CN106846086A - A kind of abnormal information detection method and system - Google Patents
A kind of abnormal information detection method and system Download PDFInfo
- Publication number
- CN106846086A CN106846086A CN201611182652.7A CN201611182652A CN106846086A CN 106846086 A CN106846086 A CN 106846086A CN 201611182652 A CN201611182652 A CN 201611182652A CN 106846086 A CN106846086 A CN 106846086A
- Authority
- CN
- China
- Prior art keywords
- information
- record
- screening
- granularity
- abnormal
- 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
Classifications
-
- 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
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0609—Buyer or seller confidence or verification
-
- 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
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0633—Lists, e.g. purchase orders, compilation or processing
- G06Q30/0635—Processing of requisition or of purchase orders
Abstract
The invention discloses a kind of abnormal information detection method, methods described includes:All first record informations in acquisition specified location area, and the trace information of each first record information is extracted, wherein, the specified location area is the position coordinates scope selected;Position feature value is extracted in the trace information;According to the position feature value, the second record information for meeting default similarity is screened in all first record informations;Using second record information as abnormal information.
Description
Technical field
The application is related to electronic technology field, more particularly to a kind of abnormal information detection method and system.
Background technology
Currently, network about car is gradually popularized, and user can generate order by client, and system will be according to client
The order for sending to distribute corresponding driver end for client, and driver end here is to provide the driver's correspondence for servicing by bus eventually
End equipment.Driver end can determine client position according to what system sent, so as to drive to client present position
For client provides service by bus.
Currently, some driver ends are to extract more unlawful interests, using the cheating mode of a car multiterminal, i.e., one car
It is upper to place multiple mobile phones, and multiple driver ends are installed, while true (or false) list is drawn, draw one or more false single along band
To obtain more unlawful interests.This behavior seriously compromises the interests of platform, and upset it is normal use car order, influence is flat
The security of platform.
The content of the invention
A kind of abnormal information detection method and system are the embodiment of the invention provides, being used to solve driver in the prior art makes
Faked with many driver ends single, cause the problem of platform security reduction.
Its specific technical scheme is as follows:
A kind of abnormal information detection method, methods described includes:
All first record informations in specified location area are obtained, and extracts the track of each first record information
Information, wherein, the specified location area is the position coordinates scope selected;
Position feature value is extracted in the trace information;
According to the position feature value, the second note for meeting default similarity is screened in all first record informations
Record information;
Using second record information as abnormal information.
Optionally, all first record informations in designated area are obtained, and extracts the rail in each first record information
Mark information, including:
Screening time section is transferred, wherein, the screening time section is the specified time period of the 3rd record information of screening;
The 4th record information in the screening time section is screened in the 3rd record information;
All first record informations in designated area are obtained in the 4th record information, and extracts each first note
Trace information in record information.
Optionally, position feature value is extracted in the trace information, including:
Determine time dimension and positional information dimension, wherein, when the time dimension characterizes the positioning of each anchor point
Carve, the precision of the positional information dimensional representation positional information;
According to the time dimension and the positional information dimension, position feature value is extracted in the trace information.
Optionally, according to the position feature value extracted, screened in all first record informations and meet default similar
Second record information of degree, including:
According to the position feature value extracted, the position feature value is screened according to the first granularity, met
First recording track set of the first granularity, wherein, the screening numerical value that the first granularity characterizes when carrying out screening for the first time takes
Value scope;
The first recording track set is screened according to the second granularity, is met the second of default similarity
Record information, wherein, the second granularity characterizes screening numerical value span when carrying out programmed screening, second granularity
Less than first granularity.
Optionally, further include:
The abnormal driver end of monitoring is detected as abnormal total degree, wherein, the corresponding driver end of the abnormal information is different
Normal driver end;
Judge whether the total degree exceedes predetermined threshold value;
If so, then transferring default alarm regulation, and perform the default alarm regulation;
If it is not, then continuing to monitor the abnormal driver end.
A kind of abnormal information detecting system, the system includes:
Acquisition module, for obtaining all first record informations in specified location area, and extract each described first
Trace information in record information;
Extraction module, for extracting position feature value in the trace information;
Screening module, for according to the position feature value extracted, being screened in all first record informations and meeting pre-
If the second record information of similarity, second record information is abnormal information.
