CN104700646A - Online GPS data based abnormal taxi track real-time detection method - Google Patents
Online GPS data based abnormal taxi track real-time detection method Download PDFInfo
- Publication number
- CN104700646A CN104700646A CN201510148076.3A CN201510148076A CN104700646A CN 104700646 A CN104700646 A CN 104700646A CN 201510148076 A CN201510148076 A CN 201510148076A CN 104700646 A CN104700646 A CN 104700646A
- Authority
- CN
- China
- Prior art keywords
- taxi
- msub
- abnormal
- mrow
- atr
- 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
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 88
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000011897 real-time detection Methods 0.000 title claims abstract description 26
- 238000001514 detection method Methods 0.000 claims abstract description 24
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 18
- 238000012544 monitoring process Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000001914 filtration Methods 0.000 claims description 2
- 238000007726 management method Methods 0.000 description 10
- 238000004458 analytical method Methods 0.000 description 9
- 230000006399 behavior Effects 0.000 description 9
- 230000029305 taxis Effects 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 6
- 238000007405 data analysis Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 5
- 239000013598 vector Substances 0.000 description 5
- 238000005065 mining Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000000354 decomposition reaction Methods 0.000 description 2
- 238000005034 decoration Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 230000001174 ascending effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 238000000059 patterning Methods 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 238000012805 post-processing Methods 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/20—Monitoring the location of vehicles belonging to a group, e.g. fleet of vehicles, countable or determined number of vehicles
- G08G1/205—Indicating the location of the monitored vehicles as destination, e.g. accidents, stolen, rental
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
- G01S19/38—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system
- G01S19/39—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system the satellite radio beacon positioning system transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
- G01S19/42—Determining position
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Traffic Control Systems (AREA)
- Navigation (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an online GPS data based abnormal taxi track real-time detection method. The method comprises the steps of 1, building a road network model to a target city according to open source type open street map data; 2, solving the recommended taxi driving route candidate set Rec in the road network model through the k shortest route algorithm; 3, detecting the abnormal track of an online operating taxi on real time according to the recommended route candidate set Rec and the recommended route selected by a driver, the real-time GPS data set of the current taxi and the feedback of a passenger to the current taxi driving track, and reporting the real-time detection result to a transportation bureau; 4, analyzing the online taxi abnormal track detection result, and extracting the specific taxi running rules to obtain the regional taxi abnormal driving reports.
Description
Technical Field
The invention relates to the field of traffic big data processing and computer real-time calculation, in particular to a taxi abnormal track real-time detection method based on online GPS data.
Background
With the rapid development of sensor technology, a great amount of Position track information is continuously generated by sensors, in particular gps (global Position systems) sensors, and potential data values hidden behind the track information can be mined by an effective data analysis method. The mobile traffic data collected from taxis loaded with GPS devices provides a versatile analysis method for analyzing taxi driver behavior and road network changes. And the specific GPS track mode is mined, so that the public traffic management, the city construction and the public social service quality can be improved. The potential value of the GPS track is reflected by a plurality of applications, for example, J.Yuan et al uses a mass of taxi GPS records to mine the fastest and most intelligent driving direction in a T-drive, driving direction based on taxi tracks to provide convenient and fast path navigation for users; ziebart et al, in "Navigate like a cab, from detected context-aware behavor", used historical GPS trajectories to provide users with optimal driving routes to destinations based on taxi drivers' driving experiences; giannotti et al provide an accurate description of frequent Trajectory patterns from a spatial and temporal perspective in the "Trajectory patterning".
As managers throughout the taxi industry, the traffic authorities are now faced with numerous management issues, particularly the management of current taxi monitoring systems. Due to the limitation of the prior art and a monitoring system and the quantity of a large number of operating taxis, a traffic and management bureau cannot achieve efficient fine-grained taxi supervision. Compared with the increase and processing complexity of the current taxi track data, the taxi monitoring system cannot meet the supervision requirement at the present stage, and when the passenger complains about the taxi driver, the traffic management bureau must invest considerable manpower and material resources to solve the problem of the passenger. It is further noted that there are currently no effective measures and methods to stop taxi fraud passenger behaviors performed by taxi drivers.
At present, a plurality of abnormal model mining works aiming at the GPS track have achieved some achievements, and the traditional abnormal detection is that track abnormal pattern recognition and mining are carried out on the basis of track distance, track density, track distribution, track deviation and other aspects on the basis of on-line data, and in addition, abnormal track pattern mining is carried out through training on the basis of algorithms such as machine learning and the like. Although many track anomaly detection technologies exist at the present stage, some problems are still not effectively solved, for example, most of the track anomaly detection technologies mainly aim at detection of taxi fraud behaviors after a long time, so that the effect of post-processing can be achieved, and the traffic and administration bureau also needs to bear the cost of taxi driver identification, and cannot provide effective management for supervision of a taxi market. Furthermore, most of the current abnormal track detection depends on data analysis reasoning and cannot handle the special requirements of some passengers.
Disclosure of Invention
The purpose of the invention is as follows: the invention aims to solve the technical problem of providing a real-time detection method for abnormal tracks of taxis based on online GPS data aiming at the defects of the prior art.
In order to solve the technical problem, the invention discloses a taxi abnormal track real-time detection method based on online GPS data, which comprises the following steps:
step 1: performing road network modeling on a target city based on open street map (OpenStreetMap) data of an open source;
step 2: for each taxi, according to an journey starting point received by a vehicle-mounted sensor (the vehicle-mounted sensor in a tablet personal computer) and a journey end point confirmed by a passenger, efficient and accurate taxi driving path recommendation is carried out on a road network model by applying a k shortest path algorithm (KSP) from two aspects of road network road distance and road network road average driving time, and a recommended path candidate set Rec is obtained;
and step 3: according to a recommended path candidate set Rec and a recommended path selected by a driver from the recommended path candidate set Rec, combining a real-time GPS data set of the current taxi and integrating the feedback of a passenger on the running path of the current taxi, carrying out real-time detection on the abnormal path of the taxi running on line, wherein the real-time detection result comprises information such as the number plate information of the abnormal taxi, basic information of the taxi driver, the abnormal place (longitude and latitude), the abnormal time, the passenger getting-on place (longitude and latitude), a taxi transaction order number and the like, and uploading and recording the real-time detection result into a database appointed by a traffic administration;
and 4, step 4: and analyzing the detection result according to a data analysis algorithm for the online abnormal taxi track detection result, extracting the urban taxi running rule comprising abnormal taxi record statistics of different urban areas, different time periods and different companies, grading taxi drivers in different areas of the city monthly, quarterly and annually on the basis, and finally feeding the result back to relevant departments such as a traffic bureau and a taxi company.
