Trajectory data processing method and device, electronic equipment and computer readable medium
By dividing the spatial grid and establishing a spatiotemporal probability model in trajectory data processing, the problems of low trajectory point sampling rate and position information noise are solved, thereby improving the accuracy of trajectory spatiotemporal collision detection.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- YIDU CLOUD (BEIJING) TECH CO LTD
- Filing Date
- 2022-09-06
- Publication Date
- 2026-07-31
AI Technical Summary
In existing technologies, the low sampling rate of trajectory points and the presence of noise in the location information reduce the accuracy of trajectory spatiotemporal collision detection.
By acquiring the trajectory data of the target object, dividing the two-dimensional space into multiple spatial grids, calculating the positioning error between the trajectory points and the grids, and determining the position transfer probability based on the trajectory data, a spatiotemporal probability model is established to detect the trajectory collision probability.
It improves the accuracy of trajectory spatiotemporal collision detection, can effectively calculate trajectory collision probability under the influence of noise, and supports collision detection at any time and location.
Smart Images
Figure CN117708249B_ABST
Abstract
Description
Technical Field
[0001] This disclosure relates to the field of data processing technology, and more specifically, to a method for processing trajectory data, a device for processing trajectory data, an electronic device, and a computer-readable medium. Background Technology
[0002] Currently, most trajectory spatiotemporal collision detection methods suffer from low trajectory point sampling rates and noise in the collected location information, leading to reduced accuracy in trajectory spatiotemporal collision detection.
[0003] Therefore, there is an urgent need in this field for a trajectory data processing method that can solve the problems of low trajectory point sampling rate and noise in position information, and improve the accuracy of trajectory spatiotemporal collision detection.
[0004] It should be noted that the information disclosed in the background section above is only used to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention
[0005] The purpose of this disclosure is to provide a method for processing trajectory data, a device for processing trajectory data, an electronic device, and a computer-readable medium, thereby at least to some extent solving the problems of low trajectory point sampling rate and noise in position information, and improving the accuracy of trajectory spatiotemporal collision detection.
[0006] According to a first aspect of this disclosure, a method for processing trajectory data is provided, comprising:
[0007] Obtain trajectory text related to the activity trajectory of the target object, and obtain trajectory data of the target object based on the trajectory text, wherein the trajectory data contains the position information of the trajectory points of the target object at each sampling time point;
[0008] The two-dimensional space is divided into multiple spatial grids, and the positioning error between each spatial grid and each trajectory point is obtained based on the position information of each trajectory point of the target object and the grid position information corresponding to each spatial grid.
[0009] The probability of the target object's position shift between every two adjacent sampling time points is determined based on the target object's trajectory data;
[0010] Based on the positioning error between each of the spatial grids and each of the trajectory points, and the position transfer probability of the target object between every two adjacent sampling time points, a spatiotemporal probability model corresponding to the target object is determined. The spatiotemporal probability model is used to determine the trajectory collision probability between different target objects.
[0011] In one exemplary embodiment of this disclosure, the method further includes:
[0012] Determine the spatiotemporal probability models for objects other than the target object;
[0013] Based on the spatiotemporal probability model corresponding to the target object and the spatiotemporal probability models corresponding to the other objects, the trajectory collision probability between the target object and the other objects at the target time is determined.
[0014] In an exemplary embodiment of this disclosure, obtaining the positioning error between each spatial grid and each trajectory point based on the position information of each trajectory point of the target object and the grid position information corresponding to each spatial grid includes:
[0015] Based on the position information of each trajectory point of the target object and the grid position information corresponding to each spatial grid, the distance error between each spatial grid and each trajectory point is obtained;
[0016] Based on the preset probability distribution function, the distance error between each spatial grid and each trajectory point, and the prior position noise, the positioning error between each spatial grid and each trajectory point is obtained.
[0017] In one exemplary embodiment of this disclosure, determining the position transition probability of the target object between every two adjacent sampling time points based on the trajectory data of the target object includes:
[0018] The average moving speed of the target object between every two adjacent sampling time points is obtained based on the trajectory data of the target object, and the moving speed array corresponding to the target object is obtained based on the average moving speed of the target object between every two adjacent sampling time points.
[0019] The corresponding bandwidth is obtained based on the moving speed array corresponding to the target object, and the position transfer probability of the target object between every two adjacent sampling time points is determined based on the preset kernel density function, the moving speed array, and the bandwidth.
