HK40065988B - Trajectory detection method and apparatus, electronic device and storage medium - Google Patents

Description

Track detection method and device, electronic equipment and storage medium

Technical Field

The embodiment of the application relates to the technical field of intelligent travel, in particular to a track detection method and device, electronic equipment and a storage medium.

Background

In the technical fields of intelligent transportation and the like, in order to ensure the accuracy and timeliness of map or road network information, effective track data needs to be acquired to update the map or road network information. In some cases, the trajectory data provider may perform a cheating process on the original trajectory data to generate cheated trajectory data for some reasons, and therefore, before updating the map or road network information by using the trajectory data, it is first necessary to detect the trajectory data to remove abnormal trajectory data.

Currently, an abnormal trajectory is determined by determining the similarity between two trajectories, for example by calculating the distance between coordinate sequences of the two trajectories; or determining the similarity between the two tracks based on the similarity measure of the neural network; or determining the similarity between the two tracks based on the similarity calculation of the semantic information.

However, the above methods have problems of large calculation amount and inaccurate calculation when determining the similarity between two tracks.

Disclosure of Invention

The embodiment of the application provides a track detection method and device, electronic equipment and a storage medium, so that the calculation amount of track detection is reduced, and the detection accuracy is improved.

In a first aspect, an embodiment of the present application provides a trajectory detection method, including:

constructing N tracks based on M track points reported in a preset time period, wherein M, N are positive integers greater than 1;

determining a road section matched with each track in the N tracks;

determining a key road section of each track according to at least one of the attribute information of the road section matched with each track and the motion information of the track point corresponding to the road section;

and determining abnormal tracks in the N tracks according to the key road sections of each track in the N tracks.

In a second aspect, an embodiment of the present application provides a trajectory detection apparatus, including:

the construction unit is used for constructing N tracks based on M track points reported in a preset time period, wherein M, N are positive integers larger than 1;

the road section determining unit is used for determining a road section matched with each track in the N tracks;

the key road section determining unit is used for determining the key road section of each track according to at least one of the attribute information of the road section matched with each track and the motion information of the track point corresponding to the road section;

and the abnormal track determining unit is used for determining an abnormal track in the N tracks according to the key road section of each track in the N tracks.

In some embodiments, the critical road segment determining unit is specifically configured to determine, for an ith track of the N tracks, a first importance of each of K road segments according to attribute information of each of the K road segments matched with the ith track, where i is a positive integer from 1 to N; determining a second importance of each road section in the K road sections according to the motion information of the track point corresponding to each road section in the K road sections; and determining the key road section of the ith track according to at least one of the first importance and the second importance of each road section in the K road sections.

In some embodiments, the attribute information of the road segment includes at least one of a number of road segments connected to the road segment, a function level of the road segment, an angle between the road segment and a next adjacent road segment, and a number of road segments within a preset range around the road segment, and the key road segment determining unit is specifically configured to determine, for a jth road segment of the K road segments, at least one of a number of first road segments connected to the jth road segment, a function level of the jth road segment, an angle between the jth road segment and a next adjacent road segment, and a number of second road segments within a preset range around the jth road segment, where j is a positive integer from 1 to K; and determining the first importance of the jth road section according to at least one of the first road section number, the function level, the angle and the second road section number.

In some embodiments, the critical road segment determining unit is specifically configured to determine a weighted sum of at least one of the first road segment number, the function level, the angle, and the second road segment number as the first importance of the jth road segment.

In some embodiments, the critical road segment determining unit is specifically configured to perform a normalization process on at least one of the first road segment number, the function level, the angle, and the second road segment number; determining a weighted sum of at least one of the normalized first road segment number, the normalized function level, the normalized angle, and the normalized second road segment number as a first importance of the jth road segment.

In some embodiments, the critical road segment determining unit is specifically configured to determine a first direction angle of the jth road segment and a second direction angle of the next adjacent road segment, respectively; if a first difference between the first direction angle and the second direction angle is smaller than or equal to a first preset value, determining the first difference as an angle between the jth road section and the next adjacent road section; and if the first difference is larger than the first preset value, determining a second difference between a second preset value and the first difference as an angle between the jth road section and the next adjacent road section.

In some embodiments, the key segment determining unit is specifically configured to determine, for a jth segment of the K segments, that a second importance of the jth segment is a first numerical value if motion information of at least one of track points corresponding to the jth segment is greater than a preset threshold, where j is a positive integer from 1 to K; and if the motion information of each track point corresponding to the jth road section is less than or equal to the preset threshold value, determining that the second importance of the jth road section is a second numerical value, wherein the second numerical value is less than the second numerical value.

In some embodiments, the motion information of the trace point includes at least one of a velocity, an acceleration, a direction angle, and a rotation angle.

Optionally, the first value is 1, and the second value is 0.

In some embodiments, the critical segment determining unit is specifically configured to determine, as the critical segment of the ith track, a segment of the K segments, where the first importance is greater than a preset threshold and the second importance is equal to a first numerical value.

In some embodiments, the abnormal trajectory determining unit is specifically configured to determine, according to the key road segment of each of the N trajectories, a similarity between every two of the N trajectories; and determining the track with the similarity larger than a preset value in the N tracks as the abnormal track.

In some embodiments, the abnormal trajectory determining unit is specifically configured to determine, for a first trajectory and a second trajectory of the N trajectories, a similarity between a key segment of the first trajectory and a key segment of the second trajectory, where the first trajectory and the second trajectory are both any one of the N trajectories, and the first trajectory is different from the second trajectory; determining the similarity between the key road sections of the first track and the second track as the similarity between the first track and the second track.

In some embodiments, the abnormal trajectory determination unit is specifically configured to determine a distance between a critical segment of the first trajectory and a critical segment of the second trajectory; and determining the similarity between the key road section of the first track and the key road section of the second track according to the distance.

In some embodiments, the distance is any one of an edit distance, a cosine distance, and a jaccard distance.

In some embodiments, the constructing unit is specifically configured to arrange, according to the time information and the identifier included in the track points reported in the preset time period, the track points under the same identifier according to a time sequence to form a track, so as to obtain the N tracks.

In some embodiments, the construction unit is specifically configured to remove an abnormal trace point from the M trace points to obtain P normal trace points, where P is a positive integer greater than 1 and less than or equal to M; and constructing the N tracks based on the P normal track points.

In a third aspect, a computing device is provided that includes a processor and a memory. The memory is configured to store a computer program, and the processor is configured to call and execute the computer program stored in the memory to perform the method in the first aspect or each implementation manner thereof.

In a fourth aspect, a chip is provided for implementing the method in any one of the above first aspects or implementations thereof. Specifically, the chip includes: a processor, configured to call and run a computer program from a memory, so that a device on which the chip is installed performs the method according to any one of the above first aspects or the implementation manners thereof.

In a fifth aspect, a computer-readable storage medium is provided for storing a computer program, the computer program causing a computer to perform the method of any one of the above aspects or implementations thereof.

A sixth aspect provides a computer program product comprising computer program instructions for causing a computer to perform the method of any of the above aspects or implementations thereof.

In a seventh aspect, a computer program is provided, which, when run on a computer, causes the computer to perform the method of any one of the above first aspects or implementations thereof.

In summary, the present application constructs N tracks based on M track points reported within a preset time period, and M, N are positive integers greater than 1; determining a road section matched with each track in the N tracks; determining a key road section of each track according to at least one of attribute information of the road section matched with each track and motion information of a track point corresponding to the road section; and determining abnormal tracks in the N tracks according to the key road sections of each track in the N tracks. Namely, in the embodiment of the application, the abnormal track is determined by determining the key road sections of the track, and because the number of the key road sections of the track is small and the key road sections of the track can represent the characteristics of the track, the data volume to be processed can be reduced when abnormal track detection is performed on the basis of the key road sections of the track, and further the detection efficiency is improved.

Drawings

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

Fig. 1 is a schematic view of an application scenario according to an embodiment of the present application;

fig. 2 is a schematic flow chart of a track detection method according to an embodiment of the present application;

FIG. 3 is a schematic diagram of a track;

fig. 4 is a schematic diagram of track point correction according to an embodiment of the present application;

FIG. 5 is a schematic diagram of road network matching according to an embodiment of the present application;

FIG. 6 is a diagram of a road example according to an embodiment of the present application;

fig. 7 is a schematic flowchart of a track detection method according to an embodiment of the present application;

fig. 8 is a schematic structural diagram of a track detection apparatus according to an embodiment of the present application;

fig. 9 is a schematic block diagram of a computing device provided by an embodiment of the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application.

The embodiment of the application is applied to the technical field of maps and the like.

It should be understood that, in the present embodiment, "B corresponding to a" means that B is associated with a. In one implementation, B may be determined from a. It should also be understood that determining B from a does not mean determining B from a alone, but may be determined from a and/or other information.

In the description of the present application, "plurality" means two or more than two unless otherwise specified.

In addition, in order to facilitate clear description of technical solutions of the embodiments of the present application, in the embodiments of the present application, terms such as "first" and "second" are used to distinguish the same items or similar items having substantially the same functions and actions. Those skilled in the art will appreciate that the terms "first," "second," etc. do not denote any order or quantity, nor do the terms "first," "second," etc. denote any order or importance.

The embodiment of the application can be applied to the fields of maps, traffic, automatic driving, vehicle-mounted and the like.

An Intelligent Transportation System (ITS), also called Intelligent Transportation System (Intelligent Transportation System), is a comprehensive Transportation System which effectively and comprehensively applies advanced scientific technologies (information technology, computer technology, data communication technology, sensor technology, electronic control technology, automatic control theory, operational research, artificial intelligence and the like) to Transportation, service control and vehicle manufacturing, strengthens the relation among vehicles, roads and users, and thus forms a safety-guaranteeing, efficiency-improving, environment-improving and energy-saving comprehensive Transportation System.

The related concepts related to the embodiments of the present application are introduced.

GPS track points: the GPS module equipment receives GPS signals in real time to perform positioning and generate coordinate points, the coordinate points are transmitted back to the background through a network, usually, the track is reported to a channel provider by the end-to-end equipment, and the channel provider performs anonymity and uploads the track to a big data buyer after compliance processing.

GPS track: the GPS track points are connected together according to the time sequence to form a track line (string).

Road updating: and updating the attributes of the elements in the map by using the tracks or pictures, adding deleted elements and the like.

Link (link): the method comprises the steps of abstracting a real road network in an electronic map, abstracting each road network into a link, marking the position of the link by a coordinate point string, and marking the attributes (such as vehicle information, traffic signs, number of lanes, length, width and the like) on the road section by a series of attributes.

Track cheating: after receiving the GPS track points on the intelligent equipment, the channel trader shifts the track of one piece of equipment to generate a plurality of tracks and uploads the tracks to the track data buyer.

Fig. 1 is a schematic view of an application scenario in an embodiment of the present application, and as shown in fig. 1, the application scenario includes: a plurality of terminal devices 101, a distributor device 102 and a server 103.

In the application scenario shown in fig. 1, the terminal devices 101 send collected track point data, for example, GPS track point data, to the distributor device 102. The distributor device 102 performs anonymization and compliance processing on the positioning track data, optionally, the distributor device 102 may also perform cheating processing on track points reported by the terminal device 101 to increase data volume, for example, increase noise, perform offset processing, and generate cheating data. Then, the distributor device 102 reports the processed positioning track data to the server 103. The server 103 detects the positioning track data reported by the distributor equipment 102 according to the track detection method provided by the embodiment of the application. Optionally, the server 103 may also update data such as a map or a road network by using the positioning track data after the detection is qualified. Optionally, the data purchaser may additionally follow up with the distributor according to the detection result of the server 103.

That is, in the scenario shown in fig. 1, the positioning track data is processed by the distributor device 102 and then reported to the server 103.

In some embodiments, the plurality of terminal devices 101 in the embodiment of the present application may be intelligent devices under the same channel provider, or may be intelligent devices under different channel providers. The terminal device 101 is mainly used for positioning and forming track points.

Optionally, the terminal device 101 may be a vehicle-mounted device, such as an intelligent automobile data recorder, a car machine, a rearview mirror, and the like. Optionally, the terminal device 101 may also be other devices having a positioning function, such as a smart phone, a tablet computer (Pad), a computer with a wireless transceiving function, a Virtual Reality (VR) user device, an Augmented Reality (AR) user device, and the like, which are not limited herein.

The distributor device 102 may be a server, or may be other computing devices, for example, an intelligent terminal, and the like.

In some embodiments, the server 103 may be one or more. When the servers 103 are multiple, at least two servers 103 exist for providing different services, and/or at least two servers 103 exist for providing the same service, for example, the same service is provided in a load balancing manner, which is not limited in the embodiment of the present application. The server 103 may be an independent physical server 103, a server 103 cluster or a distributed system formed by a plurality of physical servers 103, or a cloud server 103 providing basic cloud computing services such as a cloud service, a cloud database, cloud computing, a cloud function, cloud storage, a Network service, cloud communication, a middleware service, a domain name service, a security service, a CDN (Content Delivery Network), a big data and artificial intelligence platform, and the like. The server 103 may also become a node of the blockchain.

It should be noted that the application scenarios in the embodiment of the present application include, but are not limited to, that shown in fig. 1, for example, the terminal device 101 may also directly report the positioning track data to the server 103 after performing anonymization, compliance and cheating on the positioning track data, and omit the distributor device 102.

At present, when a road is updated by using track data of mass intelligent equipment or real world laws are mined by using the track data, track original data are particularly important, if a cheating track exists, a false track not only influences the accuracy of data mining, but also influences the efficiency of crowdsourcing and updating the road of the equipment, the updating period and even causes updating errors, so that the cheating track needs to be detected, and the quality and the cost are ensured. At present, the track data does not have a unique device identifier, so that detection needs to be performed through similarity between tracks.

The current track similarity detection method is mainly divided into 3 types, and the first type is calculated by the distance between two track coordinate sequences; a second class of neural network-based similarity measures; the fourth category is similarity calculation based on semantic information.

Based on the distance calculation of the two track coordinate sequences, the distance calculation method comprises the following steps: the Euclidean Distance, the Hausdorff Distance, the LCSS (Long Common Subsequence), the EPR, the EDR (Edit Distance on Real), the DTW (Dynamic Time Warping), and the elliptic indefinite motion are measured on the basis of combining the Euclidean Distance, and are calculated by using coordinate points between space-Time relationship matching tracks.

The similarity measurement method based on the neural network is to utilize an embedded vector to identify tracks by utilizing a deep learning algorithm and calculate the similarity between the tracks.

The similarity calculation method based on semantic information calculates information such as a stop point and a POI (point of interest) on a track as semantic information.

However, in the case of low-precision trajectory data or trajectory data drifting and confusion, the above-mentioned similarity measurement method based on neural network and the similarity calculation method based on semantic information have a large deviation, and two cheating trajectories, in which after one of the two trajectories is added with a partial skip point, semantic information and neural network serialization information change greatly, resulting in a large difference in final results.

In the distance calculation method based on the two track coordinate sequences, when the cheating track is a segment of the original track, a large error occurs, so that part of the cheating track cannot be identified. Meanwhile, in the face of noise data, the noise resistance is poor, the track quality is inherently poor when equipment such as a driving recorder and the like is used in urban canyons, and in addition, the track is difficult to identify due to cheating of tasks.