In the invention, according to four basic data structures provided by open street map data of a target city: and the Node, the road Way, the model Relation relationship, and the model Tag abstract out a basic road network model of the target city. The link Segment is a basic unit of each road, which is a unit of links with shorter distance generated by a series of Nodes in a sequential order. And a Segment Section is a further abstraction of a Segment that is generated from a series of sequential Segments, and the end points of the Segments are intersections between roads. Therefore, by abstracting the basic data structure of the open street map data, a road network model of a target city based on Section can be obtained.
According to the generated target urban road network model, the taxi initial passenger carrying place O and the journey end point D determined after the passenger gets on the taxi, a k-Shortest Path algorithm (KSP) is used for carrying out corresponding travel Path recommendation on subsequent passenger carrying behaviors of the taxi from two aspects of road network road distance and road network road average travel time.
Because the expression form of the traditional discrete GPS taxi-hiring track tr cannot meet the requirement of subsequent online abnormal track real-time detection, in the invention, the discrete GPS taxi-hiring track is converted into a Section sequence corresponding to a GPS point, namely an abstract taxi track atr, and the expression form is as follows:
atr＝{sec1→…→secj→…→secm} (1)
wherein secjIs the Section projected and mapped by the GPS point p in tr, and the sequence of the sections in atr is consistent with the sequence of the GPS point p in tr.
Therefore, after the passenger determined O and D are given, k recommended paths are given by using a k shortest path algorithm (KSP) from the aspect of the distance of the road network road and the average travel time of the road network road to form a recommended path candidate set Rec, i.e. Rec ═ { atr1，…，atrk}。
In the invention, according to the recommended route candidate set Rec and the reference recommended route atr finally selected by the taxi driver in RecbenchAnd combining a real-time GPS data set of the current taxi, respectively carrying out real-time detection on the abnormal track of the taxi in online operation from two aspects of the current taxi running direction and running distance, merging the detection result into the real-time feedback of passengers, so that the detection result of the abnormal track is more accurate, and meanwhile, reporting the real-time detection result to a traffic management bureau.
From the current taxi driving direction, after the starting point O and the end point D are given, the general direction of taxi driving can be determined, and when the recommended route candidate set Rec and the reference recommended route atr finally selected by the driver in Rec are givenbenchWhen the taxi runs, the running direction of the taxi can be more easily determined within a certain range. Determining whether the current driving direction of the taxi is abnormal according to the following formula:
wherein, scoredirRepresents an abnormal value of the driving direction, the temperature coefficient is more than or equal to 0 and less than or equal to 1,is a set of sections generated by all the atrs in the recommended Path candidate set Rec, and | atrbenchI andrespectively represent atrbenchAndnumber of middle Section, | SimbenchI and I SimcddI respectively represents the Section and the atr of the current taxibenchNumber similar to middle Section, andthe number of Section in (A) is similar.
If scoredir＞λdirThen the current driving direction of the taxi can be determined as abnormal, wherein lambdadirIs a direction threshold.
From the current taxi driving distance, according to the determined starting point O and the determined end point D and the current taxi position pcurrentDistance d that taxi has traveledpass、pcurrentThe shortest distance D remaining from the end point DminRmAnd the average distance d of the recommended paths in the recommended path candidate set RecavgThe three distance variables can be substituted into the following formula to judge whether the current taxi driving distance is abnormal or not:
wherein, scoredisAn abnormal value of the travel distance is indicated,and isSec represents the travel distance of Section.
If scoredis＞λdisThen the current driving distance of the taxi can be determined as abnormal, wherein lambdadisIs a distance threshold.
Because the current taxi track is constantly changed, the historical moving state of the taxi passenger carrying track can also influence the judgment of the driving direction and the driving distance of the current taxi. Therefore, the current taxi state is judged more comprehensively and accurately by introducing the enhanced state score phi. History score over time from the taxi's entire passenger-carrying journeydirAnd scoredisFor the current scoredirAnd scoredisThere is a smaller and smaller effect, so the effect of the history state on the current state can be balanced by the weighting factor τ.
Suppose that the time intervals Δ t for adjacent GPS points in the taxi real-time GPS dataset are all equal and thatInitial time t0Is/are as followsWhereinIs equal toOrPhi at any time can be obtained by the following formula,
so for score at time tdir，tAnd scoredis，tAll can be replaced byAndand (6) judging the state.
If the driving direction or the driving distance of the current taxi is judged to be abnormal, the current state of the taxi is changed into a suspicious state, and at the moment, the system sends a prompt to a passenger on the taxi to request for confirming whether the current driving path is an abnormal path or not, and if the passenger confirms that the current driving path is the abnormal driving path, the driving record of the taxi is reported to a delivery administration for close monitoring; if the passenger confirms that the taxi is not an abnormal driving path, the passenger can drive the taxi according to the current driving position pcurrentAnd D, repeating the step 2 and the step 3, generating a new recommended route candidate set, and continuously detecting the current taxi driving route until the taxi reaches the end D.
In the invention, the detection result of the online abnormal taxi track is analyzed according to a data analysis algorithm, a specific taxi driving rule is extracted, and the analysis result is finally fed back to related departments such as a traffic bureau, a taxi company and the like.
Compared with the prior art, the invention has the beneficial effects that:
(1) the taxi track detection is performed in real time according to online data, and after the abnormity is detected, the driving behavior of a taxi driver can be guided or intervened quickly. Compared with off-line processing of track data, the method is more time-efficient.
(2) The feedback of the current passenger is added into the taxi track abnormity detection result, the state change of the taxi in running is effectively recorded, and a reliable basis is provided for the follow-up analysis of the driving behavior of a taxi driver and the complaint of the passenger.
Drawings
The foregoing and/or other advantages of the invention will become further apparent from the following detailed description of the invention when taken in conjunction with the accompanying drawings.
FIG. 1 is a flow chart of the present invention for online anomaly detection.
FIG. 2 is a basic block diagram of the method of the present invention.
Detailed Description
The present invention will be described in detail with reference to the accompanying drawings. It should be noted that the described embodiments are for illustrative purposes only and are not limiting on the scope of the invention.
