CN106557955A - Net about car exception order recognition methodss and system - Google Patents
Net about car exception order recognition methodss and system Download PDFInfo
- Publication number
- CN106557955A CN106557955A CN201611072064.8A CN201611072064A CN106557955A CN 106557955 A CN106557955 A CN 106557955A CN 201611072064 A CN201611072064 A CN 201611072064A CN 106557955 A CN106557955 A CN 106557955A
- Authority
- CN
- China
- Prior art keywords
- order
- order data
- data
- abnormal
- passenger
- 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
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0207—Discounts or incentives, e.g. coupons or rebates
- G06Q30/0225—Avoiding frauds
-
- 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
- G06Q30/018—Certifying business or products
- G06Q30/0185—Product, service or business identity fraud
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- Marketing (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Theoretical Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a kind of net about car exception order recognition methodss and system, using inside call a taxi Data Detection brush list suspicion order while, inter-trade data are based on also, driver and/or passenger are obtained from inter-trade data base detects whether the supplementary detection data that there is abnormal order for supplement, secondary judgement is carried out to order data from one or more dimensions according to the supplementary data, anomalous identification is carried out to order data；And classification of risks can also be carried out to order data based on various dimensions.It is of the invention to carry out from many aspects brushing single identification, the single accuracy of identification specialty brush is effectively improved, and is avoided as much as judging behavior of normally calling a taxi by accident, retain preferable Consumer's Experience.
Description
Technical field
The present invention relates to net about car order identification field, the about car exception order recognition methodss of more particularly to a kind of net, with
And a kind of net about car exception order identifying system.
Background technology
In recent years, due to the convenient and practicality of net about car, net about car scale is expanded rapidly, but but also exposes more and more
Problem.In the company that O2O fields are ridden on a horse to enclose at this stage, various " preferential " " subsidy " is released in order to compete for market share, it is many
The lofty stance that individual trip taxi taking platform relies on one day to burn several ten million dollars, while results user, order high-volume increase,
There are the operations risks such as a large number of users brush list, forgery, arbitrage.Become nearly fertile soil being most keen to by Arbitrageur for 2 years with garage's industry.
It is limited with garage's industry factor data dimension, and because of the behavior of various brush list data falsifications for occurring on the market, use car
Industry relies only on its own data base to detect the mode of brush single act, and limitation is larger, it is impossible to identify brush single file exactly
For, it is often more important that, it is also possible to there is the behavior of normally calling a taxi that real user was killed, manslaughtered to more serious mistake.Therefore, use garage
Outside industry urgent need, inter-trade data are verified to user's behavior of calling a taxi, and differentiate whether driver and passenger are malice brush single files
For.
The content of the invention
The present invention goal of the invention be：For above-mentioned problem, there is provided net about car exception order recognition methodss and
System, based on inter-trade data, effectively improves the single accuracy of identification specialty brush.
The technical solution used in the present invention is as follows：
Scheme one
The present invention proposes a kind of about car exception order recognition methodss of net, the method comprising the steps of：
S1, acquisition order data, obtain order data to be detected from taxi taking platform data base；
S2, abnormal preliminary identification, are tentatively judged to the order data, are recognized whether the sequence information in order data deposits
In exception, and score value is given for the sequence information, be designated as the first score value；
S3, obtain inter-trade data, obtain from inter-trade data base target driver and/or target passenger for supplementing detection
With the presence or absence of the supplementary detection data of abnormal order；
S4, abnormal secondary identification, carry out secondary judgement according to the supplementary detection data to the order data, order described in identification
Sequence information in forms data is with the presence or absence of exception, and gives score value for the sequence information, is designated as the second score value；
S5, judgement brush single act, are weighted summation to first score value and the second score value of identical sequence information, and unite
The general comment score value of all sequence informations in single order data is counted, judges that the order data is according to the general comment score value of order data
It is no for abnormal order.
Based on above-mentioned embodiment, further, in abnormal secondary identification, by the sequence information in order data by dimension
Degree is classified, and carries out secondary judgement to the order data from multiple dimensions according to the supplementary detection data.
Accordingly, when brush single act is judged, the dimension for counting the sequence information of each dimension in single order data is commented
Multiple dimension score value weighted sums are obtained the general comment score value by score value, judge that this is ordered according to the general comment score value of order data
Whether forms data is abnormal order, and the risk classifications of abnormal order are judged according to each dimension score value.
Based on any of the above-described embodiment, further, in step S1, after obtaining the order data, will be described
The sequence information of order data is stored in History Order data base, and the sequence information includes order initial data and according to order
The detection parameter for abnormal judgement that initial data is calculated.
In step s 5, if it is determined that the order data is abnormal order, also which is identified, and renewal is ordered to history
In single database.
Preferably, methods described also includes step S6：From History Order data base, what acquisition was associated with target driver
Driver's order data, and the passenger's order data being associated with target passenger, and be identified as in calculating driver's order data different
The ratio of normal order, and the doubtful brush digital ratio equation of abnormal order in passenger's order data, is identified as, according to doubtful brush digital ratio equation
Brush single act judgement is carried out to the current order data of target driver or target passenger.
Scheme two
The invention allows for a kind of net about car exception order identifying system, the system includes：
Order data acquiring unit, for obtaining order data to be detected from taxi taking platform data base；
Abnormal preliminary recognition unit, for tentatively being judged to the order data, recognizes the sequence information in order data
With the presence or absence of exception, and score value is given for the sequence information, be designated as the first score value；
Inter-trade data capture unit, for obtain from inter-trade data base target driver and/or target passenger for mending
Fill the supplementary detection data for detecting whether there is abnormal order；
Abnormal secondary recognition unit, for secondary judgement is carried out to the order data according to the supplementary detection data, identification
Sequence information in the order data is with the presence or absence of exception, and gives score value for the sequence information, is designated as the second score value；
Brush single act identifying unit, for first score value and the second score value of identical sequence information are weighted and are asked
With, and the general comment score value of all sequence informations in single order data is counted, judge that this is ordered according to the general comment score value of order data
Whether forms data is abnormal order.
Further, when the preliminary recognition unit of the exception is tentatively judged to the order data, by order data
In sequence information classified by dimension, two are carried out to the order data from multiple dimensions according to the supplementary detection data
Secondary judgement.
The brush single act identifying unit counts the order of each dimension in single order data when brush single act is judged
Multiple dimension score value weighted sums are obtained the general comment score value, according to the general comment of order data by the dimension score value of information
Whether score value judges the order data as abnormal order, and the risk classifications of abnormal order are judged according to each dimension score value.
Further, the system may also include History Order data base, and the order data acquiring unit obtains described
After order data, the sequence information of the order data is stored in History Order data base, the sequence information includes order
Initial data and the detection parameter for abnormal judgement calculated according to order initial data.If the brush single act identifying unit
Judge that the order data is abnormal order, also need to be identified which, and update in History Order data base.
Preferably, the system may also include the single comprehensive assessment unit of brush, and the brush list comprehensive assessment unit is ordered from history
In single database, the driver's order data being associated with target driver, and the passenger's order numbers being associated with target passenger are obtained
According to, and the ratio of abnormal order in calculating driver's order data, is identified as, and in passenger's order data, it is identified as abnormal ordering
The current order data of target driver or target passenger are carried out brush single file according to doubtful brush digital ratio equation by single doubtful brush digital ratio equation
To judge.
In sum, as a result of above-mentioned technical proposal, the invention has the beneficial effects as follows：
Net proposed by the invention about car exception order recognition methodss and system, compared to the brush list of existing identification taxi-hailing software
Technology, while using taxi taking platform Data Detection brush list suspicion order, also based on inter-trade data, is tieed up using location track
Degree, relation loop dimension, communication behavior dimension and cat pond support many detection dimensions such as card dimension to calculate the score value of sequence information, root
Judge that order data has the risk class of brush single act according to default score criteria, carry out from many aspects brushing single identification.The present invention
Focus on and lift the single accuracy of identification brush, professional brush single act is recognized from data, and it is true to be avoided as much as erroneous judgement
The behavior of normally calling a taxi of real client, retains preferable Consumer's Experience.
