CN111583642B - Traffic track streaming type big data real-time processing method - Google Patents
Traffic track streaming type big data real-time processing method Download PDFInfo
- Publication number
- CN111583642B CN111583642B CN202010374262.XA CN202010374262A CN111583642B CN 111583642 B CN111583642 B CN 111583642B CN 202010374262 A CN202010374262 A CN 202010374262A CN 111583642 B CN111583642 B CN 111583642B
- Authority
- CN
- China
- Prior art keywords
- time coordinate
- coordinate data
- source data
- data sequence
- sequence
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 16
- 238000000034 method Methods 0.000 claims abstract description 35
- 238000012163 sequencing technique Methods 0.000 claims 2
- 230000000875 corresponding effect Effects 0.000 description 37
- 238000004364 calculation method Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 6
- 238000001514 detection method Methods 0.000 description 5
- 230000002776 aggregation Effects 0.000 description 3
- 238000004220 aggregation Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000002596 correlated effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012417 linear regression Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- OZUCXGWYZVDFOU-UHFFFAOYSA-N 2-(diethylamino)ethyl 6-hydroxy-4,7-dimethoxy-1-benzofuran-5-carboxylate;hydrochloride Chemical compound [Cl-].CC[NH+](CC)CCOC(=O)C1=C(O)C(OC)=C2OC=CC2=C1OC OZUCXGWYZVDFOU-UHFFFAOYSA-N 0.000 description 1
- 230000004931 aggregating effect Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000037361 pathway Effects 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
- G08G1/0129—Traffic data processing for creating historical data or processing based on historical data
Landscapes
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
The present specification provides a traffic trajectory streaming big data real-time processing method, including: acquiring N seed source data collected in a first time period; carrying out track modeling on each time coordinate data sequence in the previous M source data to obtain a corresponding track model; respectively calculating a difference index according to the track model corresponding to each time coordinate data sequence in the ith source data and each time coordinate data sequence in the jth source data; determining a temporary association relation between a time coordinate data sequence in the ith seed source data and a time coordinate data sequence in the jth seed source data according to the difference index; and determining a time coordinate data sequence which represents the same target running track in all the source data according to the temporary association relation. The method provided by the specification can determine the time coordinate data sequence representing the same target running track under the condition that the time coordinate data sequences of targets in different source data cannot be directly related through the existing information.
Description
Technical Field
The invention relates to the technical field of traffic data processing, in particular to a traffic track streaming type big data real-time processing method.
Background
The method for acquiring the real-time running track of the vehicle comprises an active reporting method and a passive detection method; taking air transportation as an example, the active Reporting method includes a method of Reporting flight data by using an automatic dependent Surveillance broadcast (ADS-B) System and an Aircraft Communication Addressing and Reporting System (ACARS), and the passive detecting method includes a Secondary air traffic Radar (SSR) scanning method.
Due to aviation safety application considerations and equipment replacement cost requirements, the aforementioned active safety methods and passive detection methods will coexist for a long time. However, due to different detection principles, the motion trajectories reported by different detection modes may have large deviations, and when the flight path is crowded, different source data representing one airplane may be identified as data of different airplanes, so that problems of flight path planning errors and the like threatening flight safety are caused; in addition, under the influence of environmental factors, methods such as navigation management secondary radar and the like can have the defects that the data precision is seriously reduced due to weather conditions, and the methods cannot be effectively used.
Disclosure of Invention
The present specification provides a traffic trajectory streaming big data real-time processing method, including:
acquiring N seed source data collected in a first time period; each of said source data comprising a sequence of time-coordinate data of at least two targets; n is more than or equal to 2; the incidence relation of the time coordinate data sequences of various source data is unknown;
carrying out track modeling on each time coordinate data sequence in the previous M source data to obtain a corresponding track model; m is more than or equal to 1 and less than or equal to N-1;
respectively calculating a difference index according to the track model corresponding to each time coordinate data sequence in the ith source data and each time coordinate data sequence in the jth source data; i is more than or equal to 1 and less than or equal to M, i < j and less than or equal to N;
on the premise that the difference index is smaller than a set value, determining a one-to-one temporary association relationship between the time coordinate data sequence in the ith source data and the time coordinate data sequence in the jth source data according to the difference index corresponding to each time coordinate data sequence in the ith source data and the difference index corresponding to each time coordinate data sequence in the jth source data;
and determining a time coordinate data sequence which represents the same target running track in all the source data according to the temporary association relation.
Optionally, calculating a difference index according to the trajectory model corresponding to each time coordinate data sequence in the ith source data and each time coordinate data sequence in the jth source data respectively; the method comprises the following steps:
respectively substituting time data in each time coordinate data sequence in the jth source data into each track model to obtain calculated data;
and calculating coordinate data in each time coordinate data sequence in the jth source data and an absolute deviation average value corresponding to the calculated data, and taking the absolute deviation average value as the difference index.
Optionally, before performing trajectory modeling on the time coordinate data sequence of each target in the previous M source data, the method further includes:
and sorting according to the sequence of the positioning accuracy of the N source data from high to low, and/or sorting according to the sequence of the data quantity in the time coordinate data sequence of the N source data from high to low.
Optionally, performing trajectory modeling on each time coordinate data sequence in the previous M source data to obtain a corresponding trajectory model, specifically: carrying out track modeling on each time coordinate data sequence in the first source data to obtain a corresponding track model;
determining a time coordinate data sequence which represents the same target running track in all the source data according to the temporary association relationship, wherein the time coordinate data sequence comprises the following steps: and determining all the time coordinate data sequences of other source data establishing the temporary association relation with one time coordinate data sequence in the first source data as sequences representing the same target running track.
Optionally, j ═ i + 1;
determining a time coordinate data sequence which represents the same target running track in all the source data according to the temporary association relationship, wherein the time coordinate data sequence comprises the following steps: determining time coordinate data sequences which represent the same target running track in the (k-1) th source data and the (k + 1) th source data according to two temporary association relations corresponding to the time coordinate data sequences in the kth source data until determining the time coordinate data sequences which represent the same target running track in all the source data; k is more than or equal to 2 and less than or equal to N-1.
Optionally, M is more than or equal to 2 and less than or equal to N-1, and N is more than or equal to 3;
determining a time coordinate data sequence which represents the same target running track in all the source data according to the temporary association relationship, wherein the time coordinate data sequence comprises the following steps:
starting from a time coordinate data sequence of the first source data, establishing a temporary association path network according to the temporary association relation;
in the case that the temporary associated path forms a branch at a time coordinate data sequence, reserving a path with the minimum difference index at the branch;
and taking the time coordinate data sequence in the longest path in the temporary associated path network as the time coordinate data sequence representing the same target running track, or taking all the time coordinate data sequences in other source data associated with one time coordinate data sequence of the first source data as the time coordinate data sequence representing the same target running track.
Optionally, wherein N ═ 3.
Optionally, determining a time coordinate data sequence representing the same target trajectory in all the source data according to the temporary association relationship includes:
starting from a time coordinate data sequence of the first source data, establishing a temporary association path network according to the temporary association relation;
reserving a path with the minimum path difference degree in the temporary association path network; the path difference degree is the average value of difference degree indexes in the path;
and taking the time coordinate data sequence of each source data corresponding to the path with the minimum path difference degree as a time coordinate data sequence representing the same target running track.
The method provided by the specification can determine the time coordinate data sequence representing the same target running track under the condition that the time coordinate data sequences of targets in different source data cannot be directly associated through the existing information, and then can gather the time coordinate data sequences representing the same target running track together for storage and/or output.
In the invention, the technical schemes can be combined with each other to realize more preferable combination schemes. Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and drawings.
Drawings
The drawings are only for purposes of illustrating particular embodiments and are not to be construed as limiting the invention.
FIG. 1 is a flow chart of a traffic trajectory streaming big data real-time processing method provided by an embodiment;
FIG. 2 is a schematic diagram of determining a temporary association relationship;
FIG. 3 is a diagram illustrating an association path network established in an exemplary application;
FIG. 4 is a schematic structural diagram of a traffic track streaming big data real-time processing device provided by an embodiment;
the system comprises a data acquisition unit 11, a model construction unit 12, a difference index calculation unit 13 and an association relation determination unit 14.
Detailed Description
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate preferred embodiments of the invention and together with the description, serve to explain the principles of the invention and not to limit the scope of the invention.
The embodiment of the specification provides a traffic track streaming big data real-time processing method for aggregating track data of multiple source data (the track data can also be understood as a time coordinate data sequence).
It should be noted that the processing method provided by the present embodiment is applied to a data processing apparatus. The data processing apparatus may be connected in communication with various types of source data to receive time-coordinate data sequences generated by the respective source data in real time. For example, if the data processing apparatus is applied to process trajectory data for an aircraft, the source data may include broadcast auto correlation monitoring systems and aircraft communication addressing and reporting systems in the aircraft, and may also include secondary radar.
Fig. 1 is a flow chart of a traffic track streaming big data real-time processing method provided by the embodiment. As shown in fig. 1, the method provided by the present embodiment includes steps S101-S106.
S101: n seed source data collected in a first time period are obtained.
It should be noted that the N source data in the present embodiment are source data generated for N different types of source data, each of which includes time coordinate data series of at least two targets (i.e., vehicles to be monitored).
It should also be noted that, in the present embodiment, the association relationship of the time coordinate data series of various source data is unknown, that is, the time coordinate data series of targets in different source data cannot be directly associated with known information.
In practical application, the data processing equipment may collect o kinds of source data, o > N; and o source data already have at least two source data which can be aggregated through a known association relation; for such source data, the present embodiment directly uses the known association relationship for aggregation, and does not use the following method steps for processing. After the subordinate steps are executed, the time coordinate data sequences in the source data with known association relation are aggregated through the time coordinate data sequences in other source data with known association relation.
In this embodiment, the time coordinate data sent by each data source may have different structural forms, and in this case, the data processing device performs normalization processing on different types of time-coordinate data after receiving the time coordinate data sent by each data source. The normalization process includes: (1) converting time of various time coordinate data sequences into standard time, and converting coordinate data of various time coordinate data sequences into standard coordinate space data, wherein the standard time can be UTC time, and the standard coordinate space data can be longitude and latitude data and altitude data of the earth. (2) And converting the format of the time-coordinate data into a standard format. For example, for an aircraft, each time coordinate data sequence may be converted to an "ID: time, longitude value, latitude value, altitude value "; the ID is a number of a destination corresponding to the source data.
After the foregoing processing, the time-coordinate data having the same ID number in one source data may be arranged in time order, so as to obtain a corresponding time-coordinate data sequence.
In this embodiment, the length of the first time period may be set according to the type of various source data and the requirement of the actual application. For example, in one application, if a source data transmits p pieces of time coordinate data every n unit times and the time coordinate data sequence of the source data has the best effect when taking m pieces, the length of the first period of time may be set to m × n ÷ p.
S102: and carrying out track modeling on each time coordinate data sequence in the former M source data to obtain a corresponding track model.
Wherein M is more than or equal to 1 and less than or equal to N-1.
In this embodiment, although each source data is a source data representing target time-coordinate data, there is no need for sorting each other; however, in the embodiment of the present invention, a trajectory model can be obtained by using a time coordinate data sequence in the source data a, the trajectory model is substituted by time data in the source data B to perform calculation to obtain calculation data, and subsequent judgment is performed; and avoiding obtaining the track model by reusing the time coordinate data sequence in the B source data, obtaining the calculated data by substituting the time data in the A source data into the track model and executing repeated operation caused by subsequent judgment, and avoiding judgment conflict caused by repeated operation.
In practical applications, the ordering of the N source data is not strictly limited, and the N source data can be ordered in a random manner. In order to improve the aggregation accuracy of the time coordinate data sequence as much as possible, in the embodiment, the positioning accuracies of the N source data are preferably sorted from high to low, or the data numbers in the time coordinate data sequence of the N source data are sorted from high to low. Correspondingly, the corresponding effects are described later.
In this embodiment, performing trajectory modeling on each time coordinate data sequence of a source data is to establish a trajectory model of time-coordinates. In practical application, the trajectory model may be a straight line model or a model of various possible moving trajectories of the target according to different actual trajectories of the target, and the other trajectory models may be a parabolic curve model, an arc model or a random curve model.
In this embodiment, a trajectory model is established by a regression analysis method. For example, if a target moves linearly at a constant speed, the corresponding trajectory modeling is performed by determining a linear regression model h using linear regression analysisθ(t)＝[x,y,z]＝[θx,θy,θz]×t+[bx,by,bz]Process of [ theta ], [ theta ]x,θy,θz]And [ b)x,by,bz]The coefficients of the model to be calculated are calculated.
In this embodiment, the process of performing the trajectory modeling on the first M source data in step S102 may be executed in parallel or in series.
S103: and respectively calculating the difference degree index according to the track model corresponding to each time coordinate data sequence in the ith source data and each time coordinate data sequence in the jth source data.
In this embodiment, i is greater than or equal to 1 and less than or equal to M, and i is greater than or equal to j and less than or equal to N.
In a specific application, the operation step of step S103 may include steps S1031 and S1032.
S1031: and respectively substituting the time data in each time coordinate data sequence in the jth source data into each track model to obtain the calculated data.
S1032: and calculating the absolute deviation average value of the coordinate data in each time coordinate data sequence in the jth source data and the corresponding calculation data, and taking the absolute deviation average value as a difference index.
It is conceivable that, in step S1031, the time data in the time coordinate data sequence in the jth source data is substituted as an input into each trajectory model, and the obtained calculation data exhibits the following characteristics: if the track formed by the time coordinate data sequence of the jth source data is more similar to the track formed by the time coordinate data sequence in the ith source data, the closer the calculation data is to the coordinate data in the time coordinate data sequence corresponding to the jth source data, the smaller the corresponding absolute deviation average value is; therefore, the average value of absolute deviations of the coordinate data in each time coordinate data series in the jth source data and the corresponding calculation data can be used as the disparity index.
In this embodiment, the index of the degree of difference is represented by D.
S104: and judging whether the difference index is smaller than a set value. If the index of the degree of difference is smaller than the set value, S105 is performed.
In consideration of the actual application scenario, the time coordinate data sequences of various source data representing the same target have the same trajectory characteristics with high probability, and the corresponding difference degree index is also small. Considering reversely, if the difference index is smaller than the set value, the probability that the corresponding time coordinate data sequence represents the same target is higher; and if the difference index is larger than the set value, the probability that the corresponding time coordinate data sequence is not the same target is higher. Therefore, in this embodiment, if the difference index is greater than the set value, S106 is directly executed, the corresponding difference index is discarded, and only in the case that the difference index is less than the set value, step 105 and the subsequent steps are normally executed.
S105: and determining the one-to-one temporary association relationship between the time coordinate data sequence in the ith source data and the time coordinate data sequence in the jth source data according to the difference degree indexes corresponding to the time coordinate data sequences in the ith source data and the difference degree indexes corresponding to the time coordinate data sequences in the jth source data.
In the embodiment, i is more than or equal to 1 and less than or equal to M, and i is less than or equal to j and less than or equal to N.
Fig. 2 is a schematic diagram of determining a temporary association relationship. As shown in FIG. 2, the source data A has three time coordinate data series A-I, A-II and A-III, the source data B has four time coordinate data series B-I, B-III, B-IV and B-VII, and the index of the degree of difference between A-I and B-V is larger than the set value and is no longer correlated.
As shown in FIG. 2, since A-III and A-II each have a degree of difference index from B-III which is less than a set value, A-II and B-III and B-IV each have a degree of difference index from B-III which is less than a set value. Therefore, whether A-II in the source data A can form a one-to-one temporary association relationship with B-III or form a temporary association relationship with B-III or B-IV needs to be determined according to the magnitude comparison between the difference degree indexes.
According to the meaning of the difference index, if the difference index between two time coordinate data sequences is smaller, the priority of the association relationship between the two time coordinate data sequences is higher.
By comparison, because
Then it can be determined that A-III and B-III establish a temporary association relationship, and A-II and B-IV establish a temporary association relationship.
S106: and determining a time coordinate data sequence which represents the same target running track in all the source data according to the incidence relation.
Step S106 accepts or rejects the temporary association relationship with the corresponding determination rule according to the temporary association relationship established in step S105, and determines a time coordinate data sequence representing the same target trajectory in all the source data.
In the step S106, the determination rule is different according to different preconditions. Several judgment rules are explained below.
Judgment rule under first precondition
The first precondition is that the aforementioned M is set to 1, that is, step S102 calculates only the respective time coordinate data series of the first source data to build the trajectory model. In this case, the time coordinate data sequence of the source data from 2 nd to nth may establish a temporary association with the time coordinate data sequence of the first source data only; step S106 is to use the time coordinate data sequence in the first source data as a link, and use the time coordinate data sequences in all other source data with which the temporary association relationship is established as the time coordinate data sequences representing the same target moving track (of course, the time coordinate data sequence of the first source data is also used as the time coordinate sequence representing the same target moving track).
Here, it is conceivable that, if the positioning accuracy of the N source data is sorted from high to low, or the number of data in the time coordinate data sequence of the N source data is sorted from high to low, the accuracy of the trajectory model may be improved as much as possible, so that the temporary correspondence established in step S105 is more reliable, and the probability that the result in step S106 meets the reality is higher.
Judgment rule under second precondition
The second precondition is that j ═ i +1, and M may be 1 or another positive integer. In this case, only the temporal relationship between the time coordinate data series in the kth source data and the (k + 1) th source data, k ≦ 2 ≦ N-1, can be determined in step S105.
Correspondingly, in step S106, it is necessary to use the time coordinate data sequence of the kth source data as a tie, so that the time coordinate data sequences representing the same target in the kth source data-1 and the kth source data-1 are determined.
Judgment rule under the third precondition
Judgment rule under the third precondition
The third precondition is that M is more than or equal to 2 and less than or equal to N-1, and N is more than or equal to 3.
Under a third precondition, step S106 may include steps S1061-S1063.
S1061: and establishing a temporary association path network from the time coordinate data sequence of the first source data according to the temporary association relation.
Fig. 3 is a schematic diagram of an association path network established in a specific application of the embodiment. It can be seen that the temporary association pathway network established from A-III is A-III → B-III → C-VII and A-III → CX. It can be seen from the two correlation paths described above that a logical conflict arises at this time (C-VII and C X cannot be correlated with A-III at the same time, since C-VII and C X are time-coordinate data sequences for two targets and it is unlikely that the two targets are too close). At this time, a bifurcation occurs in A-III to B-III and CX.
And S1062, in the case that the temporary associated path network forms a branch at a time coordinate data sequence, reserving the path with the minimum difference index at the branch.
Because of the fact that
Therefore, A-III → B-III → C-VII remains.
S1063: and taking the time coordinate data sequence in other source data associated with one time coordinate data sequence of the first source data as a time coordinate representing the same target running track.
According to the operation logic of S1063 and the aforementioned step S1062, the time coordinate data series of a-iii, B-iii, and C-vii may be used as the time coordinate data series representing the same target trajectory.
It can be considered that if the positioning accuracy of the N source data is sorted from high to low, or the number of data in the time coordinate data sequence of the N source data is sorted from high to low, the accuracy of the trajectory model can be improved as much as possible, so that the comparison result in step S106 is more reliable.
In other embodiments, step S1063 may also replace the time coordinate data sequence in the longest path in the temporary associated path network as the time coordinate data sequence representing the same target running track.
Under a third precondition, step S106 may include steps S1064-S1066.
S1064: and establishing a temporary association path network from the time coordinate data sequence of the first source data according to the temporary association relation.
Step S1064 is similar to step S1061, and will not be repeated here.
S1065: reserving a path with the minimum path difference degree in the temporary association path network; the path difference degree is the average value of the difference degree indexes in the path.
Taking the temporary associative path network as A-III → B-III → C-VII and A-III → CX as an example, using the difference index of two adjacent time coordinate data sequences in the path A-III → B-III → C-VII, calculating the average value of the difference index, comparing the average value of the difference index with the difference index of A-III → CX, and if the average value of the difference index is smaller than the difference index of A-III → CX, keeping A-III → B-III → C-VII.
S1066: and taking the time coordinate data sequence of each source data corresponding to the path with the minimum path difference degree as a time coordinate data sequence representing the same target running track.
In the traffic track streaming type big data real-time processing method provided by this embodiment, when the time coordinate data sequences of the targets in different source data cannot be directly associated with each other through the existing information, the time coordinate data sequences representing the same target running track can be determined by using the foregoing steps S101 to S106, and then the time coordinate data sequences representing the same target running track can be gathered together for storage and/or output. Specifically, before the aggregation storage and/or output, the time coordinate data sequence may be further sorted according to a time sequence.
It should be noted that in the case of the foregoing method, there may be some time-coordinate data sequences that are isolated data sequences and not associated with other data sequences; at this point, such data sequences may be stored for a certain time for subsequent data matching.
By adopting the traffic track streaming type big data real-time processing method provided by the embodiment, the vehicle motion tracks generated by various detection methods are integrated, and complete track time coordinate information can be conveniently extracted for analysis in the follow-up process.
Besides providing the foregoing traffic track streaming type big data real-time processing method, this specification also provides a traffic track streaming type big data real-time processing device. Because the processing device and the processing method adopt the same inventive concept, only the structure of the processing device is described below; for the corresponding technical implementation process, the technical problems to be solved and the technical effects, please refer to the above method.
Fig. 4 is a schematic structural diagram of a traffic track streaming type big data real-time processing device according to an embodiment. As shown in fig. 4, the processing apparatus includes a data acquisition unit 11, a model construction unit 12, a difference degree index calculation unit 13, and an association relation determination unit 14.
The data acquisition unit 11 is configured to acquire N seed source data acquired in a first time period; each of said source data comprising a sequence of time-coordinate data of at least two targets; n is more than or equal to 2; the incidence relation of the time coordinate data sequences of various source data is unknown;
the model building unit 12 is configured to perform trajectory modeling on each time coordinate data sequence in the previous M seed source data to obtain a corresponding trajectory model; m is more than or equal to 1 and less than or equal to N-1;
a discrepancy degree index calculating unit 13, configured to calculate a discrepancy degree index according to the trajectory model corresponding to each time coordinate data sequence in the ith source data and each time coordinate data sequence in the jth source data; i is more than or equal to 1 and less than or equal to M, i < j and less than or equal to N;
an association relation determining unit 14, configured to determine, on the premise that the difference index is smaller than the set value, a one-to-one temporary association relation between the time coordinate data sequence in the ith source data and the time coordinate data sequence in the jth source data according to the difference index corresponding to each time coordinate data sequence in the ith source data and the difference index corresponding to each time coordinate data sequence in the jth source data; and determining a time coordinate data sequence which represents the same target running track in all the source data according to the temporary association relation.
In one application, the difference index calculation unit 13 substitutes time data in each time coordinate data sequence in the jth source data into each trajectory model respectively to obtain calculation data; and calculating coordinate data in each time coordinate data sequence in the jth source data and an absolute deviation average value corresponding to the calculated data, and taking the absolute deviation average value as the difference index.
In one application, the data obtaining unit 11 sorts the N source data in the order of high positioning accuracy to low positioning accuracy, and/or sorts the N source data in the order of decreasing data number in the time coordinate data sequence.
In one application, M ═ 1; specifically, the model construction unit 12 performs trajectory modeling on each time coordinate data sequence in the first source data to obtain a corresponding trajectory model; the association relation determining unit 14 determines all the time coordinate data sequences of the other source data that establish the temporary association relation with one time coordinate data sequence in the first source data as sequences representing the same target running track.
In one application, j ═ i + 1; the association relation determining unit 14 determines a time coordinate data sequence representing the same target trajectory in all the source data according to the temporary association relation, including: determining time coordinate data sequences which represent the same target running track in the kth source data, the kth source data and the (k + 1) th source data according to two temporary association relations corresponding to the time coordinate data sequences in the kth source data until the time coordinate data sequences which represent the same target running track in all the source data are determined; k is more than or equal to 2 and less than or equal to N-1.
In one application, M is more than or equal to 2 and less than or equal to N-1, and N is more than or equal to 3; the association relation determining unit 14 determines a time coordinate data sequence representing the same target trajectory in all the source data according to the temporary association relation, including: starting from a time coordinate data sequence of the first source data, establishing a temporary association path network according to the temporary association relation; in the case that the temporary associated path forms a branch at a time coordinate data sequence, reserving a path with the minimum difference index at the branch; and taking the time coordinate data sequence in the longest path in the temporary associated path network as the time coordinate data sequence representing the same target running track, or taking all the time coordinate data sequences in other source data associated with one time coordinate data sequence of the first source data as the time coordinate data sequence representing the same target running track. In one application, the association determining unit 14 determines a time coordinate data sequence representing the same target trajectory in all the source data according to the temporary association, including: starting from a time coordinate data sequence of the first source data, establishing a temporary association path network according to the temporary association relation; reserving a path with the minimum path difference degree in the temporary association path network; the path difference degree is the average value of difference degree indexes in the path; and taking the time coordinate data sequence of each source data corresponding to the path with the minimum path difference degree as a time coordinate data sequence representing the same target running track.
In addition to providing the foregoing method and apparatus, embodiments of the present specification also provide a computer-readable storage medium storing program instructions; the program instructions can execute the traffic track streaming big data real-time processing method after being loaded by the processor. In practical applications, the computer readable storage medium is a magnetic disk, an optical disk, a read-only memory or a random access memory.
The embodiment of the specification also provides electronic equipment. The electronic device includes a memory and a processor. The memory stores program instructions; the program instructions can execute the traffic track streaming big data real-time processing method after being loaded by the processor.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention.
Claims (9)
1. A traffic track streaming big data real-time processing method is characterized by comprising the following steps:
acquiring N seed source data collected in a first time period; each of said source data comprising a sequence of time-coordinate data of at least two targets; n is more than or equal to 2; the incidence relation of time coordinate data sequences in various source data is unknown;
carrying out track modeling on each time coordinate data sequence in the previous M source data to obtain a corresponding track model; m is more than or equal to 1 and less than or equal to N-1;
respectively calculating a difference index according to the track model corresponding to each time coordinate data sequence in the ith source data and each time coordinate data sequence in the jth source data; i is more than or equal to 1 and less than or equal to M, i < j and less than or equal to N; the method comprises the following steps:
respectively substituting the time data in each time coordinate data sequence in the jth source data into the track model corresponding to each time coordinate data sequence in the ith source data to obtain calculated data;
calculating coordinate data in each time coordinate data sequence in the jth source data and an absolute deviation average value corresponding to the calculated data, and taking the absolute deviation average value as the difference index;
on the premise that the difference index is smaller than a set value, determining a one-to-one temporary association relationship between the time coordinate data sequence in the ith source data and the time coordinate data sequence in the jth source data according to the difference index corresponding to each time coordinate data sequence in the ith source data and the difference index corresponding to each time coordinate data sequence in the jth source data; the difference degree indexes corresponding to all time coordinate data sequences in the ith source data are the difference degree indexes of the corresponding track models;
and determining a time coordinate data sequence which represents the same target running track in all the source data according to the temporary association relation.
2. The method of claim 1,
before performing trajectory modeling on the time coordinate data sequence of each target in the previous M pieces of source data, the method further comprises the following steps:
and sequencing according to the sequence of the positioning accuracy of the N source data from high to low, and/or sequencing according to the sequence of the number of data in the time coordinate data sequence of the N source data from high to low.
3. The method according to claim 1 or 2,
performing track modeling on each time coordinate data sequence in the former M source data to obtain a corresponding track model, which specifically comprises the following steps: carrying out track modeling on each time coordinate data sequence in the first source data to obtain a corresponding track model;
determining a time coordinate data sequence which represents the same target running track in all the source data according to the temporary association relationship, wherein the time coordinate data sequence comprises the following steps: and determining all the time coordinate data sequences of other source data establishing the temporary association relation with one time coordinate data sequence in the first source data as sequences representing the same target running track.
4. The method according to claim 1 or 2,
j＝i+1；
determining a time coordinate data sequence which represents the same target running track in all the source data according to the temporary association relationship, wherein the time coordinate data sequence comprises the following steps:
determining time coordinate data sequences which represent the same target running track in the (k-1) th source data and the (k + 1) th source data according to two temporary association relations corresponding to the time coordinate data sequences in the kth source data until determining the time coordinate data sequences which represent the same target running track in all the source data; k is more than or equal to 2 and less than or equal to N-1.
5. The method according to claim 1 or 2,
m is more than or equal to 2 and less than or equal to N-1, and N is more than or equal to 3;
determining a time coordinate data sequence which represents the same target running track in all the source data according to the temporary association relationship, wherein the time coordinate data sequence comprises the following steps:
starting from a time coordinate data sequence of the first source data, establishing a temporary association path network according to the temporary association relation;
in the case that the temporary associated path forms a branch at a time coordinate data sequence, reserving a path with the minimum difference index at the branch;
and taking the time coordinate data sequence in the longest path in the temporary associated path network as the time coordinate data sequence representing the same target running track, or taking all the time coordinate data sequences in other source data associated with one time coordinate data sequence of the first source data as the time coordinate data sequence representing the same target running track.
6. The method of claim 5,
wherein N is 3.
7. The method according to claim 1 or 2,
determining a time coordinate data sequence which represents the same target running track in all the source data according to the temporary association relationship, wherein the time coordinate data sequence comprises the following steps:
starting from a time coordinate data sequence of the first source data, establishing a temporary association path network according to the temporary association relation;
reserving a path with the minimum path difference degree in the temporary association path network; the path difference degree is the average value of difference degree indexes in the path;
and taking the time coordinate data sequence of each source data corresponding to the path with the minimum path difference degree as a time coordinate data sequence representing the same target running track.
8. An electronic device comprising a memory and a processor; the memory stores program instructions; the program instructions, when loaded by the processor, are adapted to perform the method of any of claims 1-7.
9. A computer-readable storage medium, wherein the storage medium stores program instructions; the instructions when loaded by a computer device may perform the method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010374262.XA CN111583642B (en) | 2020-05-06 | 2020-05-06 | Traffic track streaming type big data real-time processing method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010374262.XA CN111583642B (en) | 2020-05-06 | 2020-05-06 | Traffic track streaming type big data real-time processing method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111583642A CN111583642A (en) | 2020-08-25 |
| CN111583642B true CN111583642B (en) | 2021-03-23 |
Family
ID=72111982
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010374262.XA Active CN111583642B (en) | 2020-05-06 | 2020-05-06 | Traffic track streaming type big data real-time processing method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111583642B (en) |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101465071B (en) * | 2009-01-08 | 2010-12-01 | 上海交通大学 | Multi-platform target tracking and distribution interactive simulation system |
| CN109923595B (en) * | 2016-12-30 | 2021-07-13 | 同济大学 | Urban road traffic abnormity detection method based on floating car data |
| CN109508000B (en) * | 2018-12-16 | 2021-09-03 | 西南电子技术研究所（中国电子科技集团公司第十研究所） | Heterogeneous multi-sensor multi-target tracking method |
| CN110288001B (en) * | 2019-05-28 | 2023-09-05 | 西南电子技术研究所（中国电子科技集团公司第十研究所） | Target recognition method based on target data feature training learning |
| CN110443288B (en) * | 2019-07-19 | 2021-09-28 | 浙江大学城市学院 | Trajectory similarity calculation method based on sequencing learning |
-
2020
- 2020-05-06 CN CN202010374262.XA patent/CN111583642B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN111583642A (en) | 2020-08-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111652427A (en) | Flight arrival time prediction method and system based on data mining analysis | |
| WO2020143170A1 (en) | Predicted path acquisition method and apparatus, computer device, and storage medium | |
| CN112862171B (en) | Flight arrival time prediction method based on space-time neural network | |
| CN114692416B (en) | Intelligent simulation in-flight airplane fault analysis system and method | |
| CN111461292A (en) | Real-time trajectory prediction method for unmanned aerial vehicle | |
| Tang et al. | A flight profile clustering method combining twed with K-means algorithm for 4D trajectory prediction | |
| CN110991913B (en) | Busy airport peak time congestion risk analysis method | |
| CN113284369B (en) | Prediction method for actually measured airway data based on ADS-B | |
| CN115966107A (en) | Airport traffic flow prediction method based on graph neural network | |
| CN111583642B (en) | Traffic track streaming type big data real-time processing method | |
| Isaacson et al. | Knowledge-based runway assignment for arrival aircraft in the terminal area | |
| CN112925964A (en) | Big data acquisition method based on cloud computing service and big data acquisition service system | |
| Wang et al. | A high-precision method of flight arrival time estimation based on xgboost | |
| Tian et al. | Assessment of flight block time reliability under different delay time windows: A case study | |
| CN111341096A (en) | Bus running state evaluation method based on GPS data | |
| Ying et al. | Terminal Traffic Flow Prediction Method Under Convective Weather Using Deep Learning Approaches. | |
| CN115130380A (en) | Strategic flight schedule delay distribution prediction method based on machine learning | |
| US20190073841A1 (en) | Method for testing the integrity of the avionics of an aircraft, associated device and computer program product | |
| CN111930137B (en) | Real-time optimization method for multi-source telemetering ballistic data frame | |
| CN113591976A (en) | Forward full-neighbor decorrelation-based out-of-order flight path fusion method | |
| CN111080110A (en) | Airport congestion risk analysis system | |
| CN110807558A (en) | Method and device for predicting departure taxi time based on deep neural network | |
| AU2020408906A1 (en) | Method and device for supervising a traffic control system | |
| CN111240361A (en) | Flight control method, device and equipment based on four-dimensional data and storage medium | |
| CN115985113B (en) | Traffic signal lamp control method and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20220104 Address after: 908, block a, floor 8, No. 116, Zizhuyuan Road, Haidian District, Beijing 100089 Patentee after: ZHONGZI DATA CO.,LTD. Address before: 100191 No. 37, Haidian District, Beijing, Xueyuan Road Patentee before: BEIHANG University |
|
| TR01 | Transfer of patent right |