Vehicle power-on time prediction method, vehicle management method and electronic equipment

By combining the vehicle's power-off time, current location and historical vehicle use information, predicting the vehicle's power-off time, solving the problem of inaccurate power-off time in the existing technology, achieving more accurate vehicle-use sections and time predictions, improving User experience.

CN119049284AActive Publication Date: 2024-11-29Z-ONE TECH CO LTD
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
CN202411201438.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-29
Publication Date
2024-11-29
Estimated Expiration
2044-08-29

AI Technical Summary

Technical Problem

In the prior art, the accuracy of vehicle power-on time prediction is not high, which affects the user experience, mainly because only considering the user's historical car use time points, and failing to make full use of the current location and historical car use information.

Method used

By determining the power-off time, current location and historical vehicle use information of the target vehicle, calculate the travel probability and historical travel time of the target vehicle on the target historical driving section, and then predict the most likely vehicle use section and vehicle use time for the user, obtain More accurate power-on time.

Benefits of technology

The accuracy of vehicle power-on time prediction is improved, making vehicle power-on time more in line with the actual needs of users and improving user experience.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119049284A_ABST
    Figure CN119049284A_ABST
Patent Text Reader

Abstract

The invention discloses a vehicle power-on time prediction method, a vehicle management method and electronic equipment, and the vehicle power-on time prediction method comprises the steps: carrying out the power-on time prediction of a target vehicle according to the current position of the target vehicle and the driving information of the target vehicle in a plurality of historical driving road sections, determining a historical travel probability of the target vehicle on a target historical travel road section taking the current position as a travel starting point, historical travel time and a corresponding historical travel time probability; determining a predicted user vehicle using road section and predicted user vehicle using time corresponding to the predicted user vehicle using road section according to the power-off time of the target vehicle, the historical travel probability, the historical travel time and the historical travel time probability; and obtaining the predicted power-on time of the target vehicle according to the predicted vehicle use time of the user. Therefore, the historical travel time probability and the historical travel probability are comprehensively considered, the most possible predicted vehicle use time of the user is determined, and the predicted vehicle power-on time which is more accurate and can better meet user requirements is obtained.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of vehicle management technology, and in particular to a vehicle power-on time prediction method, a vehicle management method and an electronic device. Background Art

[0002] For a vehicle in a parked and powered-off state, the vehicle power-on time can be predicted by predicting the next time the user uses the vehicle. Automatically powering on and starting the vehicle at the predicted power-on time can make the vehicle better meet user needs.

[0003] Currently, the method for predicting the next time a user uses the car is mainly to count the frequency of the user's historical car use time, and use the car use time with a high frequency as the predicted user's car use time. However, since there are many factors that affect the actual car use time during the user's actual car use, this method of predicting the user's car use time by only considering the user's historical car use time points makes the predicted user's car use time not very accurate. Therefore, if the accuracy of the vehicle power-on time predicted based on this method is not high. If the vehicle is powered on and started according to the power-on time predicted by this method, there will be a problem that the vehicle power-on start time is not the travel time actually required by the user, which affects the user experience. Summary of the invention

[0004] The present application provides a vehicle power-on time prediction method, a vehicle management method and an electronic device, which are used to solve the problems existing in the prior art that the prediction accuracy of the vehicle power-on time is not high, affecting the user experience.

[0005] Among them, the travel probability, historical travel time and historical travel time probability of the target vehicle in the target historical driving section are determined based on the current position and historical vehicle use information, and then the predicted user vehicle use section that the user is most likely to need to travel and the predicted user vehicle use time corresponding to the predicted user vehicle use section are determined based on the power-off time, historical travel probability, historical travel time and historical travel time probability, and the predicted power-on time for driving the predicted user vehicle use section is obtained. In this way, the vehicle's next travel section and the vehicle power-on time for driving the section are predicted, and the predicted vehicle use section and power-on time are the driving section and travel time that the user needs more, and the travel time prediction can be predicted based on the driving section. If the predicted driving section is different, the predicted power-on time corresponding to the driving section will be different, making the power-on time prediction more accurate and the user experience better.

[0006] To solve the above technical problems, on the first aspect, the implementation method of the present application discloses a vehicle power-on time prediction method, the method comprising: determining the power-off time, current position and historical vehicle usage information of the target vehicle, the historical vehicle usage information including the driving information of the target vehicle in multiple historical driving sections; determining the historical travel probability and historical travel time of the target vehicle in the target historical driving section according to the current position and the historical vehicle usage information, and determining the historical travel time probability corresponding to the historical travel time, the target historical driving section is a historical driving section whose driving starting point is the current position in the historical driving section included in the historical vehicle usage information; determining the predicted user vehicle usage section according to the power-off time, the historical travel probability, the historical travel time and the historical travel time probability, and determining the predicted user vehicle usage time corresponding to the predicted user vehicle usage section; obtaining the predicted power-on time of the target vehicle according to the predicted user vehicle usage time.

[0007] The vehicle power-on time prediction method provided by the implementation of the present application determines the historical travel probability and historical travel time of the target vehicle in the target historical driving section with the current position as the driving starting point according to the current position and the historical vehicle use information, and determines the historical travel time probability corresponding to the historical travel time, so that the predicted user vehicle use section where the user is most likely to travel and the most likely predicted user vehicle use time for traveling the predicted user vehicle use section can be determined based on the power-off time, the historical travel probability, the historical travel time and the historical travel time probability, and the vehicle power-on time is obtained. In this way, the driving section of the next trip of the target vehicle and the travel time of traveling the driving section from the current position are predicted according to the historical vehicle use information, so that the predicted driving section and power-on time are the driving section and travel time that the user needs more, and the travel time prediction can be predicted based on the driving section. If the predicted driving section is different, the power-on time corresponding to the predicted driving section will be different, so that the power-on time prediction is more accurate and the user experience is better.

[0008] According to another specific implementation of the present application, the implementation of the present application discloses a vehicle power-on time prediction method, which determines a predicted user vehicle usage section and a predicted user vehicle usage time corresponding to the predicted user vehicle usage section based on the power-off time, historical travel probability, historical travel time and historical travel time probability, including: taking the historical travel time that is later than the power-off time and has the highest historical travel time probability as the target historical travel time; determining the predicted travel probability corresponding to the target historical driving section based on the historical travel probability of the target historical driving section and the historical travel time probability corresponding to the target historical travel time; taking the target historical driving section with the highest predicted travel probability as the predicted user vehicle usage section, and taking the target historical travel time corresponding to the predicted user vehicle usage section as the predicted user vehicle usage time.

[0009] By adopting the above technical solution, the target historical travel time corresponding to the target historical driving section, which is later than the power-off time and has the highest probability of historical travel time, is determined, and then the predicted travel probability corresponding to the target historical driving section is obtained based on the historical travel probability of the target historical driving section and the historical travel time probability corresponding to the target historical travel time, and the target historical driving section with the highest predicted travel probability is used as the predicted user car section, and the target historical travel time corresponding to the predicted user car section is used as the predicted user car time. In this way, by comprehensively considering the historical travel time probability and the historical travel probability, the predicted user car section where the user is most likely to travel and the most likely predicted user car time for traveling the predicted user car section are determined, and then the vehicle power-on time is obtained, so that the vehicle power-on time prediction is more accurate and can better meet user needs.

[0010] According to another specific implementation of the present application, the implementation of the present application discloses a vehicle power-on time prediction method, and the driving information of the target vehicle in multiple historical driving sections is obtained in the following manner: determining the initial historical vehicle position and the corresponding initial historical vehicle use time of the target vehicle; clustering the initial historical vehicle position and the initial historical vehicle use time based on a clustering algorithm to obtain the historical vehicle position and historical vehicle use time of the target vehicle; obtaining the driving information of the target vehicle in multiple historical driving sections based on the historical vehicle position and the corresponding historical vehicle use time.

[0011] By adopting the above technical solution, the initial historical vehicle position and initial historical vehicle time are clustered based on the clustering algorithm to obtain the historical vehicle position and historical vehicle time of the target vehicle, and then the driving information of the target vehicle on multiple historical driving sections is obtained according to the historical vehicle position and the corresponding historical vehicle time. In this way, the historical vehicle information is more standardized, and the vehicle power-on time can be better and more accurately predicted.

[0012] According to another specific implementation method of the present application, the implementation method of the present application discloses a vehicle power-on time prediction method, which determines the historical travel probability of the target vehicle in the target historical driving section based on the current position and historical vehicle usage information, including: determining the vehicle position transfer probability matrix of the target vehicle based on the historical vehicle usage information; determining the historical travel probability of the target vehicle in the target historical driving section from the vehicle position transfer probability matrix based on the current position.

[0013] By adopting the above technical solution, the vehicle position transfer probability matrix is ​​determined according to the historical vehicle use information, and then when predicting the vehicle power-on time, the historical travel probability of the target vehicle on the target historical driving section can be obtained by querying the vehicle position transfer probability matrix. In this way, the vehicle power-on time prediction is faster.