The invention discloses a real-time detection method for taxi abnormal tracks based on online GPS data, a flow chart of the detection method is shown in figure 1, and the method comprises the following steps:
step 1: road network modeling is performed on a target city based on open street map (OpenStreetMap) data of an open source. From the current technology, there are currently two main basic urban decomposition techniques: mesh and electrogram methods. The grid method is characterized in that a city is divided into grid areas with the same size, and a grid sequence is used for representing the driving track of a vehicle, and the grid method has the advantages of simplicity, practicability and convenience in operation, but has some obvious problems, for example, when the grid areas are not suitable for modeling the current city, the moving behavior of the vehicle in the grid cannot be obtained; if the grid number is too sparse, the analysis of the online road vehicle condition cannot be carried out, and the decomposition coefficient theta of each city is different and is not easy to determine; the road conditions of a specific road and the vehicle conditions cannot be analyzed. Therefore, in the present invention, we use electronic mapping, i.e. modeling the road network of the target city by open street map data of open source. The method has the advantages that the analysis can be carried out according to the road network in real life, and the high efficiency of the model is kept. According to four basic data structures provided by open street map data of a target city: and the Node, the road Way, the model Relation relationship and the model Tag abstract a basic road network model of the target city. The link Segment is a basic unit of each road, which is a unit of links with shorter distance generated by a series of Nodes in a sequential order. And a Segment Section is a further abstraction of a Segment that is generated from a series of sequential Segments, and the end points of the Segments are intersections between roads. For example, if a Node is given a sequence of Nodes Node1…Nodei…Nodej…Nodem(i is more than or equal to 1 and less than or equal to j and less than or equal to m), wherein i and j represent the marks of different nodes, and m is the total number of nodes in the target city developed street map data, so that
seci，j＝{segi，i+1，…，segj-1，j}
Therefore, by abstracting the basic data structure of the open street map data, a road network model of a target city with Section as a basic unit can be obtained.
Step 2: for each taxi, according to the generated target urban road network model, the taxi initial passenger carrying place O and the journey end point D determined after the passenger gets on the taxi, a k shortest path algorithm (KSP) is used for carrying out corresponding travel path recommendation on subsequent passenger carrying behaviors of the taxi from two aspects of road network road distance and road network road average travel time.
In the present invention, all the trajectories refer to trajectories of taxis carrying passengers. A conventional GPS taxi track tr is a sequence of GPS points, i.e.
tr＝{p1→…→pi→…→pn}
Wherein, GPS point piIs a triple<lat，lng，timestamp>And lat, ng, timestamp refer to latitude, longitude and timestamp of the GPS point, respectively.
Because the expression form of the traditional discrete GPS taxi-hiring track tr cannot meet the requirement of subsequent online abnormal track real-time detection, in the invention, the discrete GPS taxi-hiring track is converted into a Section sequence corresponding to a GPS point, namely an abstract taxi track atr, and the expression form is as follows:
atr＝{sec1→…→secj→…→secm}
wherein secjIs the Section projected and mapped by the GPS point p in tr, and the sequence of the sections in atr is consistent with the sequence of the GPS point p in tr.
Therefore, after the passenger determined O and D are given, k recommended paths are given by using a k shortest path algorithm (KSP) from the aspect of the distance of the road network road and the average travel time of the road network road to form a recommended path candidate set Rec, i.e. Rec ═ { atr1，…，atrk}. K is a natural number, generally within 10.
The specific recommended route is divided into three steps,
(1) filtering the road intersection Node according to the nearest Euclidean distance through the determined OD and the current taxi driving directionOAnd NodeDThen with NodeOAnd NodeDRespectively serving as a starting point and an end point, and generating k recommended paths by using a k shortest path algorithm;
(2) in the k shortest path algorithm, path recommendation is performed according to a weight value of each Section of a road network model, wherein the weight refers to two aspects: road network road distance and road network road average travel time, i.e.
Where, | sec | | represents at atriLength (1. ltoreq. i. ltoreq.k) of Section in (1), and weight coefficientwsecIs marked according to the road grade of Section [ http:// works]The specific weight values are shown in Table 1, and the Section average velocity coefficient vsecIs calculated according to the road network average speed report issued by the traffic administration.
TABLE 1 weight coefficients corresponding to different road classes
| Road grade | Weight coefficient |
| motorway,motorway_junction,motorway_link | 0.3 |
| trunk,trunk_link | 0.4 |
| primary,primary_link | 0.6 |
| secondary,tertiary | 0.8 |
| cicleway,living_street,path | 1.5 |
| pedestrian,steps,footway | 2.0 |
| other | 1 |
(3) According toAndfor atriSorting, selecting the top k atrsiA final set of recommended path candidates Rec is formed. The sequencing algorithm comprises the following basic steps: will ATriAre pressed respectivelyAndsorting in ascending order, the sorting results are respectively expressed as ListdisAnd ListtimeThen followed by random slave ListdisOr ListtimeSelect the atr of the top-ranked positioniInserted into the recommended Path candidate set Rec if atriAnd repeating the random selection process until the number of the elements in Rec reaches k, and stopping sorting to finally obtain Rec containing k elements.
And step 3: according to the recommended path candidate set Rec and the reference recommended path atr finally selected by the taxi driver in RecbenchAnd combining a real-time GPS data set of the current taxi, respectively carrying out real-time detection on the abnormal track of the taxi in online operation from two aspects of the current taxi running direction and running distance, merging the detection result into the real-time feedback of passengers, so that the detection result of the abnormal track is more accurate, and meanwhile, reporting the real-time detection result to a traffic management bureau.
From the current taxi driving direction, after the starting point O and the end point D are given, the general direction of taxi driving can be determined, and when the recommended route candidate set Rec and the reference recommended route atr finally selected by the driver in Rec are givenbenchIn time, taxi runsIs more easily determined to be within a certain range. Determining whether the current driving direction of the taxi is abnormal according to the following formula:
wherein the temperature coefficient is more than or equal to 0 and less than or equal to 1,is a set of sections generated by all the atrs in the recommended Path candidate set Rec, and | atrbenchI andrespectively represent atrbenchAndnumber of middle Section, | SimbenchI and I SimcddI respectively represents the Section and the atr of the current taxibenchNumber similar to middle Section, andthe number of Section in (A) is similar. In this patent, the similarity between Section sections is measured using cosine similarity (cosine similarity), and it is specified if sec is presentiAnd secjSimilarity of (c) cos (sec)i，secj) > 0 (where i and j represent different Section identifiers, respectively), seciAnd secjSimilarly, wherein
Here, point A, B represents seciPoint C, D represents secjAnd vector ofRepresents seciDirection, vector of taxiRepresents secjThe direction of travel of the taxi,represents the vector inner product of the two vectors,andrespectively represent vectorsAndthe die of (1).
If scoredir＞λdirThen the current driving direction of the taxi can be determined as abnormal, wherein lambdadirIs a direction threshold.
