Grouping method, device and equipment for multi-source trajectory data

Abstract

The invention discloses a multi-source trajectory data grouping method, device and equipment, and the method comprises the steps: carrying out the travel segmentation of a single-vehicle full-amount trajectory based on the starting and ending point time and starting and ending point distance of the single-vehicle full-amount trajectory passing through a tile trajectory of an adjacent tile; judging whether the single-vehicle travel track segments after travel segmentation repeatedly pass through the same tile or not; if yes, whether the distance between the entry points entering the tile is smaller than a preset distance threshold value or not is judged; if yes, carrying out secondary segmentation on the same tile to obtain single-circle track data of the single-vehicle travel section; and based on the similarity of the single-circle trajectory data, grouping the single-circle trajectory data to obtain a plurality of single-circle trajectory groups. According to the method, continuous single-circle trajectory data of the same road section are divided into one group, so that the number of tiles passed by the single-circle trajectory data in each single-circle trajectory grouped data is minimum, the trajectory similarity between the groups is lowest, each group can be processed concurrently, and the operation time is shortened by increasing the parallelism.

Description

Technical Field

[0001] The present invention relates to the field of geographic information technology, and more particularly to a method, device and equipment for grouping multi-source trajectory data. Background Art

[0002] High-precision maps can be used for autonomous driving, and the recognition and production of road signs are important components of generating high-precision maps. Road signs (semantic objects) are generally identified and extracted through road image information collected by cameras mounted on vehicles.

[0003] In the process of making high-precision maps, in order to solve the drawback of large resource investment in single-trip closed-loop collection (closed-loop single-trip collection) and optimize application scenarios, the inventor previously proposed a solution for making high-precision maps based on multi-source crowdsourcing data, that is, by using private cars as collection equipment, data collection is performed without interfering with the stable and fast driving of the vehicle. In the process of using private cars to collect data, since it is impossible to stipulate that a certain vehicle strictly follows a closed-loop trajectory, most vehicle trajectories are only one-way trajectories from the starting point to the destination, so multiple single-track data is used in the later production of high-precision maps, that is, multiple / multiple image collections are required for the same location, and then the road sign information in each collected image is extracted separately, and finally the same road sign collected in multiple trips is fused, and then a high-precision map is produced based on multi-source crowdsourcing data. Summary of the invention

[0004] In order to improve the ability to process multi-source data, and thereby improve computing power while ensuring the accuracy of high-precision maps, so as to enrich technical routes and increase selection space, a method, device and equipment for grouping multi-source trajectory data are provided in an embodiment of the present invention.

[0005] In a first aspect, an embodiment of the present invention provides a method for grouping multi-source trajectory data, which may include:

[0006] Based on the start and end time and the start and end distance in the tile trajectory of the full bicycle trajectory passing through adjacent tiles, the full bicycle trajectory is segmented into a trip;

[0007] Determine whether the bicycle travel trajectory segment after the travel segmentation passes through the same tile repeatedly;

[0008] If so, determining whether the distance between the entry points into the tile is less than a preset distance threshold;

[0009] If it is less than, the same tile is split twice to obtain the single-circle trajectory data of the bicycle travel segment;

[0010] The single-circle trajectory data are grouped based on similarities of the single-circle trajectory data to obtain a plurality of single-circle trajectory groups.

[0011] Optionally, grouping the single-circle trajectory data based on the similarity of the single-circle trajectory data may include:

[0012] The single-circle trajectory data are sorted in descending order based on their similarity, and the single-circle trajectory data are merged in descending order based on their similarity, so as to group the single-circle trajectory data into a plurality of single-circle trajectory groups based on a comparison result between the number of tiles passed by the single-circle trajectory in the group and a preset threshold value of the number of tiles in the group.

[0013] Optionally, grouping the single-circle trajectory data based on the similarity of the single-circle trajectory data may specifically include:

[0014] Sorting the single-circle trajectory data in descending order based on their similarity, and iteratively merging the single-circle trajectory data in descending order of similarity;

[0015] Compare the sum of the number of tiles passed by all the single-circle trajectory data included in the group where the two single-circle trajectory data with the greatest similarity are located with a preset threshold value of the number of tiles in the group;

[0016] If it is greater than the tile number threshold in the group, two single-circle trajectory data are selected from the largest to the smallest similarity and compared again;

[0017] If it is less than the tile data threshold within the group, the groups where the two single-circle trajectory data are located are merged into one single-circle trajectory group.

