A method, device, storage medium and terminal for predicting vehicle destination

Abstract

The present invention discloses a method, device, storage medium and terminal for predicting a vehicle destination. The method comprises: when a prediction request for a target vehicle to be predicted is received, a dictionary tree corresponding to the enterprise to which the target vehicle belongs is loaded; according to the current position point of the target vehicle, the electronic fence at the entrance and exit of the current administrative area passed at the moment closest to the current moment is determined from the dictionary tree; the destination probability value corresponding to the electronic fence at the entrance and exit of the current administrative area is queried from a memory database; when the current destination probability value is greater than a preset probability threshold, the destination corresponding to the current destination probability value is determined as the final destination of the target vehicle. Since the present application determines the dynamically changing destination probability value corresponding to the electronic fence passed through from the memory database by touching different electronic fences during the dynamic driving of the vehicle, and judges the credibility of the final destination according to the dynamically changing destination probability value, the accuracy of the destination prediction is improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent transportation technology, and in particular to a method, device, storage medium and terminal for predicting a vehicle destination. Background Art

[0002] With the development of intelligent transportation technology, vehicle destination prediction has very important practical significance. For example, by predicting the destination of a truck, the information of logistics sites along the way can be transmitted to the truck manager, and the cargo information in the logistics sites along the way can also be transmitted to the truck manager, thereby facilitating the truck manager to transport and manage the cargo.

[0003] At present, the method for predicting the vehicle destination, such as patent CN110832284A, retrieves the historical destination location corresponding to the departure location and trigger time, and then uses the pre-stored destination matching algorithm to determine the selection probability of one or more historical destination locations, and finally determines the recommended destination location based on the selection probability, which is the same as one or more historical destination locations. In the actual scenario of the vehicle driving process, as the path information is continuously supplemented during the vehicle's approach to the real destination, this probability will change, and then the prior art calculates a constant probability based on the initial static data, thereby reducing the accuracy of the destination prediction. Summary of the invention

[0004] The embodiments of the present application provide a method, device, storage medium and terminal for predicting a vehicle destination. In order to have a basic understanding of some aspects of the disclosed embodiments, a simple summary is given below. This summary is not a general review, nor is it intended to identify key / important components or describe the scope of protection of these embodiments. Its only purpose is to present some concepts in a simple form as a preface to the detailed description that follows.

[0005] In a first aspect, an embodiment of the present application provides a method for predicting a vehicle destination, the method comprising:

[0006] When a prediction request for a target vehicle to be predicted is received, a dictionary tree corresponding to the enterprise to which the target vehicle belongs is loaded;

[0007] According to the current position point of the target vehicle, the electronic fence at the entrance and exit of the current administrative area passed by the vehicle at the closest time to the current time is determined from the dictionary tree;

[0008] Query the destination probability value corresponding to the electronic fence at the entrance and exit of the current administrative area from the memory database;

[0009] When the current destination probability value is greater than a preset probability threshold, the destination corresponding to the current destination probability value is determined as the final destination of the target vehicle.

[0010] Optionally, before receiving a prediction request for a target vehicle to be predicted, the method further includes:

[0011] Get the real-time driving trajectory points of each vehicle;

[0012] Load the route relationship matrix corresponding to the enterprise to which each vehicle belongs from the pre-generated route relationship matrix library;

[0013] When the driving trajectory point enters the pre-built electronic fence at the entrance and exit of the administrative area, the frequency corresponding to the electronic fence is extracted from the route relationship matrix;

[0014] The probability value of each vehicle's current destination is calculated based on the frequency, and the probability value of each vehicle's current destination is saved in the memory database.

[0015] Optionally, the method further includes:

[0016] When the destination probability value is less than a preset probability threshold, multiple downstream entrance and exit electronic fences of the current administrative district entrance and exit electronic fence are obtained;

[0017] Constructing line segments between the electronic fence at the entrance and exit of the current administrative district and the electronic fences at the entrance and exit of multiple downstream administrative districts to obtain multiple line segments;

[0018] Construct the target line segment between the location point of the target vehicle and the electronic fence at the entrance and exit of the current administrative area;

[0019] calculating an angle between a target line segment and each of the plurality of line segments;

[0020] determining a length of each of the plurality of line segments based on a cosine of the angle;

[0021] The final destination of the target vehicle is calculated based on the similarity corresponding to the line segment with the smallest length.

[0022] Optionally, generate a route relationship matrix library by following the steps below, including:

[0023] Create an enterprise electronic fence for each business based on the vehicle's parking point;

[0024] Obtain the driving trajectory data of freight vehicles in each enterprise, and calculate the set of trajectory points entering and exiting the administrative area based on the driving trajectory data;

[0025] Cluster the set of trajectory points entering and exiting the administrative area to generate multiple electronic fences at the entrance and exit of each enterprise;

[0026] Construct a first dictionary tree for each enterprise according to the enterprise electronic fence of each enterprise and the electronic fences of multiple administrative district entrances and exits of each enterprise;

[0027] A route relationship matrix library is generated according to the first dictionary tree of each enterprise.

[0028] Optionally, a set of trajectory points entering and exiting the administrative area is calculated based on the driving trajectory data, including:

[0029] Acquire multiple groups of first trajectory points before and after the administrative district is changed from the driving trajectory data;

[0030] Calculating the distance between each group of trajectory points in the plurality of groups of first trajectory points to generate a plurality of distance values;

[0031] Identifying distance values ​​greater than a preset threshold value among a plurality of distance values ​​one by one;

[0032] One by one, a group of first trajectory points corresponding to distance values ​​greater than a preset threshold are removed from the multiple groups of first trajectory points to generate multiple groups of second trajectory points;

[0033] The center point between each group of second trajectory points in the multiple groups of second trajectory points is calculated to generate a set of trajectory points entering and leaving the administrative area.

[0034] Optionally, cluster the historical stop points to generate multiple administrative district entrance and exit electronic fences for each enterprise, including:

[0035] Clustering algorithm is used to cluster the center point set of the trajectory point group to generate a cluster area;

[0036] Calculate the center point of the cluster area, mark the center point with a unique ID, and then get the entrance and exit of the administrative area;

[0037] With the entrance and exit of each administrative district as the center and a circle with a preset radius, an electronic fence is generated for the entrance and exit of each administrative district;

[0038] The electronic fences at the entrances and exits of each administrative district are combined to generate multiple electronic fences at the entrances and exits of each enterprise.

[0039] Optionally, a route relationship matrix library is generated based on the first dictionary tree of each enterprise, including:

[0040] Using a depth-first search algorithm to label the attribute parameters of each node in the first dictionary tree of each enterprise, a second dictionary tree of each enterprise is generated;

[0041] Deconstruct the second dictionary tree of each enterprise to generate a route relationship matrix from the entrance and exit of each enterprise to each end point;

[0042] The route relationship matrix from each enterprise's entrance and exit to each end point is saved to generate a route relationship matrix library.

[0043] In a second aspect, an embodiment of the present application provides a device for predicting a vehicle destination, the device comprising:

[0044] A dictionary tree loading module is used to load the dictionary tree corresponding to the enterprise to which the target vehicle belongs when receiving a prediction request for the target vehicle to be predicted;

[0045] The electronic fence at the entrance and exit of the current administrative area is used to determine the electronic fence at the entrance and exit of the current administrative area passed by the target vehicle at the closest time to the current time from the dictionary tree according to the current position point of the target vehicle;

[0046] The destination probability value query module is used to query the destination probability value corresponding to the electronic fence at the entrance and exit of the current administrative area from the memory database;

[0047] The destination determination module is used to determine the destination corresponding to the current destination probability value as the final destination of the target vehicle when the current destination probability value is greater than a preset probability threshold.

[0048] In a third aspect, an embodiment of the present application provides a computer storage medium, which stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the above-mentioned method steps.

[0049] In a fourth aspect, an embodiment of the present application provides a terminal, which may include: a processor and a memory; wherein the memory stores a computer program, and the computer program is suitable for being loaded by the processor and executing the above-mentioned method steps.

[0050] The technical solution provided by the embodiments of the present application may have the following beneficial effects:

[0051] In an embodiment of the present application, the device for predicting the destination of a vehicle first loads the dictionary tree corresponding to the enterprise to which the target vehicle belongs when receiving a prediction request for the target vehicle to be predicted, and then determines from the dictionary tree the electronic fence at the entrance and exit of the current administrative district that is passed at the moment closest to the current moment according to the current position of the target vehicle, and then queries the destination probability value corresponding to the electronic fence at the entrance and exit of the current administrative district from the memory database, and finally, when the current destination probability value is greater than the preset probability threshold, determines the destination corresponding to the current destination probability value as the final destination of the target vehicle. Since the present application determines the dynamically changing destination probability value corresponding to the electronic fence passed by from the memory database by touching different electronic fences during the dynamic driving of the vehicle, and judges the credibility of the final destination based on the dynamically changing destination probability value, the accuracy of the destination prediction is improved.

[0052] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0054] Figure 1 It is a flowchart of a method for predicting a vehicle destination provided by an embodiment of the present application;

[0055] Figure 2 This is a schematic diagram of a constructed enterprise dictionary tree provided in an embodiment of the present application;

[0056] Figure 3 It is a schematic diagram of a driving route of enterprise vehicles provided in an embodiment of the present application;

[0057] Figure 4 It is a schematic diagram of a road section construction provided in an embodiment of the present application;

[0058] Figure 5 is a schematic block diagram of a process for predicting a vehicle destination provided by an embodiment of the present application;

[0059] Figure 6 It is a structural schematic diagram of a device for constructing a highway exit location provided in an embodiment of the present application;

[0060] Figure 7 It is a structural diagram of a terminal provided in an embodiment of the present application. DETAILED DESCRIPTION

[0061] The following description and the drawings sufficiently illustrate specific embodiments of the invention to enable those skilled in the art to practice them.

