CN107170237A - Share the abnormal detection method of bicycle in a kind of city - Google Patents
Share the abnormal detection method of bicycle in a kind of city Download PDFInfo
- Publication number
- CN107170237A CN107170237A CN201710597722.3A CN201710597722A CN107170237A CN 107170237 A CN107170237 A CN 107170237A CN 201710597722 A CN201710597722 A CN 201710597722A CN 107170237 A CN107170237 A CN 107170237A
- Authority
- CN
- China
- Prior art keywords
- bicycle
- riding
- abnormal
- frequency
- bicyclist
- 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.)
- Pending
Links
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 136
- 238000001514 detection method Methods 0.000 title claims abstract description 54
- 230000005856 abnormality Effects 0.000 claims description 14
- 238000011160 research Methods 0.000 abstract description 5
- 238000004458 analytical method Methods 0.000 abstract description 3
- 238000005516 engineering process Methods 0.000 description 5
- 238000007726 management method Methods 0.000 description 5
- 230000007423 decrease Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000000034 method Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06315—Needs-based resource requirements planning or analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/40—Business processes related to the transportation industry
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Educational Administration (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Traffic Control Systems (AREA)
Abstract
The detection method that bicycle is ridden extremely is shared in a kind of city that the present invention is provided, is ridden data according to bicycle, the exception of bicycle is detected by statistic law, wherein, the exception of bicycle includes the abnormal fn (P of riding speedn), the abnormal ff (P for duration of ridingn), the abnormal fc (P for charging of ridingn), bicyclist with car frequency of use abnormal fe (Pn), bicycle guarantee abnormal fg (Pn), the abnormal fh (P at interval of ridingn), the abnormal fi (P of bicycle positionv), the abnormal fi (P of bicycle frequency of usev) and ride mileage or number of times of riding abnormal fk (Pv).The exception that one aspect of the present invention can go out bicycle from data automatic detection of riding is ridden, and support is provided for the scheduling and management of bicycle；On the other hand respectively using bicyclist and bicycle as research object, riding and repeatedly riding from single counts riding for many traffic analyses exceptions, can reach quick, the abnormal purpose ridden of robust detection.The management of bicycle can not only be simplified, the traffic safety of bicycle can also be improved.
Description
Technical field
The abnormal detection method of bicycle is shared the present invention relates to internet arena, more particularly to a kind of city.
Background technology
Under the big Policy Background of " internet+", shared economy obtains booming, the development especially to share bicycle
It is the rapidest.From in August, 2007, Beijing starts public bicycles introducing domestic market, take government as leading, point city system
The development of the city public bicycle of one management is lukewarm always, and the operation in many cities is bad, suffers great loss.Until 2014
Since year Beijing University graduate Dai Wei foundes OFO, blowout growth is just presented in shared bicycle.End in May, 2017, according to incomplete system
Meter, shares the bicycle operation enterprise family more than 30, adds up to deliver bicycle quantity more than 10,000,000, registered user surpasses 100,000,000 people
It is secondary, it is accumulative to serve more than 1,000,000,000 person-times.The generation of shared bicycle greatly facilitates public's short distance trip and public transport is plugged into
Transfer, is handed over preferably meeting Public Traveling demand, effectively solving urban transportation trip " last one kilometer " problem, alleviation city
Positive role has been played in terms of logical congestion, structure Green Travel system, shared expanding economy has been promoted.
However, during actually operation, sharing the use also Challenge of bicycle, such as：Bicycle is by the infringement of malice
Cause to use, the too fast easy influence of bicycle riding speed ride traffic safety, bicycle taken privately by same bicyclist,
Bicycle because mileage of riding is long and caused by technology status decline etc. abnormal conditions appearance, due to bicycle injected volume and use
It is surprising, these abnormal detections can not be investigated by artificial by car by people.
The content of the invention
The abnormal detection method of bicycle is shared it is an object of the invention to provide a kind of city, existing bicycle is solved abnormal
Need manually to investigate by people by car, the cost caused is too high, can not precisely exclude abnormal defect.
In order to achieve the above object, the technical solution adopted by the present invention is：
The abnormal detection method of bicycle is shared in a kind of city that the present invention is provided, is ridden data according to bicycle, passes through statistics
Method detects the exception of bicycle, wherein, the exception of bicycle includes the abnormal fn (P of riding speedn), the abnormal ff (P for duration of ridingn)、
Ride the abnormal fc (P of chargingn), bicyclist with car frequency of use abnormal fe (Pn), bicycle guarantee abnormal fg (Pn), ride
Abnormal fh (the P at intervaln), the abnormal fi (P of bicycle positionv), the abnormal fi (P of bicycle frequency of usev) and ride and mileage or ride
Abnormal fk (the P of number of timesv)；
The data of riding of bicycle include specifically including bicyclist IDPn, bicycle Quick Response Code Pv, initial time of riding Pa, ride
Row end time Pb, the starting point P that rideso, the destination P that ridesd, the mileage P that ridese, the duration P that ridesfWith the expense of riding
Pc。
Preferably, riding speed exception fn (Pn) detection method：Once riding for bicyclist is randomly selected, according to formula
(1) riding speed of bicyclist is judged, makes the velocity anomaly of bicyclist be labeled as fn (Pn), as fn (PnDuring)=1, then
Represent that riding speed is abnormal；As fn (PnDuring)=0, then it represents that riding speed is normal：
Wherein, v is average riding speed,Tv1For low velocity threshold；Tv2For High Speed Threshold.