[0018] Optionally, the above-mentioned sorting, comparing and merging steps are iterated repeatedly until the single-circle trajectory grouping does not meet the merging requirement.

[0019] Optionally, the similarity between the two single-circle trajectory data is determined by the following method:

[0020] Determine respectively the tile lists and the longest continuous common tile string passed by the two single-circle trajectory data;

[0021] Determine the proportion of the longest continuous common tile string based on the tile list and the longest continuous common tile string;

[0022] The similarity between the two single-circle trajectory data is determined based on the proportion of the longest continuous common tile strings in the two single-circle trajectory data.

[0023] Optionally, after determining the tile list that the single-circle trajectory data passes through, the following steps may also be performed:

[0024] Deduplication processing is performed on the part of the tile list where adjacent tiles are the same tile.

[0025] Optionally, the method may further include: preprocessing the single-trip trajectory segment in the tile based on the vehicle ID and trajectory point information in the multi-source trajectory data to obtain the full trajectory of the single vehicle.

[0026] Optionally, the method may further include: constructing a lane model based on the semantic object and lane object associated with each single-lap trajectory data in the single-lap trajectory group.

[0027] In a second aspect, an embodiment of the present invention provides a device for grouping multi-source trajectory data, which may include:

[0028] A trip segmentation module, for segmenting the full track of a bicycle based on the start and end time and the start and end distance in the tile track of the full track of the bicycle passing through adjacent tiles;

[0029] The first judgment module is used to judge whether the bicycle travel track segment after the travel segmentation passes through the same tile repeatedly;

[0030] If the first judgment module determines that it is yes, the second judgment module is used to determine whether the distance between the entry points into the tile is less than a preset distance threshold;

[0031] If the second judgment module determines that it is less than, the secondary segmentation module is used to perform secondary segmentation on the same tile to obtain the single-circle trajectory data of the bicycle travel segment;

[0032] The grouping module is used to group the single-circle trajectory data based on the similarity of the single-circle trajectory data to obtain a plurality of single-circle trajectory groups.

[0033] In a third aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, the method for grouping multi-source trajectory data as described in the first aspect is implemented.

[0034] In a fourth aspect, an embodiment of the present invention provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for grouping multi-source trajectory data as described in the first aspect is implemented.

[0035] The beneficial effects of the above technical solution provided by the embodiment of the present invention include at least:

[0036] The embodiment of the present invention provides a method, device and apparatus for grouping multi-source trajectory data. The method divides the single-circle trajectory data of the same continuous road section into a group, so that the single-circle trajectory data in each single-circle trajectory group data passes through the least number of tiles, and the trajectory similarity between groups is the lowest. When processing data, the lane model module can process each group concurrently, and the running time is reduced by increasing the parallelism. Furthermore, the multi-source data processing capability is improved, thereby improving the computing power while ensuring the accuracy of high-precision map production.

[0037] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0038] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0040] Figure 1 A flowchart of a method for grouping multi-source trajectory data provided in an embodiment of the present invention;

[0041] Figure 2 A simplified flowchart of a method for grouping multi-source trajectory data provided in an embodiment of the present invention;

[0042] Figure 3 A schematic diagram of different tile trajectories provided in an embodiment of the present invention after being spliced;

[0043] Figure 4 A flowchart of a method for grouping single-circle trajectory data provided in an embodiment of the present invention;

[0044] Figure 5 A flowchart for determining the similarity of two single-circle trajectory data provided in an embodiment of the present invention;

[0045] Figure 6 An example of itinerary segmentation provided in an embodiment of the present invention;

[0046] Figure 7 This is an example of secondary segmentation (multi-circle segmentation) provided in an embodiment of the present invention;

[0047] Figure 8 This is an example of full data provided in an embodiment of the present invention;

[0048] Fig. 9 for Figure 8 Example after grouping;

[0049] Fig.10 Schematic diagram of the structure of a device for grouping multi-source trajectory data provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0050] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0051] When making a high-precision map based on multi-source trajectory data (multi-source crowdsourcing data), the lane model module (a module for making high-precision maps based on multi-source data) takes too long to process data due to the large amount of imported data, and a single run consumes a lot of time. In order to improve mapping efficiency, the present invention is proposed to process data before importing the lane model module, thereby improving computing power and work efficiency.

