A big data-based residual driving time length prediction method and computer device

Abstract

This invention discloses a method and computer device for predicting remaining driving time based on big data. The method includes obtaining a navigation route from the origin to the destination of a first vehicle; dividing the navigation route into multiple navigation segments; determining the predicted driving time for any navigation segment not yet traversed by the first vehicle based on the actual driving time taken by a second vehicle traversing that segment; and determining the remaining driving time of the first vehicle based on the sum of the predicted driving times for all untraversed navigation segments. This invention can determine the predicted driving time for a vehicle traversing a route not yet traversed by the first vehicle based on the actual driving time taken by other vehicles traversing routes not yet traversed by the first vehicle, resulting in more accurate predictions. By segmenting the navigation route and obtaining the actual driving conditions of other vehicles in each segment, it can more precisely reflect the differences between road segments, resulting in smaller errors. This invention has wide applications in the field of automotive technology.

Description

Technical Field

[0001] This invention relates to the field of automotive technology, and in particular to a method and computer device for predicting remaining driving time based on big data. Background Technology

[0002] During driving, there is a need to estimate the remaining travel time from the current location to the destination. Accurately estimating the remaining travel time helps drivers and passengers plan their trips reasonably, and also helps prevent dangerous driving behaviors caused by unreasonable time arrangements, thus maintaining traffic safety.

[0003] Current technologies typically estimate the remaining travel time by detecting the vehicle's current speed and the remaining distance from the current location to the destination. However, these technologies rely on idealized models, resulting in rough and distorted estimates that often differ significantly from the actual travel time from the current location to the destination. Summary of the Invention

[0004] In view of the technical problems such as the inaccuracy of current technology in estimating remaining driving time, the purpose of this invention is to provide a method and computer device for predicting remaining driving time based on big data.

[0005] On one hand, embodiments of the present invention include a method for predicting remaining driving time based on big data, the method comprising:

[0006] Obtain the origin and destination of the first vehicle;

[0007] Obtain the navigation route from the departure point to the destination;

[0008] The navigation route is divided into multiple navigation segments;

[0009] For any of the navigation segments that the first vehicle has not passed through, the predicted travel time corresponding to the navigation segment is determined based on the actual travel time taken by the second vehicle to pass through the navigation segment; the second vehicle is the vehicle that passed through the navigation segment before the first vehicle;

[0010] The remaining travel time of the first vehicle is determined based on the total predicted travel time of all the navigation segments that have not been traversed.

[0011] Furthermore, dividing the navigation route into multiple navigation segments includes:

[0012] Select a trial split point on the navigation route;

[0013] At the location corresponding to the trial segmentation point, obtain the average value of the first position corresponding to each of the second vehicles;

[0014] Starting from the trial segmentation point, the search is performed to obtain the average value of the second position corresponding to each second vehicle at the position corresponding to the point on the navigation route;

[0015] When it is detected that the deviation between the second position average and the first position average is greater than a threshold, the point on the navigation route corresponding to the second position average that has a deviation greater than the threshold and is closest to the first position average is set as a determination split point;

[0016] A navigation segment is defined by the portion of the navigation route between two adjacent defined dividing points.

[0017] Further, the step of selecting a trial split point on the navigation route includes:

[0018] The points on the navigation route corresponding to the starting point are determined as the trial split point and the confirmed split point;

[0019] Once a navigation segment is determined, one of the determined dividing points in the navigation segment is designated as a new trial dividing point.

[0020] Further, defining a navigation segment as the portion of the navigation route between two adjacent defined dividing points includes:

[0021] Set the minimum segment length;

[0022] When the portion of the navigation route between two adjacent defined dividing points is not less than the minimum segment length, the portion of the navigation route between two adjacent defined dividing points is defined as a navigation segment.

[0023] When the portion of the navigation route between two adjacent defined dividing points is less than the minimum segment length, the next defined dividing point between the two adjacent defined dividing points is searched, and the portion of the navigation route between the two adjacent defined dividing points and the next defined dividing point is determined as a navigation segment.

[0024] Further, determining the predicted travel time corresponding to the navigation segment based on the actual travel time of the second vehicle traversing the navigation segment includes:

[0025] Obtain the actual travel time of all second vehicles traversing the navigation segment;

[0026] Determine the average duration of the actual travel time consumed by all the second vehicles;

[0027] The average duration is determined as the predicted travel time corresponding to the navigation segment.

[0028] Further, determining the average actual driving time consumed by all the second vehicles includes:

[0029] Calculate the arithmetic mean of the actual driving time consumed by all the second vehicles, and use it as the average time.

[0030] Further, determining the average actual driving time consumed by all the second vehicles includes:

[0031] Determine the driving environment parameters for each of the second vehicles on the navigation route;

[0032] Using the driving environment parameters as weights, a weighted average of the actual driving time consumed by all the second vehicles is calculated, which is then used as the average duration.

[0033] Furthermore, the method for predicting remaining driving time based on big data also includes:

[0034] From each of the navigation segments, determine the segments that the first vehicle has already passed and the segments that it has not yet passed;

[0035] Obtain the actual travel time of the first vehicle on the already traversed road segment;

[0036] Based on the deviation between the actual travel time of the already traversed road segments and the corresponding predicted travel time, the predicted travel time for the untraversed road segments is adjusted.

[0037] Further, adjusting the predicted travel time for the untraveled road segments based on the deviation between the actual travel time and the corresponding predicted travel time of the already traversed road segments includes:

[0038] Based on the driving environment parameters of the second vehicle on the already traversed road section and the driving environment parameters of the second vehicle on the untraversed road section, an adjustment coefficient is determined;

[0039] The time adjustment value is determined based on the deviation between the actual travel time of the already traversed road segment and the corresponding predicted travel time, and the adjustment coefficient.

[0040] Based on the time adjustment value, the predicted travel time corresponding to the unpassed road segment is adjusted.

[0041] On the other hand, embodiments of the present invention include a computer device including a memory and a processor, the memory being used to store at least one program, and the processor being used to load the at least one program to execute the big data-based remaining driving time prediction method of the embodiments.

[0042] The beneficial effects of this invention are as follows: The big data-based remaining driving time prediction method in the embodiments can determine the predicted driving time of the vehicle when traveling a route that the vehicle has not traveled before, based on the actual driving time consumed by other vehicles when traveling a route that the vehicle has not traveled before. The prediction is based on the actual driving conditions of other vehicles. Compared with predicting solely based on the conditions of the vehicle itself, it can obtain more accurate prediction results. By segmenting the navigation route and obtaining the actual driving conditions of other vehicles in each segment, the final prediction results can more accurately reflect the differences between road segments and have smaller errors. Attached Figure Description

[0043] Figure 1 This is a flowchart of the remaining driving time prediction method based on big data in the embodiment;

[0044] Figure 2 This is a schematic diagram of a system in which a big data-based method for predicting remaining driving time can be applied in the embodiments.

[0045] Figure 3 This is a schematic diagram of the navigation route and navigation segments in the embodiment;

[0046] Figure 4 This is a schematic diagram illustrating the principle of segmenting the navigation route in the embodiment. Detailed Implementation

[0047] In this embodiment, refer to Figure 1 The method for predicting remaining driving time based on big data includes the following steps:

[0048] S1. Obtain the origin and destination of the first vehicle;

[0049] S2. Obtain navigation routes from the origin to the destination;

[0050] S3. Divide the navigation route into multiple navigation segments;

[0051] S4. For any navigation segment, determine the predicted travel time corresponding to the navigation segment based on the actual travel time taken by the second vehicle to pass through the navigation segment; the second vehicle is the vehicle that passed through the navigation segment before the first vehicle;

[0052] S5. Determine the remaining travel time of the first vehicle based on the total predicted travel time of all untraveled navigation segments.

[0053] In this embodiment, the remaining driving time prediction method based on big data can be applied to... Figure 2 The system shown. Figure 2 The system includes multiple vehicles, such as Vehicle 1, Vehicle 21, and Vehicle 22. These vehicles are equipped with data processing modules, such as ECUs, which have functions including data acquisition, processing, and output. These data processing modules can install functional software such as navigation software, and also have communication modules capable of direct external communication or communication via mobile phones or other terminals carried by passengers. The communication modules can access the internet via wireless communication protocols such as 5G, establishing a connection with a server, thereby enabling the server to transmit data with the data processing modules of each vehicle.

[0054] In this embodiment, the first vehicle is referred to as "this vehicle," which is the vehicle whose remaining driving time needs to be obtained by executing the remaining driving time prediction method based on big data; the second vehicle is referred to as "other vehicles" besides "this vehicle" for illustration. When a second vehicle i needs to obtain its remaining driving time by executing the remaining driving time prediction method based on big data, then this second vehicle i becomes "this vehicle," that is, the first vehicle.

[0055] During the execution of steps S1-S5, the first vehicle can perform steps S1-S5. In step S4, the first vehicle queries the server, and the server returns data such as the actual travel time of the second vehicle traversing the navigation route. Alternatively, the first vehicle can perform steps S1-S2 and upload the obtained navigation route to the server. The server then performs steps S3-S5, returning the remaining travel time of the first vehicle to the first vehicle.

[0056] Regardless of the form in which the big data-based remaining driving time prediction method is implemented, the server and each vehicle (including the first vehicle and the second vehicle 1, the second vehicle 2, and all other second vehicles) can legally obtain the data uploaded by each vehicle through an agreement. This includes location data indicating the current location, as well as driving data indicating the current speed, acceleration, throttle depth, or the time spent passing through a specific road segment.

[0057] In this embodiment, steps S1-S5 performed by the first vehicle are used as an example for explanation.

[0058] In step S1, the first vehicle can set its departure and destination using the navigation software installed in the vehicle. Generally, in a given trip, the destination remains unchanged, while the departure point can be static, i.e., the starting point of the entire trip. However, since the navigation software continuously detects the vehicle's latest position to execute the navigation algorithm, the departure point can also be dynamically changing, i.e., the vehicle's latest position, i.e., the starting point of the remaining route traveled by the vehicle. Regardless of the form of the departure point, steps S1-S5 can be executed.

[0059] In step S2, the first vehicle executes a navigation algorithm using its local navigation software to calculate a navigation route based on the origin and destination. The starting point of the navigation route is the origin, and the ending point is the destination. The navigation route can be stored as an array, containing the latitude and longitude coordinates of each point it passes through.

[0060] In step S3, refer to Figure 3 The curve represents the navigation route from origin A to destination B. Based on a server-defined segmentation rule, the route can be divided into L1, L2, L3…L… segments using specific, standardized locations along the route as dividing points. m Multiple navigation segments, where each segment is part of the navigation route. For example, the navigation route can be divided into equal parts, with each resulting segment being of equal length.

[0061] In step S4, the first vehicle sends a query to the server to request the predicted travel time of each navigation segment relative to the first vehicle, which is the actual travel time of the second vehicle when passing through this navigation segment.

[0062] For example, if the first vehicle is currently in navigation segment L1 and is about to enter navigation segment L2, then for the first vehicle, L2, L3...L m The navigation routes are all sections that the first vehicle has not yet traversed, while the second vehicle has already passed through L2, L3...L...L... m The navigation section, meaning the second vehicle passed through L2, L3...L before the first vehicle. m Vehicles waiting for navigation on the designated route.

[0063] In step S4, the first vehicle can request the server to query L2, L3...L m The actual travel time consumed when a second vehicle passes through each navigation segment.

[0064] For example, if a road segment L2 that has not been traversed is traversed by multiple second vehicles, and the average actual travel time is t2, then we can determine that the actual travel time of the second vehicle traversing the navigation road segment L2 is t2, meaning the predicted travel time for navigation road segment L2 is t2. Similarly, we can determine the predicted travel time for navigation road segment L3 as t3, and so on... m The corresponding predicted travel time is t m .

[0065] In this embodiment, when the server obtains the actual travel time of the second vehicle through a certain navigation segment, the second vehicle can calculate the actual travel time and upload it to the server. Alternatively, the server can determine the time when the second vehicle enters and leaves the navigation segment based on the location data reported by the second vehicle at regular intervals, thereby calculating the actual travel time of the second vehicle through the navigation segment.

[0066] In this embodiment, since "first vehicle" refers to a specific vehicle (i.e., "this vehicle") and "second vehicle" refers to other vehicles besides the first vehicle, the second vehicles passing through different navigation segments are not necessarily the same when calculating the predicted travel time for each navigation segment. For example, the second vehicles passing through navigation segment L2 include multiple vehicles other than the first vehicle, and the second vehicles passing through navigation segment L3 also include multiple vehicles other than the first vehicle. The second vehicles passing through navigation segment L2 and the second vehicles passing through navigation segment L3 may not be the same.

[0067] In step S5, for the first vehicle, the total predicted travel time for all untraveled navigation segments is t. s = t2 + t3 + ... + t m Therefore, the total predicted travel time t can be used as a basis. s Determine the remaining travel time of the first vehicle. Specifically, the total predicted travel time t can be directly calculated. s If the remaining travel time of the first vehicle is determined, this is equivalent to ignoring the time required for the first vehicle to travel the remaining distance of navigation segment L1 and enter navigation segment L2. Since the first vehicle has already passed a portion of navigation segment L1, and the length of each navigation segment is relatively small compared to the length of the navigation route, the error caused by ignoring the time required for the first vehicle to travel the remaining distance of navigation segment L1 is within an acceptable range. Alternatively, the time required for the first vehicle to travel the remaining distance of navigation segment L1 can be calculated from the remaining distance of the first vehicle through navigation segment L1 and its current speed, and then added to the predicted total travel time t. s The sum of these values ​​is used as the remaining driving time of the first vehicle, thus minimizing the error.

[0068] After completing steps S1-S5 to obtain the remaining driving time of the first vehicle, the remaining driving time can be displayed on the center console or other locations of the first vehicle, so that the people in the vehicle can accurately estimate the time it will take for the first vehicle to reach its destination and make time arrangements.

[0069] In this embodiment, by executing steps S1-S5, the predicted travel time for the vehicle to travel a route it has not yet traveled can be determined based on the actual travel time of other vehicles traveling a route that the vehicle has not yet traveled. The prediction is based on the actual travel conditions of other vehicles, which can obtain more accurate prediction results compared to simply predicting based on the vehicle's own conditions. By segmenting the navigation route and obtaining the actual travel conditions of other vehicles in each segment, the final prediction results can more accurately reflect the differences between road segments and have smaller errors.

[0070] In this embodiment, when performing step S3, which is to divide the navigation route into multiple navigation segments, the following steps can be performed:

[0071] S301. Select a trial dividing point on the navigation route;

[0072] S302. Obtain the average value of the first position corresponding to each second vehicle at the position corresponding to the trial segmentation point;

[0073] S303. Start the search from the trial split point and obtain the average value of the second position of each second vehicle at the position corresponding to the point on the navigation route;

[0074] S304. When it is detected that the deviation between the second position average value and the first position average value is greater than a threshold, the point on the navigation route corresponding to the second position average value, which has a deviation greater than the threshold and is closest to the first position average value, is set as a determination split point;

[0075] S305. A navigation segment is defined by the portion of the navigation route between two adjacent defined dividing points.

[0076] When performing steps S301-S305, you can refer to Figure 4 In step S301, trial dividing points can be determined on the navigation route through methods such as random selection, for example... Figure 4 p1 in the middle.

[0077] In step S302, the first vehicle queries the server to obtain the average first position of each second vehicle at the location corresponding to the trial segment point p1 on the navigation route. Specifically, the trial segment point p1 is not a mathematically ideal point; it corresponds to a relatively small area (e.g., 100m × 100m) on the navigation route. Several second vehicles will exist in this area. Based on the big data uploaded by these second vehicles, the server determines the position of each second vehicle within the area corresponding to the trial segment point p1. Then, a fixed origin is determined, and vectors are drawn from the origin to the positions of each second vehicle. The arithmetic mean of these vectors is then calculated. The arithmetic mean of these vectors points from the origin to the point where the first position of each second vehicle is located.

[0078] In step S303, starting from the trial split point p1, the vehicle moves towards both the starting point A and the destination B in a certain step size (e.g., 1 km) to determine each point. Following the principle of step S302, the average position of all second vehicles at each point (similar to the trial split point p1, corresponding to an area in the navigation route) is calculated, i.e., the second position average.

[0079] Since the first position average and each of the second position averages represent the position averages corresponding to the second vehicle at a specific location on the navigation route, the distance between the position averages and a reference location on the navigation route (e.g., the same shoulder of the road) can be calculated, thus expressing the first position average and each of the second position averages as distances relative to the reference location on the navigation route.

[0080] In step S304, the deviation between the first position average and each second position average is calculated. If no deviation between the second position average and the first position average is detected to be greater than a threshold, a new point can be searched in the direction of the starting point A or the destination B according to the step size, and a new second position average can be calculated. When any deviation between the second position average and the first position average is detected to be greater than a threshold (e.g., ...), the deviation between the first and second position averages is calculated. Figure 4 Points c1, c2, and c3 in the map all satisfy this condition. The points on the navigation route that are closest to the average value of the second position (i.e., c1 and c2) are set as the dividing points.

[0081] In step S305, c1 and c2 are two adjacent dividing points, so the navigation route between c1 and c2 is determined as a navigation segment.

[0082] The principle of steps S301-S305 is as follows: For each point on the navigation route, the determined first position average (for the trial split point) or second position average (for other points searched from the trial split point) represents the average position of the second vehicle at that point, which can reflect the driving order of the second vehicle at that point. The deviation between the first position average and the second position average can indicate the degree of change in the driving order of the second vehicle. When the deviation between the first position average and the second position average is less than a threshold, it can be determined that the driving order of the second vehicle has not changed. However, during the driving process, the driving order may change due to overtaking or accidents. By detecting the closest second position average with a deviation greater than the threshold, the location where the driving order has changed can be determined, thereby identifying a segment of the navigation route where the driving order remains unchanged as a navigation segment. By executing steps S301-S305, the navigation route can be segmented according to the driving order of the second vehicle, so that the driving order within each navigation segment remains unchanged. This eliminates the important factor of changing driving order that affects driving time, and allows for a more precise acquisition of the predicted driving time for each navigation segment, thereby improving the accuracy of the prediction of the remaining driving time of the first vehicle.

[0083] In this embodiment, during steps S301-S305, the location of the starting point A on the navigation route can be determined as a trial split point and a final split point. The average value of the first position corresponding to the starting point A is calculated. Then, starting from the trial split point and heading towards the destination B, the point whose second average position deviates from the first average position by less than a threshold and is closest to it is searched as the final split point. The navigation route from the starting point A to this final split point is then defined as a navigation segment. After determining this navigation segment, a final split point of this navigation segment (another final split point besides the starting point A) is used as a new trial split point, and the search continues towards the destination B to find a new final split point. Through this method, the search can be performed according to a single, defined direction on the navigation route (towards the destination B), requiring less data processing compared to a bidirectional search.

[0084] In this embodiment, a minimum road segment length l can be set. min When the portion of the navigation route between two adjacent defined dividing points (to be designated as the navigation segment) is not less than the minimum segment length l min Then this part can be defined as a navigation segment; when the portion of the navigation route between two adjacent defined dividing points (to be designated as a navigation segment) is less than the minimum segment length l min Then, this part is merged with the parts from the next two adjacent defined dividing points, until the merged road segment is not less than the minimum road segment length l. minBy merging road segments, it is possible to avoid obtaining navigation segments that are too short or too numerous, which helps to reduce the amount of data processing required to implement the remaining driving time prediction method based on big data.

[0085] In this embodiment, when performing step S4, which is to determine the predicted travel time corresponding to the navigation segment based on the actual travel time of the second vehicle traversing the navigation segment, the navigation segment L is used as the reference. m For example, the navigation route L can be calculated. m The average actual travel time of all second vehicles is used to obtain the navigation segment L. m The corresponding predicted travel time.

[0086] Specifically, the average duration can be in the form of an arithmetic mean or a weighted average. When using a weighted average, the average duration can be calculated using the following steps:

[0087] S401. Determine the driving environment parameters of each second vehicle in the navigation segment;

[0088] S402. Using driving environment parameters as weights, calculate the weighted average of the actual driving time consumed by all second vehicles, and use it as the average duration.

[0089] In step S401, the obtained driving environment parameters can be quantitative parameters reflecting the environment and driving mode of the second vehicle. Specifically, these can include parameters such as weather (temperature, humidity, rainfall, illuminance, etc.), time, terrain (road curvature radius, altitude, etc.), and driving habits (driving experience, vehicle type, vehicle speed, load). These driving environment parameters form a driving environment parameter vector, meaning each second vehicle has a corresponding driving environment parameter vector. Taking the second vehicle j as an example, its corresponding driving environment parameter vector is (parameter...). 1j parameter 2j , ...).

[0090] In step S402, navigation segment L is used. m For example, navigation segment L can be used. m The normalized result of the driving environment parameter vector corresponding to each second vehicle [taking the second vehicle j as an example, its corresponding weight is |(parameter 1j parameter 2j ,……)| / sqrt(parameter 1j 2 +parameter 2j 2+……), where || represents the magnitude of the vector, sqrt represents the square root, and [[as weights] are used to calculate the navigation segment L. m The weighted average of the actual driving time consumed by all the corresponding second vehicles is used as the average duration.