Preferably, ride the abnormal ff (P of durationn) detection method：Once riding for bicyclist is randomly selected, according to formula
(2) duration of riding ridden to this time judges that the duration abnormal marking for making bicyclist is ff (Pn), as ff (PnDuring)=1,
Then represent abnormal duration of riding；As ff (PnDuring)=0, normal duration of riding is represented：
Wherein, Tf1For threshold value in short-term；Tf2For it is long when threshold value.
Preferably, ride the abnormal fc (P of chargingn) detection：Sentenced according to the charging of riding that formula (3) is ridden to this time
Disconnected, the charging abnormal marking for making bicyclist is fc (Pn), as fc (Pn)=1 represents charging exception of riding；As fc (Pn)=0 is represented
Charging of riding is normal：
Wherein, CaAnd CbActual delivery expense is represented respectively and should pay expense.
Preferably, abnormal fe (P of the bicyclist with car frequency of usen) detection：Randomly select riding several times for bicyclist
Number of times is as observation frequency, in observation frequency, filters out bicyclist and rides the most identical bicycle of number of times, then by the bicycle
The ratio of number of times and observation frequency of riding is defined as the same car frequency of use of bicyclist；According to formula (4) to same car frequency of use
It is abnormal to be judged, when the same car frequency of use of bicyclist is more than threshold value T1When, make with car frequency of use abnormal marking fe (Pn)=
1, it is exception to represent the same car frequency of use of bicyclist；When the same car frequency of use of bicyclist is less than or equal to threshold value T1When, order is same
Car frequency of use abnormal marking fe (Pn)=0, the same car frequency of use for representing bicyclist is normal：
Wherein, Nu is observation frequency, represents bicyclist PnNearest n times ride；Na is represented in observation frequency using secondary
The access times of several most bicycles；Na and Nu ratio is defined as same car frequency of use.
Preferably, the abnormal fg (P of bicycle guaranteen) detection：The number of times of riding several times of bicyclist is taken as observation at random
Number of times, in observation frequency, the guarantee number of times of bicyclist and the ratio of observation frequency are defined as bicycle and report frequency for repairment, according to formula
(5) it is abnormal to bicycle guarantee to detect, it is more than threshold value T when reporting frequency for repairment2When, the abnormal marking fg (P for making bicycle report for repairmentn)=
1, represent that bicycle reports exception for repairment；It is less than or equal to threshold value T when reporting frequency for repairment2When, the abnormal fg (P for making bicycle report for repairmentn)=0, represents single
Car is reported for repairment normally：
Wherein, Nb represents the number of times that bicyclist reports for repairment in observation frequency；Na and Nu ratio is defined as reporting frequency for repairment.
Preferably, ride the abnormal fh (P at intervaln) detection：The random number of times of riding several times for taking bicycle is as observation time
Number, in observation frequency, calculates the interval of riding of bicycle, and the not good bicycle of experience of riding is filtered out by interval of riding；Ride
Interval is defined as：It is adjacent to ride twice, the previous difference ridden the end time and ride the time started next time；
Detected according to formula (6) is abnormal to interval of riding, when adjacent interval of riding twice is more than threshold value T3When, order is ridden
Between-line spacing abnormal marking fh (Pn)=1, represents the exception at interval of riding；When adjacent interval of riding twice is less than or equal to threshold value T3When,
Order is ridden, and interval is abnormal to mark fh (Pn)=0, represents the normal of interval of riding：
Wherein, Oti+1(Pn) represent bicyclist Pn i+1 time ride at the beginning of between；Dti(Pn) represent bicyclist Pn's
The end time that ith is ridden.
Preferably, the abnormal fi (P of bicycle positionv)：If the geographical position of bicycle exceeds normal geographical position, bicycle is made
Frequency of use abnormal marking fi (Pv)=1, represents that the geographical position of bicycle is abnormal；If the geographical position of bicycle is beyond normal geographical
During position, bicycle frequency of use abnormal marking fi (P are madev)=0, represents that the geographical position of bicycle is normal；
Wherein, normal geographical position is obtained particular by statistic law statistics：The frequency of occurrences exists in statistics a period of time
More than 80% geographical position needs to be updated in time as normal geographical location database, and the geographical position.
Preferably, the abnormal fi (P of bicycle frequency of usev) detection：Bicycle frequency of use is defined as within the observation period
The access times of bicycle, are detected according to formula (7) to the exception of bicycle frequency of use；If bicycle frequency of use is less than threshold value T4
When, make bicycle frequency of use abnormal marking fi (Pv)=1, represents that bicycle frequency of use is abnormal；If bicycle frequency of use be more than etc.
In threshold value T4When, make bicycle frequency of use abnormal marking fi (Pv)=0, represents that bicycle frequency of use is normal：
Wherein, Nv represents bicycle P in observation periodvAccess times；T4Value taken out to count in normal geographical position
Average access times of the sample bicycle in observation period.
