CN111862606B - Illegal operating vehicle identification method based on multi-source data - Google Patents
Illegal operating vehicle identification method based on multi-source data Download PDFInfo
- Publication number
- CN111862606B CN111862606B CN202010711331.1A CN202010711331A CN111862606B CN 111862606 B CN111862606 B CN 111862606B CN 202010711331 A CN202010711331 A CN 202010711331A CN 111862606 B CN111862606 B CN 111862606B
- Authority
- CN
- China
- Prior art keywords
- track
- vehicle
- intersection
- base station
- information
- 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
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
- G08G1/0125—Traffic data processing
-
- 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
- G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
-
- 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
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
- G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
-
- 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
- G08G1/052—Detecting movement of traffic to be counted or controlled with provision for determining speed or overspeed
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/123—Traffic control systems for road vehicles indicating the position of vehicles, e.g. scheduled vehicles; Managing passenger vehicles circulating according to a fixed timetable, e.g. buses, trains, trams
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The invention discloses an illegal operating vehicle identification method based on multi-source data, which is characterized in that user mobile information is obtained based on mobile phone signaling data, users conforming to operating vehicle characteristics are screened out, suspicious illegal operating vehicles are preliminarily screened out in combination with a staying hot spot area, suspected vehicle owner track information is screened out by comparing with a legal operating vehicle GPS on the basis, and finally, a suspected illegal operating vehicle license plate number is obtained by matching with a vehicle passing sequence of checkpoint data. Compared with the prior art, the vehicle screening method and the vehicle screening system can screen all vehicles based on the existing data source, and additional sensing equipment and human participation are not needed in the process of inspecting the suspicious vehicles. The data sources involved do not involve user privacy concerns, and no cooperation by passengers or other personnel is required, and the data acquisition technology is easy to implement. Traffic law enforcement personnel can adjust the action scheme in time according to the vehicle track to break through the previous 'fixed time interval and fixed place' hitting mode, and the accuracy of hitting 'black cars' is improved.
Description
Technical Field
The invention belongs to the field of intelligent transportation, and particularly relates to an illegal operating vehicle identification method based on multi-source data.
Background
With the continuous opening of the vehicle operation market and the continuous increase of travel demands, a large number of illegal operation vehicles are bred at present, and particularly at important traffic nodes of cities, huge potential safety hazards are brought, and the overall external image of the cities is also damaged. Compared with legal taxis and network appointment vehicles, illegal operation vehicles refer to motor transportation vehicles such as taxis, coaches and minibuses which are not permitted by the government and do not obtain operation licenses issued by industry supervision departments, and people are usually pulled randomly in regions with concentrated and urgent people flow and travel demands such as stations, hospitals, scenic spots and schools, on one hand, adverse effects are caused on the transportation market, the market transportation order is seriously disturbed, on the other hand, great potential safety hazards are also caused on passengers, and legal rights and interests cannot be guaranteed.
At present, the monitoring of illegal operating vehicles is difficult, and the main reason is that corresponding detection means are lacked under open market conditions. Because the traffic supervision department only masters the operation running information of the normal operation vehicles, including vehicle license plates, driver mobile phone numbers, vehicle operation GPS information and the like, the travel track information of other private vehicles is difficult to obtain by the supervision department, and therefore the difficulty of the identification supervision work of illegal operation vehicles is increased. The mobile phone signaling data can continuously track the position information of the user in real time, and the acquisition is simple without additional sensing equipment except the mobile phone used in daily life. With the progress of the development and communication of the society, almost people have mobile phones, especially drivers, and the frequency of the mobile phones is higher due to the need of navigation. The invention discloses an illegal operation vehicle detection system and method (application number: 201410361120.4) by utilizing mobile phone signaling data and field detection equipment, wherein the current position of a vehicle to be detected is identified through a license plate, the current position of a driver mobile phone associated with the vehicle is analyzed by combining mobile phone signaling, the current position and the license plate are compared, and if the mobile phone of the driver is not arranged around the vehicle to be detected, the vehicle to be detected is considered to be the illegal operation vehicle. The invention relates to an illegal operating vehicle identification method based on automobile electronic identification data (application number: 201910511579.0), which mainly comprises the following steps: 1) Counting vehicle data passing through the same electronic identification acquisition point for multiple times and vehicle data passing through a city district for multiple times aiming at a vehicle with longer running time; 2) Carrying out weight distribution on the times of multiple passing through the same electronic identification acquisition point and the times of multiple passing through the urban district, and establishing an illegal operating vehicle suspicion degree evaluation data model; 3) And evaluating the vehicle according to the model.
The existing illegal operating vehicle identification method mainly aims at identifying specific vehicles, does not realize full-coverage investigation and monitoring, needs to be additionally provided with field detection equipment, and has certain difficulty in implementation due to the privacy problem of mobile phone signaling data matched with numbers.