From the current driving distance of the taxi, according to the confirmationDetermining a starting point O and an end point D and the position p of the taxicurrentDistance d that taxi has traveledpass、pcurrentThe shortest distance D remaining from the end point DminRmAnd the average distance d of the recommended paths in the recommended path candidate set RecavgThe three distance variables can be substituted into the following formula to judge whether the current taxi driving distance is abnormal or not:
wherein, <math>
<mrow>
<mi>η</mi>
<mo>=</mo>
<mfrac>
<mrow>
<msub>
<mi>d</mi>
<mi>pass</mi>
</msub>
<mo>+</mo>
<msub>
<mi>d</mi>
<mrow>
<mi>min</mi>
<mi>Rm</mi>
</mrow>
</msub>
</mrow>
<msub>
<mi>d</mi>
<mi>avg</mi>
</msub>
</mfrac>
<mo>,</mo>
</mrow>
</math> and is <math>
<mrow>
<msub>
<mi>d</mi>
<mi>avg</mi>
</msub>
<mo>=</mo>
<mfrac>
<mrow>
<msub>
<mi>Σ</mi>
<mrow>
<msub>
<mi>atr</mi>
<mi>i</mi>
</msub>
<mo>∈</mo>
<mi>Rec</mi>
</mrow>
</msub>
<msub>
<mi>Σ</mi>
<mrow>
<mi>sec</mi>
<mo>∈</mo>
<msub>
<mi>atr</mi>
<mi>i</mi>
</msub>
</mrow>
</msub>
<mo>|</mo>
<mo>|</mo>
<mi>sec</mi>
<mo>|</mo>
<mo>|</mo>
</mrow>
<mi>k</mi>
</mfrac>
<mo>,</mo>
</mrow>
</math> And sec represents the travel distance of the Section.
If scoredis＞λdisThen the current driving distance of the taxi can be determined as abnormal, wherein lambdadisIs a distance threshold.
Because the current taxi track is constantly changed, the historical moving state of the taxi passenger carrying track can also influence the judgment of the driving direction and the driving distance of the current taxi. Therefore, the current taxi state is judged more comprehensively and accurately by introducing the enhanced state score phi. From the taxi's entire passenger-carrying journey, over time, historical scotedirAnd scoredisFor the current scoredirAnd scoredisThere is a smaller and smaller effect, so the effect of the history state on the current state can be balanced by the weighting factor τ.
Suppose that the time intervals Δ t for adjacent GPS points in the taxi real-time GPS dataset are all equal and the initial time t0Is/are as followsWhereinIs equal toOrThen, at time t1Is rated asThus at any time tkIs evaluated in terms of the state of (a),
and the above formula can be extended to
Therefore, the above calculation formula can be simplified into the following form to obtain phi at any time,
so for score at time tdir，tAnd scoredis，tAll can be replaced byAndand (6) judging the state.
As shown in fig. 2, if the driving direction or the driving distance of the current taxi is determined to be abnormal, the current state of the taxi is changed into a suspicious state, and at this time, the system sends a prompt to a passenger on the taxi to request to confirm whether the current driving path is an abnormal path, and if the passenger confirms that the current driving path is the abnormal driving path, the driving record of the taxi is reported to a delivery bureau for close monitoring; if the passenger confirms that the taxi is not the abnormal driving path, the taxi is driven according to the current taxiPosition pcurrentAnd D, repeating the steps 2 and 3, generating a new recommended route candidate set, and continuously detecting the current taxi driving route until the taxi reaches the end D.
And 4, step 4: and analyzing the detection result according to a data analysis algorithm for the online abnormal taxi track detection result, extracting a specific taxi running rule, and finally feeding back the analysis result to relevant departments such as a traffic bureau, a taxi company and the like.
Aiming at the detection result analyzed in the step 4, the invention has the following application values:
(1) if the number of times of finding the abnormal track of a taxi driver in the detection result is gradually reduced along with the time, the traffic management bureau can conclude that the driver is a taxi driver beginner, and can judge that the driving skill of the driver is slowly improved along with the time. In this case, the traffic authority can provide guidance for certain driving experiences in a targeted manner by way of mail or telephone consultation, which allows the driver's driving skills to grow faster.
(2) If the analysis result shows that the number of abnormal tracks of a taxi driver in a certain period of time is more and more, the traffic management bureau can conclude that the taxi driver has a tendency of being more inclined to taxi fraud to obtain illegal money. At this point, the traffic authority needs to notify or warn the driver of compliance with the basic taxi industry driving standards.
(3) By examining the periodic abnormal track of the taxi drivers of the taxi companies, the operation condition of the taxi drivers of each taxi company can be reasonably inferred, so that the taxi drivers can be reasonably and effectively scored for each taxi company better, the operation quality of the taxi companies can be effectively promoted and improved, and the benign development of the taxi industry is promoted.
Examples
This example uses a data set generated over a month period for all taxis in city a for a simulation experiment.
Firstly, open street map data of an open source is obtained on the Internet aiming at a city A, the concrete website is (http:// www.openstreetmap.org /), a road network model taking Section as a basic unit is abstracted aiming at Node, Way, relationship and Tag of the city map data, a visual user-friendly road network model interface is built on a Linux server through the data, and the concrete used technology is a leaf front-end operation technology and an open layer API (WebGISOpenlayersJavascript API).
TABLE 2OD region vs. base information
| OD1 | OD2 | OD3 | OD4 | OD5 | |
| Number of tracks | 1505 | 845 | 728 | 1007 | 895 |
Then, the real-time abnormal track detection results of the taxis within a certain time are obtained by simulating the whole process of actually carrying passengers of a plurality of taxis. By extracting taxi track data in 5 pairs of OD areas with large flow in a data set of city A for one month, the path recommendation algorithm has high path coverage rate under the condition that k is relatively large (k is more than or equal to 5 and less than or equal to 7 in subsequent simulation of an experiment), and meets objective and actual path recommendation requirements and real-time calculation time limit. The number of selected paths is shown in table 2, and the path coverage of k-shortest path algorithm (KSP) is shown in table 3.
TABLE 3k shortest Path Algorithm Path coverage
| OD1 | OD2 | OD3 | OD4 | OD5 | |
| k＝3 | 0.4422 | 0.3554 | 0.4321 | 0.3429 | 0.3921 |
| k＝5 | 0.6731 | 0.6517 | 0.5883 | 0.6206 | 0.5891 |
| k＝7 | 0.8231 | 0.7917 | 0.7383 | 0.7706 | 0.7152 |
For example, TaxiaReceiving a passenger at the point O, and the passenger appointing an arrival point D, respectively giving out appropriate k recommended paths from the aspects of road network road distance and road network road average travel time by using a k shortest path algorithm (KSP) according to OD information to form a recommended path candidate set Rec, namely Rec ═ { atr1，…，atrk}. The driver selects a certain path in Rec as the reference path atrbenchThen TaxiaAccording to atrbenchDriving on a specified route, and during driving, calculating a score value phi of the current driving statedirAnd phidisIf phidirOr phidisExceeds a set direction threshold lambdadirOr a distance threshold λdisThen, the determination is performed according to the determination flow shown in fig. 2, and if the driving direction or the driving distance of the Taxi is determined to be abnormal, Taxi xi is determined to be abnormalaThe current state is changed into a suspicious state, and at the moment, the system sends a prompt to a passenger on the taxi to request to confirm whether the current driving path is an abnormal path or not (the passenger can check the starting place in real time through the vehicle-mounted tablet personal computerPoint, destination point, current position and running track), if the passenger confirms that the route is abnormal, the taxi running record can be reported to the traffic administration for close monitoring; and if the passenger confirms that the taxi does not belong to the abnormal driving path, repeating the steps 2 and 3 according to the current driving position of the taxi and the terminal D, generating a new recommended path candidate set, and continuously detecting the current driving path of the taxi until the taxi reaches the terminal D. Finally, after the passenger gets off the taxi and finishes the journey, the real-time detection result of the journey is included in an overall analysis and evaluation report of the taxi driver, and the real-time detection result is reported to a traffic administration or a taxi company in a more efficient abnormal track analysis report mode, so that a foundation is laid for subsequent taxi driver behavior evaluation.