Preferably, ride the abnormal fk (P of mileage or number of times of ridingv) detection, according to formula (8) to the mileage or when riding of riding
Long exception is detected：
When accumulative mileage or the accumulative duration of riding of riding of bicycle is more than threshold T5Or T6When, make bicycle mileage mark extremely
Remember fk (Pv)=1, represents ride mileage or frequency abnormality of riding；Accumulative when bicycle rides mileage or accumulative duration of riding does not surpass
Cross threshold T5Or T6When, make bicycle mileage abnormal marking make fk (Pv)=0, expression ride mileage or number of times of riding it is normal：
Wherein, Lv (Pv) and Lt (Pv) bicycle P is represented respectivelyvAccumulative mileage and the accumulative duration of riding of riding.
Compared with prior art, the beneficial effects of the invention are as follows：
The detection method that bicycle is ridden extremely is shared in a kind of city that the present invention is provided, and data are ridden as research pair using bicycle
As, by big data digging technology and statistic law, abnormal data of riding are detected, wherein, the exception of bicycle includes riding
Abnormal fn (the P of speedn), the abnormal ff (P for duration of ridingn), the abnormal fc (P for charging of ridingn), bicyclist is with car frequency of use
Abnormal fe (Pn), bicycle guarantee abnormal fg (Pn), the abnormal fh (P at interval of ridingn), the abnormal fi (P of bicycle positionv), it is single
Abnormal fi (the P of car frequency of usev) and ride mileage or number of times of riding abnormal fk (Pv).One aspect of the present invention can be from riding
The exception that data automatic detection goes out bicycle is ridden, and support is provided for the scheduling and management of bicycle；On the other hand respectively to ride
Passerby and bicycle are research object, and riding and repeatedly riding from single counts riding for many traffic analyses exceptions, can reach fast
Speed, the abnormal purpose ridden of robust detection.The management of bicycle can not only be simplified, the traffic safety of bicycle can also be improved.
Embodiment
The present invention is described in further detail below.
The present invention proposes a kind of city and shares the detection method that bicycle is ridden extremely, and data are ridden as research pair using bicycle
As by big data digging technology, being detected to abnormal data of riding, the management of bicycle can not only be simplified, can also be improved
The traffic safety of bicycle.
And the abnormal factor of bicycle includes the exception of riding speed, the exception for duration of riding, the exception for charging of riding, ridden
Person uses frequency with the exception, the exception of bicycle guarantee, the exception at interval of riding, the exception of bicycle position, bicycle of car frequency of use
The exception of the exception of rate and ride mileage or number of times of riding.
Specifically, detected by data exception to more than of riding of bicycle, wherein, the data of riding of bicycle include tool
Body includes bicyclist ID (i.e. telephone number) Pn, bicycle Quick Response Code Pv, initial time of riding Pa, ride end time Pb, ride
Starting point Po, the destination P that ridesd, the mileage P that ridese, the duration P that ridesfWith the expense P that ridesc。
Specific detecting step is as follows：
Step S1, the abnormality detection of riding speed：
The exception of bicycle riding speed is too fast or excessively slow for the riding speed of bicycle, is ridden by the exception for the people that rides
It is extremely disadvantageous to riding safety caused by row；On the other hand it is also possible to be due to that location data error is excessive or system time
Caused by error.
It is specially for the abnormal detection of riding speed：Once riding for bicyclist is randomly selected, according to formula (1) to riding
The riding speed of person is judged, makes the velocity anomaly of bicyclist be labeled as fn (Pn), as fn (PnDuring)=1, then it represents that speed of riding
Degree is abnormal；As fn (PnDuring)=0, then it represents that riding speed is normal：
Wherein, v is average riding speed,Tv1For low velocity threshold, and setting Tv1Value is 6km/h；Tv2For
High Speed Threshold, and setting Tv2Value is 15-20km/h.
Step S2, the abnormality detection for duration of riding：
The exception of duration of riding is mainly shown as overlong time or too short of riding, the original for causing duration of riding too short or long
Abnormal occupancy of cause predominantly bicycle failure and traveler etc..
The abnormal detection of duration of riding is specially：Once riding for bicyclist is randomly selected, this time is ridden according to formula (2)
Duration of riding judged, make bicyclist duration abnormal marking be ff (Pn), as ff (PnDuring)=1, then it represents that abnormal to ride
Duration；As ff (PnDuring)=0, normal duration of riding is represented：
Wherein, Tf1For threshold value in short-term, T is setf1Value is 1min；Tf2For it is long when threshold value, set Tf2Value is 180min
(=3h).
Step S3, the abnormality detection for charging of riding：
Cause charging abnormal cause of riding to be mainly system to collapse, by the abnormality detection to charging of riding, be easy to
It is follow-up to chase after expense or move back expense processing；Charging Novel presentation of riding is ride expense and the payable expense of riding of bicyclist's actual delivery
With inconsistent.
The charging abnormal marking for making bicyclist is fc (Pn), as fc (Pn)=1 represents charging exception of riding；As fc (Pn)=0
Expression charging of riding is normal.
Wherein, CaAnd CbActual delivery expense is represented respectively and should pay expense.