[0091] By executing steps S401-S402, and using the normalized result of the driving environment parameter vector corresponding to each second vehicle as the weight, the influence of factors such as weather, time, terrain and driving habits on the driving time can be reduced. The obtained weighted average value can reflect the general time of passing through the navigation segment, and the predicted driving time corresponding to each navigation segment can be obtained more precisely, thereby improving the prediction accuracy of the remaining driving time of the first vehicle.

[0092] In this embodiment, the remaining driving time prediction method based on big data further includes the following steps:

[0093] S6. From each navigation segment, determine the segments that the first vehicle has already passed and the segments that it has not yet passed;

[0094] S7. Obtain the actual travel time of the first vehicle on the road segment it has already passed;

[0095] S8. Adjust the predicted travel time for untraveled road segments based on the deviation between the actual travel time of the already traversed road segments and the corresponding predicted travel time.

[0096] Steps S6-S8 can be performed by the first vehicle.

[0097] In step S6, assuming the first vehicle has reached the dividing point between navigation segments L1 and L2, then the segment the first vehicle has already passed is L1, and the segments it has not yet passed are L2, L3, ... L1. m .

[0098] In step S7, the first vehicle performs a real-world measurement of the navigation route L1 to determine the actual travel time t1'.

[0099] In step S8, based on the deviation between the actual travel time t1' of the already passed road segment and the corresponding predicted travel time t1, the predicted travel time t2 of the unpassed road segment is adjusted.

[0100] Specifically, when performing step S8, the following steps can be performed:

[0101] S801. Determine the adjustment coefficient based on the driving environment parameters of the second vehicle in the road section that has already been traversed and the driving environment parameters of the second vehicle in the road section that has not been traversed;

[0102] S802. Determine the time adjustment value based on the deviation and adjustment coefficient between the actual travel time of the already traversed road segment and the corresponding predicted travel time;

[0103] S803. Adjust the predicted travel time for road segments not yet traversed based on the time adjustment value.

[0104] In step S801, taking the predicted travel time t2 corresponding to navigation segment L2 as an example, the average value a1 of the normalized results of the driving environment parameter vectors corresponding to all second vehicles in the already passed segment (navigation segment L1) and the average value a2 of the normalized results of the driving environment parameter vectors corresponding to all second vehicles in the unpassed segment (navigation segment L2) are obtained, and the ratio a2 / a1 is calculated as the adjustment coefficient.

[0105] In step S802, based on the deviation (t1'-t1) between the actual travel time t1' of the already passed road segment (navigation road segment L1) and the corresponding predicted travel time t1, and the adjustment coefficient a2 / a1, the time adjustment value △t2 for the predicted travel time t2 corresponding to the unpassed road segment (navigation road segment L2) is determined according to the formula △t2=a2 / a1×(t1'-t1).

[0106] In step S803, based on the time adjustment value △t2, the predicted travel time t2 corresponding to the unpassed road segment (navigation road segment L2) is adjusted using the formula t2=t2+△t2.

[0107] After adjusting the predicted travel time for the untraveled road segments in steps S801-S803, the adjusted predicted travel time is used when step S4 is executed again.

[0108] The principle of steps S801-S803 is as follows: referring to the principle of steps S401-S402, by dividing the normalized results of the driving environment parameter vectors corresponding to the second vehicle for each of the already passed and unpassed road segments as the adjustment coefficient, the influence of factors such as weather, time, terrain and driving habits on the travel time of different road segments can be reduced. The deviation actually measured for the already passed road segments is adjusted to be suitable for the deviation of the unpassed road segments, thereby adjusting the predicted travel time of the unpassed road segments. This allows for a more precise acquisition of the predicted travel time corresponding to each navigation road segment, improving the accuracy of the prediction of the remaining travel time of the first vehicle.

[0109] In this embodiment, after the first vehicle obtains the actual driving time t1' after passing through navigation segment L1, the first vehicle uploads the actual driving time t1' to the server, and the server adds the actual driving time t1' to the big data database. When other vehicles execute the big data-based remaining driving time prediction method in this embodiment, the actual driving time t1' uploaded by the first vehicle (which will then become the second vehicle) will be called up to provide data support for other vehicles to predict the remaining driving time.

[0110] A computer program that executes the big data-based remaining driving time prediction method in this embodiment can be written into a storage medium or computer device. When the computer program is read out and run, the big data-based remaining driving time prediction method in this embodiment is executed, thereby achieving the same technical effect as the big data-based remaining driving time prediction method in the embodiment.

[0111] It should be noted that, unless otherwise specified, when a feature is referred to as "fixed" or "connected" to another feature, it can be directly fixed or connected to the other feature, or indirectly fixed or connected to the other feature. Furthermore, the descriptions of "upper," "lower," "left," and "right" used in this disclosure are only relative to the relative positional relationships of the various components of this disclosure in the accompanying drawings. The singular forms "a," "described," and "the" used in this disclosure are also intended to include the plural forms, unless the context clearly indicates otherwise. Moreover, unless otherwise defined, all technical and scientific terms used in this embodiment have the same meaning as commonly understood by one of ordinary skill in the art. The terminology used in this embodiment specification is only for describing particular embodiments and is not intended to limit the invention. The term "and / or" as used in this embodiment includes any combination of one or more of the associated listed items.

[0112] It should be understood that although the terms first, second, third, etc., may be used to describe various elements in this disclosure, these elements should not be limited to these terms. These terms are only used to distinguish elements of the same type from each other. For example, a first element may also be referred to as a second element without departing from the scope of this disclosure, and similarly, a second element may also be referred to as a first element. The use of any and all instances or exemplary language (“e.g.,” “such as,” etc.) provided in this embodiment is intended only to better illustrate embodiments of the invention and, unless otherwise required, does not impose a limitation on the scope of the invention.

[0113] It should be recognized that embodiments of the present invention can be implemented or carried out by computer hardware, a combination of hardware and software, or by computer instructions stored in a non-transitory computer-readable storage medium. The method can be implemented using standard programming techniques—including a non-transitory computer-readable storage medium configured with a computer program, wherein such a storage medium causes the computer to operate in a specific and predefined manner—according to the methods and drawings described in the specific embodiments. Each program can be implemented in a high-level procedural or object-oriented programming language to communicate with the computer system. However, if desired, the program can be implemented in assembly or machine language. In any case, the language can be a compiled or interpreted language. Furthermore, for this purpose, the program can run on a programmed application-specific integrated circuit (ASIC).

[0114] Furthermore, the procedures described in this embodiment can be performed in any suitable order unless otherwise indicated by this embodiment or clearly contradicted by the context. The procedures (or variations and / or combinations thereof) described in this embodiment can be executed under the control of one or more computer systems configured with executable instructions, and can be implemented by hardware or a combination thereof as code (e.g., executable instructions, one or more computer programs, or one or more applications) that commonly executes on one or more processors. The computer program includes a plurality of instructions executable by one or more processors.

[0115] Furthermore, the method can be implemented in any suitable type of computing platform, including but not limited to personal computers, minicomputers, mainframes, workstations, networked or distributed computing environments, standalone or integrated computer platforms, or in communication with charged particle tools or other imaging devices. Aspects of the invention can be implemented as machine-readable code stored on a non-transitory storage medium or device, whether removable or integrated into a computing platform, such as a hard disk, optical read and / or write storage medium, RAM, ROM, etc., such that it is readable by a programmable computer, and when the storage medium or device is read by the computer, it can be used to configure and operate the computer to perform the processes described herein. Furthermore, the machine-readable code, or portions thereof, can be transmitted via wired or wireless networks. The invention described in this embodiment includes these and other different types of non-transitory computer-readable storage media when such media comprises instructions or programs that implement the steps described above in conjunction with a microprocessor or other data processor. When programmed according to the methods and techniques described in the invention, the invention also includes the computer itself.

[0116] A computer program can be applied to input data to perform the functions described in this embodiment, thereby transforming the input data to generate output data stored in non-volatile memory. The output information can also be applied to one or more output devices, such as a display. In a preferred embodiment of the invention, the transformed data represents physical and tangible objects, including specific visual depictions of physical and tangible objects generated on the display.

[0117] The above description is merely a preferred embodiment of the present invention. The present invention is not limited to the above-described embodiments. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention, as long as they achieve the technical effects of the present invention by the same means, should be included within the scope of protection of the present invention. Within the scope of protection of the present invention, the technical solutions and / or implementation methods can have various modifications and variations.

Claims

1. A method for predicting remaining driving time based on big data, characterized in that, The method for predicting remaining driving time based on big data includes: Obtain the origin and destination of the first vehicle; Obtain the navigation route from the departure point to the destination; Select a trial split point on the navigation route; the trial split point is an area on the navigation route where several second vehicles exist; Obtain the average value of the first position corresponding to each second vehicle at the position corresponding to the trial segmentation point; Starting from the trial split point, the search is performed to obtain the second position average value of each second vehicle at the corresponding position of the point on the navigation route; the first position average value is the position average value of the second vehicle at the trial split point, and the second position average value is the position average value of the second vehicle at the point determined by moving from the trial split point. When it is detected that the deviation between the second position average and the first position average is greater than a threshold, the point on the navigation route corresponding to the second position average that has a deviation greater than the threshold and is closest to the first position average is set as a determination split point; A navigation segment is defined by the portion of the navigation route between two adjacent defined dividing points; For any of the navigation segments that the first vehicle has not passed through, the predicted travel time corresponding to the navigation segment is determined based on the actual travel time taken by the second vehicle to pass through the navigation segment; the second vehicle is the vehicle that passed through the navigation segment before the first vehicle; The remaining travel time of the first vehicle is determined based on the total predicted travel time of all the navigation segments that have not been traversed.

2. The method for predicting remaining driving time based on big data according to claim 1, characterized in that, The step of selecting a trial split point on the navigation route includes: The points on the navigation route corresponding to the starting point are determined as the trial split point and the confirmed split point; Once a navigation segment is determined, one of the determined dividing points in the navigation segment is designated as a new trial dividing point.

3. The method for predicting remaining driving time based on big data according to claim 1 or 2, characterized in that, The step of defining a navigation segment as the portion of the navigation route between two adjacent defined dividing points includes: Set the minimum segment length; When the portion of the navigation route between two adjacent defined dividing points is not less than the minimum segment length, the portion of the navigation route between two adjacent defined dividing points is defined as a navigation segment. When the portion of the navigation route between two adjacent defined dividing points is less than the minimum segment length, the next defined dividing point between the two adjacent defined dividing points is searched, and the portion of the navigation route between the two adjacent defined dividing points and the next defined dividing point is determined as a navigation segment.

4. The method for predicting remaining driving time based on big data according to claim 1, characterized in that, The step of determining the predicted travel time corresponding to the navigation segment based on the actual travel time of the second vehicle traversing the navigation segment includes: Obtain the actual travel time of all second vehicles traversing the navigation segment; Determine the average duration of the actual travel time consumed by all the second vehicles; The average duration is determined as the predicted travel time corresponding to the navigation segment.

5. The method for predicting remaining driving time based on big data according to claim 4, characterized in that, The determination of the average actual driving time of all the second vehicles includes: Calculate the arithmetic mean of the actual driving time consumed by all the second vehicles, and use it as the average time.

6. The method for predicting remaining driving time based on big data according to claim 4, characterized in that, The determination of the average actual driving time of all the second vehicles includes: Determine the driving environment parameters for each of the second vehicles on the navigation route; Using the driving environment parameters as weights, a weighted average of the actual driving time consumed by all the second vehicles is calculated, which is then used as the average time.

7. The method for predicting remaining driving time based on big data according to claim 6, characterized in that, The remaining driving time prediction method based on big data also includes: From each of the navigation segments, determine the segments that the first vehicle has already passed and the segments that it has not yet passed; Obtain the actual travel time of the first vehicle on the already traversed road segment; Based on the deviation between the actual travel time of the already traversed road segments and the corresponding predicted travel time, the predicted travel time for the untraversed road segments is adjusted.

8. The method for predicting remaining driving time based on big data according to claim 7, characterized in that, The step of adjusting the predicted travel time for the untraveled road segments based on the deviation between the actual travel time and the corresponding predicted travel time for the already traversed road segments includes: Based on the driving environment parameters of the second vehicle on the already traversed road section and the driving environment parameters of the second vehicle on the untraversed road section, an adjustment coefficient is determined; The time adjustment value is determined based on the deviation between the actual travel time of the already traversed road segment and the corresponding predicted travel time, and the adjustment coefficient. Based on the time adjustment value, the predicted travel time corresponding to the unpassed road segment is adjusted.

9. A computer device, characterized in that, The device includes a memory and a processor, the memory being used to store at least one program, and the processor being used to load the at least one program to execute the big data-based remaining driving time prediction method according to any one of claims 1-8.

Images