Trip chain processing method and device, storage medium and processor

Abstract

The present application discloses a method and device for processing a travel chain, a storage medium, and a processor. The method includes: performing cluster analysis on the positioning points in the target location service data based on a spatiotemporal clustering algorithm to obtain a plurality of candidate stay point sets of the target object and a non-stay point set of the target object; screening and processing the plurality of candidate stay point sets to obtain a starting point set and a destination point set of the target object, and connecting the starting point in the starting point set, the destination point in the destination point set, and the non-stay point in the non-stay point set to obtain an initial travel chain; based on the first feature information set between the positioning points in the initial travel chain, identifying the travel mode to obtain a target travel chain. The present application solves the technical problem in the related art that most of the travel chains are determined based on dense and uniform trajectory data, which are easily interfered by noise points and outliers, resulting in relatively low accuracy of the travel chain.

Description

Technical Field

[0001] The present application relates to the field of transportation technology, and more specifically, to a method and device for processing a travel chain, a storage medium, and a processor. Background Art

[0002] With the development of urbanization and motorization, the radius of residents' travel activities has gradually expanded, and the means of transportation used have become increasingly diverse. Travel demand analysis is the fundamental basis for transportation planning and management departments to make relevant decisions. Therefore, accurately obtaining travel demand is particularly important for transportation planning and design. Existing methods mostly target dense and uniform trajectory data, which is significantly affected by noise and outliers. They also have poor recognition performance for sparse trajectories with uneven sampling, resulting in missing trip chain information and low trip chain recognition rates.

[0003] Most of the above-mentioned related technologies determine travel chains based on dense uniform trajectory data, which is easily interfered by noise points and outliers, resulting in relatively low accuracy of travel chains. No effective solution has been proposed so far. Summary of the Invention

[0004] The embodiments of the present application provide a method and apparatus for processing a travel chain, a storage medium, and a processor to at least address the technical problem in related arts that most travel chains determined based on dense uniform trajectory data are easily interfered with by noise points and outliers, resulting in relatively low accuracy of the travel chain.

[0005] According to one aspect of an embodiment of the present application, a method for processing a travel chain is provided, comprising: obtaining target location service data, wherein the target location service data includes at least data information of multiple positioning points of a target object; performing cluster analysis on the positioning points in the target location service data based on a spatiotemporal clustering algorithm to obtain a plurality of candidate stay point sets and a non-stay point set of the target object, wherein the candidate stay point set includes a plurality of candidate stay points, and the non-stay point set includes a plurality of non-stay points; screening the plurality of candidate stay point sets to obtain a departure point set and a destination point set of the target object. , and connect the departure points in the departure point set, the destination points in the destination point set, and the non-stop points in the non-stop point set to obtain an initial travel chain; based on the first feature information set between the positioning points in the initial travel chain, identify the travel mode to obtain a target travel chain, wherein the target travel chain includes the travel mode of the target object, wherein the first feature information set at least includes: travel speed information from the previous positioning point to the current positioning point, distance information from the previous positioning point to the current positioning point, distance information from the current positioning point to the bus station, and distance information from the current positioning point to the rail transit station.

[0006] Furthermore, cluster analysis is performed on the positioning points in the target location service data based on a spatiotemporal clustering algorithm to obtain a set of candidate stay points for the target object and a set of non-stay points for the target object, including: determining the target data information of the positioning points in the target location service data, wherein the target data information at least includes the timestamp of the positioning points in the target location service data, the speed corresponding to the positioning points in the target location service data, and the latitude and longitude information of the positioning points in the target location service data; setting a spatial neighborhood constraint amount and a temporal neighborhood constraint amount, and based on the spatial neighborhood constraint amount, the temporal neighborhood constraint amount and the target data information, cluster analysis is performed on the positioning points in the target location service data to obtain a plurality of candidate stay point sets for the target object and a set of non-stay points for the target object.

[0007] Furthermore, the multiple candidate stay point sets are screened to obtain the starting point set and the destination point set of the target object, including: calculating the initial stay state of the candidate stay points in each candidate stay point set and the ending stay state of the candidate stay points in each candidate stay point set; and determining the starting point set and / or the destination point set of the target object from the multiple candidate stay point sets based on the initial stay state and the ending stay state.

[0008] Furthermore, if there is no departure point set and / or destination point set in the multiple candidate stay point sets, the method also includes: obtaining the historical travel patterns of the target object and constructing a stay point prediction model based on the historical travel patterns; predicting the current travel of the target object based on the stay point prediction model to obtain the travel points and / or destination points of the target object.

[0009] Furthermore, obtaining the target location service data includes: obtaining original location service data, and determining the first location service data of the target object from the original location service data, wherein the original location service data includes data information of the positioning points of multiple objects; sorting the positioning points in the first location service data in time, and calculating characteristic parameter information between adjacent positioning points, wherein the characteristic parameter information includes at least: the distance between the adjacent positioning points, the time difference between the adjacent positioning points, the speed between the adjacent positioning points and the direction angle between the adjacent positioning points; screening the positioning points in the first location service data according to the characteristic parameter information to obtain the target location service data.

[0010] Furthermore, screening the positioning points in the first location service data based on the characteristic parameter information to obtain the target location service data includes: determining the position accuracy of the positioning points in the first location service data, and screening the positioning points based on the position accuracy and the speed between the adjacent positioning points to obtain the second location service data; determining the sampling accuracy of the positioning points in the second location service data, and screening the positioning points based on the sampling accuracy to obtain the third location service data; constructing a feature matrix based on the distance between the adjacent positioning points, the time difference between the adjacent positioning points, the speed between the adjacent positioning points and the direction angle between the adjacent positioning points; judging whether the positioning points in the third location service data are oscillating based on the feature matrix, and correcting or deleting the oscillating positioning points to obtain the target location service data.

[0011] Furthermore, based on the first feature information set between the positioning points in the initial travel chain, the travel mode is identified to obtain the target travel chain, including: slicing the initial travel chain according to the spatial density to obtain multiple target slice travel chains, and extracting features from the positioning points in each target slice travel chain to obtain the first feature information set of the positioning points of each target slice travel chain; discretizing and normalizing the first feature information set of the positioning points of each slice travel chain according to the preset quantile point to obtain the second feature information set; based on the second feature information set, performing consistency clustering on each target slice travel chain through the K-means clustering algorithm to obtain the number of target classifications, and determining the category information of each target slice travel chain according to the number of target classifications; identifying the travel mode based on the category information of each target slice travel chain and the second feature information set to obtain the target travel chain containing the travel mode.

[0012] Furthermore, before the travel mode is identified based on the category information of each target slice travel chain and the first feature information set to obtain the target travel chain, the method includes: if it is detected that the category information of the first target slice travel chain is different from the category information of the second target slice travel chain, then obtaining a third feature information set between the positioning points in the second target slice travel chain, wherein the first target slice travel chain and the second target slice travel chain are adjacent target slice travel chains; based on the third feature information set, determining whether the travel mode of the second target slice travel chain is different from the travel mode of the first target slice travel chain based on the classification tree; if the travel mode of the second target slice travel chain is the same as the travel mode of the first target slice travel chain, then changing the category information of the second target slice travel chain to the category information of the first target slice travel chain.

[0013] Furthermore, travel mode identification is performed based on the category information of each target slice travel chain and the first feature information set to obtain the target travel chain, including: merging the target slice travel chains with the same category information to obtain multiple target slice travel chain groups; determining the fourth feature information set between the positioning points in each target slice travel chain group, and obtaining a travel mode prediction model; inputting the fourth feature information set into the travel mode prediction model, and outputting the travel mode of each target slice travel chain group through the travel mode prediction model; and obtaining a target travel chain including the travel mode based on the travel mode of each target slice travel chain group.

[0014] According to another aspect of an embodiment of the present application, a travel chain processing device is further provided, including: a first acquisition unit, configured to acquire target location service data, wherein the target location service data includes at least data information of multiple positioning points of a target object; an analysis unit, configured to perform cluster analysis on the positioning points in the target location service data based on a spatiotemporal clustering algorithm to obtain multiple candidate stay point sets and a non-stay point set of the target object, wherein the candidate stay point set includes multiple candidate stay points, and the non-stay point set includes multiple non-stay points; a processing unit, configured to screen the multiple candidate stay point sets to obtain a starting point set and a destination point set of the target object, and connect the starting points in the starting point set, the destination points in the destination point set, and the non-stay points in the non-stay point set to obtain an initial travel chain; and an identification unit, configured to identify a travel mode based on a first feature information set between the positioning points in the initial travel chain to obtain a target travel chain, wherein the target travel chain includes the travel mode of the target object.

[0015] Furthermore, the analysis unit includes: a first determination module, used to determine the target data information of the positioning point in the target location service data, wherein the target data information includes at least the timestamp of the positioning point in the target location service data, the speed corresponding to the positioning point in the target location service data, and the latitude and longitude information of the positioning point in the target location service data; a setting module, used to set the spatial neighborhood constraint amount and the temporal neighborhood constraint amount, and based on the spatial neighborhood constraint amount, the temporal neighborhood constraint amount and the target data information, perform cluster analysis on the positioning points in the target location service data to obtain multiple candidate stay point sets of the target object and the non-stay point set of the target object.

[0016] Furthermore, the processing unit includes: a calculation module for calculating the initial stay state of each candidate stay point set and the end stay state of each candidate stay point set; a second determination module for determining the starting point set and / or destination point set of the target object from the multiple candidate stay point sets based on the initial stay state and the end stay state.