[0020] In one exemplary embodiment of this disclosure, obtaining the average moving speed of the target object between every two adjacent sampling time points based on the trajectory data of the target object includes:
[0021] The distance the target object moves between every two adjacent sampling time points is obtained based on the trajectory data of the target object;
[0022] The average moving speed of the target object between each two adjacent sampling time points is obtained based on the moving distance of the target object between each two adjacent sampling time points and the interval time between each two adjacent sampling time points.
[0023] In one exemplary embodiment of this disclosure, obtaining the corresponding bandwidth based on the movement speed array corresponding to the target object includes:
[0024] Determine the speed standard deviation of the target object based on the movement speed array corresponding to the target object;
[0025] The bandwidth is obtained based on the speed standard deviation of the target object and the number of sample points in the movement speed array.
[0026] In one exemplary embodiment of this disclosure, obtaining the trajectory data of the target object based on the trajectory text includes:
[0027] The trajectory text is subjected to trajectory field recognition and extraction, and the trajectory field is subjected to structured processing to obtain the location names in the trajectory text and the sampling time points corresponding to each location name;
[0028] The location names in the trajectory text are normalized to obtain the trajectory points of the target object, and the location information corresponding to each trajectory point is obtained.
[0029] The trajectory data of the target object is obtained based on the location information corresponding to each trajectory point and the sampling time point corresponding to each trajectory point.
[0030] According to a second aspect of this disclosure, a trajectory data processing apparatus is provided, comprising:
[0031] The trajectory data acquisition module is used to acquire trajectory text related to the activity trajectory of the target object, and obtain the trajectory data of the target object based on the trajectory text, wherein the trajectory data includes the position information of the trajectory points of the target object at each sampling time point;
[0032] The positioning error determination module is used to divide the two-dimensional space into multiple spatial grids, and obtain the positioning error between each spatial grid and each trajectory point based on the position information of each trajectory point of the target object and the grid position information corresponding to each spatial grid.
[0033] The transition probability determination module is used to determine the position transition probability of the target object between every two adjacent sampling time points based on the trajectory data of the target object;
[0034] The probability model determination module is used to determine the spatiotemporal probability model corresponding to the target object based on the positioning error between each of the spatial grids and each of the trajectory points, and the position transfer probability of the target object between every two adjacent sampling time points. The spatiotemporal probability model is used to determine the trajectory collision probability between different target objects.
[0035] According to a third aspect of this disclosure, an electronic device is provided, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to perform a method for processing trajectory data as described in any of the preceding claims by executing the executable instructions.
[0036] According to a fourth aspect of this disclosure, a computer-readable medium is provided having a computer program stored thereon, which, when executed by a processor, implements the method for processing trajectory data as described in any of the preceding claims.
[0037] The exemplary embodiments disclosed herein can have the following beneficial effects:
[0038] In the trajectory data processing method of the exemplary embodiments of this disclosure, trajectory data of a target object is acquired. Then, based on the position information of each trajectory point and the grid position information corresponding to each spatial grid, the positioning error between each spatial grid and each trajectory point is obtained. The position transfer probability of the target object between every two adjacent sampling time points is determined based on the trajectory data of the target object. Finally, based on the positioning error between each spatial grid and each trajectory point, and the position transfer probability of the target object between every two adjacent sampling time points, the spatiotemporal probability model corresponding to the target object is determined. The trajectory data processing method in the exemplary embodiments of this disclosure can obtain a spatiotemporal probability model of the target object under the influence of noise based on the positioning error between trajectory points and spatial grids, and the position transfer probability of the target object between two sampling time points. This spatiotemporal probability model can be used for trajectory spatiotemporal collision detection between different objects, supports trajectory collision probability calculation at any time and any location, and can solve the problems of low trajectory point sampling rate and noise in the collected position information, thereby improving the accuracy of trajectory spatiotemporal collision detection.
[0039] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description
[0040] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure. It is obvious that the drawings described below are merely some embodiments of this disclosure, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.
[0041] Figure 1 A flowchart illustrating a trajectory data processing method according to an exemplary embodiment of this disclosure is shown.
[0042] Figure 2 A schematic diagram of the trajectory data extraction process according to an exemplary embodiment of this disclosure is shown;
[0043] Figure 3 A flowchart illustrating the determination of the positioning error between each spatial grid and each trajectory point in an exemplary embodiment of this disclosure is shown.