Step S4：Abnormality detection of the bicyclist with car frequency of use：
The number of times of riding several times of bicyclist is randomly selected as observation frequency, in observation frequency, bicyclist is filtered out
The ratio of ride number of times and the observation frequency of the bicycle, then be defined as the same car of bicyclist by the most identical bicycle of number of times of riding
Frequency of use, can detect whether bicycle is that abnormal occupancy or access times are too low according to the same car frequency of use of bicyclist；
According to actual needs, the value of observation frequency is 10-100 times.
When the same car frequency of use of bicyclist is more than certain value, make with car frequency of use abnormal marking fe (Pn)=1, table
It is exception to show the same car frequency of use of bicyclist；When the same car frequency of use of bicyclist is less than or equal to certain value, order makes with car
With frequency anomaly mark fe (Pn)=0, the same car frequency of use for representing bicyclist is normal.
Wherein, Nu is observation frequency, represents bicyclist PnNearest n times ride；Na is represented in observation frequency using secondary
The access times of several most bicycles；Na and Nu ratio is defined as same car frequency of use；T1For threshold value, desirable definite value is
0.2~0.4, the average that also according to historical data, can count the frequency of use of several bicyclists determines T1Value.
Step S5：The abnormality detection that bicycle is reported for repairment：
The exception guaranteed to keep in good repair by bicycle judges whether bicyclist is that malice is reported by mistake, takes riding several times for bicyclist secondary at random
Number is as observation frequency, in observation frequency, and the guarantee number of times of bicyclist and the ratio of observation frequency are defined as bicycle and report frequency for repairment
Rate；According to actual needs, observation frequency value is 10-100 times.
When reporting frequency for repairment more than certain value, the abnormal marking fg (P for making bicycle report for repairmentn)=1, represents that bicycle is reported for repairment different
Often；When reporting frequency for repairment less than or equal to certain value, the abnormal fg (P for making bicycle report for repairmentn)=0, represents that bicycle is reported for repairment normally.
Wherein, Nb represents the number of times that bicyclist reports for repairment in observation frequency；Na and Nu ratio is defined as reporting frequency for repairment；T2For
Threshold value, can use definite value is 0.2~0.4, also can be according to historical data, and the several bicyclists' of statistics reports the average of frequency for repairment to determine
T2Value.
Step S6：Ride the abnormality detection at interval：
The random number of times of riding several times for taking bicycle is as observation frequency, in observation frequency, calculates between the riding of bicycle
Every filtering out the not good bicycle of experience of riding by interval of riding.Interval of riding is defined as：It is adjacent to ride twice, it is previous ride
Row end time and the difference of next time started of riding；According to actual needs, observation frequency value is 10-100 times.
When adjacent interval of riding twice is more than certain value, order, which is ridden, is spaced abnormal marking fh (Pn)=1, represents to ride
The exception at interval；When adjacent interval of riding twice is less than or equal to certain value, order, which is ridden, is spaced abnormal mark fh (Pn)=0, is represented
Ride the normal of interval：
Wherein, Oti+1(Pn) represent bicyclist Pn i+1 time ride at the beginning of between；Dti(Pn) represent bicyclist Pn's
The end time that ith is ridden；T3For threshold value, its value is 0.5~2min.
Step S7：The abnormality detection of bicycle position：
When bicycle is ridden to remote locations, the frequency of use of bicycle can be influenceed, it is necessary to scheduling in time, it is therefore desirable to right
The exception of bicycle position is detected.
If the geographical position of bicycle exceeds normal geographical position, bicycle frequency of use abnormal marking fi (P are madev)=1, table
Show that the geographical position of bicycle is abnormal；If the geographical position of bicycle exceeds normal geographical position, bicycle frequency of use mark extremely is made
Remember fi (Pv)=0, represents that the geographical position of bicycle is normal.Wherein, the normal geographical position is by counting in a period of time
(such as：10 days) geographical position of the frequency of occurrences more than 80% as normal geographical location database, the geographical position need and
When be updated.
Step S8：The abnormality detection of bicycle frequency of use：
The factor of influence bicycle frequency of use mainly has：Geographical position inclined or bicycle failure excessively；Pass through the use to bicycle
Frequency carries out abnormality detection, bicycle can be dispatched and repair in time, so as to the more preferable operation of bicycle company.
Bicycle frequency of use is defined as the access times of bicycle within the observation period, and selection is observation period as needed
1-30 days.If bicycle frequency of use is less than certain value (value is counted by historical data and determined), make bicycle frequency of use abnormal
Mark fi (Pv)=1, represents that bicycle frequency of use is abnormal；If bicycle frequency of use is more than or equal to certain value, bicycle is made to use
Frequency anomaly mark fi (Pv)=0, represents that bicycle frequency of use is normal.
Wherein, Nv is represented in observation period (such as：1 day) bicycle PvAccess times；T4For threshold value, it can count normally
Average access times of the sampling bicycle in observation period are used as T in reason position4Value.
Step S9：Ride the abnormality detection of mileage or duration of riding：
When bicycle it is accumulative ride mileage or long accumulative total duration of riding when, the technology status of bicycle will decline, and go out
The probability of existing failure is also larger, and accumulative mileage and the accumulative duration of riding of riding of concern bicycle helps to lift the property of bicycle in time
Energy.When accumulative ride mileage or the accumulative duration of riding of bicycle are more than certain value (value is counted by historical data and determined), order
Bicycle mileage abnormal marking fk (Pv)=1, represents ride mileage or frequency abnormality of riding；When the accumulative mileage or tired of riding of bicycle
When meter rides duration more than certain value, bicycle mileage abnormal marking is made to make fk (Pv)=0, represents to ride mileage or rides number of times just
Often.
Wherein, Lv (Pv) and Lt (Pv) bicycle P is represented respectivelyvAccumulative mileage and the accumulative duration of riding of riding；T5And T6Table
Show threshold value, duration or accumulative can be ridden respectively as T at mileage by accumulative ride of the fault car of statistics 80%5And T6Take
Value.
Step S10：Algorithm terminates.
Relative to prior art, the present invention has the advantage that：
One is that the exception that can go out bicycle from data automatic detection of riding is ridden, and is provided for the scheduling and management of bicycle
Support.
Two be, respectively using bicyclist and bicycle as research object, to be ridden from single and many traffic analyses of statistics of repeatedly riding are different
Normal rides, and can reach quick, the abnormal purpose ridden of robust detection.
Claims (10)
1. the abnormal detection method of bicycle is shared in a kind of city, it is characterised in that：Ridden data, examined by statistic law according to bicycle
The exception of bicycle is surveyed, wherein, the exception of bicycle includes the abnormal fn (P of riding speedn), the abnormal ff (P for duration of ridingn), ride
Abnormal fc (the P of chargingn), bicyclist with car frequency of use abnormal fe (Pn), bicycle guarantee abnormal fg (Pn), interval of riding
Abnormal fh (Pn), the abnormal fi (P of bicycle positionv), the abnormal fi (P of bicycle frequency of usev) and ride mileage or number of times of riding
Abnormal fk (Pv)：
The data of riding of bicycle include specifically including bicyclist IDPn, bicycle Quick Response Code Pv, initial time of riding Pa, knot of riding
Beam time Pb, the starting point P that rideso, the destination P that ridesd, the mileage P that ridese, the duration P that ridesfWith the expense P that ridesc。
2. the abnormal detection method of bicycle is shared in a kind of city according to claim 1, it is characterised in that：Riding speed is different
Normal fn (Pn) detection method：Once riding for bicyclist is randomly selected, the riding speed of bicyclist is sentenced according to formula (1)
It is disconnected, make the velocity anomaly of bicyclist be labeled as fn (Pn), as fn (PnDuring)=1, then it represents that riding speed is abnormal；As fn (Pn)=0
When, then it represents that riding speed is normal：
Wherein, v is average riding speed,Tv1For low velocity threshold；Tv2For High Speed Threshold.
3. the abnormal detection method of bicycle is shared in a kind of city according to claim 1, it is characterised in that duration of riding
Abnormal ff (Pn) detection method：Once riding for bicyclist is randomly selected, the duration of riding ridden according to formula (2) to this time is carried out
Judge, the duration abnormal marking for making bicyclist is ff (Pn), as ff (PnDuring)=1, then it represents that abnormal duration of riding；As ff (Pn)
When=0, normal duration of riding is represented：
Wherein, Tf1For threshold value in short-term；Tf2For it is long when threshold value.
4. the abnormal detection method of bicycle is shared in a kind of city according to claim 1, it is characterised in that charging of riding
Abnormal fc (Pn) detection：Judged according to the charging of riding that formula (3) is ridden to this time, the charging abnormal marking for making bicyclist is
fc(Pn), as fc (Pn)=1 represents charging exception of riding；As fc (Pn)=0 represents that charging of riding is normal：
Wherein, CaAnd CbActual delivery expense is represented respectively and should pay expense.
5. the abnormal detection method of bicycle is shared in a kind of city according to claim 1, it is characterised in that the same car of bicyclist
Abnormal fe (the P of frequency of usen) detection：The number of times of riding several times of bicyclist is randomly selected as observation frequency, in observation time
In number, filter out bicyclist and ride the most identical bicycle of number of times, then by the ratio of ride number of times and the observation frequency of the bicycle
It is defined as the same car frequency of use of bicyclist；The exception of same car frequency of use is judged according to formula (4), it is same as bicyclist
Car frequency of use is more than threshold value T1When, make with car frequency of use abnormal marking fe (Pn)=1, represents that the same car of bicyclist uses frequency
Rate is abnormal；When the same car frequency of use of bicyclist is less than or equal to threshold value T1When, make with car frequency of use abnormal marking fe (Pn)=
0, the same car frequency of use for representing bicyclist is normal：
Wherein, Nu is observation frequency, represents bicyclist PnNearest n times ride；Na represents that access times are most in observation frequency
The access times of many bicycles；Na and Nu ratio is defined as same car frequency of use.
6. the abnormal detection method of bicycle is shared in a kind of city according to claim 1, it is characterised in that bicycle guarantee
Abnormal fg (Pn) detection：The number of times of riding several times of bicyclist is taken as observation frequency, in observation frequency, bicyclist's at random
The ratio of guarantee number of times and observation frequency is defined as bicycle and reports frequency for repairment, is detected according to formula (5) is abnormal to bicycle guarantee, when
Frequency is reported for repairment more than threshold value T2When, the abnormal marking fg (P for making bicycle report for repairmentn)=1, represents that bicycle reports exception for repairment；When reporting frequency for repairment
Less than or equal to threshold value T2When, the abnormal fg (P for making bicycle report for repairmentn)=0, represents that bicycle is reported for repairment normally：
Wherein, Nb represents the number of times that bicyclist reports for repairment in observation frequency；Na and Nu ratio is defined as reporting frequency for repairment.
7. the abnormal detection method of bicycle is shared in a kind of city according to claim 1, it is characterised in that interval of riding
Abnormal fh (Pn) detection：The random number of times of riding several times for taking bicycle is as observation frequency, in observation frequency, calculates bicycle
Ride interval, the not good bicycle of experience of riding is filtered out by interval of riding；Interval of riding is defined as：It is adjacent twice to ride,
The difference of previous ride end time and next time started of riding；
Detected according to formula (6) is abnormal to interval of riding, when adjacent interval of riding twice is more than threshold value T3When, between order is ridden
Every abnormal marking fh (Pn)=1, represents the exception at interval of riding；When adjacent interval of riding twice is less than or equal to threshold value T3When, order is ridden
Between-line spacing mark fh (P extremelyn)=0, represents the normal of interval of riding：
Wherein, Oti+1(Pn) represent bicyclist Pn i+1 time ride at the beginning of between；Dti(Pn) represent the i-th of bicyclist Pn
The secondary end time ridden.
8. the abnormal detection method of bicycle is shared in a kind of city according to claim 1, it is characterised in that bicycle position
Abnormal fi (Pv)：If the geographical position of bicycle exceeds normal geographical position, bicycle frequency of use abnormal marking fi (P are madev)=1,
Represent that the geographical position of bicycle is abnormal；If the geographical position of bicycle exceeds normal geographical position, make bicycle frequency of use abnormal
Mark fi (Pv)=0, represents that the geographical position of bicycle is normal；
Wherein, normal geographical position is obtained particular by statistic law statistics：The frequency of occurrences is 80% in statistics a period of time
Geographical position above needs to be updated in time as normal geographical location database, and the geographical position.
9. the abnormal detection method of bicycle is shared in a kind of city according to claim 1, it is characterised in that bicycle uses frequency
Abnormal fi (the P of ratev) detection：Bicycle frequency of use is defined as the access times of bicycle within the observation period, right according to formula (7)
The exception of bicycle frequency of use is detected；If bicycle frequency of use is less than threshold value T4When, make bicycle frequency of use abnormal marking
fi(Pv)=1, represents that bicycle frequency of use is abnormal；If bicycle frequency of use is more than or equal to threshold value T4When, make bicycle frequency of use different
Often mark fi (Pv)=0, represents that bicycle frequency of use is normal：
Wherein, Nv represents bicycle P in observation periodvAccess times；T4Value for count sampled in normal geographical position it is single
Average access times of the car in observation period.
10. the abnormal detection method of bicycle is shared in a kind of city according to claim 1, it is characterised in that mileage of riding
Or the abnormal fk (P for number of times of ridingv) detection, the exception of ride mileage or duration of riding is detected according to formula (8)：
When accumulative mileage or the accumulative duration of riding of riding of bicycle is more than threshold T5Or T6When, make bicycle mileage abnormal marking fk
(Pv)=1, represents ride mileage or frequency abnormality of riding；When accumulative mileage or the accumulative duration of riding of riding of bicycle is no more than door
Limit value T5Or T6When, make bicycle mileage abnormal marking make fk (Pv)=0, expression ride mileage or number of times of riding it is normal：
Wherein, Lv (Pv) and Lt (Pv) bicycle P is represented respectivelyvAccumulative mileage and the accumulative duration of riding of riding.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710597722.3A CN107170237A (en) | 2017-07-20 | 2017-07-20 | Share the abnormal detection method of bicycle in a kind of city |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710597722.3A CN107170237A (en) | 2017-07-20 | 2017-07-20 | Share the abnormal detection method of bicycle in a kind of city |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107170237A true CN107170237A (en) | 2017-09-15 |
Family
ID=59817937
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710597722.3A Pending CN107170237A (en) | 2017-07-20 | 2017-07-20 | Share the abnormal detection method of bicycle in a kind of city |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107170237A (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107742243A (en) * | 2017-10-18 | 2018-02-27 | 深圳市沃特沃德股份有限公司 | Shared bicycle labeling method and device |
| CN108229700A (en) * | 2017-12-30 | 2018-06-29 | 佛山潮伊汇服装有限公司 | Shared bicycle lubricated maintenance detection method and shared cell |
| CN108683732A (en) * | 2018-05-14 | 2018-10-19 | 广东高标电子科技有限公司 | A kind of failure management method of shared bicycle |
| CN108848458A (en) * | 2018-03-30 | 2018-11-20 | 汪立梅 | A kind of real-time position information acquisition method, device and its system |
| CN108877202A (en) * | 2018-08-24 | 2018-11-23 | 北京轻享科技有限公司 | A kind of monitoring method of hackney vehicle, device, vehicle and calculate equipment |
| CN108921403A (en) * | 2018-06-15 | 2018-11-30 | 杭州后博科技有限公司 | It is ridden when a kind of shared bicycle is without usage record recognition methods and system |
| CN108961132A (en) * | 2018-07-23 | 2018-12-07 | 中国联合网络通信集团有限公司 | Private accounts for the detection method and device of shared bicycle behavior |
| CN108985789A (en) * | 2018-06-15 | 2018-12-11 | 杭州后博科技有限公司 | A kind of shared bicycle is illegally occupied recognition methods and system |
| CN109450850A (en) * | 2018-09-26 | 2019-03-08 | 深圳壹账通智能科技有限公司 | Auth method, device, computer equipment and storage medium |
| CN110033303A (en) * | 2019-01-30 | 2019-07-19 | 阿里巴巴集团控股有限公司 | A kind of recognition methods that vehicle is ridden, device and equipment |
| CN110363306A (en) * | 2018-04-04 | 2019-10-22 | 韩巧珍 | Shared bicycle method for diagnosing faults |
| CN110543503A (en) * | 2019-09-06 | 2019-12-06 | 天津农学院 | data mining method aiming at fixed pile position sharing bicycle riding rule and abnormal behavior |
| US10950070B2 (en) | 2018-09-13 | 2021-03-16 | International Business Machines Corporation | Malfunction detection of shared vehicles |
| CN116701914A (en) * | 2023-06-21 | 2023-09-05 | 广东星云开物科技股份有限公司 | Hardware equipment abnormal use identification method, device, storage device and system |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101814214A (en) * | 2009-02-20 | 2010-08-25 | 上海永久自行车有限公司 | Car rental system with abnormality prompt function and abnormality prompt method thereof |
| CN102141477A (en) * | 2010-01-29 | 2011-08-03 | 上海永久自行车有限公司 | Bicycle state automatic detection system and method and bicycle locking control device |
| CN105809833A (en) * | 2016-02-24 | 2016-07-27 | 北京易代步科技有限公司 | Bicycle management method and system |
| CN106251497A (en) * | 2016-08-18 | 2016-12-21 | 浪潮集团有限公司 | City free bicycle lease management system |
| CN106530057A (en) * | 2016-11-24 | 2017-03-22 | 吴凡 | Public apparatus management method and system based on mobile phone client |
| CN106652229A (en) * | 2016-11-29 | 2017-05-10 | 北京千方科技股份有限公司 | Method and system for depositing and extracting public bicycle |
| CN106741396A (en) * | 2016-12-28 | 2017-05-31 | 北京拜克洛克科技有限公司 | A kind of intelligent bicycle and intelligent bicycle control system |
| CN106845877A (en) * | 2017-04-10 | 2017-06-13 | 上海量明科技发展有限公司 | Judge method, system, client and the shared vehicle of shared vehicle performance |
| CN206331584U (en) * | 2017-01-03 | 2017-07-14 | 上海量明科技发展有限公司 | The system of the shared vehicles use state of monitoring |
-
2017
- 2017-07-20 CN CN201710597722.3A patent/CN107170237A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101814214A (en) * | 2009-02-20 | 2010-08-25 | 上海永久自行车有限公司 | Car rental system with abnormality prompt function and abnormality prompt method thereof |
| CN102141477A (en) * | 2010-01-29 | 2011-08-03 | 上海永久自行车有限公司 | Bicycle state automatic detection system and method and bicycle locking control device |
| CN105809833A (en) * | 2016-02-24 | 2016-07-27 | 北京易代步科技有限公司 | Bicycle management method and system |
| CN106251497A (en) * | 2016-08-18 | 2016-12-21 | 浪潮集团有限公司 | City free bicycle lease management system |
| CN106530057A (en) * | 2016-11-24 | 2017-03-22 | 吴凡 | Public apparatus management method and system based on mobile phone client |
| CN106652229A (en) * | 2016-11-29 | 2017-05-10 | 北京千方科技股份有限公司 | Method and system for depositing and extracting public bicycle |
| CN106741396A (en) * | 2016-12-28 | 2017-05-31 | 北京拜克洛克科技有限公司 | A kind of intelligent bicycle and intelligent bicycle control system |
| CN206331584U (en) * | 2017-01-03 | 2017-07-14 | 上海量明科技发展有限公司 | The system of the shared vehicles use state of monitoring |
| CN106845877A (en) * | 2017-04-10 | 2017-06-13 | 上海量明科技发展有限公司 | Judge method, system, client and the shared vehicle of shared vehicle performance |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107742243A (en) * | 2017-10-18 | 2018-02-27 | 深圳市沃特沃德股份有限公司 | Shared bicycle labeling method and device |
| WO2019075833A1 (en) * | 2017-10-18 | 2019-04-25 | 深圳市沃特沃德股份有限公司 | Shared bicycle marking method and apparatus |
| CN107742243B (en) * | 2017-10-18 | 2021-02-02 | 深圳市沃特沃德股份有限公司 | Shared bicycle marking method and device |
| CN108229700A (en) * | 2017-12-30 | 2018-06-29 | 佛山潮伊汇服装有限公司 | Shared bicycle lubricated maintenance detection method and shared cell |
| CN108848458A (en) * | 2018-03-30 | 2018-11-20 | 汪立梅 | A kind of real-time position information acquisition method, device and its system |
| CN110363306A (en) * | 2018-04-04 | 2019-10-22 | 韩巧珍 | Shared bicycle method for diagnosing faults |
| CN108683732A (en) * | 2018-05-14 | 2018-10-19 | 广东高标电子科技有限公司 | A kind of failure management method of shared bicycle |
| CN108921403A (en) * | 2018-06-15 | 2018-11-30 | 杭州后博科技有限公司 | It is ridden when a kind of shared bicycle is without usage record recognition methods and system |
| CN108985789A (en) * | 2018-06-15 | 2018-12-11 | 杭州后博科技有限公司 | A kind of shared bicycle is illegally occupied recognition methods and system |
| CN108961132A (en) * | 2018-07-23 | 2018-12-07 | 中国联合网络通信集团有限公司 | Private accounts for the detection method and device of shared bicycle behavior |
| CN108877202B (en) * | 2018-08-24 | 2020-12-15 | 北京轻享科技有限公司 | Monitoring method and device for taxi, vehicle and computing equipment |
| CN108877202A (en) * | 2018-08-24 | 2018-11-23 | 北京轻享科技有限公司 | A kind of monitoring method of hackney vehicle, device, vehicle and calculate equipment |
| US10950070B2 (en) | 2018-09-13 | 2021-03-16 | International Business Machines Corporation | Malfunction detection of shared vehicles |
| CN109450850A (en) * | 2018-09-26 | 2019-03-08 | 深圳壹账通智能科技有限公司 | Auth method, device, computer equipment and storage medium |
| CN109450850B (en) * | 2018-09-26 | 2022-10-11 | 深圳壹账通智能科技有限公司 | Identity authentication method, identity authentication device, computer equipment and storage medium |
| CN110033303A (en) * | 2019-01-30 | 2019-07-19 | 阿里巴巴集团控股有限公司 | A kind of recognition methods that vehicle is ridden, device and equipment |
| CN110033303B (en) * | 2019-01-30 | 2023-12-12 | 创新先进技术有限公司 | Vehicle riding identification method, device and equipment |
| CN110543503A (en) * | 2019-09-06 | 2019-12-06 | 天津农学院 | data mining method aiming at fixed pile position sharing bicycle riding rule and abnormal behavior |
| CN110543503B (en) * | 2019-09-06 | 2022-04-26 | 天津农学院 | Data mining method aiming at fixed pile position sharing bicycle riding rule and abnormal behavior |
| CN116701914A (en) * | 2023-06-21 | 2023-09-05 | 广东星云开物科技股份有限公司 | Hardware equipment abnormal use identification method, device, storage device and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107170237A (en) | Share the abnormal detection method of bicycle in a kind of city | |
| CN108961747B (en) | A kind of urban road traffic state information extracting method under incomplete bayonet data qualification | |
| CN107798876B (en) | Road traffic abnormal jam judging method based on event | |
| CN101587643B (en) | Identification method of fake-licensed cars | |
| CN106297333B (en) | A kind of green wave appraisal procedure of main line for vehicle record of being made a slip of the tongue based on intersection | |
| CN105336162B (en) | The method for early warning and early warning system of vehicle abnormality aggregation | |
| CN109147330A (en) | A kind of congestion recognition methods and device | |
| CN203552313U (en) | Highway rapid supervision non-parking charging system | |
| CN107705238B (en) | Transportation supervision system based on position and bayonet track comparison and supervision method thereof | |
| CN104778821B (en) | Automatic alarm system and method for transportation equipment | |
| CN110097249A (en) | A kind of bus passenger flow monitoring analysis system and its method | |
| CN102945616B (en) | A kind of acquisition method of bus station information | |
| WO2011060727A1 (en) | Road traffic condition predicting method and device thereof | |
| CN107240289A (en) | A kind of bus routes optimum management method and system | |
| CN107180270A (en) | Passenger flow forecasting and system | |
| CN101814202A (en) | Vehicle toll supervision method | |
| CN106297304A (en) | A kind of based on MapReduce towards the fake-licensed car recognition methods of extensive bayonet socket data | |
| WO2018176191A1 (en) | Method and apparatus for identifying vehicle with fake registration plate | |
| CN106651732A (en) | Highway different-vehicle card-change toll-dodging vehicle screening method and system | |
| CN107329977A (en) | A kind of false-trademark car postsearch screening method based on probability distribution | |
| CN107293113A (en) | The computational methods and device of a kind of region congestion delay index | |
| CN102625083B (en) | Method for constructing video monitoring network | |
| CN104809870A (en) | Viaduct entrance ramp traffic congestion grade estimation method | |
| CN109344243A (en) | A kind of real-time stream calculation alarm analysis method and system | |
| CN107146413A (en) | A kind of smart city service platform |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170915 |
|
| RJ01 | Rejection of invention patent application after publication |