CN113778986A - Vehicle supervision analysis method based on Beidou space-time data reconstruction and data mining - Google Patents
Vehicle supervision analysis method based on Beidou space-time data reconstruction and data mining Download PDFInfo
- Publication number
- CN113778986A CN113778986A CN202110959039.6A CN202110959039A CN113778986A CN 113778986 A CN113778986 A CN 113778986A CN 202110959039 A CN202110959039 A CN 202110959039A CN 113778986 A CN113778986 A CN 113778986A
- Authority
- CN
- China
- Prior art keywords
- time
- beidou
- space
- objects
- granularity
- 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.)
- Granted
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 30
- 238000007418 data mining Methods 0.000 title claims abstract description 12
- 230000000694 effects Effects 0.000 claims abstract description 22
- 238000000034 method Methods 0.000 claims abstract description 20
- 238000010276 construction Methods 0.000 claims abstract description 11
- 238000012544 monitoring process Methods 0.000 claims abstract description 11
- 238000013499 data model Methods 0.000 claims abstract description 9
- 238000004891 communication Methods 0.000 claims abstract description 4
- 238000005065 mining Methods 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 4
- 206010038743 Restlessness Diseases 0.000 claims description 3
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 238000005259 measurement Methods 0.000 claims description 3
- 230000014759 maintenance of location Effects 0.000 claims description 2
- 230000001360 synchronised effect Effects 0.000 claims description 2
- 230000001105 regulatory effect Effects 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- DMBHHRLKUKUOEG-UHFFFAOYSA-N diphenylamine Chemical compound C=1C=CC=CC=1NC1=CC=CC=C1 DMBHHRLKUKUOEG-UHFFFAOYSA-N 0.000 description 2
- 238000012790 confirmation Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/211—Schema design and management
- G06F16/212—Schema design and management with details for data modelling support
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G06Q50/40—
Abstract
The invention relates to a vehicle supervision and analysis method based on Beidou space-time data reconstruction and data mining, and aims to solve the technical problems that the existing similar methods are difficult to accurately position the offset phenomenon and lack of track prediction and real-time monitoring and early warning. The method is characterized in that the Beidou space-time data is reconstructed, and the Beidou space-time data is abstracted by combining road network information; secondly, performing space semantic expression of combining Thiessen polygons and road network information on the abstracted data in combination with the range of the Thiessen polygons of the communication base station to realize the division of the space granularity of the Beidou space-time data; then, recording a set of spatial changes of the Beidou object along with the time changes by combining the set time granularity, and realizing the construction of a Beidou multi-granularity space-time data model; and finally, analyzing the movement track of the objects with certain similarity, and classifying the objects according to the geographic position similarity of the objects to reflect the activity rule of the objects with the same preference at the geographic position.
Description
Technical Field
The invention relates to a Beidou positioning technology, in particular to a vehicle supervision and analysis method based on Beidou space-time data reconstruction and data mining.
Background
The Beidou positioning technology is a global satellite positioning system independently developed in China, and the working principle of the Beidou positioning system is that the distance between a satellite with a known position and a user receiver is measured, and then the specific position of the receiver is known by integrating data of a plurality of satellites. Because big dipper terminal produces a large amount of data every day, consequently need carry out the reconsitution to data, can study big dipper object (delivery vehicle) more effectively, analysis delivery vehicle's rule. In the prior art, multi-granularity time-space data (data generated by Beidou comprise longitude and latitude, speed, steering, events and short messages) are generally converted and are stored in modes of point, line and plane and the like in an abstract mode, so that the operation of a user is facilitated, and the accuracy and redundancy of the data can be ensured. For example, the application No. 201610630728.1 disclosed in the chinese patent document, application publication No. 2016.11.23, entitled "traffic positioning data-based multi-granularity road diversion visual analysis method"; however, the simple point-line surface abstraction of the patent and the similar technology can cause the phenomenon that the abstracted point-line surface deviates from road network data due to the problems of loss, drift and the like of Beidou space-time data, so that accurate positioning is difficult to perform, and meanwhile, the track prediction is lacked and real-time monitoring and early warning are difficult to perform.
Disclosure of Invention
In order to overcome the defects, the invention aims to provide a vehicle supervision and analysis method based on Beidou space-time data reconstruction and data mining for the field, so that the technical problems that in the prior art, due to the fact that Beidou space-time data is lack and drifts, abstracted point-line planes and road network data deviate, accurate positioning is difficult to perform, track prediction is lack, and real-time monitoring and early warning are difficult to perform are mainly solved. The purpose is realized by the following technical scheme.
A vehicle supervision and analysis method based on Beidou space-time data reconstruction and data mining is characterized in that the vehicle supervision and analysis method reconstructs Beidou space-time data and abstracts the Beidou space-time data by combining road network information; secondly, performing space semantic expression of combining Thiessen polygons and road network information on the abstracted data in combination with the range of the Thiessen polygons of the communication base station to realize the division of the space granularity of the Beidou space-time data; then, recording a set of spatial changes of the Beidou object along with the time changes by combining the set time granularity, and realizing the construction of a Beidou multi-granularity space-time data model; on the basis of the construction of a granularity space-time data model, combining time factors, taking Delta T as time precision, covering a road network through which an object passes based on the spatial semantic expression of a Thiessen polygon, reflecting the overlapping degree of different objects at the same geographical position at adjacent time, and quickly extracting the objects with certain similarity by the method so as to realize the classification of the objects; and finally, analyzing the movement track of the objects with certain similarity, and classifying the objects according to the geographic position similarity of the objects to reflect the activity rule of the objects with the same preference at the geographic position.
The method comprises the steps of mining an object travel mode according to the activity rule of the object at the geographic position, obtaining an object stopping point by combining the stay time of the object and the average speed of the object so as to solve the problem of object track randomness, and finally mining a frequent mode of the object by adopting an FP tree so as to realize the construction of an object motion rule, thereby realizing track prediction and realizing real-time monitoring and early warning.
The time granularity of the binding setting is set to one minute and the time precision at Δ T is set to ten minutes.
The vehicle supervision and analysis method comprises the following specific steps:
step one, Beidou spatial semantic expression is carried out to realize the division of spatial granularity; 1. constructing a map of the Thiessen polygons and the road network by means of the base station and the road network information, and dividing road sections of the road network to form calibration of a road section sequence; 2. based on the road section sequence information, searching a road section with the shortest vertical distance between the Beidou track point and the road section sequence as a road section through which the object passes; 3. realizing the spatial semantic expression, and once determining the road section where the object is located, combining a series of data to express the object spatial semantic; 4. the standard time granularity is set, the change of the Beidou object along with the time and the change of the road section of the Beidou object are recorded, and the construction of a Beidou multi-granularity space-time data model is realized by the following formula:
S(t)＝{(q1,t1),(q2,t2),...,(qn,tn) The frequency of the signal is multiplied by the frequency of the signal (formula 1),
wherein q isiIndicating the serial number of the road section, tiRepresents the time granularity;
classifying the objects based on the geographic position similarity, and solving the retention rule of the objects; 1. in order to simplify the complexity of the analysis of the motion rule of the object, the object is classified by adopting a method of geographic track similarity; 2. calculating the dwell point of the similar object by combining the speed and the dwell time of the object; 3. extracting the staying time of the similar objects by combining the activity rule of the FP tree mining object to obtain the staying information and staying times of the similar object group; mining a frequent item set by adopting an FP tree, and acquiring a frequent activity mode of an object based on the frequent item set; 4. the monitoring and analysis of the delivery vehicle are realized by combining the track of the activity rule prediction object or track abnormity analysis; the real-time trajectory of the object is monitored by using the motion rule mined by the FP tree, and if the contact ratio of the real-time trajectory of the object and the frequent patterns in the similar object group is too low or the corresponding frequent patterns are not found, the system considers that the trajectory of the object is abnormal, and then an alarm can be automatically sent.
