Trajectory processing method and apparatus, storage medium, and electronic device

Abstract

Embodiments of the present specification disclose a trajectory processing method and device, a storage medium and an electronic device, wherein the method comprises: performing trajectory point matching on each vehicle travel trajectory to obtain at least one similar travel trajectory group; performing trajectory parameter constraint processing on each reference travel trajectory in the similar travel trajectory group to obtain a processed regular travel trajectory group; and determining a target regular travel trajectory based on each regular travel trajectory group.

Description

Technical Field

[0001] This specification relates to the field of computer technology, and in particular to a trajectory processing method, apparatus, storage medium, and electronic device. Background Technology

[0002] With the rapid development of cities, the number of vehicles owned by urban users is constantly increasing. As the level of intelligent transportation continues to improve, obtaining the geographical location information of moving vehicles is becoming increasingly convenient. In practical applications, it is often necessary to mine user travel patterns from a large number of vehicle travel trajectories in order to provide better services to users based on these patterns. Summary of the Invention

[0003] This specification provides a trajectory processing method, apparatus, storage medium, and electronic device, which can solve the problems of incomplete and low-accuracy patterned trajectories. The technical solution is as follows:

[0004] Firstly, embodiments of this specification provide a trajectory processing method, the method comprising:

[0005] Multiple vehicle travel trajectories are acquired, and trajectory point matching is performed on each of the vehicle travel trajectories to obtain at least one group of similar travel trajectories, wherein the group of similar trajectories includes multiple reference travel trajectories.

[0006] The reference travel trajectories within the similar travel trajectory group are subjected to trajectory parameter constraint processing to obtain the processed regular travel trajectory group;

[0007] The target regular travel trajectory is determined based on each of the aforementioned regular travel trajectory groups.

[0008] Secondly, embodiments of this specification provide a trajectory processing apparatus, the apparatus comprising:

[0009] The trajectory matching module is used to acquire multiple vehicle travel trajectories, perform trajectory point matching on each vehicle travel trajectory, and obtain at least one similar travel trajectory group, wherein the similar trajectory group includes multiple reference travel trajectories.

[0010] The parameter constraint module is used to perform trajectory parameter constraint processing on each of the reference travel trajectories in the similar travel trajectory group to obtain the processed regular travel trajectory group.

[0011] The trajectory determination module is used to determine the target regular travel trajectory based on the regular travel trajectory group.

[0012] Thirdly, embodiments of this specification provide a computer storage medium storing a plurality of instructions adapted for loading by a processor and executing the above-described method steps.

[0013] Fourthly, embodiments of this specification provide an electronic device that may include: a processor and a memory; wherein the memory stores a computer program adapted to be loaded by the processor and to execute the above-described method steps.

[0014] Fifthly, embodiments of this specification provide a vehicle that includes the aforementioned electronic equipment.

[0015] The beneficial effects of the technical solutions provided in some embodiments of this specification include at least the following:

[0016] In one or more embodiments of this specification, the electronic device can perform trajectory point matching on multiple acquired vehicle travel trajectories to obtain at least one group of similar travel trajectories. Then, trajectory parameter constraint processing is applied to each reference travel trajectory within the similar travel trajectory group to obtain a processed group of regular travel trajectories. Finally, a target regular travel trajectory is determined based on each group of regular travel trajectories. By obtaining similar travel trajectory groups through trajectory point matching and combining this with parameter constraints on the similar travel trajectory groups, the phenomenon of incomplete and low-accuracy pattern detection can be avoided. This enables accurate detection of potential pattern trajectories to cover more pattern trajectories, thereby improving the accuracy of trajectory detection. 。 Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments or prior art of this specification, the drawings used in the description of the embodiments or prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this specification. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a schematic flowchart of a trajectory processing method provided in the embodiments of this specification;

[0019] Figure 2 This is a schematic flowchart of a trajectory processing method provided in the embodiments of this specification;

[0020] Figure 3 This is a schematic diagram of the structure of a trajectory processing device provided in the embodiments of this specification;

[0021] Figure 4 This is a schematic diagram of the structure of a trajectory matching module provided in an embodiment of this specification;

[0022] Figure 5 This is a schematic diagram of the structure of a trajectory filtering unit provided in the embodiments of this specification;

[0023] Figure 6 This is a schematic diagram of the structure of a parameter constraint module provided in the embodiments of this specification;

[0024] Figure 7 This is a schematic diagram of the structure of an electronic device provided in the embodiments of this specification;

[0025] Figure 8 This is a schematic diagram of the operating system and user space structure provided in the embodiments of this specification;

[0026] Figure 9 yes Figure 8 Architecture diagram of the Android operating system in China;

[0027] Figure 10 yes Figure 8 Architecture diagram of the iOS operating system. Detailed Implementation

[0028] The technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this specification, and not all embodiments. Based on the embodiments in this specification, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this specification.

[0029] In the description of this specification, it should be understood that the terms "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance. In the description of this specification, it should be noted that, unless otherwise expressly specified and limited, "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices. Those skilled in the art can understand the specific meaning of the above terms in this specification based on the specific circumstances. Furthermore, in the description of this specification, unless otherwise stated, "multiple" means two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, and B alone. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship.

[0030] In related technologies, mining user travel patterns from a large number of vehicle travel trajectories often involves directly calculating the overlap rate between routes. However, in real-world applications, there are many interfering factors such as routes and location, and using route overlap similarity calculations can lead to problems such as incomplete patterns and low accuracy.

[0031] The present specification will now be described in detail with reference to specific embodiments.

[0032] In one embodiment, such as Figure 1 As shown, a trajectory processing method is proposed, which can be implemented using a computer program and run on a trajectory processing device based on the von Neumann architecture. This computer program can be integrated into an application or run as a standalone utility application. The trajectory processing device can be an electronic device.

[0033] Specifically, the trajectory processing method includes:

[0034] S102: Obtain multiple vehicle travel trajectories, perform trajectory point matching on each vehicle travel trajectory, and obtain at least one similar travel trajectory group, wherein the similar trajectory group includes multiple reference travel trajectories;

[0035] The vehicle travel trajectory refers to the trajectory data generated by the user riding in the vehicle during its journey. During vehicle operation, positioning technologies (such as Global Positioning System, BeiDou Navigation Satellite System, network positioning technology, etc.) can be used to periodically or in real-time acquire vehicle trajectory points (which can be understood as vehicle trajectory positions). Multiple vehicle trajectory points during the vehicle's journey constitute the vehicle travel trajectory. It is understandable that a vehicle travel trajectory is typically a trajectory composed of several vehicle trajectory points (or vehicle location points) in a corresponding time sequence.

[0036] For illustration, for any vehicle travel trajectory S, S = p1p2p3...pi...pn, where pi (1≤i≤n) represents the vehicle trajectory points in the vehicle travel trajectory, and the vehicle trajectory points can be in the form of latitude and longitude coordinates.

[0037] To illustrate, in actual traffic scenarios, a large number of vehicle travel trajectories can be obtained. The multiple vehicle travel trajectories obtained can be the travel trajectories of different vehicle users or the travel trajectories of the same vehicle user.

[0038] Furthermore, the electronic device can perform trajectory point matching on each vehicle's travel trajectory to obtain at least one group of similar travel trajectories, and the group of similar trajectories includes multiple reference travel trajectories.

[0039] Optionally, the electronic device may calculate the trajectory point matching degree of any two vehicle travel trajectories based on the trajectory (position) points corresponding to each trajectory time point or part of the trajectory time points, and determine at least one similar travel trajectory group from several vehicle travel trajectories based on the trajectory point matching degree. The similar travel trajectory group can be understood as a set of reference travel trajectories determined from the dimension of similar trajectory points.

[0040] In one feasible implementation, the electronic device performs trajectory point matching on each of the vehicle travel trajectories to obtain at least one group of similar travel trajectories, which can be:

[0041] A2: Perform trajectory point matching between the first vehicle travel trajectory and at least one second travel trajectory to obtain at least one trajectory point matching degree. The first vehicle travel trajectory is any one of all the vehicle travel trajectories, and the second travel trajectory is the vehicle travel trajectory of all the vehicle travel trajectories except the first vehicle travel trajectory.

[0042] For illustration, assume there are n vehicle travel trajectories. The current first vehicle travel trajectory is one of the n vehicle travel trajectories, and the second travel trajectory is the vehicle travel trajectory other than the first vehicle travel trajectory. For example, the n vehicle travel trajectories S can be represented as S1, S2, S3...Si...Sn.

[0043] Indicatively, for each travel trajectory point included in any vehicle travel trajectory, the travel trajectory point corresponds to a trajectory time point. The trajectory time point can be in the form of travel time, travel percentage, etc. The electronic device can use the trajectory points of each trajectory time point or some trajectory time points as a reference to calculate the matching degree of the trajectory points of the first vehicle travel trajectory with several second travel trajectories respectively.

[0044] Optionally, for any trajectory time point on the vehicle's travel trajectory, the trajectory point matching degree can be calculated by measuring the trajectory point distance between the trajectory point on the first vehicle travel trajectory and the trajectory point on the second vehicle travel trajectory, and the matching degree can be determined based on the trajectory point distance.

[0045] The vehicle travel trajectory is obtained by connecting the sampled trajectory positions in pairs according to the sampling time sequence of a number of position sampling points during the vehicle's movement. The trajectory time point can be understood as the mark of a certain position sampling point with the travel start point as the position sampling start point. The trajectory time point is often described as the i-th trajectory time point of the vehicle travel trajectory. The i-th trajectory time point can be understood as: the mark of the i-th position sampling point with the travel start point as the position sampling start point. The trajectory point corresponding to the trajectory time point can be understood as: the position sampling point obtained by the i-th position sampling point with the travel start point as the position sampling start point.

