WO2024021632A1

WO2024021632A1 - Real-time trajectory data processing method, apparatus and system, and electronic device

Info

Publication number: WO2024021632A1
Application number: PCT/CN2023/081970
Authority: WO
Inventors: 朱浩文; 吴伟; 王如斌; 隋远
Original assignee: 京东城市(北京)数字科技有限公司
Priority date: 2022-07-29
Filing date: 2023-03-16
Publication date: 2024-02-01
Also published as: CN115168527A

Abstract

Provided are a real-time trajectory data processing method, apparatus and system, and an electronic device, a readable storage medium, a computer program product and a computer program. The real-time trajectory data processing method comprises: acquiring trajectory data of moving objects, and performing denoising processing on the trajectory data, so as to obtain effective trajectory point data; acquiring M candidate road network points of the current trajectory point among the effective trajectory point data, wherein M is a positive integer; determining a variable sliding window corresponding to the current trajectory point, wherein the length of the variable sliding window is K, the variable sliding window comprises N first transition probabilities of the previous trajectory point and a corresponding first candidate road network point combination under each first transition probability, each first candidate road network point combination comprises K historical candidate road network points, and N and K are respectively positive integers; and performing map matching processing on the M candidate road network points on the basis of the variable sliding window, so as to obtain road network points of the current trajectory point.

Description

Real-time trajectory data processing method, device, system and electronic equipment

Cross-references to related applications

This disclosure claims priority from Chinese Patent Application No. 2022109111409 filed in China on July 29, 2022, the entire content of which is incorporated herein by reference.

Technical field

The present disclosure relates to the field of computer technology, and specifically to a real-time trajectory data processing method and device, system, electronic equipment, readable storage media, computer program products and computer programs.

Background technique

In related technologies, when a new trajectory point of a moving object is obtained, the trajectory point is usually added to the trajectory point set previously cached in the memory of the mobile object, and then the cache at the current time is calculated based on the offline map matching hidden Markov model. Probabilistic model of all points in the trajectory point set, and output all possible candidate trajectories after map matching. The disadvantage of this technical solution is that it requires a large amount of calculation, resulting in high latency and poor real-time performance.

Contents of the invention

Embodiments of the present disclosure provide a real-time trajectory data processing method and device, a system, an electronic device, a readable storage medium, a computer program product, and a computer program. The acquired trajectories of moving objects can be processed to achieve high-precision and low-latency real-time map matching.

In a first aspect, embodiments of the present disclosure provide a real-time trajectory data processing method, which includes: obtaining trajectory data of a moving object, and denoising the trajectory data to obtain effective trajectory point data; obtaining the effective trajectory point M candidate road network points of the current trajectory point in the data, where M is a positive integer; determine a variable sliding window corresponding to the current trajectory point, where the length of the variable sliding window is K, and the variable sliding window is The variable sliding window includes N first transition probabilities of the previous trajectory point and the corresponding first candidate road network point combinations under each first transition probability. Each of the first candidate road network point combinations includes K historical candidate routes. Network points, the N and K are respectively positive integers; map matching processing is performed on the M candidate network points based on the variable sliding window to obtain the network points of the current trajectory point.

Through this technical solution, the road network points of the current trajectory point can be obtained based on the current trajectory point and the corresponding sliding window, reducing the amount of calculation required, thereby achieving high-precision and low-latency real-time map matching of trajectory data of moving objects.

In some embodiments, performing map matching processing on the M candidate road network points based on the variable sliding window to obtain the road network points of the current trajectory point includes: based on a hidden Markov model and a Viterbi algorithm , using the variable sliding window to perform map matching processing on the M candidate road network points, and obtain the road network points of the current trajectory point.

In some embodiments, based on the hidden Markov model and Viterbi algorithm, the variable sliding window is used to The M candidate road network points are subjected to map matching processing to obtain the road network points of the current trajectory point, including: inserting the M candidate road network points into the tail of each of the first candidate road network point combinations to obtain each N second candidate road network point combinations corresponding to the candidate road network points; determine N second transition probabilities of the N second candidate road network point combinations corresponding to each of the candidate road network points, from the N second candidate road network point combinations Select the second candidate road network point combination with the largest second transition probability among the candidate road network point combinations; select the second candidate road network point combination with the largest second transition probability among the N second candidate road network point combinations corresponding to each candidate road network point. The candidate road network point combination is determined as the third candidate road network point combination to obtain M third candidate road network point combinations; the first candidate road network point is removed from each of the third candidate road network point combinations to obtain M first candidate road network points ; Based on the transition probabilities of each of the M third candidate road network point combinations, determine the road network point of the current trajectory point from the M first candidate road network points.

Through this technical solution, in the map matching process, the Viterbi algorithm is quoted based on the hidden Markov model, which can greatly reduce the algorithm complexity.

In some embodiments, determining the road network point of the current trajectory point from the M first candidate road network points based on the respective transition probabilities of the M third candidate road network point combinations includes: Among the M first candidate road network points, the first candidate road network point removed from the third candidate road network point combination with the largest transition probability is selected and determined as the road network point of the current trajectory point.

In some embodiments, the method further includes: determining the M third candidate road network point combinations after moving out of the first candidate road network point as a variable sliding window corresponding to the next trajectory point; point as the new current trajectory point, perform the map matching process on the M candidate road network points based on the variable sliding window, and obtain the road network points of the current trajectory point until the effective trajectory point data All track points in the map are matched.

In some embodiments, the method further includes: using an Upsert statement to store the obtained road network points of the trajectory points into the cache database.

In some embodiments, the method further includes: in response to a trajectory query request for the mobile object, querying the road network information of the mobile object from the cache database based on the trajectory query request; and/or, In response to a request to display the road network information of the mobile object, the road network information of the mobile object is visualized.

Through this technical solution, the obtained road network points of the trajectory points can be stored in the cache database for trajectory query and visualization processing, thereby realizing real-time query and display of the trajectory of the moving object.

In some embodiments, the method further includes: obtaining the road network points of each trajectory point in the effective trajectory data, and storing the road network points of each trajectory point in the effective trajectory data into a storage database.

In some embodiments, storing the road network points of each trajectory point in the valid trajectory data into a storage database includes: performing trajectory truncation processing on each trajectory point in the valid trajectory data according to preset trajectory truncation conditions. , and store the truncated road network points into the storage database.

Through this technical solution, the road network points of each trajectory point can be stored in the storage database, reducing the storage space occupied by the cache database and system memory, and saving storage resources.

