Methods, devices, and target vehicles for determining vehicle travel points

Abstract

This invention discloses a method, apparatus, and target vehicle for determining vehicle travel points. The method includes: acquiring vehicle data of the target vehicle, whereby the vehicle data represents the vehicle's state during its journey from a starting position to an ending position; determining a target position based on the vehicle data, whereby the target position represents the location where the target vehicle stops between the starting and ending positions; and identifying the target position based on the vehicle data corresponding to the target position, obtaining an identification result for the target position, whereby the identification result indicates whether the target position is a vehicle travel point. This invention solves the technical problem of low accuracy in determining vehicle travel points in related technologies.

Description

Technical Field

[0001] This invention relates to the field of intelligent vehicles, and more specifically, to a method, apparatus, and target vehicle for determining vehicle travel points. Background Technology

[0002] Most existing methods for determining vehicle travel points determine the travel point by identifying the position where the vehicle's speed reaches zero during travel. However, vehicles may encounter situations such as stopping at red lights, sudden braking, etc., during travel. Furthermore, some stopping positions may only be passed by the vehicle once and not again. Therefore, determining the vehicle travel point solely based on its stopping position can lead to inaccuracies.

[0003] There is currently no effective solution to the above problems. Summary of the Invention

[0004] The present invention provides a method, apparatus and target vehicle for determining vehicle travel points, so as to at least solve the technical problem of low accuracy in determining vehicle travel points in related technologies.

[0005] According to one aspect of the present invention, a method for determining vehicle travel points is provided, comprising: acquiring vehicle data of a target vehicle, the vehicle data representing the vehicle state of the target vehicle during its journey from a starting position to an ending position; determining a target position based on the vehicle data, wherein the target position represents the parking position of the target vehicle between the starting position and the ending position; identifying the target position based on the vehicle data corresponding to the target position, and obtaining an identification result of the target position, wherein the identification result indicates whether the target position is a vehicle travel point.

[0006] Optionally, based on the vehicle data corresponding to the target location, the target location is identified to obtain the identification result of the target location, including: performing feature analysis on the vehicle data corresponding to the target location to obtain multiple feature values ​​corresponding to the target location; determining the identification value corresponding to the target location based on the multiple feature values; and comparing the identification value with a preset threshold corresponding to the target vehicle to obtain the identification result.

[0007] Optionally, based on multiple feature values, the identification value corresponding to the target location is determined, including: determining the target weight of each feature value; and weighting the multiple feature values ​​and the target weight of each feature value to obtain the identification value.

[0008] Optionally, determining the target weight for each feature value includes: testing each feature value to obtain the target weight for each feature value.

[0009] Optionally, determining the target location based on vehicle data includes: acquiring the vehicle status and speed from the vehicle data; and determining the location corresponding to the vehicle data as the target location in response to the vehicle status being in a turned-off state or the vehicle status being in a working state and the speed being less than a preset speed.

[0010] Optionally, after obtaining the identification result of the target location, the method further includes: identifying the passengers in the target vehicle to obtain passenger identity information; classifying the vehicle data based on the timestamp corresponding to the vehicle data to obtain classification results, which are used to represent the category of the vehicle data; determining the target driving route based on the passenger identity information and the classification results; and pushing the target driving route to the passengers.

[0011] Optionally, the target driving route is determined based on passenger identity information and classification results, including: matching passenger identity information with vehicle travel points to obtain matching results; and determining the target driving route based on the matching results and classification results.

[0012] Optionally, when there are multiple vehicle travel points, the target driving route is determined based on the matching results and classification results, including: determining the arrival time of the vehicle travel points based on the classification results; arranging the vehicle travel points, starting positions, and ending positions based on the arrival times to obtain a directed travel graph; and determining the target driving route based on the directed travel graph.

[0013] According to another aspect of the present invention, a vehicle travel point determination device is provided, comprising: an acquisition module for acquiring vehicle data of a target vehicle, the vehicle data representing the vehicle state of the target vehicle during its journey from a starting position to an ending position; a determination module for determining a target position based on the vehicle data, wherein the target position represents the parking position of the target vehicle between the starting position and the ending position; and an identification module for identifying the target position based on the vehicle data corresponding to the target position, obtaining an identification result of the target position, wherein the identification result indicates whether the target position is a vehicle travel point.