[0046] Furthermore, by comparing any two vehicle travel trajectories, it is expected that the trajectory (location point) corresponding to any trajectory time point on a certain travel trajectory is 0 or less than a distance threshold between the trajectory (location point) corresponding to the same trajectory time point on another travel trajectory. In this case, the two travel trajectories are considered to be highly compatible. It can be understood that the smaller the trajectory point distance, the higher the matching degree. That is, the magnitude of the trajectory point distance is negatively correlated with the matching degree. A conversion relationship between trajectory point distance and trajectory point matching degree can be established to convert the trajectory point distance into trajectory point matching degree.

[0047] As an illustration, multiple trajectory time points can be set to calculate the trajectory point matching degree. When there are multiple trajectory time points, after the trajectory points of the first vehicle travel trajectory and the second travel trajectory are matched separately, the obtained trajectory point matching degree is the set of matching degrees corresponding to each trajectory time point.

[0048] For example, the trajectory point matching degree is composed of the matching degrees corresponding to x trajectory time points; or, for another example, the trajectory point matching degree is the sum of the matching degrees corresponding to x trajectory time points.

[0049] It is understandable that the number of second travel trajectories corresponding to the current first vehicle travel trajectory is usually n-1. Therefore, the matching degree of the trajectory points corresponding to the first vehicle travel trajectory and the n-1 second travel trajectories can be obtained, that is, the matching degree of the trajectory points is n-1.

[0050] A4: Based on the trajectory point matching degree, perform trajectory filtering on the at least one second travel trajectory to obtain at least one similar travel trajectory corresponding to the first vehicle travel trajectory;

[0051] Indicatively, the electronic device can acquire a trajectory point matching threshold, and filter out second travel trajectories from the at least one second travel trajectory whose trajectory point matching degree is less than the trajectory point matching threshold, to obtain at least one similar travel trajectory corresponding to the filtered first vehicle travel trajectory.

[0052] In one or more embodiments of this specification, in the process of determining similar travel trajectory groups based on trajectory point matching degree, there is usually a default trajectory point matching threshold, which is used to measure the degree of trajectory point matching between the travel trajectories of two vehicles.

[0053] Understandably, the size of the trajectory point matching threshold is related to the constraint accuracy of trajectory point matching; the larger the trajectory point matching threshold, the higher the constraint accuracy is usually.

[0054] Optionally, the default trajectory point matching threshold can be used as the trajectory point matching threshold based on the trajectory point matching degree calculated above. The default trajectory point matching threshold is usually a threshold with high constraint accuracy.

[0055] Optionally, in one or more embodiments of this specification, trajectory point matching is typically performed first to obtain similar travel trajectory groups, and then trajectory parameter constraints are applied to these similar travel trajectory groups. Multiple rounds of trajectory parameter constraints are then used to finally mine regular trajectories. Considering that there are many travel interference factors in actual application scenarios, the trajectory point matching threshold with high constraint accuracy may have issues such as difficulty in fitting regular trajectories and poor trajectory generalization during the regular trajectory mining process. Vehicle travel trajectories that are essentially of the same regular trajectory type may be filtered out. Therefore, the constraint accuracy of the default trajectory point matching threshold can be relaxed to obtain a processed reference trajectory point matching threshold. The constraint accuracy of the reference trajectory point matching threshold is less than the default trajectory point matching threshold. This reference trajectory point matching threshold is used as the current trajectory point matching threshold. This way, the subsequently obtained similar travel trajectory groups can contain more reference travel trajectories. Then, by combining multiple rounds of trajectory parameter constraints, the regular trajectory is finally mined from several similar travel trajectory groups.

[0056] Furthermore, trajectory point matching thresholds are used to filter out several second-journey trajectories. For example, suppose the trajectory point matching degrees between the first-journey trajectory and n-1 second-journey trajectories are r1, r2, r3...r n-1 Assuming the default trajectory point matching threshold is R, then based on the trajectory point matching degrees r1, r2, r3...r n-1 The system uses a default trajectory point matching threshold R to filter out trajectory points from n-1 second-journey trajectories. For example, second-journey trajectories with a trajectory point matching degree less than the threshold R are filtered out from the "n-1 second-journey trajectories," resulting in several similar travel trajectories after filtering. For instance, if the trajectory point matching degrees r1, r2, and r3 are less than the threshold R, then the second-journey trajectories corresponding to r1, r2, and r3 are filtered out. Furthermore, several subsequent similar travel trajectories and the current first travel trajectory are used as reference travel trajectories to form a group of similar travel trajectories.

[0057] A6: Based on each first vehicle travel trajectory and each similar travel trajectory corresponding to the first vehicle travel trajectory, a similar travel trajectory group corresponding to each first vehicle travel trajectory is obtained. The similar travel trajectory group includes the first vehicle travel trajectory and each similar travel trajectory corresponding to the first vehicle travel trajectory.

[0058] Understandably, for any first vehicle travel trajectory Si, the similar travel trajectories corresponding to the first vehicle travel trajectory Si can be represented as Y1, Y2, Y3...Yx; the first vehicle travel trajectory Si and the similar travel trajectories can be represented as Y1, Y2, Y3...Yx, both of which serve as reference travel trajectories within the similar travel trajectory group, in order to obtain the similar travel trajectory group corresponding to the first vehicle travel trajectory Si.

[0059] Understandably, by traversing the first vehicle trajectory Si in all vehicle travel trajectories and performing the aforementioned method, several similar travel trajectory groups can be obtained.

[0060] In one feasible implementation, the trajectory point matching of each vehicle's travel trajectory to obtain at least one similar travel trajectory group can be achieved by using feature vector engineering clustering. Feature vector engineering encodes each vehicle's travel trajectory into a travel trajectory vector. Feature vector engineering can encode the vehicle's travel trajectory into a high-dimensional vector space. In the high-dimensional vector space, the vehicle's travel trajectory is represented as a feature vector. Then, the travel trajectory vectors are clustered, and several similar travel trajectory groups are obtained based on the cluster centers.

[0061] Furthermore, feature vector engineering can be implemented using a trajectory vector extraction model created based on a machine learning model. The machine learning model can be one or more of the following models: Convolutional Neural Network (CNN), Deep Neural Network (DNN), Recurrent Neural Networks (RNN), embedding model, Gradient Boosting Decision Tree (GBDT), Logistic Regression (LR), etc.

[0062] The following explains the process of clustering travel trajectory vectors:

[0063] Clustering is performed on the travel trajectory vectors. In specific implementation, the number of clusters x for similar travel trajectory groups can be preset. The number of clusters x is less than or equal to the number of vehicle travel trajectories n. The purpose of clustering is to obtain a set of clusters with the number x indicating the number of data points from the data set composed of all travel trajectory vectors.

[0064] During clustering:

[0065] 1. Randomly select x travel trajectory vectors from the dataset as centroids;

[0066] 2. For each travel trajectory vector in the dataset, calculate the distance between the travel trajectory vector and each centroid (such as Euclidean distance or Manhattan distance), and divide the travel trajectory vector into the set to which the centroid indicated by the shortest distance belongs;

[0067] 3. Then, recalculate the centroid for each set based on the centroid calculation formula;

[0068] 4. Calculate the target distance between the new centroid and the original centroid. Based on this distance, determine whether the clustering process should be terminated. If it is terminated, sort the cluster size of each travel trajectory vector within the category and take the top X vectors of each category as reference trajectory vectors to generate similar travel trajectory groups based on the reference travel trajectories corresponding to the reference trajectory vectors. If it is not terminated, execute steps 2-4 above.

[0069] Optionally, the clustering process can be terminated based on this distance. This can be achieved by setting a distance threshold, where the process terminates when the target distance is less than the threshold, and otherwise continues with steps 2-4 above.

[0070] Optionally, the distances (between the two feature vectors) mentioned above can be calculated using at least one of the following formulas: Euclidean distance formula, Manhattan distance formula, cosine distance formula, correlation coefficient distance formula, etc.

[0071] S104: Perform trajectory parameter constraint processing on each of the reference travel trajectories in the similar travel trajectory group to obtain the processed regular travel trajectory group;

[0072] The trajectory parameter constraints can be multi-round trajectory parameter constraints, with each round of trajectory parameter constraints corresponding to a different trajectory mining method.

[0073] In one or more embodiments of this specification, several trajectory mining methods can be determined for similar travel trajectory groups, and these trajectory mining methods can be pre-defined. Then, the trajectory mining methods are used to constrain the trajectory parameters of each reference travel trajectory within the similar travel trajectory group. During the trajectory parameter constraint process: corresponding parameter indicators are calculated based on the corresponding trajectory mining method, and then the calculated parameter indicators are combined with the parameter constraint indicators corresponding to the trajectory mining method to filter the similar trajectory group or the reference travel trajectories within the similar trajectory group. Multiple trajectory mining methods correspond to the aforementioned multiple rounds of filtering processes until a regular travel trajectory group is finally obtained.

[0074] Optionally, the default parameter constraint index corresponding to the trajectory mining method can be used to filter the reference travel trajectory;

[0075] Optionally, during each round of trajectory parameter constraints on similar travel trajectory groups based on this trajectory mining method, the parameter constraint precision of the current round can be adjusted by adjusting the index value of the default parameter constraint index. This avoids the single-dimensional trajectory mining method from reaching a local optimum during the trajectory mining process. Instead, multiple rounds of trajectory parameter constraint processing are used, and multiple rounds of trajectory mining processing are applied to similar travel trajectory groups based on different trajectory parameter constraint methods. After multiple rounds of trajectory parameter constraint processing, the overall trajectory mining global optimum effect is achieved, improving the generalization ability of trajectory mining and maximizing the discovery of potential regular travel trajectories.