The invention provides a real-time detection method for taxi abnormal tracks based on online GPS data, and a plurality of methods and ways for implementing the technical scheme are provided, the above description is only a preferred embodiment of the invention, and it should be noted that, for those skilled in the art, a plurality of improvements and decorations can be made without departing from the principle of the invention, and these improvements and decorations should also be regarded as the protection scope of the invention. All the components not specified in the present embodiment can be realized by the prior art.
Claims (8)
1. A taxi abnormal track real-time detection method based on online GPS data is characterized in that: the method comprises the following steps:
step 1, performing road network modeling on a target city based on open street map data of an open source;
step 2, according to the journey starting point received by the vehicle-mounted sensor of each taxi and the journey end point confirmed by the passenger, applying a k shortest path algorithm to a road network model to obtain a taxi driving recommended path candidate set Rec;
step 3, combining a real-time GPS data set of the current taxi according to a recommended path candidate set Rec and a recommended path selected by a driver, integrating the feedback of a passenger on the current taxi running path, and carrying out real-time detection on the abnormal path of the taxi running on line, wherein the real-time detection result comprises information such as the number plate information of the abnormal taxi, basic information of the taxi driver, the abnormal place (longitude and latitude), the abnormal time, the passenger boarding place (longitude and latitude), a taxi transaction order number and the like, and uploading and recording the real-time detection result into a database appointed by a traffic management bureau;
and 4, analyzing the online abnormal taxi track detection result, and extracting the urban taxi running rules, wherein the urban taxi running rules comprise the statistics of the abnormal taxi records of different urban areas, different time periods and different companies.
2. The method for detecting taxi abnormal track in real time based on online GPS data according to claim 1, wherein the step 1 of modeling a road network of a target city comprises the following steps: the basic road network model of the target city is obtained according to a basic data structure provided by open street map data of the target city, a basic unit of each road is represented by a road Segment, the road Segment is further abstract of the road Segment, the Segment is generated by a group of continuous and ordered segments, and the end points of the segments are intersections among the roads.
3. The method for detecting the abnormal track of the taxi based on the online GPS data according to claim 2, wherein in the step 2, the process of solving the recommended route candidate set Rec comprises the following steps:
(2-1) filtering the road intersection Node according to the nearest Euclidean distance by the determined taxi location O, the journey end point D determined after the passenger gets on the taxi and the current taxi driving directionOAnd NodeDBy NodeOAnd NodeDRespectively representing a starting point road intersection and a journey end point road intersection of a taxi;
(2-2) solving road network model by adopting k shortest path algorithmThe weight value of each Section comprises the road network road distanceAnd average travel time of road in road networkThe following equations were used for calculation, respectively:
the Section is a Section which is projected and mapped by a taxi track point p recorded by the GPS, the Section represents the driving distance of the Section, and the atr represents a Section sequence corresponding to the taxi track point recorded by the GPS, and the expression form is as follows:
atr＝{sec1→…→secj→…→secm} (3)
the sequence of Section in the atr is consistent with the sequence of taxi track points p recorded by the GPS, and the atriI is more than or equal to 1 and less than or equal to k, k represents the total number of sequences corresponding to all track points of the taxi, and wsecRepresenting the weighting factor, marked according to the road class of Section, vsecRepresenting a Section average speed coefficient, and obtaining the Section average speed coefficient according to a road network average speed report issued by a traffic management bureau;
(2-3) Node according to taxi starting pointOAnd journey end NodeDAnd road network road distanceAverage travel time of road in road networkFor atriSorting, selecting the top k atrsiForming a final recommended path candidate set Rec, i.e. Rec ═ { atr1,…,atrk}。
4. The method as claimed in claim 3, wherein the real-time detection of abnormal taxi track based on online GPS data in step 3 comprises determining whether the current taxi driving direction is abnormal, and calculating the driving direction abnormal value score by using the following formuladir：
Wherein, the temperature coefficient is more than or equal to 0 and less than or equal to 1, atrbenchRepresenting the driver's chosen reference atr in Rec,is a set of sections generated by all the atrs in the recommended Path candidate set Rec, and | atrbenchI andrespectively represent atrbenchAndnumber of middle Section, | SimbenchI and I SimcddI respectively represents the Section and the atr of the current taxibenchNumber similar to middle Section, andnumber of similar middle Section, λdirAs direction threshold, when scoredir＞λdirAnd judging that the current driving direction of the taxi is abnormal.
5. The method as claimed in claim 4, wherein the real-time detection of abnormal taxi track based on online GPS data in step 3 comprises determining whether the current taxi driving distance is abnormal, and calculating the driving distance abnormal value score by using the following formuladis：
Wherein, <math>
<mrow>
<mi>η</mi>
<mo>=</mo>
<mfrac>
<mrow>
<msub>
<mi>d</mi>
<mi>pass</mi>
</msub>
<mo>+</mo>
<msub>
<mi>d</mi>
<mrow>
<mi>min</mi>
<mi>Rm</mi>
</mrow>
</msub>
</mrow>
<msub>
<mi>d</mi>
<mi>avg</mi>
</msub>
</mfrac>
<mo>,</mo>
</mrow>
</math> and is <math>
<mrow>
<msub>
<mi>d</mi>
<mi>avg</mi>
</msub>
<mo>=</mo>
<mfrac>
<mrow>
<msub>
<mi>Σ</mi>
<mrow>
<msub>
<mi>atr</mi>
<mi>i</mi>
</msub>
<mo>∈</mo>
<mi>Rec</mi>
</mrow>
</msub>
<msub>
<mi>Σ</mi>
<mrow>
<mi>sec</mi>
<mo>∈</mo>
<msub>
<mi>atr</mi>
<mi>i</mi>
</msub>
</mrow>
</msub>
<mo>|</mo>
<mo>|</mo>
<mi>sec</mi>
<mo>|</mo>
<mo>|</mo>
</mrow>
<mi>k</mi>
</mfrac>
<mo>,</mo>
</mrow>
</math> dpassIndicating the distance the taxi has travelled, dminRmIndicating the remaining shortest distance, d, of the taxi from the end pointavgRepresents the average distance, lambda, of the recommended paths in the recommended path candidate set RecdisAs distance threshold, when scoredis＞λdisAnd judging that the current running distance of the taxi is abnormal.