[0052] In an embodiment of the present invention, a method for grouping multi-source trajectory data is provided. In an embodiment of the present invention, a threshold is set for triggering the grouping method (for example, the threshold for the full amount of data is M, which can be set according to the processing performance of the lane model module). When the number of imported data files is greater than M, the method is triggered. Figure 1 and Figure 2 As shown, the method may include the following steps:

[0053] Step S11, dividing the full track of the bicycle into trips based on the start and end time and the start and end distance in the tile track of the full track of the bicycle passing through adjacent tiles.

[0054] This step is to determine different trajectory data within different trips of a single vehicle, that is, a trajectory segment of a vehicle's continuous driving, which in real road conditions corresponds to the trajectory data of a vehicle from ignition to shutdown.

[0055] Step S12, determine whether the bicycle travel trajectory segments after the travel segmentation repeatedly pass through the same tile; if so, execute step S13; otherwise, enter the grouping step S15.

[0056] Step S13, determine whether the distance between the entry points of the tile is less than a preset distance threshold; if so, execute step S14; otherwise, enter the grouping step S15.

[0057] Step S14, split the same tile twice to obtain the single-circle trajectory data of the bicycle travel segment. This step is to determine whether the bicycle travel trajectory segment repeatedly enters the same tile and the route is consistent. In this case, multi-circle segmentation is required to minimize the number of tiles passed by the single-circle trajectory data after multi-circle segmentation. For the data processing process, the smaller the granularity, the more conducive it is to use after grouping.

[0058] Step S15: grouping the single-circle trajectory data based on the similarity of the single-circle trajectory data to obtain a plurality of single-circle trajectory groups.

[0059] The embodiment of the present invention divides the single-circle trajectory data of the same continuous road section into a group, so that the number of tiles passed by the single-circle trajectory data in each single-circle trajectory group data is the least, and the trajectory similarity between groups is the lowest. During data processing, the lane model module can process each group concurrently, thereby reducing the running time by increasing the parallelism.

[0060] In an optional embodiment, also refer to Figure 1 and Figure 2 As shown, before dividing the full track of the bicycle into travel segments, the following steps may be further included:

[0061] Step S10: pre-process the single-trip trajectory segment in the tile based on the vehicle ID and trajectory point information in the multi-source trajectory data to obtain the full trajectory of the single vehicle.

[0062] In the embodiment of the present invention, step S10 is to pre-process the data. First, the summary information or attribute information of the multi-source trajectory data (trajectory file) is extracted, including but not limited to: tile ID, trajectory file name, car ID (vehicle ID), starting point longitude and latitude, starting point timestamp, end point longitude and latitude, and end point timestamp. After extracting the trajectory file summary information / attribute information, a single-trip trajectory of a single vehicle in a certain tile can be identified, and the single-trip trajectory in the tile is used as a tile trajectory, and the tile trajectory is used as the minimum processing unit for pre-processing.

[0063] In the embodiment of the present invention, the process of preprocessing to obtain the full track of a single vehicle is as follows: for the tile track data, based on the car ID, all the tile tracks are spliced ​​in ascending order of the starting point timestamp. Figure 3 As shown in the figure, a schematic diagram of the splicing of different tile trajectories is shown. In the preprocessing process of this step, a group is formed for each car ID, and the corresponding car ID in the group is spliced ​​with the full tile trajectories in the time axis order to obtain the full trajectory of a single car, for example Figure 3If the middle tile track is 1-2-3-4, then the "tile track 1-2-3-4" is taken as a single vehicle full track. If there are several vehicles in the multi-source track data, they will be divided into several groups according to the vehicle ID.

[0064] In another optional embodiment, the single-circle trajectory data are grouped based on the similarity of the single-circle trajectory data, including:

[0065] The single-circle trajectory data are sorted in descending order based on their similarity, and the single-circle trajectory data are merged from large to small in similarity, and the single-circle trajectory data are grouped into several single-circle trajectory groups based on the comparison result between the number of tiles passed by the single-circle trajectory in the group and the preset threshold value of the number of tiles in the group.

