CN105657659A - Method and system for identifying scalping user in taxi service - Google Patents
Method and system for identifying scalping user in taxi service Download PDFInfo
- Publication number
- CN105657659A CN105657659A CN201610064670.9A CN201610064670A CN105657659A CN 105657659 A CN105657659 A CN 105657659A CN 201610064670 A CN201610064670 A CN 201610064670A CN 105657659 A CN105657659 A CN 105657659A
- Authority
- CN
- China
- Prior art keywords
- credit
- driver
- user
- desired value
- order
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
-
- 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)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Finance (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Theoretical Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Traffic Control Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a method and system for identifying a scalping user in a taxi service. The method comprises the following steps: extracting a cell phone number of a user in a taxi order, and start and finish time of the order; and then acquiring position data of the cell phone number at a base station cell between the start and finish time of the order from a telecom operation server that the cell phone number of the user belongs to, and judging whether the position data of the base station cell are changed between the start and finish time of the order, if not, then the user is the scalping user, wherein the user is a driver or a passenger. The method and system for identifying the scalping user in the taxi service provided by the invention belong to the technical field of mobile Internet, can effectively recognize scalping users in the taxis service, reduce the enterprise loss and system misjudgment, and improve the recognition efficiency.
Description
Technical field
The present invention relates to a kind of identification to call a taxi the method and system of brush single user in business, belong to mobile internet technical field.
Background technology
Current passenger can issue, by mobile phone, demand of calling a taxi easily, business platform of calling a taxi receives the request of calling a taxi that passenger's mobile phone sends, and the order of this request of calling a taxi is pushed to terminal, and driver can use terminal competition for orders, and directly link up with passenger, substantially increase efficiency of calling a taxi.
Owing to O2O industry segmentation field is numerous, it is all very fierce to compete, participant in the market carrys out customer retaining by substantial amounts of cash infusion mostly, user is provided a lot of preferential subsidy by the businessman of business of calling a taxi, therefore brush single user partly is had by brush single file for completing order of calling a taxi, to profit squeeze, these brush single files are as follows for including:
1, acquaintance brushes mutually, mutually places an order, and sets up group, mutually place an order between brush single user;
2, a people has multiple stage machine and coordinates driver to brush list: brush list person buys the smart mobile phone of multiple cheap phone number and transformation, one mobile phone can support the authentication of a large amount of account, and palm off into different cellphone subscribers, simultaneously by software modification wheelpath.
Patent application CN201510284601.4 (patent name: the detection method of gps coordinate cheating and device, the applying date: 2015-05-28, applicant: tick unlimited development in science and technology company limited in Beijing) disclose the detection method that a kind of gps coordinate is practised fraud, including: obtain terminal global position system GPS coordinate information in preset time period; Obtain the described terminal adopting architecture technology or WiFi location technology to obtain the first coordinate information in described preset time period; Obtain the deviation of described GPS coordinate information and described first coordinate information, and described deviation and the first predetermined threshold value are compared; If described deviation is be more than or equal to the first predetermined threshold value, then judge that described GPS coordinate information is as forging coordinate information. This technical scheme is only limitted to identify whether user is modified gps coordinate, owing to the behavior of brush single user exists multiformity, amendment gps coordinate is a kind of brush single file therein, if the gps coordinate only in accordance with user identifies brush single user, can not effectively identify most of brush single user in the business of calling a taxi.
Therefore, it is how effectively to identify the brush single user called a taxi in business for diversified brush single file, reduces enterprises' loss, reduce system erroneous judgement simultaneously, improve recognition efficiency, it has also become current urgent need solves the technical problem that.
Summary of the invention
In view of this, it is an object of the invention to provide a kind of identification and call a taxi the method and system of brush single user in business, can effectively identify the brush single user in the business of calling a taxi, reduce enterprises' loss, reduce system erroneous judgement simultaneously, improve recognition efficiency.
In order to achieve the above object, the invention provides a kind of identification and call a taxi the method for brush single user in business, include:
Step A, extract call a taxi in the order phone number of user and the beginning of order and deadline, then the described phone number position data in the beginning of order and the base station cell, place between the deadline is obtained to the telecom operation server belonging to subscriber phone number, and judge whether the position data of described base station cell changes in the beginning of order with between the deadline, if not, then described user is brush single user, wherein, user is driver or passenger.
In order to achieve the above object, present invention also offers a kind of identification and call a taxi the system of brush single user in business, include:
Position identification device, for extracting in order of calling a taxi the phone number of user and the beginning of order and deadline, then the described phone number position data in the beginning of order and the base station cell, place between the deadline is obtained to the telecom operation server belonging to subscriber phone number, and judge whether the position data of described base station cell changes in the beginning of order with between the deadline, if not, then described user is brush single user, and wherein, user is driver or passenger.
Compared with prior art, the invention has the beneficial effects as follows: owing to the user mobile phone positional information in the base station cell, place of telecom operators side is unique and not modifiable, the present invention identifies brush single user based on the position data of base station cell, user mobile phone place, it is not limited to the GPS coordinate information of user, therefore the various brush single files that can effectively identify in the business of calling a taxi are, technical scheme is implemented simply and effectively; While according to position data identification brush single user, the present invention can also be aided with the multiple technologies schemes such as the analysis message registration of user, call behavior or driver's credit, thus brush single user being done selection further, effectively reducing system erroneous judgement, improving recognition efficiency.
Accompanying drawing explanation
Fig. 1 is the flow chart that the present invention identifies brush single user therein by calculating the credit scoring of driver.
Fig. 2 is the concrete calculation flow chart of Fig. 1 step G2.
Fig. 3 is that a kind of identification of the present invention is called a taxi the composition structural representation of the system of brush single user in business.
Fig. 4 is the composition structural representation of credit identification device.
Detailed description of the invention
For making the object, technical solutions and advantages of the present invention clearly, below in conjunction with accompanying drawing, the present invention is described in further detail.
For convenience, it is assumed that driver mobile phone is D, passenger's mobile phone is C. The situation of most normal passenger, in the time period that C and D gets off from getting on the bus to, the location track of two mobile phones is basically identical. Not being then that so the physical location of C is not changed in, and simply by mobile phone client software, mobile phone position information is forged for brush single user, the GPS location of simulation C there occurs change, and data are reported business platform of calling a taxi, to gain subsidy by cheating. But, how the mobile phone client software no matter brushing list person is transformed, the position data (i.e. the position data of base station cell, mobile phone place) of the phone number that telecom operators side records is unique and not modifiable, that is some time point, mobile phone is under the covering of certain base station of telecom operators. Based on this principle, we can obtain position (CELLID) data of base station cell, mobile phone place from telecom operators side, and judge, within the time period called a taxi, whether the CELLID of C or D changes, then may determine that this number belongs to brush single user without change.Therefore, a kind of identification of the present invention is called a taxi the method for brush single user in business, includes:
Step A, extract call a taxi in the order phone number of user's (including driver or passenger) and the beginning of order and deadline, then the described phone number position data in the beginning of order and the base station cell, place between the deadline is obtained to the telecom operation server belonging to subscriber phone number, and do you judge that the position data of described base station cell in the beginning of order and changes between the deadline? if it is not, then described user is brush single user.
The position data that position data is its base station cell, place due to the phone number that telecom operators record, precision is less, even if belonging to same position also have certain error, so whether the present invention can judge whether to belong to same position according to the difference (i.e. distance value between two position datas) between position data within the scope of certain error. Step A directly according to the subscriber phone number beginning at order with complete the position data of the two time point and judge, can farther include:
Step A1, obtain the described phone number position data in the beginning of order and the base station cell, place of deadline point to the telecom operation server belonging to subscriber phone number, and do you judge that the difference of position data of the base station cell of said two time point is less than certain alternate position spike threshold value? if, then illustrating that user mobile phone is constant in the physical location starting to put with the deadline of order, described user is brush single user. Wherein, alternate position spike threshold value can set flexibly according to practical business situation.
In order to effectively reduce system erroneous judgement, the present invention while implementing step A, can also be effectively improved recognition efficiency in conjunction with adopting one or more following technical schemes.
Normal phone number had the change of position within one day, such as owner can go out work, tourism etc., and the mobile phone of brush single user is positioned over a fixing position generally for a long time, it is used only for brush single, that is the position data of this kind of mobile phone will not change within long-time (such as one day 24 hours), therefore, the present invention can also include:
Step B, from belonging to subscriber phone number telecom operation server obtain described phone number base station cell, place within cycle certain time (such as 24 hours) position data, and do you judge that the position data of base station cell in described time cycle difference each other is both less than certain alternate position spike threshold value? if it is, described user is brush single user. Such as, the present invention can inquire about user mobile phone position data of the base station cell of several time points in 24 hours, and whether the base station cell position data comparing each two time point changes, if all without change, then illustrate that this mobile phone is for brushing list.
Owing to the GPS position information of mobile phone terminal can be forged by brush single user by positioning software, the present invention can also according to beginning (or completing) time of order time user mobile phone GPS location whether consistent with physical location, judge whether user is brush single user. Present invention additionally comprises:
Client terminal device of calling a taxi on step C1, user mobile phone reads the GPS location data of user mobile phone in beginning (or completing) time of order, and described GPS location data is reported business platform of calling a taxi;
Step C2, to the position data in the base station cell, place of beginning (or completing) time of order of the phone number described in the telecom operation server lookup belonging to subscriber phone number, then judge that the difference of the GPS location data of the user mobile phone recorded at the business platform of calling a taxi of same time point and the position data of its base station cell, place is less than certain alternate position spike threshold value?If it is not, then described user is brush single user. The position data precision of the base station cell of the phone number recorded due to telecom operators is less, and the precision of GPS location data is significantly high, so whether can only judge in the certain limit of the position data of base station cell that whether two position datas are consistent according to GPS location data, and strict coupling can not be carried out.
The present invention can also identify brush single user according to whether driver in same order is consistent with the positional information of passenger, and the present invention can also include:
Step D1, extract the phone number of the driver and passenger in order of calling a taxi and beginning (or completing) time of order, then the phone number of the driver and passenger position data in the base station cell, place of beginning (or completing) time of order is obtained respectively to the telecom operation server belonging to the phone number of driver and passenger, and do you judge that the difference of position data of the base station cell of described driver and passenger is less than certain alternate position spike threshold value? if it is not, then continue next step; If it is, this flow process terminates;
Step D2, extract driver and passenger history message registration, do you judge that the phone number of the driver and passenger number of communications in time period exceedes the threshold value of frequent number of communications? if, then representing that driver and passenger is that acquaintance brushes mutually, driver and passenger is brush single user. Likely passenger carrys out chauffeur by client terminal device of calling a taxi, but actual by bus be probably another person, the household of such as cab runner. In order to avoid brushing single erroneous judgement, therefore judge whether the phone number of passenger and driver has communication behavior frequently in history, if it is, expression is brush single file be. The threshold value of frequent number of communications can set flexibly according to actual business requirement.