[0014] According to another aspect of the present invention, a target vehicle is also provided, comprising: one or more processors; a storage device for storing one or more programs; and a method for determining vehicle travel points as described above, wherein when the one or more programs are executed by the one or more processors, the one or more processors perform the method for determining vehicle travel points as described above.

[0015] Through the above steps, vehicle data of the target vehicle is obtained, representing the vehicle's state during its journey from the starting position to the ending position. Based on the vehicle data, the target position is determined, representing the parking position of the target vehicle between the starting and ending positions. Based on the vehicle data corresponding to the target position, the target position is identified, yielding an identification result. This identification result indicates whether the target position is a vehicle travel point. It is noteworthy that after obtaining the target vehicle's data, the target position can be identified based on the corresponding vehicle data, thereby determining whether the target position is a vehicle travel point. This improves the accuracy of vehicle travel point identification, thus solving the technical problem of low accuracy in vehicle travel point identification in related technologies. Attached Figure Description

[0016] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0017] Figure 1 This is a flowchart of a method for determining vehicle travel points according to an embodiment of the present invention;

[0018] Figure 2 This is a flowchart of a method for determining a driving route according to an embodiment of the present invention;

[0019] Figure 3 This is a schematic diagram of a vehicle travel point determination device according to an embodiment of the present invention. Detailed Implementation

[0020] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0021] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0022] Example 1

[0023] According to an embodiment of the present invention, a method for determining vehicle travel points is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0024] Figure 1 This is a flowchart of a method for determining vehicle travel points according to an embodiment of the present invention, as shown below. Figure 1 As shown, the method includes the following steps:

[0025] Step S102: Obtain vehicle data of the target vehicle. The vehicle data is used to represent the vehicle status of the target vehicle during its journey from the starting position to the ending position.

[0026] The target vehicle mentioned above can be a vehicle driven by the user, or optionally, an autonomous vehicle.

[0027] The aforementioned vehicle data can be all the data generated by the target vehicle during its journey from the starting position to the ending position. Optionally, the vehicle data may include different positions collected by the positioning system during the journey of the target vehicle. The vehicle data may also include the driving speed and driving status of the target vehicle during the journey.

[0028] In one optional embodiment, vehicle data of the target vehicle can be obtained by collecting raw data from vehicle body cameras, radar, vehicle bus, and controllers. Optionally, after collecting the vehicle data of the target vehicle, analysis can be performed based on the vehicle data to determine the position of the target vehicle when it stops during its journey from the starting position to the ending position, and further, the frequently visited travel points of the target vehicle can be determined.

[0029] Step S104: Based on vehicle data, determine the target location, where the target location represents the parking position of the target vehicle from the starting position to the ending position.

[0030] The aforementioned target location can be the geographical location of the target vehicle when it stops during the driving process from the starting position to the ending position.

[0031] In one optional embodiment, after acquiring vehicle data, the geographical location of the target vehicle when it is parked can be determined by analyzing the vehicle data, and that location can be identified as the target location.

[0032] Optionally, a preset speed can be set, and the vehicle speed contained in the vehicle data can be compared with the preset speed. The geographical location of the target vehicle when the speed is less than or equal to the preset speed can be determined as the target location. The preset speed can be set manually. Alternatively, the vehicle's driving status can be determined from the vehicle data, and the location of the target vehicle when the vehicle is turned off can be determined as the target location. Alternatively, the door open / closed status information can be detected to determine whether the vehicle is parked, and the geographical location of the target vehicle when the door is open can be determined as the target location.

[0033] Furthermore, once the target location is determined, identification can be performed based on the target location to determine whether the target location is a frequently visited route point for the vehicle.

[0034] Step S106: Based on the vehicle data corresponding to the target location, the target location is identified to obtain the identification result of the target location, wherein the identification result is used to indicate whether the target location is a vehicle travel point.

[0035] The aforementioned vehicle travel points can be travel points where the target vehicle frequently stops. Optionally, a preset threshold can be set in advance, and the recognition result can be compared with the preset threshold. If the recognition result is greater than or equal to the preset threshold, the target location is determined as a vehicle travel point; or, if the recognition result is less than the preset threshold, the target location is determined as a vehicle travel point, thereby determining whether the target location is a vehicle travel point.