Disclosure of Invention
Aiming at the problems in the prior art, the method and the system fuse position and industry supervision data, screen out operating vehicles with long driving time and unfixed route characteristics based on full sample analysis by taking mobile phone signaling as a core, preliminarily screen out suspicious illegal operating vehicles by comparing and matching with taxi network taxi appointment GPS data, judge the staying characteristics of the operating vehicles in a hot spot area on the basis, and further lock the track information of the illegal operating vehicles. And finally, acquiring running track information of the suspicious illegal operating vehicles based on path matching, extracting a path intersection sequence of the suspicious illegal operating vehicles, matching the path intersection sequence with the gate data, determining license plate numbers of the suspicious illegal operating vehicles to provide auxiliary support for traffic violation management, and realizing accurate striking of the illegal operating vehicles.
The technical scheme is as follows:
the invention discloses an illegal operating vehicle identification method based on multi-source data, which is characterized in that user mobile information is obtained based on mobile phone signaling data, users conforming to operating vehicle characteristics are screened out, suspicious illegal operating vehicles are preliminarily screened out in combination with a staying hot spot area, suspected vehicle owner track information is screened out by comparing with a legal operating vehicle GPS on the basis, and finally, a suspected illegal operating vehicle license plate number is obtained by matching with a vehicle passing sequence of checkpoint data.
Preferably, it comprises the following steps:
s1, data acquisition, namely acquiring mobile phone signaling data at a mobile operator, preprocessing the original signaling data, and extracting user travel OD information comprising departure time, arrival time, departure place, arrival place and travel speed;
s2, counting the travel distance and travel time consumption characteristics of the user within a period of time, and primarily screening travel track information of a commercial vehicle driver;
s3, performing path matching on the screened signaling data with the track characteristics of the operating vehicles, and converting the position information recorded by the signaling data into intersection sequence information on a road network;
s4, GPS information of operating vehicles including touring taxis and networked taxi appointment vehicles is obtained and matched with the screened track information of the operating vehicles, and the traveling track of the suspicious illegal operating vehicles is preliminarily determined;
s5, acquiring a hot spot area for receiving passengers of illegal operation vehicles in the whole city, such as a service base station set of a railway station, a school and the like, analyzing the staying characteristics of suspicious illegal operation vehicles in the hot spot area, and further determining illegal operation vehicles;
and S6, acquiring the gate data, matching the vehicle passing track sequence of the vehicle at the intersection with the track sequence of the driver of the illegal operating vehicle, and finally determining the license plate number information of the suspected vehicle.
Preferably, the step S1 of acquiring data specifically includes:
s11, acquiring original mobile phone signaling data from a mobile operator, and performing denoising processing on the original mobile phone signaling data, including processing of repeated positioning, ping-pong positioning and drift positioning data, so as to obtain more accurate user positioning track information;
s12, identifying a stopping point and a displacement point in the track according to the space-time attribute of the positioning point, namely calculating the stopping time of the current track point and the space distance between the current track point and the next track point, marking the stopping point and the displacement point as the remaining displacement points when the stopping time is greater than a time threshold value and the space distance between the current track point and the next track point is greater than a space threshold value; the specific time-space threshold value can be determined according to the travel characteristics of a study city and the coverage range of a base station;
and S13, dividing user travel OD information including a departure point, an end point, departure time, arrival time and average speed according to the identified stop point and displacement point information.
Preferably, the step S2 of preliminary screening specifically includes:
s21, selecting a week as a research time range, and counting the accumulated travel distance of the travel track of each mobile phone number in the week, wherein the calculation method of the travel distance is a linear distance between adjacent base stations in the track;
s22, counting that the travel speed of each user in one week is greater than V car OD number N of week And OD cumulative travel time T satisfying the condition week In which V is car The average running speed of the urban cars is indicated;
s23, further, screening out the distance which meets the condition that the daily cumulative running distance is larger than a distance threshold value S max The travel speed in one week is more than V car OD number N of week Average running times per week and accumulated average running time per day T of normal non-operation vehicle week And the track information recorded by the user and the mobile phone signaling of the average value of the normal daily average running time of the non-commercial vehicle is more than.
Preferably, in step S3, the base station trajectory sequence is converted into an intersection sequence by a path matching algorithm, and the path matching algorithm specifically includes:
s311: preparing basic data, introducing mobile phone base station information into ArcGIS, generating a base station buffer area through an analysis tool, determining the radius of the buffer area by the average coverage range of an urban base station, obtaining intersection information contained in each base station buffer area through intersection analysis of a base station buffer area file and an intersection point file, calculating the distance between a base station ID and a corresponding intersection ID, and finally obtaining a corresponding table of the base station and the intersection; analyzing and acquiring a road name corresponding to the connection of each intersection in ArcGIS software, namely an intersection and road correspondence table; intersecting through a base station buffer area file and a road file in the ArcGIS to obtain a corresponding road in the coverage area of each base station and obtain a base station and road corresponding table;
s312: the algorithm is to number each travel base station track sequence extracted from mobile phone signaling data aiming at a travel base station track sequence, namely, each track S i ＝{j 1 ,j 2 ,…,j i ,…,j n Where j is i Representing the base stations occupied in the tracks, and respectively executing the following algorithm flows for each track:
s313: to S i ＝{j 1 ,j 2 ,…,j i ,…,j n Each base station j in i Finding out all road sets R corresponding to the base station according to the base station and the road corresponding table ji And for each road set R corresponding to the base station ji Accumulating the roads in the track to obtain a frequency table F of all covered roads of the track i One column of the table is the road name, and one column is the accumulated frequency of the road;
s314: to S i Each base station j in i And obtaining a base station j according to the corresponding table of the base station and the intersection i All the intersections in the coverage area are marked as a base station coverage intersection set C ji ；
S315: according to the intersection set C covered by the base station obtained in the S314 ji And obtaining a road set R consisting of roads corresponding to each intersection in the intersection set Cji corresponding to the base station by using the intersection and road corresponding table i ；
S316: according to the frequency table F obtained by statistics in S313 i Marking the corresponding set R of each base station i Road R with second highest intermediate frequency max(Fi) And screening out a set JC of intersections formed by the roads ji When R is max(Fi) If =1, delete the base station j i ；
S317: to set JC ji Each intersection C in the tree, calculate its and corresponding base station j i The distance D between the base station and the intersection is reserved according to the minimum distance principle, and the intersection closest to the base station in space distance is marked as the corresponding intersection of the base station on the road network;
s318: circularly matching all base stations in the track sequence to obtain an intersection sequence C i And calling the shortest path function for nonadjacent intersections to finally obtain a complete and connected intersection sequence on the road network.
Preferably, the step S4 of preliminarily determining the travel track of the suspicious illegal operating vehicle specifically includes:
s41, acquiring GPS information of the commercial vehicles in a research range through a traffic management department, wherein the commercial vehicles comprise touring taxis and network appointment taxis;
s42, matching the GPS data to a road network to obtain the sequence information of the mobile intersection with the time label;
s43, matching the GPS track information of the operating vehicle with the track information of the operating vehicle screened from the mobile phone signaling data, and if the matching is successful, rejecting the signaling track information of the vehicle; if the matching is unsuccessful, the travel track information of the vehicle is reserved and is regarded as a suspicious illegal operation vehicle, the next step of judgment is carried out, and the specific implementation method of the matching is as follows:
s431: for a commercial vehicle GPS track sequence, firstly screening out OD information meeting the requirement of overlapping travel time and the running time of the GPS sequence from the user track information reserved in the step S2, and taking the OD information as a commercial vehicle sequence set X to be matched;
s432: one track sequence of the commercial vehicle GPS is marked as G i ＝{g 1 ,g 2 ,…,g i ,…,g n In which g is i Representing the intersection obtained by matching in the step S42, judging the track point g of each matching sequence in the set X 1 Whether g is satisfied within a certain time range before and after 1 The distance is less than a distance threshold S match If the point exists in the track point signaling track sequence, the point is considered to be successfully matched, and all intersections g in the GPS track sequence of the commercial vehicle in the day are traversed in sequence i If all track points in one track sequence are successfully matched, the mobile phone signaling track is considered to be successfully matched with the running track of the commercial vehicle, and the mobile phone signaling track does not belong to an illegal commercial vehicle, and can be removed from the sequence to be matched;
s433: and traversing all the commercial vehicle GPS track sequences in sequence, wherein the signaling track information reserved in the sequence to be matched is the suspicious illegal commercial vehicle information screened for the first time.
Preferably, the step S5 further determines an illegal operating vehicle, and includes the specific steps of:
s51, screening mobile phone base stations covering the hot spot area to form a set J according to the hot spot area in and out of the illegal operating vehicles in the city;
and S52, analyzing the suspicious vehicle mobile phone travel track information retained in the S4, calculating the staying times and accumulated staying time of the suspicious vehicle within the range of the hotspot base station J, and judging the vehicles meeting the condition that the daily average staying time is more than two times and the accumulated staying time is within a certain time range as illegal operating vehicles.
Preferably, the license plate number information of the suspected vehicle is finally determined in step S6, and the specific steps are as follows:
s61, a gate detection system of the urban road acquires vehicle number plate data, wherein a gate needs to be capable of snapshotting and recognizing the number plate of each passing vehicle; filtering and screening original data acquired by a card port detection system to acquire effective vehicle detection data, wherein the effective vehicle detection data needs to comprise three fields of license plate numbers, card port numbers and detection time;
s62, extracting the illegal operating vehicles screened in the S5 to obtain an intersection sequence C after path matching, and removing intersections without bayonet data in the sequence;
s63, screening passing license plates within a certain time range before and after passing through each intersection in the intersection sequence C, sequentially traversing all the intersections, judging in the license plate set screened at the previous intersection each time, and considering that the matching is successful when only one license plate number is reserved, wherein the license plate number is the license plate number of the illegal operating vehicle.
The invention has the advantages of
Compared with the prior art, the vehicle screening method and the vehicle screening system can screen all vehicles based on the existing data source, and additional sensing equipment and human participation are not needed in the process of inspecting the suspicious vehicles. The data sources involved do not involve user privacy concerns, and no cooperation by passengers or other personnel is required, and the data acquisition technology is easy to implement. Traffic law enforcement personnel can adjust the action scheme in time according to the vehicle track to break through the previous 'fixed time interval and fixed place' hitting mode, and the accuracy of hitting 'black cars' is improved.
Drawings
FIG. 1 is a flow chart of the present invention
Detailed Description
The invention is further illustrated by the following examples, without limiting the scope of the invention:
the invention discloses an illegal operating vehicle identification method based on multi-source data, which comprises the steps of obtaining user mobile information based on mobile phone signaling data, screening out users according with operating vehicle characteristics, preliminarily screening out suspicious illegal operating vehicles by combining with a staying hot spot area, comparing with a legal operating vehicle GPS on the basis, screening out suspected vehicle owner track information, and finally obtaining the number plate number of the suspected illegal operating vehicle by matching with a vehicle passing sequence of checkpoint data.
With reference to fig. 1, the method comprises the following steps:
s1, data acquisition, namely acquiring mobile phone signaling data at a mobile operator, preprocessing the original signaling data, and extracting user travel OD information comprising departure time, arrival time, departure place, arrival place and travel speed;
s2, counting the travel distance and travel time consumption characteristics of the user within a period of time, and preliminarily screening out travel track information of a commercial vehicle driver;
and S3, carrying out path matching on the screened signaling data with the track characteristic of the operating vehicle, and converting the position information recorded by the signaling data into intersection sequence information on a road network.
And S4, acquiring GPS information of the operating vehicles including the patrol taxies and the network appointment vehicles, matching the GPS information with the screened track information of the operating vehicles, and preliminarily determining the traveling track of the suspicious illegal operating vehicles.
And S5, acquiring a hot spot area for receiving the illegal operating vehicles in the whole city, such as a service base station set of a railway station, a school and the like, analyzing the staying characteristics of the suspicious illegal operating vehicles in the hot spot area, and further determining the illegal operating vehicles.
And S6, acquiring the gate data, matching the vehicle passing track sequence of the vehicle at the intersection with the track sequence of the driver of the illegal operating vehicle, and finally determining the license plate number information of the suspected vehicle.
Preferably, the step S1 of data acquisition includes acquiring mobile phone signaling data at a mobile operator, preprocessing the original signaling data, and extracting user travel OD information including departure time, arrival time, departure place, arrival place, and travel speed; the method comprises the following steps:
s11, acquiring original mobile phone signaling data from a mobile operator, and performing denoising processing on the original mobile phone signaling data, including processing of repeated positioning, ping-pong positioning and drift positioning data, so as to obtain more accurate user positioning track information;
s12, identifying a stop point and a displacement point in the track according to the space-time attribute of the positioning point, namely calculating the stop time of the current track point and the space distance between the current track point and the next track point, marking the stop point as the stop point when the stop time is longer than 40min and the space distance between the stop point and the next track point is longer than 800m, and keeping the displacement points as the rest. The specific time-space threshold value can be determined according to the travel characteristics of the research city and the coverage range of the base station.
And S13, dividing user travel OD information according to the identified stop point and displacement point information, wherein one section of OD consists of two continuous stop points and a middle displacement point. The complete OD information should include start point, end point, start time, arrival time, average speed.
Preferably, step S2 is to count travel distances and travel time consumption characteristics of the user within a period of time, and preliminarily screen out travel track information of the operator of the commercial vehicle; the method comprises the following steps:
s21, selecting a week as a research time range, and counting the travel accumulated distance of the travel track corresponding to each mobile phone number in the week, wherein the travel distance is calculated by a straight line distance between adjacent base stations.
And S22, counting the OD number of the travel speed greater than 20km/h and accumulating the travel time.
S23, screening out user track information of which the cumulative daily average driving distance exceeds 80KM, the OD number of which the travel speed is more than 20KM/h in one week is more than 14 times, and the cumulative daily average driving time is more than 4 h.
Preferably, in step S3, the screened signaling data with the track characteristic of the commercial vehicle is subjected to path matching, and the position information recorded in the signaling data is converted into intersection sequence information on the road network. The method comprises the following steps:
s31, converting the base station track sequence into an intersection sequence through a path matching algorithm, wherein the path matching algorithm comprises the following specific implementation steps:
s311: and preparing basic data. Introducing mobile phone base station information into ArcGIS, generating a base station 400m buffer area through an analysis tool, obtaining intersection information contained in each base station buffer area through intersection analysis of a base station buffer area file and an intersection point file, and meanwhile calculating the distance between a base station ID and a corresponding intersection ID to finally obtain a base station and intersection corresponding table; analyzing and acquiring a road name corresponding to the connection of each intersection in ArcGIS software, namely an intersection and road correspondence table; in ArcGIS, the corresponding road in the coverage area of each base station is obtained by intersecting the file of the buffer area of 400m of the base station with the file of the road, and a correspondence table of the base station and the road is obtained.
S312: the algorithm is to number each travel base station track sequence extracted from mobile phone signaling data aiming at a travel base station track sequence, namely, to each track S i ＝{j 1 ,j 2 ,…,j n Where j is i Representing the base stations occupied in the tracks, and respectively executing the following algorithm flows for each track:
s313: to S i ＝{j 1 ,j 2 ,…,j n Each base station j in i Finding out all road sets R corresponding to the base station according to the base station and the road corresponding table ji And a road set R corresponding to each base station ji Accumulating the roads in the track to obtain a frequency table F of all covered roads of the track i The list is the road name and the list is the accumulated frequency of the road.
S314: to S i Each base station j in i And obtaining a base station j according to the corresponding table of the base station and the intersection i All intersections within the coverage area are assumed as a set C of intersections covered by the base station ji 。
S315: according to the intersection set C covered by the base station obtained in the S314 ji And the intersection and road corresponding table to obtain the intersection and road corresponding tableThe road corresponding to each intersection in the intersection set Cji corresponding to the base station forms a road set R i 。
S316: according to the frequency table F obtained by statistics in S313 i Marking the corresponding set R of each base station i Road with second highest intermediate frequency
And screening out an intersection set JC consisting of the roads ji When is coming into contact with
Then delete the base station j i 。
S317: to set JC ji Each intersection C in the group, calculate its and corresponding base station j i And D, reserving the intersection closest to the base station space according to the minimum distance principle, and marking the intersection as the corresponding intersection of the base station on the road network.
S318: circularly matching all base stations in the track sequence to obtain an intersection sequence C i And calling the shortest-path function for nonadjacent intersections to finally obtain a complete and connected intersection sequence on the road network.
Preferably, the step S4 of obtaining the GPS information of the operating vehicles including the patrol taxies and the network appointment cars, matching the GPS information with the screened track information of the operating vehicles, and preliminarily determining the traveling track of the suspicious illegal operating vehicles includes the following steps:
s41, GPS information of operating vehicles including touring taxis and network appointment taxis in a research range (corresponding to mobile phone signaling data time) is acquired through a traffic control department;
and S42, matching the GPS data to a road network to obtain the sequence information of the mobile intersection with the time label, wherein the current GPS positioning precision is higher and the map matching technology is more mature, so that the map matching method of the GPS is not elaborated in detail.
S43, matching the GPS track information of the operating vehicle with the track information of the operating vehicle screened from the mobile phone signaling data, if the matching is successful, removing the signaling track information of the vehicle, if the matching is unsuccessful, keeping the travel track information of the vehicle, regarding the travel track information as a suspicious operating vehicle, and entering the next judgment, wherein the specific implementation method of the matching is as follows:
s431: for a commercial vehicle GPS track sequence, firstly, all signaling track data with OD information in the running time range of the commercial vehicle GPS track sequence are screened out to be used as a commercial vehicle sequence set X to be matched.
S432: for a commercial vehicle GPS track sequence G i ＝{g 1 ,g 2 ,…,g n In which g is i Represents the intersection matched in step S42, from g 1 Initially, a set X of sequences to be matched is screened out to meet the requirement of g 1 Within 15Min in the front and back, there are connections and g 1 And sequentially traversing all intersections in the GPS track sequence of the operating vehicle in the day when the distance of the signaling track sequence is less than 1.5KM base station, and if only one track sequence meets the condition, considering that the matching is successful and removing the track sequence from the sequence to be matched.
S433: and traversing all the operating vehicle GPS track sequences in sequence, wherein the signaling track information retained in the sequence to be matched is the suspicious illegal operating vehicle information screened for the first time, and entering the next judgment.
Preferably, step S5 obtains a hot spot area where the illegal commercial vehicles in the whole city will pick up passengers, such as a service base station set of a train station, a school, etc., analyzes the stay characteristics of the suspicious illegal commercial vehicles in the hot spot area, and further determines the illegal commercial vehicles. The method comprises the following steps:
s51, in order to obtain maximum benefits, illegal operating vehicles generally carry out passenger seizing in places with high travel demands such as railway stations and schools and stay for a period of time to wait for passengers. And screening the mobile phone base stations covering the hot spot area to form a set J according to the hot spot area in and out of the illegal operating vehicles in the city.
And S52, analyzing the suspicious vehicle mobile phone travel track information retained in the S433, and calculating the stay times and accumulated stay time of the suspicious vehicle mobile phone travel track information within the range of the hotspot base station J. And judging the vehicles meeting the condition that the daily average stay time is more than two times and the accumulated stay time is between 30min and 5h as illegal operating vehicles.
Preferably, the step S6 of obtaining the gate data, matching the passing trajectory sequence of the vehicle at the intersection with the trajectory sequence of the driver of the illegal operating vehicle, and finally determining the license plate number information of the suspected vehicle includes the following steps:
and S61, vehicle number plate data are acquired by a checkpoint detection system of the urban road, and a checkpoint needs to be capable of snapshotting and plate recognition of each passing vehicle. The original data collected by the card port detection system is filtered and screened to obtain effective vehicle detection data, and the effective vehicle detection data needs to contain three fields of license plate number, card port number and detection time.
And S62, extracting the illegal operating vehicles screened in the S52 to obtain an intersection sequence C after path matching, and removing intersections without bayonet data in the sequence.
S63, screening the number plates passing through each intersection in the intersection sequence C within a time range of 15min before and after the intersection, sequentially traversing all the intersections, judging in the number plate set screened at the previous intersection each time, and considering that the matching is successful when only one number plate number is reserved, wherein the number plate number is the number plate of the illegal operating vehicle.
The track data of mobile phone users in the whole city and the track data of the operating vehicles are analyzed and compared based on traffic control, operation control and mobile phone signaling data, and the track information of suspected illegal operating vehicle drivers is identified by combining the hot spot area of the illegal operating vehicles, so that the related data source is easy to obtain, the investigation range is wide, the track information is not limited to specific vehicles, and an auxiliary decision basis can be provided for traffic law enforcement personnel in the process of fighting the illegal operating vehicles.
Because the mobile phone signaling data is desensitized data after anonymous processing, the real mobile phone number of the user cannot be directly obtained so as to lock related vehicle information.
The specific embodiments described herein are merely illustrative of the spirit of the invention. Various modifications or additions may be made to the described embodiments, or alternatives may be employed, by those skilled in the art, without departing from the spirit or ambit of the invention as defined in the appended claims.
Claims (3)
1. A method for identifying illegal operating vehicles based on multi-source data is characterized in that mobile information of users is obtained based on mobile phone signaling data, users which accord with characteristics of operating vehicles are screened out, suspicious illegal operating vehicles are preliminarily screened out in combination with a staying hot spot area, on the basis, comparison is carried out with a legal operating vehicle GPS to screen track information of suspected vehicle owners, and finally license plate numbers of the suspected illegal operating vehicles are obtained through matching with a vehicle passing sequence of checkpoint data; the method specifically comprises the following steps:
s1, data acquisition, namely acquiring mobile phone signaling data at a mobile operator, preprocessing the original signaling data, and extracting user travel OD information comprising departure time, arrival time, departure place, arrival place and travel speed;
s2, counting the travel distance and travel time consumption characteristics of the user within a period of time, and preliminarily screening out travel track information of a commercial vehicle driver; the step S2 of preliminary screening specifically comprises the following steps:
s21, selecting one week as a research time range, and counting the accumulated travel distance of the travel track of each mobile phone number in one week, wherein the travel distance is calculated by a linear distance between adjacent base stations in the track;
s22, counting that the travel speed of each user in one week is greater than
OD number N of week And OD cumulative travel time T satisfying the condition week In which
The average running speed of the urban cars is indicated;
s23, further, screening and simultaneouslyThe requirement that the daily accumulated running distance is larger than the distance threshold value S is met max The travel speed in one week is higher than
OD number N of week Average running times per week and accumulated average running time per day T of normal non-operation vehicle week Track information recorded by users and mobile phone signaling of the users who are not in operation and have average normal daily running time;
s3, performing path matching on the screened signaling data with the track characteristics of the operating vehicles, and converting the position information recorded by the signaling data into intersection sequence information on a road network; the path matching algorithm specifically includes:
s311: preparing basic data, importing mobile phone base station information into ArcGIS, generating a base station buffer area through an analysis tool, determining the radius of the buffer area by the average coverage area of the urban base station, obtaining intersection information contained in each base station buffer area through intersection analysis of a base station buffer area file and an intersection point file, calculating the distance between a base station ID and a corresponding intersection ID, and finally obtaining a correspondence table of the base station and the intersection; analyzing and acquiring a road name corresponding to the connection of each intersection in ArcGIS software, namely an intersection and road correspondence table; intersecting the ArcGIS through a base station buffer area file and a road file to obtain a corresponding road in the coverage area of each base station and obtain a base station and road corresponding table;
s312: the algorithm is to number each travel base station track sequence extracted from mobile phone signaling data aiming at a travel base station track sequence, namely, to each track S i ＝{j 1 ,j 2 ,…,j i ,…,j n Where j is i Representing the base stations occupied in the tracks, and respectively executing the following algorithm flows for each track:
s313: to S i ＝{j 1 ,j 2 ,…,j i ,…,j n Each base station j in i Finding out all road sets R corresponding to the base station according to the base station and the road corresponding table ji And for the road corresponding to each base stationSet R ji Accumulating the roads in the track to obtain a frequency table F of all covered roads of the track i One column of the table is the road name, and one column is the accumulated frequency of the road;
s314: to S i Each base station j in i And obtaining a base station j according to the corresponding table of the base station and the intersection i All the intersections in the coverage area are recorded as a base station coverage intersection set C ji ；
S315: according to the intersection set C covered by the base station obtained in the S314 ji And obtaining a road set R consisting of roads corresponding to each intersection in the intersection set Cji corresponding to the base station by using the intersection and road corresponding table i ；
S316: according to the frequency table F obtained by statistics in S313 i Marking out the corresponding set R of each base station i Road with second highest intermediate frequency
And screening out an intersection set JC consisting of the roads ji When is coming into contact with
Then delete the base station j i ；
S317: to set JC ji Each intersection C in the group, calculate its and corresponding base station j i The distance D between the intersection points is reserved according to the minimum distance principle, the intersection point with the closest spatial distance to the base station is marked as the corresponding intersection point of the base station on the road network;
s318: circularly matching all base stations in the track sequence to obtain an intersection sequence C i Calling the shortest-path function for nonadjacent intersections to finally obtain a complete connected intersection sequence on the road network;
s4, GPS information of operating vehicles including touring taxis and networked taxi appointment vehicles is obtained and matched with the screened track information of the operating vehicles, and the traveling track of the suspicious illegal operating vehicles is preliminarily determined; the step S4 of preliminarily determining the travel track of the suspicious illegal operation vehicle specifically includes:
s41, acquiring GPS information of the commercial vehicles in a research range through a traffic management department, wherein the commercial vehicles comprise touring taxis and network appointment taxis;
s42, matching the GPS data to a road network to obtain the sequence information of the mobile intersection with the time label;
s43, matching the GPS track information of the operating vehicle with the track information of the operating vehicle screened from the mobile phone signaling data, and if the matching is successful, rejecting the signaling track information of the vehicle; if the matching is unsuccessful, the travel track information of the vehicle is reserved and is regarded as a suspicious illegal operation vehicle, the next step of judgment is carried out, and the specific implementation method of the matching is as follows:
s431: for a commercial vehicle GPS track sequence, firstly screening out OD information meeting the travel time and overlapping with the running time of the GPS sequence from the user track information reserved in the step S2, and taking the OD information as a commercial vehicle sequence set X to be matched;
s432: one track sequence of the commercial vehicle GPS is marked as G i ＝{g 1 ,g 2 ,…,g i, …,g n In which g is i Representing the intersection obtained by matching in the step S42, judging the track point g for each matching sequence in the set X 1 Whether g is satisfied within a certain time range before and after 1 The distance is less than a distance threshold S match If the point exists in the track point signaling track sequence, the point is considered to be successfully matched, and all intersections g in the GPS track sequence of the commercial vehicle are traversed in sequence i If all track points in one track sequence are successfully matched, the mobile phone signaling track is considered to be successfully matched with the running track of the commercial vehicle, and the mobile phone signaling track does not belong to an illegal commercial vehicle, and can be removed from the sequence to be matched;
s433: sequentially traversing all commercial vehicle GPS track sequences, wherein the signaling track information reserved in the sequence to be matched is the suspicious illegal commercial vehicle information screened for the first time;
s5, acquiring a hot spot area for receiving the vehicles in illegal operation in the whole city, analyzing the staying characteristics of the suspicious illegal operation vehicles in the hot spot area, and further determining the illegal operation vehicles; step S5, further determining illegal operating vehicles, which comprises the following specific steps:
s51, screening out mobile phone base stations covering the hot spot area to form a set J according to the hot spot area in and out of the illegal operation vehicles in the city;
s52, analyzing the suspicious vehicle mobile phone travel track information retained in the S4, calculating the staying times and accumulated staying time of the suspicious vehicle in the range of the hotspot base station J, and judging the vehicles meeting the condition that the daily average staying time is more than two times and the accumulated staying time is in a certain time range as illegal operating vehicles;
and S6, acquiring the gate data, matching the vehicle passing track sequence of the vehicle at the intersection with the track sequence of the driver of the illegal operating vehicle, and finally determining the license plate number information of the suspected vehicle.
2. The method according to claim 1, wherein the step S1 of data acquisition specifically comprises:
s11, acquiring original mobile phone signaling data from a mobile operator, and performing denoising processing including repeated positioning, ping-pong positioning and drifting positioning data processing on the original mobile phone signaling data so as to obtain more accurate user positioning track information;
s12, identifying a stop point and a displacement point in the track according to the space-time attribute of the positioning point, namely calculating the stop time of the current track point and the space distance between the current track point and the next track point, marking the stop point as the stop point when the stop time is greater than a time threshold value and the space distance between the stop point and the next track point is greater than a space threshold value, and taking the displacement points as the rest;
and S13, dividing the user travel OD information according to the identified stop point and displacement point information, wherein the user travel OD information comprises a starting point, an end point, starting time, arrival time and average speed.
3. The method according to claim 1, wherein the step S6 of finally determining the license plate number information of the suspected vehicle comprises the following specific steps:
s61, a gate detection system of the urban road acquires vehicle number plate data, wherein a gate needs to be capable of snapshotting and recognizing the number plate of each passing vehicle; filtering and screening original data acquired by a card port detection system to acquire effective vehicle detection data, wherein the effective vehicle detection data needs to comprise three fields of license plate numbers, card port numbers and detection time;
s62, extracting the illegal operating vehicles screened in the S5 to obtain an intersection sequence C after path matching, and removing intersections without bayonet data in the sequence;
s63, screening passing license plates within a certain time range before and after passing through each intersection in the intersection sequence C, sequentially traversing all the intersections, judging in the license plate set screened at the previous intersection each time, and considering that the matching is successful when only one license plate number is reserved, wherein the license plate number is the license plate number of the illegal operating vehicle.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010711331.1A CN111862606B (en) | 2020-07-22 | 2020-07-22 | Illegal operating vehicle identification method based on multi-source data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010711331.1A CN111862606B (en) | 2020-07-22 | 2020-07-22 | Illegal operating vehicle identification method based on multi-source data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111862606A CN111862606A (en) | 2020-10-30 |
| CN111862606B true CN111862606B (en) | 2022-10-21 |
Family
ID=72949206
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010711331.1A Active CN111862606B (en) | 2020-07-22 | 2020-07-22 | Illegal operating vehicle identification method based on multi-source data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111862606B (en) |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113205700B (en) * | 2021-03-26 | 2022-08-30 | 福建新大陆软件工程有限公司 | High-speed vehicle position identification method based on mobile phone signaling road network matching |
| CN114116926A (en) * | 2021-06-10 | 2022-03-01 | 武汉理工大学 | Passenger travel mode identification method based on bus stop information matching |
| CN114201530B (en) * | 2021-12-02 | 2024-05-28 | 合肥学院 | Early screening and preventive supervision method for suspected abnormal operation passenger car |
| CN114187489B (en) * | 2021-12-14 | 2024-04-30 | 中国平安财产保险股份有限公司 | Method and device for detecting abnormal driving risk of vehicle, electronic equipment and storage medium |
| CN114202929B (en) * | 2021-12-14 | 2022-12-06 | 广州交信投科技股份有限公司 | Illegal operating vehicle identification method based on passing behavior of passenger car and passenger car |
| CN114529311B (en) * | 2022-02-16 | 2023-04-28 | 安徽宇疆科技有限公司 | Route track matching method based on similarity of positioning curves |
| CN114422973B (en) * | 2022-03-30 | 2022-06-28 | 北京融信数联科技有限公司 | Internet taxi appointment driver intelligent identification method and system based on big data and readable storage medium |
| CN114786135B (en) * | 2022-06-20 | 2022-10-18 | 广州万协通信息技术有限公司 | Internet of vehicles attack detection method and device, electronic equipment and storage medium |
| CN115880898B (en) * | 2022-11-10 | 2024-05-10 | 公安部交通管理科学研究所 | Private new energy automobile abnormal use judging method |
| CN117615363B (en) * | 2024-01-18 | 2024-05-10 | 北京大也智慧数据科技服务有限公司 | Method, device and equipment for analyzing personnel in target vehicle based on signaling data |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101465867A (en) * | 2007-12-18 | 2009-06-24 | 黄金富 | System and method for checking true and false license plate of business vehicle using mobile phone by passenger |
| CN202306819U (en) * | 2011-10-25 | 2012-07-04 | 深圳市华盈泰科技有限公司 | Vehicle electronic identity vehicle-mounted terminal |
| CN104123843B (en) * | 2014-07-25 | 2017-02-15 | 中国科学院自动化研究所 | Illegal operation vehicle detecting system and method |
| CN107657330A (en) * | 2017-08-16 | 2018-02-02 | 深圳先进技术研究院 | A kind of candidate's public bus network computational methods, system and electronic equipment |
| CN108389397A (en) * | 2018-02-28 | 2018-08-10 | 夏莹杰 | A method of distinguishing illegal operation vehicle based on bayonet data |
-
2020
- 2020-07-22 CN CN202010711331.1A patent/CN111862606B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN111862606A (en) | 2020-10-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111862606B (en) | Illegal operating vehicle identification method based on multi-source data | |
| US10573173B2 (en) | Vehicle type identification method and device based on mobile phone data | |
| CN106971534B (en) | Commuter characteristic analysis method based on number plate data | |
| CN106197458B (en) | A kind of mobile phone user's trip mode recognition methods based on mobile phone signaling data and navigation route data | |
| CN107730975B (en) | System and method for guiding reverse car finding and departure guiding in supermarket parking | |
| CN102521965B (en) | Effect evaluation method of traffic demand management measures based on identification data of license plates | |
| CN111653096B (en) | Urban trip mode identification method based on mobile phone signaling data | |
| US10373494B1 (en) | Method and apparatus for estimating a parking event based on device signal observations | |
| CN113194138B (en) | Travel management method and system based on AI deep learning | |
| CN111091720A (en) | Congestion road section identification method and device based on signaling data and floating car data | |
| CN106611167A (en) | Tracking method and system | |
| CN106875721A (en) | Violation information management system and its path of navigation generation method | |
| CN108491418A (en) | A kind of acquisition of traffic accident data informationization, management and analysis system and method | |
| CN105575118A (en) | Screening method of personnel without driving qualification | |
| Kumar et al. | A model based approach to predict stream travel time using public transit as probes | |
| CN103593977B (en) | Private car illegal operation detection method | |
| CN115035491A (en) | Driving behavior road condition early warning method based on federal learning | |
| CN105991598A (en) | User acquisition method and device | |
| CN107240264A (en) | A kind of non-effective driving trace recognition methods of vehicle and urban road facility planing method | |
| CN113079463A (en) | Tourist attraction tourist travel activity identification method based on mobile phone signaling data | |
| CN114550445A (en) | Urban area traffic safety state evaluation method and device | |
| CN108351858A (en) | For identifying traffic congestion basic reason based on cellular data and suggesting the method and system of possible mitigation strategy | |
| White et al. | The use of mobile phone location data for traffic information | |
| CN111624638A (en) | Method for tracing trace and generating monitoring report based on big data system | |
| Van Houten et al. | 17-05 Effects of Safe Bicycle Passing Laws on Drivers' Behavior and Bicyclists' Safety |
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 |