The present invention identifies brush single user except the above-mentioned positional information according to user, it is also possible to identify brush single user further according to the message registration of user or call behavior. Wherein, brush single user is identified according to the message registration of user, it is also possible to include:
Step E, extract driver and passenger history message registration, and judge whether that the conversation number of repetition and the conversation number number of repetition are more than call circle crossing number threshold value? if, then illustrate that driver and passenger is that acquaintance brushes mutually, driver and passenger is brush single user, and described call circle crossing number threshold value can set according to actual business requirement.
Call behavior according to user identifies brush single numbers, it is also possible to include:
Step F, history message registration according to user, calculate several history call desired value of user, and whether compare each history call desired value one by one lower than corresponding call metrics-thresholds, then the history call desired value number lower than call metrics-thresholds is added up, and do you judge that described number exceedes desired value number threshold value? if it is, described user is brush single user. Generally being likely to due to brush single user use non-mainstream terminal as brush unit device, its mobile phone terminal is difficult to, and can reduce cost so on the one hand, is also prevented from client software identification on the other hand. The present invention is by desired value analysis that the history of a large amount of normal users and brush single user is conversed, it has been found that the DOU (i.e. each household monthly flow amount of consumption) of brush single user, MOU (i.e. average each household monthly air time), talk times, note amount meansigma methods, the moon relationship cycle number, moon base station use number is all well below normal users. With this, history in step F call desired value can include but not limited to: DOU, MOU, talk times, note amount meansigma methods, the moon relationship cycle number, the moon base station use number.
Identifying brush single numbers except that according to position, message registration or call behavior, the present invention can also identify brush single user therein by the credit scoring of calculating driver, as it is shown in figure 1, present invention additionally comprises:
Step G1, several credit indexs selected, described credit index can include but not limited to: cellphone subscriber net duration, use state (shut down/normal/expired), mobile phone set meal service condition, surfing Internet with cell phone accumulation duration, the mobile phone moon duration of call, phone number system of real name information (whether system of real name, have mobile phone/fixed number/broadband number number), the consuming capacity (high, medium and low end subscriber), arrearage amount and arrearage record, enliven geographical position etc. recently;
Step G2, selected multiple sample of users, extract the credit desired value of all sample of users, and calculate the weighted value of each credit index according to the credit desired value of sample of users;
Step G3, weighted value according to the credit desired value of driver and each credit index, calculate the credit scoring of each driver, and therefrom choose the low driver of multiple credit scoring for brush single user.
As in figure 2 it is shown, Fig. 1 step G2 can further include:
Step G21, positive negative correlation according to credit desired value and credit scoring, each credit desired value of all sample of users is adjusted, namely when credit desired value and credit scoring are that (the ARPU value of such as driver is more big in positive correlation, then its credit scoring also should be more high, so ARPU value and credit scoring are positive correlation) time, the Adjustable calculation formula of described credit desired value is:When credit desired value and credit scoring are negative correlation (the arrearage number of times of such as driver are more many, and its credit scoring also should be more low, so arrearage number of times and credit scoring are negative correlation), the Adjustable calculation formula of described credit desired value is:Wherein, xijIt is the jth credit desired value of i-th sample of users, min (xj) it is jth credit index minima in all sample of users, max (xj) it is jth credit index maximum in all sample of users;
Step G22, calculate the probability that each credit desired value of all sample of users occurs under credit index:Wherein, m is selected sample of users sum;
Step G23, calculate the weighted value of each credit index:Wherein, wjBeing the weighted value of jth credit index, n is credit index sum, ejIt is the entropy of jth credit index, ejComputing formula can also be as follows further:
Step G3 can further include:
Calculate the credit scoring of each driver:Wherein, ujBe the jth credit desired value of driver, then the credit scoring of all drivers be ranked up according to order from low to high, finally from the driver ranked the first, order choose Ns�� s% driver, namely selected driver is the brush single user in the business of calling a taxi, wherein, NsBeing all drivers sum, s% is brush single user proportion threshold value, and its value can set according to practical business situation.
The system of brush single user in business as it is shown on figure 3, a kind of identification of the present invention is called a taxi, includes:
Position identification device, for extracting call a taxi in the order phone number of user's (including driver or passenger) and the beginning of order and deadline, then the described phone number position data in the beginning of order and the base station cell, place between the deadline is obtained to the telecom operation server belonging to subscriber phone number, and judge whether the position data of described base station cell changes in the beginning of order with between the deadline, if it is not, then described user is brush single user;
Call intersection identifies device, for extracting the history message registration of driver and passenger in order of calling a taxi, and judge whether that the conversation number of repetition and the conversation number number of repetition are more than call circle crossing number threshold value, if, then illustrate that driver and passenger is that acquaintance brushes mutually, driver and passenger is brush single user, and described call circle crossing number threshold value can set according to actual business requirement;
Call Activity recognition device, for extracting the history message registration of user in order of calling a taxi, calculate several history call desired value of user, and whether compare each history call desired value one by one lower than corresponding call metrics-thresholds, then the history call desired value number lower than call metrics-thresholds is added up, and judge whether described number exceedes desired value number threshold value, if, then user is brush single user, history call desired value can include but not limited to: DOU, MOU, talk times, note amount meansigma methods, month relationship cycle number, moon base station use number, the call metrics-thresholds of each history call desired value can be arranged flexibly according to practical business situation,
Credit identification device, for selecting several credit indexs, selected multiple sample of users again, extract the credit desired value of all sample of users, then the weighted value of each credit index is calculated according to the credit desired value of sample of users, weighted value finally according to the credit desired value of driver and each credit index, calculate the credit scoring of each driver, and therefrom choose the low driver of multiple credit scoring for brush single user, described credit index can include but not limited to: cellphone subscriber is at net duration, use state (shut down/normal/expired), mobile phone set meal service condition, surfing Internet with cell phone accumulation duration, phone number system of real name information (whether system of real name, have mobile phone/fixed number/broadband number number), the mobile phone moon duration of call, the consuming capacity are (high, in, low-end subscribers), arrearage amount and arrearage record, enliven geographical position etc. recently.
Position identification device can further include:
Time point position monitoring unit, for obtaining the described phone number position data in the base station cell, place starting to put of order with the deadline to the telecom operation server belonging to subscriber phone number, and judge that whether the difference of position data of the base station cell of said two time point is less than certain alternate position spike threshold value, if it is, described user is brush single user;
Time cycle position monitoring unit, for obtaining the position data of described phone number base station cell, place within cycle certain time (such as one day 24 hours) from the telecom operation server belonging to subscriber phone number, and judge whether the position data of base station cell in described time cycle difference each other is both less than certain alternate position spike threshold value, if it is, described user is brush single user.
The present invention can also according to beginning (or completing) time of order time, whether the GPS location of user mobile phone consistent with physical location identifies brush single user. Position identification device also includes:
Customer location comparing unit, for to the position data in the base station cell, place of beginning (or completing) time of order of the phone number described in the telecom operation server lookup belonging to subscriber phone number, then judge that whether the difference of the GPS location data of the user mobile phone recorded at the business platform of calling a taxi of same time point and the position data of its base station cell, place is less than certain alternate position spike threshold value, if it is not, then described user is brush single user;
Call a taxi client terminal device, for being arranged on user mobile phone, read the GPS location data of user mobile phone in beginning (or completing) time of order, and described GPS location data is reported business platform of calling a taxi.
The present invention can also identify brush single user according to whether driver in same order is consistent with the positional information of passenger, and position identification device also includes:
Department takes advantage of location comparison unit, for extracting the phone number of driver and passenger in order of calling a taxi, and the beginning of order (or completing) time, then the phone number of the driver and passenger position data in the base station cell, place of beginning (or completing) time of order is obtained respectively to the telecom operation server belonging to the phone number of driver and passenger, and judge that whether the difference of position data of the base station cell of described driver and passenger is less than certain alternate position spike threshold value, if not, then continue to extract the history message registration of driver and passenger, judge whether the phone number of the driver and passenger number of communications in time period exceedes the threshold value of frequent number of communications, if, then represent that driver and passenger is that acquaintance brushes mutually, driver and passenger is brush single user.
As shown in Figure 4, credit identification device can further include index weights computing unit and brush single user recognition unit, and described index weights computing unit has farther included:
Desired value calculating unit, for the positive negative correlation according to credit desired value and credit scoring, each credit desired value of all sample of users is adjusted, namely when credit desired value and credit scoring are that (the ARPU value of such as driver is more big in positive correlation, then its credit scoring also should be more high, so ARPU value and credit scoring are positive correlation) time, the Adjustable calculation formula of described credit desired value is:When credit desired value and credit scoring are negative correlation (the arrearage number of times of such as driver are more many, and its credit scoring also should be more low, so arrearage number of times and credit scoring are negative correlation), the Adjustable calculation formula of described credit desired value is:Wherein, xijIt is the jth credit desired value of i-th sample of users, min (xj) it is jth credit index minima in all sample of users, max (xj) it is jth credit index maximum in all sample of users;
Index probability calculation parts, for calculating the probability that each credit desired value of all sample of users occurs under credit index:Wherein, m is selected sample of users sum;
Weight calculation parts, for calculating the weighted value of each credit index:Wherein, wjBeing the weighted value of jth credit index, n is credit index sum, ejIt is the entropy of jth credit index, ejComputing formula can also be as follows further:
Brush single user recognition unit, for calculating the credit scoring of each driver:Wherein, ujBe the jth credit desired value of driver, then the credit scoring of all drivers be ranked up according to order from low to high, finally from the driver ranked the first, order choose Ns�� s% driver, namely selected driver is the brush single user in the business of calling a taxi, wherein, NsBeing all drivers sum, s% is brush single user proportion threshold value, and its value can set according to practical business situation.
The foregoing is only presently preferred embodiments of the present invention, not in order to limit the present invention, all within the spirit and principles in the present invention, any amendment of making, equivalent replacement, improvement etc., should be included within the scope of protection of the invention.
Claims (17)
1. an identification is called a taxi the method for brush single user in business, it is characterised in that include:
Step A, extract call a taxi in the order phone number of user and the beginning of order and deadline, then the described phone number position data in the beginning of order and the base station cell, place between the deadline is obtained to the telecom operation server belonging to subscriber phone number, and judge whether the position data of described base station cell changes in the beginning of order with between the deadline, if not, then described user is brush single user, wherein, user is driver or passenger.
2. method according to claim 1, it is characterised in that step A has farther included:
Step A1, obtain the described phone number position data in the beginning of order and the base station cell, place of deadline point to the telecom operation server belonging to subscriber phone number, and judge that whether the difference of position data of the base station cell of said two time point is less than certain alternate position spike threshold value, if it is, described user is brush single user.
3. method according to claim 1, it is characterised in that also include:
Step B, from belonging to subscriber phone number telecom operation server obtain described phone number base station cell, place within cycle certain time position data, and judge whether the position data of base station cell in described time cycle difference each other is both less than certain alternate position spike threshold value, if it is, described user is brush single user.
4. method according to claim 1, it is characterised in that also include:
The GPS location data of the call a taxi client terminal device beginning at order or deadline reading user mobile phone on step C1, user mobile phone, and described GPS location data is reported business platform of calling a taxi;
Step C2, to the starting or the position data of base station cell, place of deadline at order of phone number described in the telecom operation server lookup belonging to subscriber phone number, then judge that whether the difference of the GPS location data of the user mobile phone recorded at the business platform of calling a taxi of same time point and the position data of its base station cell, place is less than certain alternate position spike threshold value, if it is not, then described user is brush single user.
5. method according to claim 1, it is characterised in that also include:
Step D1, extract call a taxi in the order phone number of driver and passenger and the beginning of order or deadline, then the phone number of driver and passenger starting or the position data of base station cell, place of deadline at order is obtained respectively to the telecom operation server belonging to the phone number of driver and passenger, and judge that whether the difference of position data of the base station cell of described driver and passenger is less than certain alternate position spike threshold value, if it is not, then continue next step; If it is, this flow process terminates;
Step D2, extract driver and passenger history message registration, it is judged that whether the phone number of driver and passenger number of communications in time period exceedes the threshold value of frequent number of communications, if it is, driver and passenger is brush single user.
6. method according to claim 1, it is characterised in that also include:
Step E, extract driver and passenger history message registration, and judge whether repetition conversation number and repeat conversation number number more than call circle crossing number threshold value, if it is, driver and passenger is brush single user.
7. method according to claim 1, it is characterised in that also include:
Step F, history message registration according to user, calculate several history call desired value of user, and whether compare each history call desired value one by one lower than corresponding call metrics-thresholds, then the history call desired value number lower than call metrics-thresholds is added up, and judge whether described number exceedes desired value number threshold value, if, then described user is brush single user, described history call desired value include but not limited to: DOU, MOU, talk times, note amount meansigma methods, the moon relationship cycle number, the moon base station use number.
8. method according to claim 1, it is characterised in that also include:
Step G1, several credit indexs selected, described credit index includes but not limited to: cellphone subscriber net duration, use state, mobile phone set meal service condition, surfing Internet with cell phone accumulation duration, the mobile phone moon duration of call, phone number system of real name information, the consuming capacity, arrearage amount and arrearage record, enliven geographical position recently;
Step G2, selected multiple sample of users, extract the credit desired value of all sample of users, and calculate the weighted value of each credit index according to the credit desired value of sample of users;
Step G3, weighted value according to the credit desired value of driver and each credit index, calculate the credit scoring of each driver, and therefrom choose the low driver of multiple credit scoring for brush single user.
9. method according to claim 8, it is characterised in that step G2 has farther included:
Step G21, positive negative correlation according to credit desired value and credit scoring, be adjusted each credit desired value of all sample of users, and namely when credit desired value and credit scoring are positive correlation, the Adjustable calculation formula of described credit desired value is:When credit desired value and credit scoring are negative correlation, the Adjustable calculation formula of described credit desired value is:Wherein, xijIt is the jth credit desired value of i-th sample of users, min (xj) it is jth credit index minima in all sample of users, max (xj) it is jth credit index maximum in all sample of users;
Step G22, calculate the probability that each credit desired value of all sample of users occurs under credit index:Wherein, m is selected sample of users sum;
Step G23, calculate the weighted value of each credit index:Wherein, wjBeing the weighted value of jth credit index, n is credit index sum, ejIt is the entropy of jth credit index, ejComputing formula as follows further:
10. method according to claim 8, it is characterised in that step G3 has farther included:
Calculate the credit scoring of each driver:Wherein, wjIt is the weighted value of jth credit index, ujBe the jth credit desired value of driver, then the credit scoring of all drivers be ranked up according to order from low to high, finally from the driver ranked the first, order choose Ns�� s% driver, namely selected driver is the brush single user in the business of calling a taxi, wherein, NsBeing all drivers sum, s% is brush single user proportion threshold value.
The system of brush single user in business 11. an identification is called a taxi, it is characterised in that include:
Position identification device, for extracting in order of calling a taxi the phone number of user and the beginning of order and deadline, then the described phone number position data in the beginning of order and the base station cell, place between the deadline is obtained to the telecom operation server belonging to subscriber phone number, and judge whether the position data of described base station cell changes in the beginning of order with between the deadline, if not, then described user is brush single user, and wherein, user is driver or passenger.
12. system according to claim 11, it is characterised in that position identification device farther includes following one or more unit:
Time point position monitoring unit, for obtaining the described phone number position data in the base station cell, place starting to put of order with the deadline to the telecom operation server belonging to subscriber phone number, and judge that whether the difference of position data of the base station cell of said two time point is less than certain alternate position spike threshold value, if, then described user is brush single user
Time cycle position monitoring unit, for obtaining the position data of described phone number base station cell, place within cycle certain time from the telecom operation server belonging to subscriber phone number, and judge whether the position data of base station cell in described time cycle difference each other is both less than certain alternate position spike threshold value, if it is, described user is brush single user.
13. system according to claim 11, it is characterised in that position identification device also includes:
Customer location comparing unit, for to the starting or the position data of base station cell, place of deadline at order of phone number described in the telecom operation server lookup belonging to subscriber phone number, then judge that whether the difference of the GPS location data of the user mobile phone recorded at the business platform of calling a taxi of same time point and the position data of its base station cell, place is less than certain alternate position spike threshold value, if it is not, then described user is brush single user;
Call a taxi client terminal device, for being arranged on user mobile phone, order start or the deadline reads the GPS location data of user mobile phone, and described GPS location data is reported business platform of calling a taxi.
14. system according to claim 11, it is characterised in that position identification device also includes:
Department takes advantage of location comparison unit, for extracting the phone number of driver and passenger in order of calling a taxi, and the beginning of order or deadline, then the phone number of driver and passenger starting or the position data of base station cell, place of deadline at order is obtained respectively to the telecom operation server belonging to the phone number of driver and passenger, and judge that whether the difference of position data of the base station cell of described driver and passenger is less than certain alternate position spike threshold value, if not, then continue to extract the history message registration of driver and passenger, judge whether the phone number of the driver and passenger number of communications in time period exceedes the threshold value of frequent number of communications, if, then driver and passenger is brush single user.
15. system according to claim 11, it is characterised in that also include following one or more devices:
Call intersection identifies device, for extracting the history message registration of driver and passenger in order of calling a taxi, and judge whether that the conversation number of repetition and the conversation number number of repetition are more than call circle crossing number threshold value, if, then driver and passenger is brush single user
Call Activity recognition device, for extracting the history message registration of user in order of calling a taxi, calculate several history call desired value of user, and whether compare each history call desired value one by one lower than corresponding call metrics-thresholds, then the history call desired value number lower than call metrics-thresholds is added up, and judge whether described number exceedes desired value number threshold value, if, then user is brush single user, described history call desired value include but not limited to: DOU, MOU, talk times, note amount meansigma methods, the moon relationship cycle number, the moon base station use number
Credit identification device, for selecting several credit indexs, selected multiple sample of users again, extract the credit desired value of all sample of users, then the weighted value of each credit index is calculated according to the credit desired value of sample of users, weighted value finally according to the credit desired value of driver and each credit index, calculate the credit scoring of each driver, and therefrom choose the low driver of multiple credit scoring for brush single user, described credit index includes but not limited to: cellphone subscriber is at net duration, use state, mobile phone set meal service condition, surfing Internet with cell phone accumulation duration, phone number system of real name information, the mobile phone moon duration of call, the consuming capacity, arrearage amount and arrearage record, enliven geographical position recently.
16. system according to claim 15, it is characterised in that credit identification device includes index weights computing unit, and described index weights computing unit has farther included:
Desired value calculating unit, for the positive negative correlation according to credit desired value and credit scoring, each credit desired value of all sample of users is adjusted, and namely when credit desired value and credit scoring are positive correlation, the Adjustable calculation formula of described credit desired value is:When credit desired value and credit scoring are negative correlation, the Adjustable calculation formula of described credit desired value is:Wherein, xijIt is the jth credit desired value of i-th sample of users, min (xj) it is jth credit index minima in all sample of users, max (xj) it is jth credit index maximum in all sample of users;
Index probability calculation parts, for calculating the probability that each credit desired value of all sample of users occurs under credit index:Wherein, m is selected sample of users sum;
Weight calculation parts, for calculating the weighted value of each credit index:Wherein, wjBeing the weighted value of jth credit index, n is credit index sum, ejIt is the entropy of jth credit index, ejComputing formula as follows further:
17. system according to claim 15, it is characterised in that credit identification device includes:
Brush single user recognition unit, for calculating the credit scoring of each driver:Wherein, wjIt is the weighted value of jth credit index, ujBe the jth credit desired value of driver, then the credit scoring of all drivers be ranked up according to order from low to high, finally from the driver ranked the first, order choose Ns�� s% driver, namely selected driver is the brush single user in the business of calling a taxi, wherein, NsBeing all drivers sum, s% is brush single user proportion threshold value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610064670.9A CN105657659A (en) | 2016-01-29 | 2016-01-29 | Method and system for identifying scalping user in taxi service |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610064670.9A CN105657659A (en) | 2016-01-29 | 2016-01-29 | Method and system for identifying scalping user in taxi service |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105657659A true CN105657659A (en) | 2016-06-08 |
Family
ID=56488128
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610064670.9A Pending CN105657659A (en) | 2016-01-29 | 2016-01-29 | Method and system for identifying scalping user in taxi service |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105657659A (en) |
Cited By (27)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106127505A (en) * | 2016-06-14 | 2016-11-16 | 北京众成汇通信息技术有限公司 | The single recognition methods of a kind of brush and device |
| CN106204077A (en) * | 2016-08-30 | 2016-12-07 | 世纪恒通科技股份有限公司 | The method and system that a kind of online brush that can prevent from calling a taxi is single |
| CN106557955A (en) * | 2016-11-29 | 2017-04-05 | 流量海科技成都有限公司 | Net about car exception order recognition methodss and system |
| CN106960247A (en) * | 2017-03-24 | 2017-07-18 | 中国联合网络通信集团有限公司 | The net about monitoring method of car order, apparatus and system |
| CN106980904A (en) * | 2017-03-24 | 2017-07-25 | 中国联合网络通信集团有限公司 | The net about monitoring method of car order, platform and system |
| CN107026845A (en) * | 2017-01-03 | 2017-08-08 | 阿里巴巴集团控股有限公司 | Task cheating recognition methods and device |
| CN107093090A (en) * | 2016-10-25 | 2017-08-25 | 北京小度信息科技有限公司 | Abnormal user recognition methods and device |
| CN107124391A (en) * | 2016-09-22 | 2017-09-01 | 北京小度信息科技有限公司 | The recognition methods of abnormal behaviour and device |
| CN107146089A (en) * | 2017-03-29 | 2017-09-08 | 北京三快在线科技有限公司 | The single recognition methods of one kind brush and device, electronic equipment |
| CN107169870A (en) * | 2017-05-23 | 2017-09-15 | 上海百林通信网络科技服务股份有限公司 | It is a kind of that the credit discriminating method for preventing that car insurance from cheating is merged by positional information |
| CN107845002A (en) * | 2016-09-18 | 2018-03-27 | 法乐第(北京)网络科技有限公司 | A kind of car operation monitoring 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 |
| CN108416672A (en) * | 2018-05-11 | 2018-08-17 | 试金石信用服务有限公司 | Financial risks appraisal procedure, system, server and storage medium |
| CN108537554A (en) * | 2017-03-02 | 2018-09-14 | 北京嘀嘀无限科技发展有限公司 | Based on positioning the brush single anti-cheating recognition methods and device of having an injection |
| CN108805601A (en) * | 2018-04-03 | 2018-11-13 | 阿里巴巴集团控股有限公司 | A kind of method, apparatus and equipment for identifying user, account and registering |
| CN108985801A (en) * | 2018-07-09 | 2018-12-11 | 重庆锐云科技有限公司 | channel management method and system |
| WO2019019636A1 (en) * | 2017-07-25 | 2019-01-31 | 平安科技（深圳）有限公司 | User identification method, electronic device, and computer readable storage medium |
| CN110945881A (en) * | 2017-05-18 | 2020-03-31 | 黑莓有限公司 | Detecting improper behavior of intelligent transportation station |
| CN110969861A (en) * | 2019-12-20 | 2020-04-07 | 中国移动通信集团黑龙江有限公司 | Vehicle identification method, device, equipment and computer storage medium |
| CN111209512A (en) * | 2020-01-03 | 2020-05-29 | 北京同邦卓益科技有限公司 | User identification method, device and equipment |
| WO2020142085A1 (en) * | 2018-12-31 | 2020-07-09 | Didi Research America, Llc | Systems and methods for fraud detecting in a transportation service |
| 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 |
| US11038877B2 (en) | 2018-12-31 | 2021-06-15 | Beijing Didi Infinity Technology And Development Co., Ltd. | Systems and methods for device fingerprint determination in a transportation service |
| US11080509B2 (en) | 2018-12-31 | 2021-08-03 | Beijing Didi Infinity Technology And Development Co., Ltd. | Systems and methods for onboard fraud detection in a transportation service |
| CN113408952A (en) * | 2021-07-16 | 2021-09-17 | 首约科技(北京)有限公司 | Driver motivation judgment method |
| 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 |
| CN108985801B (en) * | 2018-07-09 | 2024-07-05 | 重庆锐云科技有限公司 | Channel management method and system |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103796207A (en) * | 2012-11-02 | 2014-05-14 | 中国移动通信集团上海有限公司 | Method and device for identifying false subscriber number |
| CN104869638A (en) * | 2015-05-28 | 2015-08-26 | 北京嘀嘀无限科技发展有限公司 | Detection method and device for GPS coordinate cheating |
-
2016
- 2016-01-29 CN CN201610064670.9A patent/CN105657659A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103796207A (en) * | 2012-11-02 | 2014-05-14 | 中国移动通信集团上海有限公司 | Method and device for identifying false subscriber number |
| CN104869638A (en) * | 2015-05-28 | 2015-08-26 | 北京嘀嘀无限科技发展有限公司 | Detection method and device for GPS coordinate cheating |
Cited By (35)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106127505A (en) * | 2016-06-14 | 2016-11-16 | 北京众成汇通信息技术有限公司 | The single recognition methods of a kind of brush and device |
| CN106204077A (en) * | 2016-08-30 | 2016-12-07 | 世纪恒通科技股份有限公司 | The method and system that a kind of online brush that can prevent from calling a taxi is single |
| CN106204077B (en) * | 2016-08-30 | 2023-04-18 | 世纪恒通科技股份有限公司 | Method and system for preventing taxi taking from online ticket swiping |
| CN107845002A (en) * | 2016-09-18 | 2018-03-27 | 法乐第(北京)网络科技有限公司 | A kind of car operation monitoring method and device |
| CN107124391A (en) * | 2016-09-22 | 2017-09-01 | 北京小度信息科技有限公司 | The recognition methods of abnormal behaviour and device |
| CN107093090A (en) * | 2016-10-25 | 2017-08-25 | 北京小度信息科技有限公司 | Abnormal user recognition methods and device |
| CN106557955A (en) * | 2016-11-29 | 2017-04-05 | 流量海科技成都有限公司 | Net about car exception order recognition methodss and system |
| CN107026845B (en) * | 2017-01-03 | 2020-04-28 | 阿里巴巴集团控股有限公司 | Task cheating behavior identification method and device |
