Processing method and device of travel trajectory data and traffic navigation method

Abstract

Embodiments of the present application provide a journey trajectory data processing method and device, electronic equipment, computer readable storage medium and traffic navigation method, and relate to the field of intelligent transportation. The journey trajectory data processing method comprises: obtaining journey trajectory data of a vehicle comprising a plurality of trajectory points sorted by collection time; identifying invalid journey segments, the invalid journey segments comprising one of trajectory points corresponding to an abnormal collection time interval of adjacent trajectory points, an abnormal driving path corresponding to the trajectory points, and trajectory points corresponding to an abnormal order state; and segmenting the journey trajectory data based on the invalid journey segments, and taking the data after the segmentation processing, except the invalid journey segments, as valid journey segments. The processed trajectory data can more accurately reflect the most commonly used or relatively efficient path selection of the vehicle in the journey with a destination, and provide a more reliable data source for establishing a database or performing navigation according to the journey trajectory data of the vehicle.

Description

Technical Field

[0001] This application relates to the field of intelligent transportation technology, and more specifically, to a method, apparatus, electronic device, computer-readable storage medium and computer program product for processing travel trajectory data, and a traffic navigation method. Background Technology

[0002] With the advent of the big data era and the development of positioning technology and services, trajectory data has received increasing attention and plays an important role in trajectory prediction, path inference, pattern mining, and other related fields.

[0003] Most current research on trajectory data focuses on cleaning the raw trajectory data, primarily addressing the issue of spoofed data points in trajectory data caused by data loss or inadequate hardware configuration. Related trajectory data cleaning methods mainly include mean filtering, Kalman particle filtering, and outlier detection, among others.

[0004] In map-related applications, raw trajectory data is typically cleaned and directly used for various downstream applications, such as navigation methods based on massive amounts of trajectory data. Route planning and time-of-arrival estimation are two crucial aspects of navigation methods. Related technologies utilize vast amounts of historical travel trajectory information, matching road networks to uncover frequently traveled routes, and then planning routes from origin to destination and estimating arrival times based on these routes and travel time records. In this application approach, the accuracy of the public trajectory data itself in reflecting the route choices of travelers significantly impacts the accuracy and precision of navigation. Currently, related technologies do not consider this factor when directly using cleaned raw trajectory data, nor do they take relevant measures. Therefore, when the public trajectory data used for navigation is suboptimal, the navigation effect is also affected. Summary of the Invention

[0005] The embodiments of this application aim to address at least one aspect of the aforementioned problems to a certain extent, providing travel data that more accurately reflects the public's travel route choices. To this end, the embodiments of this application provide a series of technical solutions for processing travel trajectory data.

[0006] According to an embodiment of the first aspect of this application, a method for processing travel trajectory data is provided, the method comprising:

[0007] Acquire vehicle travel trajectory data, which includes data from multiple trajectory points sorted by collection time;

[0008] Identify invalid travel segments in the travel trajectory data, where invalid travel segments contain trajectory points corresponding to abnormal states;

[0009] The travel trajectory data is segmented based on invalid travel segments, and the segmented data excluding invalid travel segments is taken as valid travel segments.

[0010] Abnormal states include at least one of the following: abnormal time interval between adjacent trajectory points; abnormal driving path corresponding to the trajectory point; abnormal order status corresponding to the trajectory point.

[0011] According to an embodiment of a second aspect of this application, a traffic navigation method is provided, the method comprising:

[0012] Obtain travel trajectory data processed by the method for processing travel trajectory data according to the first aspect of the present application;

[0013] Based on the processed trip trajectory data, perform one or more of the following navigation operations:

[0014] A valid travel trajectory dataset is constructed based on the processed travel trajectory data, and the valid travel trajectory dataset is used as the training set for the neural network to train the neural network. The trained neural network is then used for navigation.

[0015] Estimate the traffic flow of road segments within the area to which the processed travel trajectory data belongs based on the processed travel trajectory data;

[0016] Estimate the travel time between the start and end points within the area to which the travel trajectory data belongs based on the processed travel trajectory data;

[0017] Based on the processed travel trajectory data, route planning is performed between the start and end points within the area to which the travel trajectory data belongs; or

[0018] The electronic map of the area to which the travel trajectory data belongs is corrected based on the processed travel trajectory data.

[0019] According to an embodiment of a third aspect of this application, an apparatus for processing travel trajectory data is provided, the apparatus comprising:

[0020] The trip trajectory acquisition module is used to acquire the vehicle's trip trajectory data, which includes data from multiple trajectory points sorted by acquisition time.

[0021] The invalid travel segment identification module is used to identify invalid travel segments in travel trajectory data. The invalid travel segment contains trajectory points corresponding to abnormal states. The abnormal states include at least one of the following: abnormal collection time interval between adjacent trajectory points; abnormal driving path corresponding to the trajectory point; and abnormal order status corresponding to the trajectory point.

[0022] The trajectory segmentation module is used to segment travel trajectory data based on invalid travel segments, and to treat the segmented data, excluding invalid travel segments, as valid travel segments.

[0023] According to an embodiment of a fourth aspect of this application, an electronic device is provided, the electronic device comprising:

[0024] A memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of a method for processing travel trajectory data according to an embodiment of the first aspect of this application.

[0025] According to an embodiment of the fifth aspect of this application, a computer-readable storage medium is provided, on which a computer program is stored, wherein when the computer program is executed by a processor, it implements the steps of the method for processing travel trajectory data according to the first aspect of this application.

[0026] According to an embodiment of the sixth aspect of this application, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the method for processing travel trajectory data according to the first aspect of this application.

[0027] The series of technical solutions for processing trip trajectory data identify abnormal trip segments, such as abnormal collection time intervals between adjacent trajectory points, abnormal driving paths corresponding to trajectory points, and abnormal order statuses corresponding to trajectory points. By segmenting the trip trajectory containing abnormal trip segments, the effective trip segments can more accurately reflect the most frequently used or relatively efficient route selections of vehicles during their purposeful journeys from origin to destination. This provides a more reliable data source for subsequent establishment of trip databases or navigation based on vehicle trip trajectory data.

[0028] Furthermore, when using the data processed by the trip trajectory data processing method based on this application to implement various navigation algorithms, more accurate navigation results will be obtained. Attached Figure Description

[0029] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments of this application will be briefly introduced below.

[0030] Figure 1 This is a schematic diagram of the architecture of a trip data processing system according to an embodiment of this application;

[0031] Figure 2 This is a flowchart illustrating a method for processing travel trajectory data according to an embodiment of this application;

[0032] Figure 3This is a flowchart illustrating the operation of obtaining vehicle travel trajectory data according to an embodiment of this application;

[0033] Figure 4 This is a schematic diagram illustrating the identification of invalid travel segments with abnormal travel paths using a sliding window method according to an embodiment of this application;

[0034] Figure 5 This is a schematic diagram of a process for processing travel trajectory data according to an embodiment of this application;

[0035] Figure 6 This is a schematic diagram of a travel trajectory data processing device according to an embodiment of this application;

[0036] Figure 7 This is a schematic diagram of the structure of an electronic device for processing travel trajectory data according to an embodiment of this application. Detailed Implementation

[0037] The embodiments of this application are described below with reference to the accompanying drawings. It should be understood that the embodiments described below with reference to the accompanying drawings are exemplary descriptions for explaining the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions of the embodiments of this application.

[0038] Those skilled in the art will understand that, unless specifically stated otherwise, the singular forms “a,” “an,” “the,” and “the” used herein may also include the plural forms. It should be further understood that the terms “comprising” and “including” as used in embodiments of this application mean that the corresponding feature can be implemented as the presented feature, information, data, step, operation, element, and / or component, but do not exclude implementation as other features, information, data, step, operation, element, component, and / or combinations thereof supported by the art. It should be understood that when we say that an element is “connected” or “coupled” to another element, the one element can be directly connected or coupled to the other element, or it can mean that the one element and the other element establish a connection relationship through an intermediate element. Furthermore, “connected” or “coupled” as used herein can include wireless connection or wireless coupling. The term “and / or” as used herein indicates at least one of the items defined by the term; for example, “A and / or B” can be implemented as “A,” or as “B,” or as “A and B.”

[0039] For ease of description and understanding, some technical terms used in this disclosure are briefly introduced below. It should be noted that the following descriptions are for illustrative purposes only and do not constitute a restrictive definition of their meanings. Unless otherwise specified, in this disclosure, the meanings of technical terms well-known in the art follow their generally accepted understanding.

[0040] Intelligent Traffic Systems (ITS), also known as Intelligent Transportation Systems, effectively integrate advanced science and technology (information technology, computer technology, data communication technology, sensor technology, electronic control technology, automatic control theory, operations research, artificial intelligence, etc.) into transportation, service control, and vehicle manufacturing. This strengthens the connection between vehicles, roads, and users, thereby forming a comprehensive transportation system that ensures safety, improves efficiency, enhances the environment, and saves energy.

[0041] Intelligent Vehicle Infrastructure Cooperative Systems (IVICS) are a development direction of Intelligent Transportation Systems (ITS). IVICS utilizes advanced wireless communication and next-generation Internet technologies to implement comprehensive, real-time dynamic information exchange between vehicles and infrastructure. Based on the collection and fusion of dynamic traffic information across all times and spaces, it conducts active vehicle safety control and cooperative road management, fully realizing effective collaboration between people, vehicles, and roads. This ensures traffic safety, improves traffic efficiency, and ultimately forms a safe, efficient, and environmentally friendly road traffic system.

[0042] A journey trajectory includes multiple trajectory points ordered by time, used to describe the path information of the main body of the journey—such as a vehicle—passing sequentially within a certain time range.

[0043] A trajectory point is the smallest unit of travel trajectory data. A trajectory point typically includes sampling time, geographic location information, and other information configured as needed. The sampling time and geographic location information in trajectory point data are generally acquired and recorded through an onboard satellite positioning system or a satellite positioning module on a mobile terminal carried by the driver or passengers traveling with the vehicle. The satellite positioning system can be GPS or BeiDou, among others.

[0044] In applications such as intelligent transportation and mapping, a link is a segment of roads within a given area (typically corresponding to administrative divisions or geographical landmarks, such as a country, province, city, mountain range, or lake basin) based on the road network topology. These road segments are the smallest unit of division for the road network in electronic maps and other applications. Different map settings can employ different link segmentation strategies, and links in different locations may have varying lengths. For example, highway links may be relatively long, while urban traffic links may be relatively short.

[0045] In this disclosure, order information refers to the driving status information of the operating vehicle related to its operational purpose. Operating vehicles may include long-distance buses, long-distance trucks, city buses, taxis, and other vehicles that accept orders online to provide passenger or freight transportation services (such as various ride-hailing vehicles, transportation vehicles accepting orders through crowdsourcing platforms, etc.). The driving status related to the operation can be determined based on the passenger status of the target transported object, for example, it may include being on the way to pick up passengers, on the way to pick up passengers, waiting for passengers after accepting orders, running empty without accepting orders, or not accepting orders. It should be noted that in this disclosure, when describing the order status, "passenger" represents the target transported object, which can be a passenger or the transported goods, etc.

[0046] It should be noted that, in the optional embodiments of this application, the relevant data, such as object information (e.g., time information and satellite positioning information of the object's travel trajectory points, order information, etc.), requires the object's permission or consent when applied to specific products or technologies. Furthermore, the collection, use, and processing of this data must comply with the relevant laws, regulations, and standards of the relevant countries and regions. In other words, if the embodiments of this application involve data related to an object, this data must be obtained with the object's authorization and consent, and in accordance with the relevant laws, regulations, and standards of the country and region.

[0047] The inventors noted that while the raw data cleaned using various methods in related technologies can generally accurately reflect the vehicle's specific location during a trip, the route itself may not correspond to the public's usual route choices. For example, taxis or ride-hailing vehicles sometimes take obvious detours to pick up passengers, or vehicles may circle around due to wrong turns or no-stopping zones. These detours or circling segments negatively impact the usability of the overall trip trajectory and are considered invalid segments. Therefore, simple data cleaning cannot obtain high-quality trajectory data that aligns with the public's travel route choices. Identifying and removing such invalid segments would significantly improve the quality of the trip trajectory data.

[0048] Based on the above-mentioned technical concept, this application provides a series of technical solutions, such as methods, devices, electronic devices, computer-readable storage media, and computer program products for processing travel trajectory data, which aim to solve at least one aspect of the above-mentioned technical problems of the prior art to a certain extent.

[0049] The technical solutions of this application and their effects are described below through several exemplary embodiments. It should be noted that the following embodiments can be referenced, borrowed from, or combined with each other. Identical terms, similar features, and similar implementation steps in different embodiments will not be repeated.

[0050] To better understand the embodiments of this application, a brief introduction to the overall system framework for collecting and using travel data is provided first. See [link to relevant documentation]. Figure 1 , Figure 1 This is a schematic diagram of the architecture of a trip data processing system according to an embodiment of this application.

[0051] The trip data processing system 1000 includes multiple vehicles providing trip trajectory data, such as vehicle 101 and vehicle 102, as well as a trip trajectory processing server 200 and a valid trip database 400 for storing the processed trip trajectory data. The valid trip database 400 can be a separate hardware facility or can be located on a shared hardware facility with the trip trajectory processing server 200. The trip trajectory processing server 200 communicates with the multiple vehicles via a network 300 to obtain the trajectory data information provided by the vehicles. For vehicle 101 with order data, the trip trajectory data provided by the vehicle may include the vehicle's satellite positioning information and order information. The order information may be provided by the vehicle operator, or authorized by the operator and provided by the corresponding data platform. Alternatively, only the vehicle's satellite positioning information may be provided; in this case, the vehicle's trip trajectory data can be processed as if it were a vehicle without order data. For vehicle 102 without order data, the trip trajectory data provided by the vehicle may include the vehicle's satellite positioning information.

[0052] The valid trips obtained after processing using the trip data processing method of this application can be supplied to the traffic navigation server 200 to meet navigation needs in various scenarios. Here, the traffic navigation service 200 represents a functional logical division; it can be a separate hardware facility or it can be set up on a shared hardware facility with the trip trajectory processing server 200 or the valid trip database 400.

[0053] The navigation information from the traffic navigation server 200 can then be provided to various vehicles, offering services such as route planning and travel time estimation, or improving in-vehicle navigation devices. This forms a closed loop of information and services, where better route selection for vehicles and better route planning provided by the server mutually reinforce each other, improving the overall operational efficiency of the transportation system through positive feedback. The various methods, apparatuses, and systems according to the embodiments of this application can be used in scenarios such as urban intelligent transportation systems, logistics systems, electronic maps, improvements to in-vehicle navigation systems, ride-hailing services, and delivery services.

[0054] The following section provides a detailed explanation of the processing methods for the travel trajectory data in this application. See [link to relevant documentation]. Figure 2 , Figure 2 This is a flowchart illustrating a method for processing travel trajectory data according to an embodiment of this application. The method for processing travel trajectory data according to this embodiment includes steps S110 to S130.

[0055] In step S110, the vehicle's travel trajectory data is acquired, wherein the travel trajectory data includes data of multiple trajectory points sorted by acquisition time.

[0056] Vehicle-mounted GPS or other satellite positioning systems (GPS will be used as an example in this explanation; the use of other satellite positioning systems such as BeiDou or Iridium is similar and will not be elaborated further). Vehicle-mounted GPS modules typically acquire GPS information periodically for real-time positioning. GPS information can include time, latitude, and longitude. The acquisition of travel trajectory points is generally set up to obtain the data corresponding to the trajectory points based on the periodically acquired GPS data. The sampling period of the trajectory points can be the same as or greater than the sampling period of the vehicle's GPS. Furthermore, due to transmission failures or other reasons, some sampling points may have missing data. Therefore, when processing travel trajectory data, this application can, as needed, use mathematical methods such as function interpolation to numerically fit and fill in a small number of missing sampling points, and perform other related processing such as segmenting and discarding large numbers of missing sampling points.

[0057] A trip trajectory may include continuously collected trajectory point data within a preset duration. The preset duration can be selected to correspond to 24 hours of a day, or the main travel time from 7:00 to 21:00, or several hours corresponding to general continuous driving time, etc. This application does not impose any restrictions on this.

[0058] A trip trajectory may include continuously collected trajectory point data within a preset duration. The preset duration can be selected to correspond to 24 hours of a day, or the main travel time from 7:00 to 21:00, or several hours corresponding to general continuous driving time, etc. This application does not impose any restrictions on this.

[0059] In step S120, invalid travel segments in the travel trajectory data are identified, wherein invalid travel segments contain trajectory points corresponding to abnormal states, wherein the abnormal states include at least one of the following: abnormal collection time interval between adjacent trajectory points; abnormal driving path corresponding to the trajectory point; and abnormal order status corresponding to the trajectory point.

[0060] In the embodiments of this application, the selection of invalid travel segments is based on considerations such as whether the travel segment conforms to the general route selection habits of the public, or whether it is a continuous driving process, which can affect the reliability of the route selection or the reference significance of the travel time of the segment.

[0061] For example, if the time interval between adjacent track points is too long compared to the normal GPS sampling interval and the set track point sampling interval, it may mean that GPS data information is missing for a long time, for example, if GPS is turned off. In this case, the distance between these two adjacent GPS points and the time taken to travel this distance may not be the difference between the sampling times of the two sampling points. It is no longer appropriate to use this set of track points as if they were normal track points. The track segment between these two track points should be filtered out from the track data.

[0062] A normal driving route refers to the route that the average person would choose to travel from point A to point B, based on optimization goals such as minimizing travel time or traffic congestion. For example, if you can travel directly from point A to point B via the first road, and there is a shopping mall on one side of the first road, surrounded by a ring road, with its main entrance facing away from the first road, then the normal driving route is clearly via the first road from A to B.

[0063] However, during the journey from A to B, most empty taxis, in order to attract customers, or ride-hailing vehicles picking up passengers, will choose to detour to the main entrance of the shopping mall. This is reflected in the trip data as more frequent half-circle routes than straight routes on the A to B section. This half-circle, loop-like path is considered an abnormal driving path.

[0064] If machine learning or automated data processing such as navigation based on statistical results is performed based on this data, there is a high possibility that vehicles that normally need to get from A to B will be advised to take a detour through the main entrance of the shopping mall. This is obviously not in line with actual needs. Therefore, such data points also need to be filtered out from the trajectory data.

[0065] In the examples above, the reason why taxis and ride-hailing vehicles take detours is related to the orders. Therefore, order information can be used to some extent to avoid introducing these abnormal driving routes. For vehicles with orders corresponding to passenger or cargo transport (such as food delivery or courier delivery trips), the probability of abnormal situations such as detours during the process of transporting the order and on the way to the passenger after accepting the order is relatively small. Therefore, based on this characteristic, the trip segments corresponding to passenger pick-up and passenger transport can be considered valid trip segments, while the trip segments corresponding to other order statuses can be considered invalid trip segments and filtered out, thereby improving the efficiency of screening and filtering. This allows for a simpler way to extract valuable parts from massive amounts of trip data.

[0066] In step S130, the travel trajectory data is segmented based on invalid travel segments, and the segmented data excluding invalid travel segments is taken as valid travel segments.

[0067] For each travel trajectory, after identifying invalid travel segments, they need to be removed from the trajectory. This removal can be achieved by segmenting the trajectory data at the two ends of the invalid travel segment. The invalid travel segments are then discarded. The segmented data, excluding the invalid travel segments, is then considered as valid travel segments. Thus, depending on the number and distribution of invalid travel segments, the trajectory data, including the remaining valid travel segments, will change from one trajectory before segmentation into two or more trajectories.

[0068] By identifying abnormal travel segments such as abnormal collection time intervals between adjacent trajectory points, abnormal driving paths corresponding to trajectory points, and abnormal order statuses corresponding to trajectory points, and by segmenting travel trajectories containing abnormal travel segments, the resulting effective travel segments can more accurately reflect the most frequently used or relatively efficient route selections for vehicles on their purposeful journeys from origin to destination. This provides a more reliable data source for subsequent establishment of a travel database or navigation based on vehicle travel trajectory data.

[0069] The following provides a detailed description of each step in the method for processing travel trajectory data according to embodiments of this application.

[0070] See Figure 3 , Figure 3 This is a flowchart illustrating the operation of obtaining vehicle travel trajectory data according to an embodiment of this application. Step S110, which involves obtaining the vehicle travel trajectory data, may further include steps S111 to S114.

[0071] In step S111, satellite positioning data corresponding to the vehicle's journey is obtained. It should be noted that, in this application, the vehicle journey should be interpreted broadly, that is, it includes not only when the vehicle is in motion, but also when it is parked, etc., and it represents the sequence of the vehicle's positions within a time range.

[0072] In step S112, the satellite positioning data is cleaned to obtain trajectory data corresponding to the vehicle's actual location. This data cleaning includes removing at least one of the following: physically erroneous data, incomplete data, and logically abnormal data. One or more data processing methods from related technologies can be used for data cleaning in this step. The purpose is to remove erroneous data that does not correspond to the vehicle's actual location. Examples include erroneous data introduced by physical errors at the GPS signal receiver, physically erroneous data and incomplete data introduced by channel interference during transmission, and data with excessive errors that cannot be used to accurately describe the vehicle's location. For example, if the vehicle is traveling on a flat road, the height corresponding to the preceding and following trajectory points is the same as the road surface, but the current trajectory point suddenly corresponds to a height of 10 meters, such data is clearly abnormal.

[0073] In step S113, the trajectory data corresponding to the vehicle's actual location is matched with the road network topology data of the known area to which the vehicle's journey belongs, to obtain the road segment information in the road network topology corresponding to each trajectory point in the trajectory data corresponding to the vehicle's actual location. In current related technologies, major data map providers construct their own road segment divisions. Although the results of road segment division vary slightly between different providers, the overall principles are roughly the same. In this application, road segment division can be implemented using various division methods in related technologies, and the road segments divided in these methods can all be used in the methods of this application's embodiments.

[0074] In step S114, the travel trajectory data of the vehicle is obtained based on the trajectory data corresponding to the actual location of the vehicle and the road segment information in the road network topology corresponding to each trajectory point.

[0075] Due to factors such as terrain, GPS data accuracy, GPS receiver signal strength, and computational precision, GPS location data contains a certain degree of error, which can reach several meters or even tens of meters in some cases. However, based on the known fact that vehicles mostly travel on roads, and prior knowledge about road networks, it is possible to correct for potential GPS errors to a certain extent.

[0076] By matching each trajectory point in the trajectory data to the nearest corresponding road segment, for example, taking the projection point of the trajectory point on the road segment as the matching point of the trajectory point, and using the location of the matching point on the corresponding road segment as the location of the trajectory point, GPS errors can be corrected to some extent. For data that is originally accurate, since it is mostly located on the corresponding road segment, matching additional points will not introduce additional errors for normal accurate GPS locations.

[0077] In step S120, abnormal travel segments and abnormal trajectory points under various conditions can be identified and filtered out, or multiple abnormal travel segments can be identified and removed, or all abnormal travel segments under all conditions can be identified and removed. The identification methods for various abnormal travel segments are described in detail below.

[0078] In some embodiments, identifying invalid travel segments in travel trajectory data includes:

[0079] In the identified travel trajectory data, travel segments with adjacent trajectory points whose acquisition time interval is greater than a preset first duration as endpoints are considered invalid travel segments with abnormal acquisition time intervals.

[0080] The initial duration can be selected based on factors such as the vehicle's GPS sampling interval and road network conditions. Different initial durations correspond to different invalid trip filtering strategies. For example, setting the initial duration to several hours can be used to remove trip data anomalies introduced by GPS malfunctions, network transmission failures, or GPS shutdown due to prolonged parking. Setting the initial duration to tens of minutes can be used to filter out trajectory segments unsuitable for arrival time estimation.

[0081] To further simplify calculations, in some embodiments, a sliding window or scrolling window can be used to detect travel points corresponding to longer travel segments. The time interval between the start and end points of the window is checked; if it exceeds a specified threshold, the sliding window is considered to contain abnormal trajectory points where the interval between adjacent trajectory points is greater than a first time interval. The travel segment corresponding to this window is then directly identified as an invalid travel segment, thus reducing computational load. In this way, although a small number of normal trajectory points are discarded, in the era of big data with massive amounts of travel trajectory data, this trade-off of discarding a small amount of data for less computational cost can benefit the entire data processing process.

[0082] In some embodiments, identifying invalid travel segments in travel trajectory data includes: identifying travel segments in travel trajectory data where the positions of all trajectory points fall within a first predetermined area range within a preset second time period, as invalid travel segments with abnormal travel paths.

[0083] Wherein, the second duration can be flexibly set according to the average sampling interval between track points and the actual situation of the road network. This embodiment corresponds to the "circling" or "repeated" driving state of a vehicle in a certain trip, which usually occurs when the driver is unfamiliar with the road and tries repeatedly, or when the road is blocked and impassable.

[0084] Specifically, in some embodiments, such invalid trip segments with abnormal driving paths can be identified by the following sliding window inspection method.

[0085] First, according to the trip track data, obtain the sampling interval τ between adjacent track points; according to the second duration T and the sampling interval τ, obtain a sliding window and a sliding step of corresponding size; then sequentially intercept corresponding trip segments in the trip track data according to the sliding step with the sliding window; identify the intercepted trip segment in which all track points fall within a first predetermined area range, and take it as an invalid trip segment with abnormal driving path.

[0086] For example, for each intercepted trip segment, the geometric center of each track point in the trip segment can be obtained; identify the intercepted trip segment in which the distance from each track point to the geometric center is less than a first distance threshold L, and take it as an invalid trip segment with abnormal driving path.

[0087] A sliding window (HOP), also called Sliding Window. Different from a rolling window, windows of a sliding window can overlap. A sliding window has two parameters: slide (step size) and size. The step size is the moving distance of the window each time it slides, and the size represents the time range covered by the window or equivalently the number of track points. According to the magnitude relationship between slide and size, sliding windows can be divided into the following three cases: 1. slide < size, then the windows will overlap, and each element will be assigned to multiple windows. 2. slide = size, which is equivalent to a rolling window. 3. slide > size, which is a jumping window, and there is no overlap and gaps exist between windows. In this embodiment, the overlapping window of the first case is selected to obtain a more accurate identification result. It should be noted that rolling windows and jumping windows can also be used for screening invalid trip segments. Although their identification accuracy is not as good as that of overlapping windows, they require less computation. In some occasions where there is a demand for speed and computing power resources are insufficient, the second and third methods can be selected.

[0088] For example, the window size can be taken as

[0089]

[0090] T is the second duration, and τ is the sampling interval. The first distance threshold L is set according to the sliding window size, the road network data and the identification requirements.

[0091] Taking GPS coordinates as an example to represent the coordinates of a trajectory point and its geometric center, the distance between any two points G1 and G2 can be calculated as follows:

[0092] Let the coordinates of G1 be (lat1′, lon1′) and the coordinates of G2 be (lat2′, lon2′), then the distance dist between G1 and G2 is... 12 It can be calculated as follows:

[0093] lat1=lat1′×atr, lat2=lat2′×atr,

[0094] lon1=lon1′×atr, lon2=lon2′×atr

[0095] c=sinlat1×sinlat2+coslat1×coslat2×coslon1-lon2

[0096]

[0097] in, earth radius Let 6378137 be the radius of the Earth.

[0098] See Figure 4 , Figure 4 This diagram illustrates the identification of invalid travel segments with abnormalities in the driving path using the sliding window method described above. The vehicle's trajectory is represented by distant points, and the dashed boxes indicate sliding windows W1, W2, and W3. It should be noted that, depending on the length of the travel trajectory, the sliding window may include multiple windows covering the entire trajectory. Figure 4 The sliding windows W1, W2, and W3 in the text are only a partial example, and the solid box W4 represents the window that identifies invalid travel segments.

[0099] Using a strategy that confines vehicle trajectories to a small area to determine invalid travel segments can lead to misjudgments, such as those caused by waiting at red lights or by traffic congestion. These two types of misjudgments are highly probable given the current generally poor urban traffic conditions.

[0100] To address the problem of misjudgment of invalid travel segments, some embodiments provide methods for verifying misjudgments caused by traffic lights and methods for verifying misjudgments caused by road congestion.

[0101] In some embodiments, after identifying a travel segment with an abnormal travel path, the method further includes: obtaining the location of traffic lights within the area to which the travel trajectory data belongs; identifying invalid travel segments with abnormal travel paths that fall within a second predetermined area around any traffic light; and canceling the determination of invalid travel segments with abnormal travel paths.

[0102] The second predetermined area range around any traffic light can be either all trajectory points of the entire invalid travel segment falling into the second area range, or only a portion of the trajectory points of the second travel segment falling into the second area range.

[0103] The location of a trajectory point within a second predetermined area surrounding a traffic light can be determined directly based on the distance between the trajectory point and the traffic light. Since directly calculating the distance is computationally intensive, it's also possible to determine whether a travel segment falls within the second predefined area by comparing the road segment matched to the traffic light with the road segment matched to the trajectory point or travel segment. For example, if the trajectory point and the traffic light match the same or adjacent road segment, then the travel segment containing that trajectory point is determined to fall within the second predefined area.

[0104] The following method can be used to verify whether a misjudgment is caused by traffic congestion:

[0105] Calculate the distance between each trajectory point in the invalid travel segment with abnormal travel path and the starting trajectory point of the invalid travel segment in turn; when the distance changes in an increasing trend, cancel the determination of invalid travel segment with abnormal travel path.

[0106] This is because, during traffic jams, vehicles usually move slowly in one direction. Therefore, the distance between each trajectory point and the initial trajectory point in a given distance generally changes in the same direction. The same applies to long-distance traffic jams caused by traffic lights.

[0107] In some embodiments, identifying invalid trip segments in trip trajectory data based on order status may include the following steps.

[0108] Check if there is order status information corresponding to the trip trajectory data. The order status includes one or more of the following: picking up passengers, carrying passengers, accepting orders and waiting for passengers, not accepting orders and driving empty, or not accepting orders.

[0109] When corresponding order status information exists, the trip trajectory data is filtered based on the order status information. Specifically, this includes: matching the order status information with the trip trajectory data, and segmenting the trip trajectory according to different order statuses to obtain the trip segments corresponding to each order status; based on the trip segments corresponding to the order status, identifying any one or more of the following trip segments: the trip segment corresponding to the order-accepting and waiting-for-customers status, the trip segment corresponding to the order-not-accepting and empty-running status, or the trip segment corresponding to the order-not-accepting status, as invalid trip segments corresponding to the trajectory points of the abnormal order status.

[0110] The invalid travel segment identification methods described in the above embodiments can also be used in combination, see [link to relevant documentation]. Figure 5 , Figure 5 This is a schematic flowchart of another method for processing travel trajectory data according to an embodiment of this application. The method for processing travel trajectory data includes steps S210 to S230.

[0111] In step S210, the vehicle's travel trajectory data is acquired.

[0112] For example, a combination can be used Figure 3 The method described in the embodiment for acquiring vehicle travel trajectory data specifically includes the following steps.

[0113] Obtain satellite positioning data corresponding to the vehicle's journey.

[0114] The satellite positioning data is cleaned to obtain trajectory data corresponding to the actual location of the vehicle. The data cleaning includes removing physically erroneous data, incomplete data, and logically abnormal data.

[0115] The trajectory data corresponding to the vehicle's actual location is matched with the road network topology data of the known area to which the vehicle's journey takes place to obtain the road segment information in the road network topology corresponding to each trajectory point in the trajectory data corresponding to the vehicle's actual location.

[0116] The vehicle's travel trajectory data is obtained based on the trajectory data corresponding to the vehicle's actual location and the road segment information in the road network topology corresponding to each trajectory point.

[0117] In step S221, it is detected whether the trajectory data has corresponding order status information.

[0118] Generally speaking, for online taxi, ride-hailing, delivery, and food delivery riders, as well as for travel trajectory data from crowdsourced sources, corresponding order status information can usually be obtained. However, for other vehicles, corresponding order information is less readily available.

[0119] Order status can include one or more of the following: en route to pick up passengers, en route to transport passengers, waiting for passengers after accepting orders, empty run without accepting orders, or not accepting orders.

[0120] If there is corresponding order status information, proceed to steps S222 to S223.

[0121] In step S222, the order status information is matched with the trip trajectory data, and the trip trajectory is segmented according to different order statuses to obtain the trip segments corresponding to each order status.

[0122] In step S223, the travel segments corresponding to the order-accepting and waiting-for-passengers status, the travel segments corresponding to the order-not-accepting and empty-running status, and the travel segments corresponding to the no-order status are identified as invalid travel segments corresponding to abnormal order statuses. The travel segments corresponding to picking up passengers and carrying passengers are considered as valid travel segments.

[0123] If there is corresponding order status information, proceed to steps S224 to S226.

[0124] In step S224, in the no-order travel trajectory data, travel segments with adjacent trajectory points whose collection time interval is greater than a preset first duration as endpoints are identified as invalid travel segments with abnormal collection time intervals.

[0125] For example, a sliding window or scrolling window can be used to detect travel points corresponding to a relatively long travel segment, and to check the time interval between the start and end points of the window. If it exceeds a specified threshold, the sliding window is considered to contain abnormal trajectory points with an interval between adjacent trajectory points greater than the first time duration.

[0126] In step S225, it is identified that in the remaining travel trajectory data, within a preset second time period, the positions of all trajectory points fall within the travel segment of the first predetermined area, and are thus identified as invalid travel segments with abnormal travel paths.

[0127] For example, the following sliding window test method can be used for identification. First, based on the travel trajectory data, obtain the sampling interval τ between adjacent trajectory points; based on the second duration T and the sampling interval τ, obtain the corresponding sliding window size and sliding step size; then, according to the sliding window and the sliding step size, sequentially extract the corresponding travel segments from the travel trajectory data; identify the travel segments in each extracted travel segment where the positions of all trajectory points fall within the first predetermined area, as invalid travel segments with abnormal travel paths.

[0128] In step S226, for invalid travel segments determined to have abnormal travel paths, the errors caused by traffic lights or road congestion are checked and the incorrect judgments are cancelled.

[0129] Verification of misjudgments caused by traffic lights may include: obtaining the location of traffic lights within the area to which the travel trajectory data belongs; identifying invalid travel segments with abnormal travel paths that fall within a second predetermined area around any traffic light, and canceling the determination of invalid travel segments with abnormal travel paths.

[0130] Specifically, it can be determined whether a travel segment falls within a second predefined area based on the road segment matched by the traffic light and the road segment matched by the trajectory point or the travel segment. For example, if the trajectory point and the traffic light match the same or adjacent road segment, then the travel segment containing that trajectory point is determined to fall within the second predefined area.

[0131] Verifying false positives due to road congestion can include: sequentially calculating the distance between each trajectory point in the invalid travel segment of the abnormal travel path and the starting trajectory point of the invalid travel segment; when the distance changes in an increasing trend, the determination of the invalid travel segment of the abnormal travel path is cancelled.

[0132] Finally, step S230 is executed, which involves segmenting the travel trajectory data based on invalid travel segments, and then using the segmented data excluding invalid travel segments as valid travel segments.

[0133] For each travel trajectory, after identifying invalid travel segments, they need to be removed from the trajectory. This removal can be achieved by segmenting the trajectory data at the two ends of the invalid travel segment. The invalid travel segments are then discarded. The segmented data, excluding the invalid travel segments, is then considered as valid travel segments. Thus, depending on the number and distribution of invalid travel segments, the trajectory data, including the remaining valid travel segments, will change from one trajectory before segmentation into two or more trajectories.

[0134] The specific implementation methods for each of the above steps can be referred to the various embodiments described above, and will not be repeated here. By comprehensively utilizing multiple methods for identifying invalid data segments, invalid parts in the travel trajectory data can be identified more accurately and comprehensively. After segmenting the identified invalid data segments, more usable trajectory data can be obtained, establishing a more accurate valid travel database. This provides a more precise data source for various downstream traffic navigation applications.

[0135] According to a second aspect of the embodiments of this application, a traffic navigation method is provided, comprising:

[0136] The method for processing travel trajectory data according to the first aspect of this application obtains the processed travel trajectory data; and performs one or more of the following navigation operations based on the processed travel trajectory data.

[0137] A valid travel trajectory dataset is constructed based on the processed travel trajectory data, and the valid travel trajectory dataset is used as the training set for training the neural network. The trained neural network is then used for navigation.

[0138] Estimate the traffic flow of road segments within the area to which the processed travel trajectory data belongs based on the processed travel trajectory data;

[0139] The travel time between the starting point and the destination within the area to which the travel trajectory data belongs is estimated based on the processed travel trajectory data;

[0140] Based on the processed travel trajectory data, path planning is performed between the starting point and the ending point within the area to which the travel trajectory data belongs; or

[0141] The electronic map of the area to which the processed travel trajectory data belongs is corrected based on the processed travel trajectory data.

[0142] The specific implementation methods of the various navigation operations mentioned above can be implemented by those skilled in the art based on the methods in related technologies, and will not be elaborated here.

[0143] Since abnormal and invalid data segments have been removed from the trip trajectory data, the interference of abnormal situations on the model training or statistical analysis corresponding to routine driving route planning and time estimation is greatly reduced. Based on a more accurate effective trip database, when using the trip trajectory data processing method based on this application to implement various navigation algorithms, more accurate navigation results can be obtained.

[0144] Figure 6 This is a schematic diagram of a travel trajectory data processing device according to an embodiment of this application. The travel trajectory data processing device 210 includes a travel trajectory acquisition module 211, an invalid travel segment identification module 212, and a trajectory segmentation module 213.

[0145] The trip trajectory acquisition module 211 is used to acquire the trip trajectory data of the vehicle, wherein the trip trajectory data includes data of multiple trajectory points sorted by acquisition time.

[0146] The invalid travel segment identification module 212 is used to identify invalid travel segments in the travel trajectory data, wherein the invalid travel segment contains trajectory points corresponding to abnormal states, wherein the abnormal states include at least one of the following: abnormal collection time interval between adjacent trajectory points; abnormal driving path corresponding to the trajectory point; and abnormal order status corresponding to the trajectory point.

[0147] The trajectory segmentation module 213 is used to segment the travel trajectory data based on invalid travel segments, and to take the segmented data other than invalid travel segments as valid travel segments.

[0148] In some embodiments, the invalid travel segment identification module 212 identifies invalid travel segments in the travel trajectory data, including: identifying travel segments in the travel trajectory data whose endpoints are adjacent trajectory points with a collection time interval greater than a preset first duration, as invalid travel segments with abnormal collection time intervals.

[0149] In some embodiments, the invalid travel segment identification module 212 identifies invalid travel segments in the travel trajectory data, including: identifying travel segments in the travel trajectory data where the positions of all trajectory points fall within a first predetermined area range within a preset second time period, as invalid travel segments with abnormal travel paths.

[0150] In some embodiments, identifying a travel segment in the travel trajectory data where the positions of all trajectory points fall within a first predetermined area within a preset second time period as an invalid travel segment with an abnormal travel path includes: obtaining a sampling interval between adjacent trajectory points based on the travel trajectory data; obtaining a sliding window and a sliding step size based on the second time period and the sampling interval; sequentially extracting corresponding travel segments from the travel trajectory data according to the sliding window and the sliding step size; and identifying a travel segment in each extracted travel segment where the positions of all trajectory points fall within the first predetermined area as an invalid travel segment with an abnormal travel path.

[0151] In some embodiments, identifying a travel segment in which the positions of all trajectory points fall within a first predetermined area as an invalid travel segment with an abnormal driving path includes: obtaining the geometric center of each trajectory point within each travel segment; and identifying a travel segment in which the distance from each trajectory point to the geometric center is less than a first distance threshold as an invalid travel segment with an abnormal driving path.

[0152] In some embodiments, after identifying a travel segment with an abnormal travel path, the method further includes: obtaining the location of traffic lights within the area to which the travel trajectory data belongs; and identifying invalid travel segments with abnormal travel paths that fall within a second predetermined area around any traffic light, and canceling the determination of invalid travel segments with abnormal travel paths.

[0153] In some embodiments, after identifying a travel segment with an abnormal travel path, the method further includes: sequentially calculating the distance between each trajectory point in the invalid travel segment with an abnormal travel path and the starting trajectory point of the invalid travel segment; and canceling the determination of the invalid travel segment with an abnormal travel path when the distance changes in an increasing trend.

[0154] In some embodiments, the invalid trip segment identification module 212 identifies invalid trip segments in the trip trajectory data, including: querying whether there is order status information corresponding to the trip trajectory data, where the order status includes one or more of the following: en route to pick up passengers, en route to carry passengers, waiting for passengers after accepting orders, empty driving without accepting orders, or not accepting orders; when corresponding order status information exists, filtering the trip trajectory data according to the order status information, specifically including:

[0155] The order status information is matched with the trip trajectory data, and the trip trajectory is segmented according to different order statuses to obtain the trip segments corresponding to each order status; and

[0156] Based on the trip segments corresponding to the order status, identify any one or more of the following trip segments: trip segments corresponding to the order acceptance and waiting for customers status, trip segments corresponding to the order not accepted and empty driving status, or trip segments corresponding to the order not accepted status, and use them as trajectory points corresponding to invalid trip segments of abnormal order status.

[0157] The trip trajectory acquisition module 211 acquires the vehicle's trip trajectory data, including:

[0158] Obtain satellite positioning data corresponding to the vehicle's journey;

[0159] Data cleaning is performed on satellite positioning data to obtain trajectory data corresponding to the actual location of the vehicle. Data cleaning includes removing at least one of physically erroneous data, incomplete data, and logically abnormal data.

[0160] By matching the trajectory data corresponding to the vehicle's actual location with the road network topology data of the known area where the vehicle's journey takes place, the road segment information in the road network topology corresponding to each trajectory point in the trajectory data corresponding to the vehicle's actual location is obtained; and

[0161] The vehicle's travel trajectory data is obtained based on the trajectory data corresponding to the vehicle's actual location and the road segment information in the road network topology corresponding to each trajectory point.

[0162] The apparatus in this application embodiment can execute the method provided in this application embodiment, and the implementation principle is similar. The actions performed by each module in the apparatus of each embodiment of this application correspond to the steps in the method of each embodiment of this application. For detailed functional descriptions and effect descriptions of each module of the apparatus, please refer to the descriptions in the corresponding methods shown above, which will not be repeated here.

[0163] This application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory. The processor executes the computer program to implement the steps of the method for processing travel trajectory data according to the first aspect of this application.

[0164] This electronic device identifies abnormal travel segments, such as abnormal collection time intervals between adjacent trajectory points, abnormal driving paths corresponding to trajectory points, and abnormal order statuses corresponding to trajectory points. It then segments the travel trajectory containing abnormal travel segments, enabling the obtained effective travel segments to more accurately reflect the most frequently used or relatively efficient route selections for the vehicle's purposeful journey from origin to destination. This provides a more reliable data source for subsequent activities such as building a travel database based on the vehicle's travel trajectory data or for navigation.

[0165] Furthermore, when using the data processed by the trip trajectory data processing method based on this application to implement various navigation algorithms, more accurate navigation results will be obtained.

[0166] In one alternative embodiment, an electronic device is provided, such as Figure 7 As shown, Figure 7 The illustrated electronic device 4000 includes a processor 4001 and a memory 4003. The processor 4001 and the memory 4003 are connected, for example, via a bus 4002. Optionally, the electronic device 4000 may further include a transceiver 4004, which can be used for data interaction between the electronic device and other electronic devices, such as sending and / or receiving data. It should be noted that in practical applications, the transceiver 4004 is not limited to one type, and the structure of the electronic device 4000 does not constitute a limitation on the embodiments of this application.

[0167] Processor 4001 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 4001 may also be a combination that implements computational functions, such as including one or more microprocessor combinations, a combination of a DSP and a microprocessor, etc.

[0168] Bus 4002 may include a pathway for transmitting information between the aforementioned components. Bus 4002 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. Bus 4002 can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used to represent it in the figure, but this does not indicate that there is only one bus or one type of bus.

[0169] The memory 4003 may be ROM (Read Only Memory) or other types of static storage devices capable of storing static information and instructions, RAM (Random Access Memory) or other types of dynamic storage devices capable of storing information and instructions, or EEPROM (Electrically Erasable Programmable Read Only Memory), CD-ROM (Compact Disc Read Only Memory) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media, other magnetic storage devices, or any other medium capable of carrying or storing computer programs and capable of being read by a computer, without limitation herein.

[0170] The memory 4003 stores computer programs that execute embodiments of this application, and its execution is controlled by the processor 4001. The processor 4001 executes the computer programs stored in the memory 4003 to implement the steps shown in the foregoing method embodiments.

[0171] Electronic devices include, but are not limited to: computers, servers, cloud computing facilities, etc.

[0172] This application provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it can implement the steps and corresponding content of the aforementioned method embodiments.

[0173] This application also provides a computer program product, including a computer program that, when executed by a processor, can implement the steps and corresponding content of the aforementioned method embodiments.

[0174] Generally, computer instructions for implementing the methods of this invention can be carried on any combination of one or more computer-readable media. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. A non-transitory computer-readable medium can include any computer-readable medium except for the signal itself, which is temporarily propagating.

[0175] Computer-readable storage media can be, for example—but not limited to—electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in connection with an instruction execution system, apparatus, or device.

[0176] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including—but not limited to—electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of transmitting, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0177] The program code contained on a computer-readable medium may be transmitted using any suitable medium, including—but not limited to—wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0178] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the target computer, partially on the target computer, as a standalone software package, partially on the target computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the target computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0179] The terms "first," "second," "third," "fourth," "1," "2," etc. (if present) in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in a sequence other than that shown in the figures or text.

[0180] It should be understood that although arrows indicate various operation steps in the flowcharts of this application's embodiments, the order in which these steps are implemented is not limited to the order indicated by the arrows. Unless explicitly stated herein, in some implementation scenarios of this application's embodiments, the implementation steps in each flowchart can be executed in other orders as required. Furthermore, some or all steps in each flowchart, based on the actual implementation scenario, may include multiple sub-steps or multiple stages. Some or all of these sub-steps or stages can be executed at the same time, and each sub-step or stage can also be executed at different times. In scenarios where execution times differ, the execution order of these sub-steps or stages can be flexibly configured according to requirements, and this application's embodiments do not limit this.

[0181] The above are only optional implementation methods for some implementation scenarios of this application. It should be noted that for those skilled in the art, other similar implementation methods based on the technical concept of this application, without departing from the technical concept of this application, also fall within the protection scope of the embodiments of this application.

Claims

1. A method for processing travel trajectory data, characterized in that, include: Acquire vehicle travel trajectory data, wherein the travel trajectory data includes data of multiple trajectory points sorted by collection time; Identify invalid travel segments in the travel trajectory data, wherein the invalid travel segments contain trajectory points corresponding to abnormal states; and The travel trajectory data is segmented based on the invalid travel segments, and the segmented data excluding the invalid travel segments is taken as the valid travel segments. The step of identifying invalid travel segments in the travel trajectory data includes: If there is order status information corresponding to the trip trajectory data, the order status includes one or more of the following: accepting orders and waiting for customers, not accepting orders and driving empty, or not accepting orders; the order status information is matched with the trip trajectory data, and the trip trajectory is segmented according to different order statuses to obtain the trip segments corresponding to each order status; Based on the trip segments corresponding to the order status, identify any one or more of the trip segments corresponding to the order-accepting and waiting-for-customers status, the trip segments corresponding to the order-not-accepting and empty-running status, or the trip segments corresponding to the order-not-accepting status, and use them as trajectory points corresponding to invalid trip segments of abnormal order status. The abnormal state includes at least one of the following: abnormal time interval between adjacent trajectory points; abnormal driving path corresponding to the trajectory point; abnormal order status corresponding to the trajectory point.

2. The method for processing travel trajectory data according to claim 1, characterized in that, The process of identifying invalid travel segments in the travel trajectory data includes: In the travel trajectory data, travel segments with adjacent trajectory points whose acquisition time interval is greater than a preset first duration are identified as invalid travel segments with abnormal acquisition time intervals.

3. The method for processing travel trajectory data according to claim 1, characterized in that, The process of identifying invalid travel segments in the travel trajectory data includes: In the identified travel trajectory data, if the positions of all trajectory points fall within a first predetermined area within a preset second time period, they are considered invalid travel segments with abnormal travel paths.

4. The method for processing travel trajectory data according to claim 3, characterized in that, In the process of identifying the travel trajectory data, within a preset second time period, all trajectory points whose positions fall within a first predetermined area are considered invalid travel segments due to abnormal travel paths, including: Based on the travel trajectory data, the sampling interval between adjacent trajectory points is obtained; Based on the second duration and the sampling interval, a sliding window of corresponding size and a sliding step size are obtained; According to the sliding window and the sliding step size, the corresponding travel segments are sequentially extracted from the travel trajectory data; and In each segment of travel, the travel segments in which the positions of all trajectory points fall within the first predetermined area are identified as invalid travel segments with abnormal travel paths.

5. The method for processing travel trajectory data according to claim 4, characterized in that, The segment identified in the process where all trajectory points fall within a first predetermined area is considered an invalid segment due to an abnormal travel path, including: For each captured travel segment, obtain the geometric center of each trajectory point within the travel segment; and In the extracted travel segments, those where the distance from each trajectory point to the geometric center is less than a first distance threshold are identified as invalid travel segments with abnormal travel paths.

6. The method for processing travel trajectory data according to claim 3, characterized in that, After identifying the abnormal travel segment, the process also includes: Obtain the location of traffic lights within the area to which the travel trajectory data belongs; and Identify invalid travel segments with abnormal travel paths that fall within a second predetermined area around any traffic light, and cancel the determination of invalid travel segments with abnormal travel paths.

7. The method for processing travel trajectory data according to claim 3, characterized in that, After identifying the abnormal travel segment, the process also includes: Calculate the distance between each trajectory point in the invalid travel segment of the abnormal driving path and the starting trajectory point of the invalid travel segment in sequence; and When the distance changes in an increasing trend, the determination of invalid travel segments with abnormal travel paths is cancelled.

8. The method for processing travel trajectory data according to any one of claims 1-7, characterized in that, The acquisition of vehicle travel trajectory data includes: Obtain satellite positioning data corresponding to the vehicle's journey; The satellite positioning data is cleaned to obtain trajectory data corresponding to the actual location of the vehicle. The data cleaning includes removing at least one of physically erroneous data, incomplete data, and logically abnormal data. The trajectory data corresponding to the vehicle's actual location is matched with the road network topology data of the known area to which the vehicle's journey takes place, to obtain the road segment information in the road network topology corresponding to each trajectory point in the trajectory data corresponding to the vehicle's actual location; and The vehicle's travel trajectory data is obtained based on the trajectory data corresponding to the vehicle's actual location and the road segment information in the road network topology corresponding to each trajectory point.

9. A traffic navigation method, characterized in that, include: Obtain the travel trajectory data processed by the travel trajectory data processing method according to any one of claims 1-8; Based on the processed travel trajectory data, perform one or more of the following navigation operations: A valid travel trajectory dataset is constructed based on the processed travel trajectory data, and the valid travel trajectory dataset is used as the training set for training the neural network. The trained neural network is then used for navigation. Estimate the traffic flow of road segments within the area to which the processed travel trajectory data belongs based on the processed travel trajectory data; The travel time between the starting point and the destination within the area to which the travel trajectory data belongs is estimated based on the processed travel trajectory data; Based on the processed travel trajectory data, path planning is performed between the starting point and the ending point within the area to which the travel trajectory data belongs; or The electronic map of the area to which the processed travel trajectory data belongs is corrected based on the processed travel trajectory data.

10. A device for processing travel trajectory data, characterized in that, include: The trip trajectory acquisition module is used to acquire the trip trajectory data of the vehicle, wherein the trip trajectory data includes data of multiple trajectory points sorted by acquisition time; An invalid trip segment identification module is used to identify invalid trip segments in the trip trajectory data, wherein the invalid trip segments include trajectory points corresponding to abnormal states, wherein the abnormal states include at least one of the following: abnormal collection time interval between adjacent trajectory points; abnormal driving path corresponding to the trajectory point; abnormal order status corresponding to the trajectory point; and The trajectory segmentation module is used to segment the travel trajectory data based on the invalid travel segments, and to take the segmented data other than the invalid travel segments as valid travel segments; The invalid travel segment identification module identifies invalid travel segments in the travel trajectory data, including: If there is order status information corresponding to the trip trajectory data, the order status includes one or more of the following: accepting orders and waiting for customers, not accepting orders and driving empty, or not accepting orders; the order status information is matched with the trip trajectory data, and the trip trajectory is segmented according to different order statuses to obtain the trip segments corresponding to each order status; Based on the travel segments corresponding to the order status, identify any one or more of the travel segments corresponding to the order-accepting and waiting-for-customers status, the travel segments corresponding to the order-not-accepting and empty-running status, or the travel segments corresponding to the order-not-accepting status, and use them as trajectory points corresponding to invalid travel segments of abnormal order statuses.

11. An electronic device comprising a memory, a processor, and a computer program stored in the memory, characterized in that, The processor executes the computer program to implement the steps of the method for processing travel trajectory data according to any one of claims 1-8.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the method for processing travel trajectory data according to any one of claims 1-8.

13. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the method for processing travel trajectory data according to any one of claims 1-8.

Images