[0076] In one or more embodiments of this specification, the trajectory mining method may include at least two of the following: a distance constraint method based on a reference location point, a ratio constraint method based on the mileage difference to the mileage mean, and a variance constraint method based on the mileage variance. In practical applications, a customized trajectory mining method may also be incorporated for reference based on trajectory mining techniques in related technologies.

[0077] S106: Determine the target regular travel trajectory based on each of the aforementioned regular travel trajectory groups.

[0078] The regular travel trajectory group can be understood as a collection of identical or similar travel trajectories of the same regular travel type. By fitting several travel trajectories in a regular travel trajectory group, a target regular travel trajectory can be obtained.

[0079] In illustrative terms, in practical applications, a regular travel trajectory group could be a travel trajectory group corresponding to a user's commuting trip, including several similar or identical travel trajectories used by the user for commuting; a regular travel trajectory group could be a travel trajectory group corresponding to a user's trip to pick up / drop off family members (such as children or the elderly), including several similar or identical travel trajectories used by the user for picking up / dropping off family members (such as children or the elderly); a regular travel trajectory group could be a travel trajectory group corresponding to a user's refueling / charging trip, including several similar or identical travel trajectories used by the user for refueling / charging; a regular travel trajectory group could be a travel trajectory group corresponding to a user's trip to visit relatives and friends, including several similar or identical travel trajectories used by the user for visiting relatives and friends, and so on.

[0080] In one or more embodiments of this specification, several regular travel trajectory groups are mined by performing the aforementioned trajectory processing method. The travel trajectories in the regular travel trajectory group are highly similar in terms of the user's travel dimension, and are usually travel trajectories of the same trajectory type. Based on this, by fitting the travel trajectories in the group with a set of regular travel trajectory groups as a reference, the target regular travel trajectory can be obtained.

[0081] Optionally, using a set of regular travel trajectories as a reference, fitting the travel trajectory within the set can be done by selecting one travel trajectory from the set as the target regular travel trajectory.

[0082] Optionally, using a set of regular travel trajectories as a reference, fitting the travel trajectories within the set can be done by fitting each travel trajectory point by point to obtain the target regular travel trajectory after fitting the trajectory points. For example, using each trajectory time point as a reference, the mean value of the trajectory points corresponding to the same trajectory time point in each travel trajectory is calculated. The mean value of the trajectory points is the fitted trajectory point after fitting the trajectory time point. In this way, combining the fitted trajectory points corresponding to each trajectory time point yields a target regular travel trajectory.

[0083] Optionally, using a set of regular travel trajectories as a reference, fitting the travel trajectory within the set can be done by using the travel trajectory corresponding to the selected mileage probability value as the target regular travel trajectory. The mileage probability value includes, but is not limited to, fitting one or more of the following types: average mileage, maximum mileage, minimum mileage, median mileage.

[0084] In one or more embodiments of this specification, the electronic device can perform trajectory point matching on multiple acquired vehicle travel trajectories to obtain at least one group of similar travel trajectories. Then, trajectory parameter constraint processing is applied to each reference travel trajectory within the similar travel trajectory group to obtain a processed group of regular travel trajectories. Finally, a target regular travel trajectory is determined based on each group of regular travel trajectories. By obtaining similar travel trajectory groups through trajectory point matching and combining this with parameter constraints on the similar travel trajectory groups, the phenomenon of incomplete and low-accuracy regular trajectory discovery can be avoided. This enables accurate discovery of potential regular trajectories to cover more regular trajectories, thereby improving the accuracy of trajectory discovery.

[0085] Please see Figure 3 , Figure 3 This is a flowchart illustrating another embodiment of the trajectory processing method proposed in this specification. Specifically:

[0086] S202: Obtain multiple vehicle travel trajectories, perform trajectory point matching on each vehicle travel trajectory, and obtain at least one similar travel trajectory group, wherein the similar trajectory group includes multiple reference travel trajectories;

[0087] For details, please refer to the method steps in other embodiments of this specification, which will not be repeated here.

[0088] S204: Determine a combination of trajectory mining methods for the group of similar travel trajectories, wherein the combination of trajectory mining methods includes multiple trajectory mining methods;

[0089] The combination of trajectory mining methods includes multiple trajectory mining methods;

[0090] Optionally, the electronic device can be pre-set with a default combination of trajectory mining methods;

[0091] Optionally, multiple reference trajectory mining method combinations can be set. The trajectory mining method combination is selected based on the intra-group parameters of similar travel trajectory groups. The intra-group parameters can be one or more of the following types of parameters: intra-group average mileage, number of intra-group trajectories, maximum mileage difference, etc. The appropriate combination of trajectory parameters can be selected to constrain the trajectory parameters. Different intra-group parameters can select the most suitable trajectory mining method combination to improve the trajectory mining convergence speed and ensure the trajectory mining accuracy.

[0092] Indicatively, multiple reference group parameters are pre-established as a combination mapping relationship between the reference group parameter ranges and the corresponding reference trajectory mining methods. This combination mapping relationship can be represented by a combination mapping table, a combination mapping array, or a combination mapping function. In practical applications, intra-group parameters such as average intra-group mileage, number of intra-group trajectories, and maximum mileage difference for similar travel trajectory groups can be determined. Then, the target intra-group parameter range into which the intra-group parameters fall is determined from the multiple reference group parameter ranges. Finally, the trajectory mining method corresponding to the target group parameter range is incorporated into the reference.

[0093] In one or more embodiments of this specification, the trajectory mining method may include at least two of the following: a distance constraint method based on a reference location point, a ratio constraint method based on the mileage difference to the mileage mean, and a variance constraint method based on the mileage variance. In practical applications, a customized trajectory mining method may also be incorporated for reference based on trajectory mining techniques in related technologies. No specific limitation is made to the trajectory mining method here. The methods disclosed above are merely those involved in preferred embodiments of this specification. Therefore, equivalent variations made according to the claims of this specification, and other trajectory mining methods extended to include regular trajectory mining, are still within the scope of this specification.

[0094] S206: Using the trajectory mining methods described above, perform multiple rounds of trajectory parameter constraint processing on each of the reference travel trajectories in the similar travel trajectory group to obtain the processed regular travel trajectory group.

[0095] Specifically, trajectory mining methods can be used one by one to constrain the trajectory parameters of each reference trajectory within a similar trajectory group. During the trajectory parameter constraint process, the corresponding parameter index is calculated according to the corresponding trajectory mining method. Then, the calculated parameter index is filtered by the similar trajectory group or / or the reference trajectory within the similar trajectory group in combination with the parameter constraint index corresponding to the trajectory mining method. Multiple trajectory mining methods correspond to the aforementioned multiple rounds of filtering process until the regular trajectory group is finally obtained.

[0096] In one feasible implementation, the electronic device performs multiple rounds of trajectory parameter constraint processing on each of the aforementioned trajectory mining methods to obtain a processed regular trajectory group. This can be achieved in the following manner:

[0097] Each trajectory mining method was used to perform trajectory filtering on each similar travel trajectory group to obtain the processed regular travel trajectory group;

[0098] For example, the trajectory mining methods include distance constraint based on reference location points, ratio constraint based on mileage difference and mileage mean, and variance constraint based on mileage variance. The processing of these three constraint methods can be independent of each other and can be executed in parallel. Each similar travel trajectory group is processed by each trajectory mining method to filter out the trajectory, resulting in a processed regular travel trajectory group.

[0099] In one feasible implementation, the electronic device performs multiple rounds of trajectory parameter constraint processing on each of the aforementioned trajectory mining methods to obtain a processed regular trajectory group. This can be achieved in the following manner:

[0100] B2: Determine the constraint processing order corresponding to each of the trajectory mining methods, and determine the first trajectory mining method based on the constraint processing order;

[0101] The constraint processing order is the sequential processing order of multiple trajectory mining methods. For example, assuming the constraint processing order is "Method 1-Method 3-Method 4", the electronic device first uses "Method 1" to perform multiple rounds of trajectory parameter constraint processing on each of the reference travel trajectories in the similar travel trajectory group, then uses "Method 3" to perform multiple rounds of trajectory parameter constraint processing on each of the reference travel trajectories in the similar travel trajectory group and / or the similar travel trajectory group, and finally uses "Method 4" to perform multiple rounds of trajectory parameter constraint processing on each of the reference travel trajectories in the similar travel trajectory group and / or the similar travel trajectory group.

[0102] It is understandable that there are multiple trajectory mining methods. The first trajectory mining method can be understood as the trajectory mining method used in the current round of constraint processing.

[0103] B4: Use the first trajectory mining method to perform trajectory filtering on each of the similar travel trajectory groups to obtain at least one of the processed similar travel trajectory groups;

[0104] In one or more embodiments of this specification, the trajectory mining method is provided with parameter constraint indicators. The parameter constraint indicators are used to calculate the corresponding parameter indicators based on the trajectory mining method. Then, the similar travel trajectory group and / or the reference travel trajectory within the similar travel trajectory group that do not meet the parameter constraint indicators are filtered in combination with the parameter constraint indicators of the trajectory mining method. After each round of filtering, the processed similar travel trajectory group can be obtained.

[0105] B6: Based on the constraint processing order, determine the next second trajectory mining method corresponding to the first trajectory mining method, use the second trajectory mining method as the first trajectory mining method, and perform the step of using the first trajectory mining method to perform trajectory filtering processing on each of the similar travel trajectory groups to obtain at least one of the processed similar travel trajectory groups.