Optionally, the acquisition module, specifically for:
Screening time section is transferred, the 4th record information in the screening time section is screened in the 3rd record information;
Obtain all first record informations in specified location area in the 4th record information, and extract each the
The trace information of one record information;
Wherein, the screening time section is the specified time period of the 3rd record information of screening.
Optionally, the extraction module, specifically for:
Determine time dimension and positional information dimension;
According to the time dimension and the positional information dimension, position feature value is extracted in the trace information;
Wherein, the time dimension characterizes the time of each anchor point, the positional information dimensional representation positional information
Precision.
Optionally, the screening module, specifically for:
According to the position feature value extracted, the position feature value is screened according to the first granularity, met
First recording track set of the first granularity;
The first recording track set is screened according to the second granularity, is met the second of default similarity
Record information, second granularity is less than first granularity;
Wherein, first granularity characterizes screening numerical value span when carrying out screening for the first time, described second
Angle value characterizes screening numerical value span when carrying out programmed screening.
Optionally, processing module is further included, the processing module is used for:
The abnormal driver end of monitoring is detected as abnormal total degree, wherein the abnormal driver end is the abnormal information pair
The driver end answered;
Judge whether the total degree exceedes predetermined threshold value;
If so, then transferring default alarm regulation, and perform the default alarm regulation;
If it is not, then continuing to monitor the cheating driver end.
In technical solution of the present invention, system can filter out the sequence information in screening time section in designated area,
Screened by the first granularity and the second granularity is screened, similarity order track higher is determined, finally according to similar
Determine cheating driver end in degree order track higher.And the cheating number of times according to cheating driver end is right to be carried out to driver end
Should punish, thus can with the one-to-multiple single appearance of faking in relatively low driver end, and then improve system into single-action rate, save
System cost, improves security of system.
Brief description of the drawings
Fig. 1 is a kind of abnormal information detection method flow chart in the embodiment of the present invention;
Fig. 2 is position Eigenvalue Extraction Method flow chart in the embodiment of the present invention;
Fig. 3 is a kind of abnormal information detecting system structural representation in the embodiment of the present invention.
Specific embodiment
Technical solution of the present invention is described in detail below by accompanying drawing and specific embodiment, it will be appreciated that this hair
Particular technique feature in bright embodiment and embodiment is the explanation to technical solution of the present invention, rather than restriction, not
In the case of conflict, the particular technique feature in the embodiment of the present invention and embodiment can be mutually combined.
It is as shown in Figure 1 a kind of abnormal information detection method in the embodiment of the present invention, the method includes:
S101, obtains all first record informations in specified location area, and extract each described first record information
Trace information;
S102, extracts position feature value in order track;
S103, according to position feature value, screens the second record for meeting default similarity in all first record informations
Information;
S104, using the second record information as abnormal information.
Specifically, in embodiments of the present invention, in order to solve the one-to-multiple cheating in driver end, so needing in institute
Have in the first record information and filter out similar record information.
First, system needs to get the first record information, in embodiments of the present invention, in order to ensure the first record information
The accuracy of screening, system transfers out a screening time section first, and screening time section is the finger of the 3rd record information of screening
Fix time section.
Based on screening time section, the 3rd record letter in screening time section is filtered out in the record information for receiving
Breath, such as, screening time section can be Mon-Fri, then system will just get all records of Mon-Fri
Information, has thus filtered out all record informations in screening time section.
Certainly, all it is to be located in a region due to one-to-multiple driver end, so filtered out based on screening time section
After all 3rd record informations, all second record letters in designated area are obtained in the 3rd record information for filtering out
Breath, and extract the trace information in each second record information.Here specified location area is the position coordinates selected
Scope, such as, carry out cheating detection for Pekinese driver end, then in screening, just filter out Mon-Fri Pekinese
All record informations.
With designated area in screening time section all first just can be in systems filtered out by above-mentioned method
Record information.
After the second information for filtering out needs, system will extract the trace information in each second record information,
And position feature value is extracted in trace information, the method for position feature value is extracted as shown in Fig. 2 the method includes:
S201, determines time dimension and location dimension;
System can carry out the extraction of characteristic value, the characteristic value of trace information to the trace information in the second record information first
There are two dimensions, one is time dimension, and one is positional information dimension.
System will first determine characteristic value time dimension, here time dimension such as, time dimension is set to 1 point
Clock, that is, the time of each tracing point remains into the accuracy of minute.