[0044] Figure 4 A flowchart illustrating the determination of the position transition probability of a target object between every two adjacent sampling time points is shown in an exemplary embodiment of this disclosure.
[0045] Figure 5 A block diagram of a trajectory data processing apparatus according to an exemplary embodiment of the present disclosure is shown;
[0046] Figure 6 A schematic diagram of the structure of a computer system suitable for implementing the embodiments of the present disclosure is shown. Detailed Implementation
[0047] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided to make this disclosure more comprehensive and complete, and to fully convey the concept of the example embodiments to those skilled in the art. The described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a full understanding of embodiments of this disclosure. However, those skilled in the art will recognize that the technical solutions of this disclosure can be practiced with one or more of the specific details omitted, or other methods, components, apparatus, steps, etc., can be employed. In other instances, well-known technical solutions are not shown or described in detail to avoid obscuring various aspects of this disclosure.
[0048] Furthermore, the accompanying drawings are merely illustrative of this disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.
[0049] Trajectory data of a target object is generally represented as a sequence of location and collection time, which is important information in epidemiological investigations. If geospatial data is gridded, when two paths are in the same grid at the same time, they can be considered to have a co-location. The degree of co-location can measure the overlap between two trajectories in time and space, and this process can be achieved through trajectory spatiotemporal collision.
[0050] In some related embodiments, spatiotemporal collision detection between different objects can be performed by collecting the position information corresponding to the trajectory points of the target object. However, in most scenarios, spatiotemporal collision detection suffers from the following problems:
[0051] 1. Location information collection is subject to significant noise: Due to limitations in collection methods and accuracy, location information collection often involves considerable noise, making direct comparison of the distance between trajectory points ineffective.
[0052] 2. Low trajectory point sampling rate: Because the position points in the trajectory are sampled intermittently from the path walked by the target object, the collection of trajectory points is intermittent, and neither time nor position is continuous. Furthermore, the sampling frequency varies for different objects. Therefore, directly comparing the positions in the trajectory for spatiotemporal collision is severely affected by intermittent sampling. Even worse, the trajectory sampling frequency may be very low in some scenarios, resulting in no corresponding co-location being found during direct collision.
[0053] This example implementation first provides a method for processing trajectory data. (See reference...) Figure 1 As shown, the method for processing the above trajectory data may include the following steps:
[0054] Step S110. Obtain trajectory text related to the activity trajectory of the target object, and obtain trajectory data of the target object based on the trajectory text. The trajectory data contains the location information of the trajectory points of the target object at each sampling time point.
[0055] Step S120. Divide the two-dimensional space into multiple spatial grids, and obtain the positioning error between each spatial grid and each trajectory point based on the position information of each trajectory point of the target object and the grid position information corresponding to each spatial grid.
[0056] Step S130. Determine the position transition probability of the target object between every two adjacent sampling time points based on the trajectory data of the target object.
[0057] Step S140. Based on the positioning error between each spatial grid and each trajectory point, and the position transfer probability of the target object between every two adjacent sampling time points, determine the spatiotemporal probability model corresponding to the target object.
[0058] Among them, the spatiotemporal probability model can be used to determine the probability of trajectory collision between different target objects.
[0059] In the trajectory data processing method of the exemplary embodiments of this disclosure, trajectory data of a target object is acquired. Then, based on the position information of each trajectory point and the grid position information corresponding to each spatial grid, the positioning error between each spatial grid and each trajectory point is obtained. The position transfer probability of the target object between every two adjacent sampling time points is determined based on the trajectory data of the target object. Finally, based on the positioning error between each spatial grid and each trajectory point, and the position transfer probability of the target object between every two adjacent sampling time points, the spatiotemporal probability model corresponding to the target object is determined. The trajectory data processing method in the exemplary embodiments of this disclosure can obtain a spatiotemporal probability model of the target object under the influence of noise based on the positioning error between trajectory points and spatial grids, and the position transfer probability of the target object between two sampling time points. This spatiotemporal probability model can be used for trajectory spatiotemporal collision detection between different target objects, supports trajectory collision probability calculation at any time and any location, and can solve the problems of low trajectory point sampling rate and noise in the collected position information, thereby improving the accuracy of trajectory spatiotemporal collision detection.
[0060] Below, in conjunction with Figures 2 to 4 The steps described above in this example implementation will be explained in more detail.
[0061] In step S110, trajectory text related to the activity trajectory of the target object is obtained, and trajectory data of the target object is obtained based on the trajectory text. The trajectory data includes the position information of the trajectory points of the target object at each sampling time point.
[0062] In this example implementation, a trajectory text obtained from the investigation report could be, for example: "On May 14th at 13:37, I walked to ××× cake shop to buy a cake; around 14:20, I walked to ××× supermarket to select items; at 15:10, I left the supermarket and went home; I took the elevator upstairs, stating that there were no other passengers, and I did not go out again after returning home."
[0063] After obtaining the trajectory text related to the activity trajectory of the target object, the trajectory text can be processed accordingly to obtain the trajectory data of the target object. The trajectory data contains the location information of the trajectory points corresponding to the target object at each sampling time point.
[0064] In this example implementation, such as Figure 2 As shown, obtaining the trajectory data of a target object from trajectory text can specifically include the following steps:
[0065] Step S210. Identify and extract the trajectory fields from the trajectory text, and perform structured processing on the trajectory fields to obtain the location names in the trajectory text, as well as the sampling time points corresponding to each location name.
[0066] First, the trajectory fields in the trajectory text are identified and extracted, including the location or venue name, as well as the date and time. Then, the extracted trajectory fields are structured to obtain the location names in the trajectory text and the sampling time points corresponding to each location name.
[0067] Step S220. Normalize the location names in the trajectory text to obtain the trajectory points of the target object, and obtain the location information corresponding to each trajectory point.
[0068] The location names in the trajectory text are normalized to obtain multiple trajectory points of the target object. Then, after processing such as converting latitude and longitude, the location information corresponding to each trajectory point, i.e., latitude and longitude coordinates, is obtained.
[0069] Step S230. Obtain the trajectory data of the target object based on the location information corresponding to each trajectory point and the sampling time point corresponding to each trajectory point.
[0070] A trajectory data T can be represented as:
[0071] T={(l1,t1),(l2,t2),(l3,t3),…,(l n ,t n )}
[0072] Taking the above trajectory text as an example, the converted trajectory data is as follows:
[0073] T = {(l1,t1),(l2,t2),(l3,t3)}, where t1 = 2022-05-14 13:37:00, l1 = 116.423994, 39.922604 (××× Cake Shop); t2 = 2022-05-14 14:20:00, l2 = 116.451301, 39.912873 (××× Supermarket), etc.
[0074] The trajectory data of the target object obtained through the above steps can be used in the subsequent model calculation process.
[0075] In step S120, the two-dimensional space is divided into multiple spatial grids, and the positioning error between each spatial grid and each trajectory point is obtained based on the position information of each trajectory point of the target object and the grid position information corresponding to each spatial grid.
[0076] In this example implementation, the two-dimensional space can be divided into n spatial grids, represented as follows:
[0077] R = {r1, r2, r3, ..., r} n}
[0078] After dividing the space into grids, the positioning error between each spatial grid and each trajectory point of the target object can be calculated based on the positional relationship between each spatial grid and each trajectory point.
[0079] In this example implementation, such as Figure 3 As shown, based on the position information of each trajectory point of the target object and the corresponding grid position information of each spatial grid, the positioning error between each spatial grid and each trajectory point is obtained. This can specifically include the following steps:
[0080] Step S310. Based on the position information of each trajectory point of the target object and the position information of each spatial grid, obtain the distance error between each spatial grid and each trajectory point.
[0081] Spatial grid r and trajectory point l i Distance error between dis(r,l) i The calculation formula for ) is as follows:
[0082]
[0083] Where r(x1,x2), l i (y1, y2) represent the spatial grid r and the trajectory point l, respectively. i The corresponding latitude and longitude coordinates.
[0084] Step S320. Based on the preset probability distribution function, the distance error between each spatial grid and each trajectory point, and the prior position noise, obtain the positioning error between each spatial grid and each trajectory point.
[0085] In this example implementation, the positioning error between each spatial grid and each trajectory point can be calculated using a probability density function based on a Gaussian distribution.
[0086] The probability density function based on the Gaussian distribution indicates that the random variable x follows a probability distribution with location parameter μ and scale parameter σ, as shown in the following formula:
[0087]
[0088] Assume the trajectory point l of the target object i If the probability of being in spatial grid r follows the above Gaussian distribution, then σ can be extended to the prior parameter position noise, and the above formula can be updated to:
[0089]
[0090] Combining the distance error dis(r,l) between the spatial grid and each trajectory point i By using this method, the positioning error between the spatial grid and each trajectory point can be obtained.