6. The method for detecting the abnormal track of the taxi based on the online GPS data in real time as claimed in claim 5, wherein the step 3 comprises judging whether the current taxi running track is abnormal by introducing an enhanced state score Φ, and the following formula is adopted:
wherein phitkIs shown at time tkAn enhanced status score of a lower,andrespectively, at time tkLower driving direction abnormal value scoredirAnd a driving distance abnormal value scoredisFor the convenience of the subsequent calculation,is shown at time tkIs as followsOrAssuming that the time intervals Δ t for adjacent GPS points in the taxi real-time GPS dataset are all equal, the initial time t0Enhanced status scoring ofτ represents the weight coefficient (0 < τ < 1), so for score at time tdirAnd scoredisIt can be converted into an enhanced driving direction state score Φ by equation (6)dirAnd enhanced driving distance status score ΦdisAnd (6) judging the state.
7. The method for detecting the abnormal track of the taxi based on the online GPS data in real time as claimed in claim 6, wherein in the step 3, if the current driving direction or the driving distance of the taxi is determined to be abnormal, the current state of the taxi is determined to be a suspicious state, a prompt is sent to a passenger on the taxi to request to confirm whether the current driving path is an abnormal path, and if the passenger confirms that the current driving path is the abnormal driving path, the driving record of the taxi is reported to a traffic administration for monitoring; if the passenger confirms that the taxi does not belong to the abnormal driving path, repeating the step 2 and the step 3 according to the current driving position of the taxi and the end point of the journey until the taxi reaches the end point of the journey.
8. The method for detecting taxi abnormal tracks in real time based on the online GPS data as claimed in claim 7, wherein regional taxi abnormal running records obtained in step 4 are uploaded to a special database of a traffic administration and a taxi company for recording, online taxi abnormal track detection results are analyzed according to the regional taxi abnormal running records, city taxi running rules including statistics of taxi abnormal records of different urban areas, different time periods and different companies are extracted, and taxi drivers in different regions of a city are scored monthly, quarterly and annually on the basis.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510148076.3A CN104700646B (en) | 2015-03-31 | 2015-03-31 | A kind of taxi exception track real-time detection method based on online gps data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510148076.3A CN104700646B (en) | 2015-03-31 | 2015-03-31 | A kind of taxi exception track real-time detection method based on online gps data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104700646A true CN104700646A (en) | 2015-06-10 |
| CN104700646B CN104700646B (en) | 2016-09-14 |
Family
ID=53347717
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510148076.3A Expired - Fee Related CN104700646B (en) | 2015-03-31 | 2015-03-31 | A kind of taxi exception track real-time detection method based on online gps data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104700646B (en) |
Cited By (31)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106314438A (en) * | 2016-08-15 | 2017-01-11 | 西北工业大学 | Method and system for detecting abnormal track in driver driving track |
| CN106600068A (en) * | 2016-12-19 | 2017-04-26 | 英业达科技有限公司 | Rented vehicle driving data providing system and method |
| CN106611494A (en) * | 2015-10-21 | 2017-05-03 | 北京计算机技术及应用研究所 | Method of detecting abnormal vehicle group |
| CN106960565A (en) * | 2017-03-21 | 2017-07-18 | 合肥极友软件开发有限公司 | Taxi valuation and monitoring system based on GPS GPRS |
| CN107492063A (en) * | 2016-06-13 | 2017-12-19 | 滴滴（中国）科技有限公司 | One kind is got on the bus a recommendation process method and system |
| CN108765930A (en) * | 2018-06-26 | 2018-11-06 | 上海掌门科技有限公司 | Monitoring method of driving a vehicle and equipment |
| CN109035768A (en) * | 2018-07-25 | 2018-12-18 | 北京交通大学 | A kind of taxi detours the recognition methods of behavior |
| CN109101549A (en) * | 2018-07-09 | 2018-12-28 | 广东赛诺科技股份有限公司 | A kind of extracting method of the taxi GPS track data beyond business scope |
| CN109388409A (en) * | 2018-09-03 | 2019-02-26 | 中新网络信息安全股份有限公司 | A kind of method that Intranet disposes map tile service and path planning |
| CN109448372A (en) * | 2018-11-07 | 2019-03-08 | 南通大学 | A kind of safety monitoring and alarm method of riding |
| CN109598390A (en) * | 2017-09-29 | 2019-04-09 | 北京嘀嘀无限科技发展有限公司 | The processing method and processing unit, equipment and storage medium of stroke expense objection |
| CN109686077A (en) * | 2017-10-19 | 2019-04-26 | 株式会社日立制作所 | Traveling state of vehicle monitoring method and device |
| CN109784371A (en) * | 2018-12-14 | 2019-05-21 | 北京三快在线科技有限公司 | Net about vehicle monitoring and managing method, device and storage medium |
| CN110428193A (en) * | 2019-06-14 | 2019-11-08 | 上海中旖能源科技有限公司 | Multi-mode liquefied natural gas carrier vehicle screening technique based on track of vehicle data |
| CN110532250A (en) * | 2019-08-26 | 2019-12-03 | 腾讯科技（深圳）有限公司 | Hand over the processing method and processing device of rule data |
| CN110555992A (en) * | 2019-09-11 | 2019-12-10 | 中国矿业大学(北京) | taxi driving path information extraction method based on GPS track data |
| CN110633593A (en) * | 2018-06-21 | 2019-12-31 | 北京嘀嘀无限科技发展有限公司 | Malignant event prediction method and system |
| CN110942640A (en) * | 2019-12-04 | 2020-03-31 | 无锡华通智能交通技术开发有限公司 | Method for actively discovering suspect vehicle illegally engaged in network car booking passenger transportation |
| CN111651687A (en) * | 2020-01-10 | 2020-09-11 | 北京嘀嘀无限科技发展有限公司 | Method and device for pushing getting-on point information and method and device for pushing getting-off point information |
| CN112053163A (en) * | 2020-08-11 | 2020-12-08 | 东莞理工学院 | Method, system, terminal device and storage medium for detecting taxi fraud charging |
| CN112269940A (en) * | 2020-11-17 | 2021-01-26 | 北京嘀嘀无限科技发展有限公司 | Data processing method and device |
| US10909837B2 (en) | 2016-01-26 | 2021-02-02 | Beijing Didi Infinity Technology And Development Co., Ltd. | Systems and methods for monitoring on-route transportations |
| CN112533208A (en) * | 2019-08-27 | 2021-03-19 | 中国移动通信有限公司研究院 | Model training method, false terminal identification method and device, and electronic device |
| CN112527941A (en) * | 2020-12-18 | 2021-03-19 | 贵州黔西能源开发有限公司 | Personnel accurate positioning track reduction algorithm based on PgRouting graph calculation |
| CN112748452A (en) * | 2020-12-11 | 2021-05-04 | 上海城市交通设计院有限公司 | GPS track cleaning method based on road network data |
| CN113108806A (en) * | 2021-05-13 | 2021-07-13 | 重庆紫光华山智安科技有限公司 | Path planning method, device, equipment and medium |
| CN113111093A (en) * | 2021-03-22 | 2021-07-13 | 浙江工业大学 | Taxi driving fraud detection method based on space-time cost fusion framework |
| CN113447037A (en) * | 2021-06-04 | 2021-09-28 | 上海钧正网络科技有限公司 | Stroke yaw detection method and device |
| CN113487858A (en) * | 2021-06-25 | 2021-10-08 | 大连海事大学 | Road network data-oriented abnormal track detection method |
| CN115995151A (en) * | 2023-03-06 | 2023-04-21 | 昆明符海姚网络科技有限公司 | Network vehicle-closing abnormal behavior detection method applied to city management |
| CN117876200A (en) * | 2023-12-28 | 2024-04-12 | 北京华录高诚科技有限公司 | Multi-source data-based method for warning abnormal behavior of taxi on tour and intelligent device |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108710637B (en) * | 2018-04-11 | 2021-06-04 | 上海交通大学 | Real-time detection method for abnormal taxi track based on space-time relationship |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH08292059A (en) * | 1995-04-24 | 1996-11-05 | Nissan Motor Co Ltd | Route guiding device for vehicle |
| CN101739615A (en) * | 2009-11-30 | 2010-06-16 | 交通部公路科学研究院 | Taxi intelligent comprehensive supervision and service system |
| GB2489028A (en) * | 2011-03-17 | 2012-09-19 | David Roger Sherriff | Transportation availability broadcasting between two spatially selected catchments |
-
2015
- 2015-03-31 CN CN201510148076.3A patent/CN104700646B/en not_active Expired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH08292059A (en) * | 1995-04-24 | 1996-11-05 | Nissan Motor Co Ltd | Route guiding device for vehicle |
| CN101739615A (en) * | 2009-11-30 | 2010-06-16 | 交通部公路科学研究院 | Taxi intelligent comprehensive supervision and service system |
| GB2489028A (en) * | 2011-03-17 | 2012-09-19 | David Roger Sherriff | Transportation availability broadcasting between two spatially selected catchments |
Non-Patent Citations (2)
| Title |
|---|
| 夏英等: "实时异常轨迹检测方法及其应用", 《重庆邮电大学学报（自然科学版）》 * |
| 陈嘉等: "面向车辆监控导航的地图匹配算法研究", 《北京大学学报（自然科学版）》 * |
Cited By (46)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106611494A (en) * | 2015-10-21 | 2017-05-03 | 北京计算机技术及应用研究所 | Method of detecting abnormal vehicle group |
| US11562642B2 (en) | 2016-01-26 | 2023-01-24 | Beijing Didi Infinity Technology And Development Co., Ltd. | Systems and methods for monitoring on-route transportations |
| US10909837B2 (en) | 2016-01-26 | 2021-02-02 | Beijing Didi Infinity Technology And Development Co., Ltd. | Systems and methods for monitoring on-route transportations |
| US11257351B2 (en) | 2016-01-26 | 2022-02-22 | Beijing Didi Infinity Technology And Development Co., Ltd. | Systems and methods for monitoring on-route transportations |
| CN107492063A (en) * | 2016-06-13 | 2017-12-19 | 滴滴（中国）科技有限公司 | One kind is got on the bus a recommendation process method and system |
| CN106314438B (en) * | 2016-08-15 | 2018-09-25 | 西北工业大学 | The detection method and system of abnormal track in a kind of driver driving track |
| CN106314438A (en) * | 2016-08-15 | 2017-01-11 | 西北工业大学 | Method and system for detecting abnormal track in driver driving track |
| CN106600068A (en) * | 2016-12-19 | 2017-04-26 | 英业达科技有限公司 | Rented vehicle driving data providing system and method |
| CN106960565A (en) * | 2017-03-21 | 2017-07-18 | 合肥极友软件开发有限公司 | Taxi valuation and monitoring system based on GPS GPRS |
| CN109598390A (en) * | 2017-09-29 | 2019-04-09 | 北京嘀嘀无限科技发展有限公司 | The processing method and processing unit, equipment and storage medium of stroke expense objection |
| CN109686077B (en) * | 2017-10-19 | 2021-07-23 | 株式会社日立制作所 | Vehicle running condition monitoring method and device |
| CN109686077A (en) * | 2017-10-19 | 2019-04-26 | 株式会社日立制作所 | Traveling state of vehicle monitoring method and device |
| CN110633593A (en) * | 2018-06-21 | 2019-12-31 | 北京嘀嘀无限科技发展有限公司 | Malignant event prediction method and system |
| CN108765930A (en) * | 2018-06-26 | 2018-11-06 | 上海掌门科技有限公司 | Monitoring method of driving a vehicle and equipment |
| CN109101549B (en) * | 2018-07-09 | 2021-12-28 | 广东赛诺科技股份有限公司 | Taxi GPS track data extraction method beyond operation range |
| CN109101549A (en) * | 2018-07-09 | 2018-12-28 | 广东赛诺科技股份有限公司 | A kind of extracting method of the taxi GPS track data beyond business scope |
| CN109035768B (en) * | 2018-07-25 | 2020-11-06 | 北京交通大学 | Method for identifying taxi detour behavior |
| CN109035768A (en) * | 2018-07-25 | 2018-12-18 | 北京交通大学 | A kind of taxi detours the recognition methods of behavior |
| CN109388409A (en) * | 2018-09-03 | 2019-02-26 | 中新网络信息安全股份有限公司 | A kind of method that Intranet disposes map tile service and path planning |
| CN109448372A (en) * | 2018-11-07 | 2019-03-08 | 南通大学 | A kind of safety monitoring and alarm method of riding |
| CN109784371A (en) * | 2018-12-14 | 2019-05-21 | 北京三快在线科技有限公司 | Net about vehicle monitoring and managing method, device and storage medium |
| CN110428193B (en) * | 2019-06-14 | 2022-03-04 | 上海中旖能源科技有限公司 | Multi-mode liquefied natural gas transport vehicle screening method based on vehicle track data |
| CN110428193A (en) * | 2019-06-14 | 2019-11-08 | 上海中旖能源科技有限公司 | Multi-mode liquefied natural gas carrier vehicle screening technique based on track of vehicle data |
| CN110532250A (en) * | 2019-08-26 | 2019-12-03 | 腾讯科技（深圳）有限公司 | Hand over the processing method and processing device of rule data |
| CN110532250B (en) * | 2019-08-26 | 2023-04-07 | 腾讯科技（深圳）有限公司 | Method and device for processing traffic data |