In addition, system will also determine a positional information dimension, positional information dimension here is by two-dimensional position information
Be converted to one-dimensional position information.Such as, using the s2 storehouses in a certain database, s2 storehouses here can be that a structuring is looked into
Language database is ask, the geography information of two dimension is converted into one-dimension information.The level of currently used s2 is 15, probable ranges
It is the region in 1000 meters, the id of generation is identical, id here is the mark of each regional extent for marking off.
S202, according to time dimension and positional information dimension, extracts position feature value in trace information.
Specifically, after the time dimension and positional information dimension determined in embodiments of the present invention, it is possible to
Corresponding position feature value is extracted in the trace information for filtering out, this feature value just contains time dimension and position letter
Breath dimension.
In embodiments of the present invention, position feature value characterizes the characteristic parameter of the wheelpath in record information, the spy
It can be the regular position coordinates of certain intervals to levy parameter, such as the position coordinates point collected according to time detecting.
After position feature value is extracted, system will twice be screened to characteristic value, first according to the spy for extracting
Value indicative, screens according to the first granularity to position characteristic value, obtains meeting the first recording track set of the first granularity.
First time screening process is preliminary screening process, can so filter out partial traces information.
After the first recording track set is filtered out, the first recording track set is sieved according to the second granularity
Choosing, is met the second record information of default similarity, and the first granularity here characterizes sieve when carrying out the first screening
Numerical value span is selected, the second granularity characterizes screening numerical value span when carrying out programmed screening.
Such as, screened using the characteristic value of coarseness for the first time, using characteristic value as key, association is affiliated to be ordered
It is single.Second fmer-granularity value is screened, and the order compared two-by-two the need for being filtered out to previous step is accurately judged successively,
Because the acquisition interval of data of being set foot-point on line is 5 seconds, judge 2 points it is similar, the packet of 5 seconds, identical group are carried out to time point
If point s2 id it is identical, it is believed that the two put it is identical.
Finally, it is assured that out that corresponding driver end whether there is cheating based on the selection result, that is to say, that be
It is no to there is one-to-multiple situation.If there is one-to-multiple situation, then the similarity of multiple order tracks is just higher, so that
Can directly judge that the driver end is practised fraud.
Further, in embodiments of the present invention, after a driver end cheating is determined, the system is also by real-time monitoring
Cheating driver end is detected the total degree of cheating, and judges whether total degree exceedes predetermined threshold value, if so, then transferring out pre-
If alarm regulation, and the default alarm regulation is performed, if it is not, then continuing to monitor cheating driver end.That is, cheating driver
The cheating number of times at end exceedes after predetermined threshold value, and system will transfer out corresponding penalty mechanism, and be performed by the penalty mechanism.
Certainly, here in the embodiment of the present invention, the predetermined threshold value and default alarm regulation can be based on system operation
It is required that to adjust.The security that system can so be ensured and the accuracy for judging cheating.
For to sum up, in embodiments of the present invention, system can filter out ordering in screening time section in designated area
Single information, is screened by the first granularity and the second granularity is screened, and determines similarity trace information higher, last root
Cheating driver end is determined according to similarity trace information higher.And the cheating number of times according to cheating driver end is come to driver end
Carry out correspondence punishment, thus can with the one-to-multiple single appearance of faking in relatively low driver end, and then improve system into single-action
Rate, has saved system cost, improves security of system.
A kind of abnormal information detection method in the correspondence embodiment of the present invention, additionally provides a kind of abnormal in the embodiment of the present invention
Information detecting system, is illustrated in figure 3 a kind of abnormal information detecting system in the embodiment of the present invention, and the system includes:
Acquisition module 301, for obtaining all first record informations in specified location area, and extract each described
Trace information in one record information;
Extraction module 302, for extracting position feature value in the trace information;
Screening module 303, for according to the position feature value extracted, being screened in all first record informations and being met
Second record information of default similarity, second record information is abnormal information.
Further, in embodiments of the present invention, the acquisition module 301, specifically for:
Screening time section is transferred, the 4th record information in the screening time section is screened in the 3rd record information;
Obtain all first record informations in specified location area in the 4th record information, and extract each the
The trace information of one record information;
Wherein, the screening time section is the specified time period of the 3rd record information of screening.
Further, in embodiments of the present invention, the extraction module 302, specifically for:
Determine time dimension and positional information dimension;
According to the time dimension and the positional information dimension, position feature value is extracted in the trace information;
Wherein, the time dimension characterizes the time of each anchor point, the positional information dimensional representation positional information
Precision.
Further, in embodiments of the present invention, the screening module 303, specifically for:
According to the position feature value extracted, the position feature value is screened according to the first granularity, met
First recording track set of the first granularity;
The first recording track set is screened according to the second granularity, is met the second of default similarity
Record information, second granularity is less than first granularity;
Wherein, first granularity characterizes screening numerical value span when carrying out screening for the first time, described second
Angle value characterizes screening numerical value span when carrying out programmed screening.
Further, in embodiments of the present invention, processing module is further included, the processing module is used for:
The abnormal driver end of monitoring is detected as abnormal total degree, wherein the abnormal driver end is the abnormal information pair
The driver end answered;
Judge whether the total degree exceedes predetermined threshold value;
If so, then transferring default alarm regulation, and perform the default alarm regulation;
If it is not, then continuing to monitor the cheating driver end.
Although having been described for the preferred embodiment of the application, one of ordinary skilled in the art once knows substantially
Creative concept, then can make other change and modification to these embodiments.So, appended claims are intended to be construed to bag
Include preferred embodiment and fall into having altered and changing for the application scope.
Obviously, those skilled in the art can carry out the essence of various changes and modification without deviating from the application to the application
God and scope.So, if these modifications of the application and modification belong to the scope of the application claim and its equivalent technologies
Within, then the application is also intended to comprising these changes and modification.
Claims (10)
1. a kind of abnormal information detection method, it is characterised in that methods described includes:
All first record informations in specified location area are obtained, and extracts the track letter of each first record information
Breath, wherein, the specified location area is the position coordinates scope selected;
Position feature value is extracted in the trace information;
According to the position feature value, the second record letter for meeting default similarity is screened in all first record informations
Breath;
Using second record information as abnormal information.
2. the method for claim 1, it is characterised in that obtain all first record informations in designated area, and carry
The trace information in each first record information is taken, including:
Screening time section is transferred, wherein, the screening time section is the specified time period of the 3rd record information of screening;
The 4th record information in the screening time section is screened in the 3rd record information;
All first record informations in designated area are obtained in the 4th record information, and extracts each first record letter
Trace information in breath.
3. the method for claim 1, it is characterised in that position feature value is extracted in the trace information, including:
Determine time dimension and positional information dimension, wherein, the time dimension characterizes the time essence for positioning each anchor point
Degree, the precision of the positional information dimensional representation positional information;
According to the time dimension and the positional information dimension, position feature value is extracted in the trace information.
4. the method for claim 1, it is characterised in that according to the position feature value extracted, in all first notes
The second record information for meeting default similarity is screened in record information, including:
According to the position feature value extracted, the position feature value is screened according to the first granularity, obtain meeting first
First recording track set of granularity, wherein, the first granularity characterizes screening numerical value value model when carrying out screening for the first time
Enclose;
The first recording track set is screened according to the second granularity, is met the second record of default similarity
Information, wherein, the second granularity characterizes screening numerical value span when carrying out programmed screening, and second granularity is less than
First granularity.
5. the method for claim 1, it is characterised in that further include:
The abnormal driver end of monitoring is detected as abnormal total degree, wherein, the corresponding driver end of the abnormal information is taken charge of for abnormal
Generator terminal;
Judge whether the total degree exceedes predetermined threshold value;
If so, then transferring default alarm regulation, and perform the default alarm regulation;
If it is not, then continuing to monitor the abnormal driver end.
6. a kind of abnormal information detecting system, it is characterised in that the system includes:
Acquisition module, for obtaining all first record informations in specified location area, and extracts each described first record
Trace information in information;
Extraction module, for extracting position feature value in the trace information;
Screening module, for according to the position feature value extracted, being screened in all first record informations and meeting default phase
Like the second record information of degree, second record information is abnormal information.
7. system as claimed in claim 6, it is characterised in that the acquisition module, specifically for:
Screening time section is transferred, the 4th record information in the screening time section is screened in the 3rd record information;
All first record informations in specified location area are obtained in the 4th record information, and extracts each first note
The trace information of record information;
Wherein, the screening time section is the specified time period of the 3rd record information of screening.
8. system as claimed in claim 6, it is characterised in that the extraction module, specifically for:
Determine time dimension and positional information dimension;
According to the time dimension and the positional information dimension, position feature value is extracted in the trace information;
Wherein, the time dimension characterizes the time of each anchor point, the precision of the positional information dimensional representation positional information.