[0106] For example, assuming the constraint processing order is "Method 1-Method 3-Method 4", and assuming the current first trajectory mining method of the electronic device is "Method 1", then after performing the step of filtering the similar travel trajectory group and / or the reference travel trajectory within the similar travel trajectory group using the first trajectory mining method to obtain the processed similar travel trajectory group, according to the constraint processing order "Method 1-Method 3-Method 4", the next second trajectory mining method corresponding to the first trajectory mining method is "Method 3"; then "Method 3" is used as the first trajectory mining method and the step of filtering the similar travel trajectory group and / or the reference travel trajectory within the similar travel trajectory group using the first trajectory mining method to obtain the processed similar travel trajectory group is step B4;

[0107] B8: If it is determined based on the constraint processing order that there is no next second trajectory mining method corresponding to the first trajectory mining method, then the similar travel trajectory group is regarded as the regular travel trajectory group.

[0108] Understandably, after each round of trajectory parameter constraints, the electronic device determines whether there is a next second trajectory mining method corresponding to the first trajectory mining method based on the constraint processing order. If there is, it continues to execute the step of using the second trajectory mining method as the first trajectory mining method and performing the filtering process using the first trajectory mining method to obtain the processed similar travel trajectory group. If it is determined based on the constraint processing order that there is no next second trajectory mining method corresponding to the first trajectory mining method, the retained similar travel trajectory group is used as a regular travel trajectory group, which includes several travel trajectories.

[0109] In one or more embodiments of this specification, the multiple trajectory mining methods involved in the combination of trajectory mining methods can be regarded as a local relaxation of trajectory mining from the dimension of mining methods. After multiple rounds of trajectory parameter constraint processing, the overall trajectory mining achieves the global optimal effect, improves the generalization ability of trajectory mining, and can maximize the mining of potential regularity trajectory.

[0110] Indicatively, the trajectory mining method may be a distance constraint method based on a reference location point, a ratio constraint method based on the mileage difference to the mileage mean, or a variance constraint method based on the mileage variance. It is understood that the combination of trajectory mining methods includes at least two trajectory mining methods.

[0111] Understandably, the combination of trajectory mining methods can include two of the following: "distance constraint based on reference location points, ratio constraint based on mileage difference to mileage mean, and variance constraint based on mileage variance".

[0112] In one feasible implementation, if the trajectory mining method is a reference location point distance constraint method, the electronic device performs the following steps:

[0113] The electronic device determines at least one reference location point type corresponding to each of the similar travel trajectory groups, calculates the distance difference between the first reference location point and at least one second reference location point based on the reference location point type, and performs intra-group trajectory filtering on the reference travel trajectory of the similar travel trajectory group based on each distance difference using a distance difference threshold constraint index, to obtain the processed similar travel trajectory group, wherein the first reference location point and the second reference location point are different reference location points corresponding to the same reference location point type in different reference travel trajectories;

[0114] The reference position point distance constraint method is achieved by pre-setting several reference position point types, such as one or more of the following: starting point type, ending point type, 1 / 4 travel point type, 3 / 4 travel point type, etc. The specific reference position point type is set based on the actual application. Trajectories within a group of similar travel trajectories can be randomly combined. Then, the distance difference between different reference points of the same travel point type on each pair of different reference travel trajectories is calculated. The distance difference threshold constraint index is then used to match the distance difference, and the trajectory within the group is filtered out based on whether the match is found.

[0115] The distance difference threshold constraint index is a threshold or critical value defined for the distance difference. A default distance difference threshold constraint index can be set in advance.

[0116] Optionally, the default distance difference threshold constraint index can be relaxed to obtain a processed target parameter constraint index for this trajectory mining method.

[0117] Optionally, when there are multiple reference position point types, the distance difference can be the sum of the distance differences between any two position points indicated by all reference position point types on different reference travel trajectories. In this case, only one round of distance difference comparison is required.

[0118] Optionally, the distance difference can also be the distance difference between any two points indicated by each reference point type. In this case, the distance difference is compared with the distance difference threshold constraint index one by one. For example, if the distance difference is greater than the distance difference threshold constraint index, it is considered a mismatch. At the same time, trajectory filtering is performed in the current similar travel trajectory group.

[0119] To illustrate, a group of similar travel trajectories typically consists of the travel trajectory of a first vehicle and at least one corresponding similar travel trajectory. In this case, the distance difference calculation mentioned above can only consider the distance difference between the first vehicle's travel trajectory and any similar travel trajectory within the group. If there is a mismatch, the mismatched similar travel trajectories can be filtered out.

[0120] Furthermore, after matching, the matching status of this pair of reference travel trajectories can be labeled, indicating the "reference position point distance constraint method" mismatch type / match type. The purpose of labeling is to avoid the same calculation processing when other similar travel trajectory groups are processed in the future. That is, when processing the "reference position point distance constraint method", we can first check whether the labeling of the pair of reference travel trajectories is stored, so as to avoid the duplication of calculation processing and save computing resources.

[0121] In one feasible implementation, if the trajectory mining method is based on the ratio constraint between mileage difference and mileage mean, the electronic device performs one of the following steps:

[0122] 1. The electronic device acquires the maximum mileage difference and the average mileage of each similar travel trajectory group, determines the first mileage ratio between the maximum mileage difference and the average mileage, and if the first mileage ratio does not match the first ratio threshold constraint index, the similar travel trajectory group is filtered out; if the first mileage ratio matches the first ratio threshold constraint index, the similar travel trajectory group is retained.

[0123] The maximum mileage difference of the trajectory is obtained by traversing the mileage corresponding to all trajectories in the group, calculating the difference between the maximum mileage and the minimum mileage;

[0124] The average trajectory mileage is obtained by acquiring the mileage corresponding to each of the trajectories in the group, and then calculating the ratio of the sum of all mileages to the number of trajectories in the group.

[0125] The first mileage ratio can be understood as follows: assuming the maximum mileage difference of the trajectory is x and the average mileage of the trajectory is y, the ratio "x / y" is also the first mileage ratio.

[0126] The first ratio threshold constraint index is a threshold set for the first mileage ratio. The first ratio threshold constraint index is used to filter out similar travel trajectory groups that do not meet the index.

[0127] Optionally, the mismatch between the first mileage ratio and the first ratio threshold constraint index can be that the first mileage ratio is less than or greater than the first ratio threshold constraint index, which can be set based on the actual situation.

[0128] 2. The electronic device determines a second ratio threshold constraint index based on the first mileage ratio, obtains the trajectory mileage corresponding to each of the reference travel trajectories and determines a second mileage ratio between the trajectory mileage and the average trajectory mileage, and performs intra-group trajectory filtering processing on the similar travel trajectory group based on the second mileage ratio and the second ratio threshold constraint index to obtain the processed similar travel trajectory group;

[0129] The second ratio threshold constraint index is a threshold set based on the first mileage ratio. The second ratio threshold constraint index is used to filter out the intra-group reference trajectories of similar travel trajectory groups that do not meet the index.

[0130] In one or more embodiments of this specification, the second ratio threshold constraint index corresponding to the "ratio constraint method based on the mileage difference and the average mileage" is determined according to the first mileage ratio. For example, the first mileage ratio can be directly used as the default second ratio threshold constraint index.

[0131] Optionally, the first mileage ratio can be used as a parameter constraint index. The constraint precision of the parameter constraint index can be relaxed to obtain the processed target parameter constraint index for this trajectory mining method, which can also be used as the second parameter constraint index.

[0132] The second mileage ratio: Assuming a reference travel trajectory Si, calculate the ratio of the trajectory mileage S of the reference travel trajectory Si to the average trajectory mileage, thereby obtaining the second mileage ratio.

[0133] Indicatively, the process of filtering out reference travel trajectories within a group based on a ratio threshold constraint index using a second mileage ratio can be as follows: compare whether the second mileage ratio matches the second ratio threshold constraint index (e.g., whether the second mileage ratio is greater than or less than the ratio threshold constraint index). If they match, the trajectory is retained; if they do not match, the reference travel trajectories within the group corresponding to the mismatched second mileage ratio are filtered out.

[0134] 3. The electronic device acquires the maximum mileage difference and the average mileage of each of the similar travel trajectory groups, determines a first mileage ratio between the maximum mileage difference and the average mileage, and if the first mileage ratio does not match the first ratio threshold constraint index, performs trajectory group filtering on the similar travel trajectory group; if the first mileage ratio matches the first ratio threshold constraint index, the similar travel trajectory group is retained; and the electronic device determines a second ratio threshold constraint index based on the first mileage ratio, acquires the trajectory mileage corresponding to each of the reference travel trajectories and determines a second mileage ratio between the trajectory mileage and the average mileage, and performs intra-group trajectory filtering on the similar travel trajectory group based on the second mileage ratio and the second ratio threshold constraint index to obtain the processed similar travel trajectory group;

[0135] In one feasible implementation, if the first trajectory mining method is a variance constraint method based on mileage variance, the electronic device performs one of the following steps:

[0136] 1. The electronic device acquires the trajectory mileage variance corresponding to each of the similar travel trajectory groups. If the trajectory mileage variance does not match the variance threshold constraint index, the similar travel trajectory group is filtered out. If the trajectory mileage variance matches the variance threshold constraint index, the similar travel trajectory group is retained.

[0137] For illustration, assume that the mean trajectory mileage within a group of similar travel trajectories is M; the trajectory mileage corresponding to several reference travel trajectories within the group can be represented as X1, X2...Xn, where n is the number of travel trajectories in the group, and the variance of the trajectory mileage is denoted by S^2.

[0138] The calculation process for the variance of trajectory mileage is as follows: S^2=[(X1-M)^2+(X2-M)^2+…+(Xn-M)^2]╱n;

[0139] The variance threshold constraint index is a threshold set for the variance of trajectory mileage. This index is used to filter out similar travel trajectory groups that do not meet the index.

[0140] Optionally, the mismatch between the trajectory mileage variance and the variance threshold constraint index can be that the trajectory mileage variance is less than or greater than the variance threshold constraint index, which can be set based on the actual situation.

[0141] 2. The electronic device acquires the mean and variance of the trajectory mileage corresponding to the similar travel trajectory group, acquires the trajectory mileage corresponding to each of the reference travel trajectories and determines the square value of the trajectory mileage and the mean of the trajectory mileage, determines the mileage variance constraint index based on the trajectory mileage variance, and performs intra-group trajectory filtering processing on each of the reference travel trajectories based on the square value using the mileage variance constraint index to obtain the processed similar travel trajectory group.

[0142] For illustration, assume that the mean trajectory mileage within a group of similar travel trajectories is M; the trajectory mileage corresponding to several reference travel trajectories within the group can be represented as X1, X2...Xn, where n is the number of travel trajectories in the group, and the variance of the trajectory mileage is denoted by S^2.

[0143] The calculation process for the variance of trajectory mileage is as follows: S^2=[(X1-M)^2+(X2-M)^2+…+(Xn-M)^2]╱n;

[0144] The mileage variance constraint index is set based on the trajectory mileage variance and is used to filter out the intra-group reference trajectories of similar travel trajectory groups that do not meet the index.

[0145] This is an illustrative example of determining mileage variance constraint indicators based on trajectory mileage variance. For instance, trajectory mileage variance can be directly used as the default mileage variance constraint indicator.

[0146] Optionally, the default mileage variance constraint index can be relaxed to obtain a processed target parameter constraint index for this trajectory mining method.

[0147] Furthermore, for any reference travel trajectory Xi within the similar trajectory group, the trajectory mileage is calculated as the square of the mean of the trajectory mileage, i.e., (Xi-M)^2.

[0148] Indicatively, the process of filtering out reference travel trajectories within a group based on the squared value using a mileage variance constraint index can be as follows: compare whether the aforementioned squared value matches the mileage variance constraint index (e.g., whether the squared value is greater than or less than the mileage variance constraint index). If they match, the trajectory is retained; if they do not match, the reference travel trajectories within the group corresponding to the mismatched squared values ​​are filtered out.

[0149] 3. The electronic device acquires the trajectory mileage variance corresponding to each of the similar travel trajectory groups. If the trajectory mileage variance does not match the variance threshold constraint index, the similar travel trajectory group is filtered out. If the trajectory mileage variance matches the variance threshold constraint index, the similar travel trajectory group is retained. Furthermore, the electronic device acquires the trajectory mileage mean and trajectory mileage variance corresponding to the similar travel trajectory group, acquires the trajectory mileage corresponding to each of the reference travel trajectories, and determines the square of the trajectory mileage and the trajectory mileage mean. Based on the trajectory mileage variance, a mileage variance constraint index is determined. Based on the squared value, the mileage variance constraint index is used to perform intra-group trajectory filtering on each of the reference travel trajectories to obtain the processed similar travel trajectory group.

[0150] In one feasible implementation, during the process of constraining trajectory parameters for similar travel trajectory groups based on trajectory mining, the parameter constraint accuracy of the current round can be adjusted by adjusting the default parameter constraint index. That is, from the perspective of parameter constraint accuracy, the single-dimensional trajectory mining method can avoid reaching a local optimum during the trajectory mining process. Instead, multiple rounds of trajectory parameter constraint processing are adopted. Based on different trajectory parameter constraint methods, multiple rounds of trajectory mining processing are applied to similar travel trajectory groups. After multiple rounds of trajectory parameter constraint processing, the overall trajectory mining global optimum effect is achieved, improving the generalization ability of trajectory mining and maximizing the discovery of potential regular travel trajectories.

[0151] As an illustration, after determining the combination of trajectory mining methods, the electronic device can obtain the parameter constraint indicators corresponding to each trajectory mining method. For example, the default distance difference threshold constraint indicator in the "distance constraint method based on reference location point"; the default ratio threshold constraint indicator (i.e., the first mileage ratio) in the "ratio constraint method based on mileage difference and mileage mean"; and the default mileage variance constraint indicator (i.e., trajectory mileage variance) in the "variance constraint method based on mileage variance".

[0152] The electronic device can relax the constraint precision of the parameter constraint index to obtain the processed target parameter constraint index for the trajectory mining method. Then, based on each of the target parameter constraint indices, the trajectory mining method is used to perform multiple rounds of trajectory parameter constraint processing on the similar trajectory group / or the reference travel trajectory within the similar trajectory group to obtain the processed regular travel trajectory group.

[0153] It is understandable that the constraint precision of the target parameter constraint index is less than that of the original parameter constraint index.

[0154] Optionally, the constraint precision relaxation process can be achieved by setting a precision relaxation coefficient and fitting the parameter constraint index based on the precision relaxation coefficient. For example, the sum or difference between the precision relaxation coefficient and the parameter constraint index can be calculated to determine the new target parameter constraint index; the product of the precision relaxation coefficient and the reference constraint index can be calculated to determine the new target parameter constraint index; the product of the precision relaxation coefficient and the reference constraint index can be calculated as the fluctuation index value, and the sum of the fluctuation index value and the reference constraint index can be used to determine the new target parameter constraint index, and so on.

[0155] S208: Determine the target regular travel trajectory based on each of the aforementioned regular travel trajectory groups.

[0156] For details, please refer to the method steps in other embodiments of this specification, which will not be repeated here.

[0157] In one or more embodiments of this specification, the electronic device can perform trajectory point matching on multiple acquired vehicle travel trajectories to obtain at least one group of similar travel trajectories. Then, trajectory parameter constraint processing is applied to each reference travel trajectory within the similar travel trajectory group to obtain a processed group of regular travel trajectories. Finally, a target regular travel trajectory is determined based on each group of regular travel trajectories. This avoids the phenomenon of incomplete and low-accuracy regular trajectory discovery, accurately discovering potential regular trajectories to cover more regular trajectories and improving trajectory discovery accuracy. Furthermore, it is applicable to regular trajectory discovery with varying mileage lengths and route shapes. After multiple rounds of trajectory parameter constraint processing, a globally optimal overall trajectory discovery effect can be achieved, improving the generalization ability of trajectory discovery.

[0158] The following will combine Figure 3 This specification provides a detailed description of the trajectory processing device provided in the embodiments. It should be noted that... Figure 3 The trajectory processing device shown is used to execute this specification. Figures 1-2 The methods shown in the embodiments are illustrated for ease of explanation, showing only the parts related to the embodiments of this specification. For specific technical details not disclosed, please refer to this specification. Figures 1-2 The example shown.

[0159] Please see Figure 3 This diagram illustrates the structure of a trajectory processing device according to an embodiment of this specification. The trajectory processing device 1 can be implemented as all or part of a user terminal through software, hardware, or a combination of both. According to some embodiments, the trajectory processing device 1 includes a trajectory matching module 11, a parameter constraint module 12, and a trajectory determination module 13, specifically used for:

[0160] The trajectory matching module 11 is used to acquire multiple vehicle travel trajectories, perform trajectory point matching on each vehicle travel trajectory, and obtain at least one similar travel trajectory group, wherein the similar trajectory group includes multiple reference travel trajectories.

[0161] The parameter constraint module 12 is used to perform trajectory parameter constraint processing on each of the reference travel trajectories in the similar travel trajectory group to obtain the processed regular travel trajectory group.

[0162] The trajectory determination module 13 is used to determine the target regular travel trajectory based on the regular travel trajectory group.

[0163] Optional, such as Figure 4 As shown, the trajectory matching module 11 includes:

[0164] The trajectory matching unit 111 is used to perform trajectory point matching on the first vehicle travel trajectory and at least one second travel trajectory respectively to obtain at least one trajectory point matching degree. The first vehicle travel trajectory is any one of all the vehicle travel trajectories, and the second travel trajectory is the vehicle travel trajectory of all the vehicle travel trajectories except the first vehicle travel trajectory.

[0165] The trajectory filtering unit 112 is used to perform trajectory filtering on the at least one second travel trajectory based on the trajectory point matching degree, so as to obtain at least one similar travel trajectory corresponding to the first vehicle travel trajectory.

[0166] The similarity processing unit 113 is used to obtain a similar travel trajectory group corresponding to each first vehicle travel trajectory based on each first vehicle travel trajectory and each similar travel trajectory corresponding to the first vehicle travel trajectory. The similar travel trajectory group includes the first vehicle travel trajectory and each similar travel trajectory corresponding to the first vehicle travel trajectory.

[0167] Optional, such as Figure 5 As shown, the trajectory filtering unit 112 is used for:

[0168] The threshold acquisition subunit 1121 is used to acquire the trajectory point matching threshold.

[0169] The trajectory filtering subunit 1122 is used to filter out the second travel trajectories whose trajectory point matching degree is less than the trajectory point matching threshold from the at least one second travel trajectory, so as to obtain at least one similar travel trajectory corresponding to the filtered first vehicle travel trajectory.

[0170] Optional, parameter constraint module 12, used for:

[0171] Determine the trajectory mining method combination corresponding to the similar travel trajectory group, wherein the trajectory mining method combination includes multiple trajectory mining methods;

[0172] Each of the aforementioned trajectory mining methods is used to sequentially perform multiple rounds of trajectory parameter constraint processing on each of the similar travel trajectory groups to obtain the processed regular travel trajectory groups.