[0091] In step S130, the position transfer probability of the target object between every two adjacent sampling time points is determined based on the trajectory data of the target object.
[0092] In this example implementation, the location transition probability P((l) i+1 ,t i+1 )|(l i ,t i )) refers to the target object from time t i to t i+1 The position is from l i Transfer to l i+1 The probability of a location shift. Generally, the probability of a location shift can be calculated by counting based on a large amount of historical data.
[0093] In this example implementation, since there is no large amount of historical data to support it, the transfer probability can be calculated using the speed information of the target object. Each trajectory generates its own speed probability distribution and fully considers the changes in speed during the movement.
[0094] In this example implementation, such as Figure 4 As shown, determining the probability of a target object's position transition between every two adjacent sampling time points based on the target object's trajectory data can specifically include the following steps:
[0095] Step S410. Obtain the average moving speed of the target object between every two adjacent sampling time points based on the trajectory data of the target object, and obtain the moving speed array corresponding to the target object based on the average moving speed of the target object between every two adjacent sampling time points.
[0096] In this example implementation, the moving distance of the target object between every two adjacent sampling time points can be obtained based on the trajectory data of the target object. Then, based on the moving distance of the target object between every two adjacent sampling time points and the interval time between every two adjacent sampling time points, the average moving speed of the target object between every two adjacent sampling time points can be obtained, that is:
[0097]
[0098] Then, a velocity array S can be generated based on the average moving velocity of the target object between every two adjacent sampling time points:
[0099] S={v 1, v2,v3,…,v n}
[0100] Step S420. Obtain the corresponding bandwidth based on the moving speed array corresponding to the target object, and determine the position transition probability of the target object between every two adjacent sampling time points based on the preset kernel density function, the moving speed array, and the bandwidth.
[0101] In this example implementation, the velocity probability distribution of the trajectory can be estimated using the kernel density estimation method. The kernel density function is as follows:
[0102]
[0103] Where S is the velocity array, K(·) is the kernel function (non-negative, integral of 1, conforming to probability density properties, and with a mean of 0), and a Gaussian kernel function can be used. h>0 is a smoothing parameter called bandwidth, and n is the number of sample points in the velocity array.
[0104] In this example implementation, the speed standard deviation of the target object can be determined based on the movement speed array corresponding to the target object, and then the corresponding bandwidth can be obtained based on the speed standard deviation of the target object and the number of sample points in the movement speed array. The optimal value of bandwidth h is as follows:
[0105]
[0106] in, The speed standard deviation can be calculated from the moving speed array.
[0107] Then, the position transition probability can be obtained through the kernel density function and bandwidth h. The formula for calculating the position transition probability is as follows:
[0108]
[0109] In step S140, the spatiotemporal probability model corresponding to the target object is determined based on the positioning error between each spatial grid and each trajectory point, and the position transfer probability of the target object between every two adjacent sampling time points.
[0110] In this example implementation, based on the positioning error between each spatial grid and each trajectory point, and the position transfer probability of the target object between every two adjacent sampling time points, the spatiotemporal model (STM) of the target object under the influence of noise can be obtained.
[0111] The target object is in grid r at time t. i The probability is:
[0112]
[0113] The probability here is a conditional probability, considering sparse sampling, where t includes the sampling points outside the sampled points.
[0114] Since the points in the trajectory conform to the Markov property, meaning the current position is only affected by the previous position and the next position is only affected by the current position, the above equation can be applied by considering only t. i ,t,t i+1 Three moments. Among them, t i and t i+1 Let t be any point in time between two points where the trajectory data can be collected. Based on the Markov chain principle, after canceling out identical terms in the numerator and denominator, we obtain the following formula:
[0115]
[0116] Assume P(r) i When events (t|T) and noise events occur simultaneously, applying the positioning error and position transfer probability to the above formula yields:
[0117]
[0118] Therefore, given a trajectory T, the spatiotemporal probability model STM of the target object being in the spatial grid r at time t can be expressed as:
[0119]
[0120] In this example implementation, the aforementioned spatiotemporal probability model can be used to determine the trajectory collision probability between different target objects, that is, the probability that two individual entities will intersect within a spatiotemporal range. Specifically, the spatiotemporal probability models corresponding to objects other than the target object can be determined first, and then, based on the spatiotemporal probability models corresponding to the target object and the other objects, the trajectory collision probability of the target object and other objects at the target time can be determined.
[0121] For two known trajectories T1 and T2, the spatiotemporal probability of whether they collide at the target time t within the spatial grid r is:
[0122] P(r,t|T1,T2)=STM(r,t|T1)*STM(r,t|T2)
[0123] By setting different thresholds for the above probabilities, it can be determined whether two objects collide at the spatial grid r at the target time t.
[0124] Trajectory spatiotemporal collision has many important applications. In daily life, users leave their own trajectories in different systems. These trajectories can be seen as samples from users' daily paths. By comparing the spatiotemporal similarity of these trajectories, trajectories belonging to the same user in different systems can be matched, thus achieving a more comprehensive user trajectory analysis. In addition, trajectory collision can also reveal the relationships between different users, better serving various applications such as infectious disease tracking, product recommendation, and personalized marketing.
[0125] It should be noted that although the steps of the method in this disclosure are described in a specific order in the accompanying drawings, this does not require or imply that the steps must be performed in that specific order, or that all the steps shown must be performed to achieve the desired result. Additional or alternative steps may be omitted, multiple steps may be combined into one step, and / or a step may be broken down into multiple steps.
[0126] Furthermore, this disclosure also provides an apparatus for processing trajectory data. (See reference...) Figure 5 As shown, the trajectory data processing device may include a trajectory data acquisition module 510, a positioning error determination module 520, a transfer probability determination module 530, and a probability model determination module 540. Wherein:
[0127] The trajectory data acquisition module 510 can be used to acquire trajectory text related to the activity trajectory of the target object, and obtain the trajectory data of the target object based on the trajectory text. The trajectory data contains the location information of the trajectory points of the target object at each sampling time point.
[0128] The positioning error determination module 520 can be used to divide the two-dimensional space into multiple spatial grids, and obtain the positioning error between each spatial grid and each trajectory point based on the position information of each trajectory point of the target object and the grid position information corresponding to each spatial grid.
[0129] The transition probability determination module 530 can be used to determine the position transition probability of the target object between every two adjacent sampling time points based on the trajectory data of the target object;
[0130] The probability model determination module 540 can be used to determine the spatiotemporal probability model corresponding to the target object based on the positioning error between each spatial grid and each trajectory point, as well as the position transfer probability of the target object between every two adjacent sampling time points. The spatiotemporal probability model is used to determine the trajectory collision probability between different target objects.
[0131] In some exemplary embodiments of this disclosure, the trajectory data processing apparatus provided in this disclosure may further include a trajectory collision probability determination module, which may include other probability model determination units and trajectory collision probability determination units. Wherein:
[0132] Other probability model determination units can be used to determine the spatiotemporal probability models corresponding to objects other than the target object;
[0133] The trajectory collision probability determination unit can be used to determine the trajectory collision probability of the target object and other objects at the target time based on the spatiotemporal probability model corresponding to the target object and the spatiotemporal probability models corresponding to other objects.
[0134] In some exemplary embodiments of this disclosure, the positioning error determination module 520 may include a distance error calculation unit and a positioning error calculation unit. Wherein:
[0135] The distance error calculation unit can be used to obtain the distance error between each spatial grid and each trajectory point based on the position information of each trajectory point of the target object and the grid position information corresponding to each spatial grid.
[0136] The positioning error calculation unit can be used to obtain the positioning error between each spatial grid and each trajectory point based on a preset probability distribution function, the distance error between each spatial grid and each trajectory point, and the prior position noise.
[0137] In some exemplary embodiments of this disclosure, the transition probability determination module 530 may include a movement speed array determination unit and a position transition probability calculation unit. Wherein:
[0138] The moving speed array determination unit can be used to obtain the average moving speed of the target object between every two adjacent sampling time points based on the trajectory data of the target object, and to obtain the moving speed array corresponding to the target object based on the average moving speed of the target object between every two adjacent sampling time points;
[0139] The position transition probability calculation unit can be used to obtain the corresponding bandwidth based on the moving speed array of the target object, and determine the position transition probability of the target object between every two adjacent sampling time points based on the preset kernel density function, the moving speed array, and the bandwidth.
[0140] In some exemplary embodiments of this disclosure, the movement speed array determination unit may include a movement distance determination unit and a movement speed determination unit. Wherein:
[0141] The movement distance determination unit can be used to obtain the movement distance of the target object between every two adjacent sampling time points based on the trajectory data of the target object;
[0142] The moving speed determination unit can be used to obtain the average moving speed of the target object between two adjacent sampling time points based on the moving distance of the target object between two adjacent sampling time points and the interval time between two adjacent sampling time points.
[0143] In some exemplary embodiments of this disclosure, the position transition probability calculation unit may include a velocity standard deviation determination unit and a bandwidth determination unit. Wherein:
[0144] The velocity standard deviation determination unit can be used to determine the velocity standard deviation of a target object based on the target object's corresponding moving velocity array;
[0145] The bandwidth determination unit can be used to obtain the corresponding bandwidth based on the speed standard deviation of the target object and the number of sample points in the movement speed array.
[0146] In some exemplary embodiments of this disclosure, the trajectory data acquisition module 510 may include a trajectory field extraction unit, a location information acquisition unit, and a trajectory data determination unit. Wherein:
[0147] The trajectory field extraction unit can be used to identify and extract trajectory fields from trajectory text, and perform structured processing on the trajectory fields to obtain the location names in the trajectory text, as well as the sampling time points corresponding to each location name;
[0148] The location information acquisition unit can be used to normalize the location names in the trajectory text to obtain the trajectory points of the target object and acquire the location information corresponding to each trajectory point.
[0149] The trajectory data determination unit can be used to obtain the trajectory data of the target object based on the location information corresponding to each trajectory point and the sampling time point corresponding to each trajectory point.
[0150] The specific details of each module / unit in the above trajectory data processing device have been described in detail in the corresponding method embodiment section, and will not be repeated here.
[0151] Figure 6 A schematic diagram of a computer system suitable for implementing embodiments of the present invention is shown.
[0152] It should be noted that, Figure 6 The computer system 600 of the electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of the present invention.
[0153] like Figure 6 As shown, the computer system 600 includes a central processing unit (CPU) 601, which can perform various appropriate actions and processes based on programs stored in read-only memory (ROM) 602 or programs loaded from storage section 608 into random access memory (RAM) 603. The RAM 603 also stores various programs and data required for system operation. The CPU 601, ROM 602, and RAM 603 are interconnected via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.
[0154] The following components are connected to I / O interface 605: an input section 606 including a keyboard, mouse, etc.; an output section 607 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN card, modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to I / O interface 605 as needed. A removable medium 611, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 610 as needed so that computer programs read from it can be installed into storage section 608 as needed.
[0155] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 609, and / or installed from removable medium 611. When the computer program is executed by central processing unit (CPU) 601, it performs various functions defined in the system of this application.
[0156] It should be noted that the computer-readable medium disclosed herein may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium may be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.
[0157] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.
[0158] In another aspect, this application also provides a computer-readable medium, which may be included in the electronic device described in the above embodiments; or it may exist independently and not assembled into the electronic device. The computer-readable medium carries one or more programs that, when executed by the electronic device, cause the electronic device to perform the methods described in the above embodiments.
[0159] It should be noted that although several modules for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to embodiments of this disclosure, the features and functions of two or more modules described above can be embodied in one module. Conversely, the features and functions of one module described above can be further divided and embodied by multiple modules.
[0160] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein.
[0161] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.
Claims
1. A method of processing trajectory data, characterized by, include: Obtain trajectory text related to the activity trajectory of the target object, and obtain trajectory data of the target object based on the trajectory text, wherein the trajectory data contains the position information of the trajectory points of the target object at each sampling time point; The two-dimensional space is divided into multiple spatial grids, and the positioning error between each spatial grid and each trajectory point is obtained based on the position information of each trajectory point of the target object and the grid position information corresponding to each spatial grid. The step of obtaining the positioning error between each spatial grid and each trajectory point based on the position information of each trajectory point of the target object and the grid position information corresponding to each spatial grid includes: obtaining the distance error between each spatial grid and each trajectory point based on the position information of each trajectory point of the target object and the grid position information corresponding to each spatial grid; and obtaining the positioning error between each spatial grid and each trajectory point based on a preset probability distribution function, the distance error between each spatial grid and each trajectory point, and prior position noise. Determining the position transition probability of the target object between every two adjacent sampling time points based on the trajectory data of the target object; the determination of the position transition probability of the target object between every two adjacent sampling time points based on the trajectory data of the target object includes: obtaining the average moving speed of the target object between every two adjacent sampling time points based on the trajectory data of the target object, and obtaining a moving speed array corresponding to the target object based on the average moving speed of the target object between every two adjacent sampling time points; obtaining the corresponding bandwidth based on the moving speed array corresponding to the target object, and determining the position transition probability of the target object between every two adjacent sampling time points based on a preset kernel density function, the moving speed array, and the bandwidth; Based on the positioning error between each of the spatial grids and each of the trajectory points, and the position transfer probability of the target object between every two adjacent sampling time points, a spatiotemporal probability model corresponding to the target object is determined. The spatiotemporal probability model is used to determine the trajectory collision probability between different target objects.
2. The method of claim 1, wherein, The method further includes: Determine the spatiotemporal probability models for objects other than the target object; Based on the spatiotemporal probability model corresponding to the target object and the spatiotemporal probability models corresponding to the other objects, the trajectory collision probability between the target object and the other objects at the target time is determined.
3. The method of claim 1, wherein, The step of obtaining the average moving speed of the target object between every two adjacent sampling time points based on the trajectory data of the target object includes: The distance the target object moves between every two adjacent sampling time points is obtained based on the trajectory data of the target object; The average moving speed of the target object between each two adjacent sampling time points is obtained based on the moving distance of the target object between each two adjacent sampling time points and the interval time between each two adjacent sampling time points.
4. The method of claim 1, wherein, The step of obtaining the corresponding bandwidth based on the movement speed array corresponding to the target object includes: Determine the speed standard deviation of the target object based on the movement speed array corresponding to the target object; The bandwidth is obtained based on the speed standard deviation of the target object and the number of sample points in the movement speed array.
5. The method of claim 1, wherein, The step of obtaining the trajectory data of the target object based on the trajectory text includes: The trajectory text is subjected to trajectory field recognition and extraction, and the trajectory field is subjected to structured processing to obtain the location names in the trajectory text and the sampling time points corresponding to each location name; The location names in the trajectory text are normalized to obtain the trajectory points of the target object, and the location information corresponding to each trajectory point is obtained. The trajectory data of the target object is obtained based on the location information corresponding to each trajectory point and the sampling time point corresponding to each trajectory point.
6. A processing device of trajectory data, characterized by, include: The trajectory data acquisition module is used to acquire trajectory text related to the activity trajectory of the target object, and obtain the trajectory data of the target object based on the trajectory text, wherein the trajectory data includes the position information of the trajectory points of the target object at each sampling time point; The positioning error determination module is used to divide a two-dimensional space into multiple spatial grids, and obtain the positioning error between each spatial grid and each trajectory point based on the position information of each trajectory point of the target object and the grid position information corresponding to each spatial grid. The step of obtaining the positioning error between each spatial grid and each trajectory point based on the position information of each trajectory point of the target object and the grid position information corresponding to each spatial grid includes: obtaining the distance error between each spatial grid and each trajectory point based on the position information of each trajectory point of the target object and the grid position information corresponding to each spatial grid; and obtaining the positioning error between each spatial grid and each trajectory point based on a preset probability distribution function, the distance error between each spatial grid and each trajectory point, and prior position noise. A transition probability determination module is used to determine the position transition probability of the target object between every two adjacent sampling time points based on the trajectory data of the target object. The determination of the position transition probability of the target object between every two adjacent sampling time points based on the trajectory data of the target object includes: obtaining the average moving speed of the target object between every two adjacent sampling time points based on the trajectory data of the target object, and obtaining a moving speed array corresponding to the target object based on the average moving speed of the target object between every two adjacent sampling time points; obtaining the corresponding bandwidth based on the moving speed array corresponding to the target object, and determining the position transition probability of the target object between every two adjacent sampling time points based on a preset kernel density function, the moving speed array, and the bandwidth. The probability model determination module is used to determine the spatiotemporal probability model corresponding to the target object based on the positioning error between each of the spatial grids and each of the trajectory points, and the position transfer probability of the target object between every two adjacent sampling time points. The spatiotemporal probability model is used to determine the trajectory collision probability between different target objects.
7. An electronic device, comprising: include: processor; as well as A memory for storing one or more programs, which, when executed by the processor, cause the processor to implement the method for processing trajectory data as described in any one of claims 1 to 5.
8. A computer-readable medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method for processing trajectory data as described in any one of claims 1 to 5.