[0066] In the embodiment of the present invention, when the single-circle trajectory data are grouped, the single-circle trajectory data are merged using a greedy strategy. First, the similarity is arranged in descending order, and then the groups of two single-circle trajectory data are merged in order from high to low similarity (each single-circle trajectory data is initialized as a separate group). If the merging reaches a preset threshold, the merging is terminated, and finally a number of single-circle trajectory groups are obtained, and the single-circle trajectory groups are imported into the lane model module for processing.

[0067] In a specific embodiment, referring to Figure 4 As shown, the above method for grouping single-circle trajectory data may specifically include:

[0068] Step S41 , sorting the single-circle trajectory data in descending order based on their similarity, and iteratively merging the single-circle trajectory data in descending order of similarity.

[0069] In the embodiment of the present invention, each single-circle trajectory data is assigned a group ID to ensure that the group IDs of any two single-circle trajectory data are different. The single-circle trajectory data are sorted in descending order according to the similarity between each two single-circle trajectory data, and all single-circle trajectory data are iterated.

[0070] Step S42, compare the sum of the number of tiles passed by all the single-circle trajectory data included in the group where the two single-circle trajectory data with the greatest similarity belong to with the preset threshold of the number of tiles in the group; if it is greater than the threshold of the number of tiles in the group, execute step S43; if it is less than the threshold of the number of tiles in the group, execute step S44.

[0071] Assume that the two single-circle trajectory data corresponding to the current maximum similarity are s1 and s2, and the group IDs corresponding to the two single-circle trajectory data are G1 and G2 respectively, and the number of tile trajectories (number of tiles) in G1 and G2 are |G1| and |G2| respectively. Assume that the preset threshold value of the number of tiles in the group in the embodiment of the present invention is N, if |G1|+|G2|≥N, then execute step S43; if |G1|+|G2|<N, then execute step S44, that is, all single-circle trajectory data with group ID G2 are updated to have group ID G1.

[0072] Step S43: filter the two single-circle trajectory data in descending order of similarity and compare them again.

[0073] Step S44: merge the groups containing the two single-circle trajectory data into one single-circle trajectory group.

[0074] In a specific example, there are four single-circle trajectory groups A, B, C, and D, each of which contains several single-circle trajectory data. Specifically, group A contains 1 single-circle trajectory data, group B contains 3 single-circle trajectory data, group C contains 2 single-circle trajectory data, and group D contains 2 single-circle trajectory data. Pairing the above four groups in pairs, we get six pairs, and calculate the similarity respectively, as follows:

[0075] (AB 95%, AC 90%, AD 85%, BC 82%, BD 80%, CD 75%), N value is 4;

[0076] The first step is to calculate the number of tile tracks (number of tiles) for the pair AB corresponding to the maximum similarity. If the sum is 1+3≥4, then return and execute step S43. At this time, there are still four groups A, B, C, and D.

[0077] The second step is to continue to calculate the number of tile trajectories (number of tiles) of AC, which ranks second in similarity, and the sum of the number of tile trajectories of this pair is 1+2<4. At this time, A+C are merged into one group. At this time, there are three groups: B, D, and A+C.

[0078] The third step is to continue iterating. At this time, the groups included are B, D, and A+C. Group B still contains 3 single-circle trajectories, group D contains 2 single-circle trajectories, and group A+C contains 1+2=3 single-circle trajectories.

[0079] For AD ranked third in similarity, the sum of the number of tile trajectories (number of tiles) is calculated. At this time, group A has been merged with group C, which contains 3 single-circle trajectories. The sum of the trajectories in AD calculated finally is 3+2≥4. Then, the process returns to step S43. At this time, there are still three groups: B, D, and A+C.

[0080] Step 4: for BC ranked fourth in similarity, the sum of the number of tile tracks (number of tiles) is calculated to be 3+3≥4, then the process returns to step S43, at which point, there are still three groups: B, D, and A+C;

[0081] Step 5: for BD ranked fifth in similarity, the sum of the number of tile tracks (number of tiles) is calculated to be 3+2≥4, then the process returns to step S43, at which point, there are still three groups: B, D, and A+C;

[0082] Step 6: For CD ranked fifth in similarity, calculate the sum of the number of tile tracks (number of tiles) to be 3+2≥4, then return and execute step S43. At this time, there are still three groups: B, D, and A+C.

[0083] In another optional embodiment, the above method for grouping single-circle trajectory data may further include: step S45, repeatedly iterating the above sorting, comparing and merging steps until the single-circle trajectory groups do not meet the merging requirements.

[0084] Repeat the iterative process until the last pair cannot be merged. In the end, the result is three groups B, D, and A+C, and group B still contains 3 single-circle trajectories, group D contains 2 single-circle trajectories, and group A+C contains 1+2=3 single-circle trajectories. The reason for processing the single-circle trajectory data in this way is to control the number of tile trajectories (number of tiles) in a single group to be neither too many nor too few, so that the distribution of the number of tile trajectories (number of tiles) in the overall group is more balanced. At the same time, it can effectively avoid the situation where some lines are highly overlapped.

[0085] In another optional embodiment, for calculating the similarity of any two single-circle trajectory data, first convert the single-circle trajectory data into a tile list of the same order, calculate the length ratio of the longest continuous common tile string (longest continuous common substring) of the two tile lists in the two single-circle trajectories, and take the smaller ratio as the similarity of the two single-circle trajectory data. Figure 5 As shown, it is determined by the following method:

[0086] Step S51: respectively determine the tile lists and the longest continuous common tile string passed by two single-circle trajectory data.

[0087] In this step, the trajectory points in the single-circle trajectory data can be sampled with a fixed length (Tile length, which can reduce the amount of calculation), and then the TileID of the sampling points is calculated; then the tile list is generated by arranging the sampling points in time order.

[0088] Step S52: De-duplicate the list portion where adjacent tiles in the tile list are the same tile.

[0089] This step removes duplicates from adjacent repeated TileIDs and outputs the final tile list. For example, a certain track passes through three TileIDs A, B, and C. The TileID list generated by the above step S51 is AABBBCA, and the result after deduplication in this step is: ABCA. It should be noted that this step does not necessarily exist. If there are no duplicates in the adjacent tiles in the tile list determined in step S51, there is no need to execute this step, and step S53 can be executed directly.

[0090] Step S53: Based on the tile list and the longest continuous common tile string, determine the proportion of the longest continuous common tile string.

[0091] Step S54: determine the similarity between the two single-circle trajectory data based on the proportion of the longest continuous common tile strings in the two single-circle trajectory data.

[0092] For example, the tile lists of two single-circle trajectory data are ABCDE and ACDF respectively; then, the longest continuous common substring is "CD" with a length of 2; the tile sequence lengths of the two single-circle trajectory data are 5 and 4 respectively, accounting for 0.4 and 0.5 respectively, and the final similarity takes the smaller value, i.e. 0.4.

[0093] In another optional embodiment, after the above method is divided into single-circle trajectory groups, it may also include: constructing a lane model based on the semantic objects and lane objects associated with each single-circle trajectory data in the single-circle trajectory group. This step is to associate the single-circle trajectory data in the group with the semantics and LineInfo data (line information list) in the same time window to write them into a new directory, laying the foundation for the subsequent application layer actual application, that is, the lane model module to produce a high-precision map.

[0094] In a specific example, the results of the above multi-source trajectory data grouping method are verified as follows:

[0095] Dataset: Data size (import): 8.77 GB; Number of tiles: 66; Number of trajectory files (multi-source trajectory data): 3285. Fig. 9 Take this as an example to illustrate.

[0096] After the preprocessing in step S10, the number of tile tracks (number of tiles) is 4136; the number of car IDs is 4.

[0097] The data table after preprocessing:

[0098] car ID Number of tile tracks (number of tiles) LS6A2E161NA505442 2379 LS6A2E169NA507360 632 LS6A2E166NA505467 595 xxxx 530

[0099] After the itinerary is divided in step S11:

[0100]

[0101]

[0102] After the second cutting (multi-circle cutting) in step S13 and step S14, the effect is as follows: Figure 7 As shown, after step S15, grouping is performed, taking the threshold value of the number of tiles in each single-circle trajectory group as 800 as an example, then Figure 8 The full data grouping in Fig. 9 As shown, the group list is as follows:

[0103] Group No. Number of single-circle tracks Number of tile tracks (number of tiles) Group 1 13 489 Group 2 28 496 Group 3 54 786 Group 4 34 798 Group 5 43 778 Group 6 75 789

[0104] In the above example of the embodiment of the present invention, the grouping results are input into the lane model module for clustering to construct a high-definition map, and the calculation time is reduced by increasing the parallelism, thereby improving the mapping efficiency.

[0105] Based on the same inventive concept, an embodiment of the present invention further provides a device for grouping multi-source trajectory data, referring to Fig.10 As shown, the device may include: a trip segmentation module 131, a first judgment module 132, a second judgment module 133, a secondary segmentation module 134 and a grouping module 135, and its working principle is as follows:

[0106] The trip segmentation module 131 is used to segment the full track of the bicycle based on the start and end time and the start and end distance in the tile track of the full track of the bicycle passing through adjacent tiles;

[0107] The first determination module 132 is used to determine whether the bicycle travel track segment after the travel segmentation passes through the same tile repeatedly;

[0108] If the first judgment module 132 judges that it is yes, the second judgment module 133 is used to judge whether the distance between the entry points of the entry tile is less than a preset distance threshold;

[0109] If the second determination module 133 determines that it is less than, the secondary segmentation module 134 is used to perform secondary segmentation with the same tile to obtain the single-circle trajectory data of the bicycle travel segment;

[0110] The grouping module 135 is used to group the single-circle trajectory data based on the similarity of the single-circle trajectory data to obtain a plurality of single-circle trajectory groups.

[0111] In an optional embodiment, the grouping module 135 is used to sort the single-circle trajectory data in descending order based on their similarity, merge the single-circle trajectory data in descending order based on their similarity, and group the single-circle trajectory data into a plurality of single-circle trajectory groups based on a comparison result between the number of tiles passed by the single-circle trajectory in the group and a preset threshold value of the number of tiles in the group.

[0112] In another optional embodiment, the grouping module 135 is specifically used for:

[0113] Sorting the single-circle trajectory data in descending order based on their similarity, and iteratively merging the single-circle trajectory data in descending order of similarity;

[0114] Compare the sum of the number of tiles passed by all the single-circle trajectory data included in the group where the two single-circle trajectory data with the greatest similarity are located with a preset threshold value of the number of tiles in the group;

[0115] If it is greater than the tile number threshold in the group, two single-circle trajectory data are selected from the largest to the smallest similarity and compared again;

[0116] If it is less than the tile data threshold within the group, the groups where the two single-circle trajectory data are located are merged into one single-circle trajectory group.

[0117] In another optional embodiment, the grouping module 135 is further configured to: repeatedly iterate the above-mentioned sorting, comparing and merging steps until the single-circle trajectory grouping does not meet the merging requirement.

[0118] In another optional embodiment, the grouping module 135 is specifically used for:

[0119] Determine respectively the tile lists and the longest continuous common tile string passed by the two single-circle trajectory data;

[0120] Determine the proportion of the longest continuous common tile string based on the tile list and the longest continuous common tile string;

[0121] The similarity between the two single-circle trajectory data is determined based on the proportion of the longest continuous common tile strings in the two single-circle trajectory data.

[0122] In another optional embodiment, the grouping module 135 is specifically configured to: perform deduplication processing on the portion of the tile list where adjacent tiles are the same tile.

[0123] In another alternative embodiment, referring to Fig.10 As shown, the device may further include: a preprocessing module 130, which is used to preprocess the single-trip trajectory segment in the tile based on the vehicle ID and trajectory point information in the multi-source trajectory data to obtain the full trajectory of the single vehicle.

[0124] In another alternative embodiment, referring to Fig.10 As shown, the device may further include: a construction module 136, which is used to construct a lane model based on the semantic objects and lane objects associated with each single-circle trajectory data in the single-circle trajectory group.

[0125] Based on the same inventive concept, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, the above-mentioned multi-source trajectory data grouping method is implemented.

[0126] Based on the same inventive concept, an embodiment of the present invention further provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the above-mentioned multi-source trajectory data grouping method is implemented.

[0127] The principles of the problems solved by the above-mentioned devices, media, and related equipment in the embodiments of the present invention are similar to those of the above-mentioned methods, so their implementation can refer to the implementation of the above-mentioned methods, and the repeated parts will not be repeated.

[0128] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) containing computer-usable program code.

[0129] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0130] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0131] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0132] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for grouping multi-source trajectory data, characterized in that: include: Based on the start and end time and the start and end distance in the tile trajectory of the full bicycle trajectory passing through adjacent tiles, the full bicycle trajectory is segmented into a trip; Determine whether the bicycle travel trajectory segment after the travel segmentation passes through the same tile repeatedly; If so, determining whether the distance between the entry points into the tile is less than a preset distance threshold; If it is less than, the same tile is split twice to obtain the single-circle trajectory data of the bicycle travel segment; The single-circle trajectory data are grouped based on similarities of the single-circle trajectory data to obtain a plurality of single-circle trajectory groups.

2. The method according to claim 1, characterized in that The grouping of the single-circle trajectory data based on the similarity of the single-circle trajectory data comprises: The single-circle trajectory data are sorted in descending order based on their similarity, and the single-circle trajectory data are merged in descending order based on their similarity, so as to group the single-circle trajectory data into a plurality of single-circle trajectory groups based on a comparison result between the number of tiles passed by the single-circle trajectory in the group and a preset threshold value of the number of tiles in the group.

3. The method according to claim 2, characterized in that Specifically include: Sorting the single-circle trajectory data in descending order based on their similarity, and iteratively merging the single-circle trajectory data in descending order of similarity; Compare the sum of the number of tiles passed by all the single-circle trajectory data included in the group where the two single-circle trajectory data with the greatest similarity are located with a preset threshold value of the number of tiles in the group; If it is greater than the tile number threshold in the group, two single-circle trajectory data are selected from the largest to the smallest similarity and compared again; If it is less than the tile data threshold within the group, the groups where the two single-circle trajectory data are located are merged into one single-circle trajectory group.

4. The method according to claim 3, characterized in that The above-mentioned sorting, comparing and merging steps are iterated repeatedly until the single-circle trajectory grouping does not meet the merging requirement.

5. The method according to claim 1, characterized in that The similarity of the two single-circle trajectory data is determined by the following method: Determine respectively the tile lists and the longest continuous common tile string passed by the two single-circle trajectory data; Determine the proportion of the longest continuous common tile string based on the tile list and the longest continuous common tile string; The similarity between the two single-circle trajectory data is determined based on the proportion of the longest continuous common tile strings in the two single-circle trajectory data.

6. The method according to claim 5, characterized in that After determining the tile list that the single-circle trajectory data passes through, the method further includes: Deduplication processing is performed on the part of the tile list where adjacent tiles are the same tile.

7. The method according to any one of claims 1 to 6, characterized in that: Also includes: The single-trip track segment in the tile is preprocessed based on the vehicle ID and track point information in the multi-source track data to obtain the single-vehicle full track.

8. The method according to any one of claims 1 to 6, characterized in that: Also includes: A lane model is constructed based on the semantic objects and lane objects associated with each single-lap trajectory data in the single-lap trajectory group.

9. A device for grouping multi-source trajectory data, characterized in that: include: A trip segmentation module, for segmenting the full track of a bicycle based on the start and end time and the start and end distance in the tile track of the full track of the bicycle passing through adjacent tiles; The first judgment module is used to judge whether the bicycle travel track segment after the travel segmentation passes through the same tile repeatedly; If the first judgment module determines that it is yes, the second judgment module is used to determine whether the distance between the entry points into the tile is less than a preset distance threshold; If the second judgment module determines that it is less than, the secondary segmentation module is used to perform secondary segmentation on the same tile to obtain the single-circle trajectory data of the bicycle travel segment; The grouping module is used to group the single-circle trajectory data based on the similarity of the single-circle trajectory data to obtain a plurality of single-circle trajectory groups.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method for grouping multi-source trajectory data according to any one of claims 1 to 8 is implemented.

11. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the multi-source trajectory data grouping method according to any one of claims 1 to 8 is implemented.

Images