9. system as claimed in claim 6, it is characterised in that the screening module, specifically for:
According to the position feature value extracted, the position feature value is screened according to the first granularity, obtain meeting first
First recording track set of granularity;
The first recording track set is screened according to the second granularity, is met the second record of default similarity
Information, second granularity is less than first granularity;
Wherein, first granularity characterizes screening numerical value span when carrying out screening for the first time, second granularity
Sign carries out screening numerical value span during programmed screening.
10. system as claimed in claim 6, it is characterised in that further include processing module, the processing module is used for:
The abnormal driver end of monitoring is detected as abnormal total degree, wherein the abnormal driver end is that the abnormal information is corresponding
Driver end;
Judge whether the total degree exceedes predetermined threshold value;
If so, then transferring default alarm regulation, and perform the default alarm regulation;
If it is not, then continuing to monitor the cheating driver end.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611182652.7A CN106846086A (en) | 2016-12-19 | 2016-12-19 | A kind of abnormal information detection method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611182652.7A CN106846086A (en) | 2016-12-19 | 2016-12-19 | A kind of abnormal information detection method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106846086A true CN106846086A (en) | 2017-06-13 |
Family
ID=59139398
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611182652.7A Pending CN106846086A (en) | 2016-12-19 | 2016-12-19 | A kind of abnormal information detection method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106846086A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109146506A (en) * | 2017-06-28 | 2019-01-04 | 北京嘀嘀无限科技发展有限公司 | Examine method and system, terminal device, the computer equipment of cheating order |
CN110715658A (en) * | 2019-09-16 | 2020-01-21 | 深圳市航天华拓科技有限公司 | Cheating detection method and device applied to wearable equipment and monitoring system |
-
2016
- 2016-12-19 CN CN201611182652.7A patent/CN106846086A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109146506A (en) * | 2017-06-28 | 2019-01-04 | 北京嘀嘀无限科技发展有限公司 | Examine method and system, terminal device, the computer equipment of cheating order |
CN110715658A (en) * | 2019-09-16 | 2020-01-21 | 深圳市航天华拓科技有限公司 | Cheating detection method and device applied to wearable equipment and monitoring system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Huang et al. | Transport mode detection based on mobile phone network data: A systematic review | |
CN106314438B (en) | The detection method and system of abnormal track in a kind of driver driving track | |
Biagioni et al. | Easytracker: automatic transit tracking, mapping, and arrival time prediction using smartphones | |
CN106022296B (en) | A kind of fake-licensed car detection method of the probability polymerization based on vehicle hot spot region | |
CN107204114A (en) | A kind of recognition methods of vehicle abnormality behavior and device | |
CN104077570B (en) | It is a kind of to merge radio frequency identification and the method and system of Car license recognition | |
CN107645709B (en) | Method and device for determining personnel information | |
CN107968730A (en) | The method and system that monitoring Internet of Things network interface card is stolen | |
CN106571036A (en) | Public transportation stop determination method and apparatus thereof | |
CN109635857A (en) | People's wheel paths method for monitoring and analyzing, device, equipment and storage medium | |
CN106139536A (en) | A kind of based reminding method and device | |
CN107341668A (en) | A kind of method and device for judging True Data | |
CN110060087B (en) | Abnormal data detection method, device and server | |
CN106501834A (en) | A kind of method of use mobile phone automatic decision user movement behavior | |
CN106326835A (en) | Human face data collection statistical system and method for gas station convenience store | |
CN114140300A (en) | Method, device, storage medium and terminal for identifying vehicle stop points based on GPS data | |
Ghorpade et al. | An integrated stop-mode detection algorithm for real world smartphone-based travel survey | |
CN106846086A (en) | A kind of abnormal information detection method and system | |
CN105652304B (en) | Merge the place recognition methods of multisensor | |
CN110956822B (en) | Fake-licensed vehicle identification method and device, electronic equipment and readable storage medium | |
CN101692281A (en) | Safety monitoring method, safety monitoring device and automatic teller machine (ATM) system | |
CN108447137A (en) | A kind of ETC Transaction Informations acquisition method and equipment | |
CN106781467B (en) | A kind of bus passenger based on collaborative filtering is swiped the card site information extracting method | |
CN107507413A (en) | Vehicle location Forecasting Methodology and device | |
CN108154391A (en) | It is a kind of that attention is detected and by the method and system of its quantification based on block chain |
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 |