[0036] In one optional embodiment, after acquiring vehicle data and determining the corresponding target location, the target location can be identified. Specifically, when identifying the target location, preset vehicle data corresponding to vehicle travel points can be determined through multi-day testing. Then, by comparing the vehicle data corresponding to the target location with the preset vehicle data, it is determined whether the target location is a vehicle travel point. If the vehicle data corresponding to the target location matches the preset vehicle data, it indicates that the target location is a vehicle travel point; if the vehicle data corresponding to the target location does not match the preset vehicle data, it indicates that the target location is not a vehicle travel point. Optionally, feature analysis can also be performed on the vehicle data corresponding to the target location to determine whether the target location is a vehicle travel point. Optionally, feature analysis based on vehicle data can be performed to obtain multiple feature values. Simultaneously, multi-day testing of the feature values ​​can be performed to obtain weights for the multiple feature values. By weighting the feature values ​​with their corresponding weights, it is determined whether the target location is a vehicle travel point.

[0037] Through the above steps, vehicle data of the target vehicle is acquired, representing the vehicle's state during its journey from the starting position to the ending position. Based on the vehicle data, the target position is determined, representing the parking position of the target vehicle between the starting and ending positions. Based on the vehicle data corresponding to the target position, the target position is identified, yielding an identification result. This result indicates whether the target position is a vehicle travel point. It is noteworthy that after acquiring the target vehicle's data, the target position can be identified based on the corresponding vehicle data, thereby determining whether the target position is a vehicle travel point. This improves the accuracy of vehicle travel point identification and solves the technical problem of low accuracy in related technologies.

[0038] Optionally, based on the vehicle data corresponding to the target location, the target location is identified to obtain the identification result of the target location, including: performing feature analysis on the vehicle data corresponding to the target location to obtain multiple feature values ​​corresponding to the target location; determining the identification value corresponding to the target location based on the multiple feature values; and comparing the identification value with a preset threshold corresponding to the target vehicle to obtain the identification result.

[0039] The aforementioned feature values ​​can be obtained through feature analysis of vehicle data. Optionally, methods such as distribution analysis, comparative analysis, or correlation analysis can be used for feature analysis; no restrictions are placed on the feature analysis method here. Optionally, by performing feature analysis on the vehicle, information such as the vehicle's engine status, vehicle speed, number of doors opened, number of people inside the vehicle before the doors are opened, number of people inside the vehicle after the doors are opened, driver's identity, whether there is someone in the front passenger seat, the identity of the front passenger, whether there is someone in the back seat, the identity of the person in the back seat, and whether it is a commuting day can be obtained.

[0040] The aforementioned preset threshold can be set by the user. Optionally, the recognized value can be compared with the preset threshold, and the target location corresponding to the recognized value that is greater than or equal to the preset threshold can be used as the vehicle's travel point, or the target location corresponding to the recognized value that is less than the preset threshold can be used as the vehicle's travel point.

[0041] In one optional embodiment, the vehicle data corresponding to the target location can be analyzed and judged first. The vehicle data corresponding to the starting and ending states of the target vehicle, as well as the vehicle data when waiting at a red light or making an emergency stop, can be deleted. At the same time, the target location corresponding to the vehicle data can be deleted, and the remaining vehicle data and its corresponding target location can be retained. In subsequent steps, correlation operations can be performed only on the retained vehicle data and its corresponding target location.

[0042] Furthermore, feature analysis can be performed on the vehicle data corresponding to the retained target location to obtain multiple feature values ​​corresponding to the vehicle data. Optionally, the target weight corresponding to each feature value can be determined first, and the target weight can be determined as the identification value corresponding to the target location. The identification result is obtained based on the comparison result of the identification value and a preset threshold. Optionally, the target weight of each feature value can be determined first, and then the multiple feature values ​​and the target weight of each feature value can be weighted and summed to obtain the identification value. Further, after obtaining the identification value, the identification value can be compared with the preset threshold corresponding to the target vehicle to obtain the identification result, wherein the identification result is used to indicate whether the target location is a vehicle travel point.

[0043] Optionally, based on multiple feature values, the identification value corresponding to the target location is determined, including: determining the target weight of each feature value; and weighting the multiple feature values ​​and the target weight of each feature value to obtain the identification value.

[0044] The aforementioned target weights can be the weights assigned to each feature value.

[0045] In one optional embodiment, target weights for multiple feature values ​​can be determined based on the number of times parking occurs at the target location through multi-day testing. Optionally, after obtaining the target weights, the target weight corresponding to each feature value can be weighted and summed with its corresponding feature value to obtain the identification value of the target location.

[0046] Furthermore, after obtaining the identification value, different preset thresholds can be used to classify different groups of people to determine whether the target location is a vehicle travel point. Optionally, the classification can be based on the user's driving habits. For example, a personal tag can be set for the user, where the user can be a driver in the car. When the user's personal user tag is "commuter," it indicates that the user's driving is relatively regular. It can be defined that when the preset threshold is greater than or equal to reference value 1, the target location can be considered as the user's frequently visited travel point. When the user is not a commuter, it can be considered that the user's travel regularity is not high. To exclude the user's accidental factors, the target location can be considered as the user's frequently visited travel point only when the preset threshold is greater than or equal to reference value 2. The preset threshold and reference values ​​1 and 2 mentioned above can be set by the user, and this application does not limit them. Optionally, the reference value 2 can be greater than reference value 1.

[0047] Optionally, determining the target weight for each feature value includes: testing each feature value to obtain the target weight for each feature value.

[0048] In one optional embodiment, multiple-person, multi-day tests can be performed on each feature value to obtain the target weight of each feature value. Optionally, the target weight of each feature value can be determined by obtaining multi-day driving information of the vehicle and passenger information from in-vehicle cameras or sensors, or by using driving records. For example, after multiple-person, multi-day tests, if the target vehicle is detected to have passed through the target location multiple times over several consecutive days, the target weight of the feature value corresponding to that target location can be considered high. Optionally, the target weight can be represented by a high, medium, or low level, or by a specific numerical value; there is no limitation here.

[0049] Optionally, determining the target location based on vehicle data includes: acquiring the vehicle status and speed from the vehicle data; and determining the location corresponding to the vehicle data as the target location in response to the vehicle status being in a turned-off state or the vehicle status being in a working state and the speed being less than a preset speed.

[0050] The preset speed can be set by the user.

[0051] In one optional embodiment, after acquiring vehicle data, a preset speed can be set first, and then the vehicle speed contained in the vehicle data can be compared with the preset speed. Optionally, the location of the target vehicle when the vehicle speed is less than or equal to the preset speed can be determined as the target location. Optionally, the vehicle driving state contained in the vehicle data can be determined, and the location of the target vehicle when the vehicle is in a turned-off state can be determined as the target location.

[0052] Optionally, after obtaining the identification result of the target location, the method further includes: identifying the passengers in the target vehicle to obtain passenger identity information; classifying the vehicle data based on the timestamp corresponding to the vehicle data to obtain classification results, which are used to represent the category of the vehicle data; determining the target driving route based on the passenger identity information and the classification results; and pushing the target driving route to the passengers.

[0053] In one optional embodiment, after obtaining the identification result of the target location and determining that the target location is a frequently visited travel point of the user, the identity of the passengers in the vehicle can be identified by the in-vehicle camera, thereby obtaining the passengers' identity information.

[0054] Furthermore, vehicle data can be categorized based on the time points at which it occurs. For example, if a target vehicle passes through a certain travel point between 8:00 and 10:00, the corresponding vehicle data can be identified as {x1, x2, ... x10}. If the target vehicle passes through the same travel point again between 16:00 and 18:00, the corresponding vehicle data can also be identified as {x1, x2, ... x10}. Optionally, the categorization results can determine whether the vehicle passed through the travel point during rush hour, commuting hours, or other time periods, thus allowing for the recommendation of correct driving routes to users at different times of day.

[0055] Optionally, the target driving route is determined based on passenger identity information and classification results, including: matching passenger identity information with vehicle travel points to obtain matching results; and determining the target driving route based on the matching results and classification results.