[0062] It should be clear that the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0063] When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Instead, they are only examples of devices and methods consistent with some aspects of the present invention as detailed in the attached claims.

[0064] In the description of the present invention, it should be understood that the terms "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances. In addition, in the description of the present invention, unless otherwise specified, "plurality" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the previously associated objects are in an "or" relationship.

[0065] The present application provides a method, device, storage medium and terminal for predicting a vehicle destination to solve the problems existing in the above-mentioned related technical problems. In the technical solution provided by the present application, the present application determines the dynamically changing destination probability value corresponding to the passed electronic fence from the memory database by touching different electronic fences during the dynamic driving of the vehicle, and judges the credibility of the final destination according to the dynamically changing destination probability value, thereby improving the accuracy of the destination prediction, and an exemplary embodiment is used for detailed description below.

[0066] The following will be combined with the attached Figure 1 -Attached Figure 5 , a method for predicting a vehicle destination provided by an embodiment of the present application is introduced in detail. The method can be implemented by a computer program and can be run on a device for predicting a vehicle destination based on a von Neumann system. The computer program can be integrated into an application or run as an independent tool application.

[0067] See also Figure 1 , which is a flow chart of a method for predicting a vehicle destination according to an embodiment of the present application. Figure 1 As shown, the method of the embodiment of the present application may include the following steps:

[0068] S101, when a prediction request for a target vehicle to be predicted is received, a dictionary tree corresponding to the enterprise to which the target vehicle belongs is loaded;

[0069] The prediction request is a prediction request submitted by a user, and the dictionary tree can be called a word search tree or a Trie tree, which is a tree structure and a variant of a hash tree.

[0070] In an embodiment of the present application, when generating a dictionary tree, first, an enterprise electronic fence is created for each enterprise based on the vehicle's stop point, then the driving trajectory data of the freight vehicles in each enterprise is obtained, and the set of entry and exit trajectory points of the administrative district is calculated based on the driving trajectory data, and then the set of entry and exit trajectory points of the administrative district is clustered to generate multiple administrative district entrance and exit electronic fences for each enterprise, and finally, the first dictionary tree of each enterprise is constructed based on the enterprise electronic fence of each enterprise and the multiple administrative district entrance and exit electronic fences of each enterprise.

[0071] Furthermore, when calculating the set of trajectory points for entering and exiting the administrative district based on the driving trajectory data, firstly, multiple groups of first trajectory points before and after the administrative district is changed are obtained from the driving trajectory data, and then the distance between each group of trajectory points in the multiple groups of first trajectory points is calculated to generate multiple distance values, and then the distance values ​​greater than a preset threshold value in the multiple distance values ​​are identified one by one, and then a group of first trajectory points corresponding to the distance values ​​greater than the preset threshold value are removed one by one from the multiple groups of first trajectory points to generate multiple groups of second trajectory points, and finally the center point between each group of second trajectory points in the multiple groups of second trajectory points is calculated to generate a set of trajectory points for entering and exiting the administrative district.

[0072] Furthermore, when clustering the historical stop point set to generate multiple administrative district entrance and exit electronic fences for each enterprise, the clustering algorithm is first used to cluster the center point set of the trajectory point group to generate a clustering area, and then the center point of the clustering area is calculated, and the center point is marked with a unique ID to obtain the administrative district entrance and exit. Secondly, with each administrative district entrance and exit as the center and a circle drawn according to a preset radius, an electronic fence of each administrative district entrance and exit is generated. Finally, the electronic fences of each administrative district entrance and exit are combined together to generate multiple administrative district entrance and exit electronic fences for each enterprise.

[0073] Specifically, when creating the electronic fence of each enterprise based on the vehicle's stop points, first calculate all the vehicle's historical stop points, cluster all the vehicle's historical stop points to find the vehicle's gathering area, and use this as a clue for manual labeling to establish the enterprise's electronic fence.

[0074] Specifically, when constructing electronic fences at the entrances and exits of multiple administrative districts, the driving trajectory data of freight vehicles in each enterprise is obtained, and then the trajectory point groups before and after the administrative district changes are extracted, the abnormal point groups with a distance between two points higher than the threshold m are removed, and the center points of the remaining point groups are calculated respectively. Secondly, the center points of the point groups are clustered to generate clusters, and the center points of the clusters are calculated. At the same time, a unique ID is generated to represent the entrances and exits of the administrative district. Finally, a circle is drawn with the center point of the cluster as the center and the threshold r as the radius as the electronic fence of the entrance and exit.

[0075] Specifically, when constructing the first dictionary tree of each enterprise based on the enterprise electronic fence and the multiple administrative district entrance and exit electronic fences of each enterprise, firstly obtain the driving trajectory data of all vehicles of the enterprise, and then combine the electronic fence of the enterprise and the multiple administrative district entrance and exit electronic fences of the enterprise according to the sequence of trajectory data and running time to generate the first dictionary tree, for example Figure 2 shown.

[0076] Specifically, when representing the driving trajectory data of all the vehicles of the enterprise, the route is divided into three stages: the starting section, the middle section, and the ending section. The starting section refers to the line from the center point of the electronic fence of the shipping enterprise to the entrance and exit of the shipping administrative area; the ending section refers to the line from the entrance and exit of the unloading administrative area to the center point of the electronic fence of the unloading enterprise; and the middle section is a broken line segment composed of a series of lines passing through the entrances and exits of the administrative area, for example Figure 3 shown.

[0077] In one possible implementation, in an application scenario, when a user actively requests, a prediction request is generated and sent to the server. When the server receives a prediction request for a target vehicle to be predicted, it first needs to load the dictionary tree corresponding to the company to which the target vehicle belongs from the memory.

[0078] S102, determining the electronic fence of the entrance and exit of the current administrative area passed by the vehicle at the closest time to the current time from the dictionary tree according to the current position point of the target vehicle;

[0079] In an embodiment of the present application, the current location point of the target vehicle is first obtained, and then the electronic fence at the entrance and exit of the current administrative area passed at the time closest to the current time is determined from the dictionary tree.

[0080] S103, querying the destination probability value corresponding to the electronic fence at the entrance and exit of the current administrative area from the memory database;

[0081] In an embodiment of the present application, the data update operation in the memory database is as follows: first, the real-time driving trajectory points of each vehicle are obtained, and then the route relationship matrix corresponding to the enterprise to which each vehicle belongs is loaded from a pre-generated route relationship matrix library, and then when the driving trajectory points enter the pre-built electronic fence at the entrance and exit of the administrative area, the frequency corresponding to the electronic fence is extracted from the route relationship matrix, and then the current destination probability value of each vehicle is calculated based on the frequency, and the current destination probability value of each vehicle is saved to the memory database.

[0082] It should be noted that the probability value in the memory database is dynamically updated as the vehicle trajectory point changes dynamically and touches different electronic fences. Publish and subscribe in the message queue, and maintain the destination prediction status of each vehicle in the memory database. When the vehicle touches the entrance and exit of the administrative area, the probability calculation of the current entrance and exit to each possible destination is triggered, and the result is updated to the destination prediction result of the vehicle.

[0083] Furthermore, the route relationship matrix library is generated based on the first dictionary tree, and the specific steps include: first, using a depth-first search algorithm to mark the attribute parameters of each node in the first dictionary tree of each enterprise to generate a second dictionary tree for each enterprise, and then deconstructing the second dictionary tree of each enterprise to generate a route relationship matrix from the entrance and exit of each enterprise to each terminal, and finally saving the route relationship matrix from the entrance and exit of each enterprise to each terminal to generate a route relationship matrix library.

[0084] Specifically, the trie tree is deconstructed and indexed according to the two dimensions of administrative district and entrance and exit. Each vehicle maintains a static trie tree of frequently-traveled routes and administrative district and entrance and exit indexes, and the frequency distribution of the same administrative district and entrance and exit in the tree structure to each possible terminal administrative district is merged.

[0085] Decompose each node of the trie tree and generate a relationship matrix from the entrance and exit to each possible end point.

[0086]

[0087] Among them, m is the number of entrances and exits that the target enterprise has passed through to all its downstream enterprises in the past, n is the number of destination enterprises that the target enterprise has reached in the past, and r ij is the relationship between entrance i and end point j, which means the frequency of reaching end point j via i.

[0088] Furthermore, when calculating the probability value of each vehicle's current destination based on the frequency, the probability calculation method for the destination j that can be reached via the entrance and exit i is:

[0089]

[0090] Among them, p ij is the probability of going to the destination j via entrance i, r ij is the frequency of going from entrance i to destination j, and n is the number of possible destinations. The information stored in each relationship includes: the list of previous and subsequent entrances and exits, the list of previous and subsequent administrative districts, the list of destination enterprise information, and the centroid of candidate destination enterprises.

[0091] S104: When the current destination probability value is greater than a preset probability threshold, the destination corresponding to the current destination probability value is determined as the final destination of the target vehicle.

[0092] In a possible implementation, when the current destination probability value is greater than a preset probability threshold, the destination corresponding to the current destination probability value is determined as the final destination of the target vehicle.

[0093] In another possible implementation, when the destination probability value is less than a preset probability threshold, multiple administrative district entrance and exit electronic fences downstream of the current administrative district entrance and exit electronic fence are obtained, and then a line segment between the current administrative district entrance and exit electronic fence and the multiple downstream administrative district entrance and exit electronic fences is constructed to obtain multiple line segments, and then a target line segment between the location point of the target vehicle and the current administrative district entrance and exit electronic fence is constructed, and then the angle between the target line segment and each of the multiple line segments is calculated, and then the length of each of the multiple line segments is determined based on the cosine value of the angle, and finally the final destination of the target vehicle is calculated based on the similarity corresponding to the line segment with the smallest length.

[0094] Specifically, if the predicted probability does not meet a given threshold, the line similarity calculation is triggered, that is, the similarity between the line AB connecting the latest touched entrance and exit and each subsequent entrance and exit and the similarity between the latest touched entrance and exit and the current position AC, such as Figure 4 As shown, c is the most recently touched entrance and exit, f1 and f2 are the two subsequent entrances and exits of the most recently touched entrance and exit, p is the current position, and the cosine values ​​of angles a and b can be used to measure the distance between line segment cp and cf1 and cf2. The smaller the distance, the greater the similarity. The similarity is weighted to the frequency distribution of the administrative district of the entrance and exit terminal corresponding to the similarity, and the probability of each possible terminal administrative district is calculated and output.

[0095] Since the description of the route in actual medium and long-distance freight scenarios is not precisely enterprise X-enterprise Y or administrative region A-administrative region B, but a wider area such as the periphery of administrative region A-periphery of administrative region B, North China-South China, therefore, in order to adapt to actual medium and long-distance freight scenarios, the present invention also calculates the centroid of each possible downstream destination that may be reached at present, as well as the degree of discreteness of each possible destination relative to the centroid.

[0096] For example Figure 5 As shown, Figure 5 This is a schematic diagram of a process for predicting a vehicle destination provided by the present application. First, the enterprise electronic fence and the administrative district entrance and exit electronic fence are constructed for each enterprise, and the enterprise electronic fence and the administrative district entrance and exit electronic fence are combined to obtain a dictionary tree according to the line representation of the vehicle driving trajectory of the enterprise, and then the real-time status of the vehicle is tracked and the destination is predicted.

[0097] In an embodiment of the present application, the device for predicting the destination of a vehicle first loads the dictionary tree corresponding to the enterprise to which the target vehicle belongs when receiving a prediction request for the target vehicle to be predicted, and then determines from the dictionary tree the electronic fence at the entrance and exit of the current administrative district that is passed at the moment closest to the current moment according to the current position of the target vehicle, and then queries the destination probability value corresponding to the electronic fence at the entrance and exit of the current administrative district from the memory database, and finally, when the current destination probability value is greater than the preset probability threshold, determines the destination corresponding to the current destination probability value as the final destination of the target vehicle. Since the present application determines the dynamically changing destination probability value corresponding to the electronic fence passed by from the memory database by touching different electronic fences during the dynamic driving of the vehicle, and judges the credibility of the final destination based on the dynamically changing destination probability value, the accuracy of the destination prediction is improved.

[0098] The following are embodiments of the device of the present invention, which can be used to implement the method embodiments of the present invention. For details not disclosed in the device embodiments of the present invention, please refer to the method embodiments of the present invention.

[0099] See also Figure 6 , which shows a schematic diagram of the structure of a device for predicting a vehicle destination provided by an exemplary embodiment of the present invention. The device for predicting a vehicle destination can be implemented as all or part of a terminal through software, hardware, or a combination of both. The device 1 includes a data preprocessing module 10, a vehicle position determination module 20, a parking violation identification module 30, a reversing behavior identification module 40, a warning information generation module 50, and a vehicle warning module 60.

[0100] The dictionary tree loading module 10 is used to load the dictionary tree corresponding to the enterprise to which the target vehicle belongs when receiving a prediction request for the target vehicle to be predicted;

[0101] The current administrative district entrance and exit electronic fence 20 is used to determine the current administrative district entrance and exit electronic fence passed by the closest time to the current time from the dictionary tree according to the current position point of the target vehicle;

[0102] The destination probability value query module 30 is used to query the destination probability value corresponding to the electronic fence at the entrance and exit of the current administrative area from the memory database;

[0103] The destination determination module 40 is used to determine the destination corresponding to the current destination probability value as the final destination of the target vehicle when the current destination probability value is greater than a preset probability threshold.

[0104] It should be noted that the device for predicting the destination of a vehicle provided in the above embodiment only uses the division of the above functional modules as an example when executing the method for predicting the destination of a vehicle. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the device for predicting the destination of a vehicle provided in the above embodiment and the method embodiment for predicting the destination of a vehicle belong to the same concept. The implementation process is detailed in the method embodiment and will not be repeated here.

[0105] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0106] In an embodiment of the present application, the device for predicting the destination of a vehicle first loads the dictionary tree corresponding to the enterprise to which the target vehicle belongs when receiving a prediction request for the target vehicle to be predicted, and then determines from the dictionary tree the electronic fence at the entrance and exit of the current administrative district that is passed at the moment closest to the current moment according to the current position of the target vehicle, and then queries the destination probability value corresponding to the electronic fence at the entrance and exit of the current administrative district from the memory database, and finally, when the current destination probability value is greater than the preset probability threshold, determines the destination corresponding to the current destination probability value as the final destination of the target vehicle. Since the present application determines the dynamically changing destination probability value corresponding to the electronic fence passed by from the memory database by touching different electronic fences during the dynamic driving of the vehicle, and judges the credibility of the final destination based on the dynamically changing destination probability value, the accuracy of the destination prediction is improved.

[0107] The present invention also provides a computer-readable medium having program instructions stored thereon, and when the program instructions are executed by a processor, the method for predicting a vehicle destination provided by the above-mentioned various method embodiments is implemented.

[0108] The present invention also provides a computer program product comprising instructions, which, when executed on a computer, enables the computer to execute the method for predicting a vehicle destination in each of the above method embodiments.

[0109] See also Figure 7 , which is a schematic diagram of the structure of a terminal provided in an embodiment of the present application. Figure 7 As shown, the terminal 1000 may include: at least one processor 1001 , at least one network interface 1004 , a user interface 1003 , a memory 1005 , and at least one communication bus 1002 .

[0110] The communication bus 1002 is used to realize the connection and communication between these components.

[0111] The user interface 1003 may include a display screen (Display) and a camera (Camera), and the optional user interface 1003 may also include a standard wired interface and a wireless interface.

[0112] The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0113] Among them, the processor 1001 may include one or more processing cores. The processor 1001 uses various interfaces and lines to connect various parts of the entire electronic device 1000, and executes various functions and processes data of the electronic device 1000 by running or executing instructions, programs, code sets or instruction sets stored in the memory 1005, and calling data stored in the memory 1005. Optionally, the processor 1001 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 1001 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 1001, and it can be implemented separately through a chip.

[0114] Among them, the memory 1005 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 1005 includes a non-transitory computer-readable storage medium. The memory 1005 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 1005 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 1005 may optionally be at least one storage device located away from the aforementioned processor 1001. As Figure 7 As shown, the memory 1005 as a computer storage medium may include an operating system, a network communication module, a user interface module, and an application program for predicting a vehicle destination.

[0115] exist Figure 7 In the terminal 1000 shown, the user interface 1003 is mainly used to provide an input interface for the user and obtain the data input by the user; and the processor 1001 can be used to call the application for predicting the vehicle destination stored in the memory 1005, and specifically perform the following operations:

[0116] When a prediction request for a target vehicle to be predicted is received, a dictionary tree corresponding to the enterprise to which the target vehicle belongs is loaded;

[0117] According to the current position point of the target vehicle, the electronic fence at the entrance and exit of the current administrative area passed by the vehicle at the closest time to the current time is determined from the dictionary tree;

[0118] Query the destination probability value corresponding to the electronic fence at the entrance and exit of the current administrative area from the memory database;

[0119] When the current destination probability value is greater than a preset probability threshold, the destination corresponding to the current destination probability value is determined as the final destination of the target vehicle.

[0120] In one embodiment, before receiving a prediction request for a target vehicle to be predicted, the processor 1001 further performs the following operations:

[0121] Get the real-time driving trajectory points of each vehicle;

[0122] Load the route relationship matrix corresponding to the enterprise to which each vehicle belongs from the pre-generated route relationship matrix library;

[0123] When the driving trajectory point enters the pre-built electronic fence at the entrance and exit of the administrative area, the frequency corresponding to the electronic fence is extracted from the route relationship matrix;

[0124] The probability value of each vehicle's current destination is calculated based on the frequency, and the probability value of each vehicle's current destination is saved in the memory database.

[0125] In one embodiment, the processor 1001 further performs the following operations:

[0126] When the destination probability value is less than a preset probability threshold, multiple downstream entrance and exit electronic fences of the current administrative district entrance and exit electronic fence are obtained;

[0127] Constructing line segments between the electronic fence at the entrance and exit of the current administrative district and the electronic fences at the entrance and exit of multiple downstream administrative districts to obtain multiple line segments;

[0128] Construct the target line segment between the location point of the target vehicle and the electronic fence at the entrance and exit of the current administrative area;

[0129] calculating an angle between a target line segment and each of the plurality of line segments;

[0130] determining a length of each of the plurality of line segments based on a cosine of the angle;

[0131] The final destination of the target vehicle is calculated based on the similarity corresponding to the line segment with the smallest length.

[0132] In one embodiment, the processor 1001 generates a route relationship matrix library according to the following steps:

[0133] Create an enterprise electronic fence for each business based on the vehicle's parking point;

[0134] Obtain the driving trajectory data of freight vehicles in each enterprise, and calculate the set of trajectory points entering and exiting the administrative area based on the driving trajectory data;

[0135] Cluster the set of trajectory points entering and exiting the administrative area to generate multiple electronic fences at the entrance and exit of each enterprise;

[0136] Construct a first dictionary tree for each enterprise according to the enterprise electronic fence of each enterprise and the electronic fences of multiple administrative district entrances and exits of each enterprise;

[0137] A route relationship matrix library is generated according to the first dictionary tree of each enterprise.

[0138] In one embodiment, when the processor 1001 calculates the set of trajectory points entering and exiting the administrative area according to the driving trajectory data, the processor 1001 specifically performs the following operations:

[0139] Acquire multiple groups of first trajectory points before and after the administrative district is changed from the driving trajectory data;

[0140] Calculating the distance between each group of trajectory points in the plurality of groups of first trajectory points to generate a plurality of distance values;

[0141] Identifying distance values ​​greater than a preset threshold value among a plurality of distance values ​​one by one;

[0142] One by one, a group of first trajectory points corresponding to distance values ​​greater than a preset threshold are removed from the multiple groups of first trajectory points to generate multiple groups of second trajectory points;

[0143] The center point between each group of second trajectory points in the multiple groups of second trajectory points is calculated to generate a set of trajectory points entering and leaving the administrative area.

[0144] In one embodiment, when the processor 1001 performs clustering of the historical stop point set to generate multiple administrative district entrance and exit electronic fences for each enterprise, the following operations are specifically performed:

[0145] Clustering algorithm is used to cluster the center point set of the trajectory point group to generate a cluster area;

[0146] Calculate the center point of the cluster area, mark the center point with a unique ID, and then get the entrance and exit of the administrative area;

[0147] With the entrance and exit of each administrative district as the center and a circle with a preset radius, an electronic fence is generated for the entrance and exit of each administrative district;

[0148] The electronic fences at the entrances and exits of each administrative district are combined to generate multiple electronic fences at the entrances and exits of each enterprise.

[0149] In one embodiment, when the processor 1001 generates a route relationship matrix library according to the first dictionary tree of each enterprise, the processor 1001 specifically performs the following operations:

[0150] Using a depth-first search algorithm to label the attribute parameters of each node in the first dictionary tree of each enterprise, a second dictionary tree of each enterprise is generated;

[0151] Deconstruct the second dictionary tree of each enterprise to generate a route relationship matrix from the entrance and exit of each enterprise to each end point;

[0152] The route relationship matrix from each enterprise's entrance and exit to each end point is saved to generate a route relationship matrix library.

[0153] In an embodiment of the present application, the device for predicting the destination of a vehicle first loads the dictionary tree corresponding to the enterprise to which the target vehicle belongs when receiving a prediction request for the target vehicle to be predicted, and then determines from the dictionary tree the electronic fence at the entrance and exit of the current administrative district that is passed at the moment closest to the current moment according to the current position of the target vehicle, and then queries the destination probability value corresponding to the electronic fence at the entrance and exit of the current administrative district from the memory database, and finally, when the current destination probability value is greater than the preset probability threshold, determines the destination corresponding to the current destination probability value as the final destination of the target vehicle. Since the present application determines the dynamically changing destination probability value corresponding to the electronic fence passed by from the memory database by touching different electronic fences during the dynamic driving of the vehicle, and judges the credibility of the final destination based on the dynamically changing destination probability value, the accuracy of the destination prediction is improved.

[0154] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing related hardware through a computer program, and the program for predicting the vehicle destination can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the above-mentioned embodiments of the methods. The storage medium can be a disk, an optical disk, a read-only storage memory, or a random access memory, etc.

[0155] The above disclosure is only the preferred embodiment of the present application, which certainly cannot be used to limit the scope of rights of the present application. Therefore, equivalent changes made according to the claims of the present application are still within the scope covered by the present application.

Claims

1. A method for predicting a vehicle destination, characterized in that: The method comprises: When a prediction request for a target vehicle to be predicted is received, a dictionary tree corresponding to the enterprise to which the target vehicle belongs is loaded; Determine the electronic fence of the entrance and exit of the current administrative area passed by the time closest to the current time from the dictionary tree according to the current position point of the target vehicle; Query the destination probability value corresponding to the electronic fence at the entrance and exit of the current administrative area from the memory database; When the current destination probability value is greater than a preset probability threshold, the destination corresponding to the current destination probability value is determined as the final destination of the target vehicle; wherein, Before receiving a prediction request for a target vehicle to be predicted, the method further includes: Get the real-time driving trajectory points of each vehicle; Loading the route relationship matrix corresponding to the enterprise to which each vehicle belongs from a pre-generated route relationship matrix library; When the driving trajectory point enters the pre-constructed electronic fence at the entrance and exit of the administrative area, the frequency corresponding to the electronic fence is extracted from the route relationship matrix; Calculate the probability value of each vehicle's current destination according to the frequency, and save the probability value of each vehicle's current destination to the memory database; wherein, Follow these steps to generate a route relationship matrix library, including: Create an enterprise electronic fence for each business based on the vehicle's parking point; Obtaining the driving trajectory data of freight vehicles in each enterprise, and calculating the set of trajectory points entering and exiting the administrative area based on the driving trajectory data; Clustering the set of trajectory points of entering and exiting the administrative area to generate multiple electronic fences of entrances and exits of the administrative area for each enterprise; Constructing a first dictionary tree for each enterprise according to the enterprise electronic fence of each enterprise and the multiple administrative district entrance and exit electronic fences of each enterprise; A route relationship matrix library is generated according to the first dictionary tree of each enterprise.

2. The method according to claim 1, characterized in that The method further comprises: When the destination probability value is less than a preset probability threshold, multiple downstream administrative district entrance and exit electronic fences of the current administrative district entrance and exit electronic fence are obtained; Constructing a line segment between the electronic fence at the entrance and exit of the current administrative district and the electronic fences at the entrance and exit of the multiple downstream administrative districts to obtain multiple line segments; Constructing a target line segment between the location point of the target vehicle and the electronic fence at the entrance and exit of the current administrative area; calculating an angle between the target line segment and each of the plurality of line segments; determining a length of each of the plurality of line segments based on a cosine of the angle; The final destination of the target vehicle is calculated based on the similarity corresponding to the line segment with the smallest length.

3. The method according to claim 1, characterized in that The step of calculating a set of trajectory points entering and exiting an administrative area according to the driving trajectory data includes: Acquire multiple groups of first trajectory points before and after the administrative area is changed from the driving trajectory data; Calculating the distance between each group of trajectory points in the plurality of groups of first trajectory points to generate a plurality of distance values; Identifying distance values ​​greater than a preset threshold value among the multiple distance values ​​one by one; One by one, a group of first trajectory points corresponding to the distance values ​​greater than a preset threshold are removed from the multiple groups of first trajectory points to generate multiple groups of second trajectory points; The center point between each group of second trajectory points in the plurality of groups of second trajectory points is calculated to generate a set of trajectory points for entering and exiting the administrative area.

4. The method according to claim 3, characterized in that The set of entry and exit trajectory points is clustered to generate multiple entry and exit electronic fences of each enterprise, including: A clustering algorithm is used to cluster the set of trajectory points entering and exiting the administrative area to generate a cluster area; Calculate the center point of the gathering area, and mark the center point with a unique ID to obtain the entrance and exit of the administrative area; Taking each of the administrative district entrances and exits as the center and drawing a circle according to a preset radius, an electronic fence is generated at each of the administrative district entrances and exits; The electronic fences at the entrances and exits of each administrative district are combined to generate multiple electronic fences at the entrances and exits of each enterprise.

5. The method according to claim 1, characterized in that The generating a route relationship matrix library according to the first dictionary tree of each enterprise comprises: Using a depth-first search algorithm to perform attribute parameter marking on each node in the first dictionary tree of each enterprise, generating a second dictionary tree of each enterprise; Deconstructing the second dictionary tree of each enterprise to generate a route relationship matrix from the entrance and exit of each enterprise to each end point; The route relationship matrix from the entrance and exit of each enterprise to each end point is saved to generate a route relationship matrix library.

6. A device for predicting a vehicle destination, characterized in that: The device comprises: A dictionary tree loading module is used to load the dictionary tree corresponding to the enterprise to which the target vehicle belongs when receiving a prediction request for the target vehicle to be predicted; The electronic fence at the entrance and exit of the current administrative area is used to determine the electronic fence at the entrance and exit of the current administrative area passed by the target vehicle at the closest time to the current time from the dictionary tree according to the current position point of the target vehicle; A destination probability value query module is used to query the destination probability value corresponding to the electronic fence at the entrance and exit of the current administrative area from the memory database; A destination determination module is used to determine the destination corresponding to the current destination probability value as the final destination of the target vehicle when the current destination probability value is greater than a preset probability threshold; wherein, The device is also specifically used for: Get the real-time driving trajectory points of each vehicle; Loading the route relationship matrix corresponding to the enterprise to which each vehicle belongs from a pre-generated route relationship matrix library; When the driving trajectory point enters the pre-constructed electronic fence at the entrance and exit of the administrative area, the frequency corresponding to the electronic fence is extracted from the route relationship matrix; Calculate the probability value of each vehicle's current destination according to the frequency, and save the probability value of each vehicle's current destination to the memory database; wherein, Follow these steps to generate a route relationship matrix library, including: Create an enterprise electronic fence for each business based on the vehicle's parking point; Obtaining the driving trajectory data of freight vehicles in each enterprise, and calculating the set of trajectory points entering and exiting the administrative area based on the driving trajectory data; Clustering the set of trajectory points of entering and exiting the administrative area to generate multiple electronic fences of entrances and exits of the administrative area for each enterprise; Constructing a first dictionary tree for each enterprise according to the enterprise electronic fence of each enterprise and the multiple administrative district entrance and exit electronic fences of each enterprise; A route relationship matrix library is generated according to the first dictionary tree of each enterprise.

7. A computer storage medium, characterized in that: The computer storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the method according to any one of claims 1 to 5.

8. A terminal, characterized in that: include: A processor and a memory; wherein the memory stores a computer program, and the computer program is suitable for being loaded by the processor and executing the method according to any one of claims 1 to 5.

Images