[0173] Optional, such as Figure 6 As shown, the parameter constraint module 12 includes:

[0174] The index processing unit 121 is used to obtain the parameter constraint index corresponding to each trajectory mining method, and to perform constraint precision relaxation processing on the parameter constraint index to obtain the processed target parameter constraint index for the trajectory mining method.

[0175] The parameter constraint unit 122 is used to perform multiple rounds of trajectory parameter constraint processing on each of the similar travel trajectory groups based on the target parameter constraint index and the trajectory mining method in sequence, so as to obtain the processed regular travel trajectory group.

[0176] Optionally, the parameter constraint module 12 is used for:

[0177] Each of the aforementioned trajectory mining methods is used to perform trajectory filtering on each group of similar travel trajectories to obtain processed regular travel trajectory groups; or,

[0178] The constraint processing order corresponding to each trajectory mining method is determined. Based on the constraint processing order, a first trajectory mining method is determined. The first trajectory mining method is used to perform trajectory filtering processing on each similar travel trajectory group to obtain at least one processed similar travel trajectory group. Based on the constraint processing order, the next second trajectory mining method corresponding to the first trajectory mining method is determined. The second trajectory mining method is used as the first trajectory mining method, and the step of using the first trajectory mining method to perform trajectory filtering processing on each similar travel trajectory group to obtain at least one processed similar travel trajectory group is executed. If it is determined based on the constraint processing order that there is no next second trajectory mining method corresponding to the first trajectory mining method, then at least one similar travel trajectory group is taken as a regular travel trajectory group.

[0179] Optionally, the trajectory mining method includes at least two of the following: distance constraint based on reference location points, ratio constraint based on mileage difference to mileage mean, and variance constraint based on mileage variance.

[0180] Optionally, the parameter constraint module 12 is used for:

[0181] If the trajectory mining method is a reference location point distance constraint method, then at least one reference location point type is determined for each similar travel trajectory group. Based on the reference location point type, the distance difference between the first reference location point and at least one second reference location point is calculated. Based on each distance difference, a distance difference threshold constraint index is used to perform intra-group trajectory filtering on the reference travel trajectories of the similar travel trajectory group to obtain the processed similar travel trajectory group. The first reference location point and the second reference location point are different reference location points corresponding to the same reference location point type in different reference travel trajectories.

[0182] If the trajectory mining method is based on the ratio constraint of mileage difference and average mileage, then the maximum mileage difference and average mileage of each similar travel trajectory group are obtained, and a first mileage ratio of the maximum mileage difference to the average mileage is determined. If the first mileage ratio does not match the first ratio threshold constraint index, the similar travel trajectory group is filtered out. If the first mileage ratio matches the first ratio threshold constraint index, the similar travel trajectory group is retained. And / or, a second ratio threshold constraint index is determined based on the first mileage ratio, the trajectory mileage corresponding to each reference travel trajectory is obtained, and a second mileage ratio of the trajectory mileage to the average mileage is determined. Based on the second mileage ratio, the second ratio threshold constraint index is used to perform intra-group trajectory filtering on the similar travel trajectory group to obtain the processed similar travel trajectory group.

[0183] If the trajectory mining method is a variance constraint method based on mileage variance, then the trajectory mileage variance corresponding to each similar travel trajectory group is obtained. If the trajectory mileage variance does not match the variance threshold constraint index, the similar travel trajectory group is filtered out. If the trajectory mileage variance matches the variance threshold constraint index, the similar travel trajectory group is retained. And / or, the mean trajectory mileage and trajectory mileage variance corresponding to the similar travel trajectory group are obtained, the trajectory mileage corresponding to each reference travel trajectory is obtained, and the square value of the trajectory mileage and the mean trajectory mileage is determined. The mileage variance constraint index is determined based on the trajectory mileage variance. Based on the square value, the mileage variance constraint index is used to perform intra-group trajectory filtering on each reference travel trajectory to obtain the processed similar travel trajectory group.

[0184] It should be noted that the trajectory processing device provided in the above embodiments is only illustrated by the division of the above functional modules when executing the trajectory processing method. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the trajectory processing device and the trajectory processing method embodiments provided in the above embodiments belong to the same concept, and the implementation process is detailed in the method embodiments, which will not be repeated here.

[0185] The example numbers in this specification are for descriptive purposes only and do not represent the superiority or inferiority of the examples.

[0186] In one or more embodiments of this specification, the electronic device can perform trajectory point matching on multiple acquired vehicle travel trajectories to obtain at least one group of similar travel trajectories. Then, trajectory parameter constraint processing is applied to each reference travel trajectory within the similar travel trajectory group to obtain a processed group of regular travel trajectories. Finally, a target regular travel trajectory is determined based on each group of regular travel trajectories. This avoids the phenomenon of incomplete and low-accuracy regular trajectory discovery, accurately discovering potential regular trajectories to cover more regular trajectories and improving trajectory discovery accuracy. Furthermore, it is applicable to regular trajectory discovery with varying mileage lengths and route shapes. After multiple rounds of trajectory parameter constraint processing, a globally optimal overall trajectory discovery effect can be achieved, improving the generalization ability of trajectory discovery.

[0187] This specification also provides a computer storage medium that can store multiple instructions adapted to be loaded and executed by a processor as described above. Figures 1-2 The trajectory processing method described in the illustrated embodiment can be found in the following documentation for its specific execution process. Figures 1-2 The specific details of the illustrated embodiments will not be elaborated here.

[0188] This specification also provides a computer program product that stores at least one instruction, said at least one instruction being loaded and executed by the processor as described above. Figures 1-2 The trajectory processing method described in the illustrated embodiment can be found in the following documentation for its specific execution process. Figures 1-2 The specific details of the illustrated embodiments will not be elaborated here.

[0189] Please refer to Figure 7 This diagram illustrates a structural block diagram of an electronic device provided in an exemplary embodiment of this specification. The electronic device in this specification may include one or more components such as a processor 110, a memory 120, an input device 130, an output device 140, and a bus 150. The processor 110, memory 120, input device 130, and output device 140 may be connected via the bus 150.

[0190] Processor 110 may include one or more processing cores. Processor 110 connects to various parts of the electronic device via various interfaces and lines, and performs various functions and processes data of electronic device 100 by running or executing instructions, programs, code sets, or instruction sets stored in memory 120, and by calling data stored in memory 120. Optionally, processor 110 may be implemented using at least one hardware form of digital signal processing (DSP), field-programmable gate array (FPGA), or programmable logic array (PLA). Processor 110 may integrate one or more of the following: central processing unit (CPU), graphics processing unit (GPU), and modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the displayed content; and the modem handles wireless communication. It is understood that the modem may also not be integrated into processor 110 and may be implemented separately using a communication chip.

[0191] The memory 120 may include random access memory (RAM) or read-only memory (ROM). Optionally, the memory 120 may include a non-transitory computer-readable storage medium. The memory 120 may be used to store instructions, programs, code, code sets, or instruction sets. The memory 120 may include a program storage area and a data storage area. The program storage area may store instructions for implementing an operating system, instructions for implementing at least one function (such as touch functionality, sound playback functionality, image playback functionality, etc.), instructions for implementing the various method embodiments described below, etc. The operating system may be the Android system, including systems deeply developed based on the Android system, the iOS system developed by Apple Inc., including systems deeply developed based on the iOS system, or other systems. The data storage area may also store data created by the electronic device during use, such as phonebook data, audio and video data, chat log data, etc.

[0192] See Figure 8As shown, the memory 120 can be divided into operating system space and user space. The operating system runs in the operating system space, while native and third-party applications run in the user space. To ensure that different third-party applications can achieve good running performance, the operating system allocates corresponding system resources for each application. However, different application scenarios within the same third-party application have different requirements for system resources. For example, in local resource loading scenarios, third-party applications have high requirements for disk read speed; in animation rendering scenarios, third-party applications have high requirements for GPU performance. Since the operating system and third-party applications are independent of each other, the operating system often cannot promptly perceive the current application scenario of a third-party application, resulting in the operating system's inability to adapt system resources accordingly to the specific application scenario of the third-party application.

[0193] In order for the operating system to distinguish the specific application scenarios of third-party applications, it is necessary to establish data communication between the third-party applications and the operating system. This would allow the operating system to obtain the current scenario information of the third-party applications at any time, and then perform targeted system resource adaptation based on the current scenario.

[0194] Taking the Android operating system as an example, the programs and data stored in memory 120 are as follows: Figure 9As shown, the memory 120 can store the Linux kernel layer 320, the system runtime library layer 340, the application framework layer 360, and the application layer 380. The Linux kernel layer 320, system runtime library layer 340, and application framework layer 360 belong to the operating system space, while the application layer 380 belongs to the user space. The Linux kernel layer 320 provides low-level drivers for various hardware components of the electronic device, such as display drivers, audio drivers, camera drivers, Bluetooth drivers, Wi-Fi drivers, and power management. The system runtime library layer 340 provides support for key features of the Android system through several C / C++ libraries. For example, the SQLite library provides database support, the OpenGL / ES library provides 3D graphics support, and the Webkit library provides browser kernel support. The system runtime library layer 340 also provides the Android runtime library, which mainly provides core libraries that allow developers to write Android applications using the Java language. The Application Framework Layer 360 provides various APIs that may be used when building applications. Developers can also use these APIs to build their own applications, such as activity management, window management, view management, notification management, content provider, package management, call management, resource management, and location management. At least one application runs in the Application Layer 380. These applications can be native applications that come with the operating system, such as contacts, SMS, clock, and camera apps; or third-party applications developed by third-party developers, such as games, instant messaging, and photo editing apps.

[0195] Taking the operating system as an example (iOS), the programs and data stored in memory 120 are as follows: Figure 9As shown, the iOS system includes: Core OS layer 420, Core Services layer 440, Media layer 460, and Cocoa Touch layer 480. Core OS layer 420 includes the operating system kernel, drivers, and low-level program frameworks. These low-level program frameworks provide hardware-level functionality for use by the program frameworks located in Core Services layer 440. Core Services layer 440 provides system services and / or program frameworks required by applications, such as Foundation framework, account framework, advertising framework, data storage framework, network connectivity framework, geolocation framework, motion framework, etc. Media layer 460 provides applications with audiovisual interfaces, such as interfaces related to graphics and images, audio technology, video technology, and AirPlay (wireless playback of audio and video transmission technologies). Cocoa Touch layer 480 provides various commonly used interface-related frameworks for application development and is responsible for user touch interaction on electronic devices. Examples include local notification services, remote push services, advertising frameworks, game tool frameworks, message user interface (UI) frameworks, UIKit frameworks, map frameworks, and so on.

[0196] exist Figure 10 The framework shown includes, but is not limited to, the base framework in the core service layer 440 and the UIKit framework in the touchable layer 480. The base framework provides many basic object classes and data types, offering the most basic system services to all applications, and is independent of the UI. The UIKit framework, on the other hand, provides a basic UI class library for creating touch-based user interfaces. iOS applications can use the UIKit framework to provide their UI, thus providing the application's infrastructure for building user interfaces, drawing, handling user interaction events, responding to gestures, and so on.

[0197] The methods and principles for implementing data communication between third-party applications and the operating system in the iOS system can be found in the Android system, and will not be repeated here.

[0198] The input device 130 is used to receive input instructions or data, and includes, but is not limited to, a keyboard, mouse, camera, microphone, or touch device. The output device 140 is used to output instructions or data, and includes, but is not limited to, a display device and a speaker. In one example, the input device 130 and the output device 140 can be combined into a touch screen, which is used to receive touch operations from the user using a finger, stylus, or any suitable object on or near it, and to display the user interface of various applications. The touch screen is usually located on the front panel of the electronic device. The touch screen can be designed as a full-screen, curved screen, or irregularly shaped screen. The touch screen can also be designed as a combination of a full-screen and a curved screen, or a combination of an irregularly shaped screen and a curved screen; this specification does not limit this aspect.

[0199] In addition, those skilled in the art will understand that the structure of the electronic device shown in the above figures does not constitute a limitation on the electronic device. The electronic device may include more or fewer components than shown, or combine certain components, or have different component arrangements. For example, the electronic device may also include radio frequency circuits, input units, sensors, audio circuits, wireless fidelity (WiFi) modules, power supplies, Bluetooth modules, etc., which will not be described in detail here.

[0200] In the embodiments of this specification, the executing entity for each step can be the electronic device described above. Optionally, the executing entity for each step can be the operating system of the electronic device. The operating system can be Android, iOS, or other operating systems; this specification does not limit this.

[0201] The electronic device described in this specification may also be equipped with a display device. This display device can be any device capable of displaying information, such as a cathode ray tube display (CR), a light-emitting diode display (LED), an electronic ink screen, a liquid crystal display (LCD), or a plasma display panel (PDP). Users can use the display device on the electronic device 101 to view displayed text, images, videos, and other information. The electronic device may be a smartphone, tablet computer, gaming device, AR (Augmented Reality) device, in-vehicle device, data storage device, audio playback device, video playback device, laptop, desktop computing device, or vehicle infotainment system. In some embodiments, the electronic device may also be a server.

[0202] exist Figure 7 In the illustrated electronic device, the processor 110 can be used to call the application program stored in the memory 120 and specifically perform the following operations:

[0203] Multiple vehicle travel trajectories are acquired, and trajectory point matching is performed on each of the vehicle travel trajectories to obtain at least one group of similar travel trajectories, wherein the group of similar trajectories includes multiple reference travel trajectories.

[0204] The reference travel trajectories within the similar travel trajectory group are subjected to trajectory parameter constraint processing to obtain the processed regular travel trajectory group;

[0205] The target regular travel trajectory is determined based on each of the aforementioned regular travel trajectory groups.

[0206] In one embodiment, the processor 110 performs the following steps when performing trajectory point matching on each of the vehicle's travel trajectories to obtain at least one group of similar travel trajectories:

[0207] The first vehicle travel trajectory is matched with at least one second travel trajectory to obtain at least one trajectory point matching degree. The first vehicle travel trajectory is any one of all the vehicle travel trajectories, and the second travel trajectory is the vehicle travel trajectory of all the vehicle travel trajectories except the first vehicle travel trajectory.

[0208] Based on the trajectory point matching degree, the at least one second travel trajectory is filtered out to obtain at least one similar travel trajectory corresponding to the first vehicle travel trajectory.

[0209] Based on each first vehicle travel trajectory and each similar travel trajectory corresponding to the first vehicle travel trajectory, a similar travel trajectory group corresponding to each first vehicle travel trajectory is obtained. The similar travel trajectory group includes the first vehicle travel trajectory and each similar travel trajectory corresponding to the first vehicle travel trajectory.

[0210] In one embodiment, the processor 110 performs the following steps when executing the trajectory filtering of at least one second travel trajectory based on the trajectory point matching degree to obtain at least one similar travel trajectory corresponding to the first vehicle travel trajectory:

[0211] Obtain the trajectory point matching threshold;

[0212] From the at least one second travel trajectory, the second travel trajectories whose trajectory point matching degree is less than the trajectory point matching threshold are filtered out to obtain at least one similar travel trajectory corresponding to the filtered first vehicle travel trajectory.

[0213] In one embodiment, the processor 110 performs trajectory parameter constraint processing on each of the reference travel trajectories within the similar travel trajectory group to obtain a processed regular travel trajectory group, including:

[0214] Determine a combination of trajectory mining methods for the group of similar travel trajectories, wherein the combination of trajectory mining methods includes multiple trajectory mining methods;

[0215] Each of the aforementioned trajectory mining methods is used to sequentially perform multiple rounds of trajectory parameter constraint processing on each of the similar travel trajectory groups to obtain the processed regular travel trajectory groups.

[0216] In one embodiment, the processor 110 performs the following steps to sequentially process each of the similar travel trajectory groups using the aforementioned trajectory mining methods to obtain processed regular travel trajectory groups:

[0217] Obtain the parameter constraint index corresponding to each trajectory mining method, and perform constraint precision relaxation processing on the parameter constraint index to obtain the processed target parameter constraint index for the trajectory mining method.

[0218] Based on the target parameter constraint indicators, the trajectory mining method is used to perform multiple rounds of trajectory parameter constraint processing on each of the similar travel trajectory groups to obtain the processed regular travel trajectory groups.

[0219] In one embodiment, the processor 110 performs multiple rounds of trajectory parameter constraint processing on each of the similar travel trajectory groups using the aforementioned trajectory mining methods to obtain a processed regular travel trajectory group, including:

[0220] Each of the aforementioned trajectory mining methods is used to perform trajectory filtering on each group of similar travel trajectories to obtain processed regular travel trajectory groups; or,

[0221] The constraint processing order corresponding to each trajectory mining method is determined. Based on the constraint processing order, a first trajectory mining method is determined. The first trajectory mining method is used to perform trajectory filtering processing on each similar travel trajectory group to obtain at least one processed similar travel trajectory group. Based on the constraint processing order, the next second trajectory mining method corresponding to the first trajectory mining method is determined. The second trajectory mining method is used as the first trajectory mining method, and the step of using the first trajectory mining method to perform trajectory filtering processing on each similar travel trajectory group to obtain at least one processed similar travel trajectory group is executed. If it is determined based on the constraint processing order that there is no next second trajectory mining method corresponding to the first trajectory mining method, then at least one similar travel trajectory group is taken as a regular travel trajectory group.

[0222] In one embodiment, the trajectory mining method includes at least two of the following: a distance constraint method based on a reference location point, a ratio constraint method based on the mileage difference to the mileage mean, and a variance constraint method based on the mileage variance.

[0223] In one embodiment, when the processor 110 executes the trajectory processing method, it specifically performs the following steps:

[0224] If the trajectory mining method is a reference location point distance constraint method, then at least one reference location point type is determined for each similar travel trajectory group. Based on the reference location point type, the distance difference between the first reference location point and at least one second reference location point is calculated. Based on each distance difference, a distance difference threshold constraint index is used to perform intra-group trajectory filtering on the reference travel trajectories of the similar travel trajectory group to obtain the processed similar travel trajectory group. The first reference location point and the second reference location point are different reference location points corresponding to the same reference location point type in different reference travel trajectories.

[0225] If the trajectory mining method is based on the ratio constraint of mileage difference and average mileage, then the maximum mileage difference and average mileage of each similar travel trajectory group are obtained, and a first mileage ratio of the maximum mileage difference to the average mileage is determined. If the first mileage ratio does not match the first ratio threshold constraint index, the similar travel trajectory group is filtered out. If the first mileage ratio matches the first ratio threshold constraint index, the similar travel trajectory group is retained. And / or, a second ratio threshold constraint index is determined based on the first mileage ratio, the trajectory mileage corresponding to each reference travel trajectory is obtained, and a second mileage ratio of the trajectory mileage to the average mileage is determined. Based on the second mileage ratio, the second ratio threshold constraint index is used to perform intra-group trajectory filtering on the similar travel trajectory group to obtain the processed similar travel trajectory group.

[0226] If the trajectory mining method is a variance constraint method based on mileage variance, then the trajectory mileage variance corresponding to each similar travel trajectory group is obtained. If the trajectory mileage variance does not match the variance threshold constraint index, the similar travel trajectory group is filtered out. If the trajectory mileage variance matches the variance threshold constraint index, the similar travel trajectory group is retained. And / or, the mean trajectory mileage and trajectory mileage variance corresponding to the similar travel trajectory group are obtained, the trajectory mileage corresponding to each reference travel trajectory is obtained, and the square value of the trajectory mileage and the mean trajectory mileage is determined. The mileage variance constraint index is determined based on the trajectory mileage variance. Based on the square value, the mileage variance constraint index is used to perform intra-group trajectory filtering on each reference travel trajectory to obtain the processed similar travel trajectory group.

[0227] In one or more embodiments of this specification, the electronic device can perform trajectory point matching on multiple acquired vehicle travel trajectories to obtain at least one group of similar travel trajectories. Then, trajectory parameter constraint processing is applied to each reference travel trajectory within the similar travel trajectory group to obtain a processed group of regular travel trajectories. Finally, a target regular travel trajectory is determined based on each group of regular travel trajectories. This avoids the phenomenon of incomplete and low-accuracy regular trajectory discovery, accurately discovering potential regular trajectories to cover more regular trajectories and improving trajectory discovery accuracy. Furthermore, it is applicable to regular trajectory discovery with varying mileage lengths and route shapes. After multiple rounds of trajectory parameter constraint processing, a globally optimal overall trajectory discovery effect can be achieved, improving the generalization ability of trajectory discovery.

[0228] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory, or random access memory, etc.

[0229] The above-disclosed embodiments are merely preferred embodiments of this specification and should not be construed as limiting the scope of this specification. Therefore, any equivalent variations made in accordance with the claims of this specification shall still fall within the scope of this specification.

Claims

1. A trajectory processing method, characterized in that, The method includes: Multiple vehicle travel trajectories are acquired, and trajectory point matching is performed on each of the vehicle travel trajectories to obtain at least one group of similar travel trajectories, wherein the group of similar trajectories includes multiple reference travel trajectories. The reference travel trajectories within the similar travel trajectory group are subjected to trajectory parameter constraint processing to obtain the processed regular travel trajectory group; The target regular travel trajectory is determined based on each of the aforementioned regular travel trajectory groups; The step of performing trajectory parameter constraint processing on each reference trajectory within the similar trajectory group to obtain the processed regular trajectory group includes: The combination of trajectory mining methods corresponding to the similar travel trajectory group is determined. The combination of trajectory mining methods includes multiple trajectory mining methods. Specifically, the combination of trajectory mining methods is selected based on the intra-group parameters of the similar travel trajectory group. The intra-group parameters include fitting one or more of the following: intra-group average mileage, intra-group number of trajectories, and maximum mileage difference. The trajectory mining methods include at least two of the following: distance constraint method based on reference location point, ratio constraint method based on mileage difference to mileage mean, and variance constraint method based on mileage variance. Each of the aforementioned trajectory mining methods is used to sequentially perform multiple rounds of trajectory parameter constraint processing on each of the similar travel trajectory groups to obtain the processed regular travel trajectory groups.

2. The method according to claim 1, characterized in that, The step of matching trajectory points for each of the vehicle's travel trajectories to obtain at least one group of similar travel trajectories includes: The first vehicle travel trajectory is matched with at least one second travel trajectory to obtain at least one trajectory point matching degree. The first vehicle travel trajectory is any one of all the vehicle travel trajectories, and the second travel trajectory is the vehicle travel trajectory of all the vehicle travel trajectories except the first vehicle travel trajectory. Based on the trajectory point matching degree, the second travel trajectory is filtered out to obtain at least one similar travel trajectory corresponding to the first vehicle travel trajectory. Based on each first vehicle travel trajectory and each similar travel trajectory corresponding to the first vehicle travel trajectory, a similar travel trajectory group corresponding to each first vehicle travel trajectory is obtained. The similar travel trajectory group includes the first vehicle travel trajectory and each similar travel trajectory corresponding to the first vehicle travel trajectory.

3. The method according to claim 2, characterized in that, The step of filtering out at least one second travel trajectory based on the trajectory point matching degree to obtain at least one similar travel trajectory corresponding to the first vehicle travel trajectory includes: Obtain the trajectory point matching threshold; From the second travel trajectory, the second travel trajectories whose trajectory point matching degree is less than the trajectory point matching threshold are filtered out to obtain the filtered similar travel trajectories.

4. The method according to claim 1, characterized in that, The process involves sequentially applying multiple rounds of trajectory parameter constraint processing to each of the aforementioned trajectory mining methods to obtain a processed regular travel trajectory group, including: Obtain the parameter constraint index corresponding to each trajectory mining method, and perform constraint precision relaxation processing on the parameter constraint index to obtain the processed target parameter constraint index for the trajectory mining method. Based on the target parameter constraint indicators, the trajectory mining method is used to perform multiple rounds of trajectory parameter constraint processing on each of the similar travel trajectory groups to obtain the processed regular travel trajectory groups.

5. The method according to claim 1, characterized in that, The process involves sequentially applying multiple rounds of trajectory parameter constraint processing to each of the aforementioned trajectory mining methods to obtain a processed regular travel trajectory group, including: Each of the aforementioned trajectory mining methods is used to perform trajectory filtering on each group of similar travel trajectories to obtain processed regular travel trajectory groups; or, The constraint processing order corresponding to each trajectory mining method is determined. Based on the constraint processing order, a first trajectory mining method is determined. The first trajectory mining method is used to perform trajectory filtering processing on each similar travel trajectory group to obtain at least one processed similar travel trajectory group. Based on the constraint processing order, the next second trajectory mining method corresponding to the first trajectory mining method is determined. The second trajectory mining method is used as the first trajectory mining method, and the step of using the first trajectory mining method to perform trajectory filtering processing on each similar travel trajectory group to obtain at least one processed similar travel trajectory group is executed. If it is determined based on the constraint processing order that there is no next second trajectory mining method corresponding to the first trajectory mining method, then at least one similar travel trajectory group is taken as a regular travel trajectory group.

6. The method according to claim 4 or 5, characterized in that, The method further includes: If the trajectory mining method is a reference location point distance constraint method, then at least one reference location point type is determined for each similar travel trajectory group. Based on the reference location point type, the distance difference between the first reference location point and at least one second reference location point is calculated. Based on each distance difference, a distance difference threshold constraint index is used to perform intra-group trajectory filtering on the reference travel trajectories of the similar travel trajectory group to obtain the processed similar travel trajectory group. The first reference location point and the second reference location point are different reference location points corresponding to the same reference location point type in different reference travel trajectories. If the trajectory mining method is based on the ratio constraint of mileage difference and average mileage, then the maximum mileage difference and average mileage of each similar travel trajectory group are obtained, and a first mileage ratio of the maximum mileage difference to the average mileage is determined. If the first mileage ratio does not match the first ratio threshold constraint index, the similar travel trajectory group is filtered out. If the first mileage ratio matches the first ratio threshold constraint index, the similar travel trajectory group is retained. And / or, a second ratio threshold constraint index is determined based on the first mileage ratio, the trajectory mileage corresponding to each reference travel trajectory is obtained, and a second mileage ratio of the trajectory mileage to the average mileage is determined. Based on the second mileage ratio, the second ratio threshold constraint index is used to perform intra-group trajectory filtering on the similar travel trajectory group to obtain the processed similar travel trajectory group. If the trajectory mining method is a variance constraint method based on mileage variance, then the trajectory mileage variance corresponding to each similar travel trajectory group is obtained. If the trajectory mileage variance does not match the variance threshold constraint index, the similar travel trajectory group is filtered out. If the trajectory mileage variance matches the variance threshold constraint index, the similar travel trajectory group is retained. And / or, the mean trajectory mileage and trajectory mileage variance corresponding to the similar travel trajectory group are obtained, the trajectory mileage corresponding to each reference travel trajectory is obtained, and the square value of the trajectory mileage and the mean trajectory mileage is determined. The mileage variance constraint index is determined based on the trajectory mileage variance. Based on the square value, the mileage variance constraint index is used to perform intra-group trajectory filtering on each reference travel trajectory to obtain the processed similar travel trajectory group.

7. A regular trajectory processing device, characterized in that, The device includes: The trajectory matching module is used to acquire multiple vehicle travel trajectories, perform trajectory point matching on each vehicle travel trajectory, and obtain at least one similar travel trajectory group, wherein the similar trajectory group includes multiple reference travel trajectories. The parameter constraint module is used to perform trajectory parameter constraint processing on each of the reference travel trajectories in the similar travel trajectory group to obtain the processed regular travel trajectory group. The trajectory determination module is used to determine the target regular travel trajectory based on the group of regular travel trajectories. The parameter constraint module is used for: The combination of trajectory mining methods corresponding to the similar travel trajectory group is determined. The combination of trajectory mining methods includes multiple trajectory mining methods. Specifically, the combination of trajectory mining methods is selected based on the intra-group parameters of the similar travel trajectory group. The intra-group parameters include fitting one or more of the following: intra-group average mileage, intra-group number of trajectories, and maximum mileage difference. The trajectory mining methods include at least two of the following: distance constraint method based on reference location point, ratio constraint method based on mileage difference to mileage mean, and variance constraint method based on mileage variance. Each of the aforementioned trajectory mining methods is used to sequentially perform multiple rounds of trajectory parameter constraint processing on each of the similar travel trajectory groups to obtain the processed regular travel trajectory groups.

8. An electronic device, the electronic device comprising: A processor and a memory; wherein the memory stores a computer program adapted to be loaded by the processor and executed the method steps as claimed in any one of claims 1 to 6.

Images