In the second aspect, embodiments of the present disclosure provide a real-time trajectory data processing device. The device includes: a first processing module for acquiring trajectory data of a moving object, and performing denoising processing on the trajectory data to obtain effective results. Trajectory point data; an acquisition module, used to obtain M candidate road network points of the current trajectory point in the valid trajectory point data, where the M is a positive integer; a second processing module, used to determine the relationship with the current trajectory point The corresponding variable sliding window, wherein the length of the variable sliding window is K, the variable sliding window includes the N first transition probabilities of the previous trajectory point and the corresponding first transition probability under each of the first transition probabilities. A candidate road network point combination, each of the first candidate road network point combinations includes K historical candidate road network points, and the N and K are respectively positive integers; a third processing module, used to calculate all the candidate road network points based on the variable sliding window. The M candidate road network points are subjected to map matching processing to obtain the road network points of the current trajectory point.

In some embodiments, the third processing module is specifically configured to: use the variable sliding window to perform map matching processing on the M candidate road network points based on the hidden Markov model and the Viterbi algorithm to obtain the The road network point of the current track point.

In some embodiments, the third processing module is specifically configured to: insert the M candidate road network points into the tail of each of the first candidate road network point combinations, and obtain the corresponding corresponding to each of the candidate road network points. N second candidate road network point combinations; determine N second transition probabilities of the N second candidate road network point combinations corresponding to each of the candidate road network point combinations, and select the N second candidate road network point combinations from the N second candidate road network point combinations The second candidate road network point combination with the highest second transition probability; determine the second candidate road network point combination with the highest second transition probability among the N second candidate road network point combinations corresponding to each candidate road network point as the third Combining candidate road network points to obtain M third candidate road network point combinations; removing the first candidate road network point from each of the third candidate road network point combinations to obtain M first candidate road network points; based on the M third candidate road network point combinations The candidate road network points combine their respective transition probabilities to determine the road network point of the current trajectory point from the M first candidate road network points.

In some embodiments, the third processing module is specifically configured to: from the M first candidate road network points, select the first candidate road network point removed from the third candidate road network point combination with the largest transition probability, and determine it as The road network point of the current trajectory point.

In some embodiments, the device further includes: a fourth processing module configured to determine the M third candidate road network point combinations after moving out of the first candidate road network point as a variable sliding window corresponding to the next trajectory point ; The fifth processing module is used to use the next trajectory point as a new current trajectory point, perform the map matching process on the M candidate road network points based on the variable sliding window, and obtain the current trajectory The steps of selecting road network points until all trajectory points in the valid trajectory point data complete map matching.

In some embodiments, the device further includes: a storage module, configured to store the obtained road network points of the trajectory points into the cache database by using an Upsert statement.

In some embodiments, the device further includes: a query module, configured to respond to a trajectory query request for the mobile object and query the road network information of the mobile object from the cache database based on the trajectory query request. ; and/or, a visualization module, configured to perform visual processing on the road network information of the mobile object in response to a request to display the road network information of the mobile object.

In some embodiments, the device further includes: a sixth processing module, configured to obtain the road network points of each trajectory point in the effective trajectory data, and store the road network points of each trajectory point in the effective trajectory data to the storage in the database.

In some embodiments, the sixth processing module is specifically configured to perform trajectory truncation processing on each trajectory point in the effective trajectory data according to preset trajectory truncation conditions, and store the truncated road network points in the storage database. .

In a third aspect, embodiments of the present disclosure provide a real-time trajectory data processing system, including: a distributed stream processing engine, the distributed stream processing engine including a plurality of keyed stream partitions, wherein the plurality of keyed stream partitions adopt The real-time trajectory data processing method described in any embodiment of the first aspect performs real-time processing of trajectory data of different moving objects.

In a fourth aspect, embodiments of the present disclosure provide an electronic device, including: at least one processor; and a memory communicatively connected to the at least one processor, wherein the memory stores information that can be executed by the at least one processor. instructions, which are executed by the at least one processor, so that the at least one processor can execute the real-time trajectory data processing method as described in any embodiment of the first aspect.

In a fifth aspect, embodiments of the present disclosure provide a non-transitory computer-readable storage medium storing computer instructions, for storing instructions, and when the instructions are executed, the instructions are as described in any embodiment of the first aspect. A real-time trajectory data processing method is implemented.

In a sixth aspect, an embodiment of the present disclosure provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the real-time trajectory data processing method described in any embodiment of the first aspect.

In a seventh aspect, an embodiment of the present disclosure provides a computer program. The computer program includes a computer program code and is run on a computer based on the computer program code, so that the computer executes the real-time method as described in any embodiment of the first aspect. Trajectory data processing methods.

It should be understood that what is described in this section is not intended to identify key or important features of the embodiments of the disclosure, nor is it intended to limit the scope of the disclosure. Other features of the present disclosure will become readily understood from the following description.

Description of drawings

The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure. in:

Figure 1 is a flow chart of a real-time trajectory data processing method provided by an embodiment of the present disclosure;

Figure 2 is a schematic diagram of a real-time trajectory data processing method provided by an embodiment of the present disclosure;

Figure 3 is a flow chart of another real-time trajectory data processing method provided by an embodiment of the present disclosure;

Figure 4 is a flow chart of yet another real-time trajectory data processing method provided by an embodiment of the present disclosure;

Figure 5 is a flow chart of yet another real-time trajectory data processing method provided by an embodiment of the present disclosure;

Figure 6 is a schematic structural diagram of a real-time trajectory data processing device provided by an embodiment of the present disclosure;

Figure 7 is a schematic structural diagram of another real-time trajectory data processing device provided by an embodiment of the present disclosure;

Figure 8 is a schematic structural diagram of another real-time trajectory data processing device provided by an embodiment of the present disclosure;

Figure 9 is a schematic structural diagram of another real-time trajectory data processing device provided by an embodiment of the present disclosure;

Figure 10 is a schematic structural diagram of another real-time trajectory data processing device provided by an embodiment of the present disclosure;

Figure 11 is a schematic diagram of a real-time trajectory data processing system provided by an embodiment of the present disclosure;

Figure 12 is a schematic structural diagram of an electronic device provided by an embodiment of the present disclosure.

Detailed ways

Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of the embodiments of the present disclosure are included to facilitate understanding and should be considered to be exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the disclosure. Also, descriptions of well-known functions and constructions are omitted from the following description for clarity and conciseness.

In the description of this disclosure, unless otherwise stated, "/" means or, for example, A/B can mean A or B; "and/or" in this article is just an association relationship describing related objects, It means that there can be three relationships, for example, A and/or B, which can mean: A exists alone, A and B exist simultaneously, and B exists alone. The first, second, and other numerical numbers involved in this disclosure are only for convenience of description, and are not used to limit the scope of the embodiments of the disclosure, nor do they indicate a sequence.

With the expansion of cities and the rapid development of Internet of Things technology, applications such as vehicle navigation, shared cars, and logistics delivery have become deeply embedded in people's daily lives, and more and more trajectory data are continuously generated. These applications inevitably require the use of trajectory data recorded by positioning systems such as GPS (Global Positioning System) and Beidou. However, ordinary civilian GPS positioning systems have shortcomings such as meter-level errors and unstable signal reception. At the same time, the trajectory point sampling frequency cannot be too high under the constraints of data transmission and storage. The above factors lead to a certain distance deviation between the collected position of the moving object and its actual road. Therefore, in order to make the received position data truly reflect the running trajectory of the moving object, and at the same time enable the trajectory data to be displayed on the map in real time to allow users to more intuitively perceive the vehicle location and driving route, it is necessary to predict various trajectories in real time. Processing work, the most important and time-consuming of which is real-time map matching.

Please refer to Figure 1, which is a flow chart of a real-time trajectory data processing method provided by an embodiment of the present disclosure. As shown in Figure 1, the real-time trajectory data processing method may include but is not limited to steps S101 to S104.

Step S101: Obtain the trajectory data of the moving object, and perform denoising processing on the trajectory data to obtain effective trajectory point data.

In the embodiment of the present disclosure, a mobile object can be understood as a movable object with a positioning device, such as a car carrying a GPS device, or other movable objects with a positioning function, which will not be detailed here. limited.

For example, the trajectory data sent by the moving object with the positioning information of the moving object (for example, GPS data, Beidou positioning data, etc.) can be obtained, and the trajectory data can be denoised using preset denoising conditions.

In embodiments of the present disclosure, the preset denoising conditions may include but are not limited to the following items 1) to 5): 1) the coordinates of the trajectory data are within the preset spatial range; 2) the generation time of the trajectory data is within After the generation time of the last trajectory data obtained; 3) The speed of the moving object between the current trajectory data and the previous trajectory data is less than the preset first speed threshold; 4) The Euclidean distance between the current trajectory data and the previous trajectory data The distance is less than the preset Euclidean distance threshold; 5) There is a real road segment within the preset range near the coordinates of the trajectory data.

That is to say, after obtaining the trajectory data of the moving object, the trajectory data can be denoised first. The denoising logic has the following points: determine whether the trajectory point is within the preset spatial range. If not, then Remove the track point; determine whether the generation time of the track data is after the generation time of the last acquired track data; if not, remove the track point data; determine whether the moving object is between the track point data and the acquired previous track. Whether the speed between point data is less than the preset first speed threshold, if it is greater than or equal to the preset speed threshold, remove the track point data; determine whether the Euclidean distance between the current track point data and the previous track point data is less than The preset Euclidean distance threshold. If it is greater than or equal to the preset Euclidean distance threshold, the track point data will be removed; determine whether there is a real road segment within the preset range near the coordinates of the track point data. If it does not exist, remove it. The track point data. After denoising the trajectory data based on the above denoising logic, effective trajectory point data can be obtained.

Step S102: Obtain M candidate road network points of the current trajectory point in the valid trajectory point data.

In embodiments of the present disclosure, M is a positive integer.

For example, assuming that the current trajectory point z_t is obtained at time t, the position coordinates of the current trajectory point z_t can be used as the basis, and a spatial range query can be performed within a preset spatial range (for example: 50 meters) to obtain the location within the spatial range. All road network points, for example, the road network points that are no more than 50 meters away from the current trajectory point are queried as candidate road network points for the current trajectory point z_t.

In embodiments of the present disclosure, road network points refer to points in the actual road network.

Step S103: Determine the variable sliding window corresponding to the current trajectory point.

In the embodiment of the present disclosure, the length of the variable sliding window is K; the variable sliding window includes N first transition probabilities of the previous trajectory point and the corresponding first candidate road network point combination under each first transition probability. , each first candidate road network point combination includes K historical candidate road network points, N and K are positive integers respectively. The first transition probability is the maximum transition probability from the first historical candidate road network point to the corresponding previous trajectory point in the first candidate road network point combination.

It should be noted that in the embodiment of the present disclosure, the value of the length K of the variable sliding window can be preset, and the larger the value of K, the more accurate the final map matching effect will be. In some embodiments, the value range of K is recommended to be between 10 and between 20. It can be understood that since the value of K is small, the delay caused by calculating the road network points of the first K trajectory points can basically be ignored.

In some embodiments, please refer to FIG. 2 , which is a schematic diagram of a real-time trajectory data processing method provided by an embodiment of the present disclosure. As shown in Figure 2, assume that the time corresponding to the current trajectory point data is T, P1A, P1C,..., P1D are N different historical candidate road network points corresponding to the trajectory point data obtained at time T-K, and P2A, P2B,..., P2C are N different historical candidate road network points corresponding to the trajectory point data obtained at time T-(K-1). P3A, P3B,..., P3C are N different historical candidate road network points corresponding to the trajectory point data obtained at time T-(K-2). Candidate road network points, and so on, [PK1, PK2, ..., PKN] are the N historical candidate road network points corresponding to the trajectory point data obtained at time T-1. [P1A, P2B, P3A, …, PK1], [P1C, P2C, P3B, …, PK2] … [P1D, P2A, P3A, …, PKN] are the K number of arrivals at the historical candidate road network points PK1, PK2 … PKN respectively. A collection of historical candidate route network points with the largest transition probability at different times.

Step S104: Perform map matching processing on the M candidate road network points based on the variable sliding window to obtain the road network points of the current trajectory point.

In some embodiments, a variable sliding window can be used to perform map matching processing on M candidate road network points based on a hidden Markov model to obtain the road network points of the current trajectory point.

In some embodiments, based on the hidden Markov model and the Viterbi algorithm, a variable sliding window can be used to perform map matching processing on M candidate road network points to obtain the road network points of the current trajectory point.

According to the real-time trajectory data processing method of the embodiment of the present disclosure, the road network points of the current trajectory point can be obtained based on the current trajectory point and the corresponding sliding window, reducing the amount of calculation required, thereby achieving high precision and low latency for the trajectory data of the moving object. real-time map matching.

In order to further reduce the algorithm complexity, in the map matching process, the Viterbi algorithm can be quoted based on the hidden Markov model. Among them, the Viterbi algorithm is actually the optimal selection problem of a multi-step multi-choice model. All choices at each step save the minimum total cost (or maximum value) of the current choice from all previous steps to the current step and the current Selection of previous steps at a cost. After all steps are calculated in sequence, the optimal path is found through backtracking. Anything that conforms to this model can be solved using the Viterbi algorithm. Through the Viterbi algorithm, the final number of trajectory point combinations is equal to the number of candidate road network points of the last trajectory original point. The map matching process will be described in detail below with reference to Figure 3.

Figure 3 is a flow chart of a map matching method based on a hidden Markov model and Viterbi algorithm provided by an embodiment of the present disclosure. As shown in Figure 3, based on the hidden Markov model and the Viterbi algorithm, a variable sliding window can be used to perform map matching processing on M candidate road network points. The specific implementation method of obtaining the road network points of the current trajectory point may include steps S301-step S305.

Step S301: Insert M candidate road network points into the tail of each first candidate road network point combination to obtain N second candidate road network point combinations corresponding to each candidate road network point.

Step S302: Determine the N second transition probabilities of the N second candidate link point combinations corresponding to each candidate link point, and select the second candidate link point combination with the largest second transition probability from the N second candidate link point combinations. .

Step S303: Determine the second candidate road network point combination with the largest second transition probability among the N second candidate road network point combinations corresponding to each candidate road network point as the third candidate road network point combination, to obtain M third candidate road network point combinations. combination.

Step S304: Remove the first candidate link point from each third candidate link point combination to obtain M first candidate link points.

Step S305: Determine the road network point of the current trajectory point from the M first candidate road network points based on the transition probabilities of each of the M third candidate road network point combinations.

In some embodiments, the implementation process of determining the road network point of the current trajectory point from the M first candidate road network points based on the respective transition probabilities of the M third candidate road network points may include the following steps: Among the candidate road network points, the first candidate road network point removed from the third candidate road network point combination with the highest transition probability is selected and determined as the road network point of the current trajectory point.

In some embodiments, see Figure 2. As shown in Figure 2, P1, P2...PM are the M candidate road network points corresponding to the current trajectory point obtained at the current moment. P1, P2...PM are inserted into the tail of each first candidate road network point combination to obtain each candidate. The N second candidate road network point combinations corresponding to the road network point, assuming that the one with the largest transition probability is selected from the N second candidate road network point combinations corresponding to P1, is [P1A, P2B, P3A...PK1, P1], assuming that from P2 Select the one with the highest transition probability among the corresponding N second candidate road network point combinations, which is [P1C, P2C, P3B...PK2, P2]. Suppose that the one with the largest transition probability is selected from the N second candidate road network point combinations corresponding to PM. One, is [P1D, P2A, P3A...PKN, PM], thus obtaining M third candidate road node combinations. Remove the first candidate road network point from each third candidate road network point combination, and obtain M first candidate road network points as [P1A, P1C,...P1D], where it is assumed that the third candidate road network point combination corresponding to P1C is [P1C, P2C, P3B ...PK2, P2] has the largest transition probability, then P1C is the road network point of the current trajectory point.

It should be noted that the calculation of the second candidate road point combination [P1A, P2B, P3A...PK1, P1], [P1C, P2C, P3B...PK2, P2], ..., [P1D, P2A, P3A...PKN, PM] When transitioning the probability, since the first transition probability of the first candidate road node combination [P1A, P2B, P3A…Pk1], [P1C, P2C, P3B…PK2],…, [P1D, P2A, P3A…PKN] is known , so we only need to calculate the transition probabilities of [PK1, P1], [PK2, P2] and [PKN, PM] respectively, and add the obtained transition probability to the corresponding first transition probability to obtain each second candidate The transition probability of the road network point combination, the above calculation method is the Viterbi algorithm. Therefore, using the Viterbi algorithm based on the hidden Markov model can further reduce the algorithm complexity.

In some embodiments, the real-time trajectory data processing method further includes: determining the M third candidate route point combinations after removing the first candidate route point as a variable sliding window corresponding to the next trajectory point; As the new current trajectory point, map matching processing is performed on the M candidate road network points based on the variable sliding window to obtain the current trajectory. The steps of tracking point road network points are completed until all track points in the valid track point data have completed map matching.

For example, the M third candidate road network points after moving out of the first candidate road network point are combined as a variable sliding window corresponding to the next trajectory point. For example, as shown in Figure 2, the first candidate road network points [P1A, P1C, ...P1D] are respectively removed from the corresponding third candidate road network point combinations, and new M candidate road network point combinations are obtained. The new M candidate road network point combinations serve as a variable sliding window for the next trajectory point, and the obtained next path network point combination is One trajectory point is used as the new current trajectory point, and the above-mentioned steps of map matching processing of M candidate road network points based on the variable sliding window are repeated until all trajectory points in all valid trajectory point data of the acquired moving object have completed map matching. .

By implementing the embodiments of the present disclosure, the candidate road network point combination of the current trajectory point with the largest transition probability can be obtained based on the hidden Markov model and the Viterbi algorithm, thereby determining the road network points of the current trajectory point and realizing trajectory data of the moving object. High-precision and low-latency real-time map matching.

Please refer to Figure 4, which is a flow chart of another real-time trajectory data processing method provided by an embodiment of the present disclosure. This real-time trajectory data processing method can store the obtained road network points of the trajectory points into the cache database. As shown in Figure 4, the real-time trajectory data processing method may include but is not limited to steps S401 to S405.

Step S401: Obtain the trajectory data of the moving object, and perform denoising processing on the trajectory data to obtain effective trajectory point data.

In the embodiments of the present disclosure, step S401 can be implemented in any manner in the embodiments of the present disclosure. The embodiments of the present disclosure do not limit this and will not be described again.

Step S402: Obtain M candidate road network points of the current trajectory point in the valid trajectory point data.

In embodiments of the present disclosure, M is a positive integer.

In the embodiments of the present disclosure, step S402 can be implemented in any manner in the embodiments of the present disclosure. The embodiments of the present disclosure do not limit this and will not be described again.

Step S403: Determine the variable sliding window corresponding to the current trajectory point.

In the embodiments of the present disclosure, step S403 can be implemented in any manner in the embodiments of the present disclosure. The embodiments of the present disclosure do not limit this and will not be described again.

Among them, the length of the variable sliding window is K. The variable sliding window includes N first transition probabilities of the previous trajectory point and the corresponding first candidate path network point combinations under each first transition probability. Each first candidate path The network point combination includes K historical candidate road network points, and N and K are positive integers respectively.

Step S404: Perform map matching processing on the M candidate road network points based on the variable sliding window to obtain the road network points of the current trajectory point.

In the embodiments of the present disclosure, step S404 can be implemented in any manner in the embodiments of the present disclosure. The embodiments of the present disclosure do not limit this and will not be described again.

Step S405: Use the update and insert Upsert statement to store the obtained road network points of the trajectory points in the cache database.

For example, when the road network points of a mobile object are stored in the cache database for the first time, an Insert statement is used to create a road network point set corresponding to the mobile object in the cache database, and the road network points are stored in the cache database. collection; or, when the road network point of the mobile object is not stored in the cache database for the first time, use the Update statement to write the road network point into the road network point collection corresponding to the mobile object.

It should be noted that since frequent I/O (input/output, input/output) operations on the cache database will waste a lot of resources, the frequency with which the road network points of the trajectory points are stored in the cache database is also very important. Embodiments of the present disclosure The real-time trajectory data processing method provided allows you to customize the operating frequency according to actual needs.

In some embodiments, the operation of storing the obtained road network points of the trajectory points into the cache database can be set to be performed every 5 seconds.

In some embodiments, the real-time trajectory data processing method further includes: in response to a trajectory query request for the mobile object, querying the road network information of the mobile object from the cache database based on the trajectory query request; and/or, in response to a query request for the mobile object. The road network information display request is used to visualize the road network information of the moving object.

For example, in response to a trajectory query request for the moving object, obtain the road network point set of the mobile object from the cache database based on the trajectory query request, and feed back the road network point set as the road network information result of the trajectory query request; and/ Or, in response to a request to display the road network information of the mobile object, based on the road network point set of the mobile object, each road network point in the road network point set of the mobile object is connected on the preset map to realize the road network point of the mobile object. Visualize network information.

It should be noted that the threshold for the number of road network points in the road network point set of the mobile object in the cache database can be set in advance. When the length of the road network point set reaches the threshold, the road network point at the head of the road network point set queue will be automatically removed to free up space. Storage space to facilitate adding new road network points to the collection.

By implementing the embodiments of the present disclosure, the obtained road network points of the trajectory points can be stored in the cache database for trajectory query and visualization processing, thereby realizing real-time query and display of the trajectory of the moving object.

Please refer to FIG. 5 , which is a flow chart of another real-time trajectory data processing method provided by an embodiment of the present disclosure. This real-time trajectory data processing method can store road network points of trajectory points into a storage database. As shown in Figure 5, the real-time trajectory data processing method may include but is not limited to steps S501 to S505.

Step S501: Obtain trajectory data of the moving object, and perform denoising processing on the trajectory data to obtain effective trajectory point data.

In the embodiments of the present disclosure, step S501 can be implemented in any manner in the embodiments of the present disclosure. The embodiments of the present disclosure do not limit this and will not be described again.

Step S502: Obtain M candidate road network points of the current trajectory point in the valid trajectory point data.

In embodiments of the present disclosure, M is a positive integer.

In the embodiment of the present disclosure, step S502 can be implemented in any manner in the various embodiments of the present disclosure, The embodiments of the present disclosure do not limit this, and will not be described again.

Step S503: Determine the variable sliding window corresponding to the current trajectory point.

In the embodiments of the present disclosure, step S503 can be implemented in any manner in the embodiments of the present disclosure. The embodiments of the present disclosure do not limit this and will not be described again.

Step S504: Perform map matching processing on the M candidate road network points based on the variable sliding window to obtain the road network points of the current trajectory point.

In the embodiments of the present disclosure, step S504 can be implemented in any manner in the embodiments of the present disclosure. The embodiments of the present disclosure do not limit this and will not be described again.

Step S505: Obtain the road network points of each trajectory point in the effective trajectory data, and store the road network points of each trajectory point in the effective trajectory data in the storage database.

For example, the road network points of each track point in the effective trajectory data of the moving object are obtained, and the road network points are stored in the road network point set corresponding to the mobile object in the storage database.

In some embodiments, the real-time trajectory data processing method further includes: performing trajectory truncation processing on each trajectory point in the effective trajectory data according to preset trajectory truncation conditions, and storing the truncated road network points in a storage database.

For example, when any trajectory point in the valid trajectory data in the memory meets the preset trajectory truncation condition, the historical trajectory points before the trajectory point are removed and stored in the storage database.

In the embodiment of the present disclosure, the preset trajectory truncation condition may include but is not limited to: the speed of the moving object between the trajectory point and the previous trajectory point is greater than the preset second speed threshold; and/or, the production of the trajectory point The time interval between the time and the acquisition time of the previous trajectory point is greater than the preset time threshold; and/or, there is no connectable road network between the trajectory point and the previous trajectory point; and/or, the acquisition time of the trajectory point The time interval between the acquisition time of the trajectory point of the leader in the trajectory point sequence is greater than the preset third time threshold; and/or the number of historical trajectory points in the trajectory sequence is greater than the preset quantity threshold.

That is to say, after adding the valid track points of the moving object to the track point set of the moving object in the memory, the following processing can be performed on the track points: determine whether the speed of the moving object between the track point and the previous track point is is greater than the preset second speed threshold. If it is greater than the preset second speed threshold, the historical track points before the track point are removed and stored in the storage database; and/or, the acquisition time of the track point is determined to be consistent with the previous speed threshold. Whether the time interval between the acquisition time of a track point is greater than the preset time threshold, if it is greater than the preset time threshold, remove the historical track points before the track point and store them in the storage database; and/or determine the Is there a road network that can be connected between the track point and the previous track point? If there is no road network that you can connect to, remove the historical track points before the track point and store them in Store the database; and/or determine whether the time interval between the acquisition time of the trajectory point and the acquisition time of the trajectory point at the head of the team in the trajectory point sequence is greater than a preset third time threshold. If it is greater than the preset third time threshold, If the time threshold is reached, remove the historical track points before the track point and store them in the storage database; and/or determine whether the number of historical track points in the track sequence is greater than the preset quantity threshold. If it is greater than the preset quantity threshold, then Remove the historical track points before the track point and store them in the storage database; after processing the track points of the moving object based on the above conditions, the track points removed from the memory are stored in the storage database to save memory space.

By implementing the embodiments of the present disclosure, the road network points of each trajectory point can be stored in the storage database, and the trajectory points in the memory can be processed in stages to reduce the storage space occupied by the cache database and the memory and save storage resources.

Please refer to FIG. 6 , which is a schematic structural diagram of a real-time trajectory data processing device provided by the present disclosure. As shown in FIG. 6 , the real-time trajectory data processing device 600 includes: a first processing module 601 , an acquisition module 602 , a second processing module 603 and a third processing module 604 .

The first processing module 601 is used to: obtain the trajectory data of the moving object, and perform denoising processing on the trajectory data to obtain effective trajectory point data. The acquisition module 602 is used to: acquire M candidate road network points of the current trajectory point in the valid trajectory point data, where M is a positive integer. The second processing module 603 is used to: determine a variable sliding window corresponding to the current trajectory point, where the length of the variable sliding window is K, and the variable sliding window includes the N first transition probabilities of the previous trajectory point and each third The corresponding first candidate road network point combination under a transition probability. Each first candidate road network point combination includes K historical candidate road network points, and N and K are positive integers respectively. The third processing module 604 is used to: perform map matching processing on M candidate road network points based on a variable sliding window, and obtain the road network points of the current trajectory point.

In some embodiments, the third processing module 604 is specifically configured to: use a variable sliding window to perform map matching processing on M candidate road network points based on the hidden Markov model and the Viterbi algorithm, and obtain the road network points of the current trajectory point.

In some embodiments, the third processing module 604 is specifically configured to: insert M candidate road network points into the tail of each first candidate road network point combination, and obtain N second candidate road network points corresponding to each candidate road network point. Combination; determine the N second transition probabilities of the N second candidate road network point combinations corresponding to each candidate road network point, and select the second candidate road network point combination with the largest second transition probability from the N second candidate road network point combinations; Determine the second candidate road network point combination with the largest second transition probability among the N second candidate road network point combinations corresponding to each candidate road network point as the third candidate road network point combination, to obtain M third candidate road network point combinations; The first candidate road network point is removed from each third candidate road network point combination to obtain M first candidate road network points; based on the respective transition probabilities of the M third candidate road network point combinations, the current trajectory is determined from the M first candidate road network points Point of road network point.

In some embodiments, the third processing module 604 is specifically configured to: from the M first candidate road network points, select the first candidate road network point removed from the third candidate road network point combination with the largest transition probability, and determine it as the current trajectory point road points.

In some embodiments, please refer to Figure 7, which is another real-time trajectory data processing provided by an embodiment of the present disclosure. Structural diagram of the device. As shown in Figure 7, the real-time trajectory data processing device 700 also includes a fourth processing module 705, which is used to determine the M third candidate route node combinations after removing the first candidate route node as a variable variable corresponding to the next trajectory point. Sliding window; the fifth processing module 706 is used to use the next trajectory point as the new current trajectory point, perform map matching processing on M candidate road network points based on the variable sliding window, and obtain the road network points of the current trajectory point, Until all trajectory points in the valid trajectory point data have completed map matching. Among them, modules 701-704 in Figure 7 have the same structure and function as modules 601-604 in Figure 6 .

In some embodiments, please refer to FIG. 8 , which is a schematic structural diagram of yet another real-time trajectory data processing device provided by an embodiment of the present disclosure. As shown in FIG. 8 , the real-time trajectory data processing device 800 also includes: a storage module 805 for storing the obtained road network points of the trajectory points into the cache database by using the Upsert statement. Among them, modules 801-804 in Figure 8 have the same structure and function as modules 601-604 in Figure 6 .

In some embodiments, please refer to FIG. 9 , which is a schematic structural diagram of yet another real-time trajectory data processing device provided by an embodiment of the present disclosure. As shown in Figure 9, the real-time trajectory data processing device also includes a query module 905, configured to respond to a trajectory query request for the moving object and query the road network information of the moving object from the cache database based on the trajectory query request; and/or, The visualization module 906 is configured to perform visual processing on the road network information of the moving object in response to a request for displaying the road network information of the moving object. Among them, modules 901-904 in Figure 9 have the same structure and function as modules 601-604 in Figure 6 .

In some embodiments, please refer to FIG. 10 , which is a schematic structural diagram of yet another real-time trajectory data processing device provided by an embodiment of the present disclosure. As shown in Figure 10, the real-time trajectory data processing device also includes a sixth processing module 1005, which is used to obtain the road network points of each trajectory point in the effective trajectory data, and store the road network points of each trajectory point in the effective trajectory data to the storage database. middle. Among them, modules 1001-1004 in Figure 10 and modules 601-604 in Figure 6 have the same structure and function.

In a specific embodiment, the sixth processing module 1005 is specifically configured to perform trajectory truncation processing on each trajectory point in the effective trajectory data according to preset trajectory truncation conditions, and store the truncated road network points in the storage database.

Regarding the devices in the above embodiments, the specific manner in which each module performs operations has been described in detail in the embodiments related to the method, and will not be described in detail here.

According to the real-time trajectory data processing device according to the embodiment of the present disclosure, the road network points of the current trajectory point can be obtained based on the current trajectory point and the corresponding sliding window, reducing the amount of calculation required, thereby achieving high precision and low latency for the trajectory data of the moving object. real-time map matching.

Based on embodiments of the present disclosure, the present disclosure also provides a real-time trajectory data processing system, which system includes: a distributed stream processing engine, the distributed stream processing engine includes a plurality of keyed stream partitions, wherein the plurality of The keyed stream partition uses the method described in any embodiment of the present disclosure to process the trajectory data of different moving objects in real time.

In some embodiments, the distributed stream processing engine may be the Apache Flink distributed streaming data flow engine.

Please refer to Figure 11, which is a schematic diagram of a real-time trajectory data processing system provided by an embodiment of the present disclosure. As shown in Figure 11, the trajectory data of multiple moving objects can be obtained through message middleware (for example: distributed message middleware Kafka) and connected to Apache Flink in real time. Through the identification information of each moving object (for example: license plate) No.) divides the trajectory data of multiple moving objects into multiple keyed stream partitions. At the same time, the road network data required for real-time map matching is distributed to each keyed stream partition through broadcast streams to avoid repeated reading and construction of road network data. After real-time preprocessing (for example: denoising) and map matching for each keyed stream partition, the matched trajectory is stored in the cache database in real time through Apache Flink side output at a preset frequency for subsequent trajectories. Query and visual display. The main output is to accumulate the trajectory points after matching multiple moving object maps, and output them to the storage database after reaching a certain threshold.

Based on the embodiments of the present disclosure, the present disclosure also provides an electronic device, including: at least one processor; and a memory communicatively connected to the at least one processor, wherein the memory stores instructions that can be executed by the at least one processor, and the instructions Executed by at least one processor, so that at least one processor can execute the real-time trajectory data processing method of any of the foregoing embodiments.

Based on the embodiments of the present disclosure, the present disclosure also provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause the computer to perform real-time processing according to any of the foregoing embodiments provided by the embodiments of the present disclosure. Trajectory data processing methods.

Please refer to FIG. 12. As shown in FIG. 12, it is a schematic block diagram of an electronic device that can be used to implement embodiments of the present disclosure. Electronic devices are intended to refer to various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The components shown herein, their connections and relationships, and their functions are examples only and are not intended to limit implementations of the disclosure described and/or claimed herein.

As shown in Figure 12, the device 1200 includes a computing unit 1201, which can be loaded into a random access memory (Random Access Memory, RAM) according to a computer program stored in a read-only memory (Read-Only Memory, ROM) 1202 or from a storage unit 1208. )1203 to perform various appropriate actions and processes. In the RAM 1203, various programs and data required for the operation of the device 1200 can also be stored. Computing unit 1201, ROM 1202 and RAM 1203 are connected to each other via bus 1204. An input/output (I/O) interface 1205 is also connected to bus 1204.

Multiple components in the device 1200 are connected to the I/O interface 1205, including: input unit 1206, such as a keyboard, mouse, etc.; output unit 1207, such as various types of displays, speakers, etc.; storage unit 1208, such as a magnetic disk, optical disk, etc. ; and communication unit 1209, such as a network card, modem, wireless communication transceiver, etc. The communication unit 1209 allows the device 1200 to exchange information/data with other devices through computer networks such as the Internet and/or various telecommunications networks.

Computing unit 1201 may be a variety of general and/or special purpose processing components having processing and computing capabilities. computing unit Some examples of 1201 include, but are not limited to, Central Processing Unit (CPU), Graphics Processing Unit (GPU), various dedicated artificial intelligence (AI) computing chips, various types of machines that run machine learning model algorithms. Computing unit, digital signal processor (Digital Signal Process, DSP), and any appropriate processor, controller, microcontroller, etc. The computing unit 1201 performs various methods and processes described above, such as real-time trajectory data processing methods. For example, in some embodiments, the real-time trajectory data processing method may be implemented as a computer software program that is tangibly embodied in a machine-readable medium, such as the storage unit 1208. In some embodiments, part or all of the computer program may be loaded and/or installed onto device 1200 via ROM 1202 and/or communication unit 1209 . When the computer program is loaded into the RAM 1203 and executed by the computing unit 1201, one or more steps of the real-time trajectory data processing method described above may be performed. Alternatively, in other embodiments, the computing unit 1201 may be configured to perform the real-time trajectory data processing method in any other suitable manner (eg, by means of firmware).

Various implementations of the systems and techniques described above may be implemented in digital electronic circuit systems, integrated circuit systems, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Parts (ASSP), System On Chip (SOC), Complex Programmable Logic Device (CPLD), computer hardware, firmware, software, and/or they realized in a combination. These various embodiments may include implementation in one or more computer programs executable and/or interpreted on a programmable system including at least one programmable processor, the programmable processor The processor, which may be a special purpose or general purpose programmable processor, may receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device. An output device.

Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing device, such that the program codes, when executed by the processor or controller, cause the functions specified in the flowcharts and/or block diagrams/ The operation is implemented. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of this disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media may include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media would include electrical connections based on one or more wires, laptop disks, hard drives, random access memory (RAM), read only memory (ROM), erasable programmable ROM (Erasable Programmable Read-Only Memory, EPROM or flash memory), optical fiber, portable compact disk read-only memory (Compact Disc Read-Only Memory, CD-ROM), optical storage device, magnetic storage device, or Any suitable combination of the above.

To provide interaction with a user, the systems and techniques described herein may be implemented on a computer having: a display device (e.g., a cathode ray tube (CRT)) or LCD (Liquid Display Device) for displaying information to the user Crystal Display (liquid crystal display) monitor); and a keyboard and pointing device (such as a mouse or trackball) through which a user can provide input to the computer. Other kinds of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and may be provided in any form, including acoustic input, voice input, or tactile input) to receive input from the user.

The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., A user's computer having a graphical user interface or web browser through which the user can interact with implementations of the systems and technologies described herein), or including such backend components, middleware components, or any combination of front-end components in a computing system. The components of the system may be interconnected by any form or medium of digital data communication (eg, a communications network). Examples of communication networks include: Local Area Network (LAN), Wide Area Network (WAN), the Internet, and blockchain networks.

Computer systems may include clients and servers. Clients and servers are generally remote from each other and typically interact over a communications network. The relationship of client and server is created by computer programs running on corresponding computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host. It is a host product in the cloud computing service system to solve the management problems that exist in traditional physical hosts and VPS (Virtual Private Server) services. It has the disadvantages of high difficulty and weak business scalability. The server can also be a distributed system server or a server combined with a blockchain.

Based on the embodiments of the present disclosure, the present disclosure also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the real-time trajectory data processing method described in any of the foregoing embodiments.

Based on the embodiments of the present disclosure, the present disclosure also provides a computer program, the computer program includes a computer program code, and is run on a computer based on the computer program code, so that the computer executes the real-time trajectory described in any of the foregoing embodiments. Data processing methods.

It should be noted that the aforementioned explanations of the real-time trajectory data processing method and device embodiments are also applicable to the above-mentioned preceding vehicle behavior recognition and processing system, electronic equipment, computer-readable storage media, computer program products and computer programs, and are not included here. Again.

It should be understood that various forms of the process shown above may be used, with steps reordered, added or deleted. For example, each step described in the present application can be executed in parallel, sequentially, or in a different order. As long as the desired results of the technical solution of the present disclosure can be achieved, there is no limitation here.

The above-mentioned specific embodiments do not constitute a limitation on the scope of the present disclosure. It will be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions are possible depending on design requirements and other factors. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of this disclosure shall be included in the protection scope of this disclosure.

Claims

A real-time trajectory data processing method, characterized by including:

Obtain trajectory data of the moving object, and perform denoising processing on the trajectory data to obtain effective trajectory point data;

Obtain M candidate road network points of the current trajectory point in the valid trajectory point data, where the M is a positive integer;

Determine a variable sliding window corresponding to the current trajectory point, where the length of the variable sliding window is K, and the variable sliding window includes the N first transition probabilities of the previous trajectory point and each of the first A corresponding first candidate road network point combination under a transition probability, each of the first candidate road network point combinations includes K historical candidate road network points, and the N and K are respectively positive integers;

Map matching processing is performed on the M candidate road network points based on the variable sliding window to obtain the road network points of the current trajectory point.
The method according to claim 1, characterized in that, performing map matching processing on the M candidate road network points based on the variable sliding window to obtain the road network points of the current trajectory point includes:

Based on the hidden Markov model and the Viterbi algorithm, the variable sliding window is used to perform map matching processing on the M candidate road network points to obtain the road network points of the current trajectory point.
The method according to claim 2, characterized in that, based on the hidden Markov model and the Viterbi algorithm, the variable sliding window is used to perform map matching processing on the M candidate road network points to obtain the current Road network points of track points, including:

Insert the M candidate road network points into the tail of each of the first candidate road network point combinations to obtain N second candidate road network point combinations corresponding to each of the candidate road network point combinations;

Determine N second transition probabilities of N second candidate link point combinations corresponding to each candidate link point, and select the second candidate with the largest second transition probability from the N second candidate link point combinations. Road network point combination;

The second candidate road network point combination with the highest second transition probability among the N second candidate road network point combinations corresponding to each candidate road network point is determined as the third candidate road network point combination, so as to obtain M third candidate road network point combinations. Outlet combination;

Remove the first candidate road network point from each of the third candidate road network point combinations to obtain M first candidate road network points;

Based on the transition probabilities of respective combinations of the M third candidate road network points, the road network point of the current trajectory point is determined from the M first candidate road network points.
The method according to claim 3, characterized in that the path of the current trajectory point is determined from the M first candidate path node points based on the respective transition probabilities of the M third candidate path node combinations. Outlets, including:

From the M first candidate road network points, the first candidate road network point removed from the third candidate road network point combination with the largest transition probability is selected and determined as the road network point of the current trajectory point.
The method according to claim 3 or 4, further comprising:

Determine the M third candidate road network point combinations after removing the first candidate road network point as a variable sliding window corresponding to the next trajectory point;

Use the next trajectory point as a new current trajectory point, perform the map matching process on the M candidate road network points based on the variable sliding window, and obtain the road network points of the current trajectory point, until All trajectory points in the valid trajectory point data have completed map matching.
The method according to claim 1, further comprising:

The Upsert statement is used to store the obtained road network points of the trajectory points into the cache database.
The method according to claim 6, further comprising:

In response to a trajectory query request for the mobile object, query the road network information of the mobile object from the cache database based on the trajectory query request;

And/or, in response to a request for displaying the road network information of the mobile object, visualizing the road network information of the mobile object.
The method according to claim 1, further comprising:

Obtain the road network points of each trajectory point in the effective trajectory data, and store the road network points of each trajectory point in the effective trajectory data into a storage database.
The method according to claim 8, wherein storing the road network points of each trajectory point in the effective trajectory data into a storage database includes:

Perform trajectory truncation processing on each trajectory point in the effective trajectory data according to preset trajectory truncation conditions, and store the truncated road network points in the storage database.
A real-time trajectory data processing device, characterized in that the device includes:

The first processing module is used to obtain the trajectory data of the moving object, and perform denoising processing on the trajectory data to obtain effective trajectory point data;

An acquisition module, used to acquire M candidate road network points of the current trajectory point in the valid trajectory point data, where the M is a positive integer;

The second processing module is used to determine a variable sliding window corresponding to the current trajectory point, wherein the length of the variable sliding window is K, and the variable sliding window includes N first transitions of the previous trajectory point probability and the first candidate road network point combination corresponding to each first transition probability, each of the first candidate road network point combinations includes K historical candidate road network points, and the N and K are respectively positive integers;

The third processing module is configured to perform map matching processing on the M candidate road network points based on the variable sliding window to obtain the road network points of the current trajectory point.
The device according to claim 10, characterized in that the third processing module is specifically used to:

Based on the Hidden Markov Model and Viterbi Algorithm, the variable sliding window is used to select the M candidate road network points. Perform map matching processing to obtain the road network point of the current trajectory point.
The device according to claim 11, characterized in that the third processing module is specifically used to:

Insert the M candidate road network points into the tail of each of the first candidate road network point combinations to obtain N second candidate road network point combinations corresponding to each of the candidate road network point combinations;

Determine N second transition probabilities of N second candidate link point combinations corresponding to each candidate link point, and select the second candidate with the largest second transition probability from the N second candidate link point combinations. Road network point combination;

The second candidate road network point combination with the highest second transition probability among the N second candidate road network point combinations corresponding to each candidate road network point is determined as the third candidate road network point combination, so as to obtain M third candidate road network point combinations. Outlet combination;

Remove the first candidate road network point from each of the third candidate road network point combinations to obtain M first candidate road network points;

Based on the transition probabilities of respective combinations of the M third candidate road network points, the road network point of the current trajectory point is determined from the M first candidate road network points.
The device according to claim 12, characterized in that the third processing module is specifically used to:

From the M first candidate road network points, the first candidate road network point removed from the third candidate road network point combination with the largest transition probability is selected and determined as the road network point of the current trajectory point.
The device according to claim 12 or 13, characterized in that the device further includes:

The fourth processing module is used to determine the M third candidate road network point combinations after removing the first candidate road network point as a variable sliding window corresponding to the next trajectory point;

The fifth processing module is used to use the next trajectory point as a new current trajectory point, perform the map matching process on the M candidate road network points based on the variable sliding window, and obtain the current trajectory point. of road network points until all trajectory points in the valid trajectory point data complete map matching.
The device according to claim 10, characterized in that the device further includes:

The storage module is used to store the obtained road network points of the trajectory points into the cache database using the Upsert statement.
The device according to claim 15, characterized in that the device further includes:

A query module, configured to respond to a trajectory query request for the mobile object and query the road network information of the mobile object from the cache database based on the trajectory query request;

And/or, a visualization module, configured to perform visual processing on the road network information of the mobile object in response to a request for displaying the road network information of the mobile object.
The device according to claim 10, characterized in that the device further includes:

The sixth processing module is used to obtain the road network points of each trajectory point in the effective trajectory data, and store the road network points of each trajectory point in the effective trajectory data into a storage database.
The device according to claim 17, characterized in that the sixth processing module is specifically used for:

Perform trajectory truncation processing on each trajectory point in the effective trajectory data according to the preset trajectory truncation conditions, and truncate The subsequent road network points are stored in the storage database.
A real-time trajectory data processing system, which is characterized by including:

Distributed stream processing engine, the distributed stream processing engine includes a plurality of keyed stream partitions, wherein the multiple keyed stream partitions use the method according to any one of claims 1 to 9 to process different moving objects. Trajectory data are processed in real time.
An electronic device, characterized by including:

at least one processor;

and a memory communicatively connected to the at least one processor;

Wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor, so that the at least one processor can execute any one of claims 1 to 9. The real-time trajectory data processing method described in the item.
A non-transient computer-readable storage medium storing computer instructions, characterized in that the computer instructions are used to cause the computer to execute the real-time trajectory data processing method according to any one of claims 1 to 9.
A computer program product, comprising a computer program, characterized in that, when executed by a processor, the computer program implements the steps of the real-time trajectory data processing method according to any one of claims 1 to 9.
A computer program, characterized in that the computer program includes computer program code, and is run on a computer based on the computer program code, so that the computer performs real-time trajectory data processing as described in any one of claims 1 to 9 method.