In addition, the methods are low in calculation efficiency, low in calculation speed and high in complexity, and in a service scene of crowdsourcing of equipment, the track data volume is large and many, so that the calculation resource consumption is large.

In order to solve the problems of inaccurate detection and large calculation amount in the conventional track data detection, the method and the device determine the key road section of the track according to at least one of the attribute information of the road section matched with the track and the motion information of the track point corresponding to the road section, and determine the abnormal track according to the key road section of the track, so that the calculation amount of the track data detection is reduced, and the detection accuracy is improved.

The technical solutions of the embodiments of the present application are described in detail below with reference to some embodiments. The following several embodiments may be combined with each other and may not be described in detail in some embodiments for the same or similar concepts or processes.

Fig. 2 is a schematic flow chart of a trajectory detection method according to an embodiment of the present application, where an execution main body of the embodiment of the present application is a device having a trajectory detection function, for example, a trajectory detection device, and the trajectory detection device may be a part of the server 101 shown in fig. 1 or the server 101. For convenience of description, the following embodiment takes the execution subject as the server 101 as an example.

As shown in fig. 3, the trajectory detection method according to the embodiment of the present application includes the following steps:

s201, constructing N tracks based on M track points reported in a preset time period.

M, N are positive integers greater than 1, M is greater than N, and each track comprises at least two track points.

The track point of the embodiment of the application is also called a positioning point, namely, the movement position point of the terminal equipment in the movement process of the terminal equipment.

The embodiment of the application does not limit the positioning system, for example, the positioning system can be a GPS (global positioning system), a Beidou positioning system and the like.

If the positioning system used in the embodiment of the present application is a GPS positioning system, the track points are also referred to as GPS track points.

If the positioning system used in the embodiment of the application is a Beidou positioning system, the track points are also called Beidou track points.

Trajectory, which is a type of spatio-temporal data, refers to a moving segment of an object in space, and is usually represented as a curve made up of a sequence of discrete trajectory points, as shown in fig. 3. Where the track point pi = (lat, lng, t), indicating that the object is located at the geographic coordinate position (lat, lng) at time t, where lat and lng represent latitude and longitude, respectively.

Taking the application scenario shown in fig. 1 as an example, the terminal device 101 sends the acquired track point data to the distributor device 102. The distributor device 102 anonymizes the trace point data, performs compliance processing, and sends the processed trace point data to the server 103. Optionally, when the distributor device 102 performs data processing, it may also perform cheating processing on the trace point data reported by the terminal device 101 to increase the data volume to obtain more returns, for example, increase noise, perform offset and other processing, and generate cheating data. And then, the channel provider equipment 102 reports the processed track point data to the server 103. The server 103 detects the track point data reported by the distributor equipment 102 according to the track detection method provided by the embodiment of the application.

In some embodiments, the terminal device 101 sends the trace point data to the distributor device 102 in real time, and the distributor device 102 reports the processed trace point data to the server 103 according to a preset time period.

In some embodiments, the terminal device 101 reports the collected trajectory point data to the distributor device 102 according to a preset time period. The distributor device 102 processes the track point data and sends the processed track point data to the server 103 in real time.

That is, the trajectory point data obtained by the server 103 is the trajectory point data within a preset time period. The specific value of the preset time period is not limited in the embodiment of the present application, and is, for example, 10 minutes, 5 minutes, and the like.

In some embodiments, the terminal device 101 may also directly report the track point data to the server 103 without passing through the intermediate distributor device 102.

And after obtaining the M track points reported in the preset time period, the server constructs N tracks based on the M track points.

Each track point of the embodiment of the application comprises time information and a mark, wherein the time information can be understood as the time when the terminal equipment is located at the track point, and the mark can be understood as a track mark or an equipment mark and is used for indicating which track the track point belongs to. When a track is constructed, the method is constructed based on time information and marks of track points, and specifically comprises the following steps:

S201-A, arranging the track points under the same identification according to a time sequence to form a track according to time information and the identification included in the reported track points in a preset time period, and obtaining N tracks.

Specifically, according to the identifiers included in the trace points, the trace points under the same identifier are divided into one trace point group, so that the obtained M trace points can be divided into N trace point groups. Aiming at each track point group in the N track point groups, sequencing all track points in the track point group according to time information and position information, drawing a track corresponding to the track point group, and further obtaining N tracks.

In some embodiments, in the track point acquisition process, due to reasons such as network or equipment, there is a problem of inaccurate acquisition, and therefore, in order to improve the construction accuracy of the track, before constructing the track, the embodiment of the present application performs preprocessing on the obtained M track points.

That is, before executing the above S201, the embodiment of the present application further includes the following preprocessing steps:

s200, eliminating abnormal track points in the M track points to obtain P normal track points.

Wherein, P is a positive integer greater than 1 and less than or equal to M.

In the embodiment of the present application, a manner of rejecting an abnormal track point from the M track points includes at least one of the following examples.

Example 1, trace points without time information and/or without coordinate information and/or without identification in the M trace points are culled.

Example 2, among the trace points, the trace point with time information being confused is corrected, for example, as shown in fig. 4, when the time information at point b is wrong, correction can be performed by using a point a and a point c before and after the point b.

Illustratively, the time information correction is performed by the following formula (1):

Tb = Ta + (Tc-Ta)* （dis(a,b)/dis(a,c)）（1）

where Tb is time information of corrected point b, Ta is time information of point a, Tc is time information of point c, dis (a, b) is a distance between point a and point b, and may be determined from coordinates (xa, ya) of point a and coordinates (xb, yb) of point b, dis (a, c) is a distance between point a and point c, and may be determined from coordinates (xa, ya) of point a and coordinates (xc, yc) of point c. The point with wrong time information in the M track points can be corrected according to the formula (1).

Example 3, if all attributes of the front and rear track points in the same track point group are consistent, the rear track point is deleted.

It should be noted that, in the above S200, the mode of removing the abnormal track point from the M track points to obtain the P normal track points may include other modes in addition to the above examples, which is not limited in this embodiment of the present application.

According to the mode, the server rejects abnormal track points in the M track points to obtain P normal track points, and then constructs N tracks based on the P normal track points. Based on the P normal track points, the process of constructing the N tracks is the same as the manner of S201-a, and is described with reference to the description of S201-a, which is not repeated herein.

After obtaining N tracks corresponding to the M track points according to the above steps, the following step S202 is executed.

S202, determining the road section matched with each track in the N tracks.

Road network data is composed of a plurality of road segments (links), which may be understood as the center lines of roads and may represent a section of a road.

According to the steps, after the N tracks are obtained, the N tracks are matched with the road network, and a road section (link) matched with each track in the N tracks can be obtained.

The method for determining the road section matched with each track in the N tracks is not limited in the embodiment of the application.

In a possible implementation manner, the HMM algorithm may be used to obtain the corresponding road segment that is adsorbed by the track, and obtain the time sequence road segment string corresponding to the track. And traversing each track point on the track, and calculating a road section closest to each track point to obtain the relation between the track point and the road section.

For example, as shown in fig. 5, by road network matching, the original track is matched with the road network data, and the road segments matched with the track include two road segments, namely, a road segment 1 and a road segment 2.

And S203, determining a key road section of each track according to at least one of the attribute information of the road section matched with each track and the motion information of the track point corresponding to the road section.

In the embodiment of the application, the mode of determining the key road section by each track in the N tracks is the same. For convenience of description, the embodiment of the present application takes any one of the N tracks as an example.

In the embodiment of the present application, the ways of determining the key segments of the track include, but are not limited to, the following ways:

in the first mode, according to the attribute information of the road section matched with the track, the key road section is determined from all the road sections matched with the track.

And secondly, determining a key road section from each road section matched with the track according to the motion information of the track point corresponding to the road section matched with the track.

And determining a key road section from each road section matched with the track according to the attribute information of the road section matched with the track and the motion information of the track point corresponding to the road section.

In some embodiments, the attribute information for the road segment includes basic attributes, such as road class, attributes, function, intersection, and the like.

In some embodiments, the motion information of the track point corresponding to the road segment includes information such as speed, angular acceleration, and the like.

According to the embodiment of the application, the key road sections of the track are determined according to at least one of the attribute information of the road sections matched with the track and the motion information of the track points corresponding to the road sections, the number of the key road sections of the track is small, and the characteristics of the track can be represented.

In some embodiments, the step S203 comprises the following steps S203-A to S203-C:

S203-A, aiming at the ith track in the N tracks, determining the first importance of each road section in the K road sections according to the attribute information of each road section in the K road sections matched with the ith track.

Wherein i is a positive integer from 1 to N.

For convenience of description, the ith track of the N tracks is taken as an example for illustration.

In the embodiment of the application, first importance of each road section is determined according to attribute information of each road section matched with the ith track, second importance of each road section is determined according to motion information of track points corresponding to each road section, and a key road section of the ith track is determined according to at least one of the first importance and the second importance of each road section.

In the embodiment of the present application, according to the attribute information of each of the K road segments matched by the ith track, the manner of determining the first importance of each of the K road segments includes, but is not limited to, the following:

in a first mode, according to the road grade in the attribute information of the road section, and according to the road grade, the first importance of the road section is determined, wherein the higher the road grade is, the higher the first importance of the corresponding road section is.

In a second mode, the attribute information of the road segment includes at least one of a number of road segments connected to the road segment, a function level of the road segment, an angle between the road segment and a next adjacent road segment, and a number of road segments within a preset range around the road segment, and then the S203-a includes the following steps:

S203-A1, aiming at the jth road section in the K road sections, determining at least one of the number of first road sections connected with the jth road section, the function level of the jth road section, the angle between the jth road section and the next adjacent road section and the number of second road sections in the peripheral preset range of the jth road section, wherein j is a positive integer from 1 to K;

S203-A2, determining a first importance of the jth road segment according to at least one of the number of the first road segments, the function level, the angle and the number of the second road segments.

In the embodiment of the present application, the road segments matched with the ith track include K road segments, and the manner of determining the first importance of each road segment in the K road segments is consistent.

The attribute information of the road segment in the embodiment of the present application includes at least one of the number of road segments connected to the road segment, the function level of the road segment, the angle between the road segment and the next adjacent road segment, and the number of road segments within the preset range around the road segment, and therefore, before determining the first importance of the jth road segment, it is first necessary to determine the attribute information of the jth road segment, that is, at least one of the number of first road segments connected to the jth road segment, the function level of the jth road segment, the angle between the jth road segment and the next adjacent road segment, and the number of second road segments within the preset range around the jth road segment.

Take the jth link as the link a shown in fig. 6 as an example.

The links connected to the link a are the link D, the link C, and the link B, and thus the number of links connected to the link a LO _ num is 3. For convenience of description, in the embodiment of the present application, the number of links LO _ num connected to the link a is recorded as the first number of links.

Exemplary, road segment function class kidd_A1 to 5 levels respectively, the higher the level the more important it is, the level 5 is usually a high speed, city express way, etc.

The road segments within the preset range around the road segment a are 4 road segments, namely, the road segment D, the road segment C, the road segment B and the road segment E, so that the number of the road segments AR _ num within the preset range around the road segment a is 4. For convenience of description, in the embodiment of the present application, the number of links AR _ num in a preset range around the link a is recorded as the second number of links.

The next adjacent road section of the road section A is a road section B, and the angle between the road section A and the road section B is determined_ABTo determine whether the section a is a straight section, a turn section, or a turn-off section, etc. For example, as shown in fig. 6, the angle between the link a and the link B is 0, which indicates that the link a is not a turn link.

In some embodiments, the angle between the jth road segment and the next adjacent road segment may be determined as follows:

step 1, respectively determining a first direction angle of a jth road section and a second direction angle of a next adjacent road section.

Optionally, the road network data includes a direction angle of each road segment, so that the server may obtain a first direction angle of a jth road segment and a second direction angle of a next adjacent road segment of the jth road segment from the road network data.

Step 2, if a first difference value between the first direction angle and the second direction angle is smaller than or equal to a first preset value, determining the first difference value as an angle between the jth road section and the next adjacent road section;

and 3, if the first difference is larger than the first preset value, determining a second difference between the second preset value and the first difference as an angle between the jth road section and the next adjacent road section.

The specific values of the first preset value and the second preset value are not limited in the embodiment of the application.

Optionally, the first preset value is 180 degrees, and the second preset value is 360 degrees.

In one possible implementation, the angle between the jth road segment and the next adjacent road segment is determined according to the following equation (2):

（2）

wherein angle is the angle between the jth road section and the next adjacent road section, A_angleIs the direction angle of the jth road segment and is marked as the first direction angle, B_angleAnd the direction angle of the next adjacent road section is recorded as a second direction angle.

According to the method, after determining attribute information of the jth road segment, namely determining at least one of the number of first road segments connected with the jth road segment, the function level of the jth road segment, the angle between the jth road segment and the next adjacent road segment and the number of second road segments in a preset range around the jth road segment, the first importance of the jth road segment is determined according to at least one of the determined number of first road segments, the determined function level, the determined angle and the determined number of second road segments.

The implementation manners of S203-a2 in the embodiment of the present application include, but are not limited to, the following:

in a first mode, the sum of at least one of the number of the first road segments, the function level of the jth road segment, the angle between the jth road segment and the next adjacent road segment, and the number of the second road segments is determined as the first importance of the jth road segment.

In a second mode, an average value of at least one of the number of the first road segments, the function level of the jth road segment, an angle between the jth road segment and a next adjacent road segment, and the number of the second road segments is determined as the first importance of the jth road segment.

In a third aspect, a weighted sum of at least one of the number of the first link, the function level of the jth link, an angle between the jth link and the next adjacent link, and the number of the second link is determined as the first importance of the jth link.

For example, a weighted sum of the first number of road segments, the function level of the jth road segment, the angle between the jth road segment and the next adjacent road segment, and the second number of road segments is determined as the first importance of the jth road segment.

Illustratively, the first importance of the jth road segment is determined according to the following formula (3):

Link_V_A=w1*LO_Num_A+w2*kind_A +w3*AR_Num_A+w4*angle_AB(3)

wherein, Link _ V_AIs the first importance of the jth road segment, LO _ Num_AFor the first number of road sections, kind, connected to the jth road section_AFor the function level of the jth road segment, AR _ Num_AFor a second number of road sections, angle, within a predetermined range around the jth road section_ABIs the angle between the jth road segment and the next adjacent road segment.

The weight corresponding to each piece of information may be a preset value or an empirical value, which is not limited in the present application.

In some embodiments, the sum of the weights corresponding to the above information is 1, i.e., w1+ w2+ w3+ w4+ w5= 1.

In some embodiments, before the third method is performed, the method further includes performing a normalization process on at least one of the first number of road segments, the function level, the angle, and the second number of road segments, and determining a weighted sum of the normalized at least one of the first number of road segments, the function level, the angle, and the second number of road segments as the first importance of the jth road segment.

In one possible implementation, the above-described pieces of information may be normalized using a normalization formula shown in the following formula (4).

（4）

Taking the example of normalizing the first road segment number of the jth road segment, where x is the first road segment number of the jth road segment, min is the minimum value of the first road segment numbers of the K road segments, and max is the maximum value of the first road segment numbers of the K road segments, according to the formula (4), the normalized first road segment number x of the jth road segment can be determined. The normalization process of the other information may be identical to the normalization process of the first link number, and the reference may be made.

According to the method, at least one of the first road segment number, the function level, the angle and the second road segment number of the jth road segment is subjected to standardization processing, and the weighted sum of the at least one of the first road segment number, the function level, the angle and the second road segment number after the jth road segment standardization processing is determined as the first importance of the jth road segment.

Optionally, in some embodiments, the first importance of the road segment may also be determined by voting or thresholding.

And S203-B, determining the second importance of each road section in the K road sections according to the motion information of the track point corresponding to each road section in the K road sections.

The track point of the embodiment of the application not only comprises time information, position information and identification, but also comprises motion information. The motion information of the track point can be understood as the motion information of the terminal device such as speed, acceleration and the like when the track point is located.

The orbit of this application embodiment is formed by connecting gradually the track point, after determining the highway section that the orbit matches, can determine the track point that each highway section corresponds, as shown in fig. 5, the track point that highway section 1 corresponds is the track point that is located the approximate horizontal direction in fig. 5 top in the orbit shown in fig. 5. Therefore, the second importance of each road section in the K road sections can be determined according to the motion information of the track point corresponding to each road section in the K road sections.

In the above S203-B, the ways of determining the second importance of each of the K road segments according to the motion information of the track point corresponding to each of the K road segments include, but are not limited to, the following:

in the first mode, for each of the K road segments, the average value of the motion information of the track point corresponding to the road segment is determined as the second importance of the road segment.

And determining the maximum value in the motion information of the track point corresponding to the road section as the second importance of the road section.

In a third mode, the step S203-B includes the steps of:

S203-B1, aiming at the jth road segment in the K road segments, if the motion information of at least one track point in the track points corresponding to the jth road segment is greater than a preset threshold value, determining that the second importance of the jth road segment is a first numerical value, and j is a positive integer from 1 to K;

S203-B2, if the motion information of each track point corresponding to the jth road section is less than or equal to the preset threshold, determining that the second importance of the jth road section is a second numerical value, and the second numerical value is less than the second numerical value.

In the third mode, the second importance of the link is divided into two values, one is the first numerical value, and the other is the second numerical value.

Specifically, if the motion information of at least one track point in the track points corresponding to the jth road segment is greater than the preset threshold, it is indicated that the behavior of the terminal device at the track point of which the motion information is greater than the preset threshold suddenly changes, for example, suddenly accelerates or suddenly decelerates, or suddenly turns, etc., the jth road segment is marked as the key road segment of the track, and at this time, the second importance of the jth road segment is determined as the first numerical value.

If the motion information of each track point corresponding to the jth road section is smaller than or equal to the preset threshold, it is indicated that the behavior of the terminal device does not change suddenly at the jth road section, the jth road section is marked as a non-key road section of the track, and at this time, the second importance of the jth road section is determined to be a second numerical value.

The embodiment of the application does not limit the specific values of the motion information of the track points.

In one example, the motion information of the track points includes at least one of speed, acceleration, direction angle, rotation angle, distance, and the like.

The embodiment of the application does not limit the specific values of the first numerical value and the second numerical value, but only ensures that the first numerical value and the second numerical value are positive numbers and the first numerical value is greater than the second numerical value.

In one possible example, the first value is 1 and the second value is 0.

In some embodiments, the second importance of the road segment may be determined according to equation (5) as follows:

（5）

wherein, Link _ U_AIn this embodiment of the application, if at least one acceleration abnormality exists in the track points corresponding to the jth road segment, that is, the acceleration is greater than the preset acceleration threshold, or the speed is abnormal, that is, the speed is greater than the preset speed threshold, it is determined that the second importance of the jth road segment is 1. And if the motion information of each track point corresponding to the jth road section is normal, for example, the speed, the acceleration and the like are smaller than the corresponding preset threshold, determining that the second importance of the jth road section is 0.

According to the above manner, the first importance and the second importance of each of the K segments matched with the ith trajectory are determined, and then, the following S203-C is performed.

S203-C, determining the key road section of the ith track according to at least one of the first importance and the second importance of each road section in the K road sections.

In this embodiment of the application, determining the critical section of the ith track according to at least one of the first importance and the second importance of each section of the K sections in S203-C includes at least the following examples:

example 1, the critical section of the ith track is determined according to the first importance of each of the K sections, for example, the section with the first importance greater than a certain preset value among the K sections is determined as the critical section of the ith track.

Example 2, the critical section of the ith track is determined according to the second importance of each of the K sections, for example, the section with the second importance greater than a preset value among the K sections is determined as the critical section of the ith track.

Example 3, the critical section of the ith trajectory is determined according to the first importance and the second importance of each of the K sections.

In one implementation of example 3, a segment of the K segments whose first importance is greater than a preset value 1 and whose second importance is greater than a preset value 2 is determined as a critical segment of the ith trajectory.

In one implementation of example 3, a segment of the K segments whose first importance is greater than a preset threshold and whose second importance is equal to a first value is determined as a critical segment of the ith trajectory.

The specific value of the preset threshold is not limited in the embodiment of the application, and is determined according to actual needs.

Optionally, the preset threshold is 0.8.

Optionally, the first value is 1.

Illustratively, Link _ U is screened out from K road segments matched with the ith track_A=1 and Link _ U_A>And 0.8, which is determined as the key road section of the ith track.

In the above embodiment, the determination of the critical section of the ith track in the N tracks is taken as an example, and the determination process of the critical sections of other tracks may refer to the ith track.

And S204, determining abnormal tracks in the N tracks according to the key road sections of each track in the N tracks.

According to the method, after the key road section of each track in the N tracks is determined, the abnormal track in the N tracks is determined according to the key road section of each track in the N tracks.

The method and the device for determining the abnormal track in the N tracks are not limited according to the key road sections of each track in the N tracks.

In some embodiments, the S204 includes: and comparing the key road sections of the N tracks with each other, judging whether the key road sections between every two tracks are the same, and if the key road sections of the two tracks are the same, determining that the two tracks are abnormal tracks.

In some embodiments, the step S204 includes the following steps:

S204-A1, determining the similarity between every two tracks in the N tracks according to the key road section of each track in the N tracks;

and S204-A2, determining the track with the similarity larger than the preset value in the N tracks as an abnormal track.

In this embodiment, the critical segments of the track are a few of the many segments matched by the track, for example, the ith track has 40 matched segments and 4 matched critical segments. That is to say, the amount of data included in the key sections of the track is small, and when the similarity between the tracks is determined based on the key sections of the track with a small amount of data, the calculation complexity can be greatly reduced, and the calculation efficiency is improved.

In addition, the key road sections of the track can embody the main characteristics of the track, so that the accuracy of similarity calculation can be improved when the similarity calculation of the track is carried out on the basis of the key road sections of the track, and the detection accuracy of abnormal tracks is further improved.

In some embodiments, the S204-a1 described above includes:

and S204-A11, determining the similarity between the key road section of the first track and the key road section of the second track aiming at the first track and the second track in the N tracks.

The first track and the second track are any one of the N tracks, and the first track is different from the second track.

And S204-A12, determining the similarity between the key road sections of the first track and the second track as the similarity between the first track and the second track.

In the embodiment of the present application, for any two tracks of the N tracks, for example, a first track and a second track, a similarity between a road segment string 1 composed of key road segments of the first track and a road segment string 2 composed of key road segments of the second track is calculated, and the similarity is determined as a similarity between the first track and the second track.

The method for determining the similarity between the key road section of the first track and the key road section of the second track is not limited in the embodiments of the present application. For example, any manner of determining similarity between two strings may be used.

In a possible implementation manner, the step S204-a12 includes the following steps:

S204-A121, determining the distance between the key road section of the first track and the key road section of the second track;

and S204-A122, determining the similarity between the key road section of the first track and the key road section of the second track according to the distance.

Optionally, the distance is any one of an edit distance, a cosine distance, and a jaccard distance.

For example, an edit distance, a cosine distance, or a jackard distance between the key segment of the first track and the key segment of the second track is determined, a similarity between the key segment of the first track and the key segment of the second track is determined according to the distance, and a difference between a certain preset value and the distance may be determined as the similarity between the key segment of the first track and the key segment of the second track since the smaller the distance, the more similar the representation.

Taking the edit distance as an example, the edit distance between the key segment of the first track and the key segment of the second track may be determined according to the following equation (6).

（6）

The edit distance between the key road segment of the first track and the key road segment of the second track can be understood as how many steps are needed to change the key road segment of the first track into the key road segment of the second track, and the smaller the steps, the more similar the first track and the second track are.

lev_a,b(i, j) refers to the distance between the first i track points in the critical segment string a of the first track and the first j track points in the critical segment string b of the second track.

And (3) determining an editing distance between the key road section of the first track and the key road section of the second track according to the formula (6), and determining the similarity between the key road section of the first track and the key road section of the second track according to the editing distance, namely the smaller the editing distance is, the more similar the key road section of the first track and the key road section of the second track is.

The embodiment of the present application may also determine the distance between the key road segment of the first track and the key road segment of the second track by using other distance calculation methods, which is not limited in the embodiment of the present application.

According to the embodiment of the application, the similarity between every two tracks is determined by calculating the similarity between the key road sections of every two tracks in the N tracks, and the track with the similarity larger than a preset value in the N tracks is determined as the abnormal track. The data volume to be processed in the whole calculation process is small, and the calculation speed is high.

According to the track detection method provided by the embodiment of the application, N tracks are constructed based on M track points reported in a preset time period, and M, N are positive integers greater than 1; determining a road section matched with each track in the N tracks; determining a key road section of each track according to at least one of attribute information of the road section matched with each track and motion information of a track point corresponding to the road section; and determining abnormal tracks in the N tracks according to the key road sections of each track in the N tracks. Namely, in the embodiment of the application, the abnormal track is determined by determining the key road sections of the track, and because the number of the key road sections of the track is small and the key road sections of the track can represent the characteristics of the track, the data volume to be processed can be reduced when abnormal track detection is performed on the basis of the key road sections of the track, and further the detection efficiency is improved.

Fig. 7 is a schematic flowchart of a track detection method according to an embodiment of the present application, and fig. 7 can be understood as a specific embodiment of the method shown in fig. 2. As shown in fig. 7, the method of the embodiment of the present application includes:

s701, eliminating abnormal track points in the M track points to obtain P normal track points.

S702, constructing N tracks based on the P normal track points.

For example, according to the time information and the identifiers included in the trace points reported in the preset time period, the trace points under the same identifier are arranged according to the time sequence to form a trace, and thus N traces are obtained.

The specific implementation process of S701 and S702 refers to the description of S201, and is not described herein again.

And S703, determining the road section matched with each track in the N tracks.

The specific implementation process of S703 refers to the description of S202, and is not described herein again.

S704, aiming at the ith track in the N tracks, determining the first importance of each road section in the K road sections according to the attribute information of each road section in the K road sections matched with the ith track.

For example, for a jth road segment of the K road segments, determining at least one of a first road segment number connected to the jth road segment, a function level of the jth road segment, an angle between the jth road segment and a next adjacent road segment, and a second road segment number within a preset range around the jth road segment, where j is a positive integer from 1 to K; and determining the first importance of the jth road section according to at least one of the number of the first road sections, the function level, the angle and the number of the second road sections. For example, a weighted sum of at least one of the first number of road segments, the function level, the angle, and the second number of road segments is determined as the first importance of the jth road segment. Or at least one of the first road section quantity, the function grade, the angle and the second road section quantity is subjected to standardization processing; and determining the weighted sum of at least one of the normalized first road section number, the normalized function level, the normalized angle and the normalized second road section number as the first importance of the jth road section.

S705, determining a second importance of each road section in the K road sections according to the motion information of the track point corresponding to each road section in the K road sections.

For example, for a jth road segment in the K road segments, if the motion information of at least one track point in the track points corresponding to the jth road segment is greater than a preset threshold, determining that the second importance of the jth road segment is a first numerical value, and j is a positive integer from 1 to K; and if the motion information of each track point corresponding to the jth road section is less than or equal to the preset threshold, determining that the second importance of the jth road section is a second numerical value, wherein the second numerical value is less than the second numerical value.

Optionally, the motion information of the track point includes at least one of a speed, an acceleration, a direction angle, and a rotation angle.

Optionally, the first value is 1, and the second value is 0.

S706, determining the road sections with the first importance degree larger than the preset threshold value and the second importance degree equal to the first numerical value in the K road sections as the key road sections of the ith track.

The specific implementation process of S706 refers to the description of S203, which is not described herein again.

And S707, determining the similarity between every two tracks in the N tracks according to the key road section of each track in the N tracks.

For example, for a first track and a second track in N tracks, determining a similarity between a key segment of the first track and a key segment of the second track, where the first track and the second track are both any one of the N tracks, and the first track is different from the second track; and determining the similarity between the key road section of the first track and the key road section of the second track as the similarity between the first track and the second track.

For example, determining the similarity between the key segment of the first track and the key segment of the second track includes: determining a distance between a critical section of the first track and a critical section of the second track; and determining the similarity between the key road section of the first track and the key road section of the second track according to the distance.

Optionally, the distance may be any one of an edit distance, a cosine distance, and a jaccard distance.

And S708, determining the track with the similarity larger than a preset value in the N tracks as an abnormal track.

According to the method and the device for determining the key road sections of the N tracks, the first importance and the second importance of the road sections matched with the N tracks are determined for each track, and the key road sections of the N tracks are determined according to the first importance and the second importance of the road sections. The similarity between every two tracks in the N tracks is obtained by calculating the similarity between the key sections of every two tracks in the N tracks, the track with the similarity larger than a preset value is determined as an abnormal track, the calculation amount in the whole process is small, the track detection efficiency is improved, the key sections can represent the main characteristics of the track, and the detection accuracy can be improved when abnormal track detection is carried out based on the key path.

The preferred embodiments of the present application have been described in detail with reference to the accompanying drawings, however, the present application is not limited to the details of the above embodiments, and various simple modifications can be made to the technical solution of the present application within the technical idea of the present application, and these simple modifications are all within the protection scope of the present application. For example, the various features described in the foregoing detailed description may be combined in any suitable manner without contradiction, and various combinations that may be possible are not described in this application in order to avoid unnecessary repetition. For example, various embodiments of the present application may be arbitrarily combined with each other, and the same should be considered as the disclosure of the present application as long as the concept of the present application is not violated.

It should also be understood that, in the various method embodiments of the present application, the sequence numbers of the above-mentioned processes do not imply an execution sequence, and the execution sequence of the processes should be determined by their functions and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

Method embodiments of the present application are described in detail above with reference to fig. 2 to 7, and apparatus embodiments of the present application are described in detail below with reference to fig. 8 to 9.

Fig. 8 is a schematic structural diagram of a track detection apparatus according to an embodiment of the present application. The trace detection apparatus may be a computing device, which may be a server as shown in fig. 1, or may be a component (e.g., an integrated circuit, a chip, etc.) of a computing device.

As shown in fig. 8, the trajectory detection device 10 includes:

the constructing unit 11 is configured to construct N tracks based on the M track points reported in the preset time period, where M, N are positive integers greater than 1;

a road section determining unit 12, configured to determine a road section matched to each of the N tracks;

a key road section determining unit 13, configured to determine a key road section of each track according to at least one of attribute information of a road section matched to each track and motion information of a track point corresponding to the road section;

an abnormal trajectory determining unit 14, configured to determine an abnormal trajectory in the N trajectories according to the key road segment of each trajectory in the N trajectories.

In some embodiments, the critical road segment determining unit 13 is specifically configured to determine, for an ith track in the N tracks, a first importance of each of K road segments according to attribute information of each of the K road segments matched with the ith track, where i is a positive integer from 1 to N; determining a second importance of each road section in the K road sections according to the motion information of the track point corresponding to each road section in the K road sections; and determining the key road section of the ith track according to at least one of the first importance and the second importance of each road section in the K road sections.

In some embodiments, the attribute information of the road segment includes at least one of a number of road segments connected to the road segment, a function level of the road segment, an angle between the road segment and a next adjacent road segment, and a number of road segments within a preset range around the road segment, and the critical road segment determining unit 13 is specifically configured to determine, for a jth road segment of the K road segments, at least one of a number of first road segments connected to the jth road segment, a function level of the jth road segment, an angle between the jth road segment and a next adjacent road segment, and a number of second road segments within a preset range around the jth road segment, where j is a positive integer from 1 to K; and determining the first importance of the jth road section according to at least one of the first road section number, the function level, the angle and the second road section number.

In some embodiments, the critical road segment determining unit 13 is specifically configured to determine a weighted sum of at least one of the first road segment number, the function level, the angle, and the second road segment number as the first importance of the jth road segment.

In some embodiments, the critical road segment determining unit 13 is specifically configured to perform a normalization process on at least one of the first road segment number, the function level, the angle, and the second road segment number; determining a weighted sum of at least one of the normalized first road segment number, the normalized function level, the normalized angle, and the normalized second road segment number as a first importance of the jth road segment.

In some embodiments, the critical road segment determining unit 13 is specifically configured to determine a first direction angle of the jth road segment and a second direction angle of the next adjacent road segment respectively; if a first difference between the first direction angle and the second direction angle is smaller than or equal to a first preset value, determining the first difference as an angle between the jth road section and the next adjacent road section; and if the first difference is larger than the first preset value, determining a second difference between a second preset value and the first difference as an angle between the jth road section and the next adjacent road section.

In some embodiments, the key road segment determining unit 13 is specifically configured to determine, for a jth road segment in the K road segments, that a second importance of the jth road segment is a first numerical value if motion information of at least one of track points corresponding to the jth road segment is greater than a preset threshold, where j is a positive integer from 1 to K; and if the motion information of each track point corresponding to the jth road section is less than or equal to the preset threshold value, determining that the second importance of the jth road section is a second numerical value, wherein the second numerical value is less than the second numerical value.

In some embodiments, the motion information of the trace point includes at least one of a velocity, an acceleration, a direction angle, and a rotation angle.

Optionally, the first value is 1, and the second value is 0.

In some embodiments, the critical road segment determining unit 13 is specifically configured to determine, as the critical road segment of the ith track, a road segment of the K road segments, where the first importance is greater than a preset threshold and the second importance is equal to a first numerical value.

In some embodiments, the abnormal trajectory determining unit 14 is specifically configured to determine, according to the key road segment of each of the N trajectories, a similarity between every two of the N trajectories; and determining the track with the similarity larger than a preset value in the N tracks as the abnormal track.

In some embodiments, the abnormal trajectory determining unit 14 is specifically configured to determine, for a first trajectory and a second trajectory of the N trajectories, a similarity between a key segment of the first trajectory and a key segment of the second trajectory, where the first trajectory and the second trajectory are both any one of the N trajectories, and the first trajectory is different from the second trajectory; determining the similarity between the key road sections of the first track and the second track as the similarity between the first track and the second track.

In some embodiments, the abnormal trajectory determination unit 14 is specifically configured to determine a distance between a critical segment of the first trajectory and a critical segment of the second trajectory; and determining the similarity between the key road section of the first track and the key road section of the second track according to the distance.

In some embodiments, the distance is any one of an edit distance, a cosine distance, and a jaccard distance.

In some embodiments, the constructing unit 11 is specifically configured to arrange, according to the time information and the identifier included in the track points reported in the preset time period, the track points under the same identifier according to a time sequence to form a track, so as to obtain the N tracks.

In some embodiments, the constructing unit 11 is specifically configured to eliminate an abnormal trace point from the M trace points to obtain P normal trace points, where P is a positive integer greater than 1 and less than or equal to M; and constructing the N tracks based on the P normal track points.

It is to be understood that apparatus embodiments and method embodiments may correspond to one another and that similar descriptions may refer to method embodiments. To avoid repetition, further description is omitted here. Specifically, the apparatus shown in fig. 8 may perform the embodiment of the method, and the foregoing and other operations and/or functions of each module in the apparatus are respectively for implementing the embodiment of the method corresponding to the computing device, and are not described herein again for brevity.

The apparatus of the embodiments of the present application is described above in connection with the drawings from the perspective of functional modules. It should be understood that the functional modules may be implemented by hardware, by instructions in software, or by a combination of hardware and software modules. Specifically, the steps of the method embodiments in the present application may be implemented by integrated logic circuits of hardware in a processor and/or instructions in the form of software, and the steps of the method disclosed in conjunction with the embodiments in the present application may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. Alternatively, the software modules may be located in random access memory, flash memory, read only memory, programmable read only memory, electrically erasable programmable memory, registers, and the like, as is well known in the art. The storage medium is located in a memory, and a processor reads information in the memory and completes the steps in the above method embodiments in combination with hardware thereof.

Fig. 9 is a schematic block diagram of a computing device provided in an embodiment of the present application, and configured to execute the above method embodiment.

As shown in fig. 9, the computing device 30 may include:

a memory 31 and a processor 32, the memory 31 being arranged to store a computer program 33 and to transfer the program code 33 to the processor 32. In other words, the processor 32 may call and run the computer program 33 from the memory 31 to implement the method in the embodiment of the present application.

For example, the processor 32 may be adapted to perform the above-mentioned method steps according to instructions in the computer program 33.

In some embodiments of the present application, the processor 32 may include, but is not limited to:

general purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, and the like.

In some embodiments of the present application, the memory 31 includes, but is not limited to:

volatile memory and/or non-volatile memory. The non-volatile Memory may be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically Erasable PROM (EEPROM), or a flash Memory. Volatile Memory can be Random Access Memory (RAM), which acts as external cache Memory. By way of example, but not limitation, many forms of RAM are available, such as Static random access memory (Static RAM, SRAM), Dynamic Random Access Memory (DRAM), Synchronous Dynamic random access memory (Synchronous DRAM, SDRAM), Double Data Rate Synchronous Dynamic random access memory (DDR SDRAM), Enhanced Synchronous SDRAM (ESDRAM), Synchronous SDRAM (sync-connected DRAM, SLDRAM), and Direct Rambus RAM (DR RAM).

In some embodiments of the present application, the computer program 33 may be divided into one or more modules, which are stored in the memory 31 and executed by the processor 32 to perform the method of recording pages provided herein. The one or more modules may be a series of computer program instruction segments capable of performing certain functions, the instruction segments describing the execution of the computer program 33 in the computing device.

As shown in fig. 9, the computing device 30 may further include:

a transceiver 34, the transceiver 34 being connectable to the processor 32 or the memory 31.

The processor 32 may control the transceiver 34 to communicate with other devices, and specifically, may transmit information or data to the other devices or receive information or data transmitted by the other devices. The transceiver 34 may include a transmitter and a receiver. The transceiver 34 may further include one or more antennas.

It should be understood that the various components in the computing device 30 are connected by a bus system that includes a power bus, a control bus, and a status signal bus in addition to a data bus.

According to an aspect of the present application, there is provided a computer storage medium having a computer program stored thereon, which, when executed by a computer, enables the computer to perform the method of the above-described method embodiments. In other words, the present application also provides a computer program product containing instructions, which when executed by a computer, cause the computer to execute the method of the above method embodiments.

According to another aspect of the application, a computer program product or computer program is provided, comprising computer instructions stored in a computer readable storage medium. The computer instructions are read by a processor of the computing device from the computer-readable storage medium, and the processor executes the computer instructions to cause the computing device to perform the method of the above-described method embodiment.

In other words, when implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. The procedures or functions described in accordance with the embodiments of the present application occur, in whole or in part, when the computer program instructions are loaded and executed on a computer. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored on a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website, computer, server, or data center to another website, computer, server, or data center via wire (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that includes one or more of the available media. The usable medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium (e.g., a Digital Video Disk (DVD)), or a semiconductor medium (e.g., a Solid State Disk (SSD)), among others.

Those of ordinary skill in the art will appreciate that the various illustrative modules and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present 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. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the module is merely a logical division, and other divisions may be realized in practice, 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 through some interfaces, devices or modules, and may be in an electrical, mechanical or other form.

Modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical modules, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. For example, functional modules in the embodiments of the present application may be integrated into one processing module, or each of the modules may exist alone physically, or two or more modules are integrated into one module.

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 (18)

1. A trajectory detection method, comprising:

constructing N tracks based on M track points reported in a preset time period, wherein M, N are positive integers greater than 1;

determining a road section matched with each track in the N tracks;

determining a key road section of each track according to at least one of attribute information of the road section matched with each track and motion information of a track point corresponding to the road section;

determining an abnormal track in the N tracks according to the key road section of each track in the N tracks;

determining a key road section of each track according to at least one of attribute information of the road section matched with each track and motion information of a track point corresponding to the road section, wherein the determining comprises the following steps:

for the ith track in the N tracks, determining the first importance of each road section in the K road sections according to the attribute information of each road section in the K road sections matched with the ith track, wherein i is a positive integer from 1 to N;

determining a second importance of each road section in the K road sections according to the motion information of the track point corresponding to each road section in the K road sections;

and determining the key road section of the ith track according to at least one of the first importance and the second importance of each road section in the K road sections.

2. The method according to claim 1, wherein the attribute information of the road segment includes at least one of a number of road segments connected to the road segment, a function level of the road segment, an angle between the road segment and a next adjacent road segment, and a number of road segments within a preset range around the road segment, and the determining the first importance of each of the K road segments according to the attribute information of each of the K road segments matched by the ith track includes:

determining at least one of a first road segment number connected with a jth road segment in the K road segments, a function level of the jth road segment, an angle between the jth road segment and a next adjacent road segment, and a second road segment number in a preset range around the jth road segment, wherein j is a positive integer from 1 to K;

and determining the first importance of the jth road section according to at least one of the first road section number, the function level, the angle and the second road section number.

3. The method of claim 2, wherein determining the first importance of the jth segment based on at least one of the first number of segments, the function level, the angle, and the second number of segments comprises:

determining a weighted sum of at least one of the first number of road segments, the function level, the angle, and the second number of road segments as a first importance of the jth road segment.

4. The method of claim 3, wherein determining a weighted sum of at least one of the first number of road segments, the function level, the angle, and the second number of road segments as a first importance for the jth road segment comprises:

standardizing at least one of the first number of road segments, the function level, the angle, and the second number of road segments;

determining a weighted sum of at least one of the normalized first road segment number, the normalized function level, the normalized angle, and the normalized second road segment number as a first importance of the jth road segment.

5. The method of claim 2, wherein determining an angle between the jth segment and an adjacent next adjacent segment comprises:

respectively determining a first direction angle of the jth road section and a second direction angle of the next adjacent road section;

if a first difference between the first direction angle and the second direction angle is smaller than or equal to a first preset value, determining the first difference as an angle between the jth road section and the next adjacent road section;

and if the first difference is larger than the first preset value, determining a second difference between a second preset value and the first difference as an angle between the jth road section and the next adjacent road section.

6. The method according to claim 1, wherein the determining the second importance of each of the K segments according to the motion information of the track point corresponding to each of the K segments comprises:

for a jth road segment in the K road segments, if motion information of at least one track point in each track point corresponding to the jth road segment is greater than a preset threshold value, determining that a second importance of the jth road segment is a first numerical value, wherein j is a positive integer from 1 to K;

and if the motion information of each track point corresponding to the jth road section is less than or equal to the preset threshold value, determining that the second importance of the jth road section is a second numerical value, wherein the second numerical value is less than the second numerical value.

7. The method of claim 6, wherein the motion information of the track points comprises at least one of speed, acceleration, direction angle, and rotation angle.

8. The method of claim 6, wherein the first value is 1 and the second value is 0.

9. The method according to any one of claims 1-8, wherein determining the critical segments of the ith trajectory according to at least one of the first importance and the second importance of each of the K segments comprises:

and determining the road sections of which the first importance is greater than a preset threshold value and the second importance is equal to a first numerical value in the K road sections as the key road sections of the ith track.

10. The method according to any one of claims 1-8, wherein the determining abnormal tracks in the N tracks according to the critical sections of each track in the N tracks comprises:

determining the similarity between every two tracks in the N tracks according to the key road section of each track in the N tracks;

and determining the track with the similarity larger than a preset value in the N tracks as the abnormal track.

11. The method according to claim 10, wherein the determining the similarity between each two tracks in the N tracks according to the key road segment of each track in the N tracks comprises:

determining similarity between a key road section of the first track and a key road section of the second track aiming at a first track and a second track in the N tracks, wherein the first track and the second track are any one of the N tracks, and the first track is different from the second track;

determining the similarity between the key road sections of the first track and the second track as the similarity between the first track and the second track.

12. The method of claim 11, wherein determining the similarity between the critical segments of the first track and the critical segments of the second track comprises:

determining a distance between a critical segment of the first track and a critical segment of the second track;

and determining the similarity between the key road section of the first track and the key road section of the second track according to the distance.

13. The method of claim 12, wherein the distance is any one of an edit distance, a cosine distance, and a Jacard distance.

14. The method according to any one of claims 1 to 8, wherein constructing N tracks based on the M track points reported in the preset time period includes:

and arranging the track points under the same identifier according to the time sequence to form a track according to the time information and the identifier included in the reported track points in the preset time period, so as to obtain the N tracks.

15. The method according to any one of claims 1 to 8, wherein before constructing N tracks based on the M track points reported within the preset time period, the method includes:

rejecting abnormal track points in the M track points to obtain P normal track points, wherein P is a positive integer which is more than 1 and less than or equal to M;

the method for constructing N tracks based on M track points reported in a preset time period comprises the following steps:

and constructing the N tracks based on the P normal track points.

16. A trajectory detection device, comprising:

the construction unit is used for constructing N tracks based on M track points reported in a preset time period, wherein M, N are positive integers larger than 1;

the road section determining unit is used for determining a road section matched with each track in the N tracks;

the key road section determining unit is used for determining the key road section of each track according to at least one of the attribute information of the road section matched with each track and the motion information of the track point corresponding to the road section;

an abnormal track determining unit, configured to determine an abnormal track in the N tracks according to the key road segment of each track in the N tracks;

the key road section determining unit is specifically configured to determine, for an ith track of the N tracks, a first importance of each road section of the K road sections according to attribute information of each road section of the K road sections matched with the ith track, where i is a positive integer from 1 to N; determining a second importance of each road section in the K road sections according to the motion information of the track point corresponding to each road section in the K road sections; and determining the key road section of the ith track according to at least one of the first importance and the second importance of each road section in the K road sections.

17. A computing device, comprising: a memory, a processor;

the memory for storing a computer program;

the processor for executing the computer program to implement the method of any one of the preceding claims 1 to 15.

18. A computer-readable storage medium having computer-executable instructions stored thereon, which when executed by a processor, are configured to implement the method of any one of claims 1 to 15.