[0056] In one optional embodiment, after obtaining passenger information, passengers can be matched with vehicle travel points to obtain matching results. For example, if the passengers in the car are passenger A and passenger B, and the classification result shows that the travel point is reached between 8:00 AM and 10:00 AM, this time period can be considered as commuting time. Further, the commuting route profile can be determined as: home location → frequently visited travel point 1 (school) → company location 1, where A can represent an adult driver and B can represent a child. If the users in the car are users A, B, and C, and the classification result shows that the travel point is reached between 8:00 AM and 10:00 AM, the commuting route can be: home location → frequently visited travel point 1 (school) → frequently visited travel point 2 (company 2) → company location 1, where C can be an adult sitting in the front passenger seat. Optionally, the matching results can be used to identify the passengers who get off at the destination. Furthermore, the matching results can be combined with the classification results to determine the drop-off times of different passengers at different vehicle destinations. Optionally, more accurate travel routes can be recommended to users based on the matching and classification results.

[0057] Optionally, when there are multiple vehicle travel points, the target driving route is determined based on the matching results and classification results, including: determining the arrival time of the vehicle travel points based on the classification results; arranging the vehicle travel points, starting positions, and ending positions based on the arrival times to obtain a directed travel graph; and determining the target driving route based on the directed travel graph.

[0058] In one optional embodiment, the arrival time of a vehicle's journey point can be determined based on the classification results of the vehicle data. Based on this, a directed graph of the journey can be determined according to the vehicle's starting and ending positions and the journey points. For example, if a vehicle departs from home location A at 8:30, arrives at a transit point B at 8:45 where someone gets off, arrives at a roadside point C at 9:05 where someone gets off, and arrives at its destination D at 9:30, then the directed graph of this journey can be A→B→C→D.

[0059] It is important to note that a node in a directed graph can only be routed to the location of the vehicle's journey point when someone gets off the vehicle. If a node simply passes through a location without anyone getting off, that location is not considered a journey point for picking up or dropping off a passenger.

[0060] At the same time, when there are multiple passengers in the vehicle, the frequency of recommended routes can be compared to determine the most suitable route. For example, during the time period of 8:30-10:00, when there is a driver, a front passenger, and a child in the vehicle, routes such as A→B→C→D and A→C→B→D may occur. In this case, all routes can be compared pairwise to obtain the final ranking.

[0061] For example, when there are a driver, a child, and a front passenger on a trip, there are three possible routes. If the ratio of the frequency of Route 1 to the frequency of Route 2 is greater than 1, then Route 1 is considered to be more likely to occur. If the frequency of Route 1 is compared with the frequency of Route 3, and the ratio is less than 1, then Route 3 is considered to be the optimal route sort. That is, Route 3 is a commonly used directed graph topological sort when there is a driver, a front passenger, and a child on the bus around 8:30 am on a weekday.

[0062] Figure 2 This is a flowchart illustrating a method for determining a driving route according to an embodiment of the present invention, as follows: Figure 2 As shown, the operation process can be divided into the following steps:

[0063] S202: Specify the start and end points of the user's trip;

[0064] S204: Based on vehicle speed, find the points in the driving trajectory where the vehicle speed is 0 or the vehicle is turned off;

[0065] S206: Identify whether a person's travel point is a pick-up or drop-off point based on feature analysis;

[0066] S208: When the point where the vehicle speed is 0 or the vehicle is turned off is the trip point for picking up or dropping off the passenger, match the trip point of the passenger with the passenger in the vehicle;

[0067] S210: Sort the travel points based on the directed graph;

[0068] S212: Match the corresponding recommended route based on the sorting results.

[0069] In one alternative embodiment, existing commuter route recommendations are mostly point-to-point recommendations based on home and workplace locations. These locations are typically set by the user or obtained through clustering algorithms based on vehicle driving information. However, this often overlooks situations where multiple people share a ride, such as picking up family members from get off work / school or colleagues / friends. Therefore, recommending point-to-point routes solely based on home and workplace locations can lead to inaccurate recommendations.

[0070] In the above embodiments of this application, multi-source information fusion can be used, where the multi-source information may include information identified by the camera and vehicle condition information, which can effectively identify the pick-up and drop-off points of the user's trip in the corresponding time period and add the trip points to the feature database. When the user gets on the vehicle, the corresponding route is recommended based on the identification results of the passengers in the vehicle by the camera, thereby improving the accuracy of route recommendation.

[0071] Example 2

[0072] According to embodiments of the present invention, a vehicle travel point determination device is also provided, which can execute the vehicle simulation processing method described in the above embodiments. Figure 3 This is a schematic diagram of a vehicle travel point determination device according to an embodiment of the present invention, such as... Figure 3 As shown, the device includes the following components:

[0073] The acquisition module 302 acquires vehicle data of the target vehicle, which represents the vehicle status of the target vehicle during its journey from the starting position to the ending position.

[0074] The determination module 304 determines the target position based on vehicle data, wherein the target position is used to represent the parking position of the target vehicle from the starting position to the ending position.

[0075] The identification module 306 identifies the target location based on the vehicle data corresponding to the target location, and obtains the identification result of the target location. The identification result is used to indicate whether the target location is a vehicle travel point.

[0076] Optionally, the recognition module 306 includes: an analysis unit for performing feature analysis on vehicle data corresponding to the target location to obtain multiple feature values ​​corresponding to the target location; a first determination unit for determining the recognition value corresponding to the target location based on the multiple feature values; and a comparison unit for comparing the recognition value with a preset threshold corresponding to the target vehicle to obtain a recognition result.

[0077] Optionally, the first determining unit includes: a first determining subunit for determining the target weight of each feature value; and a weighting subunit for weighting and summing multiple feature values ​​and the target weight of each feature value to obtain an identification value.

[0078] Optionally, the first determining subunit is also used to test each feature value to obtain the target weight of each feature value.

[0079] Optionally, the determining module 304 includes: an acquisition unit for acquiring the vehicle status and speed from the vehicle data; and a second determining unit for determining the position corresponding to the vehicle data as the target position in response to the vehicle status meeting the off state or the vehicle status meeting the working state and the speed being less than a preset speed.

[0080] Optionally, the device further includes: an identification module for identifying passengers in the target vehicle to obtain passenger identity information; a classification module for classifying vehicle data based on the timestamp corresponding to the vehicle data to obtain a classification result, the classification result being used to represent the category of the vehicle data; a determination module for determining the target driving route based on the passenger identity information and the classification result; and a recommendation module for pushing the target driving route to the passenger.

[0081] Optionally, the determining module includes: a matching unit, used to match passenger identity information with vehicle travel points to obtain a matching result; and a third determining unit, used to determine the target driving route based on the matching result and the classification result.

[0082] Optionally, the third determining unit includes: a second determining subunit, used to determine the arrival time of the vehicle's travel points based on the classification results; an arranging subunit, used to arrange the vehicle's travel points, starting position, and ending position based on the arrival time to obtain a directed travel graph; and a third determining subunit, used to determine the target travel route based on the directed travel graph.

[0083] Example 3

[0084] According to another aspect of the present invention, a target vehicle is also provided, characterized in that it includes: one or more processors; a storage device for storing one or more programs; and when the one or more programs are executed by the one or more processors, causing the one or more processors to perform the vehicle trip point determination method described above.

[0085] Example 4

[0086] According to an embodiment of the present invention, a non-volatile storage medium is also provided, the non-volatile storage medium including a stored program, wherein, when the program is running, it controls the processor of the device to execute any of the above-described methods for determining vehicle travel points.

[0087] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0088] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0089] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some interfaces; indirect couplings or communication connections between units or modules may be electrical or other forms.

[0090] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0091] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0092] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0093] The above are merely preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for determining vehicle travel points, characterized in that, include: Acquire vehicle data of the target vehicle, wherein the vehicle data is used to represent the vehicle status of the target vehicle during its journey from the starting position to the ending position; Based on the vehicle data, a target location is determined, wherein the target location represents the parking position of the target vehicle between the starting position and the ending position; Based on the vehicle data corresponding to the target location, the target location is identified to obtain the identification result of the target location, including: Feature analysis is performed on the vehicle data corresponding to the target location to obtain multiple feature values ​​corresponding to the target location. The multiple feature values ​​include: vehicle engine off status, vehicle speed status, number of doors opened, number of people in the vehicle before the doors are opened, number of people in the vehicle after the doors are opened, driver's identity, whether there is someone in the front passenger seat, front passenger's identity, whether there is someone in the back seat, back seat identity, and whether it is a commuting day. Based on the plurality of feature values, a recognition value corresponding to the target location is determined, wherein determining the recognition value corresponding to the target location based on the plurality of feature values ​​includes: determining a target weight for each feature value, and determining the target weight as the recognition value corresponding to the target location; or, determining a target weight for each feature value, and performing a weighted sum of the plurality of feature values ​​and the target weight of each feature value to obtain the recognition value; The identification value is compared with a preset threshold corresponding to the target vehicle to obtain the identification result, wherein the identification result is used to indicate whether the target location is a vehicle travel point, and the vehicle travel point is used to indicate the travel point where the target vehicle frequently stops; The method further includes: Based on the starting position, the ending position, and the vehicle travel points, a directed travel graph is determined, wherein the nodes in the directed travel graph are determined based on passenger disembarkation data.

2. The method according to claim 1, characterized in that, Determine the target weight for each feature value, including: Each feature value is tested to obtain the target weight of each feature value.

3. The method according to claim 1, characterized in that, Based on the vehicle data, the target location is determined, including: Obtain the vehicle status and speed from the vehicle data; In response to the vehicle status being in a shutdown state, or the vehicle status being in a working state and the vehicle speed being less than a preset speed, the location corresponding to the vehicle data is determined as the target location.

4. The method according to claim 1, characterized in that, After obtaining the identification result of the target location, the method further includes: The passengers inside the target vehicle are identified to obtain passenger identity information; Based on the timestamps corresponding to the vehicle data, the vehicle data is classified to obtain classification results; Based on the passenger identity information and the classification results, the target driving route is determined; The target travel route is pushed to the passenger.

5. The method according to claim 4, characterized in that, Based on the passenger identity information and the classification results, the target driving route is determined, including: The passenger identity information is matched with the vehicle's travel points to obtain the matching result; Based on the matching results and the classification results, the target driving route is determined.

6. The method according to claim 5, characterized in that, When there are multiple vehicle travel points, the target driving route is determined based on the matching result and the classification result, including: Based on the classification results, the arrival time of the vehicle's travel point is determined; The travel points, starting position, and ending position of the vehicle are arranged based on the arrival time to obtain the directed travel graph; Based on the directed graph of the journey, the target travel route is determined.

7. A device for determining the travel point of a vehicle, characterized in that, include: The acquisition module is used to acquire vehicle data of the target vehicle, which represents the vehicle status of the target vehicle during its journey from the starting position to the ending position. The determining module is used to determine a target location based on the vehicle data, wherein the target location represents the parking position of the target vehicle between the starting position and the ending position; The identification module is used to perform feature analysis on the vehicle data corresponding to the target location to obtain multiple feature values ​​corresponding to the target location. These multiple feature values ​​include: vehicle engine off status, vehicle speed, number of open doors, number of people inside the vehicle before the door is opened, number of people inside the vehicle after the door is opened, driver's identity, whether there is someone in the front passenger seat, the identity of the front passenger, whether there is someone in the back seat, the identity of the back seat occupants, and whether it is a commuting day. Based on these multiple feature values, the module determines an identification value corresponding to the target location. This determination includes: determining a target weight for each feature value and setting the target weight as the identification value corresponding to the target location; or, determining a target weight for each feature value and performing a weighted sum of the multiple feature values ​​and their target weights to obtain the identification value. The module also compares the identification value with a preset threshold corresponding to the target vehicle to obtain an identification result. The identification result indicates whether the target location is a vehicle travel point, where the vehicle travel point represents a travel point where the target vehicle frequently stops. The device is also used to determine a directed graph of the journey based on the starting position, the ending position, and the vehicle travel points, wherein the nodes in the directed graph of the journey are determined based on passenger disembarkation data.

8. A target vehicle, characterized in that, include: One or more processors; Storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors perform the vehicle trip point determination method according to any one of claims 1 to 6.

Images