Description of the drawings
Examples of the present invention will be described by way of reference to the accompanying drawings, wherein：
Fig. 1 is the schematic flow sheet of net about car exception order recognition methodss in the present invention.
Fig. 2 is the structural representation of net about car exception order identifying system in the present invention.
Specific embodiment
All features disclosed in this specification, or disclosed all methods or during the step of, except mutually exclusive
Feature and/or step beyond, can combine by any way.
This specification（Including any accessory claim, summary）Disclosed in any feature, unless specifically stated otherwise,
Replaced by other equivalent or alternative features with similar purpose.I.e., unless specifically stated otherwise, each feature is a series of
An example in equivalent or similar characteristics.
It should be noted that, heretofore described taxi taking platform data base refers generally to the net about self-built data of car trip company
Storehouse；It is and heretofore described inter-trade data base includes operator database and social platform database, described inter-trade
Data base is the data base of non-net about car trip company, is the data base of the relevant information with target driver or target passenger,
The relevant information is mainly the location information of target driver or target passenger, displacement information, mutual relation information and logical
Letter behavioural information etc., such as operator database of the Virtual network operator such as China Telecom, China Mobile, CHINAUNICOM, and such as QQ,
The binding such as wechat, microblogging has telephone number, includes the various social platform numbers of the information such as positioning, displacement, social activity, circle of friends
According to storehouse.When using social platform data base, using its corresponding social activity account number of the telephone number searching of driver and passenger, and
Extract the object time location information and displacement information, and verification driver whether be friend relation with passenger, whether communicate row
To realize carrying out anomalous identification to order data from various dimensions using social platform data base with this.The present invention is mainly with operation
Quotient data storehouse come illustrate the net based on inter-trade data base about car exception order recognition methodss and system specific embodiment, utilize
Social platform data base and other inter-trade data bases can be obtained in the same manner come the specific embodiment for recognizing abnormal order.
（One）Net about car exception order recognition methodss
As shown in figure 1, the present invention proposes a kind of about car exception order recognition methodss of net, methods described at least includes step：
S1, acquisition order data, obtain order data to be detected from taxi taking platform data base；
S2, abnormal preliminary identification, are tentatively judged to the order data, are recognized whether the sequence information in order data deposits
In exception, and score value is given for the sequence information, be designated as the first score value；
S3, obtain inter-trade data, obtain from inter-trade data base target driver and/or target passenger for supplementing detection
With the presence or absence of the supplementary detection data of abnormal order；
S4, abnormal secondary identification, carry out secondary judgement according to the supplementary detection data to the order data, order described in identification
Sequence information in forms data is with the presence or absence of exception, and gives score value for the sequence information, is designated as the second score value；
S5, judgement brush single act, are weighted summation to first score value and the second score value of identical sequence information, and unite
The general comment score value of all sequence informations in single order data is counted, judges that the order data is according to the general comment score value of order data
It is no for abnormal order.Further, the general comment score value that can also pass through abnormal order carries out risk stratification to which.
Further, may also include step S6：From History Order data base, the driver being associated with target driver is obtained
Order data, and the passenger's order data being associated with target passenger, and in calculating driver's order data, it is identified as abnormal ordering
Single ratio, and the doubtful brush digital ratio equation of abnormal order in passenger's order data, is identified as, according to doubtful brush digital ratio equation to mesh
The current order data of mark driver or target passenger carry out brush single act judgement, to realize that the brush list to driver end and passenger end is disliked
Doubting carries out comprehensive assessment, and the comprehensive assessment result can also be fed back to taxi taking platform, be easy to public affairs of calling a taxi by output integrated assessment result
Single identification is more accurately brushed by department, identifies the brush single act of specialty, and reduces erroneous judgement as far as possible, improves Consumer's Experience.
Further, in step S1, after the order data is obtained, also the order of the order data can be believed
Breath is stored in History Order data base, and the sequence information generally comprises order initial data and calculated according to order initial data
For the abnormal detection parameter for judging.
The order initial data includes but is not limited to passenger loading base station location information, passenger getting off car architecture letter
Breath, driver end telephone number, passenger end telephone number, order generation time, passenger select car time, passenger to select car vehicle, driver
Time in place, stroke time started, stroke end time, driver's order distance, the order amount of money, charging duration and charged mileage etc.
Deng.
In step S1, also its operator can be judged by the telephone number of the telephone number at driver end and passenger end,
It is easy to from corresponding operator database transfer the relevant information of the driver or passenger.
Sequence information is extracted from order data, is calculated for the abnormal detection parameter for judging according to order initial data,
The general detection parameter includes but is not limited to parameter 1_A to parameter 1_L.
The ratio of parameter 1_A, the positional distance of passenger getting on/off and charged mileage.Wherein, the position of passenger getting on/off away from
From being calculated by passenger loading base station location information and passenger getting off car base station information.
Parameter 1_B, order speed per hour.Can pass through driver's order distance divided by order generate time to driver's time in place when
Between interval being calculated.
Parameter 1_C, driving speed per hour.Can be obtained divided by charging duration calculation by charged mileage.
Parameter 1_D, unit interval price.Can be obtained divided by charging duration calculation by the order amount of money.
Driving speed per hour between parameter 1_E, the two neighboring order in driver end.Can be by the adjacent two single location interval in driver end
Divided by the adjacent two single time interval in the driver end, the adjacent two single location interval in the driver end can terminate for an order on driver end
To the running distance started to next order, the adjacent two single time interval in the driver end can be the stroke of an order on driver end
The time difference of end time to the stroke time started of next order.
In parameter 1_F, the order data of the driver, the accounting of each operator passenger.
In parameter 1_G, the order data of the driver, whether passenger has the order behavior as driver identification, for judging
Multiple drivers mutually brush list.
In parameter 1_H, the order data of the driver, passenger has the accounting of order behavior.
In parameter 1_I, the order data of the driver, passenger loading base station location information is identical with passenger getting off car base station information
Or ratio of its spacing in predeterminable range threshold value.As between passenger loading base station location information and passenger getting off car base station information
Distance also assert that passenger getting on/off position is identical within 100 meters, then.
Driving speed per hour between parameter 1_J, the two neighboring order in passenger end.Can be by the adjacent two single location interval in passenger end
Divided by the adjacent two single time interval in the passenger end, the adjacent two single location interval in the passenger end can terminate for an order on passenger end
To the running distance started to next order, the adjacent two single time interval in the passenger end can be the stroke of an order on passenger end
The time difference of end time to the stroke time started of next order.
Farthest architecture distance in parameter 1_K, passenger's day range of activity, i.e. passenger end day order.
Parameter 1_L, passenger's day total kilometrage number.
Further, above-mentioned parameter 1_A is being calculated to parameter 1_L, order data can detected parameter with each
Association is stored in History Order data base, so as to follow-up abnormality detection.
Step S2, abnormal preliminary identification, are tentatively judged to the order data by order abnormality detection model, right
Abnormal order carries out preliminary identification.
The present invention is based on statistical analysiss, the distribution situation of each detection parameter in analysis of history order data, by distribution number
Concentrated part according in is considered as normal order colony, to being considered as doubtful brush simple group body away from concentrated part, bigger away from distance,
Single risk is brushed then higher.Therefore, the present invention is first arranged to some detection parameters according to certain rules, forms detection parameter number
Group, and outlier threshold is set, special instruction, the bound of parameters in the not necessarily normal order of the outlier threshold
Threshold value.For, outside outlier threshold, being labeled as abnormal information.What is normal order to not initiative recognition of the invention, is passed through
The distribution situation of historical data, portrays the behavioural habits of driver and passenger, filters out the abnormal letter differed greatly with main foreigner tourists
Breath.The advantage being so designed that is：If simply having some exceptions in order data, but it is believed that in the reasonable scope,
Then it is not determined to the presence of brush single act.Further, the present invention can also possess learning behavior ability, in multiple anomalous identification
Afterwards, whether rationally to verify set outlier threshold, if what is arranged is too strict, be easy to judge normal order by accident.
The exception tentatively identification is at least including in order feature detection, driver end feature detection and passenger end feature detection
One or more combination.