| CN107026845A (en) * | 2017-01-03 | 2017-08-08 | 阿里巴巴集团控股有限公司 | Task cheating recognition methods and device |
| CN108537554A (en) * | 2017-03-02 | 2018-09-14 | 北京嘀嘀无限科技发展有限公司 | Based on positioning the brush single anti-cheating recognition methods and device of having an injection |
| CN106980904A (en) * | 2017-03-24 | 2017-07-25 | 中国联合网络通信集团有限公司 | The net about monitoring method of car order, platform and system |
| CN106960247A (en) * | 2017-03-24 | 2017-07-18 | 中国联合网络通信集团有限公司 | The net about monitoring method of car order, apparatus and system |
| CN106960247B (en) * | 2017-03-24 | 2020-11-10 | 中国联合网络通信集团有限公司 | Monitoring method, device and system for network taxi appointment orders |
| CN106980904B (en) * | 2017-03-24 | 2020-07-31 | 中国联合网络通信集团有限公司 | Monitoring method, platform and system for network taxi appointment orders |
| CN107146089A (en) * | 2017-03-29 | 2017-09-08 | 北京三快在线科技有限公司 | The single recognition methods of one kind brush and device, electronic equipment |
| CN107146089B (en) * | 2017-03-29 | 2020-11-13 | 北京三快在线科技有限公司 | Method and device for identifying bill swiping and electronic equipment |
| CN110945881A (en) * | 2017-05-18 | 2020-03-31 | 黑莓有限公司 | Detecting improper behavior of intelligent transportation station |
| US11146408B2 (en) | 2017-05-18 | 2021-10-12 | Blackberry Limited | Detecting misbehavior of intelligent transport stations |
| CN107169870A (en) * | 2017-05-23 | 2017-09-15 | 上海百林通信网络科技服务股份有限公司 | It is a kind of that the credit discriminating method for preventing that car insurance from cheating is merged by positional information |
| WO2019019636A1 (en) * | 2017-07-25 | 2019-01-31 | 平安科技（深圳）有限公司 | User identification method, electronic device, and computer readable storage medium |
| 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 |
| CN108805601A (en) * | 2018-04-03 | 2018-11-13 | 阿里巴巴集团控股有限公司 | A kind of method, apparatus and equipment for identifying user, account and registering |
| CN108416672A (en) * | 2018-05-11 | 2018-08-17 | 试金石信用服务有限公司 | Financial risks appraisal procedure, system, server and storage medium |
| CN108985801A (en) * | 2018-07-09 | 2018-12-11 | 重庆锐云科技有限公司 | channel management method and system |
| CN108985801B (en) * | 2018-07-09 | 2024-07-05 | 重庆锐云科技有限公司 | Channel management method and system |
| WO2020142085A1 (en) * | 2018-12-31 | 2020-07-09 | Didi Research America, Llc | Systems and methods for fraud detecting in a transportation service |
| CN112823348A (en) * | 2018-12-31 | 2021-05-18 | 北京嘀嘀无限科技发展有限公司 | System and method for on-board fraud detection in transportation services |
| US11038877B2 (en) | 2018-12-31 | 2021-06-15 | Beijing Didi Infinity Technology And Development Co., Ltd. | Systems and methods for device fingerprint determination in a transportation service |
| US11080509B2 (en) | 2018-12-31 | 2021-08-03 | Beijing Didi Infinity Technology And Development Co., Ltd. | Systems and methods for onboard fraud detection in a transportation service |
| CN110969861A (en) * | 2019-12-20 | 2020-04-07 | 中国移动通信集团黑龙江有限公司 | Vehicle identification method, device, equipment and computer storage medium |
| CN111209512A (en) * | 2020-01-03 | 2020-05-29 | 北京同邦卓益科技有限公司 | User identification method, device and equipment |
| 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 |
| 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 |
| CN113408952A (en) * | 2021-07-16 | 2021-09-17 | 首约科技(北京)有限公司 | Driver motivation judgment method |
| 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 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105657659A (en) | Method and system for identifying scalping user in taxi service | |
| Leng et al. | Analysis of taxi drivers' behaviors within a battle between two taxi apps | |
| CN109429230B (en) | Communication fraud identification method and system | |
| Blumenstock et al. | Divided we call: disparities in access and use of mobile phones in Rwanda | |
| CN106557955A (en) | Net about car exception order recognition methodss and system | |
| CN103035117B (en) | The method and system that taxi intelligent electricity is recruited | |
| CN101370187A (en) | Position advertisement service mass-decentralized method and system based on area policy | |
| CN105741161A (en) | Method and system for recognizing click farming users in taxi businesses on basis of driver credit | |
| CN102083043B (en) | Method and relevant device for determining expense discount program provided for user | |
| CN104636439A (en) | Method and device for analyzing user social relation | |
| CN101620716A (en) | Payment real-time question answering system and method | |
| CN108154566B (en) | Intelligent card punching method and device | |
| CN109087132B (en) | Knowledge graph-based user question pushing method and device | |
| CN103092863A (en) | Questionnaire data processing method | |
| CN101557582B (en) | Method and device for mobile communication user information statistics | |
| CN106303951A (en) | Advertisement placement method, platform and the network equipment | |
| CN105323322A (en) | Information pushing method and device | |
| CN102711076A (en) | Method for forecasting mobile phone credit remaining in real time | |
| CN102014364A (en) | Semiautomatic charging accuracy testing method based on virtual call test | |
| CN111104468B (en) | Method for deducing user activity based on semantic track | |
| CN101282500B (en) | Control method and system for increment service supporting multiple access modes | |
| CN107844986A (en) | One kind uses car order pricing method and server | |
| CN107862400A (en) | Scheduling method and device | |
| CN111327661A (en) | Pushing method, pushing device, server and computer readable storage medium | |
| CN105205605B (en) | Interactive service system of city intelligent portal terminal and electric power marketing terminal |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160608 |
|
| RJ01 | Rejection of invention patent application after publication |