In the second step, the objects are classified by adopting space-time slices, namely, the geographic position similarity of the objects in a certain time precision range is found out based on the time precision of the objects by taking Delta T as time precision, so that the activity rule of the objects with the same preference in the geographic position is reflected; expressed as:
the method sets a threshold value of object similarity S (u, v) to be 0.3, and if the similarity calculation in one day is more than 0.3, the objects are classified into one class; reducing the complexity of the system for solving the law of the activity of the object, wherein Ti(u) is the timestamp of the location of the object u within the time range of Δ T, marked by setting a standard time granularity, since Δ T is set to ten minutes, then the time precision of 15: 01 to 15: 10 is calculated, the geographic position of the object u and the object v are similar, then the object u starts to move at 15: 3, and the object v has already started to move at 15: 1, although the time is not synchronous, at 15: 1 and 15: 2, the similarity of u and v is 0, since the object u has no data; delta (q)i(u),qj(v) Delta (q) represents the degree of overlap of geographical locations if they are all on the same road segment at a certain time granularityi(u),qj(v) ) is equal to 1, otherwise is equal to 0.
And in the second step, the speed and the stay time of the object are used for extracting the object stay point, and the track formula of the object is assumed as follows:
Tri＝{(q1,q2,t1,t2),(q2,q3,t2,t3),...,(qn-1,qn,tn-1,tn) } (equation 3);
if the object stays on the same road section for a time tn-tn-1If the time threshold T is larger than the threshold T, the object is present qnAnd q isn-1Lingering between; next, the speed of the object is calculated, there is also a case where the object is moving at a low speed, wandering around a place, thus the object dwell point measurement is made by the speed of the object, vn＝(|qn-1-qn|)/(tn-tn-1) If at oneDelta T average velocity
Below 2m/s, the object is considered to wander in a certain place, also by default to stay.
The vehicle supervision and analysis method disclosed by the invention is accurate in positioning, and the travel mode of the object is excavated according to the activity rule of the object, and the trajectory prediction accuracy is improved and real-time monitoring and early warning can be realized by combining the stay time and stay speed of the stay point; the Beidou satellite positioning and early warning method is suitable for positioning through Beidou space-time data, track prediction and real-time monitoring and early warning, and is suitable for technical improvement of similar methods.
Drawings
FIG. 1 is a flow chart of the working principle of the present invention.
Fig. 2 is a schematic diagram of the invention based on road segment division.
Fig. 3 is a schematic diagram of the determination of the link based on the shortest vertical distance according to the present invention.
Detailed Description
The specific steps of the present invention will now be described in further detail with reference to the accompanying drawings. The vehicle supervision analysis method is a flow chart, as shown in fig. 1.
Step one, Beidou space semantic expression is carried out, and space granularity division is achieved.
1. And constructing a map of the Thiessen polygons and the road network by means of the base station and the road network information, and dividing the road network to form the calibration of the road sequence. As shown in fig. 2, the diagram is divided based on the road segments; the map shows a mapping relation map layer based on intersection of the Thiessen polygons and the road network, and road sections of the road network are divided based on the two map layers, wherein each road section is the length covered by the Thiessen polygons; and forming calibration of the road section sequence based on the division of each road section.
2. And based on the road section sequence information, searching the road section with the shortest vertical distance between the Beidou track point and the road section sequence as the road section through which the object passes. As shown in fig. 3, is determined based on the link whose vertical distance is the shortest.
3. The space semantic expression is realized, and once the road section where the object is located is determined, the space semantic expression of the object needs to be carried out by combining a series of data. Because the Beidou positioning points have the drift phenomenon, in the process of determining the spatial semantics, a series of track points are combined to determine the road section where the object is located, and multiple confirmation is carried out on the road section by adopting a plurality of positioning points; in addition, this is particularly true for the range of intersection points of an intersection, so that when an object passes through the intersection, the road segment determined by the positioning point may drift. Therefore, in the movement process, data of a plurality of points need to be judged, and a probability method is adopted; for example, if 70 points of 100 points are marked on the 001 road segment and the other 30 points are marked on the 008 road segment, the 001 road segment is taken as the object at the time granularity (the time of the 100 points, the positioning time interval set by the beidou is 1-5 seconds).
4. And setting a standard time granularity (set to one minute), recording a set of the change of the Beidou object along with the time and the change of the road section of the Beidou object, and realizing the construction of a Beidou multi-granularity space-time data model. The formula is as follows:
S(t)＝{(q1,t1),(q2,t2),...,(qn,tn) } (equation 1);
wherein q isiIndicating the serial number of the road section, tiRepresenting temporal granularity.
And step two, classifying the objects based on the geographic position similarity, and solving the stay rule of the objects.
1. In order to simplify the complexity of the analysis of the motion law of the object, the object is classified by adopting a method of geographic track similarity. Based on the characteristics of the objects in space-time distribution, the method classifies the objects to perform space-time slicing, namely based on the time precision (set as ten minutes) of the objects with the delta T, finds out the geographic position similarity of the objects in a certain time precision range, and reflects the activity rule of the objects with the same preference in the geographic position. Expressed as:
the method sets the threshold value of the similarity S (u, v) of the objects to be 0.3, and if the similarity calculation in one day is more than 0.3, the objects are classified into one class. Therefore, the complexity of solving the object activity rule by the system is reduced. Wherein T isi(u) is the timestamp of the location of the object u within the time range of Δ T, marked by setting a standard time granularity (set to one minute), since Δ T is set to ten minutes, then the time precision of 15: 01 to 15: 10 is calculated, the geographic position of the object u and the object v are similar, then the object u starts moving at 15: 3, and the object v starts moving at 15: 1, although the time is asynchronous, the similarity of u and v is 0 at 15: 1 and 15: 2, since the object u has no data. Delta (q)i(u),qj(v) Delta (q) represents the degree of overlap of geographical locations if they are all on the same road segment at a certain time granularityi(u),qj(v) ) is equal to 1, otherwise is equal to 0.
2. And combining the speed and the residence time of the object to obtain the dwell point of the similar object. Since the trajectory of the object has randomness, in order to solve the interference of randomness on the prediction of the trajectory of the object, it is necessary to extract a stop point. The method combines the speed and dwell time of the object to extract the dwell point of the object. Assume that the trajectory formula of an object is expressed as:
Tri＝{(q1,q2,t1,t2),(q2,q3,t2,t3),...,(qn-1,qn,tn-1,tn) } (equation 3);
if the object stays on the same road section for a time tn-tn-1If the time threshold T is larger than the threshold T, the object is present qnAnd q isn-1Lingering between; next, the speed of the object is calculated, there is also a case where the object is moving at a low speed, wandering around a place, thus the object dwell point measurement is made by the speed of the object, vn＝(|qn-1-qn|)/(tn-tn-1) If the speed is averaged at a Δ T
Below 2m/s, the object is considered to wander in a certain place, also by default to stay. To simplify the model, the center points of the two locations (two road segments) are taken, after all the method is marked with a set standard time granularity (set to one minute), which error is present for object tracking. The above-mentioned extraction of the stopping point of the object by time and speed satisfies that the object is considered to be stopped in any case.
3. And mining the activity rule of the object by combining the FP tree. Combining the previous step, extracting the staying time of the similar objects to obtain the staying information and staying times of the similar object group; and mining a frequent item set by adopting the FP tree, and acquiring the frequent activity pattern of the object based on the frequent item set.
4. And (4) the monitoring and analysis of the delivery vehicle are realized by combining the track of the activity rule prediction object or the track abnormity analysis. By mining the motion rule of the similar object, the method monitors the real-time track of the object by using the motion rule mined by the FP tree, and if the contact ratio of the real-time track of the object and the frequent patterns in the similar object group is too low or the corresponding frequent patterns are not found, the system considers that the track of the object is abnormal, and then an alarm can be automatically sent.
The innovation points of the vehicle supervision and analysis method are as follows: 1. and performing space semantic expression combining the Thiessen polygons and road network information on the abstracted data in combination with the range of the Thiessen polygons of the communication base station, so as to realize the division of the space granularity of the Beidou space-time data. 2. The Beidou multi-granularity space-time data model is constructed, the Beidou space-time data reporting frequency is considered, the set time granularity (set to one minute) is adopted, and the data calculation complexity is reduced. 3. By adopting a time slicing mode, the similarity of the geographic positions of the objects is innovatively provided, and the objects are classified to reflect the activity rule of the objects with the same preference in the geographic positions. 4. And combining the staying time of the object and the average speed of the object to obtain an object staying point so as to solve the problem of object track randomness. 5. And excavating a frequent sequence of the object by adopting the FP tree, and realizing the construction of the motion rule of the object, thereby realizing the track prediction of the carrier and realizing the real-time monitoring and early warning.
Claims (6)
1. A vehicle supervision and analysis method based on Beidou space-time data reconstruction and data mining is characterized in that the vehicle supervision and analysis method reconstructs Beidou space-time data and abstracts the Beidou space-time data by combining road network information; secondly, performing space semantic expression of combining Thiessen polygons and road network information on the abstracted data in combination with the range of the Thiessen polygons of the communication base station to realize the division of the space granularity of the Beidou space-time data; then, recording a set of spatial changes of the Beidou object along with the time changes by combining the set time granularity, and realizing the construction of a Beidou multi-granularity space-time data model; on the basis of the construction of a granularity space-time data model, combining time factors, taking Delta T as time precision, covering a road network through which an object passes based on the spatial semantic expression of a Thiessen polygon, reflecting the overlapping degree of different objects at the same geographical position at adjacent time, and quickly extracting the objects with certain similarity by the method so as to realize the classification of the objects; and finally, analyzing the movement track of the objects with certain similarity, and classifying the objects according to the geographic position similarity of the objects to reflect the activity rule of the objects with the same preference at the geographic position.
2. The vehicle supervision and analysis method based on Beidou space-time data reconstruction and data mining as claimed in claim 1, characterized in that the activity rule of the object at the geographic position is obtained by mining an object travel mode and combining the stay time of the object and the average speed of the object, so as to solve the problem of object track randomness, and finally, the frequent mode of the object is mined by adopting an FP tree, so that the object motion rule construction is realized, and thus, the track prediction is realized and the real-time monitoring and early warning are realized.
3. The vehicle regulatory analysis method based on Beidou spatiotemporal data reconstruction and data mining of claim 2, wherein the time granularity of the combined setting is set to one minute and the time precision at Δ T is set to ten minutes.
4. The vehicle supervision and analysis method based on Beidou space-time data reconstruction and data mining according to claim 3, characterized in that the vehicle supervision and analysis method comprises the following specific steps:
step one, Beidou spatial semantic expression is carried out to realize the division of spatial granularity; 1. constructing a map of the Thiessen polygons and the road network by means of the base station and the road network information, and dividing road sections of the road network to form calibration of a road section sequence; 2. based on the road section sequence information, searching a road section with the shortest vertical distance between the Beidou track point and the road section sequence as a road section through which the object passes; 3. realizing the spatial semantic expression, and once determining the road section where the object is located, combining a series of data to express the object spatial semantic; 4. the standard time granularity is set, the change of the Beidou object along with the time and the change of the road section of the Beidou object are recorded, and the construction of a Beidou multi-granularity space-time data model is realized by the following formula:
S(t)＝{(q1,t1),(q2,t2),...,(qn,tn) The frequency of the signal is multiplied by the frequency of the signal (formula 1),
wherein q isiIndicating the serial number of the road section, tiRepresents the time granularity;
classifying the objects based on the geographic position similarity, and solving the retention rule of the objects; 1. in order to simplify the complexity of the analysis of the motion rule of the object, the object is classified by adopting a method of geographic track similarity; 2. calculating the dwell point of the similar object by combining the speed and the dwell time of the object; 3. extracting the staying time of the similar objects by combining the activity rule of the FP tree mining object to obtain the staying information and staying times of the similar object group; mining a frequent item set by adopting an FP tree, and acquiring a frequent activity mode of an object based on the frequent item set; 4. the monitoring and analysis of the delivery vehicle are realized by combining the track of the activity rule prediction object or track abnormity analysis; the real-time trajectory of the object is monitored by using the motion rule mined by the FP tree, and if the contact ratio of the real-time trajectory of the object and the frequent patterns in the similar object group is too low or the corresponding frequent patterns are not found, the system considers that the trajectory of the object is abnormal, and then an alarm can be automatically sent.
5. The vehicle supervision and analysis method based on Beidou space-time data reconstruction and data mining as claimed in claim 4, characterized in that in the second step, objects are classified by adopting 'space-time slicing', that is, geographic position proximity of the objects within a certain time precision range is found out based on the time precision of the objects taking Δ T as time precision, so as to reflect the activity rule of the 'objects' with the same preference at the geographic position; expressed as:
the method sets a threshold value of object similarity S (u, v) to be 0.3, and if the similarity calculation in one day is more than 0.3, the objects are classified into one class; reducing the complexity of the system for solving the law of the activity of the object, wherein Ti(u) is the timestamp of the location of the object u within the time range of Δ T, marked by setting a standard time granularity, since Δ T is set to ten minutes, then the time precision of 15: 01 to 15: 10 is calculated, the geographic position of the object u and the object v are similar, then the object u starts to move at 15: 3, and the object v has already started to move at 15: 1, although the time is not synchronous, at 15: 1 and 15: 2, the similarity of u and v is 0, since the object u has no data; delta (q)i(u),qj(v) ) represent the degree of coincidence of geographical locations if they are all on the same road segment at a certain time granularity，δ(qi(u),qj(v) ) is equal to 1, otherwise is equal to 0.
6. The vehicle supervision analysis method based on Beidou spatiotemporal data reconstruction and data mining according to claim 4, characterized in that in the second step, the speed and dwell time of the object are used for extracting the object dwell point, and the trajectory formula of the object is assumed to be:
Tri＝{(q1,q2,t1,t2),(q2,q3,t2,t3),...,(qn-1,qn,tn-1,tn) } (equation 3);
if the object stays on the same road section for a time tn-tn-1If the time threshold T is larger than the threshold T, the object is present qnAnd q isn-1Lingering between; next, the speed of the object is calculated, there is also a case where the object is moving at a low speed, wandering around a place, thus the object dwell point measurement is made by the speed of the object, vn＝(|qn-1-qn|)/(tn-tn-1) If the speed is averaged at a Δ T
Below 2m/s, the object is considered to wander in a certain place, also by default to stay.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110959039.6A CN113778986B (en) | 2021-08-20 | 2021-08-20 | Carrier supervision analysis method based on Beidou space-time data reconstruction and data mining |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110959039.6A CN113778986B (en) | 2021-08-20 | 2021-08-20 | Carrier supervision analysis method based on Beidou space-time data reconstruction and data mining |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113778986A true CN113778986A (en) | 2021-12-10 |
| CN113778986B CN113778986B (en) | 2023-08-29 |
Family
ID=78838434
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110959039.6A Active CN113778986B (en) | 2021-08-20 | 2021-08-20 | Carrier supervision analysis method based on Beidou space-time data reconstruction and data mining |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113778986B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007233646A (en) * | 2006-02-28 | 2007-09-13 | Toyota Motor Corp | Object track prediction method, device, and program |
| CN106997666A (en) * | 2017-02-28 | 2017-08-01 | 北京交通大学 | A kind of method that utilization mobile phone signaling data position switching obtains traffic flow speed |
| WO2018113787A1 (en) * | 2016-12-23 | 2018-06-28 | 中兴通讯股份有限公司 | Region division method and device, and storage medium |
| CN110428604A (en) * | 2019-07-30 | 2019-11-08 | 山东交通学院 | It is a kind of based on the taxi illegal parking of GPS track data and map datum monitoring and method for early warning |
-
2021
- 2021-08-20 CN CN202110959039.6A patent/CN113778986B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007233646A (en) * | 2006-02-28 | 2007-09-13 | Toyota Motor Corp | Object track prediction method, device, and program |
| WO2018113787A1 (en) * | 2016-12-23 | 2018-06-28 | 中兴通讯股份有限公司 | Region division method and device, and storage medium |
| CN106997666A (en) * | 2017-02-28 | 2017-08-01 | 北京交通大学 | A kind of method that utilization mobile phone signaling data position switching obtains traffic flow speed |
| CN110428604A (en) * | 2019-07-30 | 2019-11-08 | 山东交通学院 | It is a kind of based on the taxi illegal parking of GPS track data and map datum monitoring and method for early warning |
Non-Patent Citations (3)
| Title |
|---|
| 孙爽等: "轨迹数据的时空模式挖掘与管理决策研究综述", 《计算机工程与应用》, pages 16 * |
| 李建勋;佟瑞;张永进;唐子豪;: "基于趋势面与SSIM的时空数据相似度算法", 计算机工程, no. 09, pages 52 * |
| 蔡少华,翟战强: "GIS基础空间关系分析", 测绘工程, no. 02, pages 38 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113778986B (en) | 2023-08-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10984652B2 (en) | Method and system for modeling and processing vehicular traffic data and information and applying thereof | |
| KR101385928B1 (en) | Method and apparatus for traffic management | |
| JP5705110B2 (en) | How to create a speed estimate | |
| Zhang et al. | Accuracy analysis of freeway traffic speed estimation based on the integration of cellular probe system and loop detectors | |
| KR20050025979A (en) | A method for measuring road traffic load based on analyzing cellular communications | |
| CN107516417A (en) | A kind of real-time highway flow estimation method for excavating spatial and temporal association | |
| Menard et al. | Comparing the GPS capabilities of the iPhone 4 and iPhone 3G for vehicle tracking using FreeSim_Mobile | |
| CN104217588A (en) | Method, server and system for acquiring real-time traffic information | |
| Schulze et al. | Map-matching cell phone trajectories of low spatial and temporal accuracy | |
| Huang et al. | CTS: A cellular-based trajectory tracking system with GPS-level accuracy | |
| US10582341B2 (en) | Facilitating estimation of mobile device presence inside a defined region | |
| Rodrigues et al. | Impact of crowdsourced data quality on travel pattern estimation | |
| CN113778986A (en) | Vehicle supervision analysis method based on Beidou space-time data reconstruction and data mining | |
| Moreira et al. | The impact of data quality in the context of pedestrian movement analysis | |
| Patroumpas | Online mobility tracking against evolving maritime trajectories | |
| Menard et al. | FreeSim_Mobile: A novel approach to real-time traffic gathering using the apple iPhone™ | |
| Dalla Torre et al. | A map-matching algorithm dealing with sparse cellular fingerprint observations | |
| Han et al. | Evaluation of freeway travel speed estimation using anonymous cellphones as probes: a field study in China | |
| TWI569225B (en) | A Method of Estimating Traffic Information Based on Multiple Regression Model of Mobile Network Signaling | |
| CN113409018B (en) | People stream density determining method, device, equipment and storage medium | |
| CN113379790B (en) | AI early warning positioning method for high-altitude observation object based on 3D model | |
| Kakarla et al. | Travel Time Prediction and Route Performance Analysis in BRTS based on Sparse GPS Data | |
| Sun et al. | Crowdsourced GNSS Satellite SNR in Degraded Environments for Dependability Improvement | |
| Andrieș et al. | Predicting user activities using gps collections | |
| CN117729628A (en) | Information determination method, apparatus, device and computer readable storage medium |
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 |