[0014] According to another specific implementation of the present application, the implementation of the present application discloses a vehicle power-on time prediction method, which determines the vehicle position transfer probability matrix of the target vehicle based on historical vehicle usage information, including: determining the historical vehicle usage times corresponding to the historical driving section based on the historical vehicle usage information; determining the historical travel probability of the target vehicle in the historical driving section based on the historical vehicle usage times of the target vehicle in the historical driving section; and obtaining the vehicle position transfer probability matrix based on the historical travel probability of the target vehicle in the historical driving section.

[0015] By adopting the above technical solution, the historical vehicle usage times corresponding to all historical driving sections are determined according to the historical vehicle usage information, and then the historical travel probabilities of all historical driving sections are obtained, and the vehicle position transfer probability matrix is ​​generated, so that when predicting the vehicle power-on time, the historical travel probability of the target vehicle in the target historical driving section can be obtained by querying the vehicle position transfer probability matrix. In this way, the vehicle power-on time prediction is made faster.

[0016] According to another specific implementation of the present application, the implementation of the present application discloses a vehicle power-on time prediction method, wherein the historical vehicle use position includes a power-on position and a power-off position, and the historical travel probability of the target vehicle in the historical driving section is determined according to the historical vehicle use times of the target vehicle in the historical driving section, including: obtaining the historical travel probability of the target vehicle in the historical driving section according to the ratio of the historical vehicle use times of the target vehicle in the historical driving section with the first power-on position as the driving starting point and the first power-off position as the driving end point to the historical vehicle use times of all historical driving sections with the first power-on position as the driving starting point and all power-off positions as the driving end points.

[0017] By adopting the above technical solution, the historical travel probability of the target vehicle in the historical driving section is obtained according to the ratio of the historical vehicle usage times of the historical driving section corresponding to the first power-on position as the driving starting point and the first power-off position as the driving end point and the historical vehicle usage times of all historical driving sections corresponding to the first power-on position as the driving starting point and all power-off positions as the driving end points. In this way, the historical travel probability of each historical driving section in the historical vehicle usage information of the vehicle can be obtained, which is convenient for the subsequent prediction of the user's vehicle usage section and user's vehicle usage time.

[0018] According to another specific implementation of the present application, the implementation of the present application discloses a vehicle power-on time prediction method, wherein the historical vehicle usage time includes the power-on time and the power-off time, and the driving information of multiple historical driving sections of the target vehicle is obtained according to the historical vehicle usage positions and the corresponding historical vehicle usage times, including: if it is determined that the time interval between the power-off time of the target vehicle traveling from a first power-on position to a first power-off position and the power-on time of the target vehicle traveling from the first power-off position to a second power-off position is less than a preset first time interval threshold, then the driving information of the historical driving section of the target vehicle is determined as the power-on position being the first power-on position, the power-off position being the second power-off position, the power-on time being the power-on time of the target vehicle at the first power-on position, and the power-off time being the power-off time of the target vehicle at the second power-off position.

[0019] By adopting the above technical solution, the historical driving sections are integrated according to the time interval between the power-off time of the target vehicle traveling from the first power-on position to the first power-off position and the power-on time of the target vehicle traveling from the first power-off position to the second power-off position, so that the prediction of the user's vehicle usage section and the user's vehicle usage time is more accurate.

[0020] According to another specific implementation method of the present application, the implementation method of the present application discloses a vehicle power-on time prediction method, which determines the historical vehicle usage times corresponding to the historical driving section based on the historical vehicle usage information, including: if it is determined that the time interval between the power-on time and the power-off time of the target vehicle traveling from the first power-on position to the first power-off position in the historical driving section is less than a preset second time interval threshold, and the average speed of the target vehicle is less than the preset speed threshold, then the historical vehicle usage times in the historical driving section are determined to be zero.

[0021] By adopting the above technical scheme, the historical number of times the target vehicle was used in the historical driving section is determined based on the time interval between the power-on time and the power-off time when the target vehicle travels from the first power-on position to the first power-off position in the historical driving section, and the average speed of the target vehicle. In this way, the interference of invalid data is eliminated, and the determination of the historical number of times the vehicle is used is more accurate, thereby making the prediction of the user's vehicle usage section and the user's vehicle usage time more accurate.

[0022] According to another specific implementation method of the present application, the implementation method of the present application discloses a vehicle power-on time prediction method, which determines the vehicle position transfer probability matrix of the target vehicle based on historical vehicle usage information, including: when it is determined that the historical vehicle usage information satisfies the corresponding conditions of the Markov chain model, obtaining the vehicle position transfer probability matrix based on the historical vehicle usage information.

[0023] By adopting the above technical solution, when it is determined that the historical vehicle usage information meets the corresponding conditions of the Markov chain model, the vehicle position transfer probability matrix is ​​obtained according to the historical vehicle usage information, so that the vehicle position transfer probability matrix can be obtained according to the historical vehicle usage information that meets the corresponding conditions of the Markov chain model, which facilitates subsequent historical travel probability queries.

[0024] According to another specific implementation method of the present application, the implementation method of the present application discloses a vehicle power-on time prediction method, which determines the historical travel time of the target vehicle in the target historical driving section based on the current position and historical vehicle usage information, and determines the historical travel time probability corresponding to the historical travel time, including: determining the historical travel time and the historical travel time probability of the target vehicle in the historical driving section based on the historical vehicle usage information; determining the historical travel time and the historical travel time probability of the target vehicle corresponding to the historical travel time of the target historical driving section from the historical travel time and the historical travel time probability of the historical driving section based on the current position of the target vehicle.

[0025] By adopting the above technical scheme, the historical travel time and historical travel time probability of the target vehicle in all historical driving sections are first determined. Then, when determining the historical travel time and historical travel time probability, the historical travel time and historical travel time probability of the corresponding target historical driving section can be queried, which facilitates the query of historical travel time and historical travel time probability of the target historical driving section and speeds up the efficiency of vehicle power-on time prediction.

[0026] According to another specific implementation of the present application, the implementation of the present application discloses a vehicle power-on time prediction method, wherein the historical vehicle usage time includes the power-on time, and the historical travel time and the historical travel time probability of the target vehicle in the historical driving section are determined based on the historical vehicle usage information, including: determining all historical travel times of the target vehicle in the historical driving section and the historical vehicle usage times corresponding to all historical travel times based on the power-on time; determining the historical vehicle usage times of the target vehicle at the historical travel times; determining the historical travel time probability of the target vehicle in the historical driving section at the historical travel time based on the ratio of the historical vehicle usage times of the target vehicle at the historical travel times to the historical vehicle usage times corresponding to all historical travel times.

[0027] By adopting the above technical scheme, the historical travel time probability corresponding to each historical travel time in each historical driving section can be determined, and the predicted travel probability of the target historical driving section can be determined based on the historical travel time probability. Then, the predicted user car usage section and the predicted user car usage time can be obtained based on the predicted travel probability, making the predicted user car usage section and the predicted user car usage time more accurate.

[0028] According to another specific implementation method of the present application, the implementation method of the present application discloses a vehicle power-on time prediction method, which determines the historical travel time probability corresponding to the historical travel time, including: determining the historical travel time probability corresponding to each historical travel time of the target vehicle in the historical driving section based on a Gaussian mixture model.

[0029] By adopting the above technical solution, the historical travel time probability corresponding to each historical travel time of the target vehicle in the historical driving section is determined based on the Gaussian mixture model, making the calculation of the historical travel time probability faster and simpler.

[0030] According to another specific implementation method of the present application, the implementation method of the present application discloses a vehicle power-on time prediction method, which determines the historical travel probability and historical travel time of the target vehicle in the target historical driving section according to the current position and historical vehicle usage information, and determines the historical travel time probability corresponding to the historical travel time, including: when it is determined according to the current position and historical vehicle usage information that the current position is within a preset range of one of the power-on positions of the historical vehicle usage positions, determining the historical travel probability and historical travel time of the target vehicle in the target historical driving section according to the historical vehicle usage information, and determining the historical travel time probability corresponding to the historical travel time.

[0031] By adopting the above technical solution, the vehicle power-on time prediction can be performed only when the current position is within the preset range of one of the power-on positions in the historical vehicle usage information included in the historical vehicle usage information, so that the vehicle power-on time predicted based on the historical vehicle usage information is more accurate.

[0032] According to another specific implementation method of the present application, a vehicle power-on time prediction method disclosed in the implementation method of the present application uses the target historical driving section with the highest predicted travel probability as the predicted user vehicle section, including: when it is determined that the maximum predicted travel probability is greater than a preset travel probability threshold, the target historical driving section with the highest predicted travel probability is used as the predicted user vehicle section.

[0033] By adopting the above technical solution, the target historical driving section with the highest predicted travel probability is used as the predicted user driving section. In this way, the target driving section, the historical travel probability and the historical travel time probability are fully considered, so that the predicted user driving section is determined to be the driving section that the user is most likely to travel next time, which meets the user's needs and improves the user experience.

[0034] In the second aspect, the implementation method of the present application also discloses a vehicle management method, which includes: determining the predicted power-on time of a target vehicle in a parked and powered-off state, the predicted power-on time being obtained based on the vehicle power-on time prediction method provided by any implementation method of the first aspect; and powering on the target vehicle at the predicted power-on time.

[0035] By adopting the above technical solution, the vehicle can be powered on in advance through accurate power-on time prediction, thereby improving the overall user experience.

[0036] According to another specific implementation of the present application, the implementation of the present application discloses a vehicle management method, which also includes: determining a predicted destination of a target vehicle in a parked and powered-off state, the predicted destination being determined based on a predicted user vehicle section obtained in the vehicle power-on time prediction method provided in any one of the implementations of the first aspect; determining a driving route of the target vehicle based on the predicted destination.

[0037] By adopting the above technical solution, the driving route of the target vehicle is determined according to the predicted destination, so that the driving route for the next trip can be planned for the user, giving the user a better car experience.

[0038] In a third aspect, an implementation of the present application provides an electronic device, comprising: a processor, and a memory communicatively connected to the processor; the memory stores a computer program; the processor executes the computer program stored in the memory, so that the electronic device implements a vehicle power-on time prediction method as provided in any implementation of the first aspect, and / or implements a vehicle management method as provided in any implementation of the second aspect.

[0039] In a fourth aspect, an implementation method of the present application provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, it is used to implement a vehicle power-on time prediction method as provided in any implementation method of the first aspect, and / or to implement a vehicle management method as provided in any implementation method of the second aspect.

[0040] In a fifth aspect, an implementation method of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements a vehicle power-on time prediction method as provided in any implementation method of the first aspect, and / or implements a vehicle management method as provided in any implementation method of the second aspect.

[0041] It can be understood that the beneficial effects of the third to fifth aspects mentioned above can also be found in the relevant descriptions in the first and / or second aspects mentioned above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 It is a flow chart of a vehicle power-on time prediction method provided in an embodiment of the present application;

[0043] Figure 2 It is a schematic diagram of a process of obtaining driving information of a historical driving section provided in an embodiment of the present application;

[0044] Figure 3 It is a schematic diagram of the principle of obtaining the vehicle position transfer probability matrix provided by an embodiment of the present application;

[0045] Figure 4 is a schematic diagram of a process for determining a historical travel probability provided by an embodiment of the present application;

[0046] Figure 5 is a schematic diagram of a process for determining a vehicle position transfer probability matrix provided in an embodiment of the present application;

[0047] Figure 6 It is a schematic diagram of a process for determining historical travel time and historical travel time probability provided by an embodiment of the present application;

[0048] Figure 7 It is a flowchart of determining a predicted user's car use section and predicting the user's car use time provided in an embodiment of the present application;

[0049] Figure 8 It is a flow chart of a vehicle management method provided in an embodiment of the present application;

[0050] Fig. 9 It is a flowchart of another vehicle management method provided in an embodiment of the present application;

[0051] Fig.10 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application.

[0052] Specific implementation method

[0053] At present, for vehicles in the parked and powered-off state, the vehicle power-on time can be predicted by predicting the next time the user uses the vehicle. Automatically powering on the vehicle at the predicted power-on time can make the vehicle better meet user needs. Therefore, the prediction of vehicle power-on time is of great significance for realizing personalized services and improving user experience.

[0054] However, the current vehicle prediction is mostly focused on predicting the driving destination of the vehicle, that is, predicting the destination of the user's trip based on the user's power-on time and the location of the vehicle when the power is on. This method does not achieve the prediction of the power-on time.

[0055] Furthermore, even if there is a solution to predict the vehicle power-on time, it is also done by counting the frequency of the user's historical car usage time, and taking the car usage time with a high frequency as the predicted user's car usage time. However, since there are many factors that affect the actual car usage time during the user's actual car usage, for example, if the travel destination is different, the travel time will also be different, and the vehicle power-on time will also be different. This method of predicting the user's car usage time by only considering the user's historical car usage time points makes the predicted user car usage time not very accurate. Therefore, the accuracy of the vehicle power-on time predicted based on this method is not high. If the vehicle is powered on and started according to the power-on time predicted by this method, there will be a problem that the vehicle power-on start time is not the travel time actually required by the user, which affects the user experience.

[0056] Based on this, the implementation of the present application provides a vehicle power-on time prediction method and a vehicle management method, which determines the travel probability, historical travel time and historical travel time probability of the target vehicle in the target historical driving section based on the current position and historical vehicle use information, and then determines the predicted user vehicle use section that the user is most likely to need to travel and the predicted user vehicle use time corresponding to the predicted user vehicle use section based on the power-off time, historical travel probability, historical travel time and historical travel time probability, and obtains the predicted power-on time for driving the predicted user vehicle use section. In this way, the vehicle's next travel section and the vehicle power-on time for driving the section are predicted, and the predicted vehicle use section and power-on time are the driving section and travel time that the user needs more, and the travel time prediction can be predicted based on the driving section. If the predicted driving section is different, the predicted power-on time corresponding to the driving section will be different, making the power-on time prediction more accurate and the user experience better.

[0057] Next, the vehicle power-on time prediction method provided by the implementation of the present application is described in detail.

[0058] In the implementation of this application, Figure 1 As shown, the vehicle power-on time prediction method specifically includes the following steps:

[0059] S100, determining the power-off time, current location and historical vehicle use information of the target vehicle, where the historical vehicle use information includes driving information of the target vehicle on multiple historical driving sections.

[0060] S200, determining the historical travel probability and historical travel time of the target vehicle on the target historical driving section according to the current position and historical vehicle use information, and determining the historical travel time probability corresponding to the historical travel time.

[0061] The target historical driving section is a historical driving section whose driving starting point is the current position among the historical driving sections included in the historical vehicle use information.

[0062] S300, determining a predicted user vehicle usage section and a predicted user vehicle usage time corresponding to the predicted user vehicle usage section according to the power-off time, the historical travel probability, the historical travel time and the historical travel time probability.

[0063] S400, obtaining a predicted power-on time of a target vehicle according to the predicted vehicle usage time of the user.

[0064] The vehicle power-on time prediction method provided by the implementation of the present application determines the historical travel probability and historical travel time of the target vehicle at the target historical driving section with the driving starting point (i.e., the starting location) as the current position based on the historical vehicle use information, and determines the historical travel time probability corresponding to the historical travel time, so that the predicted user vehicle use section where the user is most likely to travel and the most likely predicted user vehicle use time for traveling the predicted user vehicle use section can be determined based on the power-off time, historical travel probability, historical travel time, and historical travel time probability, and the vehicle power-on time is obtained. In this way, the driving section of the next trip of the target vehicle and the travel time of traveling the driving section from the current position are predicted based on the historical vehicle use information, so that the predicted driving section and power-on time are the driving section and travel time that the user needs more, and the travel time prediction can be predicted based on the driving section. If the predicted driving section is different, the predicted power-on time corresponding to the driving section will be different, so that the power-on time prediction is more accurate and the user experience is better.

[0065] In one implementation of the present application, the vehicle power-on time prediction method provided in the implementation of the present application can be applied to the cloud, and the vehicle power-on time prediction method is performed by the cloud.

[0066] Among them, for step S100, determining the power-off time, current position and historical vehicle usage information of the target vehicle includes obtaining the vehicle identification code (i.e., VIN code), power-off time T and GPS signal L at the time of power-off (as an example of the current position) of the target vehicle after monitoring the power-off of the vehicle, and determining the historical vehicle usage information of the target vehicle through the VIN code, and the historical vehicle usage information includes the driving information of the vehicle on multiple historical driving sections.

[0067] The driving information of the vehicle on multiple historical driving sections, for example, the power-on position A, power-off position B, power-on time T of the target vehicle on the AB driving section AB1 , power-off time T AB1 ′, the target vehicle’s power-on position A, power-off position B, and power-on time T on the AB driving section AB2 , power-off time T AB2 ′, ..., the target vehicle's power-on position A, power-off position B, power-on time T on the AB driving section ABn , power-off time T ABn′; The target vehicle’s power-on position B, power-off position A, and power-on time T on the BA driving section BA1 , power-off time T BA1 ′, ..., the target vehicle's power-on position B, power-off position A, and power-on time T on the BA driving section BAn , power-off time T BAn ′; The target vehicle’s power-on position A, power-off position C, and power-on time T on the AC driving section AC1 , power-off time T AC1 ′, ..., the target vehicle's power-on position A, power-off position C, and power-on time T on the AC driving section ACn , power-off time T ACn ', of course, the driving section is determined based on the historical vehicle location and historical vehicle usage time of the target vehicle, which is only used as an example here.

[0068] In one implementation of the present application, Figure 2 As shown in FIG. 1 , the driving information of the target vehicle on multiple historical driving sections is obtained in the following manner:

[0069] S110, determining an initial historical vehicle location and a corresponding initial historical vehicle time of the target vehicle.

[0070] For example, Figure 3 As shown, the processed driving cycle records within a period of target history (for example, three months or six months) are obtained, and the driving cycle records include the power-on GPS (as an example of the power-on position), the power-off GPS (as an example of the power-off position), the power-on time, and the power-off time.

[0071] It should be noted that the power-off GPS is the power-on GPS for the next trip.

[0072] S120, clustering the initial historical vehicle location and the initial historical vehicle time based on a clustering algorithm to obtain the historical vehicle location and historical vehicle time of the target vehicle.

[0073] In the implementation of the present application, the historical vehicle usage position includes the power-on position and the power-off position, and the historical vehicle usage time includes the power-on time and the power-off time.

[0074] Exemplarily, a clustering algorithm is used to cluster the powered-on GPS to obtain multiple powered-on GPSs marked as the same category. For example, points A and B are the power-on positions after clustering, and points C, D, E, and F are the powered-on GPSs of abnormal points, which also represent different power-on positions (as examples of historical vehicle locations).

[0075] Furthermore, in the present application, a clustering algorithm is also used to cluster the power-on time and the power-off time to obtain multiple categories of power-on time and power-off time marked as the same category (as an example of historical vehicle usage time).

[0076] S130, obtaining driving information of the target vehicle on multiple historical driving sections according to historical vehicle locations and corresponding historical vehicle use times.

[0077] Exemplarily, after the historical power usage locations after clustering processing (e.g., power-on location and power-off location (i.e., power-on and power-off GPS longitude and latitude data)) are GPS mapped one by one, multiple driving cycle records (e.g., AB, BC, CA, ..., ED, DA, AF, FB) containing corresponding location categories are obtained (as an example of historical driving sections). Then, the driving information of the target vehicle in each historical driving section is obtained, including the power-on location of the target vehicle corresponding to the historical driving section (e.g., A, B, C, ..., E, D, A, F), the power-on time corresponding to the power-on location, the power-off location (e.g., B, C, A, ..., D, A, F, B), and the power-off time corresponding to the power-off location.

[0078] In another implementation of the present application, driving information of multiple historical driving sections of the target vehicle is obtained based on historical vehicle usage positions and corresponding historical vehicle usage times, including: if it is determined that the time interval between the power-off time of the target vehicle traveling from a first power-on position to a first power-off position and the power-on time of the target vehicle traveling from the first power-off position to a second power-off position is less than a preset first time interval threshold, then the driving information of the historical driving section of the target vehicle is determined as the power-on position being the first power-on position, the power-off position being the second power-off position, the power-on time being the power-on time of the target vehicle at the first power-on position, and the power-off time being the power-off time of the target vehicle at the second power-off position.

[0079] Exemplarily, continuous driving cycle data (i.e., driving cycle records) of a vehicle over a period of time is obtained, and corresponding data processing is performed. If the time interval between the power-off time when the target vehicle travels from a first power-on position to a first power-off position and the power-on time when the target vehicle travels from the first power-off position to a second power-off position is less than a preset first time interval threshold (e.g., 15 minutes), it is determined that the two sections of driving cycle data are a historical driving section.

[0080] That is, if the downtime of two adjacent driving cycle data is less than 15 minutes, the two driving cycles are combined into one driving cycle to obtain a historical driving section in which the power-on position is the first power-on position, the power-off position is the second power-off position, the power-on time is the power-on time of the target vehicle at the first power-on position, and the power-off time is the power-off time of the target vehicle at the second power-off position. Of course, the preset first time interval threshold can be set according to actual needs, and is only used for exemplary description here.

[0081] Further, for step S200, the historical travel probability and historical vehicle usage time of the target vehicle in the target historical driving section are determined based on the current position and historical vehicle usage information, and the historical travel time probability corresponding to the historical travel time is determined, including: when it is determined based on the current position and historical vehicle usage information that the current position is within a preset range of one of the power-on positions of the historical vehicle usage positions, the historical travel probability and historical vehicle usage time of the target vehicle in the target historical driving section are determined based on the historical vehicle usage information, and the historical travel time probability corresponding to the historical travel time is determined.

[0082] Exemplarily, the distance between the GPS signal L (i.e., the current position) and the different location categories in the historical vehicle location when the target vehicle is powered off is calculated to obtain the minimum distance value (assuming that the distance between L and point A is the smallest). If the distance is within a preset range (e.g., 1 meter, 5 meters, etc.) (i.e., less than or equal to the preset distance threshold), it is determined that the current position belongs to the historical vehicle location where the location category point C is located, and the subsequent steps can be continued. If it does not fall within the preset range (i.e., greater than the preset distance threshold), it is considered that the current position is a location that does not exist in the historical vehicle location, so there is no matching location category, and the subsequent prediction of the user's vehicle section is not performed, and the vehicle power-on time prediction can be directly based on the historical vehicle time. Of course, the preset distance threshold (i.e., the preset range) can be set according to actual needs, and this is only an exemplary description.

[0083] Furthermore, in one implementation of the present application, Figure 4 As shown, the historical travel probability of the target vehicle on the target historical driving section is determined according to the current position and historical vehicle use information, including the following steps:

[0084] S210, determining a vehicle position transfer probability matrix of the target vehicle according to historical vehicle usage information.

[0085] Exemplarily, in the implementation of the present application, self-learning can be performed based on historical vehicle usage information to obtain a vehicle position transfer probability matrix for each historical driving section containing different location categories (ie, from different power-on positions to different power-off positions).

[0086] Furthermore, if Figure 5 As shown, in one implementation of the present application, the vehicle position transfer probability matrix of the target vehicle is determined according to the historical vehicle use information, including:

[0087] S211, determining the historical vehicle usage times corresponding to the historical driving section according to the historical vehicle usage information.

[0088] Exemplarily, the historical vehicle usage times corresponding to each historical driving section are obtained based on the historical location information obtained after clustering processing. For example, the historical vehicle usage times of AA are 0 times, the historical vehicle usage times of AB are 50 times, the historical vehicle usage times of AC are 10 times, the historical vehicle usage times of AD are 30 times, the historical vehicle usage times of AE are 0 times, the historical vehicle usage times of AF are 10 times, etc., and the historical vehicle usage times from all power-on locations to all power-off locations are determined in this way.

[0089] In another implementation of the present application, the historical number of vehicle usage corresponding to the historical driving section is determined based on the historical vehicle usage information, including: if it is determined that the time interval between the power-on time and the power-off time of the target vehicle traveling from the first power-on position to the first power-off position in the historical driving section is less than a preset second time interval threshold, and the average speed of the target vehicle is less than the preset speed threshold, then the historical number of vehicle usage in the historical driving section is determined to be zero.

[0090] Exemplarily, in order to ensure the accuracy of the probability after self-learning, the implementation of the present application will also process the driving cycle data. For example, if the time interval between the power-on time and the power-off time from the first power-on position to the first power-off position is less than a preset second time interval threshold (e.g., 15 minutes), and the average speed of the target vehicle is less than a preset speed threshold (e.g., 3 km / h), then it is determined that the number of historical vehicle uses in this historical driving section is zero.

[0091] That is, if the driving duration of a driving cycle (the first power-off time minus the first power-on time) is less than 15 minutes, and the average vehicle driving speed is less than 3 km / h, the driving cycle is deleted and not included in the calculation. Of course, the preset second time interval threshold and the preset vehicle speed threshold can be set according to actual needs, which is only an example here.

[0092] S212, determining a historical travel probability of the target vehicle on the historical driving section according to the historical vehicle usage times of the target vehicle on the historical driving section.

[0093] Exemplarily, in one implementation of the present application, a historical travel probability of a target vehicle in a historical driving section is determined based on the historical number of times the target vehicle has been used in the historical driving section, including: obtaining the historical travel probability of the target vehicle in the historical driving section based on the ratio of the historical number of times the target vehicle has been used in the historical driving section corresponding to the first power-on position as the driving starting point and the first power-off position as the driving end point, and the historical number of times the target vehicle has been used in all the historical driving sections corresponding to the first power-on position as the driving starting point and all power-off positions as the driving end points.

[0094] Exemplarily, taking the calculation of the historical travel probability of AB (as an example of a historical driving segment) as an example, the driving cycle record of the power-on GPS category (that is, the power-on position) = A is obtained. For example, the historical driving segment with A (as an example of the first power-on position) as the starting point and all power-off positions as the end points has a total of n historical vehicle usage times, which is 100 in the above example.

[0095] Then obtain the driving cycle record with power-on GPS category = A and power-off GPS category (that is, power-off position) = B (as an example of the first power-off position), for example, the historical vehicle usage times of the historical driving section with A as the driving starting point and B as the driving end point total m, which is 50 in the above example.

[0096] Then, the historical travel probability of the historical driving section with the first power-on position as the driving starting point and the first power-off position as the driving end point is m / n, that is, 50 / 100=0.5.

[0097] In this way, the total historical vehicle usage times from all the first power-on positions to all the first power-off positions are calculated (for example, the total historical vehicle usage times of AA, B, C, D, E, and F, the total historical vehicle usage times of BA, B, C, D, E, and F, the total historical vehicle usage times of CA, B, C, D, E, and F, ..., the total historical vehicle usage times of FA, B, C, D, E, and F), and then the historical vehicle usage times from the first power-on position to each first power-off position are calculated (for example, the historical vehicle usage times of AA, AB, ..., AF, BA, ..., BF, ..., FA, ..., FF), and then the historical travel probability from the first power-on position to each first power-off position is obtained (for example, the historical travel probability of AA relative to AA, B, C, D, E, and F, ..., the historical travel probability of BF relative to BA, B, C, D, E, and F, ..., the historical travel probability of FF relative to FA, B, C, D, E, and F).

[0098] S213, obtaining a vehicle position transfer probability matrix according to the historical travel probability of the target vehicle on the historical driving section.

[0099] Exemplarily, the historical travel probabilities from each first power-on position to each first power-off position are summarized as follows: Figure 3 The table shown in the figure is used to obtain the GPS state transfer matrix (as an example of the vehicle position transfer probability matrix). In this way, the vehicle position transfer probability matrix is ​​obtained by self-learning in advance. When predicting the vehicle power-on time, the current position is determined, and the historical travel probability of the target historical driving section corresponding to each power-off position is queried from the vehicle position transfer probability matrix, thereby accelerating the efficiency of vehicle power-on prediction.

[0100] For example Figure 3 As shown, the historical travel probability of AA is 0, the historical travel probability of AB is 0.5, the historical travel probability of AC is 0.1, the historical travel probability of AD is 0.3, the historical travel probability of AE is 0, the historical travel probability of AF is 0.1, the historical travel probability of BA is 0.6, the historical travel probability of BB is 0, the historical travel probability of BC is 0.2, the historical travel probability of BD is 0, the historical travel probability of BE is 0.1, the historical travel probability of BF is 0.1, the historical travel probability of CA is 0.8, the historical travel probability of CB is 0, the historical travel probability of CC is 0, the historical travel probability of CD is 0.1, the historical travel probability of CE is 0, the historical travel probability of CF is 0.1, and the historical travel probability of D is 0. The vehicle position transfer probability matrix is: A's historical travel probability is 0.7, DB's historical travel probability is 0.1, DC's historical travel probability is 0.1, DD's historical travel probability is 0.1, DE's historical travel probability is 0, DF's historical travel probability is 0, EA's historical travel probability is 0, EB's historical travel probability is 0, EC's historical travel probability is 0, ED's historical travel probability is 0.9, EE's historical travel probability is 0.1, EF's historical travel probability is 0, FA's historical travel probability is 0.1, FB's historical travel probability is 0.6, FC's historical travel probability is 0.3, FD's historical travel probability is 0, FE's historical travel probability is 0, and FF's historical travel probability is 0.

[0101] Furthermore, in another implementation of the present application, the state transition of the vehicle GPS is actually calculated based on the Markov chain model. Therefore, in the present application, determining the vehicle position transition probability matrix of the target vehicle based on the historical vehicle use information includes: when determining that the historical vehicle use information satisfies the corresponding conditions of the Markov chain model, obtaining the vehicle position transition probability matrix based on the historical vehicle use information.

[0102] It should be noted that the Markov chain can be defined by a transfer matrix and a transfer graph. Therefore, when the historical vehicle usage information satisfies the transfer matrix calculation principle of the Markov chain model (as an example of the corresponding conditions), the historical travel probability of the historical driving sections of the target vehicle can be calculated based on the historical vehicle usage information based on the calculation principle of the Markov chain model, and then the vehicle position transfer probability matrix can be obtained.

[0103] S220, determining the historical travel probability of the target vehicle on the target historical driving section from the vehicle position transfer probability matrix according to the current position.

[0104] Exemplarily, according to the current position, the historical travel probability of the target historical driving section corresponding to each power-off position with the power-on position as the current position and the power-off position as the power-off position is queried from the vehicle position transfer probability matrix.

[0105] For example, if the current position is determined to be A, the historical travel probabilities of AA, AB, AC, AD, AE, and AF are queried from the vehicle position transfer probability matrix.

[0106] Furthermore, in one implementation of the present application, in order to ensure the self-learning accuracy of the vehicle position transfer probability matrix, the travel mode (i.e., historical travel probability) of the target vehicle is only learned and trained when the driving cycle data (i.e., historical driving sections) of the target vehicle is greater than or equal to a preset threshold.

[0107] In this way, in the present application, the vehicle position transfer probability matrix is ​​obtained in advance. When the vehicle power-on time prediction is required, the vehicle position transfer probability matrix corresponding to the vehicle VIN number can be directly obtained, and then the historical travel probability of the target historical driving section can be queried from the vehicle position transfer probability matrix.

[0108] Furthermore, in the implementation of the present application, after calculating the historical travel probability of each historical driving section, it is also necessary to calculate the historical travel time and the historical travel time probability of each historical driving section.

[0109] Among them, in one implementation of the present application, Figure 4 As shown, the historical travel time of the target vehicle on the target historical driving section is determined according to the current position and the historical vehicle use information, and the historical travel time probability corresponding to the historical travel time is determined, including the following steps.

[0110] S230, determining the historical travel time and the historical travel time probability of the target vehicle on the historical driving section according to the historical vehicle use information.

[0111] In one implementation of the present application, Figure 6 As shown, determining the historical travel time and the historical travel time probability of the target vehicle on the historical driving section according to the historical vehicle use information includes the following steps.

[0112] S231, determining all historical travel times of the target vehicle on the historical driving sections and the historical vehicle usage times corresponding to all historical travel times according to the power-on time.

[0113] Exemplarily, taking the calculation of the historical travel time and the historical travel time probability of AB (as an example of a historical driving segment) as an example, all power-on times (as examples of historical travel times) of the driving cycle record set I with the power-on GPS category (i.e., the power-on position) = A and the power-off GPS category (i.e., the power-off position) = B (as an example of the first power-off position) and the historical number of vehicle uses based on each power-on time, i.e., the aforementioned m times (e.g., 50 times), are obtained.

[0114] S232, determining the historical usage times of the target vehicle during historical travel time.

[0115] For example, assume that the historical travel times of the 50 historical driving sections corresponding to AB are 8 o'clock, 12 o'clock, 13 o'clock, and 15 o'clock, and it is determined that the historical number of vehicle usages at 8 o'clock is 12 times, the historical number of vehicle usages at 12 o'clock is 15 times, the historical number of vehicle usages at 13 o'clock is 20 times, and the historical number of vehicle usages at 15 o'clock is 3 times.

[0116] S233, determining the historical travel time probability of the target vehicle on the historical driving section at the historical travel time according to the ratio of the historical vehicle usage times at the historical travel time to the historical vehicle usage times corresponding to all historical travel times.

[0117] Exemplarily, the historical travel time probability of the target vehicle in the historical driving section at each historical travel time is determined according to the ratio of the historical vehicle usage times of the target vehicle in the historical driving section to the total historical vehicle usage times in the historical driving section. For example, in the AB historical driving section, the historical vehicle usage times of the target vehicle at 8 o'clock are 12 times, and the historical travel time probability of the target vehicle in the AB historical driving section at 8 o'clock is 0.24, the historical vehicle usage times at 12 o'clock are 15 times, and the historical travel time probability of the target vehicle in the AB historical driving section at 12 o'clock is 0.3, the historical vehicle usage times at 13 o'clock are 20 times, and the historical travel time probability of the target vehicle in the AB historical driving section at 13 o'clock is 0.4, and the historical vehicle usage times at 15 o'clock are 3 times, and the historical travel time probability of the target vehicle in the AB historical driving section at 15 o'clock is 0.06.

[0118] In this way, the above-mentioned calculation method is used to calculate the historical travel time of the target vehicle in each historical driving section (for example, AA, AB, ..., AF, BA, ..., BF, ..., FA, ..., FF), and then based on the historical travel times of each historical travel time in each historical driving section (for example, the historical travel times of AB's historical travel time 1) and the total historical travel times in the corresponding historical driving section (for example, the historical travel times of AB), the historical travel time probability of the target vehicle in the corresponding historical driving section at each historical travel time is obtained.

[0119] S240, determining, according to the current position of the target vehicle, from the historical travel time of the historical travel section and the historical travel time probability, the historical travel time probability corresponding to the historical travel time of the target vehicle in the target historical travel section.

[0120] Exemplarily, based on the current position, the historical travel time probabilities corresponding to the historical travel times of the historical driving sections and the historical travel times are determined from the historical travel times of the historical driving sections with the power-on position as the current position and the power-off position as the target historical driving sections corresponding to each power-off position.

[0121] For example, if the current position is determined to be A, then all historical travel times and the historical travel time probabilities of each historical travel time of AA, all historical travel times and the historical travel time probabilities of each historical travel time of AB, all historical travel times and the historical travel time probabilities of each historical travel time of AC, all historical travel times and the historical travel time probabilities of each historical travel time of AD, all historical travel times and the historical travel time probabilities of each historical travel time of AE, and all historical travel times and the historical travel time probabilities of each historical travel time of AF are queried from the vehicle position transfer probability matrix.

[0122] In another implementation of the present application, before calculating the probability of historical travel time, as described above, the initial historical travel time of each historical driving section set I is clustered based on a clustering algorithm to obtain the processed historical travel time. That is, multiple historical travel times within a preset time interval are clustered into the same historical travel time.

[0123] For example, if the power-on time (ie, historical travel time) is determined to be 12:55, 13:05, 13:10, and 13:12, the historical travel time is obtained as 13 o'clock after clustering. In this way, all initial historical travel times are clustered to obtain multiple categories K of historical travel times.

[0124] It should be noted that the clustering algorithm in the implementation of the present application can be a k-medoids algorithm, a Clara algorithm, etc., and of course it can also be other algorithms. Those skilled in the art can choose according to data distribution or application scenarios.

[0125] In another implementation of the present application, the historical travel time probability calculation can also be performed based on the Gaussian mixture model. Therefore, the vehicle power-on time prediction method provided in the implementation of the present application determines the historical travel time probability corresponding to the historical travel time, including: determining the historical travel time probability corresponding to each historical travel time of the target vehicle in the historical driving section based on the Gaussian mixture model.

[0126] Exemplarily, for each historical travel time of multiple categories K corresponding to each historical driving section, K sub-models of a mixed Gaussian distribution model (i.e., a Gaussian mixture model) are established, each sub-model corresponds to a historical travel time, and then the historical travel number, historical travel time and K of the historical driving section are input, and based on the historical travel times in set I, the EM algorithm (Expectation Maximization Algorithm, also known as the expectation maximization algorithm) is used to solve the parameters of the Gaussian mixture model to obtain a Gaussian mixture model suitable for the historical driving section, and then the historical travel time probabilities of each historical travel time of the historical driving section are obtained based on the Gaussian mixture model.

[0127] Furthermore, in another implementation of the present application, in order to ensure the accuracy of the historical travel time probability of the historical travel time, the self-learning of the historical travel time and the historical travel time probability is performed only when the number of historical travels of the historical driving section is greater than or equal to the preset threshold. If it is not satisfied, the predicted user's car use time is directly determined based on the historical travel time with the largest number of historical travel times. Of course, the preset threshold can be set based on actual needs and is not specifically limited here.

[0128] Thus, in the present application, the historical travel time probability of each historical driving section is obtained in advance, and when the vehicle power-on time prediction is required, the historical travel time probability of the target historical driving section can be directly queried.

[0129] Furthermore, in one implementation of the present application, Figure 7 As shown, in step S300, according to the power-off time, the historical travel probability, the historical travel time and the historical travel time probability, the predicted user car use section is determined, and the predicted user car use time corresponding to the predicted user car use section is determined, including:

[0130] S310: taking a historical travel time that is later than the power-off time and has the highest probability among the historical travel times as the target historical travel time.

[0131] S320, determining a predicted travel probability corresponding to the target historical travel section according to the historical travel probability of the target historical travel section and the historical travel time probability corresponding to the target historical travel time.

[0132] For example, according to the vehicle position transfer probability matrix, the transfer probability (ie, historical travel probability) of the historical driving section from point A (as an example of the current position) to other power-off position i can be obtained as P Ai, where i represents different location categories (i.e., different power-off locations), and the power-on time probability (i.e., the historical travel time probability corresponding to the historical travel time) of Ai (e.g., AA, AB, AC, AD, AE, AF, as examples of the target historical driving sections) obtained according to the Gaussian mixture model. According to the power-off time T, the time t with the largest historical travel time probability and t>T among the historical travel times of each target historical driving section is obtained. i (as an example of the target historical travel time) and the probability P corresponding to the target historical travel segment ci_time , then at t i The predicted travel probability r of the target historical driving section from point A to point i i =P ci ×P ci_time .

[0133] For example, taking the target historical driving section AB as an example, and the power-off time T as 12 o'clock as an example, as mentioned above, the 10 historical travel times of the target historical driving section AB are 8 o'clock, 12 o'clock, 13 o'clock, and 15 o'clock. And the historical travel time probability of the target vehicle in the historical driving section AB at 8 o'clock is 0.24, the historical travel time probability of the target vehicle in the historical driving section AB at 12 o'clock is 0.3, the historical travel time probability of the target vehicle in the historical driving section AB at 13 o'clock is 0.4, and the historical travel time probability of the target vehicle in the historical driving section AB at 15 o'clock is 0.06.

[0134] The historical travel time t>T is determined to be 13 o'clock and 15 o'clock. The probability of the historical travel time with the highest probability between 13 o'clock and 15 o'clock is 0.4 corresponding to 13 o'clock. The target historical travel time t of the target historical driving section AB is determined as follows: i It is 13 o'clock, and the historical travel probability of AB is 0.5, then the predicted travel probability of going to point B at point A and at 13 o'clock is 0.5*0.4=0.2.

[0135] Furthermore, the target historical travel time is calculated for all target historical travel sections corresponding to the driving starting point A (i.e., the power-on position) to other driving end points (i.e., the power-off position), whose historical travel time is later than (i.e., greater than) the power-off time and whose historical travel time has the highest probability.

[0136] For example, assuming that the historical travel time in AA is later than the power-off time, and the target historical travel time with the highest probability is 14 o'clock, the historical travel time probability at 14 o'clock is 0.2, and the historical travel probability of AA is 0, then the predicted travel probability of powering on at point A and heading to point A at 14 o'clock is 0.2*0=0; assuming that the historical travel time in AC is later than the power-off time, and the target historical travel time with the highest probability is 17 o'clock, the historical travel time probability at 17 o'clock is 0.5, and the historical travel probability of AC is 0.1, then the predicted travel probability of powering on at point A and heading to point C at 17 o'clock is 0.5*0.1=0.05; assuming that the historical travel time in AD is later than the power-off time, and the target historical travel time with the highest probability is 17 o'clock, the historical travel time at 17 o'clock is The probability is 0.8, and the historical travel probability of AD is 0.3. Then the predicted travel probability of powering on at point A and heading to point D at 17 o'clock is determined to be 0.8*0.3=0.24; assuming that the historical travel time in AE is later than the power-off time, and the target historical travel time with the largest probability of historical travel time is 13 o'clock, the historical travel time probability of 13 o'clock is 0.3, and the historical travel probability of AE is 0. Then the predicted travel probability of powering on at point A and heading to point B at 14 o'clock is determined to be 0.3*0=0; assuming that the historical travel time in AF is later than the power-off time, and the target historical travel time with the largest probability of historical travel time is 16 o'clock, the historical travel time probability of 16 o'clock is 0.4, and the historical travel probability of AF is 0.1. Then the predicted travel probability of powering on at point A and heading to point F at 16 o'clock is determined to be 0.1*0.4=0.04.

[0137] S330, taking the target historical driving section with the largest predicted travel probability as the predicted user's car use section, and taking the target historical travel time corresponding to the predicted user's car use section as the predicted user's car use time.

[0138] Exemplarily, the target historical driving section with the highest predicted travel probability is determined to be AD (as an example of the predicted user car use section), and the target historical travel time corresponding to AD is 17:00 (as an example of the predicted user car use time). In this way, based on the user's historical car use information, the predicted user car use section where the user is most likely to travel (that is, the predicted travel probability is the highest) is determined to be AD, and the predicted user car use time when the user is most likely to travel on the predicted user car use section (that is, the historical travel time probability is the highest) is determined to be 17:00, so that the vehicle power-on time can be determined based on the predicted user car use section, which can make the vehicle power-on time prediction more accurate.

[0139] Furthermore, in one implementation of the present application, the target historical driving section with the highest predicted travel probability is used as the predicted user vehicle section, including: when it is determined that the maximum predicted travel probability is greater than a preset travel probability threshold, the target historical driving section with the highest predicted travel probability is used as the predicted user vehicle section.

[0140] For example, assume that point A is F The probability of powering on at time (e.g. 17:00) and heading to D is the highest. If the value is greater than or equal to a preset threshold (e.g. 0.2), the target historical driving section corresponding to AD is determined as the predicted user driving section. If it is less than 0.2, the predicted user driving section is not determined.

[0141] In step S400, if the predicted user vehicle usage section (eg, AD) and the predicted user vehicle usage time (eg, 17:00) are determined, the next vehicle power-on time is predicted to be 17:00 (as an example of the predicted power-on time).

[0142] In another implementation of the present application, obtaining the predicted power-on time of the target vehicle based on the predicted user vehicle usage time may also be to determine a preset time period before the predicted user vehicle usage time as the predicted power-on time of the target vehicle.

[0143] The preset time period may specifically be a time period such as 3 minutes, 5 minutes, 8 minutes, 10 minutes, 15 minutes, etc.

[0144] For example, if the predicted user vehicle usage time is determined to be 17:00, the predicted power-on time is determined to be 16:57, 16:55, 16:52, 16:50, and 16:45. In this way, the vehicle can be started in advance according to the predicted user vehicle usage time to complete the corresponding vehicle preparation operations. Then, when the user uses the vehicle at the predicted user vehicle usage time, the vehicle can be directly operated without manually powering on the vehicle.

[0145] The vehicle power-on time prediction method provided by the implementation method of the present application, whether for new energy vehicles or fuel vehicles, accurate power-on time prediction can help car owners plan vehicle power-on and improve user experience. Moreover, for new energy vehicles, accurate power-on time prediction can help car owners optimize charging plans, avoid charging during peak hours, save energy costs, and optimize energy management. The vehicle power-on time prediction method provided by the implementation method of the present application is also a vehicle power-on time prediction method based on a user travel model, which uses user historical travel data (that is, historical vehicle use information) and adopts Gaussian mixture models, Markov chain models, clustering algorithms and other technologies to learn user travel patterns (that is, predict user vehicle use sections), and then predict the next vehicle power-on time based on the current vehicle power-off GPS (that is, current location) and power-off time data.

[0146] Specifically, we first study the user travel patterns.

[0147] Among them, data preparation is first performed: historical vehicle use information is obtained, such as obtaining continuous driving cycle data of the vehicle within a period of time (that is, driving information of historical driving sections), and each driving cycle data includes the vehicle power-on time, the corresponding GPS information when powered on (that is, the power-on position), the vehicle power-off time, and the corresponding GPS information when powered off (that is, the power-off position). Further, data processing is performed. As mentioned above, if the downtime of two adjacent driving cycles is less than 15 minutes, the two driving cycles are merged into one driving cycle; if the driving time of a driving cycle is less than 5 minutes and the average driving speed is less than 3km / h, the driving cycle is deleted and the number of historical vehicle usage is not recorded. And when the number of historical driving sections of the vehicle is greater than or equal to the preset threshold, the travel mode of the vehicle is learned and trained.

[0148] Next, model learning is performed: driving from the GPS at power-on (i.e., power-on position) to the GPS at power-off (i.e., power-off position) is called a GPS transfer. The transfer probabilities between different GPSs are statistically analyzed based on the driving cycle data within a period of history, and a transfer probability matrix (i.e., vehicle position transfer probability matrix) is constructed. Further, for each pair of GPS transfer relationships, its power-on time model is learned. Take GPS1→GPS2 as an example: all driving cycle records that satisfy "power-on GPS = GPS1 and power-off GPS = GPS2" are obtained from the above driving cycle data set, and the power-on time (i.e., historical travel time) of these records is obtained to form a power-on time set on_time_list. The density clustering algorithm (i.e., the aforementioned EM algorithm) is used to cluster on_time_list to obtain the number of categories K (i.e., the number of historical travel times) of the time set. The initial parameters (e.g., historical travel time) and K are input, and a Gaussian mixture model is learned based on the time set on_time_list to obtain the historical travel time probability.

[0149] Secondly, the vehicle power-on time is predicted: the GPS data (i.e. current location) and power-off time of the vehicle when it was last powered off are obtained. The next possible travel destination of the current vehicle (i.e. predicted user vehicle usage route) and probability (i.e. predicted travel probability) can be obtained through the GPS transfer probability matrix (i.e. vehicle position transfer probability matrix). Combined with the vehicle power-off time, the time point with the highest probability of the next trip (i.e. predicted user vehicle usage time) is comprehensively calculated, which is the next power-on time (i.e. predicted power-on time).

[0150] That is, the vehicle power-on time prediction method provided by the implementation of the present application first obtains the vehicle's historical travel data (that is, historical vehicle usage information), including: the vehicle power-on time, the corresponding GPS information when powered on (that is, the power-on position), the vehicle power-off time, the corresponding GPS information when powered off (that is, the power-off position). Then, the user's travel pattern is learned based on the historical travel data, including: learning the transition probability matrix between different GPSs (that is, the vehicle position transfer probability matrix), and learning the power-on time model. Finally, predictions are made based on the learned user travel patterns, including: predicting the destination of the vehicle's next trip based on the GPS when the current vehicle is powered off (that is, predicting the user's vehicle usage section), and calculating the next power-on time with the highest probability based on the power-off time (that is, predicting the user's vehicle usage time).

[0151] Furthermore, the implementation of the present application also provides a vehicle management method, see Figure 8 , specifically including the following steps.

[0152] S10, determining a predicted power-on time of a target vehicle in a parking and power-off state.

[0153] Exemplarily, after the predicted power-on time is obtained by using the aforementioned vehicle power-on time prediction method, the predicted power-on time of the target vehicle in the parked and powered-off state is obtained.

[0154] S20, powering on the target vehicle at the predicted power-on time.

[0155] For example, the target vehicle is powered on at the predicted power-on time, and the vehicle is prepared. In this way, accurate power-on time prediction can help the owner complete vehicle preparation behaviors such as turning on the air conditioner and adjusting the seat in advance, thereby improving the overall user experience.

[0156] Furthermore, in the implementation method of the present application, after obtaining the predicted user's vehicle usage section and the predicted user's vehicle usage time, notification information can also be generated based on the predicted user's vehicle usage section and the predicted user's vehicle usage time (for example, it is predicted that you will set off for location D at 17:00, and the vehicle will automatically start at 17:00. Please confirm whether it needs to be started) and sent to the user terminal to confirm with the user whether the vehicle will be powered on at the predicted user's vehicle usage time, and obtain the user's response information based on the notification information. If it is confirmed that the vehicle will be powered on at the predicted user's vehicle usage time according to the response information, the target vehicle will be controlled to be powered on at the predicted vehicle power-on time.

[0157] Further, in one implementation of the present application, see Fig. 9 , the vehicle management method also includes the following steps.

[0158] S30, determining a predicted destination of the target vehicle in a parked and powered-off state.

[0159] Exemplarily, after obtaining the predicted user vehicle usage section using the aforementioned vehicle power-on time prediction method, the travel end point of the predicted user vehicle usage section is used as the predicted destination.

[0160] S40, determining a driving route of the target vehicle according to the predicted destination.

[0161] For example, if it is confirmed according to the response information that the vehicle is powered on at the predicted time when the user uses the vehicle, the driving route of the target vehicle is planned according to the power-off location and the predicted destination, and navigation information is generated.

[0162] It should be noted that step S10 and step S30 can be executed simultaneously, or S10 can be executed first and then S30, or S30 can be executed first and then S10. Step S20 and step S30 can be executed simultaneously, or S20 can be executed first and then S30, or S30 can be executed first and then S20.

[0163] The vehicle power-on time prediction method and vehicle management method provided by the implementation of the present application can also be applied to electronic devices such as vehicles and remote terminals.

[0164] See also Fig.10 , Fig.10 The figure shows a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Fig.10 As shown, the electronic device may include: a transceiver 121 , a processor 122 , and a memory 123 .

[0165] The processor 122 executes the computer-executable instructions stored in the memory, so that the processor 122 executes part of the technical solutions of the vehicle power-on time prediction method and / or the vehicle management method in the above-mentioned embodiment. The processor 122 can be a general-purpose processor, including a central processing unit CPU, a network processor (NP), etc.; it can also be a digital data processor DSP, an application-specific integrated circuit ASIC, a field programmable gate array FPGA or other programmable logic devices, discrete gates or transistor logic devices, and discrete hardware components.

[0166] The memory 123 is connected to the processor 122 via a system bus and completes communication between them. The memory 123 is used to store computer program instructions.

[0167] By way of example and not limitation, the memory 123 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a tape, or a universal serial bus (USB) drive, or a combination of two or more of these. Where appropriate, the memory 123 may include a removable or non-removable (or fixed) medium. Where appropriate, the memory 123 may be inside or outside the integrated gateway device. In a particular embodiment, the memory 123 is a non-volatile solid-state memory. In a particular embodiment, the memory 123 includes a read-only memory (ROM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically rewritable ROM (EAROM), or a flash memory, or a combination of two or more of these.

[0168] The transceiver 121 may be used to obtain tasks to be executed and configuration information of the tasks to be executed.

[0169] The system bus can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The system bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus. The transceiver is used to realize the communication between the database access device and other computers (such as clients, read-write libraries, and read-only libraries). The memory may include random access memory (RAM) and may also include non-volatile memory.

[0170] An embodiment of the present application also provides a chip for running instructions, which is used to execute the technical solutions of the vehicle power-on time prediction method and / or the vehicle management method in the above-mentioned embodiments.

[0171] An embodiment of the present application also provides a computer-readable storage medium, which stores computer instructions. When the computer instructions are executed on a processor of an electronic device, the processor of the electronic device executes the technical solutions of the vehicle power-on time prediction method and / or the vehicle management method of the above-mentioned embodiment.

[0172] In some possible implementations, various aspects of the method provided in the present application can also be implemented in the form of a program product, which includes program code. When the program product is run on a processor of an electronic device, the program code is used to enable the processor of the electronic device to execute the steps of the method described above in this specification according to various exemplary implementations of the present application. For example, the electronic device can execute the vehicle power-on time prediction method and / or vehicle management method recorded in the embodiments of the present application.

[0173] The program product may employ any combination of one or more readable media. The readable medium may be a readable data medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0174] The implementation method of the present application also provides a computer program product, which includes a computer program stored in a computer-readable storage medium. At least one processor can read the computer program from the computer-readable storage medium. When at least one processor executes the computer program, it can implement the technical solutions of the vehicle power-on time prediction method and / or the vehicle management method in the above-mentioned embodiments.

[0175] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices and computer program products according to the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable information processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable information processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0176] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable information processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0177] These computer program instructions can also be loaded onto a computer or other programmable information processing device so that a series of operation steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0178] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary technical means in the art that are not disclosed in the present application.

[0179] It should be noted that, in addition to the implementation of the present application described in the above-mentioned specific embodiments, those skilled in the art can easily understand other advantages and effects of the present application from the contents disclosed in this specification. Although the description of the present application is introduced in conjunction with the preferred embodiment, this does not mean that the features of this invention are limited to the implementation. On the contrary, the purpose of introducing the invention in conjunction with the implementation is to cover other options or modifications that may extend based on the claims of the present application. In order to provide an in-depth understanding of the present application, the above description contains many specific details, and the present application may also be implemented without using these details. In addition, in order to avoid confusion or blurring the focus of the present application, some specific details will be omitted in the description. It should be noted that, in the absence of conflict, the embodiments in the present application and the features in the embodiments can be combined with each other.

[0180] It should be noted that in this specification, similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings.

[0181] Although the present application has been illustrated and described by referring to certain preferred implementations of the present application, it should be understood by those skilled in the art that the above contents are further detailed descriptions of the present application in combination with specific implementations, and it cannot be determined that the specific implementation of the present application is limited to these descriptions. Those skilled in the art may make various changes in form and details, including making several simple deductions or substitutions, without departing from the spirit and scope of the present application.

Claims

1. A vehicle power-on time prediction method, characterized in that: The method comprises: Determine the power-off time, current location, and historical vehicle usage information of the target vehicle, wherein the historical vehicle usage information includes driving information of the target vehicle on multiple historical driving sections; Determine the historical travel probability and historical travel time of the target vehicle in a target historical travel section according to the current position and the historical vehicle use information, and determine the historical travel time probability corresponding to the historical travel time, wherein the target historical travel section is a historical travel section whose travel starting point is the current position among the historical travel sections included in the historical vehicle use information; Determine a predicted user car usage section according to the power-off time, the historical travel probability, the historical travel time, and the historical travel time probability, and determine a predicted user car usage time corresponding to the predicted user car usage section; The predicted power-on time of the target vehicle is obtained according to the predicted user vehicle use time.

2. The vehicle power-on time prediction method according to claim 1, characterized in that: Determining a predicted user car use section according to the power-off time, the historical travel probability, the historical travel time, and the historical travel time probability, and determining a predicted user car use time corresponding to the predicted user car use section, including: The historical travel time that is later than the power-off time and has the highest probability among the historical travel times is used as the target historical travel time; Determine a predicted travel probability corresponding to the target historical travel section according to the historical travel probability of the target historical travel section and the historical travel time probability corresponding to the target historical travel time; The target historical driving section with the largest predicted travel probability is used as the predicted user car use section, and the target historical travel time corresponding to the predicted user car use section is used as the predicted user car use time.

3. The vehicle power-on time prediction method according to claim 1 or 2, characterized in that: The driving information of the target vehicle on multiple historical driving sections is obtained in the following manner: Determine the initial historical vehicle location and the corresponding initial historical vehicle time of the target vehicle; Performing clustering processing on the initial historical vehicle location and the initial historical vehicle time based on a clustering algorithm to obtain the historical vehicle location and historical vehicle time of the target vehicle; The driving information of the target vehicle on the plurality of historical driving sections is obtained according to the historical vehicle locations and the corresponding historical vehicle use times.

4. The vehicle power-on time prediction method according to claim 3, characterized in that: Determining the historical travel probability of the target vehicle on the target historical travel section according to the current position and the historical vehicle use information includes: Determine a vehicle position transfer probability matrix of the target vehicle according to the historical vehicle use information; The historical travel probability of the target vehicle on the target historical driving section is determined from the vehicle position transfer probability matrix according to the current position.

5. The vehicle power-on time prediction method according to claim 4, characterized in that: Determining a vehicle position transfer probability matrix of a target vehicle according to the historical vehicle use information includes: Determine the historical vehicle usage times corresponding to the historical driving section according to the historical vehicle usage information; Determine the historical travel probability of the target vehicle in the historical driving section according to the historical vehicle usage times of the target vehicle in the historical driving section; The vehicle position transfer probability matrix is ​​obtained according to the historical travel probability of the target vehicle on the historical driving section.

6. The vehicle power-on time prediction method according to claim 5, characterized in that: The historical vehicle usage position includes a power-on position and a power-off position, and determining the historical travel probability of the target vehicle in the historical driving section according to the historical vehicle usage times of the target vehicle in the historical driving section includes: The historical travel probability of the target vehicle in the historical driving section is obtained based on the ratio of the historical number of times the target vehicle has been used in the historical driving section corresponding to the first power-on position as the driving starting point and the first power-off position as the driving end point, and the historical number of times the target vehicle has been used in all the historical driving sections corresponding to the first power-on position as the driving starting point and all power-off positions as the driving end points.

7. The vehicle power-on time prediction method according to claim 6, characterized in that: The historical vehicle use time includes a power-on time and a power-off time. The driving information of the target vehicle on multiple historical driving sections is obtained according to the historical vehicle use position and the corresponding historical vehicle use time, including: If it is determined that the time interval between the power-off time of the target vehicle traveling from the first power-on position to the first power-off position and the power-on time of traveling from the first power-off position to the second power-off position is less than a preset first time interval threshold, then the driving information of the historical driving section of the target vehicle is determined as the power-on position being the first power-on position, the power-off position being the second power-off position, the power-on time being the power-on time of the target vehicle at the first power-on position, and the power-off time being the power-off time of the target vehicle at the second power-off position.

8. The vehicle power-on time prediction method according to claim 7, characterized in that: Determining the historical vehicle usage times corresponding to the historical driving section according to the historical vehicle usage information includes: If it is determined that the time interval between the power-on time and the power-off time of the target vehicle traveling from the first power-on position to the first power-off position in the historical driving section is less than a preset second time interval threshold, and the average speed of the target vehicle is less than a preset speed threshold, then it is determined that the historical number of vehicle uses in the historical driving section is zero.

9. The vehicle power-on time prediction method according to any one of claims 4 to 8, characterized in that: Determining a vehicle position transfer probability matrix of the target vehicle according to the historical vehicle use information includes: When it is determined that the historical vehicle use information satisfies the corresponding condition of the Markov chain model, the vehicle position transfer probability matrix is ​​obtained according to the historical vehicle use information.

10. The vehicle power-on time prediction method according to any one of claims 4 to 8, characterized in that: Determining the historical travel time of the target vehicle on the target historical travel section according to the current position and the historical vehicle use information, and determining the historical travel time probability corresponding to the historical travel time, including: Determine the historical travel time and the historical travel time probability of the target vehicle on the historical driving section according to the historical vehicle use information; The historical travel time of the target vehicle at the target historical travel section and the historical travel time probability corresponding to the historical travel time are determined from the historical travel time of the historical travel section according to the current position of the target vehicle.

11. The vehicle power-on time prediction method according to claim 10, characterized in that: The historical vehicle usage time includes the power-on time. Determining the historical travel time and the historical travel time probability of the target vehicle on the historical driving section according to the historical vehicle usage information includes: Determine all historical travel times of the target vehicle on the historical driving section and the number of historical vehicle usages corresponding to all historical travel times according to the power-on time; Determine the historical number of times the target vehicle was used during the historical travel time; The historical travel time probability of the target vehicle at the historical travel time in the historical driving section is determined based on the ratio of the historical vehicle usage times at the historical travel time to the historical vehicle usage times corresponding to all the historical travel times.

12. The vehicle power-on time prediction method according to claim 11, characterized in that: Determining the historical travel time probability corresponding to the historical travel time includes: The historical travel time probabilities corresponding to the historical travel times of the target vehicle on the historical driving section are determined based on a Gaussian mixture model.

13. The vehicle power-on time prediction method according to any one of claims 3 to 12, characterized in that: Determining the historical travel probability and historical travel time of the target vehicle on the target historical travel section according to the current position and the historical vehicle use information, and determining the historical travel time probability corresponding to the historical travel time, including: When it is determined based on the current position and the historical vehicle usage information that the current position is within a preset range of one of the power-on positions of the historical vehicle usage positions, the historical travel probability and historical travel time of the target vehicle on the target historical driving section are determined based on the historical vehicle usage information, and the historical travel time probability corresponding to the historical travel time is determined.

14. The vehicle power-on time prediction method according to claim 2, characterized in that: Using the target historical driving section with the maximum predicted travel probability as the predicted user vehicle driving section includes: When it is determined that the maximum predicted travel probability is greater than a preset travel probability threshold, the target historical driving section with the maximum predicted travel probability is used as the predicted user vehicle use section.

15. A vehicle management method, characterized in that: The method comprises: Determine a predicted power-on time of a target vehicle in a parking and power-off state, wherein the predicted power-on time is obtained based on the vehicle power-on time prediction method according to any one of claims 1 to 14; The target vehicle is powered on at the predicted power-on time.

16. The vehicle management method according to claim 15, characterized in that: The method further comprises: Determine a predicted destination of the target vehicle in a parked and powered-off state, wherein the predicted destination is determined based on a predicted user vehicle use section obtained in the vehicle power-on time prediction method according to any one of claims 1 to 14; A driving route of the target vehicle is determined according to the predicted destination.

17. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores the computer program; The processor executes a computer program stored in the memory so that the electronic device implements the vehicle power-on time prediction method as described in any one of claims 1-14, and / or the vehicle management method as described in claim 15 or 16.

Citation Information

Patent Citations

  • Method for recognizing travel mode of driver based on OBD data

    CN106682703A

  • Vehicle-computer-terminal starting method, system and device

    CN108749596A

  • Electric vehicle user travel time prediction method and device

    CN114219124A

  • Automobile perception service information processing method, core network element and storage medium

    CN117750328A

  • Method and apparatus for predicting travel time of electric vehicle user

    WO2023082474A1