| CN112533208A (en) * | 2019-08-27 | 2021-03-19 | 中国移动通信有限公司研究院 | Model training method, false terminal identification method and device, and electronic device |
| CN110555992A (en) * | 2019-09-11 | 2019-12-10 | 中国矿业大学(北京) | taxi driving path information extraction method based on GPS track data |
| CN110555992B (en) * | 2019-09-11 | 2021-05-28 | 中国矿业大学(北京) | Taxi driving path information extraction method based on GPS track data |
| CN110942640A (en) * | 2019-12-04 | 2020-03-31 | 无锡华通智能交通技术开发有限公司 | Method for actively discovering suspect vehicle illegally engaged in network car booking passenger transportation |
| CN111651687B (en) * | 2020-01-10 | 2021-02-26 | 北京嘀嘀无限科技发展有限公司 | Method and device for pushing getting-on point information and method and device for pushing getting-off point information |
| CN111651687A (en) * | 2020-01-10 | 2020-09-11 | 北京嘀嘀无限科技发展有限公司 | Method and device for pushing getting-on point information and method and device for pushing getting-off point information |
| CN112053163A (en) * | 2020-08-11 | 2020-12-08 | 东莞理工学院 | Method, system, terminal device and storage medium for detecting taxi fraud charging |
| CN112269940A (en) * | 2020-11-17 | 2021-01-26 | 北京嘀嘀无限科技发展有限公司 | Data processing method and device |
| CN112748452A (en) * | 2020-12-11 | 2021-05-04 | 上海城市交通设计院有限公司 | GPS track cleaning method based on road network data |
| CN112748452B (en) * | 2020-12-11 | 2022-09-23 | 上海城市交通设计院有限公司 | GPS track cleaning method based on road network data |
| CN112527941A (en) * | 2020-12-18 | 2021-03-19 | 贵州黔西能源开发有限公司 | Personnel accurate positioning track reduction algorithm based on PgRouting graph calculation |
| CN113111093B (en) * | 2021-03-22 | 2022-05-24 | 浙江工业大学 | Taxi driving fraud detection method based on space-time cost fusion framework |
| CN113111093A (en) * | 2021-03-22 | 2021-07-13 | 浙江工业大学 | Taxi driving fraud detection method based on space-time cost fusion framework |
| CN113108806A (en) * | 2021-05-13 | 2021-07-13 | 重庆紫光华山智安科技有限公司 | Path planning method, device, equipment and medium |
| CN113108806B (en) * | 2021-05-13 | 2024-01-19 | 重庆紫光华山智安科技有限公司 | Path planning method, device, equipment and medium |
| CN113447037A (en) * | 2021-06-04 | 2021-09-28 | 上海钧正网络科技有限公司 | Stroke yaw detection method and device |
| CN113487858B (en) * | 2021-06-25 | 2022-05-10 | 大连海事大学 | Road network data-oriented abnormal track detection method |
| CN113487858A (en) * | 2021-06-25 | 2021-10-08 | 大连海事大学 | Road network data-oriented abnormal track detection method |
| CN115995151A (en) * | 2023-03-06 | 2023-04-21 | 昆明符海姚网络科技有限公司 | Network vehicle-closing abnormal behavior detection method applied to city management |
| CN115995151B (en) * | 2023-03-06 | 2023-12-22 | 北京白龙马云行科技有限公司 | Network vehicle-closing abnormal behavior detection method applied to city management |
| CN117876200A (en) * | 2023-12-28 | 2024-04-12 | 北京华录高诚科技有限公司 | Multi-source data-based method for warning abnormal behavior of taxi on tour and intelligent device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104700646B (en) | 2016-09-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104700646B (en) | A kind of taxi exception track real-time detection method based on online gps data | |
| Sadeghi-Niaraki et al. | Real world representation of a road network for route planning in GIS | |
| CN101739823A (en) | Road-section average travel time measuring method suitable for low-frequency sampling | |
| Du et al. | Artificial neural network model for estimating temporal and spatial freeway work zone delay using probe-vehicle data | |
| Li et al. | Socio-demographic impacts on lane-changing response time and distance in work zone with Drivers' Smart Advisory System | |
| Chepuri et al. | Study of travel time variability using two-wheeler probe data–an Indian experience | |
| Gore et al. | Exploring credentials of Wi‐Fi sensors as a complementary transport data: an Indian experience | |
| Komol et al. | Deep transfer learning based intersection trajectory movement classification for big connected vehicle data | |
| AlRajie | Investigation of using microscopic traffic simulation tools to predict traffic conflicts between right-turning vehicles and through cyclists at signalized intersections | |
| Arnesen et al. | A forward Markov model for predicting bicycle speed | |
| Makarova et al. | Reducing the Impact of Vehicles on the Environment by the Modernization of Transport Infrastructure | |
| Choi et al. | Real-time prediction of arterial vehicle trajectories: An application to predictive route guidance for an emergency vehicle | |
| Gopalakrishnan et al. | Smart and sustainable transport: Short review of the special issue | |
| Guin et al. | Freeway Travel-Time Estimation and Forecasting [2013] | |
| Nassrullah | Development of a micro-simulation model for motorway roadworks with the use of narrow lanes and lane closure schemes | |
| Ma et al. | Finding optimal reconstruction plans for separating trucks and passenger vehicles systems at urban intersections considering environmental impacts | |
| Muniruzzaman et al. | Calibration and validation of microscopic simulation model for non-lane based heterogeneous traffic stream of developing country | |
| Bao et al. | Understanding children's cycling route selection through spatial trajectory data mining | |
| Liang et al. | Traffic impedance estimation driven by trajectories for urban roads | |
| Hussain et al. | An integrated VISSIM-SSAM approach to predicting and mitigating pedestrian crashes and severity along urban crossings | |
| Tin et al. | Measuring similarity between vehicle speed records using dynamic time warping | |
| Fazekas et al. | Detecting change in the urban road environment along a route based on traffic sign and crossroad data | |
| Adeke et al. | Prediction of Bus Travel Time on Urban Routes without Designated Bus Stops in Makurdi Town, Benue State, Nigeria | |
| Gastaldi et al. | A methodology for calibrating road link travel time functions using data from driving simulator experiments | |
| Frosch | Evaluation of Shared Space to Reduce Traffic Congestion: A case study on West Virginia University's Downtown Campus |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20160914 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |