to use navigation because they are familiar with the route, which makes the vehicle terminal need to predict the future driving route of the vehicle in real time to achieve the purpose of realizing the intelligent function of the vehicle.

[0003] However, the prior art usually only simply predicts the future driving route of the vehicle according to the departure time and departure location of the vehicle, which is not comprehensive enough, resulting in low prediction accuracy of the driving route. SUMMARY

[0004] The embodiments of the present application provide a driving route prediction method, device, vehicle terminal, and computer readable storage medium, which improves the prediction accuracy of the driving route.

[0005] In a first aspect, the embodiments of the present application provide a driving route prediction method, comprising:

[0006] obtaining a first departure time, a first departure location of a vehicle, and a position coordinate set of the vehicle in a driving process;

[0007] determining a driven route of the vehicle according to the position coordinate set;

[0008] inputting the first departure time, the first departure location, the position coordinate set, and the driven route into a route prediction model for processing to obtain a target driving route of the vehicle; wherein the route prediction model is a pre-trained neural network model.

[0009] Optionally, the inputting the first departure time, the first departure location, the position coordinate set, and the driven route into the route prediction model for processing to obtain the target driving route of the vehicle comprises:

[0010] obtaining a plurality of standard routes corresponding to the vehicle pre-stored, and determining respective feature information corresponding to the plurality of standard routes; wherein the feature information comprises a departure time, a departure location, and a driving position coordinate;

[0011] According to the first departure time, the first departure location, the set of position coordinates, the traveled route, and feature information corresponding to each of the plurality of standard routes, a first difference value corresponding to each of the traveled route and the plurality of standard routes in a plurality of first preset dimensions is calculated;

[0012] The first difference value corresponding to each of the traveled route and the plurality of standard routes in the plurality of first preset dimensions is input into the route prediction model for processing to obtain the target travel route.

[0013] Optionally, the obtaining of the plurality of standard routes corresponding to the vehicle and pre-stored includes:

[0014] A plurality of historical travel routes of the vehicle in a historical time period are obtained, and a departure location and an end location of each of the historical travel routes are determined.

[0015] The plurality of historical travel routes are divided according to the departure location and the end location of each of the historical travel routes to obtain a plurality of route sets; all historical travel routes in each of the route sets have the same departure location and end location.

[0016] For each of the route sets, the historical travel route with the highest occurrence frequency in the route set is determined as the standard route.

[0017] Optionally, before the first difference value corresponding to each of the traveled route and the plurality of standard routes in the plurality of first preset dimensions is input into the route prediction model for processing to obtain the target travel route, the method further includes:

[0018] Each of the historical travel routes is split based on a set condition to obtain a plurality of sub-travel routes corresponding to each of the historical travel routes.

[0019] A second departure time and a second departure location corresponding to each of the sub-travel routes are determined.

[0020] For each of the sub-travel routes, a second difference value corresponding to each of the sub-travel route and the plurality of standard routes in the plurality of first preset dimensions is calculated according to the second departure time, the second departure location, position coordinates of the sub-travel route, and feature information corresponding to each of the plurality of standard routes.

[0021] The neural network model is trained according to the second difference value corresponding to each of the sub-travel route and the plurality of standard routes in the plurality of first preset dimensions to obtain the route prediction model.

[0022] Optionally, the training of the neural network model according to the second difference value corresponding to each of the sub travel route and each of the standard route in each of the first preset dimension obtains the route prediction model, including:

[0023] The second difference value corresponding to each of the sub travel route and each of the standard route in each of the first preset dimension is associated with the historical travel route corresponding to each of the sub travel route, respectively;

[0024] The third difference value corresponding to each of the historical travel route and each of the standard route in each of the second preset dimension is calculated;

[0025] The target standard route corresponding to each of the historical travel route is determined according to the third difference value, and each of the historical travel route is labeled based on the target standard route;

[0026] The neural network model is trained according to each of the historical travel route carrying the label and the third difference value associated with each of the historical travel route, and the route prediction model is obtained.

[0027] Optionally, the second preset dimension includes a starting point dimension, an end point dimension and a route dimension; and the determination of the target standard route corresponding to each of the historical travel route according to the third difference value includes:

[0028] For each of the historical travel route, if the third difference value of the historical travel route and one of the standard routes in the starting point dimension is less than or equal to a first threshold value, the third difference value of the historical travel route and the one of the standard routes in the end point dimension is less than or equal to a second threshold value, and the route similarity calculated according to the third difference value of the route dimension is greater than or equal to a third threshold value, the one of the standard routes is determined as the target standard route corresponding to the historical travel route.

[0029] Optionally, after the first departure time, the first departure location, the set of position coordinates and the traveled route are input into the route prediction model for processing to obtain the target travel route of the vehicle, the method further includes:

[0030] The target location and the target travel position corresponding to the vehicle are determined according to the target travel route;

[0031] The set map interface is called to enable the map interface to output the environmental information and the travel information of the vehicle under the target travel route according to the target location and the target travel position.

[0032] In a second aspect, an embodiment of the present application provides a travel route prediction device, including:

[0033] a first obtaining unit, configured to obtain a first departure time, a first departure location, and a set of position coordinates of a vehicle in a driving process;

[0034] a first determining unit, configured to determine a driven route of the vehicle according to the set of position coordinates;

[0035] a first processing unit, configured to input the first departure time, the first departure location, the set of position coordinates, and the driven route into a route prediction model for processing, to obtain a target driving route of the vehicle; the route prediction model is a pre-trained neural network model.

[0036] In a third aspect, an embodiment of the present application provides a vehicle terminal, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor, and the processor implements the method for predicting a driving route according to any one of the first aspect.

[0037] In a fourth aspect, an embodiment of the present application provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the method for predicting a driving route according to any one of the first aspect.

[0038] In a fifth aspect, an embodiment of the present application provides a computer program product, which, when running on a vehicle terminal, enables the vehicle terminal to execute the method for predicting a driving route according to any one of the first aspect.

[0039] Compared with the prior art, the embodiment of the present application has the following beneficial effects:

[0040] The method for predicting a driving route provided by the embodiment of the present application includes the following steps: obtaining a first departure time, a first departure location, and a set of position coordinates of a vehicle in a driving process; determining a driven route of the vehicle according to the set of position coordinates; and inputting the first departure time, the first departure location, the set of position coordinates, and the driven route into a route prediction model for processing, to obtain a target driving route of the vehicle; the route prediction model is a pre-trained neural network model. Compared with the prior art which only predicts a future driving route of a vehicle according to a departure time and a departure location of the vehicle, the method provided by the present application needs to combine the departure time, the departure location, the set of position coordinates of the vehicle in the driving process, and the driven route of the vehicle to predict the driving route of the vehicle, thereby improving the prediction accuracy of the driving route. BRIEF DESCRIPTION OF DRAWINGS

[0041] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments or prior art description will be briefly introduced. Obviously, the drawings in the following description only constitute some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor.

[0042] Figure 1 is an implementation flowchart of the driving route prediction method provided by an embodiment of the present application;

[0043] Figure 2 is an implementation flowchart of the driving route prediction method provided by another embodiment of the present application;

[0044] Figure 3 is an implementation flowchart of the driving route prediction method provided by still another embodiment of the present application;

[0045] Figure 4 is an implementation flowchart of the driving route prediction method provided by yet another embodiment of the present application;

[0046] Figure 5 is a working principle schematic diagram of the cumulative segmentation method provided by an embodiment of the present application;

[0047] Figure 6 is an implementation flowchart of the driving route prediction method provided by yet another embodiment of the present application;

[0048] Figure 7 is a structural schematic diagram of the driving route prediction device provided by an embodiment of the present application;

[0049] Figure 8 is a structural schematic diagram of the vehicle-mounted terminal provided by an embodiment of the present application. DETAILED DESCRIPTION

[0050] In the following description, specific details are set forth in order to provide a thorough understanding of embodiments of the present application. However, persons of ordinary skill in the art will readily recognize that embodiments of the present application can be practiced without these specific details. In other instances, well-known structures, devices, circuits, and methods have not been described in detail in order to avoid obscuring the present application.

[0051] It should be understood that, when used in the specification and the appended claims of the present application, the term "comprising" indicates the presence of the described features, integers, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0052] It should also be understood that the term "and / or" as used herein refers to any one of the associated listed items, or a combination of any of the associated listed items, and all possible combinations thereof.

[0053] As used in the description of the application and the appended claims, the term "if' can be interpreted to mean "when" or "upon" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrase "if it is determined" or "if [a described condition or event] is detected" can be interpreted to mean "upon determining" or "in response to determining" or "upon detecting [the described condition or event]" or "in response to detecting [the described condition or event]," depending on the context.

[0054] In addition, the terms "first", "second", "third", etc. as used in the description of the application and the appended claims are merely used to differentiate descriptions, and cannot be understood as indicating or implying relative importance.

[0055] Reference in the specification to "one embodiment" or "some embodiments" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the application. The appearances of the phrases "in one embodiment", "in some embodiments", "in other embodiments", "in additional embodiments", etc. in various places in the specification are not necessarily all referring to the same embodiment, although they can. The terms "comprising", "including", "having" and their variants, mean "including but not limited to", unless otherwise expressly specified.

[0056] Reference is made to Figure 1 , Figure 1 is an implementation flowchart of a driving route prediction method provided by an embodiment of the application. In the embodiment of the application, the execution subject of the driving route prediction method is a vehicle terminal.

[0057] As shown in Figure 1 , the driving route prediction method provided by an embodiment of the application can include S101-S103, which are described in detail as follows:

[0058] In S101, the first departure time, the first departure location of the vehicle, and the position coordinate set of the vehicle in the driving process are acquired.

[0059] In actual applications, with the increasing intelligence of vehicles, many intelligent functions need to be used based on navigation data (such as the route passed by the vehicle to reach the destination) to be used. At present, most vehicle owners do not use the car navigation system to navigate the route when driving the vehicle. Some vehicle owners choose to use mobile phone navigation, and some vehicle owners do not need to use navigation because they are familiar with the route, which makes the vehicle terminal need to predict the future driving route of the vehicle in real time to achieve the purpose of realizing the intelligent function of the vehicle.

[0060] Based on this, in the embodiments of the present application, when the intelligent function of the vehicle needs to be used, the vehicle terminal can obtain the first departure time of the vehicle, the first departure location and the position coordinate set of the vehicle in the driving process. Each set of position coordinates in the position coordinate set specifically refers to the latitude and longitude of the vehicle at a certain time in the driving process.

[0061] It should be noted that the driving process of the vehicle specifically refers to the process from the first departure time of the vehicle to the time when the vehicle terminal obtains the above information.

[0062] In some possible embodiments, in order to further improve the prediction accuracy of the future driving route of the vehicle, the vehicle terminal can also obtain first weather information at the first departure time and first date characteristics of the departure date corresponding to the first departure time. The first weather information is used to describe the weather at the first departure time; and the first date characteristics are used to describe whether the departure date corresponding to the first departure time is a holiday.

[0063] In S102, the traveled route of the vehicle is determined according to the position coordinate set.

[0064] In the embodiments of the present application, after obtaining the position coordinate set, the vehicle terminal can determine the traveled route of the vehicle according to the position coordinates of the vehicle at different times contained in the position coordinate set.

[0065] It should be noted that the traveled route specifically refers to the route traveled by the vehicle from the first departure time to the time when the vehicle terminal obtains the above information.

[0066] In S103, the first departure time, the first departure location, the position coordinate set and the traveled route are input into a route prediction model for processing to obtain the target driving route of the vehicle; wherein the route prediction model is a pre-trained neural network model.

[0067] In the embodiment of the present application, after the vehicle terminal obtains the first departure time, the first departure location, the position coordinate set and the traveled route of the vehicle, the first departure time, the first departure location, the position coordinate set and the traveled route are input to the route prediction model for processing, so that the route prediction model predicts the future driving route of the vehicle according to the first departure time, the first departure location, the position coordinate set and the traveled route of the vehicle, thereby obtaining the target driving route of the vehicle.

[0068] As can be seen from the above, the driving route prediction method provided in the embodiment of the present application comprises the following steps: obtaining the first departure time, the first departure location and the position coordinate set of the vehicle in the driving process; determining the traveled route of the vehicle according to the position coordinate set; inputting the first departure time, the first departure location, the position coordinate set and the traveled route to the route prediction model for processing to obtain the target driving route of the vehicle; wherein the route prediction model is a pre-trained neural network model. Compared with the prior art which only predicts the future driving route of the vehicle according to the departure time and the departure location of the vehicle, the method provided in the present application needs to combine the departure time, the departure location, the position coordinate set in the driving process and the traveled route of the vehicle to predict the driving route of the vehicle, thereby improving the prediction accuracy of the driving route.

[0069] Please refer to Figure 2 , Figure 2 The driving route prediction method provided in another embodiment of the present application is described below. Figure 1 In order to further improve the prediction accuracy of the future driving route of the vehicle, in the embodiment, step S103 can specifically include steps S201-S203, which are described in detail as follows:

[0070] In S201, a plurality of standard routes corresponding to the vehicle are obtained, and the feature information corresponding to each of the plurality of standard routes is determined; wherein the feature information includes the departure time, the departure location and the driving position coordinate.

[0071] It should be noted that the standard route refers to a complete route with the highest repetition frequency at the same departure location and end location, which is obtained by statistically analyzing the departure location, the end location and the complete route of the vehicle.

[0072] Specifically, in one embodiment of the present application, the vehicle terminal can determine the standard route of the vehicle through steps S301-S303 as shown in Figure 3 , which are described in detail as follows:

[0073] In S301, a plurality of historical driving routes of the vehicle in a historical time period are acquired, and a starting location and an ending location of each of the historical driving routes are determined.

[0074] In an implementation form of the embodiment, the vehicle terminal can acquire the plurality of historical driving routes of the vehicle in the historical time period in advance and store them in a memory of the vehicle terminal. When the vehicle terminal needs to acquire the plurality of historical driving routes of the vehicle in the historical time period, the vehicle terminal can acquire the plurality of historical driving routes in the historical time period from the memory of the vehicle terminal. The historical time period can be determined according to actual needs, which is not limited here.

[0075] In some possible embodiments, in order to ensure the timeliness of the acquired plurality of historical driving routes, the historical time period can be set as the most recent 30 days before the vehicle terminal needs to acquire the plurality of historical driving routes. For example, assuming that the date when the vehicle terminal needs to acquire the plurality of historical driving routes is November 20, 2022, the historical time period can be the time period from October 22, 2022 to November 21, 2022.

[0076] It should be noted that, since each historical driving route contains position coordinates at different times, the vehicle terminal can determine the starting location and the ending location of each historical driving route according to the position coordinates at different times contained in each historical driving route.

[0077] In S302, the plurality of historical driving routes are divided according to the starting location and the ending location of each of the historical driving routes, to obtain a plurality of route sets; wherein the starting location and the ending location of all historical driving routes in each of the route sets are the same.

[0078] In the embodiment, after the vehicle terminal acquires the plurality of historical driving routes of the vehicle in the historical time period, in order to accurately determine the standard route of the vehicle, the vehicle terminal can divide the historical driving routes according to the starting location and the ending location of each historical driving route, and divide the historical driving routes with the same starting location and ending location into the same route set, that is, the starting location and the ending location of all historical driving routes in each route set are the same.

[0079] In S303, for each of the route sets, the historical driving route with the highest occurrence frequency in the route set is determined as the standard route.

[0080] In this embodiment, after obtaining the plurality of route sets, the vehicle terminal can directly determine the historical driving route with the most travel times in each route set as the standard route of the vehicle, because the starting location and ending location of all historical driving routes in each route set are the same. The historical driving route with the most travel times is used to represent the historical driving route with the most repeated trajectories in the route set.

[0081] In this embodiment, after obtaining the plurality of standard routes of the vehicle, the vehicle terminal can determine the feature information of each standard route, because each standard route is a historical driving route, and each historical driving route includes position coordinates at different time points.

[0082] It should be noted that the driving coordinate positions include a plurality of driving coordinate positions, and each driving coordinate position is used to describe the latitude and longitude of the vehicle at a certain time point.

[0083] In some possible embodiments, in combination with S101, in order to further improve the prediction accuracy of the future driving route of the vehicle, the feature information can further include second weather information and second date characteristics. The second weather information is used to describe the weather on the departure date corresponding to each standard route, and the second date characteristics are used to describe whether the departure date corresponding to each standard route is a holiday.

[0084] In S202, according to the first departure time, the first departure location, the set of position coordinates, the already traveled route, and the feature information of each of the plurality of standard routes, a first difference value corresponding to each of the plurality of standard routes in a plurality of first preset dimensions is calculated.

[0085] It should be noted that the plurality of first preset dimensions include but are not limited to a time dimension, a location dimension, a coordinate dimension, and a route dimension.

[0086] Therefore, in this embodiment, for each standard route, the vehicle terminal can calculate the first difference value corresponding to the already traveled route and the standard route in the time dimension according to the first departure time of the vehicle and the departure time corresponding to the standard route; the vehicle terminal can calculate the first difference value corresponding to the already traveled route and the standard route in the location dimension according to the first departure location of the vehicle and the departure location corresponding to the standard route; the vehicle terminal can calculate the first difference value corresponding to the already traveled route and the standard route in the coordinate dimension according to the set of position coordinates of the vehicle and the driving position coordinates of the standard route; and the vehicle terminal can calculate the first difference value corresponding to the already traveled route and the standard route in the route dimension according to the specific driving trajectory of the already traveled route and the specific driving trajectory of the standard route.

[0087] In combination with S201, in an embodiment of the present application, the plurality of first preset dimensions can further include a weather dimension and a date dimension.

[0088] Based on this, for each standard route, the vehicle terminal can further calculate a first difference value corresponding to the weather dimension between the traveled route and the standard route according to the first weather information corresponding to the traveled route and the second weather information corresponding to the standard route; and the vehicle terminal can further calculate a first difference value corresponding to the date dimension between the traveled route and the standard route according to the first date feature corresponding to the traveled route and the second date feature corresponding to the standard route.

[0089] In S203, the first difference value corresponding to each of the plurality of first preset dimensions between the traveled route and each of the standard routes is input into the route prediction model for processing to obtain the target driving route.

[0090] In the embodiment, after obtaining the first difference value corresponding to each of the plurality of first preset dimensions between the traveled route and each of the standard routes, the vehicle terminal can input the first difference value into the route prediction model for processing, so that the route prediction model predicts the future driving route of the vehicle according to the first difference value, thereby obtaining the target driving route of the vehicle.

[0091] It can be understood that in combination with S202, the vehicle terminal can input the first difference value corresponding to the time dimension between the traveled route and the standard route, the first difference value corresponding to the location dimension between the traveled route and the standard route, the first difference value corresponding to the coordinate dimension between the traveled route and the standard route, and the first difference value corresponding to the route dimension between the traveled route and the standard route, into the route prediction model for processing, so that the route prediction model can accurately predict the future driving route of the vehicle according to the above first difference values.

[0092] In an embodiment of the present application, in combination with S202, the vehicle terminal can input the first difference value corresponding to the time dimension between the traveled route and the standard route, the first difference value corresponding to the location dimension between the traveled route and the standard route, the first difference value corresponding to the coordinate dimension between the traveled route and the standard route, the first difference value corresponding to the route dimension between the traveled route and the standard route, the first difference value corresponding to the weather dimension between the traveled route and the standard route, and the first difference value corresponding to the date dimension between the traveled route and the standard route, into the route prediction model for processing, so that the route prediction model can accurately predict the future driving route of the vehicle according to the above first difference values.

[0093] As can be seen from the above, the route prediction method provided in this embodiment obtains multiple pre-stored standard routes corresponding to the vehicle and determines the feature information corresponding to each of the multiple standard routes. The feature information includes departure time, departure location, and driving position coordinates. Based on the first departure time, first departure location, set of position coordinates, the already traveled route, and the feature information corresponding to each of the multiple standard routes, the method calculates the first difference between the already traveled route and each standard route in multiple first preset dimensions. The first difference between the already traveled route and each standard route in multiple first preset dimensions is input into the route prediction model for processing to obtain the target route. The prediction method provided in this embodiment requires combining the first difference between the already traveled route and each standard route in multiple first preset dimensions to predict the vehicle's future route. Since each of these differences describes the gap between the already traveled route and each standard route, the similarity between the already traveled route and each standard route can be determined based on these differences, thereby accurately predicting the vehicle's target route, thus improving the prediction accuracy of the vehicle's future route.

[0094] Please see Figure 4 , Figure 4 This is another embodiment of the method for predicting driving routes provided in this application. Compared to... Figure 2 In a corresponding embodiment, to further improve the accuracy of predicting the vehicle's future driving route, the on-board terminal needs to train a pre-built neural network model. Therefore, this embodiment may also include S401 to S404 before S203, as detailed below:

[0095] In S401, each historical driving route is split based on set conditions to obtain multiple sub-driving routes corresponding to each historical driving route.

[0096] In S402, the second departure time and the second departure location corresponding to each of the sub-routes are determined.

[0097] In one implementation of this embodiment, the setting condition can be: an additive splitting method. The additive splitting method refers to using the starting point of the historical driving route as the starting point of all sub-driving routes of that historical driving route, and the length of the current sub-driving route is the sum of the length of the previous sub-driving route and a preset length. The preset length can be determined according to actual needs and is not limited here.

[0098] For example, please refer to Figure 5 , Figure 5 This is a schematic diagram illustrating the principle of the cumulative splitting method provided in the embodiments of this application. For example... Figure 5As shown, the line segment L is a complete historical driving route, the line segment l1 is a first sub-driving route of the historical driving route, the line segment l2 is a second sub-driving route of the historical driving route, the line segment l3 is a third sub-driving route of the historical driving route, the line segment l4 is a fourth sub-driving route of the historical driving route, and so on, and the line segment ln is an n-th sub-driving route of the historical driving route.

[0099] In this embodiment, since each historical driving route contains position coordinates at different time points, for each historical driving route, the vehicle terminal can determine the second departure time and the second departure location corresponding to each sub-driving route of the historical driving route according to the position coordinates at different time points contained in the historical driving route.

[0100] In some possible embodiments, in order to improve the prediction accuracy of the route prediction model, the vehicle terminal can further obtain third weather information at the second departure time and a third date feature of the departure date corresponding to the second departure time. The third weather information is used to describe the weather at the second departure time, and the third date feature is used to describe whether the departure date corresponding to the second departure time is a holiday.

[0101] In S403, for each sub-driving route, a second difference value corresponding to each of the sub-driving route and the standard route in each of the first preset dimensions is calculated according to the second departure time, the second departure time, the position coordinates of the sub-driving route, and the feature information corresponding to each of the standard routes.

[0102] It should be noted that the plurality of first preset dimensions include but are not limited to the time dimension, the location dimension, the coordinate dimension, and the route dimension.

[0103] Therefore, in this embodiment, for each sub-driving route, the vehicle terminal can calculate a second difference value corresponding to each of the sub-driving route and the standard route in the time dimension according to the second departure time corresponding to the sub-driving route and the departure time corresponding to each of the standard routes; the vehicle terminal can calculate a second difference value corresponding to each of the sub-driving route and the standard route in the location dimension according to the second departure location corresponding to the sub-driving route and the departure location corresponding to each of the standard routes; the vehicle terminal can calculate a second difference value corresponding to each of the sub-driving route and the standard route in the coordinate dimension according to the position coordinates of the sub-driving route and the driving position coordinates of each of the standard routes; and the vehicle terminal can calculate a second difference value corresponding to each of the sub-driving route and the standard route in the route dimension according to the specific driving trajectory of the sub-driving route and the specific driving trajectory of each of the standard routes.

[0104] In combination with S402, in an embodiment of the present application, the plurality of first preset dimensions can further include a weather dimension and a date dimension.

[0105] Based on this, for each sub-driving route, the vehicle terminal can further calculate a second difference value corresponding to each of the plurality of standard routes and the sub-driving route in the weather dimension according to the third weather information corresponding to the sub-driving route and the second weather information corresponding to each of the plurality of standard routes; and the vehicle terminal can further calculate a second difference value corresponding to each of the plurality of standard routes and the sub-driving route in the date dimension according to the third date feature corresponding to the sub-driving route and the second date feature corresponding to each of the plurality of standard routes.

[0106] In S404, the neural network model is trained according to the second difference value corresponding to each of the plurality of standard routes and each sub-driving route in the plurality of first preset dimensions, to obtain the route prediction model.

[0107] In the embodiment, after obtaining the second difference value corresponding to each of the plurality of standard routes and each sub-driving route in the plurality of first preset dimensions, the vehicle terminal can train the neural network model according to the second difference value to obtain the route prediction model.

[0108] It can be understood that in combination with S403, the vehicle terminal can train the neural network model according to the second difference value corresponding to each of the plurality of standard routes and each sub-driving route in the time dimension, the second difference value corresponding to each of the plurality of standard routes and each sub-driving route in the location dimension, the second difference value corresponding to each of the plurality of standard routes and each sub-driving route in the coordinate dimension, and the second difference value corresponding to each of the plurality of standard routes and each sub-driving route in the route dimension.

[0109] In an embodiment of the present application, in combination with S403, the vehicle terminal can further train the neural network model according to the second difference value corresponding to each of the plurality of standard routes and each sub-driving route in the time dimension, the second difference value corresponding to each of the plurality of standard routes and each sub-driving route in the location dimension, the second difference value corresponding to each of the plurality of standard routes and each sub-driving route in the coordinate dimension, the second difference value corresponding to each of the plurality of standard routes and each sub-driving route in the route dimension, the second difference value corresponding to each of the plurality of standard routes and each sub-driving route in the weather dimension, and the second difference value corresponding to each of the plurality of standard routes and each sub-driving route in the date dimension.

[0110] In an embodiment of the present application, the vehicle terminal can specifically train the neural network model through S501-S504 as shown in Figure 6 The details are as follows:

[0111] In S501, the second difference of each sub travel route and each standard route in each of the first preset dimensions is respectively associated with the historical travel route corresponding to the sub travel route.

[0112] In this embodiment, the vehicle terminal can associate the second difference of each sub travel route and each standard route in each of the first preset dimensions with the historical travel route corresponding to the sub travel route, that is, the second difference and the historical travel route have a corresponding relationship.

[0113] In S502, the third difference of each historical travel route and each standard route in each of the second preset dimensions is calculated.

[0114] It should be noted that the second preset dimensions include but are not limited to the start point dimension, the end point dimension, and the route dimension.

[0115] Therefore, in this embodiment, for each historical travel route, the vehicle terminal can calculate the third difference of the historical travel route and the standard route in the start point dimension according to the starting location of the historical sub travel route and the starting location corresponding to the standard route; the vehicle terminal can calculate the third difference of the historical travel route and the standard route in the end point dimension according to the ending location of the historical sub travel route and the ending location corresponding to the standard route; and the vehicle terminal can calculate the third difference of the historical travel route and the standard route in the route dimension according to the specific travel trajectory of the historical sub travel route and the specific travel trajectory of the standard route.

[0116] In S503, the target standard route corresponding to each historical travel route is determined according to the third difference, and each historical travel route is labeled based on the target standard route.

[0117] In this embodiment, after obtaining the third difference, the vehicle terminal can compare the third difference with a set threshold. The set threshold can be determined according to actual needs, which is not limited here.

[0118] The vehicle terminal can determine the target standard route corresponding to each historical travel route according to the comparison result between the third difference and the set threshold.

[0119] In an embodiment of the present application, in combination with S502, for each historical driving route, since the third difference includes but is not limited to: the third difference of the historical driving route and each of the plurality of standard routes in the starting point dimension, the third difference of the historical driving route and each of the plurality of standard routes in the terminal point dimension, and the third difference of the historical driving route and each of the plurality of standard routes in the route dimension, therefore, the threshold value includes but is not limited to the first threshold value, the second threshold value and the third threshold value. Wherein the first threshold value can be any value in [0, 1km], such as 500m, 1km, etc., the second threshold value can be any value in [0, 1km], such as 500m, 1km, etc., and the third threshold value can be any value in [80%, 99%], such as 80%, 95%, etc.

[0120] Based on this, the vehicle terminal can specifically determine the target standard route corresponding to each historical driving route according to the following steps, which are described in detail as follows:

[0121] For each of the historical driving routes, if the third difference of the historical driving route and one of the plurality of standard routes in the starting point dimension is less than or equal to the first threshold value, the third difference in the terminal point dimension is less than or equal to the second threshold value, and the route similarity calculated according to the third difference in the route dimension is greater than or equal to the third threshold value, then the one standard route is determined as the target standard route corresponding to the historical driving route.

[0122] In this embodiment, for each historical driving route, the vehicle terminal detects that the third difference of the historical driving route and a certain standard route in the plurality of standard routes in the starting point dimension is less than or equal to the first threshold value, the third difference in the terminal point dimension is less than or equal to the second threshold value, and the route similarity calculated according to the third difference in the route dimension is greater than or equal to the third threshold value, then the above certain standard route is determined as the target standard route corresponding to the historical driving route.

[0123] In an embodiment of the present application, the vehicle terminal can calculate the route similarity according to the Hausdorff distance and the third difference in the route dimension.

[0124] In another embodiment of the present application, the vehicle terminal can also calculate the route similarity according to the longest common subsequence (LCS) algorithm and the third difference in the route dimension.

[0125] In this embodiment, after the vehicle terminal determines the target standard route corresponding to each historical driving route, it can set a label for the historical driving route based on the target standard route.

[0126] In S504, the neural network model is trained according to each of the historical travel routes carrying the label and the third difference value associated with each of the historical travel routes, to obtain the route prediction model.

[0127] In this embodiment, after obtaining each of the historical travel routes carrying the label and the third difference value associated with each of the historical travel routes, the vehicle terminal can train the neural network model according to each of the historical travel routes carrying the label and the third difference value associated with each of the historical travel routes, to obtain the route prediction model.

[0128] As can be seen from the above, the prediction method of the travel route provided in this embodiment splits each of the historical travel routes based on the set conditions to obtain a plurality of sub travel routes corresponding to each of the historical travel routes; determines a second departure time and a second departure location corresponding to each of the sub travel routes; for each of the sub travel routes, calculates a second difference value corresponding to each of the sub travel routes and each of the standard routes in a plurality of first preset dimensions according to the second departure time, the second departure location, the position coordinates of the sub travel route, and the feature information corresponding to each of the plurality of standard routes; and trains the neural network model according to the second difference value corresponding to each of the sub travel routes and each of the standard routes in the plurality of first preset dimensions, to obtain the route prediction model. The prediction method provided in this embodiment trains the neural network model according to the calculated second difference value corresponding to each of the sub travel routes and each of the standard routes in the plurality of first preset dimensions, which can improve the prediction accuracy of the route prediction model in the later stage.

[0129] In another embodiment of the present application, after obtaining the target travel route of the vehicle, the vehicle terminal can further perform the following steps:

[0130] determining a target location where the vehicle travels and a plurality of target travel positions corresponding to the vehicle according to the target travel route;

[0131] calling a set map interface to cause the map interface to output environment information and travel information of the vehicle under the target travel route according to the target location and the plurality of target travel positions.

[0132] In this embodiment, after obtaining the target travel route of the vehicle, the vehicle terminal can determine a target location where the vehicle travels and a plurality of target travel positions corresponding to the vehicle according to the target travel route, because the target travel route is a standard route, and each standard route includes its corresponding travel coordinate position and end location.

[0133] Based on this, the vehicle terminal can call the set map interface to make the map interface output the environmental information and driving information of the vehicle on the target driving route according to the target location and the plurality of target driving positions. The set map interface can be determined according to actual needs, and is not limited here.

[0134] In this embodiment, the environmental information includes but is not limited to the area where the vehicle is located, the road condition information of the area, and the distance between the current location of the vehicle and the end location of the target driving route, etc. The driving information includes but is not limited to the vehicle speed of the vehicle, etc.

[0135] As can be seen from the above, the driving route prediction method provided in this embodiment can determine the target location of the vehicle and the plurality of target driving positions corresponding to the vehicle directly according to the target driving route of the vehicle after obtaining the target driving route of the vehicle; call the set map interface to make the map interface output the environmental information and driving information of the vehicle on the target driving route according to the target location and the plurality of target driving positions, so that the vehicle terminal can still obtain the environmental information and driving information of the vehicle on the target driving route according to the predicted target driving route when the user does not use the car navigation system of the vehicle and cannot obtain the navigation data of the vehicle in real time, that is, the intelligent function of the vehicle is realized.

[0136] It should be understood that the size of the serial number of each step in the above embodiment does not mean the order of execution, and the execution order of each process should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0137] corresponding to the driving route prediction method described in the above embodiments, Figure 7 A structure block diagram of a driving route prediction device provided by an embodiment of the present application is shown, only the parts related to the embodiments of the present application are shown for ease of description. For reference Figure 7 The driving route prediction device 700 includes a first acquisition unit 71, a first determination unit 72, and a first processing unit 73. Wherein:

[0138] The first acquisition unit 71 is configured to acquire a first departure time, a first departure location, and a set of position coordinates of the vehicle in the driving process.

[0139] The first determination unit 72 is configured to determine the traveled route of the vehicle according to the set of position coordinates.

[0140] The first processing unit 73 is configured to input the first departure time, the first departure location, the set of position coordinates, and the traveled route to a route prediction model for processing to obtain the target driving route of the vehicle; wherein the route prediction model is a pre-trained neural network model.

[0141] In an embodiment of the present application, the first processing unit 72 specifically comprises a second obtaining unit, a first calculating unit and a second processing unit. Wherein:

[0142] The second obtaining unit is configured to obtain a plurality of standard routes corresponding to the vehicle and determine feature information corresponding to each of the plurality of standard routes; wherein the feature information comprises a departure time, a departure location and a driving position coordinate.

[0143] The first calculating unit is configured to calculate a first difference corresponding to each of the standard routes in a plurality of first preset dimensions based on the first departure time, the first departure location, the set of position coordinates, the driven route and the feature information corresponding to each of the plurality of standard routes.

[0144] The second processing unit is configured to input the first difference corresponding to each of the standard routes in the plurality of first preset dimensions to the route prediction model for processing to obtain the target driving route.

[0145] In an embodiment of the present application, the second obtaining unit specifically comprises a third obtaining unit, a second determining unit and a third determining unit. Wherein:

[0146] The third obtaining unit is configured to obtain a plurality of historical driving routes of the vehicle in a historical time period and determine a departure location and an end location of each of the historical driving routes.

[0147] The second determining unit is configured to divide the plurality of historical driving routes based on the departure location and the end location of each of the historical driving routes to obtain a plurality of route sets; wherein the departure location and the end location of all historical driving routes in each of the route sets are the same.

[0148] The third determining unit is configured to determine, for each of the route sets, a historical driving route with the highest occurrence frequency in the route set as the standard route.

[0149] In an embodiment of the present application, the driving route prediction device 700 further comprises a splitting unit, a fourth determining unit, a second calculating unit and a first training unit. Wherein:

[0150] The splitting unit is configured to split each of the historical driving routes based on a set condition to obtain a plurality of sub-driving routes corresponding to each of the historical driving routes.

[0151] The fourth determining unit is configured to determine a second departure time and a second departure location corresponding to each of the sub-driving routes.

[0152] The second computing unit is configured to, for each of the sub travel routes, calculate a second difference value corresponding to each of the sub travel routes and each of the standard routes in the plurality of first preset dimensions according to the second departure time, the second departure time, position coordinates of the sub travel route, and feature information corresponding to each of the standard routes.

[0153] The first training unit is configured to train the neural network model according to the second difference value corresponding to each of the sub travel routes and each of the standard routes in the plurality of first preset dimensions, to obtain the route prediction model.

[0154] In an embodiment of the present application, the first training unit specifically includes an association unit, a third computing unit, a setting unit, and a second training unit. Wherein:

[0155] The association unit is configured to associate the second difference value corresponding to each of the sub travel routes and each of the standard routes in the plurality of first preset dimensions with the historical travel route corresponding to each of the sub travel routes respectively.

[0156] The third computing unit is configured to calculate a third difference value corresponding to each of the historical travel routes and each of the standard routes in a plurality of second preset dimensions.

[0157] The setting unit is configured to determine a target standard route corresponding to each of the historical travel routes according to the third difference value, and set a label for each of the historical travel routes based on the target standard route.

[0158] The second training unit is configured to train the neural network model according to each of the historical travel routes carrying a label and the third difference value associated with each of the historical travel routes, to obtain the route prediction model.

[0159] In an embodiment of the present application, the plurality of second preset dimensions includes a start point dimension, an end point dimension, and a route dimension; and the setting unit specifically includes a fifth determination unit.

[0160] The fifth determination unit is configured to, for each of the historical travel routes, if the third difference value of the historical travel route and one of the standard routes in the start point dimension is less than or equal to a first threshold value, the third difference value of the historical travel route and the one of the standard routes in the end point dimension is less than or equal to a second threshold value, and a route similarity calculated according to the third difference value of the historical travel route and the one of the standard routes in the route dimension is greater than or equal to a third threshold value, determine that the one of the standard routes is the target standard route corresponding to the historical travel route.

[0161] In an embodiment of the present application, the route prediction device 700 further includes a sixth determination unit and an output unit. Wherein:

[0162] The sixth determining unit is configured to determine a target location of the vehicle and a plurality of target driving positions corresponding to the vehicle according to the target driving route.

[0163] The output unit is configured to call a set map interface to output environment information and driving information of the vehicle under the target driving route according to the target location and the plurality of target driving positions.

[0164] It should be noted that the information interaction and execution process between the above devices / units are based on the same concept as the method embodiments of the present application, and the specific functions and technical effects can be referred to the method embodiments part, which will not be repeated here.

[0165] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above-mentioned division of functional units and modules is exemplified, and in actual application, the above-mentioned functions can be completed by different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the above-described functions. The functional units and modules in the embodiments can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be realized in the form of hardware or software function unit. In addition, the specific name of each functional unit and module is only for easy distinction, and does not limit the protection scope of the present application. The specific working process of the units and modules in the system can refer to the corresponding process in the foregoing method embodiments, which will not be repeated here.

[0166] Figure 8 The structure schematic diagram of the vehicle terminal provided by an embodiment of the present application is shown in FIG. 8. As shown in the figure, the vehicle terminal 8 of the embodiment includes at least one processor 80 (only one processor is shown in the figure), a memory 81, and a computer program 82 stored in the memory 81 and executable on the at least one processor 80, wherein the processor 80 executes the computer program 82 to implement the steps in any of the above-mentioned driving route prediction method embodiments. Figure 8 Figure 8 The vehicle terminal can include, but is not limited to, the processor 80 and the memory 81. Those skilled in the art can understand that the vehicle terminal 8 shown in the figure is only an example, and does not constitute a limitation on the vehicle terminal 8, and can include more or fewer components than shown in the figure, or combine certain components, or different components, for example, can also include input / output devices, network access devices, etc.

[0167] The vehicle terminal can include, but is not limited to, the processor 80 and the memory 81. Those skilled in the art can understand that the vehicle terminal 8 shown in the figure is only an example, and does not constitute a limitation on the vehicle terminal 8, and can include more or fewer components than shown in the figure, or combine certain components, or different components, for example, can also include input / output devices, network access devices, etc. Figure 8 The vehicle terminal can include, but is not limited to, the processor 80 and the memory 81. Those skilled in the art can understand that the vehicle terminal 8 shown in the figure is only an example, and does not constitute a limitation on the vehicle terminal 8, and can include more or fewer components than shown in the figure, or combine certain components, or different components, for example, can also include input / output devices, network access devices, etc.​

[0168] The processor 80 can be a central processing unit (CPU), and can also be other general-purpose processors, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0169] The memory 81 can be an internal storage unit of the vehicle terminal 8, such as a memory of the vehicle terminal 8, in some embodiments. The memory 81 can also be an external storage device of the vehicle terminal 8, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the vehicle terminal 1, in other embodiments. Further, the memory 81 can include both the internal storage unit and the external storage device of the vehicle terminal 8. The memory 81 is used to store an operating system, an application program, a boot loader, data, and other programs, such as program codes of the computer program, etc. The memory 81 can also be used to temporarily store data that has been output or is to be output.

[0170] The embodiments of the present application further provide a computer readable storage medium storing a computer program, and the computer program is executed by a processor to implement the steps in the above various method embodiments.

[0171] The embodiments of the present application provide a computer program product, and when the computer program product is run on a vehicle terminal, the vehicle terminal is caused to implement the steps in the above various method embodiments.

[0172] The integrated unit, if implemented in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, all or part of the processes in the above-mentioned embodiment methods can be completed by instructing related hardware through a computer program. The computer program can be stored in a computer readable storage medium, and the computer program can implement the steps of each method embodiment when executed by a processor. The computer program includes computer program code, which can be in the form of source code, object code, executable files or some intermediate forms. The computer readable medium at least includes any entity or device capable of carrying the computer program code to the vehicle terminal, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium. For example, U disk, mobile hard disk, magnetic disk or optical disk, etc. In some jurisdictions, according to legislation and patent practice, the computer readable medium cannot be an electrical carrier signal and a telecommunication signal.

[0173] In the above embodiments, the description of each embodiment has its own focus, and the parts not described or recorded in detail in a certain embodiment can be referred to the relevant description of other embodiments.

[0174] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A travel route prediction method characterized by comprising: The method comprises: obtaining a first departure time, a first departure location and a set of position coordinates of the vehicle during driving; determining a traveled route of the vehicle according to the set of position coordinates; inputting the first departure time, the first departure location, the set of position coordinates and the traveled route into a route prediction model for processing to obtain a target driving route of the vehicle; wherein the route prediction model is a pre-trained neural network model; the inputting the first departure time, the first departure location, the set of position coordinates and the traveled route into the route prediction model for processing to obtain the target driving route of the vehicle comprises: obtaining a plurality of standard routes corresponding to the vehicle and determining feature information corresponding to each of the plurality of standard routes; wherein the feature information comprises a departure time, a departure location and driving position coordinates; the standard route refers to a historical driving route with the highest occurrence frequency in a route set with the same departure location and end location; calculating first difference values corresponding to each of the standard routes and the traveled route in a plurality of first preset dimensions according to the first departure time, the first departure location, the set of position coordinates, the traveled route and the feature information corresponding to each of the plurality of standard routes; the plurality of first preset dimensions comprise a time dimension, a location dimension, a coordinate dimension and a route dimension; inputting the first difference values corresponding to each of the standard routes and the traveled route in the plurality of first preset dimensions into the route prediction model for processing to obtain the target driving route.

2. The prediction method of claim 1, wherein, the obtaining the plurality of standard routes corresponding to the vehicle comprises: obtaining a plurality of historical driving routes of the vehicle in a historical time period and determining a departure location and an end location of each of the historical driving routes; dividing the plurality of historical driving routes according to the departure location and the end location of each of the historical driving routes to obtain a plurality of route sets; wherein the departure location and the end location of all historical driving routes in each of the route sets are the same; for each of the route sets, determining a historical driving route with the highest occurrence frequency in the route set as the standard route.

3. The prediction method of claim 2, wherein, before the inputting the first difference values corresponding to each of the standard routes and the traveled route in the plurality of first preset dimensions into the route prediction model for processing to obtain the target driving route, the method further comprises: splitting each of the historical driving routes based on a set condition to obtain a plurality of sub-driving routes corresponding to each of the historical driving routes; determining a second departure time and a second departure location corresponding to each of the sub-driving routes; for each of the sub-driving routes, calculating second difference values corresponding to each of the standard routes and the sub-driving route in the plurality of first preset dimensions according to the second departure time, the second departure time, position coordinates of the sub-driving route and the feature information corresponding to each of the plurality of standard routes; The neural network model is trained according to the second difference value corresponding to each of the sub travel routes and each of the standard routes in the plurality of first preset dimensions, to obtain the route prediction model.

4. The prediction method of claim 3, wherein, The training of the neural network model according to the second difference value corresponding to each of the sub travel routes and each of the standard routes in the plurality of first preset dimensions comprises: associating the second difference value corresponding to each of the sub travel routes and each of the standard routes in the plurality of first preset dimensions with the historical travel route corresponding to each of the sub travel routes respectively; calculating a third difference value corresponding to each of the historical travel routes and each of the standard routes in a plurality of second preset dimensions; determining a target standard route corresponding to each of the historical travel routes according to the third difference value, and setting a label for each of the historical travel routes based on the target standard route; training the neural network model according to each of the historical travel routes carrying a label and the third difference value associated with each of the historical travel routes, to obtain the route prediction model.

5. The prediction method of claim 4, wherein, The plurality of second preset dimensions include a starting point dimension, an ending point dimension, and a route dimension; and the determination of the target standard route corresponding to each of the historical travel routes according to the third difference value comprises: for each of the historical travel routes, if the third difference value of the historical travel route and one of the standard routes in the starting point dimension is less than or equal to a first threshold value, the third difference value of the historical travel route and the one of the standard routes in the ending point dimension is less than or equal to a second threshold value, and the route similarity calculated according to the third difference value of the route dimension is greater than or equal to a third threshold value, then the one of the standard routes is determined as the target standard route corresponding to the historical travel route.

6. The prediction method according to any one of claims 1 to 5, characterized in that, After inputting the first departure time, the first departure location, the set of position coordinates, and the traveled route into the route prediction model for processing to obtain the target travel route of the vehicle, the method further comprises: determining a target location of the vehicle and a plurality of target travel positions corresponding to the vehicle according to the target travel route; calling a set map interface to enable the map interface to output environmental information and travel information of the vehicle under the target travel route according to the target location and the plurality of target travel positions.

7. A travel route prediction device characterized by comprising: comprises: a first acquisition unit configured to acquire a first departure time, a first departure location, and a set of position coordinates of a vehicle during travel; a first determination unit configured to determine a traveled route of the vehicle according to the set of position coordinates; a first processing unit configured to input the first departure time, the first departure location, the set of position coordinates, and the traveled route into a route prediction model for processing to obtain a target travel route of the vehicle; wherein the route prediction model is a pre-trained neural network model; the first processing unit specifically comprises: A second obtaining unit is configured to obtain a plurality of pre-stored standard routes corresponding to the vehicle, and determine characteristic information corresponding to each of the plurality of standard routes; wherein the characteristic information comprises a departure time, a departure location, and a driving position coordinate; and the standard route indicates a historical driving route with the most occurrences in a route set with the same departure location and end location. A first calculating unit is configured to calculate, according to the first departure time, the first departure location, the set of position coordinates, the driven route, and the characteristic information corresponding to each of the plurality of standard routes, a first difference value corresponding to each of the driven route and each of the standard routes in a plurality of first preset dimensions; and the plurality of first preset dimensions comprises a time dimension, a location dimension, a coordinate dimension, and a route dimension. A second processing unit is configured to input the first difference value corresponding to each of the driven route and each of the standard routes in the plurality of first preset dimensions into the route prediction model for processing, to obtain the target driving route.

8. An in-vehicle terminal comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor executes the computer program to implement the driving route prediction method of any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 8. The computer program is executed by the processor to implement the driving route prediction method of any one of claims 1 to 6.

Images