CN111723835A

CN111723835A - Vehicle movement track distinguishing method and device and electronic equipment

Info

Publication number: CN111723835A
Application number: CN201910218091.9A
Authority: CN
Inventors: 甘谊昂
Original assignee: Beijing Didi Infinity Technology and Development Co Ltd
Current assignee: Beijing Didi Infinity Technology and Development Co Ltd
Priority date: 2019-03-21
Filing date: 2019-03-21
Publication date: 2020-09-29

Abstract

The application provides a vehicle movement track distinguishing method, a vehicle movement track distinguishing device and electronic equipment, wherein the method comprises the following steps: acquiring moving track data to be identified, wherein the moving track data comprises attribute data of each track point; based on the attribute data of each track point, carrying out feature extraction on the moving track data to obtain target feature data, wherein the target feature data comprises: behavior characteristic data of the movement trajectory data and/or time characteristic data of the movement trajectory data; and performing prediction processing on the target characteristic data by using the recognition model to obtain a processing result, wherein the processing result is used for determining the type of the vehicle to which the movement track data belongs. The method and the device can solve the problems that in the prior art, when the vehicle to which the moving track belongs is identified, the identification precision is poor, and the identification efficiency is low in a mode of carrying out prediction processing on the target characteristic data.

Description

Vehicle movement track distinguishing method and device and electronic equipment

Technical Field

The application relates to the technical field of internet, in particular to a vehicle movement track distinguishing method and device and electronic equipment.

Background

In anti-cheating services of a designated driving platform, a service provider collects relevant benefits by means of false order reporting, wherein the false order reporting means that the service provider does not generate actual automobile designated driving services, but adopts a bicycle as a travel tool to run towards a target terminal point to perform simulated designated driving services. Therefore, it is necessary to efficiently identify whether or not a false order is made from the trajectory data of each order, and thus to translate the problem into the identification of the vehicle to which the trajectory data corresponds. At present, the vehicle identification can be realized by methods such as image identification, namely, images are acquired by external acquisition equipment, and image content information is acquired by image identification technologies such as deep learning.

Disclosure of Invention

In view of this, an object of the embodiments of the present application is to provide a method and an apparatus for distinguishing a vehicle movement track, and an electronic device, which can solve the problems of poor recognition accuracy and low recognition efficiency in recognizing a vehicle to which a movement track belongs in the prior art by performing prediction processing on target feature data.

According to one aspect of the present application, an electronic device is provided that may include one or more storage media and one or more processors in communication with the storage media. One or more storage media store machine-readable instructions executable by a processor. When the electronic device is operated, the processor is communicated with the storage medium through the bus, and the processor executes the machine readable instructions to execute one or more of the vehicle movement track distinguishing methods.

According to another aspect of the present application, there is also provided a vehicle movement track distinguishing method, including: acquiring moving track data to be identified, wherein the moving track data comprises attribute data of each track point; based on the attribute data of each track point, performing feature extraction on the moving track data to obtain target feature data, wherein the target feature data comprises: behavior characteristic data of the movement trajectory data and/or time characteristic data of the movement trajectory data; and performing prediction processing on the target characteristic data by using an identification model to obtain a processing result, wherein the processing result is used for determining the type of a vehicle to which the movement track data belongs.

In a preferred embodiment of the present application, the behavior feature data includes at least one of: the method comprises the following steps of (1) speed discrete distribution proportion, speed variance, minimum non-zero speed, maximum speed, average speed, maximum acceleration, minimum non-zero acceleration, average acceleration, the number of track points in a staying state and the total staying time of the track points in the staying state; the temporal characteristic data comprises at least one of: the mark information is used for representing whether the moving track data belongs to the congestion peak period or not, the time period to which the moving track data belongs and the duration of the moving track data.

In a preferred embodiment of the present application, the attribute data includes coordinate information, time stamp information, and speed information; based on the attribute data of each track point, performing feature extraction on the moving track data to obtain target feature data, wherein the target feature data comprises: and calculating the characteristic information of the moving track data according to the coordinate information, the timestamp information and the speed information of each track point in the moving track data to obtain the target characteristic data.

In a preferred embodiment of the present application, the performing a prediction process on the target feature data by using a recognition model to obtain a processing result includes: predicting the target characteristic data through the identification model to obtain a prediction result, wherein the prediction result is used for representing probability information of various vehicles to which the movement track data belongs; comparing the prediction result with corresponding type thresholds, wherein different types of vehicles correspond to different type thresholds; and if the comparison result is that the prediction result is greater than or equal to the corresponding type threshold, obtaining a processing result of the transportation tool corresponding to the corresponding type threshold to which the movement track data belongs.

In a preferred embodiment of the present application, the method further comprises: and verifying the processing result by utilizing a category correction strategy, wherein the category correction strategy is a strategy determined based on behavior characteristic data of the movement track data.

In a preferred embodiment of the present application, the types of vehicles include: a bicycle; the bicycle comprises: motorcycles, electric bicycles, or mechanical bicycles; the verifying the processing result by using the class correction strategy comprises the following steps: comparing the speed of each track point in the moving track data with a first preset speed threshold, wherein the first preset speed threshold is the highest speed threshold of the bicycle; and verifying whether the moving track data belongs to the bicycle or not according to the number of first track points with the speed greater than a first preset speed threshold value contained in the moving track data.

In a preferred embodiment of the present application, verifying whether the movement trajectory data belongs to a bicycle according to the number of first trajectory points included in the movement trajectory data and having a speed greater than a first preset speed threshold includes: if the comparison result shows that the moving track data comprises a first track point with the speed greater than a first preset speed threshold value, verifying that the moving track data does not belong to the bicycle; or if the comparison result shows that the number of the first track points with the speed greater than the preset speed threshold value contained in the moving track data is greater than the first preset number, the moving track data is verified not to belong to the bicycle.

In a preferred embodiment of the present application, the types of vehicles include: an automobile; the verifying the processing result by using the class correction strategy comprises the following steps: comparing the speed of each track point in the moving track data with a second preset speed threshold, wherein the second preset speed threshold is the lowest speed threshold of the automobile; and verifying whether the moving track data belongs to the automobile or not according to the number of second track points with the speed greater than a second preset speed threshold value contained in the moving track data.

In a preferred embodiment of the present application, determining whether the movement track data belongs to an automobile according to the number of second track points included in the movement track data, where the speed of the second track points is greater than a second preset speed threshold, includes: if the comparison result is that the moving track data contains a second track point with the speed smaller than a second preset speed threshold value, verifying that the moving track data does not belong to the automobile; or if the comparison result shows that the number of second track points with the speed smaller than a second preset speed threshold value in the moving track data is larger than a second preset number, the moving track data is verified not to belong to the automobile.

In a preferred embodiment of the present application, the method further comprises: acquiring training sample data, wherein the training sample data comprises a plurality of first track data, and each first track data comprises the following attribute data: ID identification information, longitude and latitude coordinate information of each track point, timestamp information of each track point, speed information of each track point and category information of a vehicle to which the first track data belongs; and repeatedly training the Xgboost model by using the training sample data, and taking the Xgboost model after training as the recognition model when the Xgboost model meets the training precision.

In a preferred embodiment of the present application, training an Xgboost model by using the training sample data to obtain the recognition model includes: extracting features of each training sample data to obtain behavior feature data and time feature data of each training sample data; and training the Xgboost model by using the behavior characteristic data and the time characteristic data of each training sample data to obtain the recognition model.

In a preferred embodiment of the present application, after the training of the recognition model, the method further includes: and adjusting the type threshold of the identification model, wherein the type threshold is one or more, and each type threshold corresponds to one type of vehicle.

In a preferred embodiment of the present application, after performing a training on the Xgboost model with the training sample data, the method further comprises: obtaining test sample data, wherein the test sample data comprises a plurality of second track data, and each second track data comprises the following attribute data: ID identification information, longitude and latitude coordinate information of each track point, timestamp information of each track point, speed information of each track point and category information of a vehicle to which the second track data belongs; processing the test sample data by using the obtained identification model to obtain a category prediction result of each second track data; comparing the category prediction result of each second trajectory data with the category information of the vehicle to which the second trajectory data belongs to determine target trajectory data with wrong prediction in the plurality of second trajectory data; judging whether the Xgboost model meets the training precision or not according to the number of the target track data; if so, taking the trained Xgboost model as the recognition model; otherwise, continuing to train the Xgboost model by using the training sample data.

In a preferred embodiment of the present application, after determining the target trajectory data with the wrong prediction in the plurality of second trajectory data, the method further includes: and determining a category correction strategy based on the strategy determined by the behavior characteristic data of the target track data.

According to another aspect of the present application, there is also provided a vehicle movement trajectory distinction apparatus including: the device comprises a first acquisition unit, a second acquisition unit and a control unit, wherein the first acquisition unit is used for acquiring movement track data to be identified, and the movement track data comprises attribute data of each track point; the feature extraction unit is configured to perform feature extraction on the movement track data based on attribute data of each track point to obtain target feature data, where the target feature data includes: behavior characteristic data of the movement trajectory data and/or time characteristic data of the movement trajectory data; and the prediction processing unit is used for performing prediction processing on the target characteristic data by using the recognition model to obtain a processing result, wherein the processing result is used for determining the type of the vehicle to which the movement track data belongs.

In a preferred embodiment of the present application, the attribute data includes coordinate information, time stamp information, and speed information; the feature extraction unit is configured to: and calculating the characteristic information of the moving track data according to the coordinate information, the timestamp information and the speed information of each track point in the moving track data to obtain the target characteristic data.

In a preferred embodiment of the present application, the prediction processing unit is configured to: predicting the target characteristic data through the identification model to obtain a prediction result, wherein the prediction result is used for representing probability information of various vehicles to which the movement track data belongs; comparing the prediction result with corresponding type thresholds, wherein different types of vehicles correspond to different type thresholds; and if the comparison result is that the prediction result is greater than or equal to the corresponding type threshold, obtaining a processing result of the transportation tool corresponding to the corresponding type threshold to which the movement track data belongs.

In a preferred embodiment of the present application, the apparatus further comprises: and the verification unit is used for verifying the processing result by utilizing a class correction strategy, wherein the class correction strategy is a strategy determined based on behavior characteristic data of the movement track data.

In a preferred embodiment of the present application, the types of vehicles include: a bicycle; the bicycle comprises: motorcycles, electric bicycles, or mechanical bicycles; the authentication unit includes: the first comparison module is used for comparing the speed of each track point in the moving track data with a first preset speed threshold, wherein the first preset speed threshold is the highest speed threshold of the bicycle; and the first verification module is used for verifying whether the moving track data belongs to the bicycle or not according to the number of the first track points of which the speed is greater than a first preset speed threshold value, wherein the first track points are contained in the moving track data.

In a preferred embodiment of the present application, the first verification module is configured to: if the comparison result shows that the moving track data comprises a first track point with the speed greater than a first preset speed threshold value, verifying that the moving track data does not belong to the bicycle; or if the comparison result shows that the number of the first track points with the speed greater than the preset speed threshold value contained in the moving track data is greater than the first preset number, the moving track data is verified not to belong to the bicycle.

In a preferred embodiment of the present application, the types of vehicles include: an automobile; the authentication unit further includes: the second comparison module is used for comparing the speed of each track point in the moving track data with a second preset speed threshold, wherein the second preset speed threshold is the lowest speed threshold of the automobile; and the second verification module is used for determining whether the moving track data belongs to the automobile or not according to the number of second track points of which the speed is greater than a second preset speed threshold value and contained in the moving track data.

In a preferred embodiment of the present application, the second verification module is configured to: if the comparison result is that the moving track data contains a second track point with the speed smaller than a second preset speed threshold value; or if the comparison result shows that the number of second track points with the speed smaller than a second preset speed threshold value in the moving track data is larger than a second preset number, determining that the moving track data does not belong to the automobile.

In a preferred embodiment of the present application, the apparatus further comprises: a second obtaining unit, configured to obtain training sample data, where the training sample data includes multiple first trajectory data, and each first trajectory data includes the following attribute data: ID identification information, longitude and latitude coordinate information of each track point, timestamp information of each track point, speed information of each track point and category information of a vehicle to which the first track data belongs; and the training unit is used for repeatedly training the Xgboost model by using the training sample data, and taking the trained Xgboost model as the recognition model when the Xgboost model meets the training precision.

In a preferred embodiment of the present application, the training unit is configured to: extracting features of each training sample data to obtain behavior feature data and time feature data of each training sample data; and training the Xgboost model by using the behavior characteristic data and the time characteristic data of each training sample data to obtain the recognition model.

In a preferred embodiment of the present application, the apparatus is further configured to: after the recognition model is obtained through training, adjusting the type threshold of the recognition model, wherein the type threshold is one or more, and each type threshold corresponds to one type of vehicle.

In a preferred embodiment of the present application, the apparatus is further configured to: after the Xgboost model is trained for one time by using the training sample data, obtaining test sample data, wherein the test sample data comprises a plurality of second track data, and each second track data comprises the following attribute data: ID identification information, longitude and latitude coordinate information of each track point, timestamp information of each track point, speed information of each track point and category information of a vehicle to which the second track data belongs; processing the test sample data by using the obtained identification model to obtain a category prediction result of each second track data; comparing the category prediction result of each second trajectory data with the category information of the vehicle to which the second trajectory data belongs to determine target trajectory data with wrong prediction in the plurality of second trajectory data; judging whether the Xgboost model meets the training precision or not according to the number of the target track data; if so, taking the trained Xgboost model as the recognition model; otherwise, continuing to train the Xgboost model by using the training sample data.

In a preferred embodiment of the present application, the apparatus is further configured to: after the target track data with the wrong prediction in the plurality of second track data are determined, determining a category correction strategy based on the strategy determined by the behavior characteristic data of the target track data.

According to another aspect of the present application, there is also provided a computer-readable storage medium having a computer program stored thereon, which, when being executed by a processor, performs the steps of the method for vehicle movement trajectory differentiation as set forth in any one of the above.

In this embodiment, first, movement trajectory data to be recognized is acquired; and finally, performing prediction processing on the target characteristic data by using the recognition model to obtain a processing result, wherein the processing result is used for determining the type of a vehicle to which the movement track data belongs. In the embodiment, the problems of poor identification precision and low identification efficiency in the prior art when the vehicle to which the moving track belongs is identified can be solved by extracting the characteristics of the moving track data to obtain the target characteristic data.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.

FIG. 1 illustrates a block diagram of a vehicle movement trajectory discrimination system 100 of some embodiments of the present application;

FIG. 2 illustrates a schematic diagram of exemplary hardware and software components of an electronic device 200 of a server 110, a service requester terminal 130, a service provider terminal 140 that may implement the concepts of the present application for some embodiments of the present application;

FIG. 3 is a flowchart illustrating a vehicle movement track distinguishing method according to an embodiment of the present disclosure;

FIG. 4 is a flow chart illustrating another vehicle movement track distinguishing method provided by the embodiment of the present application;

FIG. 5 is a flow chart illustrating a further method for distinguishing a vehicle movement track according to an embodiment of the present application;

fig. 6 shows a schematic structural diagram of another vehicle movement track distinguishing device provided in the embodiment of the present application.

Detailed Description

In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it should be understood that the drawings in the present application are for illustrative and descriptive purposes only and are not used to limit the scope of protection of the present application. Additionally, it should be understood that the schematic drawings are not necessarily drawn to scale. The flowcharts used in this application illustrate operations implemented according to some embodiments of the present application. It should be understood that the operations of the flow diagrams may be performed out of order, and steps without logical context may be performed in reverse order or simultaneously. One skilled in the art, under the guidance of this application, may add one or more other operations to, or remove one or more operations from, the flowchart.

In addition, the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present application, presented in the accompanying drawings, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present application without making any creative effort, shall fall within the protection scope of the present application.

To enable those skilled in the art to utilize the present disclosure, the following embodiments are presented in conjunction with a specific application scenario, "a network appointment scenario". It will be apparent to those skilled in the art that the general principles defined herein may be applied to other embodiments and applications without departing from the spirit and scope of the application. Although the present application is described primarily in the context of a network appointment scenario, it should be understood that this is only one exemplary embodiment. The present application may be applied to the following vehicles: may include a taxi, a private car, a tailgating, a bus, an unmanned vehicle, or the like, or any combination thereof.

It should be noted that in the embodiments of the present application, the term "comprising" is used to indicate the presence of the features stated hereinafter, but does not exclude the addition of further features.

The terms "passenger," "requestor," "service person," "service requestor," and "customer" are used interchangeably in this application to refer to an individual, entity, or tool that can request or order a service. The terms "driver," "provider," "service provider," and "provider" are used interchangeably in this application to refer to an individual, entity, or tool that can provide a service. The term "user" in this application may refer to an individual, entity or tool that requests a service, subscribes to a service, provides a service, or facilitates the provision of a service. For example, the user may be a passenger, a driver, an operator, etc., or any combination thereof. In the present application, "passenger" and "passenger terminal" may be used interchangeably, and "driver" and "driver terminal" may be used interchangeably.

The term "order" in this application refers to a request initiated by a passenger, a service requester, a driver, a service provider, a supplier, or the like, or any combination thereof. The "order" may be accepted by a passenger, a service requester, a driver, a service provider, a supplier, or the like, or any combination thereof. The service request may be charged or free.

One aspect of the present application relates to a vehicle movement trajectory differentiation system. The system firstly obtains moving track data to be identified, wherein the moving track data comprises attribute data of each track point; then, based on the attribute data of each track point, performing feature extraction on the moving track data to obtain target feature data, wherein the target feature data comprises: behavior characteristic data of the movement trajectory data and/or time characteristic data of the movement trajectory data; and finally, performing prediction processing on the target characteristic data by using the recognition model to obtain a processing result, wherein the processing result is used for determining the type of the transportation means to which the movement track data belongs. According to the method and the device for identifying the vehicle, the target characteristic data is obtained by extracting the characteristics of the moving track data, so that the problems that the identification precision is poor and the identification efficiency is low when the vehicle to which the moving track belongs is identified in the prior art can be solved, and the effect of improving the identification efficiency is achieved by determining the vehicle to which the moving track belongs through the track data which is easy to obtain.

The moving track data records the real-time motion state of each order of the service provider, and the driving behavior modes of the service provider in different space-time environments are implied. The movement track data comprises the following attribute data: ID identification information, longitude and latitude coordinate information of each track point, timestamp information of each track point, speed information of each track point and category information of a vehicle to which the moving track data belongs. In the prior art, the transportation means to which the movement track data belongs is determined by methods such as image recognition, but the method has the disadvantages of high technical difficulty and high computing resource demand, no image information is available in the actual service scene of the designated driving, and the method is not suitable for the service scene.

In the embodiment, the target characteristic data is obtained by performing characteristic extraction on the moving track data, and then the target characteristic data is used for prediction processing, so that the problems of poor identification precision and low identification efficiency in the prior art when the vehicle to which the moving track belongs is identified can be solved.

FIG. 1 is a block diagram of a vehicle movement trajectory discrimination system 100 of some embodiments of the present application. For example, vehicle movement trajectory differentiation system 100 may be an online transportation service platform for transportation services such as taxis, designated driving services, express, pool, bus services, driver rentals, or regular bus services, or any combination thereof. Vehicle movement trajectory differentiation system 100 may include one or more of a server 110, a network 120, a service requester terminal 130, a service provider terminal 140, and a database 150, and server 110 may include a processor that performs instruction operations.

In some embodiments, the server 110 may be a single server or a group of servers. The set of servers can be centralized or distributed (e.g., the servers 110 can be a distributed system). In some embodiments, the server 110 may be local or remote to the terminal. For example, the server 110 may access information and/or data stored in the service requester terminal 130, the service provider terminal 140, or the database 150, or any combination thereof, via the network 120. As another example, the server 110 may be directly connected to at least one of the service requester terminal 130, the service provider terminal 140, and the database 150 to access stored information and/or data. In some embodiments, the server 110 may be implemented on a cloud platform; by way of example only, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud (community cloud), a distributed cloud, an inter-cloud, a multi-cloud, and the like, or any combination thereof.

In some embodiments, the server 110 may include a processor. The processor may process information and/or data related to the service request to perform one or more of the functions described herein. In some embodiments, a processor may include one or more processing cores (e.g., a single-core processor (S) or a multi-core processor (S)). Merely by way of example, a Processor may include a Central Processing Unit (CPU), an Application Specific Integrated Circuit (ASIC), an Application Specific Instruction Set Processor (ASIP), a Graphics Processing Unit (GPU), a Physical Processing Unit (PPU), a Digital Signal Processor (DSP), a Field Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), a controller, a microcontroller Unit, a reduced Instruction Set computer (reduced Instruction Set computer), a microprocessor, or the like, or any combination thereof.

Network 120 may be used for the exchange of information and/or data. In some embodiments, one or more components (e.g., server 110, service requester terminal 130, service provider terminal 140, and database 150) in the vehicle movement trajectory differentiation system 100 may send information and/or data to other components. In some embodiments, the network 120 may be any type of wired or wireless network, or combination thereof. Merely by way of example, Network 130 may include a wired Network, a Wireless Network, a fiber optic Network, a telecommunications Network, an intranet, the internet, a Local Area Network (LAN), a Wide Area Network (WAN), a Wireless Local Area Network (WLAN), a WLAN, a Metropolitan Area Network (MAN), a Wide Area Network (WAN), a Public Switched Telephone Network (PSTN), a bluetooth Network, a ZigBee Network, a Near Field Communication (NFC) Network, or the like, or any combination thereof. In some embodiments, network 120 may include one or more network access points. For example, the network 120 may include wired or wireless network access points, such as base stations and/or network switching nodes, through which one or more components of the vehicle movement trajectory discrimination system 100 may connect to the network 120 to exchange data and/or information.

In some embodiments, the user of the service requestor terminal 130 may be someone other than the actual demander of the service. In some embodiments, the user of the service provider terminal 140 may be the actual provider of the service or may be another person than the actual provider of the service. In some embodiments, "service requester" and "service requester terminal" may be used interchangeably, and "service provider" and "service provider terminal" may be used interchangeably.

In some embodiments, the service requester terminal 130 may comprise a mobile device, a tablet computer, a laptop computer, or a built-in device in a motor vehicle, etc., or any combination thereof. In some embodiments, the service provider terminal 140 may be a similar or identical device as the service requestor terminal 130. In some embodiments, the service provider terminal 140 may be a device with location technology for locating the location of the service provider and/or the service provider terminal.

Database 150 may store data and/or instructions. In some embodiments, the database 150 may store data obtained from the service requester terminal 130 and/or the service provider terminal 140. In some embodiments, database 150 may store data and/or instructions for the exemplary methods described herein. In some embodiments, database 150 may include mass storage, removable storage, volatile Read-write Memory, or Read-Only Memory (ROM), among others, or any combination thereof. By way of example, mass storage may include magnetic disks, optical disks, solid state drives, and the like; removable memory may include flash drives, floppy disks, optical disks, memory cards, zip disks, tapes, and the like; volatile read-write Memory may include Random Access Memory (RAM); the RAM may include Dynamic RAM (DRAM), Double data Rate synchronous Dynamic RAM (DDR SDRAM); static RAM (SRAM), Thyristor-Based Random Access Memory (T-RAM), Zero-capacitor RAM (Zero-RAM), and the like. By way of example, ROMs may include Mask Read-Only memories (MROMs), Programmable ROMs (PROMs), Erasable Programmable ROMs (PERROMs), Electrically Erasable Programmable ROMs (EEPROMs), compact disk ROMs (CD-ROMs), digital versatile disks (ROMs), and the like. In some embodiments, database 150 may be implemented on a cloud platform. By way of example only, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, across clouds, multiple clouds, or the like, or any combination thereof.

In some embodiments, a database 150 may be connected to the network 120 to communicate with one or more components of the vehicle movement trajectory differentiation system 100 (e.g., the server 110, the service requester terminal 130, the service provider terminal 140, etc.). One or more components of the vehicle movement trajectory differentiation system 100 may access data or instructions stored in the database 150 via the network 120. In some embodiments, the database 150 may be directly connected to one or more components in the vehicle movement trajectory differentiation system 100 (e.g., the server 110, the service requester terminal 130, the service provider terminal 140, etc.); alternatively, in some embodiments, database 150 may also be part of server 110.

In some embodiments, one or more components (e.g., server 110, service requester terminal 130, service provider terminal 140, etc.) in the vehicle movement trajectory differentiation system 100 may have access to the database 150. In some embodiments, one or more components in the vehicle movement trajectory differentiation system 100 may read and/or modify information related to a service requester, a service provider, or the public, or any combination thereof, when certain conditions are met. For example, server 110 may read and/or modify information for one or more users after receiving a service request.

Fig. 2 illustrates a schematic diagram of exemplary hardware and software components of an electronic device 200 of a server 110, a service requester terminal 130, a service provider terminal 140, which may implement the concepts of the present application, according to some embodiments of the present application. For example, a processor may be used on the electronic device 200 and to perform the functions herein.

The electronic device 200 may be a general purpose computer or a special purpose computer, both of which may be used to implement the vehicle movement trajectory discrimination method of the present application. Although only a single computer is shown, for convenience, the functions described herein may be implemented in a distributed fashion across multiple similar platforms to balance processing loads.

For example, the electronic device 200 may include a network port 210 connected to a network, one or more processors 220 for executing program instructions, a communication bus 230, and a different form of storage medium 240, such as a disk, ROM, or RAM, or any combination thereof. Illustratively, the computer platform may also include program instructions stored in ROM, RAM, or other types of non-transitory storage media, or any combination thereof. The method of the present application may be implemented in accordance with these program instructions. The electronic device 200 also includes an Input/Output (I/O) interface 250 between the computer and other Input/Output devices (e.g., keyboard, display screen).

For ease of illustration, only one processor is depicted in the electronic device 200. However, it should be noted that the electronic device 200 in the present application may also comprise a plurality of processors, and thus the steps performed by one processor described in the present application may also be performed by a plurality of processors in combination or individually. For example, if the processor of the electronic device 200 executes steps a and B, it should be understood that steps a and B may also be executed by two different processors together or separately in one processor. For example, a first processor performs step a and a second processor performs step B, or the first processor and the second processor perform steps a and B together.

Referring to fig. 3, a flowchart of a vehicle movement track distinguishing method is shown.

The vehicle movement track distinguishing method shown in fig. 3 is described by taking a server applied to a designated driving platform as an example, and the method includes the following steps:

step S302, obtaining moving track data to be identified, wherein the moving track data comprises attribute data of each track point;

step S304, based on the attribute data of each track point, performing feature extraction on the movement track data to obtain target feature data, wherein the target feature data comprises: behavior characteristic data of the movement trajectory data and/or time characteristic data of the movement trajectory data;

step S306, carrying out prediction processing on the target characteristic data by using the recognition model to obtain a processing result, wherein the processing result is used for determining the type of the vehicle to which the movement track data belongs.

It should be noted that, in this embodiment, the methods described in the above steps S302 to S306 may be applied to a server side, and may also be applied to a driver platform APP installed in a terminal device to which a service provider belongs.

If the method is applied to the server, the server may obtain the movement trajectory data collected by the terminal device to which the service provider belongs, and analyze and process the movement trajectory data according to the processes described in the step S302 to the step S306, so as to obtain a processing result.

If the method is applied to the terminal device to which the service provider belongs, the terminal device to which the service provider belongs may collect the movement trajectory data, analyze and process the movement trajectory data according to the processes described in the above steps S302 to S306, obtain a processing result, and send the processing result to the server for analysis and storage.

In this embodiment, the terminal device to which the service provider belongs may be set to collect the movement trajectory data of the service provider every preset time period. For example, every N seconds, the latitude and longitude position of the service provider, the traveling speed of the service provider at the latitude and longitude position, the timestamp corresponding to the current collection operation, and data identification information (for example, ID information) are collected.

The moving track data comprises attribute data of each track point, and the attribute data of each track point is the following information collected when the collection operation is executed each time: the longitude and latitude position, the running speed of the service provider at the longitude and latitude position, the timestamp corresponding to the current acquisition operation, and data identification information (for example, ID information).

It should be noted that each track point in the moving track data belongs to the same service order.

As can be seen from the above description, in this embodiment, first, the mobile track data of the service provider is acquired by acquiring the terminal device to which the service provider belongs; and then, based on the attribute data of each track point, performing feature extraction on the moving track data to obtain target feature data. The obtained target characteristic data comprises behavior characteristic data and/or time characteristic data.

If the attribute data includes coordinate information, timestamp information, and speed information, in an optional implementation manner, in step S304, performing feature extraction on the movement trajectory data based on the attribute data of each trajectory point to obtain target feature data includes the following steps:

step S3041, calculating feature information of the movement trajectory data according to the coordinate information, the timestamp information, and the speed information of each trajectory point in the movement trajectory data, to obtain the target feature data.

The coordinate information may be a longitude and latitude position. Based on this, in the present embodiment, the behavior feature data and/or the time feature data may be calculated based on the coordinate information, the time stamp information, and the speed information of each trajectory point in the movement trajectory data.

Optionally, the behavioral characteristic data includes at least one of: the system comprises a speed discrete distribution proportion, a speed variance, a minimum non-zero speed, a maximum speed, an average speed, a maximum acceleration, a minimum non-zero acceleration, an average acceleration, the number of track points in a stay state and the total stay time of the track points in the stay state.

In this embodiment, the speed discrete distribution ratio is a distribution ratio of speeds corresponding to each track point in the moving track data. For example, a plurality of speed intervals may be divided in advance, and then the speed corresponding to each trace point is mapped to each speed interval, so as to obtain the speed discrete distribution ratio.

Optionally, the temporal characteristic data comprises at least one of: the mark information is used for representing whether the moving track data belongs to the congestion peak period or not, the time period to which the moving track data belongs and the duration of the moving track data.

In the present embodiment, the congestion peak period is preset, for example, the peak is early peak by default from 7 o 'clock 30 to 9 o' clock in the morning on monday to friday morning, and the peak is late peak by default from 5 o 'clock to 7 o' clock half in the afternoon on monday to friday. At this time, if the collection time period of the moving track data is located in the early peak time period, the marking information is the marking information used for representing the congestion peak time to which the moving track data belongs and belonging to the congestion early peak time period.

It should be noted that, in this embodiment, the congestion peak time is not fixed, and different cities or different areas of the same city may set different congestion peak times according to actual conditions, which is not specifically limited in this embodiment. In addition, in this embodiment, the early peak period and the late peak period may be distinguished, or the peak period and the late peak period may not be distinguished, and may be specifically set according to actual needs.

In this embodiment, after the target feature data (behavior feature data of the movement trace data and/or time feature data of the movement trace data) is obtained according to the processing method described above, the target feature data may be subjected to prediction processing by using the recognition model, so as to obtain a processing result.

In an alternative embodiment, as shown in fig. 4, in step S306, performing a prediction process on the target feature data by using a recognition model, and obtaining a processing result includes the following steps:

step S3061, predicting the target characteristic data through the recognition model to obtain a prediction result, wherein the prediction result is used for representing probability information of various vehicles to which the movement track data belongs;

step S3062, comparing the prediction result with corresponding type thresholds, wherein different types of vehicles correspond to different type thresholds;

step S3063, if the comparison result is that the prediction result is greater than or equal to the corresponding type threshold, obtaining a processing result that the movement trajectory data belongs to the vehicle corresponding to the corresponding type threshold.

In this embodiment, the target feature data may be subjected to prediction processing by the recognition model, and the obtained prediction result is probability information that the movement trajectory data belongs to various types of vehicles.

In this embodiment, two types of transportation means are selected, namely a bicycle and an automobile, wherein the bicycle may further include: motorcycles, electric bicycles or mechanical bicycles, automobiles can be divided into: an electric vehicle or a fuel vehicle, etc., and the embodiment is not particularly limited. At this time, the prediction results may be probability information a1 that the movement trace data belongs to the bicycle and probability information a2 that the movement trace data belongs to the automobile.

The prediction can then be compared to corresponding type thresholds, such as bicycles and automobiles. The bicycle is set to be B1 corresponding to a type threshold, and the automobile is set to be B2 corresponding to a type threshold. After obtaining the prediction result: after the probability information a1 that the movement trajectory data belongs to the bicycle and the probability information a2 that the movement trajectory data belongs to the car, a1 and B1 may be compared, and a2 and B2 may be compared.

And if the comparison result is that the prediction result is greater than or equal to the corresponding type threshold, obtaining a processing result of the transportation tool corresponding to the corresponding type threshold to which the movement track data belongs. For example, if a1 is greater than or equal to B1 and a2 is smaller than B2, it is determined that the movement trajectory data belongs to a bicycle. If A1 is smaller than B1 and A2 is greater than or equal to B2, it is determined that the movement trace data belongs to a car. If a1 is less than B1 and a2 is less than B2, the movement trajectory data may be further corrected, and if a1 is equal to or greater than B1 and a2 is equal to or greater than B2, the movement trajectory data may also be further corrected.

As can be seen from the above description, in the present embodiment, compared with the prior art, the way of predicting the target feature data by using the recognition model, the way of determining the vehicle to which the target feature data belongs by using the trajectory data that is easier to obtain, achieves the effect of improving the recognition efficiency.

As can be seen from the above description, if a1 is smaller than B1 and a2 is smaller than B2, the movement trace data can be further corrected, and if a1 is equal to or greater than B1 and a2 is equal to or greater than B2, the movement trace data can also be further corrected. Besides, after the transportation means to which the movement trajectory data belongs is determined, the processing result may also be verified, and a specific verification (or correction) process is described as follows:

step S308, verifying the processing result by using a category correction policy, wherein the category correction policy is determined based on behavior feature data of the movement trajectory data.

That is, in this embodiment, a corresponding class modification policy is set for the recognition mode in advance, and the class modification policy can further correct and verify the result of the recognition model, so that the processing result is more accurate.

In this embodiment, the category modification policy is preferably formulated using behavior feature data in the movement trajectory data. For example, the category correction strategy is formulated by behavior characteristic data about speed in the movement trajectory data, and the above verification (or correction) process will be described below separately in connection with two cases.

In case one, the type of the vehicle to which the movement trace data belongs includes: a bicycle; the bicycle comprises: motorcycles, electric bicycles, or mechanical bicycles.

Step S308, verifying the processing result by using the category correction policy includes:

step S11, comparing the speed of each track point in the moving track data with a first preset speed threshold value, wherein the first preset speed threshold value is the highest speed threshold value of the bicycle;

and step S12, verifying whether the movement track data belongs to a bicycle or not according to the number of first track points with the speed greater than a first preset speed threshold value contained in the movement track data.

In this embodiment, a first preset speed threshold is preset, which is the maximum speed threshold allowed for the bicycle to travel.

Optionally, if the processing result indicates that the vehicle to which the moving trajectory data belongs is a bicycle, the speed of each trajectory point in the moving trajectory data may be compared with a first preset threshold, so as to obtain the number of first trajectory points, of which the speed is greater than the first preset threshold, included in each trajectory point. And then, whether the moving track data belongs to the bicycle is verified according to the number.

Alternatively, the above-described case is a process of verifying the processing result of the bicycle to which the movement trajectory belongs, in the case where the processing result has been obtained. If the processing result that the moving track belongs to the bicycle or the automobile at the same time is obtained, or the processing result that the moving track data does not belong to the bicycle or the automobile at the same time is obtained, the vehicle to which the moving track data belongs may be further confirmed by the method described in the above step S11 and step S12.

In this embodiment, by setting the category correction policy, the processing result can be further corrected (or verified), so that the accuracy of the processing result is further ensured, and the accuracy of data processing is improved.

In an optional embodiment, in step S12, verifying whether the movement trajectory data belongs to a bicycle according to the number of first trajectory points included in the movement trajectory data and having a speed greater than a first preset speed threshold includes the following steps:

if the comparison result shows that the moving track data comprises a first track point with the speed greater than a first preset speed threshold value, verifying that the moving track data does not belong to the bicycle;

or if the comparison result shows that the number of the first track points with the speed greater than the preset speed threshold value contained in the moving track data is greater than the first preset number, the moving track data is verified not to belong to the bicycle.

At this time, the following cases can be classified.

In the first case, if the moving trajectory data includes a first trajectory point whose speed is greater than or equal to a first preset speed threshold, it can be verified that the moving trajectory data does not belong to the bicycle. Since the first predetermined speed threshold is a speed that the bicycle is unable to travel. If the moving track data includes the first track point, it indicates that the processing result obtained in step S306 is inaccurate, and at this time, the processing result may be corrected, where the processing result after the correction is: the movement track data belongs to the automobile, but not to the bicycle.

In the second case, if the number of first track points with a speed greater than the preset speed threshold included in the movement track data is greater than the first preset number, it can be verified that the movement track data does not belong to a bicycle, but belongs to an automobile.

It should be noted that, in this embodiment, the bicycle is classified into a motorcycle, an electric bicycle or a mechanical bicycle, and the first preset speed thresholds corresponding to different types of bicycles are different, and may be specifically set according to actual needs.

In case two, the type of the vehicle to which the movement trace data belongs includes an automobile.

Step S308, the step of verifying the processing result by using the class correction strategy comprises the following steps:

step S21, comparing the speed of each track point in the moving track data with a second preset speed threshold value, wherein the second preset speed threshold value is the lowest speed threshold value of the automobile;

and step S22, verifying whether the moving track data belongs to the automobile or not according to the number of second track points with the speed greater than a second preset speed threshold value contained in the moving track data.

In this embodiment, a second preset speed threshold is preset, which is the lowest speed threshold allowed for the bicycle to travel. Specifically, the determination may be performed according to the lowest speed limit identifier of the road segment to which the movement trajectory data belongs. If the road section has no lowest speed limit sign, a default value may be selected for processing, and this embodiment is not particularly limited.

Optionally, if the processing result indicates that the vehicle to which the moving trajectory data belongs is an automobile, the speed of each trajectory point in the moving trajectory data may be compared with a second preset threshold, so as to obtain the number of second trajectory points, of which the speed is smaller than the second preset threshold, included in each trajectory point. And then, whether the movement track data belongs to the automobile is verified according to the number.

Alternatively, the above-described case is a process of verifying a processing result of the automobile to which the movement trajectory belongs, in the case where the processing result has been obtained. If the processing result that the moving track belongs to the bicycle or the automobile at the same time is obtained, or the processing result that the moving track data does not belong to the bicycle or the automobile at the same time is obtained, the vehicle to which the moving track data belongs may be further confirmed by the method described in the above step S21 and step S22.

Optionally, in step S22, determining whether the movement track data belongs to an automobile according to the number of second track points included in the movement track data and having a speed greater than a second preset speed threshold includes the following steps:

if the comparison result is that the moving track data contains a second track point with the speed smaller than a second preset speed threshold value, verifying that the moving track data does not belong to the automobile;

or if the comparison result shows that the number of second track points with the speed smaller than a second preset speed threshold value in the moving track data is larger than a second preset number, the moving track data is verified not to belong to the automobile.

At this time, the following cases can be classified.

In the first case, if the moving track data includes a second track point whose speed is less than a second preset speed threshold, it can be verified that the moving track data does not belong to the automobile. If the second track point is included in the moving track data, it indicates that the processing result obtained in step S306 is inaccurate, and at this time, the processing result may be corrected, where the processing result after the correction is: the movement track data belongs to a bicycle, but not to an automobile.

In the second case, if the speed included in the movement trace data is less than the second preset speed threshold and the number of trace points is greater than the second preset number, it can be verified that the movement trace data does not belong to the car, but belongs to the bicycle.

In this embodiment, before determining the tool type to which the movement trajectory data belongs through the steps described in step S302 to step S306, a recognition model needs to be built and trained, and a specific process is described as follows:

firstly, obtaining training sample data, wherein the training sample data comprises a plurality of first track data, and each first track data comprises the following attribute data: ID identification information, longitude and latitude coordinate information of each track point, timestamp information of each track point, speed information of each track point and category information of a vehicle to which the first track data belongs;

and then, repeatedly training the Xgboost model by using the training sample data, and taking the Xgboost model after training as the recognition model when the Xgboost model meets the training precision.

Specifically, in the present embodiment, first, position information, speed information, time stamp information, and the like of a service provider who is riding a certain vehicle for a certain period of time may be acquired at a certain periodic frequency by a terminal device to which the service provider belongs or a portable sensor mounted on the terminal device, thereby obtaining a plurality of first trajectory data, each of which has a unique ID. While each first trajectory data is labeled with information of the category of the vehicle to which it belongs, for example, a car or a bicycle.

It should be noted that after the designated driving order is started, the data collected by the terminal device or the portable sensor carries identification information capable of indicating the type information of the vehicle to which the designated driving order belongs.

And then, performing feature extraction on each training sample data to obtain behavior feature data and time feature data of each training sample data. In addition, discretization and normalization processing can be performed on the behavior characteristic data by using a one-hot encoding method, so that the processed behavior characteristic data can be obtained.

Then, the Xgboost model may be trained by using the time characteristic data of each training sample data and the processed behavior characteristic data to obtain the recognition model.

After the recognition model is obtained through training, the type threshold of the recognition model can be adjusted, wherein the type threshold is one or more, and each type threshold corresponds to one type of vehicle.

In the present embodiment, the type threshold value is 0.5 by default, and after each training of the Xgboost model by training sample data, the type threshold value of the recognition model may be adjusted. For example, the technician enters the type threshold after adjustment, or adjusts the type threshold based on each training result of the Xgboost model through the neural network.

In this embodiment, after the Xgboost model is trained once by using the training sample data, test sample data may be further obtained, where the test sample data includes a plurality of second trajectory data, and each second trajectory data includes the following attribute data: ID identification information, longitude and latitude coordinate information of each track point, timestamp information of each track point, speed information of each track point and category information of a vehicle to which the second track data belongs.

After test sample data are obtained, the obtained identification model is used for processing the test sample data to obtain the category prediction result of each second track data.

And then comparing the class prediction result of each second track data with the class information of the vehicle to which the second track data belongs to determine target track data with wrong prediction in the plurality of second track data. And judging whether the Xgboost model meets the training precision or not according to the number of the target track data.

If so, taking the trained Xgboost model as the recognition model; otherwise, continuing to train the Xgboost model by using the training sample data.

After the target trajectory data with the wrong prediction in the plurality of second trajectory data is determined, a category correction strategy can be further determined based on the strategy determined by the behavior characteristic data of the target trajectory data.

In this embodiment, after the Xgboost model is trained once by using the training sample data to obtain the trained Xgboost model and the class correction strategy, the test sample data may be tested again by using the trained Xgboost model and the class correction strategy, so as to adjust the weight parameter of the Xgboost model or adjust the class correction strategy according to the test result.

As can be seen from the above description, in each training process, first, the Xgboost model is trained by using training sample data. And then, performing prediction processing on the test sample data by using the trained Xgboost model. And determining whether to continue training the Xgboost model according to the class prediction result. If yes, the category correction strategy can be determined after the training is finished. And after the class correction strategy is determined, testing the test sample data again by combining the Xgboost model after the training is finished and the class correction strategy, and determining whether to adjust the weight parameter of the Xgboost model or adjust the class correction strategy according to the class test result. By the processing mode, the prediction accuracy and precision of the model can be further ensured.

Fig. 5 is a flowchart illustrating a vehicle movement trajectory discrimination method of the present application. As shown in fig. 5, in the present embodiment, the main processing procedure of the method is described as follows:

a training stage: firstly, acquiring original data, and processing the original data to obtain training sample data, wherein the training sample data comprises a plurality of first track data, and each first track data comprises the following attribute data: ID identification information, longitude and latitude coordinate information of each track point, timestamp information of each track point, speed information of each track point and category information of a vehicle to which the first track data belongs. Extracting target characteristic data of each first track data, training an Xgboost model by using the target characteristic data of the first track data to obtain an identification model, and determining a class correction strategy of the identification model.

And (3) a testing stage: firstly, obtaining movement track data to be processed, and performing feature extraction on the movement track data to obtain target feature data of the movement track data. And predicting target characteristic data of the moving track data through the recognition model to obtain a processing result. And verifying or correcting the processing result by using a class correction strategy. The specific implementation process is as described above, and is not described herein again.

In this embodiment, the method described above can be applied to a designated driving platform.

In a designated driving report scenario, a service provider of a designated driving platform often obtains benefits through a false report, which is mostly completed by using mobility tools such as an electric bicycle. Therefore, in the present embodiment, by adopting the above method, whether the service provider generates the designated driving service can be effectively determined by identifying the vehicle corresponding to the movement trajectory data.

In the designated driving equity order scene, a service provider of a designated driving platform obtains a large amount of extra fee benefits in a multi-running mode after normal service, and based on the method, by adopting the method, the track data of the whole order can be identified in a segmented mode, and a cheating driver can be caught by combining a certain strategy.

In the embodiment, the problems of poor identification precision and low identification efficiency in the prior art when the vehicle to which the moving track belongs is identified can be solved by extracting the characteristics of the moving track data to obtain the target characteristic data.

Fig. 6 is a block diagram illustrating a vehicle movement trajectory differentiation apparatus of some embodiments of the present application, which implements functions corresponding to the steps performed by the above-described method. The device may be understood as the server or the processor of the server, or may be understood as a component that is independent of the server or the processor and implements the functions of the present application under the control of the server, and as shown in the figure, the vehicle movement track distinguishing device may include a first obtaining unit 610, a feature extracting unit 620 and a prediction processing unit 630.

A first obtaining unit 610, configured to obtain movement trajectory data to be identified, where the movement trajectory data includes attribute data of each trajectory point;

a feature extraction unit 620, configured to perform feature extraction on the moving trajectory data based on attribute data of each trajectory point to obtain target feature data, where the target feature data includes: behavior characteristic data of the movement trajectory data and/or time characteristic data of the movement trajectory data;

the prediction processing unit 630 is configured to perform prediction processing on the target feature data by using a recognition model to obtain a processing result, where the processing result is used to determine a type of a vehicle to which the movement trajectory data belongs.

Optionally, the behavioral characteristic data includes at least one of: the method comprises the following steps of (1) speed discrete distribution proportion, speed variance, minimum non-zero speed, maximum speed, average speed, maximum acceleration, minimum non-zero acceleration, average acceleration, the number of track points in a staying state and the total staying time of the track points in the staying state; the temporal characteristic data comprises at least one of: the mark information is used for representing whether the moving track data belongs to the congestion peak period or not, the time period to which the moving track data belongs and the duration of the moving track data.

Optionally, the attribute data includes coordinate information, timestamp information, and speed information; the feature extraction unit is configured to: and calculating the characteristic information of the moving track data according to the coordinate information, the timestamp information and the speed information of each track point in the moving track data to obtain the target characteristic data.

Optionally, the prediction processing unit is configured to: predicting the target characteristic data through the identification model to obtain a prediction result, wherein the prediction result is used for representing probability information of various vehicles to which the movement track data belongs; comparing the prediction result with corresponding type thresholds, wherein different types of vehicles correspond to different type thresholds; and if the comparison result is that the prediction result is greater than or equal to the corresponding type threshold, obtaining a processing result of the transportation tool corresponding to the corresponding type threshold to which the movement track data belongs.

Optionally, the apparatus further comprises: and the verification unit is used for verifying the processing result by utilizing a class correction strategy, wherein the class correction strategy is a strategy determined based on behavior characteristic data of the movement track data.

Optionally, the type of vehicle comprises: a bicycle; the bicycle comprises: motorcycles, electric bicycles, or mechanical bicycles; the authentication unit includes: the first comparison module is used for comparing the speed of each track point in the moving track data with a first preset speed threshold, wherein the first preset speed threshold is the highest speed threshold of the bicycle; and the first verification module is used for verifying whether the moving track data belongs to the bicycle or not according to the number of the first track points of which the speed is greater than a first preset speed threshold value, wherein the first track points are contained in the moving track data.

Optionally, the first authentication module is configured to: if the comparison result shows that the moving track data comprises a first track point with the speed greater than a first preset speed threshold value, verifying that the moving track data does not belong to the bicycle; or if the comparison result shows that the number of the first track points with the speed greater than the preset speed threshold value contained in the moving track data is greater than the first preset number, the moving track data is verified not to belong to the bicycle.

Optionally, the type of vehicle comprises: an automobile; the authentication unit further includes: the second comparison module is used for comparing the speed of each track point in the moving track data with a second preset speed threshold, wherein the second preset speed threshold is the lowest speed threshold of the automobile; and the second verification module is used for determining whether the moving track data belongs to the automobile or not according to the number of second track points of which the speed is greater than a second preset speed threshold value and contained in the moving track data.

Optionally, the second authentication module is configured to: if the comparison result is that the moving track data contains a second track point with the speed smaller than a second preset speed threshold value; or if the comparison result shows that the number of second track points with the speed smaller than a second preset speed threshold value in the moving track data is larger than a second preset number, determining that the moving track data does not belong to the automobile.

Optionally, the apparatus further comprises: a second obtaining unit, configured to obtain training sample data, where the training sample data includes multiple first trajectory data, and each first trajectory data includes the following attribute data: ID identification information, longitude and latitude coordinate information of each track point, timestamp information of each track point, speed information of each track point and category information of a vehicle to which the first track data belongs; and the training unit is used for repeatedly training the Xgboost model by using the training sample data, and taking the trained Xgboost model as the recognition model when the Xgboost model meets the training precision.

Optionally, the training unit is configured to: extracting features of each training sample data to obtain behavior feature data and time feature data of each training sample data; and training the Xgboost model by using the behavior characteristic data and the time characteristic data of each training sample data to obtain the recognition model.

Optionally, the apparatus is further configured to: after the recognition model is obtained through training, adjusting the type threshold of the recognition model, wherein the type threshold is one or more, and each type threshold corresponds to one type of vehicle.

Optionally, the apparatus is further configured to: after the Xgboost model is trained for one time by using the training sample data, obtaining test sample data, wherein the test sample data comprises a plurality of second track data, and each second track data comprises the following attribute data: ID identification information, longitude and latitude coordinate information of each track point, timestamp information of each track point, speed information of each track point and category information of a vehicle to which the second track data belongs; processing the test sample data by using the obtained identification model to obtain a category prediction result of each second track data; comparing the category prediction result of each second trajectory data with the category information of the vehicle to which the second trajectory data belongs to determine target trajectory data with wrong prediction in the plurality of second trajectory data; judging whether the Xgboost model meets the training precision or not according to the number of the target track data; if so, taking the trained Xgboost model as the recognition model; otherwise, continuing to train the Xgboost model by using the training sample data.

Optionally, the apparatus is further configured to: after the target track data with the wrong prediction in the plurality of second track data are determined, determining a category correction strategy based on the strategy determined by the behavior characteristic data of the target track data.

The modules (or units) described above may be connected or in communication with each other via a wired or wireless connection. The wired connection may include a metal cable, an optical cable, a hybrid cable, etc., or any combination thereof. The wireless connection may comprise a connection over a LAN, WAN, bluetooth, ZigBee, NFC, or the like, or any combination thereof. Two or more modules may be combined into a single module, and any one module may be divided into two or more units.

It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the system and the apparatus described above may refer to corresponding processes in the method embodiments, and are not described in detail in this application. In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. The above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is merely a logical division, and there may be other divisions in actual implementation, and for example, a plurality of modules or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or modules through some communication interfaces, and may be in an electrical, mechanical or other form.

The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.

The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a non-volatile computer-readable storage medium executable by a processor. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a U disk, a removable hard disk, a ROM, a RAM, a magnetic disk, or an optical disk.

The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A vehicle movement track distinguishing method is characterized by comprising the following steps:

acquiring moving track data to be identified, wherein the moving track data comprises attribute data of each track point;

based on the attribute data of each track point, performing feature extraction on the moving track data to obtain target feature data, wherein the target feature data comprises: behavior characteristic data of the movement trajectory data and/or time characteristic data of the movement trajectory data;

and performing prediction processing on the target characteristic data by using an identification model to obtain a processing result, wherein the processing result is used for determining the type of a vehicle to which the movement track data belongs.

2. The method of claim 1, wherein the behavior feature data comprises at least one of: the method comprises the following steps of (1) speed discrete distribution proportion, speed variance, minimum non-zero speed, maximum speed, average speed, maximum acceleration, minimum non-zero acceleration, average acceleration, the number of track points in a staying state and the total staying time of the track points in the staying state;

the temporal characteristic data comprises at least one of: the mark information is used for representing whether the moving track data belongs to the congestion peak period or not, the time period to which the moving track data belongs and the duration of the moving track data.

3. The method according to claim 1 or 2, wherein the attribute data includes coordinate information, time stamp information, and speed information;

based on the attribute data of each track point, performing feature extraction on the moving track data to obtain target feature data, wherein the target feature data comprises:

and calculating the characteristic information of the moving track data according to the coordinate information, the timestamp information and the speed information of each track point in the moving track data to obtain the target characteristic data.

4. The method of claim 1, wherein the performing a prediction process on the target feature data using a recognition model to obtain a processing result comprises:

predicting the target characteristic data through the identification model to obtain a prediction result, wherein the prediction result is used for representing probability information of various vehicles to which the movement track data belongs;

comparing the prediction result with corresponding type thresholds, wherein different types of vehicles correspond to different type thresholds;

and if the comparison result is that the prediction result is greater than or equal to the corresponding type threshold, obtaining a processing result of the transportation tool corresponding to the corresponding type threshold to which the movement track data belongs.

5. The method of claim 1, further comprising:

and verifying the processing result by utilizing a category correction strategy, wherein the category correction strategy is a strategy determined based on behavior characteristic data of the movement track data.

6. The method of claim 5, wherein the type of vehicle comprises: a bicycle; the bicycle comprises: motorcycles, electric bicycles, or mechanical bicycles;

the verifying the processing result by using the class correction strategy comprises the following steps:

comparing the speed of each track point in the moving track data with a first preset speed threshold, wherein the first preset speed threshold is the highest speed threshold of the bicycle;

and verifying whether the moving track data belongs to the bicycle or not according to the number of first track points with the speed greater than a first preset speed threshold value contained in the moving track data.

7. The method according to claim 6, wherein verifying whether the movement trajectory data belongs to the bicycle according to the number of first trajectory points included in the movement trajectory data and having a speed greater than a first preset speed threshold comprises:

if the comparison result shows that the moving track data comprises a first track point with the speed greater than a first preset speed threshold value, verifying that the moving track data does not belong to the bicycle; alternatively, the first and second electrodes may be,

and if the comparison result shows that the number of the first track points with the speed greater than the preset speed threshold value in the moving track data is greater than the first preset number, verifying that the moving track data does not belong to the bicycle.

8. The method of claim 5, wherein the type of vehicle comprises: an automobile;

comparing the speed of each track point in the moving track data with a second preset speed threshold, wherein the second preset speed threshold is the lowest speed threshold of the automobile;

and verifying whether the moving track data belongs to the automobile or not according to the number of second track points with the speed greater than a second preset speed threshold value contained in the moving track data.

9. The method according to claim 8, wherein determining whether the movement track data belongs to the automobile according to the number of second track points with the speed greater than a second preset speed threshold value, which are contained in the movement track data, comprises:

if the comparison result is that the moving track data contains a second track point with the speed smaller than a second preset speed threshold value, verifying that the moving track data does not belong to the automobile; or

And if the comparison result shows that the number of the second track points with the speed smaller than the second preset speed threshold value in the moving track data is larger than the second preset number, verifying that the moving track data does not belong to the automobile.

10. The method of claim 1, further comprising:

acquiring training sample data, wherein the training sample data comprises a plurality of first track data, and each first track data comprises the following attribute data: ID identification information, longitude and latitude coordinate information of each track point, timestamp information of each track point, speed information of each track point and category information of a vehicle to which the first track data belongs;

and repeatedly training the Xgboost model by using the training sample data, and taking the Xgboost model after training as the recognition model when the Xgboost model meets the training precision.

11. The method of claim 10, wherein training an Xgboost model using the training sample data to obtain the recognition model comprises:

extracting features of each training sample data to obtain behavior feature data and time feature data of each training sample data;

and training the Xgboost model by using the behavior characteristic data and the time characteristic data of each training sample data to obtain the recognition model.

12. The method of claim 10 or 11, wherein after training the recognition model, the method further comprises:

and adjusting the type threshold of the identification model, wherein the type threshold is one or more, and each type threshold corresponds to one type of vehicle.

13. The method according to claim 10, wherein after one training of the Xgboost model with the training sample data, the method further comprises:

obtaining test sample data, wherein the test sample data comprises a plurality of second track data, and each second track data comprises the following attribute data: ID identification information, longitude and latitude coordinate information of each track point, timestamp information of each track point, speed information of each track point and category information of a vehicle to which the second track data belongs;

processing the test sample data by using the obtained identification model to obtain a category prediction result of each second track data;

comparing the category prediction result of each second trajectory data with the category information of the vehicle to which the second trajectory data belongs to determine target trajectory data with wrong prediction in the plurality of second trajectory data;

judging whether the Xgboost model meets the training precision or not according to the number of the target track data;

14. The method of claim 13, wherein after determining the mispredicted target trajectory data of the second plurality of trajectory data, the method further comprises:

and determining a category correction strategy based on the strategy determined by the behavior characteristic data of the target track data.

15. A vehicle movement locus discrimination device, characterized by comprising:

the device comprises a first acquisition unit, a second acquisition unit and a control unit, wherein the first acquisition unit is used for acquiring movement track data to be identified, and the movement track data comprises attribute data of each track point;

the feature extraction unit is configured to perform feature extraction on the movement track data based on attribute data of each track point to obtain target feature data, where the target feature data includes: behavior characteristic data of the movement trajectory data and/or time characteristic data of the movement trajectory data;

and the prediction processing unit is used for performing prediction processing on the target characteristic data by using the recognition model to obtain a processing result, wherein the processing result is used for determining the type of the vehicle to which the movement track data belongs.

16. The apparatus of claim 15, wherein the behavior feature data comprises at least one of: the method comprises the following steps of (1) speed discrete distribution proportion, speed variance, minimum non-zero speed, maximum speed, average speed, maximum acceleration, minimum non-zero acceleration, average acceleration, the number of track points in a staying state and the total staying time of the track points in the staying state;

17. The apparatus according to claim 15 or 16, wherein the attribute data includes coordinate information, time stamp information, and speed information;

the feature extraction unit is configured to:

18. The apparatus of claim 15, wherein the prediction processing unit is configured to:

19. The apparatus of claim 15, further comprising:

and the verification unit is used for verifying the processing result by utilizing a class correction strategy, wherein the class correction strategy is a strategy determined based on behavior characteristic data of the movement track data.

20. The apparatus of claim 19, wherein the type of vehicle comprises: a bicycle; the bicycle comprises: motorcycles, electric bicycles, or mechanical bicycles;

the authentication unit includes:

the first comparison module is used for comparing the speed of each track point in the moving track data with a first preset speed threshold, wherein the first preset speed threshold is the highest speed threshold of the bicycle;

and the first verification module is used for verifying whether the moving track data belongs to the bicycle or not according to the number of the first track points of which the speed is greater than a first preset speed threshold value, wherein the first track points are contained in the moving track data.

21. The apparatus of claim 20, wherein the first authentication module is configured to:

22. The apparatus of claim 19, wherein the type of vehicle comprises: an automobile;

the authentication unit further includes:

the second comparison module is used for comparing the speed of each track point in the moving track data with a second preset speed threshold, wherein the second preset speed threshold is the lowest speed threshold of the automobile;

and the second verification module is used for determining whether the moving track data belongs to the automobile or not according to the number of second track points of which the speed is greater than a second preset speed threshold value and contained in the moving track data.

23. The apparatus of claim 22, wherein the second authentication module is configured to:

if the comparison result is that the moving track data contains a second track point with the speed smaller than a second preset speed threshold value; or

And if the comparison result shows that the number of the second track points with the speed smaller than a second preset speed threshold value in the moving track data is larger than a second preset number, determining that the moving track data does not belong to the automobile.

24. The apparatus of claim 15, further comprising:

a second obtaining unit, configured to obtain training sample data, where the training sample data includes multiple first trajectory data, and each first trajectory data includes the following attribute data: ID identification information, longitude and latitude coordinate information of each track point, timestamp information of each track point, speed information of each track point and category information of a vehicle to which the first track data belongs;

and the training unit is used for repeatedly training the Xgboost model by using the training sample data, and taking the trained Xgboost model as the recognition model when the Xgboost model meets the training precision.

25. The apparatus of claim 24, wherein the training unit is configured to:

26. The apparatus of claim 24 or 25, wherein the apparatus is further configured to:

after the recognition model is obtained through training, adjusting the type threshold of the recognition model, wherein the type threshold is one or more, and each type threshold corresponds to one type of vehicle.

27. The apparatus of claim 24, wherein the apparatus is further configured to:

after the Xgboost model is trained for one time by using the training sample data, obtaining test sample data, wherein the test sample data comprises a plurality of second track data, and each second track data comprises the following attribute data: ID identification information, longitude and latitude coordinate information of each track point, timestamp information of each track point, speed information of each track point and category information of a vehicle to which the second track data belongs;

28. The apparatus of claim 27, wherein the apparatus is further configured to:

after the target track data with the wrong prediction in the plurality of second track data are determined, determining a category correction strategy based on the strategy determined by the behavior characteristic data of the target track data.

29. An electronic device, comprising: a processor, a storage medium and a bus, the storage medium storing machine-readable instructions executable by the processor, the processor and the storage medium communicating via the bus when the electronic device is running, the processor executing the machine-readable instructions to perform the steps of the method for vehicle movement trajectory differentiation according to any one of claims 1 to 14.

30. A computer-readable storage medium, characterized in that a computer program is stored thereon, which, when being executed by a processor, carries out the steps of the method of vehicle movement trajectory differentiation according to any one of claims 1 to 14.