1）The order feature detection：Order feature detection：By carrying out to the History Order data in order database
Statistical analysiss, carry out abnormal judgement to the sequence information in single order data to be detected, if the single order to be detected
There is abnormal information in data, then the single order data to be detected is judged as abnormal suspicion order, and determine that this single is treated
Brush monotype corresponding to the order data of detection, is scored and is identified to the abnormal suspicion order.
General, can be judged in the order data by parameter 1_A, parameter 1_B, parameter 1_C and parameter 1_D etc.
Sequence information whether with History Order sample matches.
For example, in theory, the positional distance of passenger getting on/off is about 1 with the ratio of charged mileage, in practical operation, can
If a normal ratio scope, if the value of parameter 1_A of the order data is not in the range of default normal ratio, the order
Parameter A of data is mismatched with History Order sample, can determine that the order data for abnormal order.If order in the order data
Speed per hour is mismatched with the order speed per hour scope of History Order sample, then parameter 1_B exception.If the order data middle rolling car speed per hour with
The driving speed per hour scope of History Order sample is mismatched, then parameter 1_C exception.If the unit interval price in the order data with
The unit interval Price Range of History Order sample is mismatched, then parameter 1_D exception.Wherein, unit interval price is needed according to not
Same vehicle difference matching detection.
2）Driver end feature detection：Driver end feature detection：By to the History Order data in order database
Statistical analysiss are carried out, abnormal judgement is carried out to the sequence information in driver's order data of the driver, if driver's order data
In there is abnormal information, then judge that driver's order data is abnormal suspicion order, and determine corresponding to driver's order data
Brush monotype, the abnormal suspicion order is scored and is identified.
According to driver's order record of calling a taxi for a period of time, the Behavior preference of driver's dimension is analyzed, from History Order data
Some recent driver's order data of target driver is extracted in storehouse, drivers ' behavior figure is portrayed using some recent driver's order datas
Picture, including the normal time of received orders section of driver, the daily order volume of driver, driver operation geographical position, order average amount, order put down
Mileage, order average speed etc. portray drivers ' behavior image.Portray drivers ' behavior image to can be used to calculate recent driver's order
The accounting of abnormal order is identified as in data, whether the brush digital ratio equation for judging the driver is larger, if accounting is larger, should
Driver is emphasis object of suspicion.
Can also pass through to judge the brush monotype whether these abnormal orders show, determine whether single risk of its brush etc.
Level, for example for exist various brush monotypes or single brush single mode formula weight it is bigger to belong to brush one way degree serious, can mark
Note high-risk grade.
3）Passenger end feature detection：It is by carrying out statistical analysiss to the History Order data in order database, right
Sequence information in passenger's order data of the passenger carries out abnormal judgement, if there is abnormal information in passenger's order data,
Then judge that passenger's order data is abnormal suspicion order, and determine the brush monotype corresponding to passenger's order data, to institute
State abnormal suspicion order to be scored and identified.
According to passenger's order record of calling a taxi for a period of time, the Behavior preference of passenger's dimension is analyzed, from History Order data
Some recent passenger's order data of target passenger is extracted in storehouse, passenger behavior figure is portrayed using some recent passenger's order datas
Picture, including the normal travel time section of passenger, passenger are measured by bus, often the geographical position of trip, order average amount, order are average for passenger
Mileage etc. is portrayed passenger and is called a taxi behavior figure picture, and the accounting of abnormal order is identified as in calculating some recent passenger's order datas,
Judge whether the brush digital ratio equation of the passenger is larger, if accounting is larger, the passenger is emphasis object of suspicion.
Can also pass through to judge the brush monotype whether these abnormal orders show in the feature detection of passenger end, come further
Judge its single risk class of brush, for example for exist various brush monotypes or single brush single mode formula weight it is bigger to belong to brush single
Degree is serious, can mark high-risk grade.
It is of the present invention acquisition inter-trade data the step of S3, also can during execution step S1, while perform, step
The execution stage of rapid S3 flexibly can be arranged.
For example, after the supplementary detection data is obtained, detection information, the benefit are supplemented from supplementing to extract in detection data
Fill detection information and include but is not limited to driver end number and place an order time, driver's time in place, stroke time started, stroke in passenger
Passenger end place base station location during beginning, the passenger end passenger end at the end of time, stroke end time and stroke that places an order is located
Base station location etc..
Further, be that follow-up abnormal secondary judgement is prepared, also detection can be supplemented to extracting from supplementary detection data
Information is analyzed process, calculates detection parameter, and the general detection parameter includes but is not limited to parameter 2_A to parameter 2_J.
When parameter 2_A, stroke start, order generates the base station location of position and the base station position of driver end present position
The distance between put.
When parameter 2_B, stroke start, order generates the base station location of position and the base station position of passenger end present position
The distance between put.
At the end of parameter 2_C, stroke, order generates the base station location of position and the base station position of driver end present position
The distance between put.
At the end of parameter 2_D, stroke, order generates the base station location of position and the base station position of passenger end present position
The distance between put.
Driver end place base station location at the end of driver end place base station location and stroke when parameter 2_E, stroke start
Distance.
Passenger end place base station location at the end of passenger end place base station location and stroke when parameter 2_F, stroke start
Distance.
The distance of driver end place base station location and passenger end place base station location when parameter 2_G, stroke start.
The distance of driver end place base station location and passenger end place base station location at the end of parameter 2_H, stroke.
Parameter 2_I, order place an order the distance of time driver end place base station location and passenger end place base station location.
Driver end place base station location when parameter 2_J, order place an order time driver end place base station location and stroke starts
Distance.
Further, above-mentioned parameter 2_A is being calculated to parameter 2_J, order data can detected parameter with each
Association is stored in History Order data base, so as to follow-up abnormality detection and the single assessment of brush.
In addition, driver end telephone number can be inquired about from operator database also and passenger end telephone number terminates in order
When for the previous period the caller message registration in cycle, incoming call record and call forwarding message registration.Obtain each call note
The calling number of record, called number, communication time, converse time started, the IMEI number of call terminal and call terminal place base
Station location etc..
Further, be that follow-up abnormal secondary judgement is prepared, also detection can be supplemented to extracting from supplementary detection data
Information is analyzed process, calculates detection parameter, and the general detection parameter includes but is not limited to parameter 3_A to parameter 3_C.
Parameter 3_A, driver end place an order the time within the stroke end time in order, if there is incoming call record.
Parameter 3_B, passenger end place an order the time within the stroke end time in order, if there is incoming call record.
Parameter 3_C, driver end and passenger end place an order time interior for the previous period talk times in order.
Further, above-mentioned parameter 3_A is being calculated to parameter 3_C, order data can detected parameter with each
Association is stored in History Order data base, so as to follow-up abnormality detection and the single assessment of brush.
The step of abnormal secondary identification is carried out in S4, the order data need to be carried out according to the supplementary detection data
Secondary judgement, recognizes that the sequence information in the order data whether there is exception, and gives score value, note for the sequence information
For the second score value.Further, the sequence information in order data can be classified by dimension, according to the supplementary detection
Data carry out secondary judgement to the order data from multiple dimensions；Accordingly, when brush single act is judged, count single order
Multiple dimension score value weighted sums are obtained the overall score by the dimension score value of the sequence information of each dimension in data
Whether value, judge the order data as abnormal order according to the general comment score value of order data, and sentenced according to each dimension score value
The risk classifications of disconnected exception order.
The dimension includes that in card dimension is supported in location track dimension, relation loop dimension, communication behavior dimension and cat pond
Plant or multiple combination.
1）Location track dimension
In abnormal secondary identification, when secondary judgement is carried out to the order data from location track dimension, according to driver end and
The base station location information and satellite positioning information at passenger end, detects to its travel position：
Whether 1. whether the positional information of driver end stroke beginning and end matches, for detecting driver end such as taxi-hailing software APP
Satellite positioning location it is consistent, if having；
Whether 2. whether the positional information of passenger end stroke beginning and end matches, for detecting passenger end such as taxi-hailing software APP
Input position is consistent, and whether passenger getting on/off position matches；
3., before order is generated, the position relationship at driver end and passenger end for detecting that driver starts front position with passenger's order is
It is no identical, for determining whether same people or acquaintance etc.；
4. during stroke, the position relationship at driver end and passenger end, for detecting during stroke whether are driver and passenger position
Unanimously, driver's air-service return-to-home position and the true manned return-to-home position of driver are distinguished.
If there is above-mentioned situation in the base station location information and satellite positioning information at driver end and passenger end, to order data
Identified accordingly.The detection of aforementioned four position is complemented each other, and any one position mismatches will increase the single risk of brush, but because
Any one position is unmatched, and nor be judged to brush single act immediately, but which is carried out to brush single suspicion mark, finally
Also need to determine the single suspicion order of brush with reference to other dimension comprehensive analysis.
2）Relation loop dimension
In abnormal secondary identification, when carrying out secondary judgement to the order data from relation loop dimension, according to driver end and take advantage of
The telephone number at objective end, detects that the call behavior record between driver end and passenger end is sentenced in a period of time before order generation
Relation between disconnected driver and passenger knows well degree, and is identified.
If driver has message registration with passenger in the detection time before order generation, show that driver is ripe with passenger
People, and carry out acquaintance's mark.For the order data that there is acquaintance's mark, can comprehensive passenger call a taxi before call behavior and position
The detection such as relation parameter determines whether that the order is that acquaintance calls a taxi or acquaintance's brush is single.
3）Communication behavior dimension
In abnormal secondary identification, when secondary judgement is carried out to the order data from communication behavior dimension, according to driver end and
The telephone number at passenger end, in the time period started to stroke after detecting order generation, the call between driver end and passenger end
Behavior record, judges whether there is acknowledgement of orders communication behavior between driver end and passenger end, and is identified.
If there is no message registration in the time period that driver is started to stroke after order generation with passenger, i.e., do not order
It is single confirming communication behavior mark, if the order data also has acquaintance's mark, can the order data be labeled as brushing single wind
Dangerous order.
4）Support card dimension in cat pond
In abnormal secondary identification, when supporting card dimension from cat pond and carrying out secondary judgement to the order data, according to driver end and
Card behavior is supported with the presence or absence of cat pond in the telephone number at passenger end, detection driver end or passenger end, and is identified.
It is that user supports card apparatus using a kind of cat pond that can be modeled to mobile phone terminal that card behavior is supported in cat pond, and the cat pond is supported card and set
It is standby to put multiple phonecards simultaneously, make to show on business system these phonecards for open state, then brush single user is utilized
Request of calling a taxi is registered and initiated to these phonecards in taxi-hailing software APP, brushes single so as to help driver to carry out malice.
It is to detect whether driver end or the telephone number at passenger end have cat pond to support card behavior that card detection is supported in cat pond, and card is supported in cat pond
Principal character includes that non-system of real name, architecture position rarely have change, the low, flow of moon consumption to use and message registration is few, connection
It is that people is single etc..Cat pond is supported card detection data and can be provided by operator, existing cat pond may also be employed and supports card test method inspection
Measure.
If detecting in driver end or passenger end, the telephone number of either one has cat pond to support card behavior, then to the order numbers
Card behavior mark is supported according to cat pond is carried out.
（Two）Net about car exception order identifying system
As shown in Fig. 2 Fig. 2 describes a kind of net about car exception order identifying system, net about car exception order identifying system is adopted
The about car exception order recognition methodss of above-mentioned net, the system at least include that order data acquiring unit, abnormal preliminary identification are single
First, inter-trade data capture unit, abnormal secondary recognition unit and brush single act identifying unit.
1. order data acquiring unit, for obtaining order data to be detected from taxi taking platform data base.
2. abnormal preliminary recognition unit, for tentatively being judged to the order data, recognizes ordering in order data
Single information is with the presence or absence of exception, and gives score value for the sequence information, is designated as the first score value.
3. inter-trade data capture unit, for obtain from inter-trade data base driver and/or passenger for supplementing
Detect whether the supplementary detection data that there is abnormal order.
4. abnormal secondary recognition unit, for carrying out secondary sentencing to the order data according to the supplementary detection data
It is disconnected, recognize that the sequence information in the order data whether there is exception, and score value is given for the sequence information, be designated as second
Score value.
5. brush single act identifying unit, for carrying out to first score value and the second score value of identical sequence information
Weighted sum, and the general comment score value of all sequence informations in single order data is counted, sentenced according to the general comment score value of order data
Whether the fixed order data is abnormal order.
Further, the system also includes：
6. History Order data base, after order data acquiring unit obtains the order data, by ordering for the order data
Single information is stored in History Order data base, and the sequence information includes order initial data and calculated according to order initial data
For the abnormal detection parameter for judging；It is when brush single act identifying unit if it is determined that the order data is abnormal order, also right
Which is identified, and updates in History Order data base.
Further, the system also includes：
7. single comprehensive assessment unit is brushed, the brush list comprehensive assessment unit is obtained and target driver from History Order data base
Associated driver's order data, and the passenger's order data being associated with target passenger, and calculate quilt in driver's order data
The doubtful brush digital ratio equation of abnormal order is identified as in being designated the ratio of abnormal order, and passenger's order data, according to doubtful
Brush digital ratio equation carries out brush single act judgement to the current order data of target driver or target passenger.
Preferably, the preliminary recognition unit of the exception can also complete various dimensions abnormality detection, by the order in order data
Information is classified by dimension, carries out secondary judgement to the order data from multiple dimensions according to the supplementary detection data.
Accordingly, the brush single act identifying unit counts the order of each dimension in single order data when brush single act is judged
Multiple dimension score value weighted sums are obtained the general comment score value, according to the general comment of order data by the dimension score value of information
Whether score value judges the order data as abnormal order, and the risk classifications of abnormal order are judged according to each dimension score value.
Further, the preliminary recognition unit of the exception at least includes order feature detection module, driver end feature detection
One or more combination in module and passenger end feature detection module.
The order feature detection module, for by carrying out statistical to the History Order data in order database
Analysis, carries out abnormal judgement to the sequence information in single order data to be detected, if in the single order data to be detected
There is abnormal information, then the single order data to be detected is judged as abnormal suspicion order, and determine that this is single to be detected
Brush monotype corresponding to order data, is scored and is identified to the abnormal suspicion order.
Driver end feature detection module：For by carrying out statistical to the History Order data in order database
Analysis, carries out abnormal judgement to the sequence information in driver's order data of the driver, if existing in driver's order data abnormal
Information, then judge that driver's order data is abnormal suspicion order, and determine the brush monotype corresponding to driver's order data,
The abnormal suspicion order is scored and identified.
Passenger end feature detection module：For by carrying out statistical to the History Order data in order database
Analysis, carries out abnormal judgement to the sequence information in passenger's order data of the passenger, if existing in passenger's order data abnormal
Information, then judge that passenger's order data is abnormal suspicion order, and determine the brush monotype corresponding to passenger's order data,
The abnormal suspicion order is scored and identified.
Based on said system embodiment, further, the secondary recognition unit of the exception at least includes location track dimension
One in card dimension detection module is supported in detection module, relation loop dimension detection module, communication behavior dimension detection module and cat pond
Plant or multiple combination.
The location track dimension detection module, for base station location information and satellite according to driver end and passenger end
Position information, detects to its travel position：1. whether the positional information of driver end stroke beginning and end matches；2. passenger end
Whether the positional information of stroke beginning and end matches；3. before order is generated, the position relationship at driver end and passenger end；4. stroke
The position relationship at period, driver end and passenger end；And identified accordingly.
The relation loop dimension detection module, for the telephone number according to driver end and passenger end, detection order is generated
In front a period of time, the call behavior record between driver end and passenger end judges that the relation between driver and passenger is known well
Degree, and be identified.
The communication behavior dimension detection module, for the telephone number according to driver end and passenger end, detection order life
In the time period that Cheng Houzhi strokes start, the call behavior record between driver end and passenger end judges driver end and passenger end
Between whether have acknowledgement of orders communication behavior, and be identified.
Card dimension detection module is supported in the cat pond, for the telephone number according to driver end and passenger end, detection driver end
Or card behavior is supported with the presence or absence of cat pond in passenger end, and it is identified.
The present invention also based on inter-trade data, is adopted while using taxi taking platform Data Detection brush list suspicion order
Location track dimension, relation loop dimension, communication behavior dimension and cat pond support many detection dimensions such as card dimension to calculate sequence information
Score value, carry out brushing single identification from many aspects, and focus on and lift the single accuracy of identification brush, from data identification specialty
Brush single act, and be avoided as much as judging the behavior of normally calling a taxi of actual customer by accident, retain preferable Consumer's Experience.
The invention is not limited in aforesaid specific embodiment.The present invention is expanded to and any is disclosed in this manual
New feature or any new combination, and the arbitrary new method that discloses or the step of process or any new combination.
Claims (10)
1. net about car exception order recognition methodss, it is characterised in that comprise the following steps：
S1, acquisition order data, obtain order data to be detected from taxi taking platform data base；
S2, abnormal preliminary identification, are tentatively judged to the order data, are recognized whether the sequence information in order data deposits
In exception, and score value is given for the sequence information, be designated as the first score value；
S3, obtain inter-trade data, obtain from inter-trade data base target driver and/or target passenger for supplementing detection
With the presence or absence of the supplementary detection data of abnormal order；
S4, abnormal secondary identification, carry out secondary judgement according to the supplementary detection data to the order data, order described in identification
Sequence information in forms data is with the presence or absence of exception, and gives score value for the sequence information, is designated as the second score value；
S5, judgement brush single act, are weighted summation to first score value and the second score value of identical sequence information, and unite
The general comment score value of all sequence informations in single order data is counted, judges that the order data is according to the general comment score value of order data
It is no for abnormal order.
2. based on the about car exception order recognition methodss of the net described in claim 1, it is characterised in that in abnormal secondary identification,
Sequence information in order data is classified by dimension, according to the supplementary detection data from multiple dimensions to the order
Data carry out secondary judgement；
When brush single act is judged, the dimension score value of the sequence information of each dimension in single order data is counted, to multiple
Dimension score value weighted sum obtains the general comment score value, according to the general comment score value of order data judge the order data whether as
Abnormal order, and the risk classifications of abnormal order are judged according to each dimension score value.
3. based on the about car exception order recognition methodss of the net described in claim 1 or 2, it is characterised in that in step S1, obtain
After taking the order data, the sequence information of the order data is stored in History Order data base, the sequence information bag
The detection parameter for abnormal judgement for including order initial data and being calculated according to order initial data；
In step s 5, if it is determined that the order data is abnormal order, also which is identified, and updates History Order data
Storehouse.
4. based on the about car exception order recognition methodss of the net described in claim 3, it is characterised in that methods described also includes step
S6：From History Order data base, driver's order data that acquisition is associated with target driver, and be associated with target passenger
Passenger's order data, and marked during the ratio of abnormal order, and passenger's order data are identified as in calculating driver's order data
Know the doubtful brush digital ratio equation for abnormal order, according to current order data of the doubtful brush digital ratio equation to target driver or target passenger
Carry out brush single act judgement.
5. based on the about car exception order recognition methodss of the net described in claim 3, it is characterised in that the exception tentatively recognize to
Less including one or more combination in order feature detection, driver end feature detection and passenger end feature detection：
Order feature detection：By carrying out statistical analysiss to the History Order data in order database, to single to be detected
Sequence information in order data carries out abnormal judgement, if there is abnormal information in the single order data to be detected, sentences
The fixed single order data to be detected is abnormal suspicion order, and determines the brush corresponding to single order data to be detected
Monotype, is scored and is identified to the abnormal suspicion order；
Driver end feature detection：By carrying out statistical analysiss to the History Order data in order database, to the driver's
Sequence information in driver's order data carries out abnormal judgement, if there is abnormal information in driver's order data, judges the department
Machine order data is abnormal suspicion order, and determines the brush monotype corresponding to driver's order data, to the abnormal suspicion
Order is scored and is identified；
Passenger end feature detection：By carrying out statistical analysiss to the History Order data in order database, to the passenger's
Sequence information in passenger's order data carries out abnormal judgement, if there is abnormal information in passenger's order data, judges that this is taken advantage of
Objective order data is abnormal suspicion order, and determines the brush monotype corresponding to passenger's order data, to the abnormal suspicion
Order is scored and is identified.
6. based on the about car exception order recognition methodss of the net described in claim 2, it is characterised in that：The dimension includes position rail
One or more combination in card dimension is supported in mark dimension, relation loop dimension, communication behavior dimension and cat pond：
In abnormal secondary identification, when secondary judgement is carried out to the order data from location track dimension, according to driver end and
The base station location information and satellite positioning information at passenger end, detects to its travel position, including：1. driver end stroke starts
Whether match with the positional information for terminating；2. whether the positional information of passenger end stroke beginning and end matches；3. order is generated
Before, the position relationship at driver end and passenger end；4. during stroke, the position relationship at driver end and passenger end；And carry out corresponding
Mark；
In abnormal secondary identification, when carrying out secondary judgement to the order data from relation loop dimension, according to driver end and take advantage of
The telephone number at objective end, detects that the call behavior record between driver end and passenger end is sentenced in a period of time before order generation
Relation between disconnected driver and passenger knows well degree, and is identified；
In abnormal secondary identification, when secondary judgement is carried out to the order data from communication behavior dimension, according to driver end and
The telephone number at passenger end, in the time period started to stroke after detecting order generation, the call between driver end and passenger end
Behavior record, judges whether there is acknowledgement of orders communication behavior between driver end and passenger end, and is identified；
In abnormal secondary identification, when supporting card dimension from cat pond and carrying out secondary judgement to the order data, according to driver end and
Card behavior is supported with the presence or absence of cat pond in the telephone number at passenger end, detection driver end or passenger end, and is identified.
7. net about car exception order identifying system, it is characterised in that the system includes：
Order data acquiring unit, for obtaining order data to be detected from taxi taking platform data base；
Abnormal preliminary recognition unit, for tentatively being judged to the order data, recognizes the sequence information in order data
With the presence or absence of exception, and score value is given for the sequence information, be designated as the first score value；
Inter-trade data capture unit, for obtain from inter-trade data base target driver and/or target passenger for mending
Fill the supplementary detection data for detecting whether there is abnormal order；
Abnormal secondary recognition unit, for secondary judgement is carried out to the order data according to the supplementary detection data, identification
Sequence information in the order data is with the presence or absence of exception, and gives score value for the sequence information, is designated as the second score value；
Brush single act identifying unit, for first score value and the second score value of identical sequence information are weighted and are asked
With, and the general comment score value of all sequence informations in single order data is counted, judge that this is ordered according to the general comment score value of order data
Whether forms data is abnormal order.
8. based on the about car exception order identifying system of the net described in claim 7, it is characterised in that：The exception tentatively recognizes list
When unit is tentatively judged to the order data, the sequence information in order data is classified by dimension, according to described
Supplementing detection data carries out secondary judgement to the order data from multiple dimensions；
The brush single act identifying unit counts the sequence information of each dimension in single order data when brush single act is judged
Dimension score value, the general comment score value is obtained to multiple dimension score value weighted sums, according to the general comment score value of order data
Whether the order data is judged as abnormal order, and the risk classifications of abnormal order are judged according to each dimension score value.
9. based on the about car exception order identifying system of the net described in claim 7, it is characterised in that：The exception tentatively recognizes list
Unit at least includes the one kind or many in order feature detection module, driver end feature detection module and passenger end feature detection module
Plant combination：
Order feature detection module：For by carrying out statistical analysiss to the History Order data in order database, to single
Sequence information in order data to be detected carries out abnormal judgement, if there is abnormal letter in the single order data to be detected
Breath, then judge the single order data to be detected as abnormal suspicion order, and determine the single order data institute to be detected
Corresponding brush monotype, is scored and is identified to the abnormal suspicion order；
Driver end feature detection module：For by carrying out statistical analysiss to the History Order data in order database, to institute
The sequence information stated in driver's order data of driver carries out abnormal judgement, if there is abnormal information in driver's order data,
Judge that driver's order data is abnormal suspicion order, and determine the brush monotype corresponding to driver's order data, to described
Abnormal suspicion order is scored and is identified；
Passenger end feature detection module：For by carrying out statistical analysiss to the History Order data in order database, to institute
The sequence information stated in passenger's order data of passenger carries out abnormal judgement, if there is abnormal information in passenger's order data,
Judge that passenger's order data is abnormal suspicion order, and determine the brush monotype corresponding to passenger's order data, to described
Abnormal suspicion order is scored and is identified.
10. based on the about car exception order identifying system of the net described in claim 7, it is characterised in that：The secondary identification of the exception
Unit at least includes location track dimension detection module, relation loop dimension detection module, communication behavior dimension detection module and cat
Support one or more combination in card dimension detection module in pond：
The location track dimension detection module, believes for the base station location information according to driver end and passenger end and satellite fix
Breath, detects to its travel position：1. whether the positional information of driver end stroke beginning and end matches；2. passenger end stroke
Whether the positional information of beginning and end matches；3. before order is generated, the position relationship at driver end and passenger end；4. stroke phase
Between, the position relationship at driver end and passenger end；And identified accordingly；
The relation loop dimension detection module, for the telephone number according to driver end and passenger end, before detection order is generated
In a period of time, the call behavior record between driver end and passenger end judges that the relation between driver and passenger knows well degree,
And be identified；
The communication behavior dimension detection module, for the telephone number according to driver end and passenger end, after detection order is generated
In the time period started to stroke, the call behavior record between driver end and passenger end is judged between driver end and passenger end
Whether there is acknowledgement of orders communication behavior, and be identified；
Card dimension detection module is supported in the cat pond, for the telephone number according to driver end and passenger end, is detected driver end or is taken advantage of
Card behavior is supported with the presence or absence of cat pond in objective end, and is identified.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611072064.8A CN106557955A (en) | 2016-11-29 | 2016-11-29 | Net about car exception order recognition methodss and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611072064.8A CN106557955A (en) | 2016-11-29 | 2016-11-29 | Net about car exception order recognition methodss and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106557955A true CN106557955A (en) | 2017-04-05 |
Family
ID=58445862
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611072064.8A Pending CN106557955A (en) | 2016-11-29 | 2016-11-29 | Net about car exception order recognition methodss and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106557955A (en) |
Cited By (46)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107341716A (en) * | 2017-07-11 | 2017-11-10 | 北京奇艺世纪科技有限公司 | A kind of method, apparatus and electronic equipment of the identification of malice order |
| CN107392801A (en) * | 2017-07-21 | 2017-11-24 | 上海携程商务有限公司 | The method and its device, storage medium, electronic equipment of order are upset in control |
| CN107423883A (en) * | 2017-06-15 | 2017-12-01 | 阿里巴巴集团控股有限公司 | Risk Identification Method and device, the electronic equipment of pending business |
| CN107464169A (en) * | 2017-08-10 | 2017-12-12 | 北京小度信息科技有限公司 | Information output method and device |
| CN107609950A (en) * | 2017-09-27 | 2018-01-19 | 掌合天下（北京）信息技术有限公司 | Order processing method and device |
| CN107872767A (en) * | 2017-11-07 | 2018-04-03 | 中国联合网络通信集团有限公司 | A kind of net about car brush single act recognition methods and identifying system |
| CN107958346A (en) * | 2017-12-14 | 2018-04-24 | 北京小度信息科技有限公司 | The recognition methods of abnormal behaviour and device |
| CN108182587A (en) * | 2018-01-29 | 2018-06-19 | 北京信息科技大学 | A kind of electric business platform brush single act detection method and system |
| CN108390883A (en) * | 2018-02-28 | 2018-08-10 | 武汉斗鱼网络科技有限公司 | Recognition methods, device and the terminal device of brush popularity user |
| CN108647997A (en) * | 2018-04-13 | 2018-10-12 | 北京三快在线科技有限公司 | A kind of method and device of detection abnormal data |
| CN108734537A (en) * | 2017-04-24 | 2018-11-02 | 北京京东尚科信息技术有限公司 | The method and apparatus for counting violation order |
| CN108830608A (en) * | 2017-04-28 | 2018-11-16 | 北京嘀嘀无限科技发展有限公司 | Cheat detection method and device |
| CN109285009A (en) * | 2018-08-06 | 2019-01-29 | 北京三快在线科技有限公司 | It brushes single recognition methods and brushes single identification device |
| CN109377301A (en) * | 2018-08-27 | 2019-02-22 | 中国民航信息网络股份有限公司 | A kind of Feature Extraction Method based on Airline reservation behavioral data |
| CN109508519A (en) * | 2017-09-14 | 2019-03-22 | 北京京东尚科信息技术有限公司 | Method and apparatus for handling request |
| CN109524088A (en) * | 2018-10-27 | 2019-03-26 | 平安医疗健康管理股份有限公司 | Medical monitoring method, device, terminal and medium based on data visualization |
| CN109636413A (en) * | 2018-11-23 | 2019-04-16 | 杭州优行科技有限公司 | A kind of storage medium, server, brush single act recognition methods and device |
| CN110097316A (en) * | 2019-04-26 | 2019-08-06 | 张文 | A kind of no vehicle acknowledgement of consignment management method and system |
| CN110751586A (en) * | 2019-02-21 | 2020-02-04 | 北京嘀嘀无限科技发展有限公司 | Order travel abnormity identification method and system |
| CN110751531A (en) * | 2018-11-13 | 2020-02-04 | 北京嘀嘀无限科技发展有限公司 | Track identification method and device and electronic equipment |
| CN110782111A (en) * | 2019-02-21 | 2020-02-11 | 北京嘀嘀无限科技发展有限公司 | Risk assessment method and system |
| CN110784435A (en) * | 2019-04-15 | 2020-02-11 | 北京嘀嘀无限科技发展有限公司 | Abnormal service identification method and device, electronic equipment and storage medium |
| CN110807685A (en) * | 2019-10-22 | 2020-02-18 | 上海钧正网络科技有限公司 | Information processing method, device, terminal and readable storage medium |
| CN110992072A (en) * | 2018-11-30 | 2020-04-10 | 北京嘀嘀无限科技发展有限公司 | Abnormal order prediction method and system |
| CN110992119A (en) * | 2019-02-21 | 2020-04-10 | 北京嘀嘀无限科技发展有限公司 | Method and system for sequencing risk orders |
| CN110991781A (en) * | 2019-02-21 | 2020-04-10 | 北京嘀嘀无限科技发展有限公司 | Risk order display method and system |
| CN111179000A (en) * | 2018-11-09 | 2020-05-19 | 北京嘀嘀无限科技发展有限公司 | Order management method and device, server and computer readable storage medium |
| CN111311411A (en) * | 2020-02-14 | 2020-06-19 | 北京三快在线科技有限公司 | Illegal behavior identification method and device |
| CN111401030A (en) * | 2018-12-28 | 2020-07-10 | 北京嘀嘀无限科技发展有限公司 | Service abnormity identification method, device, server and readable storage medium |
| CN111459701A (en) * | 2020-04-07 | 2020-07-28 | 北京思特奇信息技术股份有限公司 | Abnormal order detection processing system and method |
| CN111598372A (en) * | 2019-02-21 | 2020-08-28 | 北京嘀嘀无限科技发展有限公司 | Risk prevention method and system |
| CN111598368A (en) * | 2019-02-21 | 2020-08-28 | 北京嘀嘀无限科技发展有限公司 | Risk identification method, system and device based on stopping abnormity after stroke ends |
| CN111626828A (en) * | 2020-05-29 | 2020-09-04 | 上海钧正网络科技有限公司 | Wind control detection method, system and device for network appointment vehicle order and storage medium |
| CN111833135A (en) * | 2019-08-01 | 2020-10-27 | 北京嘀嘀无限科技发展有限公司 | Order data analysis method and device and electronic equipment |
| CN112116158A (en) * | 2020-09-21 | 2020-12-22 | 北京嘀嘀无限科技发展有限公司 | Data processing method, data processing apparatus, storage medium, and electronic device |
| CN112926881A (en) * | 2021-03-29 | 2021-06-08 | 广州宸祺出行科技有限公司 | Detection method and system for preventing driver from swiping bill based on vehicle-mounted system |
| CN112950298A (en) * | 2019-11-26 | 2021-06-11 | 北京沃东天骏信息技术有限公司 | Malicious order identification method and device and storage medium |
| US20210192402A1 (en) * | 2019-12-20 | 2021-06-24 | Beijing Didi Infinity Technology And Development Co., Ltd. | Abnormal trip monitor |
| CN113469789A (en) * | 2021-07-01 | 2021-10-01 | 易纳购科技(北京)有限公司 | Abnormal order detection method and device and computer equipment |
| CN113723970A (en) * | 2021-08-25 | 2021-11-30 | 深圳依时货拉拉科技有限公司 | Order list pushing method and device, storage medium and computer equipment |
| CN113780854A (en) * | 2021-09-16 | 2021-12-10 | 广州宸祺出行科技有限公司 | Method and device for identifying online taxi booking driver idle running list brushing |
| CN113781156A (en) * | 2021-05-13 | 2021-12-10 | 北京沃东天骏信息技术有限公司 | Malicious order recognition method, malicious order model training method, malicious order recognition equipment and malicious order model training storage medium |
| CN114841712A (en) * | 2022-03-01 | 2022-08-02 | 北京北大千方科技有限公司 | Method and device for determining illegal operation state of network appointment vehicle tour and electronic equipment |
| CN117575546A (en) * | 2024-01-17 | 2024-02-20 | 北京白龙马云行科技有限公司 | Background management system for network vehicle-restraining platform |
| CN117635403A (en) * | 2023-11-08 | 2024-03-01 | 杭州一喂智能科技有限公司 | Abnormal order alarm method, device, electronic equipment and computer readable medium |
| CN117635403B (en) * | 2023-11-08 | 2024-06-21 | 杭州一喂智能科技有限公司 | Abnormal order alarm method, device, electronic equipment and computer readable medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130111019A1 (en) * | 2011-10-28 | 2013-05-02 | Electronic Arts Inc. | User behavior analyzer |
| CN105657659A (en) * | 2016-01-29 | 2016-06-08 | 北京邮电大学 | Method and system for identifying scalping user in taxi service |
| CN106059847A (en) * | 2016-04-08 | 2016-10-26 | 久远谦长（北京）技术服务有限公司 | User ordering behavior detection method and device |
-
2016
- 2016-11-29 CN CN201611072064.8A patent/CN106557955A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130111019A1 (en) * | 2011-10-28 | 2013-05-02 | Electronic Arts Inc. | User behavior analyzer |
| CN105657659A (en) * | 2016-01-29 | 2016-06-08 | 北京邮电大学 | Method and system for identifying scalping user in taxi service |
| CN106059847A (en) * | 2016-04-08 | 2016-10-26 | 久远谦长（北京）技术服务有限公司 | User ordering behavior detection method and device |
Cited By (68)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108734537B (en) * | 2017-04-24 | 2021-04-30 | 北京京东尚科信息技术有限公司 | Method and device for counting violation orders |
| CN108734537A (en) * | 2017-04-24 | 2018-11-02 | 北京京东尚科信息技术有限公司 | The method and apparatus for counting violation order |
| CN108830608B (en) * | 2017-04-28 | 2021-08-06 | 北京嘀嘀无限科技发展有限公司 | Cheating detection method and device |
| CN108830608A (en) * | 2017-04-28 | 2018-11-16 | 北京嘀嘀无限科技发展有限公司 | Cheat detection method and device |
| CN107423883A (en) * | 2017-06-15 | 2017-12-01 | 阿里巴巴集团控股有限公司 | Risk Identification Method and device, the electronic equipment of pending business |
| CN107423883B (en) * | 2017-06-15 | 2020-04-07 | 创新先进技术有限公司 | Risk identification method and device for to-be-processed service and electronic equipment |
| US11367075B2 (en) | 2017-06-15 | 2022-06-21 | Advanced New Technologies Co., Ltd. | Method, apparatus and electronic device for identifying risks pertaining to transactions to be processed |
| US11494774B2 (en) | 2017-06-15 | 2022-11-08 | Advanced New Technologies Co., Ltd. | Method, apparatus and electronic device for identifying risks pertaining to transactions to be processed |
| CN107341716A (en) * | 2017-07-11 | 2017-11-10 | 北京奇艺世纪科技有限公司 | A kind of method, apparatus and electronic equipment of the identification of malice order |
| CN107392801A (en) * | 2017-07-21 | 2017-11-24 | 上海携程商务有限公司 | The method and its device, storage medium, electronic equipment of order are upset in control |
| CN107464169A (en) * | 2017-08-10 | 2017-12-12 | 北京小度信息科技有限公司 | Information output method and device |
| CN107464169B (en) * | 2017-08-10 | 2020-11-10 | 北京星选科技有限公司 | Information output method and device |
| CN109508519A (en) * | 2017-09-14 | 2019-03-22 | 北京京东尚科信息技术有限公司 | Method and apparatus for handling request |
| CN107609950A (en) * | 2017-09-27 | 2018-01-19 | 掌合天下（北京）信息技术有限公司 | Order processing method and device |
| CN107872767A (en) * | 2017-11-07 | 2018-04-03 | 中国联合网络通信集团有限公司 | A kind of net about car brush single act recognition methods and identifying system |
| CN107958346A (en) * | 2017-12-14 | 2018-04-24 | 北京小度信息科技有限公司 | The recognition methods of abnormal behaviour and device |
| CN108182587A (en) * | 2018-01-29 | 2018-06-19 | 北京信息科技大学 | A kind of electric business platform brush single act detection method and system |
| CN108390883B (en) * | 2018-02-28 | 2020-08-04 | 武汉斗鱼网络科技有限公司 | Identification method and device for people-refreshing user and terminal equipment |
| CN108390883A (en) * | 2018-02-28 | 2018-08-10 | 武汉斗鱼网络科技有限公司 | Recognition methods, device and the terminal device of brush popularity user |
| CN108647997A (en) * | 2018-04-13 | 2018-10-12 | 北京三快在线科技有限公司 | A kind of method and device of detection abnormal data |
| CN109285009A (en) * | 2018-08-06 | 2019-01-29 | 北京三快在线科技有限公司 | It brushes single recognition methods and brushes single identification device |
| CN109285009B (en) * | 2018-08-06 | 2021-03-02 | 北京三快在线科技有限公司 | Bill brushing identification method and bill brushing identification device |
| CN109377301A (en) * | 2018-08-27 | 2019-02-22 | 中国民航信息网络股份有限公司 | A kind of Feature Extraction Method based on Airline reservation behavioral data |
| CN109524088B (en) * | 2018-10-27 | 2024-02-13 | 深圳平安医疗健康科技服务有限公司 | Medical monitoring method, device, terminal and medium based on data visualization |
| CN109524088A (en) * | 2018-10-27 | 2019-03-26 | 平安医疗健康管理股份有限公司 | Medical monitoring method, device, terminal and medium based on data visualization |
| CN111179000B (en) * | 2018-11-09 | 2023-08-11 | 北京嘀嘀无限科技发展有限公司 | Order management method and device, server and computer readable storage medium |
| CN111179000A (en) * | 2018-11-09 | 2020-05-19 | 北京嘀嘀无限科技发展有限公司 | Order management method and device, server and computer readable storage medium |
| CN110751531A (en) * | 2018-11-13 | 2020-02-04 | 北京嘀嘀无限科技发展有限公司 | Track identification method and device and electronic equipment |
| CN109636413A (en) * | 2018-11-23 | 2019-04-16 | 杭州优行科技有限公司 | A kind of storage medium, server, brush single act recognition methods and device |
| CN110992072A (en) * | 2018-11-30 | 2020-04-10 | 北京嘀嘀无限科技发展有限公司 | Abnormal order prediction method and system |
| CN111401030A (en) * | 2018-12-28 | 2020-07-10 | 北京嘀嘀无限科技发展有限公司 | Service abnormity identification method, device, server and readable storage medium |
| CN111401030B (en) * | 2018-12-28 | 2024-01-09 | 北京嘀嘀无限科技发展有限公司 | Method and device for identifying service abnormality, server and readable storage medium |
| CN111598368A (en) * | 2019-02-21 | 2020-08-28 | 北京嘀嘀无限科技发展有限公司 | Risk identification method, system and device based on stopping abnormity after stroke ends |
| CN110992119A (en) * | 2019-02-21 | 2020-04-10 | 北京嘀嘀无限科技发展有限公司 | Method and system for sequencing risk orders |