[0017] Furthermore, the device also includes: a second acquisition unit, which is used to obtain the historical travel patterns of the target object and construct a stay point prediction model based on the historical travel patterns if there is no departure point set and / or destination point set in the multiple candidate stay point sets; a prediction unit, which is used to predict the current travel of the target object based on the stay point prediction model to obtain the travel points and / or destination points of the target object.

[0018] Furthermore, the first acquisition unit includes: a third determination module, used to obtain original location service data, and determine the first location service data of the target object from the original location service data, wherein the original location service data includes data information of the positioning points of multiple objects; a sorting module, used to time-sort the positioning points in the first location service data, and calculate characteristic parameter information between adjacent positioning points, wherein the characteristic parameter information includes at least: the distance between the adjacent positioning points, the time difference between the adjacent positioning points, the speed between the adjacent positioning points and the direction angle between the adjacent positioning points; a screening module, used to screen the positioning points in the first location service data according to the characteristic parameter information to obtain the target location service data.

[0019] Furthermore, the screening module includes: a first determination submodule, used to determine the position accuracy of the positioning points in the first position service data, and screen the positioning points based on the position accuracy and the speed between the adjacent positioning points to obtain the second position service data; a second determination submodule, used to determine the sampling accuracy of the positioning points in the second position service data, and screen the positioning points based on the sampling accuracy to obtain the third position service data; a construction submodule, used to construct a feature matrix based on the distance between the adjacent positioning points, the time difference between the adjacent positioning points, the speed between the adjacent positioning points and the direction angle between the adjacent positioning points; a judgment submodule, used to judge whether the positioning points in the third position service data are oscillating based on the feature matrix, and correct or delete the oscillating positioning points to obtain the target position service data.

[0020] Furthermore, the identification unit includes: an extraction module for slicing the initial travel chain according to spatial density to obtain multiple target slice travel chains, and performing feature extraction on the positioning points in each target slice travel chain to obtain a first feature information set of the positioning points of each target slice travel chain; a processing module for discretizing and normalizing the first feature information set of the positioning points of each slice travel chain according to a preset quantile point to obtain a second feature information set; a clustering module for performing consistency clustering on each target slice travel chain based on the second feature information set using a K-means clustering algorithm to obtain the number of target classifications, and determining the category information of each target slice travel chain based on the number of target classifications; an identification module for performing travel mode identification based on the category information of each target slice travel chain and the second feature information set to obtain a target travel chain containing the travel mode.

[0021] Furthermore, the device includes: a third acquisition unit, for identifying the travel mode based on the category information of each target slice travel chain and the first feature information set, and before obtaining the target travel chain, if it is detected that the category information of the first target slice travel chain is different from the category information of the second target slice travel chain, then obtaining the third feature information set between the positioning points in the second target slice travel chain, wherein the first target slice travel chain and the second target slice travel chain are adjacent target slice travel chains; a judgment unit, for determining whether the travel mode of the second target slice travel chain is different from the travel mode of the first target slice travel chain based on the classification tree according to the third feature information set; a change unit, for changing the category information of the second target slice travel chain to the category information of the first target slice travel chain if the travel mode of the second target slice travel chain is the same as the travel mode of the first target slice travel chain.

[0022] Furthermore, the identification module includes: a processing submodule, which is used to merge the target slice travel chains of the same category information to obtain multiple target slice travel chain groups; a second determination submodule, which is used to determine the fourth feature information set between the positioning points in each target slice travel chain group and obtain a travel mode prediction model; a prediction submodule, which is used to input the fourth feature information set into the travel mode prediction model and output the travel mode of each target slice travel chain group through the travel mode prediction model; a third determination submodule, which is used to obtain the target travel chain based on the travel mode of each target slice travel chain group.

[0023] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided, which stores a program. When the program is executed, the device where the storage medium is located is controlled to execute any one of the above-mentioned methods for processing a travel chain.

[0024] According to another aspect of an embodiment of the present invention, an electronic device is provided, including: a memory storing an executable program; and a processor for running the program, wherein the program executes the above-mentioned travel chain processing method when running.

[0025] In an embodiment of the present application, target location service data is obtained, wherein the target location service data includes at least data information of multiple positioning points of the target object; the positioning points in the target location service data are clustered and analyzed based on a spatiotemporal clustering algorithm to obtain multiple candidate stay point sets and a non-stay point set of the target object, wherein the candidate stay point set includes multiple candidate stay points, and the non-stay point set includes multiple non-stay points; the multiple candidate stay point sets are screened to obtain a starting point set and a destination point set of the target object, and the starting point in the starting point set, the destination point in the destination point set, and the non-stay points in the non-stay point set are connected to obtain an initial travel chain; based on the first feature information set between the positioning points in the initial travel chain, the travel mode is identified to obtain a target travel chain, wherein the target travel chain includes the travel mode of the target object, which solves the technical problem in the related art that most travel chains are determined based on dense and uniform trajectory data, which are easily interfered by noise points and outliers, resulting in relatively low accuracy of the travel chain. In this solution, location service data is first preprocessed to address common issues with location service data, such as location point drift, duplication / redundancy, and accuracy. A spatiotemporal clustering algorithm is then used to extract candidate stopover points from all the locations in the location service data to generate an initial trip chain. Finally, based on this initial trip chain, travel modes are identified. The trip chain containing these travel modes, referred to as the target trip chain, is derived from location service data, which offers advantages such as high positioning accuracy, wide coverage, high penetration, and rich information. The spatiotemporal clustering algorithm considers both temporal and spatial proximity, effectively handles poor signal quality and unevenly sampled trajectory segments, and is less susceptible to interference from noise points and outliers, thereby improving the accuracy of the trip chain. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0027] Figure 1 is a schematic diagram of a computer terminal provided according to Embodiment 1 of the present invention;

[0028] Figure 2 This is a flowchart of a method for processing a travel chain according to the first embodiment of the present application;

[0029] Figure 3 is a schematic diagram of a target travel chain provided according to Example 1 of the present application;

[0030] Figure 4 is a flowchart of an optional travel chain processing method provided in accordance with the first embodiment of the present application;

[0031] Figure 5 This is a flowchart of a method for processing a travel chain according to the second embodiment of the present application;

[0032] Figure 6 is a schematic diagram of a processing device for a travel chain provided according to the third embodiment of the present application;

[0033] Figure 7 This is a schematic diagram of a computer terminal provided according to Example 4 of the present application. DETAILED DESCRIPTION

[0034] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this application.

[0035] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in a sequence other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0036] First, some nouns or terms that appear in the description of the embodiments of the present application are subject to the following interpretations:

[0037] LBS: Location-based services (LBS) use various types of positioning technologies to obtain the current location of positioning devices and provide information resources and basic services to positioning devices through the mobile Internet;

[0038] Trip chain: a combination of a series of trips between the starting point and the end point, including one or more intermediate activity points;

[0039] Positioning point: Location-based services use various types of positioning technologies to obtain the current location of the positioning device based on a fixed time period. Each positioning is called a positioning point.

[0040] Stop point: the location where the user stops during the trip;

[0041] Departure point: where the user departs from on this trip; Destination point: where the user's destination is on this trip;

[0042] Purpose trip: a complete trip made by the traveler according to the travel purpose;

[0043] Mode of travel: In a complete trip, the travel segments are divided according to different travel modes;

[0044] ST-DBSCAN:Spat ia l Tempora l-Dens ity Based Spat ia l Cluster ingof App l icat ions with Noi se, a density clustering algorithm based on spatiotemporal neighbor constraints;

[0045] K-Means: k-means cl uster ing a lgor ithm, k-means clustering algorithm.

[0046] Example 1

[0047] According to an embodiment of the present application, a method for processing a travel chain is also provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0048] The method embodiment provided in the first embodiment of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Figure 1 The hardware structure block diagram of a computer terminal (or mobile device) for implementing the processing method of the travel chain is shown. Figure 1As shown, the computer terminal 10 (or mobile device 10) may include one or more (illustrated as 102a, 102b, ..., 102n) processors (the processor may include but is not limited to a microprocessor MCU or a programmable logic device FPGA, etc.), a memory 104 for storing data, and a transmission module 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the BUS bus), a network interface, a power supply and / or a camera. It will be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components than shown, or with Figure 1 Different configurations shown.

[0049] It should be noted that the one or more processors and / or other data processing circuits described above may generally be referred to herein as "data processing circuitry." The data processing circuitry may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuitry may be a single, independent processing module, or may be fully or partially integrated into any of the other components of the computer terminal 10 (or mobile device).

[0050] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the travel chain processing method in the embodiment of the present application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, implementing the above-mentioned travel chain processing method. The memory 104 may include a high-speed random access memory and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely located relative to the processor, and these remote memories may be connected to the computer terminal 10 via a network. Examples of the above-mentioned network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0051] The transmission device 106 is used to receive or send data via a network. A specific example of the network may include a wireless network provided by the communications provider of the computer terminal 10. In one embodiment, the transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to enable communication with the Internet. In another embodiment, the transmission device 106 may be a radio frequency (RF) module for wireless communication with the Internet.

[0052] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the computer terminal 10 (or mobile device).

[0053] With the development of urbanization and motorization, the radius of residents' travel activities has gradually expanded, and the means of transportation used have become increasingly diverse. Travel demand analysis is the basis for transportation planning and management departments to make relevant decisions. Therefore, how to obtain accurate travel demand is particularly important for transportation planning and design. Traditional methods based on travel surveys have problems such as long collection cycles, high costs, and incomplete information. With the development of information technology and the popularization of tools such as mobile communication devices that record GPS trajectory data, more detailed and rich travel trajectory information has been recorded in large quantities. Travel chain identification is the basis for identifying various travel information. Before various travel analysis studies, it is crucial to identify the different travel segments and stop points in user travel behavior.

[0054] In the above technical background, this application provides Figure 2 The processing method of the trip chain shown. Figure 2 This is a flowchart of a method for processing a travel chain according to the first embodiment of the present application, specifically including:

[0055] Step S201: acquiring target location service data, wherein the target location service data at least includes data information of multiple positioning points of a target object;

[0056] Specifically, location-based services (LBS) data refers to the geographic coordinates of users recorded when mobile terminals use wireless communication networks (or satellite positioning systems) to provide services to users. Compared to traditional mobile phone signaling data, LBS data offers advantages such as high accuracy, wide coverage, and rich information. LBS data analysis can be used to uncover travel information about mobile users, serving as a key basis for decision-making in areas such as traffic assessment and planning.

[0057] Therefore, the original location service data (LBS data) including multiple objects is obtained. The LBS data has problems such as positioning point drift, positioning point duplication / redundancy and positioning point accuracy. In order to solve the above problems, the LBS data is preprocessed to obtain the target location service data.

[0058] Step S202: performing cluster analysis on the positioning points in the target location service data based on a spatiotemporal clustering algorithm to obtain a plurality of candidate stay point sets and a non-stay point set of the target object, wherein the candidate stay point set includes a plurality of candidate stay points, and the non-stay point set includes a plurality of non-stay points;

[0059] Specifically, after the target location service data is obtained through preprocessing, all the positioning point data of the same traveler (i.e., the target object mentioned above) are obtained from the target location service data through the traveler's ID. The spatial proximity and temporal proximity of the positioning points are considered simultaneously through the spatiotemporal clustering algorithm (ST-DBSCAN) to identify the traveler's candidate stay point set and non-stay point set.

[0060] Step S203: Filter multiple candidate stay point sets to obtain a departure point set and a destination point set of the target object, and connect the departure points in the departure point set, the destination points in the destination point set, and the non-stay points in the non-stay point set to obtain an initial trip chain.

[0061] Specifically, the set of candidate stop points obtained through the spatiotemporal clustering algorithm may include the traveler's starting and destination points, as well as a set of misidentified non-stop points. For example, a traveler's waiting time at a bus stop may be mistakenly identified as a stop. Therefore, the candidate stop point set needs to be processed through judgment and screening to obtain the traveler's starting and destination points.

[0062] After determining the set of departure points, destination points, and non-stop points, these points are connected in chronological order to form the initial trip chain. Since the current initial trip chain only includes relevant information such as the departure point and destination points, it is also necessary to identify the travel mode.

[0063] In step S204, the travel mode is identified based on the first feature information set between the positioning points in the initial travel chain to obtain a target travel chain, wherein the target travel chain includes the travel mode of the target object, and the first feature information set includes at least: travel speed information from the previous positioning point to the current positioning point, distance information from the previous positioning point to the current positioning point, distance information from the current positioning point to the bus stop, and distance information from the current positioning point to the rail transit station.

[0064] Specifically, a first feature information set between each positioning point in the initial travel chain is obtained. The first feature information set includes at least the following information: travel speed from the previous positioning point to the current positioning point, distance from the previous positioning point to the current positioning point, shortest distance from the current positioning point to the bus stop, shortest distance from the current positioning point to the rail transit station, etc. The appearance mode is identified through the above first feature information set to obtain a target travel chain containing the travel mode, for example, Figure 3 It should be noted that the positioning points in the initial travel chain are the above-mentioned starting point, destination point and non-stop point.

[0065] In summary, this solution first preprocesses location service data to address common issues with location service data, such as location point drift, duplication / redundancy, and accuracy. A spatiotemporal clustering algorithm is then used to extract candidate stopover points from all the locations in the location service data to generate an initial trip chain. Finally, based on this initial trip chain, travel modes are identified. The trip chain containing these travel modes, referred to as the target trip chain, is derived from location service data, which offers advantages such as high positioning accuracy, wide coverage, high penetration, and rich information. The spatiotemporal clustering algorithm considers both temporal and spatial proximity, effectively handles poor signal quality and unevenly sampled trajectory segments, and is less susceptible to interference from noise points and outliers, thereby improving the accuracy of the trip chain.

[0066] In order to improve the accuracy of stay point identification, cluster analysis is performed on the positioning points in the target location service data based on the spatiotemporal clustering algorithm to obtain a set of candidate stay points of the target object and a set of non-stay points of the target object, including the following steps: determining the target data information of the positioning point in the target location service data, wherein the target data information at least includes the timestamp of the positioning point in the target location service data, the speed corresponding to the positioning point in the target location service data, and the latitude and longitude information of the positioning point in the target location service data; setting a spatial neighborhood constraint amount and a temporal neighborhood constraint amount, and based on the spatial neighborhood constraint amount, the temporal neighborhood constraint amount and the target data information, performing cluster analysis on the positioning points in the target location service data to obtain multiple candidate stay point sets of the target object and a set of non-stay points of the target object.

[0067] Specifically, the trajectory dataset D (i.e. the target location service data mentioned above) sets the spatial neighborhood constraint E1 and the temporal neighborhood constraint E2, and sets the minimum number of positioning points in a cluster set. Where: D = {t, v, d} = {(t1, t2, ... t n ), (v1, v2, ...v n ), (d1, d2, ... d n)}, t is the timestamp, v is the speed, d is the latitude and longitude information of the positioning point, according to the spatial neighborhood constraint E1 and the temporal neighborhood constraint E2 and the minimum number of positioning points in a cluster set, the positioning points in the trajectory dataset are clustered and analyzed. The clusters C and noise N are obtained after clustering. Cluster C is the corresponding set of multiple candidate stay points, and noise N is the corresponding set of non-stay points, where:

[0068]

[0069] Moreover, i<k<k<n. n It is a cluster with similar characteristics obtained by clustering, that is, a set of candidate stay points.

[0070] N=[N1, N2,...,N1,...,N m ,...,N n ]

[0071] Among them, l<m<n, the noise N is fragmented, and the features between the noises are not obvious. Therefore, the noise corresponds to the above-mentioned non-stop point set.

[0072] In summary, the spatiotemporal clustering algorithm considers both temporal and spatial proximity, can better cope with trajectory segments with poor signals and uneven sampling, and improves the accuracy of stay point identification.

[0073] Clusters obtained based on the similarity between trajectory points are considered to be identified stay points. However, the identification of sparse trajectories may easily result in missing stay points. To address this issue, the trip chain processing method provided in the first embodiment of the present invention further includes the following:

[0074] Screening multiple candidate stay point sets to obtain a starting point set and a destination point set of a target object includes: calculating an initial stay state of each candidate stay point in the candidate stay point set and an ending stay state of each candidate stay point in the candidate stay point set; and determining a starting point set and / or a destination point set of the target object from the multiple candidate stay point sets based on the initial stay state and the ending stay state.

[0075] If the starting point set and / or the destination point set do not exist in the multiple candidate stay point sets, the method further includes: obtaining the historical travel patterns of the target object and building a stay point prediction model based on the historical travel patterns; and predicting the current travel of the target object based on the stay point prediction model to obtain the travel points and / or the destination points of the target object.

[0076] Specifically, first determine whether there is a starting point set and / or a destination point set in the multiple candidate stay point sets obtained by clustering identification. Candidate stay point set C = [C1, C2, ... C n], for each candidate stay point set such as C i =[(t i ,...t j ), (v i ,...v j ), (d i ,...d j )], calculation starts the stay state End the stay status Based on the start and end stay states, it is determined whether the candidate stay point set is a departure point set or a destination point set. For example, if the stay time of a candidate stay point set is relatively short based on the start and end stay states, the candidate stay point set is considered not to be a departure point set or a destination point set.

[0077] If the target location service data is a relatively sparse trajectory, the actual starting and destination points may not exist in the candidate stop point set. Therefore, in order to obtain a complete trip chain, the starting and destination points that were omitted due to missing data are supplemented by the following method:

[0078] First, the historical travel patterns of the traveler (the target person) are obtained. For example, during a certain time period, the traveler will go from home to work, or from work to the mall to eat. Then, using the traveler's historical travel patterns as a training set, a stop point prediction model is trained to predict stop points. The stop point prediction model is then used to predict the traveler's current trip, resulting in the target person's departure points and / or destination.

[0079] In summary, the ST-DBSCAN clustering method, based on temporal and spatial proximity, is used to identify stop points, effectively addressing poor signal quality and unevenly sampled trajectories. Furthermore, a stop point prediction model is developed based on travelers' historical travel patterns to complement missing stop points due to sparse data sampling. These steps improve the accuracy of identifying travel chains.

[0080] Data cleaning and processing will directly affect the effectiveness of LBS data mining. Data cleaning can filter out abnormal or redundant data and improve the accuracy of downstream algorithm calculations.

[0081] Therefore, obtaining the target location service data includes the following steps: determining the first location service data of the target object from the original location service data; sorting the positioning points in the first location service data in time, and calculating the characteristic parameter information between adjacent positioning points, wherein the characteristic parameter information at least includes: the distance between adjacent positioning points, the time difference between adjacent positioning points, the speed between adjacent positioning points and the direction angle between adjacent positioning points; screening the positioning points in the first location service data according to the characteristic parameter information to obtain the target location service data.

[0082] Screening the positioning points in the first location service data based on the characteristic parameter information to obtain the target location service data includes: determining the position accuracy of the positioning points in the first location service data, and screening the positioning points based on the position accuracy and the speed between adjacent positioning points to obtain the second location service data; determining the sampling accuracy of the positioning points in the second location service data, and screening the positioning points based on the sampling accuracy to obtain the third location service data; constructing a feature matrix based on the distance between adjacent positioning points, the time difference between adjacent positioning points, the speed between adjacent positioning points and the direction angle between adjacent positioning points; judging whether the positioning points in the third location service data are oscillating based on the feature matrix, and correcting or deleting the oscillating positioning points to obtain the target location service data.

[0083] Specifically, the main problems with raw LBS data include positioning point drift, positioning point duplication / redundancy, positioning point accuracy, etc. To address the above problems, data preprocessing mainly includes the following steps:

[0084] (1) Anchor point feature extraction: The anchor points of the same user ID are sorted in time, and characteristic parameters such as the distance between adjacent anchor points (dis_to), the time difference between adjacent anchor points (time_to), the speed between adjacent anchor points (speed_to), and the direction angle (ang_to) are calculated as the basis for downstream analysis.

[0085] (2) Low-quality positioning point filtering: Based on the position accuracy of the positioning points, the speed between adjacent positioning points and other characteristic parameters, the positioning points with low positioning accuracy or obviously unreasonable are filtered.

[0086] (3) Duplicate / redundant data processing: For the same positioning point data collected by multiple data sources, the data can be retained or filtered according to the level of data source collection accuracy. For high-frequency sampling points in a small range, redundant points can also be filtered by downsampling without affecting the trajectory quality.

[0087] (4) Abnormal drift point processing: By constructing a feature matrix of moving distance, time, speed, direction angle, etc. between adjacent positioning points, it can identify whether there is oscillation and perform correction or deletion operations on the oscillating positioning points.

[0088] In summary, by preprocessing the raw location service data, abnormal or redundant data can be filtered out, thereby improving the precision and accuracy of downstream stop point identification and trip chain determination.

[0089] In order to improve the accuracy of travel mode identification, the travel mode is identified based on the first feature information set between the positioning points in the initial travel chain, and the target travel chain is obtained, including the following steps: slicing the initial travel chain according to the spatial density to obtain multiple target slice travel chains, and extracting features from the positioning points in each target slice travel chain to obtain the first feature information set of the positioning points of each target slice travel chain; discretizing and normalizing the first feature information set of the positioning points of each slice travel chain according to the preset quantile point to obtain the second feature information set; based on the second feature information set, performing consistency clustering on each target slice travel chain by the K-means clustering algorithm to obtain the number of target classifications, and determining the category information of each target slice travel chain according to the number of target classifications; identifying the travel mode based on the category information of each target slice travel chain and the second feature information set to obtain the target travel chain containing the travel mode.

[0090] Specifically, the form of the initial trip chain obtained by connecting the departure point in the departure point set, the destination point in the destination point set, and the non-stop points in the non-stop point set can be as follows:

[0091] T=[Trj m , Trj m+1 ,...Trj n ]={(t m , t m+1 ,...t n ), (v m , v m+1 ,...v n ), (d m , d m+1 ,...d n )};

[0092] Based on the complete initial travel chain, travel segments are cut for subsequent refined travel mode identification, transfer and connection analysis, etc.

[0093] The initial travel chain is sliced ​​and the feature information set between the positioning points in the sliced ​​travel chain (i.e., the first feature information set mentioned above) is extracted, including features such as speed, time, distance to bus stops and rail transit stops, etc., to identify the travel mode of the sliced ​​travel chain and obtain the target travel chain containing the travel mode.

[0094] First, the initial travel chain is sliced ​​according to the spatial density, and the feature information of the positioning points in the multiple sliced ​​travel chains is extracted to obtain the feature information set T = [TC m , TC m+1 ,...TC n ], TC m This is the first feature information set mentioned above, where speed_to m is the travel speed from the previous positioning point m-1 to the current positioning point m, dis_to m is the distance from the previous positioning point m-1 to the current positioning point m, disto_bus m is the shortest distance from the current location m to the bus station, disto_metro m It should be noted that the initial travel chain can be sliced ​​by the distance between the starting point and the destination point.

[0095] Then, the first feature information set of the positioning points of each sharded travel chain is discretized and normalized according to the 25%, 50%, and 75% quantiles to obtain the second feature information set. The second feature information set is clustered consistently using the K-Means (K-means clustering algorithm) to obtain the optimal number of target classifications K and the category information of each sharded travel chain. It should be noted that the K-means clustering algorithm is used here to classify each sharded travel chain, rather than directly obtaining the travel mode corresponding to each sharded travel chain.

[0096] Finally, the travel mode of the fragmented travel chain under each category is identified through the category information of each fragmented travel chain and the second feature information set, and the target travel chain containing the travel mode is obtained.

[0097] Since travelers may transfer during the actual travel process, before the travel mode is identified based on the category information of each target slice travel chain and the first feature information set to obtain the target travel chain, the method also includes: if it is detected that the category information of the first target slice travel chain and the category information of the second target slice travel chain are different, then the third feature information set between the positioning points in the second target slice travel chain is obtained, wherein the first target slice travel chain and the second target slice travel chain are adjacent target slice travel chains; based on the third feature information set, it is determined whether the travel mode of the second target slice travel chain is different from the travel mode of the first target slice travel chain based on the classification tree; if the travel mode of the second target slice travel chain is the same as the travel mode of the first target slice travel chain, then the category information of the second target slice travel chain is changed to the category information of the first target slice travel chain.

[0098] Travel mode identification is performed based on the category information and the first feature information set of each target slice travel chain to obtain the target travel chain, including: merging the target slice travel chains with the same category information to obtain multiple target slice travel chain groups; determining the fourth feature information set between the positioning points in each target slice travel chain group, and obtaining a travel mode prediction model; inputting the fourth feature information set into the travel mode prediction model, and outputting the travel mode of each target slice travel chain group through the travel mode prediction model; and obtaining a target travel chain including the travel mode based on the travel mode of each target slice travel chain group.

[0099] Specifically, first, when the Type of the adjacent slice trip chain (ie, the first target slice trip chain and the second target slice trip chain) is detected m With Type m+1 If they are different, the third feature information set between the positioning points in the second target segment travel chain is obtained. The third feature information set includes at least the following information: type_dur: duration, type_dis: starting and ending distance, is_se: whether it is the starting point type or the destination point type. Based on the third feature information set, the classification tree is used to determine whether the travel mode of the second target segment travel chain is different from that of the first target segment travel chain. That is, the Type m+1 Is it really a travel chain of a new travel mode, or just a noise point?

[0100] Then, if the travel mode of the second target shard travel chain is the same as that of the first target shard travel chain, the category information of the second target shard travel chain is changed to the category information of the first target shard travel chain, that is, the first target shard travel chain and the second target shard travel chain are of the same category. If the travel mode of the second target shard travel chain is different from that of the first target shard travel chain, the category information of the second target shard travel chain remains unchanged.

[0101] Secondly, the target segmented travel chains of the same category information are merged into a target segmented travel chain group, and then the fourth feature information set between the positioning points in each target segmented travel chain group is determined. The fourth feature information set includes at least the following information: the travel speed from the previous positioning point m-1 to the current positioning point m, the distance from the previous positioning point m-1 to the current positioning point m, the shortest distance from the current positioning point m to the bus station, and the shortest distance from the current positioning point m to the rail transit station.

[0102] Finally, the travel mode prediction model is obtained, and the above-mentioned feature information set is input into the travel mode prediction model. The travel mode prediction model outputs the travel mode of each target segment travel chain group; according to the travel mode of each target segment travel chain group, the target travel chain containing the travel mode is obtained, that is, Figure 3 The target travel chain is shown. It should be noted that the travel mode prediction model matches the most appropriate travel mode based on the feature information set in each target segmented travel chain group. The travel mode prediction model is trained using travel chains with known travel modes.

[0103] In an optional embodiment, after obtaining the target travel chain including the travel mode, a traffic travel demand analysis can be performed based on the target travel chain to obtain traffic travel demand information, and then traffic planning can be performed based on the traffic travel demand information.

[0104] In an optional embodiment, the following may be used: Figure 4 The flowchart shown implements the processing of the trip chain. Step 1: LBS data preprocessing: (1) positioning point feature extraction; (2) low-quality positioning point filtering; (3) duplicate / redundant data processing and (4) abnormal drift point processing. Step 2: Stay point identification: trajectory dataset D, spatial neighborhood constraint E1, temporal neighborhood constraint E2, and the minimum number of cluster points M. Among them:

[0105] D={t, v, d}={(t1, t2,...t n ), (v1, v2, ...v n ), (d1, d2, ... d n )}, t is the timestamp, v is the speed, d is the positioning latitude and longitude information, and the candidate stay point set C = [C1, C2, ... C n ]. Step 3: Destination trip identification: Based on the start stop state and the end stop state, determine the starting point set and the destination point set from the candidate stop point set. If the starting point set and the destination point set are missing, the starting point or destination point is predicted based on the user's historical travel pattern and the stop point prediction model. The positioning points are spliced ​​together to obtain the initial trip chain. Step 4: Mode trip segmentation: Extract the positioning point features of the initial trip chain The feature set is discretized and normalized, and cluster analysis is performed using the K-means clustering algorithm to obtain the target travel chain of travel modes.

[0106] In summary, 1) the data source adopts location-based service (LBS) data, which has the advantages of high positioning accuracy, wide coverage, high penetration, and rich information compared to traditional mobile phone signaling data. 2) Potential stay points are identified based on ST-DBSCAN, and missing stay points are supplemented based on the probability distribution of the user's historical stay points to form a complete destination travel chain. This method takes into account both temporal and spatial proximity, and can better deal with poor signals and uneven sampling trajectory segments. 3) Different slicing and modeling features are adopted for the complete travel chain according to trajectories with the same density, and slice travel modes are classified based on K-Means to identify transfer points in the complete travel chain, and the complete travel chain is divided into multiple travel chains corresponding to different travel modes, effectively dealing with uneven sampling and sparse sampling trajectory segments. Therefore, the travel chain processing method provided by Example 1 of the present invention can effectively improve the accuracy of the travel chain.

[0107] In the travel chain processing method provided in the first embodiment of the present invention, target location service data is obtained, wherein the target location service data at least includes data information of multiple positioning points of the target object; the positioning points in the target location service data are clustered and analyzed based on a spatiotemporal clustering algorithm to obtain multiple candidate stay point sets and a non-stay point set of the target object, wherein the candidate stay point set includes multiple candidate stay points, and the non-stay point set includes multiple non-stay points; the multiple candidate stay point sets are screened to obtain a starting point set and a destination point set of the target object, and the starting point in the starting point set, the destination point in the destination point set, and the non-stay points in the non-stay point set are connected to obtain an initial travel chain; based on the first feature information set between the positioning points in the initial travel chain, the travel mode is identified to obtain a target travel chain, wherein the target travel chain includes the travel mode of the target object. This solves the technical problem in the related art that most travel chains are determined based on dense and uniform trajectory data, which is easily interfered by noise points and outliers, resulting in relatively low accuracy of the travel chain. In this solution, location service data is first preprocessed to address common location service data issues such as location point drift, duplication / redundancy, and location point accuracy, thereby improving subsequent calculation accuracy. A spatiotemporal clustering algorithm is then used to extract candidate stop points from all the location service data points to generate an initial trip chain. Finally, based on this initial trip chain, travel modes are identified. The trip chain containing these travel modes, referred to as the target trip chain, is derived from location service data, which offers advantages such as high positioning accuracy, wide coverage, high penetration, and rich information. The spatiotemporal clustering algorithm considers both temporal and spatial proximity, effectively handles poor signal quality and unevenly sampled trajectory segments, and is less susceptible to interference from noise points and outliers, thereby improving the accuracy of the trip chain.

[0108] It should be noted that for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by this application.

[0109] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus the necessary general hardware platform, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods of each embodiment of the present application.

[0110] Example 2

[0111] According to an embodiment of the present invention, a method for processing a travel chain is also provided. Figure 5 As shown, the method includes:

[0112] Step S501: obtaining original location service data sent by the client;

[0113] Step S502: pre-processing the original location service data in the cloud server to obtain target location service data, performing cluster analysis on the positioning points in the target location service data based on a spatiotemporal clustering algorithm to obtain multiple candidate stay point sets and a non-stay point set of the target object, screening the multiple candidate stay point sets to obtain a starting point set and a destination point set of the target object, and connecting the starting point in the starting point set, the destination point in the destination point set, and the non-stay points in the non-stay point set to obtain an initial travel chain; identifying the travel mode based on the first feature information set between the positioning points in the initial travel chain to obtain a target travel chain, wherein the original location service data includes data information of the positioning points of multiple objects, and the target location service data includes data information of at least multiple positioning points of the target object; wherein the candidate stay point set includes multiple candidate stay points, the non-stay point set includes multiple non-stay points, and the target travel chain includes the travel mode of the target object;

[0114] Step S503: Return the target travel link to the client.

[0115] In the cloud server, the specific method for processing the travel chain is the same as that in Example 1 and will not be repeated here.

[0116] It should be noted that for the aforementioned method embodiments, for simplicity of description, they are all expressed as a series of action combinations. However, those skilled in the art should be aware that the present invention is not limited by the order of the actions described, because according to the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0117] Through the description of the above embodiments, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus the necessary general hardware platform, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods of various embodiments of the present invention.

[0118] Example 3

[0119] According to an embodiment of the present application, a device for implementing the above-mentioned processing method of the travel chain is also provided, such as Figure 6 As shown, the device includes: a first acquisition unit 601, an analysis unit 602, a processing unit 603 and an identification unit 604.

[0120] The first acquisition unit 601 is configured to acquire target location service data, wherein the target location service data at least includes data information of multiple positioning points of a target object;

[0121] An analyzing unit 602 is configured to perform cluster analysis on the positioning points in the target location service data based on a spatiotemporal clustering algorithm to obtain a plurality of candidate stay point sets and a non-stay point set of the target object, wherein the candidate stay point set includes a plurality of candidate stay points, and the non-stay point set includes a plurality of non-stay points;

[0122] The processing unit 603 is configured to screen the plurality of candidate stay point sets to obtain a departure point set and a destination point set of the target object, and connect the departure points in the departure point set, the destination points in the destination point set, and the non-stay points in the non-stay point set to obtain an initial trip chain;

[0123] The identification unit 604 is configured to identify the travel mode according to the first feature information set between the positioning points in the initial travel chain, and obtain a target travel chain, wherein the target travel chain includes the travel mode of the target object.

[0124] In the trip chain processing device provided in the third embodiment of the present invention, a first acquisition unit 601 acquires target location service data, wherein the target location service data includes at least data information of multiple positioning points of a target object. An analysis unit 602 performs cluster analysis on the positioning points in the target location service data based on a spatiotemporal clustering algorithm to obtain multiple candidate stay point sets and a non-stay point set of the target object, wherein the candidate stay point set includes multiple candidate stay points, and the non-stay point set includes multiple non-stay points. A processing unit 603 screens the multiple candidate stay point sets to obtain a starting point set and a destination point set of the target object, and connects the starting points in the starting point set, the destination points in the destination point set, and the non-stay points in the non-stay point set to obtain an initial trip chain. An identification unit 604 identifies travel modes based on a first feature information set between the positioning points in the initial trip chain to obtain a target trip chain, wherein the target travel chain includes the travel mode of the target object. This solves the technical problem in the related art that most travel chains determined based on dense uniform trajectory data are easily interfered with by noise points and outliers, resulting in relatively low accuracy of the travel chain. In this solution, location-based service data is first preprocessed to address common issues with location-based service data, such as drift, duplication / redundancy, and accuracy, to improve subsequent computational accuracy. A spatiotemporal clustering algorithm is then used to extract candidate stopover points from all the locations in the location-based service data to generate an initial trip chain. Finally, based on this initial trip chain, travel modes are identified. The trip chain containing these travel modes, referred to as the target trip chain, is derived from location-based service (LBS) data, which offers advantages such as high positioning accuracy, wide coverage, high penetration, and rich information. The spatiotemporal clustering algorithm considers both temporal and spatial proximity, effectively handles poor signal quality and unevenly sampled trajectory segments, and is less susceptible to interference from noise points and outliers, thereby improving the accuracy of the trip chain.

[0125] Optionally, in the travel chain processing device provided in Example 3 of the present invention, the analysis unit 602 includes: a first determination module, used to determine the target data information of the positioning point in the target location service data, wherein the target data information includes at least the timestamp of the positioning point in the target location service data, the speed corresponding to the positioning point in the target location service data, and the latitude and longitude information of the positioning point in the target location service data; a setting module, used to set the spatial neighborhood constraint amount and the temporal neighborhood constraint amount, and based on the spatial neighborhood constraint amount, the temporal neighborhood constraint amount and the target data information, perform cluster analysis on the positioning points in the target location service data to obtain multiple candidate stay point sets of the target object and a non-stay point set of the target object.

[0126] Optionally, in the travel chain processing device provided in Example 3 of the present invention, the processing unit 603 includes: a calculation module for calculating the initial stay state of the candidate stay points in each candidate stay point set and the end stay state of the candidate stay points in each candidate stay point set; a second determination module for determining the starting point set and / or destination point set of the target object from multiple candidate stay point sets based on the initial stay state and the end stay state.

[0127] Optionally, in the travel chain processing device provided in Example 3 of the present invention, the device also includes: a second acquisition unit, used to obtain the historical travel patterns of the target object if there is no departure point set and / or destination point set in multiple candidate stay point sets, and to construct a stay point prediction model based on the historical travel patterns; a prediction unit, used to predict the current travel of the target object based on the stay point prediction model to obtain the travel points and / or destination points of the target object.

[0128] Optionally, in the travel chain processing device provided in Example 3 of the present invention, the first acquisition unit 601 includes: a third determination module, used to determine the first location service data of the target object from the original location service data; a sorting module, used to time-sort the positioning points in the first location service data, and calculate the characteristic parameter information between adjacent positioning points, wherein the characteristic parameter information includes at least: the distance between adjacent positioning points, the time difference between adjacent positioning points, the speed between adjacent positioning points and the direction angle between adjacent positioning points; a screening module, used to screen the positioning points in the first location service data according to the characteristic parameter information to obtain the target location service data.

[0129] Optionally, in the travel chain processing device provided in Example 3 of the present invention, the screening module includes: a first determination submodule, used to determine the position accuracy of the positioning points in the first position service data, and screen the positioning points based on the position accuracy and the speed between adjacent positioning points to obtain second position service data; a second determination submodule, used to determine the sampling accuracy of the positioning points in the second position service data, and screen the positioning points based on the sampling accuracy to obtain third position service data; a construction submodule, used to construct a feature matrix based on the distance between adjacent positioning points, the time difference between adjacent positioning points, the speed between adjacent positioning points and the direction angle between adjacent positioning points; a judgment submodule, used to judge whether the positioning points in the third position service data are oscillating based on the feature matrix, and correct or delete the oscillating positioning points to obtain target position service data.

[0130] Optionally, in the travel chain processing device provided in Example 3 of the present invention, the identification unit includes: an extraction module, which is used to slice the initial travel chain according to spatial density to obtain multiple target slice travel chains, and perform feature extraction on the positioning points in each target slice travel chain to obtain a first feature information set of the positioning points of each target slice travel chain; a processing module, which is used to discretize and normalize the first feature information set of the positioning points of each slice travel chain according to a preset quantile point to obtain a second feature information set; a clustering module, which is used to perform consistency clustering on each target slice travel chain based on the second feature information set using the K-means clustering algorithm to obtain the number of target classifications, and determine the category information of each target slice travel chain based on the number of target classifications; an identification module, which is used to identify the travel mode based on the category information of each target slice travel chain and the second feature information set to obtain a target travel chain containing the travel mode.

[0131] Optionally, in the travel chain processing device provided in Example 3 of the present invention, the device includes: a third acquisition unit, used to identify the travel mode based on the category information of each target slice travel chain and the first feature information set, and before obtaining the target travel chain, if it is detected that the category information of the first target slice travel chain and the category information of the second target slice travel chain are different, then obtain the third feature information set between the positioning points in the second target slice travel chain, wherein the first target slice travel chain and the second target slice travel chain are adjacent target slice travel chains; a judgment unit, used to determine whether the travel mode of the second target slice travel chain is different from the travel mode of the first target slice travel chain based on the classification tree according to the third feature information set; a change unit, used to change the category information of the second target slice travel chain to the category information of the first target slice travel chain if the travel mode of the second target slice travel chain is the same as that of the first target slice travel chain.

[0132] Optionally, in the travel chain processing device provided in Example 3 of the present invention, the identification module includes: a processing submodule, which is used to merge the target slice travel chains of the same category information to obtain multiple target slice travel chain groups; a second determination submodule, which is used to determine the fourth feature information set between the positioning points in each target slice travel chain group and obtain a travel mode prediction model; a prediction submodule, which is used to input the fourth feature information set into the travel mode prediction model, and output the travel mode of each target slice travel chain group through the travel mode prediction model; a third determination submodule, which is used to obtain the target travel chain based on the travel mode of each target slice travel chain group.

[0133] It should be noted that the first acquisition unit 601, analysis unit 602, processing unit 603, and identification unit 604 described above correspond to steps S201 to S204 in Example 1. The examples and application scenarios implemented by the units and corresponding steps are the same, but are not limited to those disclosed in Example 1. It should be noted that the above modules, as part of the apparatus, can be run in the computer terminal 10 provided in Example 1.

[0134] It should be noted that the preferred implementation scheme involved in the above embodiments of this application is the same as the scheme provided in Example 1, as well as the application scenario and implementation process, but is not limited to the scheme provided in Example 1.

[0135] Example 4

[0136] The embodiment of the present application can provide a computer terminal, which can be any computer terminal device in a computer terminal group. Optionally, in this embodiment, the computer terminal can also be replaced by a terminal device such as a mobile terminal.

[0137] Optionally, in this embodiment, the computer terminal may be located in at least one network device among a plurality of network devices of a computer network.

[0138] In this embodiment, the above-mentioned computer terminal can execute the program code of the following steps in the travel chain processing method: obtaining target location service data, wherein the target location service data includes at least data information of multiple positioning points of the target object; performing cluster analysis on the positioning points in the target location service data based on the spatiotemporal clustering algorithm to obtain multiple candidate stay point sets and non-stay point sets of the target object, wherein the candidate stay point set includes multiple candidate stay points, and the non-stay point set includes multiple non-stay points; screening the multiple candidate stay point sets to obtain the starting point set and the destination point set of the target object, and connecting the starting point in the starting point set, the destination point in the destination point set, and the non-stay points in the non-stay point set to obtain an initial travel chain; identifying the travel mode based on the first feature information set between the positioning points in the initial travel chain to obtain a target travel chain, wherein the target travel chain includes the travel mode of the target object.

[0139] The above-mentioned computer terminal can also execute the program code of the following steps in the travel chain processing method: clustering analysis is performed on the positioning points in the target location service data based on the spatiotemporal clustering algorithm to obtain a set of candidate stay points of the target object and a set of non-stay points of the target object, including: determining the target data information of the positioning point in the target location service data, wherein the target data information at least includes the timestamp of the positioning point in the target location service data, the speed corresponding to the positioning point in the target location service data and the latitude and longitude information of the positioning point in the target location service data; setting a spatial neighborhood constraint amount and a temporal neighborhood constraint amount, and based on the spatial neighborhood constraint amount, the temporal neighborhood constraint amount and the target data information, clustering analysis is performed on the positioning points in the target location service data to obtain multiple candidate stay point sets of the target object and a set of non-stay points of the target object.

[0140] The above-mentioned computer terminal can also execute the program code of the following steps in the travel chain processing method: screening and processing multiple candidate stay point sets to obtain the starting point set and destination point set of the target object, including: calculating the initial stay state of the candidate stay point in each candidate stay point set and the ending stay state of the candidate stay point in each candidate stay point set; based on the initial stay state and the ending stay state, determining the starting point set and / or destination point set of the target object from multiple candidate stay point sets.

[0141] The above-mentioned computer terminal can also execute the program code of the following steps in the travel chain processing method: if there is no departure point set and / or destination point set in multiple candidate stay point sets, the method also includes: obtaining the historical travel patterns of the target object, and constructing a stay point prediction model based on the historical travel patterns; predicting the current travel of the target object based on the stay point prediction model to obtain the travel points and / or destination points of the target object.

[0142] The above-mentioned computer terminal can also execute the program code of the following steps in the travel chain processing method: Obtaining the target location service data includes: determining the first location service data of the target object from the original location service data; sorting the positioning points in the first location service data in time, and calculating the characteristic parameter information between adjacent positioning points, wherein the characteristic parameter information at least includes: the distance between adjacent positioning points, the time difference between adjacent positioning points, the speed between adjacent positioning points and the direction angle between adjacent positioning points; screening the positioning points in the first location service data according to the characteristic parameter information to obtain the target location service data.

[0143] The above-mentioned computer terminal can also execute the program code of the following steps in the travel chain processing method: screening the positioning points in the first location service data based on the characteristic parameter information to obtain the target location service data, including: determining the position accuracy of the positioning points in the first location service data, and screening the positioning points based on the position accuracy and the speed between adjacent positioning points to obtain the second location service data; determining the sampling accuracy of the positioning points in the second location service data, and screening the positioning points based on the sampling accuracy to obtain the third location service data; constructing a feature matrix based on the distance between adjacent positioning points, the time difference between adjacent positioning points, the speed between adjacent positioning points and the direction angle between adjacent positioning points; judging whether the positioning points in the third location service data are oscillating based on the feature matrix, and correcting or deleting the oscillating positioning points to obtain the target location service data.

[0144] The above-mentioned computer terminal can also execute the program code of the following steps in the travel chain processing method: based on the first feature information set between the positioning points in the initial travel chain, the travel mode is identified to obtain the target travel chain, including: slicing the initial travel chain according to the spatial density to obtain multiple target slice travel chains, and extracting features from the positioning points in each target slice travel chain to obtain the first feature information set of the positioning points of each target slice travel chain; discretizing and normalizing the first feature information set of the positioning points of each slice travel chain according to the preset quantile point to obtain the second feature information set; based on the second feature information set, performing consistency clustering on each target slice travel chain through the K-means clustering algorithm to obtain the target classification number, and determining the category information of each target slice travel chain based on the target classification number; identifying the travel mode based on the category information of each target slice travel chain and the second feature information set to obtain the target travel chain containing the travel mode.

[0145] The above-mentioned computer terminal can also execute the program code of the following steps in the travel chain processing method: before the travel mode is identified based on the category information and the first feature information set of each target slice travel chain to obtain the target travel chain, the method includes: if it is detected that the category information of the first target slice travel chain and the category information of the second target slice travel chain are different, then obtain the third feature information set between the positioning points in the second target slice travel chain, wherein the first target slice travel chain and the second target slice travel chain are adjacent target slice travel chains; based on the third feature information set, determine whether the travel mode of the second target slice travel chain is different from the travel mode of the first target slice travel chain based on the classification tree; if the travel mode of the second target slice travel chain is the same as the travel mode of the first target slice travel chain, then change the category information of the second target slice travel chain to the category information of the first target slice travel chain.

[0146] The above-mentioned computer terminal can also execute the program code of the following steps in the travel chain processing method: travel mode identification is performed based on the category information and the first feature information set of each target slice travel chain to obtain the target travel chain, including: merging the target slice travel chains with the same category information to obtain multiple target slice travel chain groups; determining the fourth feature information set between the positioning points in each target slice travel chain group, and obtaining a travel mode prediction model; inputting the fourth feature information set into the travel mode prediction model, and outputting the travel mode of each target slice travel chain group through the travel mode prediction model; based on the travel mode of each target slice travel chain group, obtaining a target travel chain containing the travel mode.

[0147] Optionally, Figure 7 This is a structural block diagram of a computer terminal according to an embodiment of the present application. Figure 7 As shown, the computer terminal 10 may include: one or more ( Figure 7 Only one is shown) processor, memory.

[0148] The memory can be used to store software programs and modules, such as the program instructions / modules corresponding to the travel chain processing method and device in the embodiments of the present application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, implementing the above-mentioned travel chain processing method. The memory may include a high-speed random access memory and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory may further include a memory remotely located relative to the processor, and these remote memories may be connected to the computer terminal 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0149] The processor can call the information and application stored in the memory through the transmission device to perform the following steps: obtaining target location service data, wherein the target location service data includes at least data information of multiple positioning points of the target object; performing cluster analysis on the positioning points in the target location service data based on the spatiotemporal clustering algorithm to obtain multiple candidate stay point sets and non-stay point sets of the target object, wherein the candidate stay point set includes multiple candidate stay points, and the non-stay point set includes multiple non-stay points; screening the multiple candidate stay point sets to obtain a starting point set and a destination point set of the target object, and connecting the starting point in the starting point set, the destination point in the destination point set, and the non-stay points in the non-stay point set to obtain an initial travel chain; identifying the travel mode based on the first feature information set between the positioning points in the initial travel chain to obtain a target travel chain, wherein the target travel chain includes the travel mode of the target object.

[0150] Optionally, the processor may also execute the program code of the following steps: performing cluster analysis on the positioning points in the target location service data based on a spatiotemporal clustering algorithm to obtain a set of candidate stay points for the target object and a set of non-stay points for the target object, including: determining the target data information of the positioning points in the target location service data, wherein the target data information includes at least the timestamp of the positioning points in the target location service data, the speed corresponding to the positioning points in the target location service data, and the latitude and longitude information of the positioning points in the target location service data; setting a spatial neighborhood constraint amount and a temporal neighborhood constraint amount, and performing cluster analysis on the positioning points in the target location service data based on the spatial neighborhood constraint amount, the temporal neighborhood constraint amount and the target data information to obtain multiple candidate stay point sets for the target object and a set of non-stay points for the target object.

[0151] Optionally, the processor may also execute the program code of the following steps: screening multiple candidate stay point sets to obtain the starting point set and destination point set of the target object, including: calculating the initial stay state of the candidate stay points in each candidate stay point set and the ending stay state of the candidate stay points in each candidate stay point set; determining the starting point set and / or destination point set of the target object from multiple candidate stay point sets based on the initial stay state and the ending stay state.

[0152] Optionally, the processor may also execute the program code of the following steps: if a departure point set and / or a destination point set do not exist in a set of multiple candidate stay points, the method further includes: obtaining the historical travel patterns of the target object, and constructing a stay point prediction model based on the historical travel patterns; predicting the current travel of the target object based on the stay point prediction model to obtain the travel points and / or destination points of the target object.

[0153] Optionally, the processor may also execute the program code of the following steps: obtaining the target location service data includes: determining the first location service data of the target object from the original location service data; sorting the positioning points in the first location service data by time, and calculating the characteristic parameter information between adjacent positioning points, wherein the characteristic parameter information includes at least: the distance between adjacent positioning points, the time difference between adjacent positioning points, the speed between adjacent positioning points, and the direction angle between adjacent positioning points; screening the positioning points in the first location service data according to the characteristic parameter information to obtain the target location service data.

[0154] Optionally, the processor may also execute the program code of the following steps: screening the positioning points in the first location service data based on the characteristic parameter information to obtain the target location service data, including: determining the position accuracy of the positioning points in the first location service data, and screening the positioning points based on the position accuracy and the speed between adjacent positioning points to obtain the second location service data; determining the sampling accuracy of the positioning points in the second location service data, and screening the positioning points based on the sampling accuracy to obtain the third location service data; constructing a feature matrix based on the distance between adjacent positioning points, the time difference between adjacent positioning points, the speed between adjacent positioning points and the direction angle between adjacent positioning points; judging whether the positioning points in the third location service data are oscillating based on the feature matrix, and correcting or deleting the oscillating positioning points to obtain the target location service data.

[0155] Optionally, the processor may also execute the program code of the following steps: based on the first feature information set between the positioning points in the initial travel chain, the travel mode is identified to obtain the target travel chain including: slicing the initial travel chain according to the spatial density to obtain multiple target slice travel chains, and extracting features from the positioning points in each target slice travel chain to obtain the first feature information set of the positioning points of each target slice travel chain; discretizing and normalizing the first feature information set of the positioning points of each slice travel chain according to the preset quantile point to obtain the second feature information set; based on the second feature information set, performing consistency clustering on each target slice travel chain using the K-means clustering algorithm to obtain the number of target classifications, and determining the category information of each target slice travel chain based on the number of target classifications; identifying the travel mode based on the category information of each target slice travel chain and the second feature information set to obtain the target travel chain containing the travel mode.

[0156] Optionally, the processor may also execute the program code of the following steps: before identifying the travel mode based on the category information of each target slice travel chain and the first feature information set to obtain the target travel chain, the method includes: if it is detected that the category information of the first target slice travel chain is different from the category information of the second target slice travel chain, obtaining a third feature information set between the positioning points in the second target slice travel chain, wherein the first target slice travel chain and the second target slice travel chain are adjacent target slice travel chains; based on the third feature information set, determining whether the travel mode of the second target slice travel chain is different from the travel mode of the first target slice travel chain based on the classification tree; if the travel mode of the second target slice travel chain is the same as the travel mode of the first target slice travel chain, changing the category information of the second target slice travel chain to the category information of the first target slice travel chain.

[0157] Optionally, the processor may also execute the program code for the following steps: identifying the travel mode based on the category information and the first feature information set of each target slice travel chain, and obtaining the target travel chain including: merging the target slice travel chains with the same category information to obtain multiple target slice travel chain groups; determining the fourth feature information set between the positioning points in each target slice travel chain group, and obtaining a travel mode prediction model; inputting the fourth feature information set into the travel mode prediction model, and outputting the travel mode of each target slice travel chain group through the travel mode prediction model; and obtaining a target travel chain including the travel mode based on the travel mode of each target slice travel chain group.

[0158] It can be understood by those skilled in the art that Figure 7 The structure shown is for illustration only, and the computer terminal may also be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a PDA, a mobile Internet device (Mobile Internet Devices, MI D), a PAD, or other terminal devices. Figure 7 It does not limit the structure of the above electronic device. For example, the computer terminal 10 may also include Figure 7 More or fewer components (such as network interfaces, display devices, etc.) shown in, or with Figure 7 Different configurations shown.

[0159] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the hardware related to the terminal device through a program, and the program can be stored in a computer-readable storage medium, which may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0160] Example 5

[0161] The embodiment of the present application further provides a computer-readable storage medium. Optionally, in this embodiment, the storage medium can be used to store the program code executed by the method for processing the trip chain provided in the first embodiment.

[0162] Optionally, in this embodiment, the storage medium may be located in any computer terminal in a computer terminal group in a computer network, or in any mobile terminal in a mobile terminal group.

[0163] Optionally, in this embodiment, the storage medium is configured to store program code for executing the following steps: obtaining target location service data, wherein the target location service data includes at least data information of multiple positioning points of the target object; performing cluster analysis on the positioning points in the target location service data based on a spatiotemporal clustering algorithm to obtain multiple candidate stay point sets of the target object and a non-stay point set of the target object, wherein the candidate stay point set includes multiple candidate stay points, and the non-stay point set includes multiple non-stay points; screening the multiple candidate stay point sets to obtain a starting point set and a destination point set of the target object, and connecting the starting point in the starting point set, the destination point in the destination point set, and the non-stay points in the non-stay point set to obtain an initial travel chain; identifying the travel mode based on the first feature information set between the positioning points in the initial travel chain to obtain a target travel chain, wherein the target travel chain includes the travel mode of the target object.

[0164] The above-mentioned storage medium is also configured to store program code for executing the following steps: clustering analysis of the positioning points in the target location service data based on the spatiotemporal clustering algorithm to obtain a set of candidate stay points of the target object and a set of non-stay points of the target object, including: determining the target data information of the positioning point in the target location service data, wherein the target data information at least includes the timestamp of the positioning point in the target location service data, the speed corresponding to the positioning point in the target location service data, and the latitude and longitude information of the positioning point in the target location service data; setting a spatial neighborhood constraint amount and a temporal neighborhood constraint amount, and based on the spatial neighborhood constraint amount, the temporal neighborhood constraint amount and the target data information, clustering analysis of the positioning points in the target location service data to obtain multiple candidate stay point sets of the target object and a set of non-stay points of the target object.

[0165] The above-mentioned storage medium is also configured to store program codes for executing the following steps: screening and processing multiple candidate stay point sets to obtain the starting point set and destination point set of the target object, including: calculating the initial stay state of the candidate stay points in each candidate stay point set and the ending stay state of the candidate stay points in each candidate stay point set; determining the starting point set and / or destination point set of the target object from multiple candidate stay point sets based on the initial stay state and the ending stay state.

[0166] The above-mentioned storage medium is also configured to store program code for executing the following steps: If there is no departure point set and / or destination point set in multiple candidate stay point sets, the method also includes: obtaining the historical travel patterns of the target object and constructing a stay point prediction model based on the historical travel patterns; predicting the current travel of the target object based on the stay point prediction model to obtain the travel points and / or destination points of the target object.

[0167] The above-mentioned storage medium is also configured to store program code for executing the following steps: obtaining target location service data includes: determining the first location service data of the target object from the original location service data; sorting the positioning points in the first location service data in time, and calculating the characteristic parameter information between adjacent positioning points, wherein the characteristic parameter information at least includes: the distance between adjacent positioning points, the time difference between adjacent positioning points, the speed between adjacent positioning points and the direction angle between adjacent positioning points; screening the positioning points in the first location service data according to the characteristic parameter information to obtain the target location service data.

[0168] The above-mentioned storage medium is also configured to store program codes for executing the following steps: screening the positioning points in the first location service data based on the characteristic parameter information to obtain the target location service data, including: determining the position accuracy of the positioning points in the first location service data, and screening the positioning points based on the position accuracy and the speed between adjacent positioning points to obtain the second location service data; determining the sampling accuracy of the positioning points in the second location service data, and screening the positioning points based on the sampling accuracy to obtain the third location service data; constructing a feature matrix based on the distance between adjacent positioning points, the time difference between adjacent positioning points, the speed between adjacent positioning points and the direction angle between adjacent positioning points; judging whether the positioning points in the third location service data are oscillating based on the feature matrix, and correcting or deleting the oscillating positioning points to obtain the target location service data.

[0169] The above-mentioned storage medium is also configured to store program codes for executing the following steps: based on the first feature information set between the positioning points in the initial travel chain, the travel mode is identified to obtain the target travel chain, including: slicing the initial travel chain according to the spatial density to obtain multiple target slice travel chains, and extracting features from the positioning points in each target slice travel chain to obtain the first feature information set of the positioning points of each target slice travel chain; discretizing and normalizing the first feature information set of the positioning points of each slice travel chain according to the preset quantile point to obtain the second feature information set; based on the second feature information set, performing consistency clustering on each target slice travel chain through the K-means clustering algorithm to obtain the number of target classifications, and determining the category information of each target slice travel chain based on the number of target classifications; identifying the travel mode based on the category information of each target slice travel chain and the second feature information set to obtain the target travel chain containing the travel mode.

[0170] The above-mentioned storage medium is also configured to store program codes for executing the following steps: before identifying the travel mode based on the category information and the first feature information set of each target slice travel chain to obtain the target travel chain, the method includes: if it is detected that the category information of the first target slice travel chain and the category information of the second target slice travel chain are different, then obtaining a third feature information set between the positioning points in the second target slice travel chain, wherein the first target slice travel chain and the second target slice travel chain are adjacent target slice travel chains; based on the third feature information set, determining whether the travel mode of the second target slice travel chain is different from the travel mode of the first target slice travel chain based on the classification tree; if the travel mode of the second target slice travel chain is the same as the travel mode of the first target slice travel chain, then changing the category information of the second target slice travel chain to the category information of the first target slice travel chain.

[0171] The above-mentioned storage medium is also configured to store program codes for executing the following steps: identifying the travel mode based on the category information and the first feature information set of each target slice travel chain, and obtaining the target travel chain including: merging the target slice travel chains with the same category information to obtain multiple target slice travel chain groups; determining the fourth feature information set between the positioning points in each target slice travel chain group, and obtaining a travel mode prediction model; inputting the fourth feature information set into the travel mode prediction model, and outputting the travel mode of each target slice travel chain group through the travel mode prediction model; obtaining a target travel chain including the travel mode based on the travel mode of each target slice travel chain group.

[0172] The serial numbers of the above embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0173] In the above embodiments of the present application, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0174] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0175] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0176] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0177] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0178] The above is only a preferred embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for processing a travel chain, characterized in that: include: Acquiring target location service data, wherein the target location service data at least includes data information of multiple positioning points of the target object; Performing cluster analysis on the positioning points in the target location service data based on a spatiotemporal clustering algorithm to obtain a plurality of candidate stay point sets of the target object and a non-stay point set of the target object, wherein the candidate stay point set includes a plurality of candidate stay points, and the non-stay point set includes a plurality of non-stay points; Filtering the plurality of candidate stay point sets to obtain a departure point set and a destination point set of the target object, and connecting the departure points in the departure point set, the destination points in the destination point set, and the non-stay points in the non-stay point set to obtain an initial travel chain; Based on the first feature information set between the positioning points in the initial travel chain, the travel mode is identified to obtain a target travel chain, wherein the target travel chain includes the travel mode of the target object, wherein the first feature information set includes at least: travel speed information from the previous positioning point to the current positioning point, distance information from the previous positioning point to the current positioning point, distance information from the current positioning point to the bus station, and distance information from the current positioning point to the rail transit station.

2. The method according to claim 1, characterized in that Performing cluster analysis on the positioning points in the target location service data based on a spatiotemporal clustering algorithm to obtain a set of candidate stay points for the target object and a set of non-stay points for the target object includes: Determine target data information of the positioning point in the target location service data, wherein the target data information includes at least a timestamp of the positioning point in the target location service data, a speed corresponding to the positioning point in the target location service data, and latitude and longitude information of the positioning point in the target location service data; A spatial neighborhood constraint amount and a temporal neighborhood constraint amount are set, and based on the spatial neighborhood constraint amount, the temporal neighborhood constraint amount and the target data information, a cluster analysis is performed on the positioning points in the target location service data to obtain multiple candidate stay point sets of the target object and a non-stay point set of the target object.

3. The method according to claim 1, characterized in that Screening the plurality of candidate stay point sets to obtain a set of departure points and a set of destination points of the target object includes: Calculating an initial stay state of each candidate stay point in the candidate stay point set and an ending stay state of each candidate stay point in the candidate stay point set; According to the initial stay state and the end stay state, a starting point set and / or a destination point set of the target object is determined from the plurality of candidate stay point sets.

4. The method according to claim 3, characterized in that If the plurality of candidate stay point sets do not include a departure point set and / or a destination point set, the method further includes: Obtaining the historical travel patterns of the target object and building a stop point prediction model based on the historical travel patterns; The current travel of the target object is predicted based on the stay point prediction model to obtain the travel points and / or destination points of the target object.

5. The method according to claim 1, wherein Acquiring the target location service data includes: Acquire original location service data, and determine first location service data of the target object from the original location service data, wherein the original location service data includes data information of positioning points of multiple objects; Time-sorting the positioning points in the first location service data, and calculating characteristic parameter information between adjacent positioning points, wherein the characteristic parameter information includes at least: the distance between the adjacent positioning points, the time difference between the adjacent positioning points, the speed between the adjacent positioning points, and the direction angle between the adjacent positioning points; The positioning points in the first location service data are screened according to the characteristic parameter information to obtain the target location service data.

6. The method according to claim 5, characterized in that Filtering the positioning points in the first location service data according to the characteristic parameter information to obtain the target location service data includes: Determining the position accuracy of the positioning points in the first location service data, and screening the positioning points according to the position accuracy and the speed between the adjacent positioning points to obtain second location service data; Determining a sampling accuracy of the positioning points in the second location service data, and screening the positioning points according to the sampling accuracy to obtain third location service data; Constructing a feature matrix according to the distance between the adjacent positioning points, the time difference between the adjacent positioning points, the speed between the adjacent positioning points, and the direction angle between the adjacent positioning points; It is determined whether the positioning points in the third location service data are oscillating according to the characteristic matrix, and the oscillating positioning points are corrected or deleted to obtain the target location service data.

7. The method according to claim 1, characterized in that Based on the first feature information set between the positioning points in the initial travel chain, the travel mode is identified to obtain a target travel chain including: Slicing the initial travel chain according to spatial density to obtain a plurality of target sliced ​​travel chains, and extracting features from the positioning points in each target sliced ​​travel chain to obtain a first feature information set of the positioning points in each target sliced ​​travel chain; Discretize and normalize the first feature information set of the positioning points of each sharded trip chain according to the preset quantiles to obtain a second feature information set; Based on the second feature information set, performing consistency clustering on each target shard trip chain using a K-means clustering algorithm to obtain a target classification number, and determining category information of each target shard trip chain based on the target classification number; Travel mode identification is performed based on the category information of each target segmented travel chain and the second feature information set to obtain a target travel chain including the travel mode.

8. The method according to claim 7, characterized in that Before identifying the travel mode based on the category information of each target segmented travel chain and the first feature information set to obtain the target travel chain, the method includes: If it is detected that the category information of the first target shard travel chain is different from the category information of the second target shard travel chain, obtaining a third feature information set between the positioning points in the second target shard travel chain, wherein the first target shard travel chain and the second target shard travel chain are adjacent target shard travel chains; Determining, based on the classification tree and according to the third feature information set, whether the travel mode of the second target segment travel chain is different from the travel mode of the first target segment travel chain; If the travel mode of the second target shard travel chain is the same as the travel mode of the first target shard travel chain, the category information of the second target shard travel chain is changed to the category information of the first target shard travel chain.

9. The method according to claim 7, characterized in that The travel mode is identified based on the category information of each target segmented travel chain and the first feature information set, and the target travel chain is obtained, including: Merge the target shard travel chains of the same category information to obtain multiple target shard travel chain groups; Determine the fourth feature information set between the positioning points in each target segment travel chain group and obtain a travel mode prediction model; Inputting the fourth feature information set into the travel mode prediction model, and outputting the travel mode of each target segment travel chain group through the travel mode prediction model; According to the travel mode of each target segment travel chain group, the target travel chain containing the travel mode is obtained.

10. A processing device for a travel chain, characterized in that: include: A first acquiring unit is configured to acquire target location service data, wherein the target location service data at least includes data information of multiple positioning points of the target object; an analyzing unit, configured to perform cluster analysis on the positioning points in the target location service data based on a spatiotemporal clustering algorithm to obtain a plurality of candidate stay point sets of the target object and a non-stay point set of the target object, wherein the candidate stay point set includes a plurality of candidate stay points, and the non-stay point set includes a plurality of non-stay points; a processing unit configured to screen the plurality of candidate stay point sets to obtain a departure point set and a destination point set of the target object, and connect the departure points in the departure point set, the destination points in the destination point set, and the non-stay points in the non-stay point set to obtain an initial travel chain; The identification unit is configured to identify the travel mode according to the first feature information set between the positioning points in the initial travel chain to obtain a target travel chain, wherein the target travel chain includes the travel mode of the target object.

11. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the storage medium is located is controlled to execute the method for processing a travel chain according to any one of claims 1 to 9.

12. An electronic device, characterized in that: include: a memory storing an executable program; A processor is used to run the program, wherein the program, when running, executes the travel chain processing method described in any one of claims 1 to 9.

Images