| WO2020169053A1 (en) * | 2019-02-21 | 2020-08-27 | Beijing Didi Infinity Technology And Development Co., Ltd. | Systems and methods for identifying abnormalities |
| CN110751586A (en) * | 2019-02-21 | 2020-02-04 | 北京嘀嘀无限科技发展有限公司 | Order travel abnormity identification method and system |
| CN111598368B (en) * | 2019-02-21 | 2023-09-05 | 北京嘀嘀无限科技发展有限公司 | Risk identification method, system and device based on stop abnormality after stroke end |
| CN110782111A (en) * | 2019-02-21 | 2020-02-11 | 北京嘀嘀无限科技发展有限公司 | Risk assessment method and system |
| CN110782111B (en) * | 2019-02-21 | 2023-04-25 | 北京嘀嘀无限科技发展有限公司 | Risk assessment method and system |
| CN110991781A (en) * | 2019-02-21 | 2020-04-10 | 北京嘀嘀无限科技发展有限公司 | Risk order display method and system |
| CN111598372A (en) * | 2019-02-21 | 2020-08-28 | 北京嘀嘀无限科技发展有限公司 | Risk prevention method and system |
| CN110784435B (en) * | 2019-04-15 | 2020-11-06 | 北京嘀嘀无限科技发展有限公司 | Abnormal service identification method and device, electronic equipment and storage medium |
| CN110784435A (en) * | 2019-04-15 | 2020-02-11 | 北京嘀嘀无限科技发展有限公司 | Abnormal service identification method and device, electronic equipment and storage medium |
| CN110097316B (en) * | 2019-04-26 | 2021-11-05 | 张文 | Carrier-free management method and system |
| CN110097316A (en) * | 2019-04-26 | 2019-08-06 | 张文 | A kind of no vehicle acknowledgement of consignment management method and system |
| CN111833135A (en) * | 2019-08-01 | 2020-10-27 | 北京嘀嘀无限科技发展有限公司 | Order data analysis method and device and electronic equipment |
| CN110807685B (en) * | 2019-10-22 | 2021-09-07 | 上海钧正网络科技有限公司 | Information processing method, device, terminal and readable storage medium |
| CN110807685A (en) * | 2019-10-22 | 2020-02-18 | 上海钧正网络科技有限公司 | Information processing method, device, terminal and readable storage medium |
| CN112950298A (en) * | 2019-11-26 | 2021-06-11 | 北京沃东天骏信息技术有限公司 | Malicious order identification method and device and storage medium |
| US20210192402A1 (en) * | 2019-12-20 | 2021-06-24 | Beijing Didi Infinity Technology And Development Co., Ltd. | Abnormal trip monitor |
| CN111311411B (en) * | 2020-02-14 | 2022-03-08 | 北京三快在线科技有限公司 | Illegal behavior identification method and device |
| CN111311411A (en) * | 2020-02-14 | 2020-06-19 | 北京三快在线科技有限公司 | Illegal behavior identification method and device |
| CN111459701A (en) * | 2020-04-07 | 2020-07-28 | 北京思特奇信息技术股份有限公司 | Abnormal order detection processing system and method |
| CN111626828A (en) * | 2020-05-29 | 2020-09-04 | 上海钧正网络科技有限公司 | Wind control detection method, system and device for network appointment vehicle order and storage medium |
| CN111626828B (en) * | 2020-05-29 | 2021-09-21 | 上海钧正网络科技有限公司 | Wind control detection method, system and device for network appointment vehicle order and storage medium |
| CN112116158A (en) * | 2020-09-21 | 2020-12-22 | 北京嘀嘀无限科技发展有限公司 | Data processing method, data processing apparatus, storage medium, and electronic device |
| CN112926881A (en) * | 2021-03-29 | 2021-06-08 | 广州宸祺出行科技有限公司 | Detection method and system for preventing driver from swiping bill based on vehicle-mounted system |
| CN113781156A (en) * | 2021-05-13 | 2021-12-10 | 北京沃东天骏信息技术有限公司 | Malicious order recognition method, malicious order model training method, malicious order recognition equipment and malicious order model training storage medium |
| CN113469789A (en) * | 2021-07-01 | 2021-10-01 | 易纳购科技(北京)有限公司 | Abnormal order detection method and device and computer equipment |
| CN113723970A (en) * | 2021-08-25 | 2021-11-30 | 深圳依时货拉拉科技有限公司 | Order list pushing method and device, storage medium and computer equipment |
| CN113723970B (en) * | 2021-08-25 | 2024-02-02 | 深圳依时货拉拉科技有限公司 | Order list pushing method, order list pushing device, storage medium and computer equipment |
| CN113780854A (en) * | 2021-09-16 | 2021-12-10 | 广州宸祺出行科技有限公司 | Method and device for identifying online taxi booking driver idle running list brushing |
| CN114841712B (en) * | 2022-03-01 | 2023-03-24 | 北京北大千方科技有限公司 | Method and device for determining illegal operation state of network appointment vehicle tour and electronic equipment |
| CN114841712A (en) * | 2022-03-01 | 2022-08-02 | 北京北大千方科技有限公司 | Method and device for determining illegal operation state of network appointment vehicle tour and electronic equipment |
| CN117635403A (en) * | 2023-11-08 | 2024-03-01 | 杭州一喂智能科技有限公司 | Abnormal order alarm method, device, electronic equipment and computer readable medium |
| CN117635403B (en) * | 2023-11-08 | 2024-06-21 | 杭州一喂智能科技有限公司 | Abnormal order alarm method, device, electronic equipment and computer readable medium |
| CN117575546A (en) * | 2024-01-17 | 2024-02-20 | 北京白龙马云行科技有限公司 | Background management system for network vehicle-restraining platform |
| CN117575546B (en) * | 2024-01-17 | 2024-04-05 | 北京白龙马云行科技有限公司 | Background management system for network vehicle-restraining platform |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106557955A (en) | Net about car exception order recognition methodss and system | |
| CN106384273B (en) | Malicious bill-swiping detection system and method | |
| CN104766473B (en) | Transit trip feature extracting method based on multi-mode public transport Data Matching | |
| CN105657659A (en) | Method and system for identifying scalping user in taxi service | |
| CN106127505A (en) | The single recognition methods of a kind of brush and device | |
| CN106204106A (en) | A kind of specific user's recognition methods and system | |
| CN106504584B (en) | A kind of City-level wisdom shutdown system | |
| CN107895281A (en) | A kind of information-pushing method, device and storage medium | |
| CN106056403A (en) | Rail transit fee determining method and rail transit fee determining device | |
| CN105931068A (en) | Cardholder consumption figure generation method and device | |
| CN106934018A (en) | A kind of doctor's commending system based on collaborative filtering | |
| CN109829485A (en) | A kind of user relationship mining method and system based on mobile data | |
| CN106952493A (en) | A kind of control method and system of shared vehicle management system | |
| CN106658564B (en) | The recognition methods of domestic consumer a kind of and device | |
| CN109214280A (en) | Shop recognition methods, device, electronic equipment and storage medium based on streetscape | |
| CN105741161A (en) | Method and system for recognizing click farming users in taxi businesses on basis of driver credit | |
| CN107705131A (en) | Public transport method of payment, device and public transport payment system | |
| CN108229749A (en) | Bad booking behavior management method based on deep learning | |
| CN103888961B (en) | A kind of user monitoring method and device | |
| CN110245288A (en) | A kind of vehicle match method and device based on multidimensional evaluation system | |
| CN106204759A (en) | Parking charge system and data processing method thereof | |
| CN110175868A (en) | A kind of Green Travel excitation system and method based on carbon transaction | |
| CN108108897A (en) | A kind of track traffic for passenger flow classifying method, system and electronic equipment | |
| CN110674879B (en) | Identification matching method and device, electronic equipment and readable storage medium | |
| CN114596111A (en) | Risk identification model generation method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |