CN109191140B - Grading card model integration method and device - Google Patents
Grading card model integration method and device Download PDFInfo
- Publication number
- CN109191140B CN109191140B CN201810732452.7A CN201810732452A CN109191140B CN 109191140 B CN109191140 B CN 109191140B CN 201810732452 A CN201810732452 A CN 201810732452A CN 109191140 B CN109191140 B CN 109191140B
- Authority
- CN
- China
- Prior art keywords
- account
- score
- historical
- mobile phone
- scoring
- 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.)
- Active
Links
Images
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
- G06Q30/018—Certifying business or products
-
- 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
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
Landscapes
- Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Engineering & Computer Science (AREA)
- Finance (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Game Theory and Decision Science (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
A scoring card model integration method and device are disclosed. A scoring card model integration method, comprising: determining a real-time scoring card model, a history scoring card model and a health scoring card model to be integrated, wherein the real-time scoring card model, the history scoring card model and the health scoring card model respectively have 1 output value, which is respectively as follows: real-time scoring, historical scoring and health scoring; acquiring a registered account and a corresponding account identifier within a preset time period from a registered account history record, wherein each account identifier comprises: the real-time scoring card model, the history scoring card model and the health degree scoring card model are used for real-time scoring, historical scoring and health degree scoring of the account identification; and taking the obtained registered account and the corresponding account identification as an integration model training sample, and training the sample by using a supervised learning algorithm to obtain an integration model, wherein the integration model is used for identifying a malicious account.
Description
Technical Field
The embodiment of the specification relates to the technical field of internet, in particular to a scoring card model integration method and device.
Background
With the continuous development of internet technology, various application systems, such as e-commerce systems, are increasing. The user generally needs to register an account as a user of the application system, for example, the account is registered by using a common email box, the account can be used as virtual identification information of the user, and the user can log in the application system through the account to use resources provided by the application system or to perform related activities.
In practical applications, a number of malicious users register accounts in large quantities (such a large-quantity registered account may be called a malicious account) so as to steal resources provided by an application system or perform some illegal activities, such as participating in cheating, fraud, applying marketing funds, gambling, and the like. Taking the e-commerce system as an example, a malicious user can log in the e-commerce system through a large number of registered malicious accounts, so that the user can swipe a bill in the e-commerce system for many times. It is therefore desirable for the application system to identify the malicious account.
Disclosure of Invention
In view of the above technical problems, an embodiment of the present specification provides a method and an apparatus for integrating score card models, and the technical scheme is as follows:
a scoring card model integration method, comprising:
determining a real-time scoring card model, a history scoring card model and a health scoring card model to be integrated, wherein the real-time scoring card model, the history scoring card model and the health scoring card model respectively have 1 output value, which is respectively as follows: real-time scoring, historical scoring and health scoring;
acquiring a registered account and a corresponding account identifier within a preset time period from a registered account history record, wherein each account identifier comprises: the real-time scoring card model, the history scoring card model and the health degree scoring card model are used for real-time scoring, historical scoring and health degree scoring of the account identification;
and taking the obtained registered account and the corresponding account identification as an integration model training sample, and training the sample by using a supervised learning algorithm to obtain an integration model, wherein the integration model is used for identifying a malicious account.
A malicious account identification method, the method comprising:
acquiring an account to be identified and an account identifier corresponding to the account to be identified;
calculating corresponding real-time score, historical score and health score for the account identification by using the real-time score card model, the history score card model and the health score card model;
and identifying the real-time score, the historical score and the health score of the account identifier by using the integration model so as to determine whether the account to be identified is a malicious account.
A scoring card model integration device, the device comprising:
the model determination module is used for determining a real-time scoring card model, a history scoring card model and a health degree scoring card model to be integrated, wherein the real-time scoring card model, the history scoring card model and the health degree scoring card model respectively have 1 output value, and the output values are as follows: real-time scoring, historical scoring and health scoring;
an obtaining module, configured to obtain, from a history record of registered accounts, registered accounts and corresponding account identifiers within a preset time period, where, for each account identifier, the obtaining module includes: the real-time scoring card model, the history scoring card model and the health degree scoring card model are used for real-time scoring, historical scoring and health degree scoring of the account identification;
and the training module is used for taking the acquired registered account and the corresponding account identification as an integration model training sample, training the sample by using a supervised learning algorithm to obtain an integration model, and the integration model is used for identifying a malicious account.
An apparatus for malicious account identification, the apparatus comprising:
the system comprises an acquisition module, a storage module and a processing module, wherein the acquisition module is used for acquiring an account to be identified and an account identifier corresponding to the account to be identified;
the score calculation module is used for calculating corresponding real-time scores, historical scores and health scores for the account identification by utilizing the real-time score card model, the history score card model and the health score card model;
and the identification module is used for identifying the real-time score, the historical score and the health score of the account identifier by using the integration model so as to determine whether the account to be identified is a malicious account.
According to the technical scheme provided by the embodiment of the specification, the acquired registered account and the corresponding account identification are used as the integrated model training sample, the sample is trained by using the supervised learning algorithm to obtain the integrated model, the obtained integrated model is used for identifying the account to be identified, and for an application system, the malicious account can be identified.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of embodiments of the invention.
In addition, any one of the embodiments in the present specification is not required to achieve all of the effects described above.
Drawings
In order to more clearly illustrate the embodiments of the present specification or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments described in the embodiments of the present specification, and other drawings can be obtained by those skilled in the art according to the drawings.
Fig. 1 is a diagram illustrating the relationship between an integration model and a real-time score card model, a history score card model and a health score card model according to an embodiment of the present disclosure;
FIG. 2 is a flowchart illustrating an implementation of a scoring card model integration method according to an embodiment of the present disclosure;
FIG. 3 is a flowchart illustrating an implementation of a malicious account identification method according to an embodiment of the present disclosure;
FIG. 4 is a schematic structural diagram of a score card model integration apparatus according to an embodiment of the present disclosure;
fig. 5 is a schematic structural diagram of a malicious account identification apparatus according to an embodiment of the present specification;
fig. 6 is a schematic structural diagram of an apparatus for configuring a device according to an embodiment of the present disclosure.
Detailed Description
Taking the e-commerce system as an example, it is not necessary to have some malicious users register accounts in large quantities, so as to steal resources of the e-commerce system, or to perform some illegal activities, for example, the malicious users can log in the e-commerce system through the malicious accounts registered in large quantities, so as to receive red packets in the e-commerce system for many times, and for example, the malicious users can log in the e-commerce system through the malicious accounts registered in large quantities, so as to swipe bills in the e-commerce system for many times. Therefore, it is urgent to need a solution to identify malicious accounts registered in large quantities.
In view of the above problems, in the embodiments of the present specification, an integration model is obtained by integrating existing score card models, and a malicious account can be identified by using the integration model. The specific technical scheme of the embodiment of the specification is as follows:
the determined scoring card models to be integrated are respectively a real-time scoring card model, a history scoring card model and a health degree scoring card model, wherein the relations between the integration model and the real-time scoring card model, the relation between the integration model and the history scoring card model and the relation between the integration model and the health degree scoring card model are shown in figure 1; acquiring a registered account and a corresponding account identifier within a preset time period from a registered account history record, wherein each account identifier comprises: the real-time scoring card model, the history scoring card model and the health degree scoring card model are used for scoring the account identification in real time, scoring the history and scoring the health degree; and taking the obtained registered account and the corresponding account identification as an integrated model training sample, and training the sample by using a supervised learning algorithm to obtain an integrated model.
Acquiring an account to be identified and an account identifier corresponding to the account to be identified; calculating corresponding real-time scores, historical scores and health scores for the account identification by using the real-time score card model, the history score card model and the health score card model; and identifying the real-time score, the historical score and the health score of the account identifier by using an integration model so as to determine whether the account to be identified is a malicious account.
In order to make those skilled in the art better understand the technical solutions in the embodiments of the present specification, the technical solutions in the embodiments of the present specification will be described in detail below with reference to the drawings in the embodiments of the present specification, and it is obvious that the described embodiments are only a part of the embodiments of the present specification, and not all the embodiments. All other embodiments that can be derived by one of ordinary skill in the art from the embodiments given herein are intended to be within the scope of protection.
The technical solutions provided in the present specification are described below in terms of "integration model construction" and "malicious account identification", respectively.
As shown in fig. 2, a flowchart of a scoring card model integration method provided in the present specification may include the following steps:
s201, determining a real-time score card model, a history score card model and a health score card model to be integrated, wherein the real-time score card model, the history score card model and the health score card model each have 1 output value, which are: real-time scoring, historical scoring and health scoring;
the method comprises the steps of firstly determining a scoring card model needing to participate in integration, such as a real-time scoring card model, a history scoring card model and a health scoring card model, wherein the real-time scoring card model can calculate real-time scoring aiming at account identification and is used for representing the risk condition of a current account corresponding to the account identification, the history scoring card model can calculate history scoring aiming at the account identification and is used for representing the risk condition of a history account corresponding to the account identification, and the health scoring card model can calculate health scoring aiming at the account identification and is used for representing the health condition of the current account and/or the history account corresponding to the account identification. Each scoring card model has a prediction data score of 1 special risk, and a plurality of input characteristics, the prediction output score of the real-time scoring card model can be called real-time scoring, the prediction output score of the history scoring card model can be called history scoring, and the prediction output score of the health scoring card model can be called health scoring.
S202, acquiring the registered account and the corresponding account identifier in the preset time period from the registered account history record, wherein each account identifier comprises: the real-time scoring card model, the history scoring card model and the health degree scoring card model are used for real-time scoring, historical scoring and health degree scoring of the account identification;
for the score card model participating in the integration determined in S201, the registered account and the corresponding account identifier within the preset time period are obtained from the registered account history record, where the registered account and the corresponding account identifier within the preset time period may be the registered account and the corresponding account identifier within a certain time window (for example, the past week, the past year, and the like). For any account identifier i, the data to be acquired includes real-time score, history score and health score of the account identifier i by the real-time score card model, the history score and the health score of the health score card model, as shown in table 1:
| account identification ID | Real-time scoring | Historical scoring | Health score |
| 1 | 0 | 1 | 1 |
| 2 | 0 | 1 | 2 |
| 3 | 1 | 1 | 1 |
TABLE 1
S203, taking the obtained registered account and the corresponding account identification as an integration model training sample, and training the sample by using a supervised learning algorithm to obtain an integration model, wherein the integration model is used for identifying a malicious account.
For the registration account and the corresponding account identifier obtained in S202, taking the obtained registration account and the corresponding account identifier as an integration model training sample, training the sample by using a supervised learning algorithm to obtain an integration model, specifically, training the sample by using the supervised learning algorithm to obtain the integration model includes the following steps:
s203a, performing box separation processing on the value ranges of the respective output values of the real-time scoring card model, the history scoring card model and the health degree scoring card model, dividing the value ranges into L, M, N sub-intervals respectively, and dynamically combining L M N point value combinations consisting of real-time scoring, history scoring and health degree scoring, wherein L is more than or equal to 2, M is more than or equal to 2, and N is more than or equal to 2;
the general real-time score card model, the history score card model and the health score card model all have respective value ranges of output values, for example, the value ranges of the output values of the real-time score card model, the history score card model and the health score card model are all 0, 1 and 2, for example, the value range of the output value of the real-time score card model is 0 to 1, the value ranges of the output values of the history score card model are 0, 1 and 2, and the value range of the output value of the health score card model is 0 to 1, which is not limited in the present specification.
The value ranges of the output values of the real-time scoring card model, the history scoring card model and the health scoring card model are subjected to binning processing and are respectively divided into L, M, N sub-intervals, and taking the example that the value ranges of the output values of the real-time scoring card model, the history scoring card model and the health scoring card model are 0, 1 and 2, the value ranges of the output values of the real-time scoring card model, the history scoring card model and the health scoring card model are respectively subjected to binning processing and are respectively divided into 3 sub-intervals, and the corresponding sub-intervals can be called binning 1 (comprising 0), binning 2 (comprising 1) and binning 3 (comprising 2). Wherein L is greater than or equal to 2, M is greater than or equal to 2, N is greater than or equal to 2, and L, M, N can be determined according to practical situations, which is not limited in the specification, and L, M, N can be equal or unequal.
After the sub-intervals are divided, L × M × N score combinations composed of real-time score, historical score, and health score are dynamically combined, as described above, the value ranges of the respective output values of the real-time score card model, the history score card model, and the health score card model are divided into 3 sub-intervals, the corresponding sub-intervals may be referred to as "bin 1 (including 0"), bin 2 (including 1), and bin 3 (including 2 "), and the score combinations composed of real-time score, historical score, and health score have 3 × 3 — 27, for example, the score combinations composed of real-time score 1, historical score 1, and health score 1.
S203b, counting the number of registered accounts corresponding to the account identification matched with the score combination for any score combination consisting of real-time score, historical score and health score;
for any score combination composed of real-time score, history score and health score in S203a, the number of registered accounts corresponding to the account id matching the score combination is counted, for example, for the score combination composed of real-time score 1, history score 1 and health score 1, the account ids of real-time score 1, history score 1 and health score 1 are counted in the obtained account ids, and then the number of corresponding registered accounts is counted, for example, in the obtained registered accounts, the account ids corresponding to 10000 registered accounts have real-time score 1, history score 1 and health score 1.
S203c, calculating the authentication rate of the counted registered accounts;
for the registered accounts counted in S203b, the authentication ratio of the counted registered accounts is calculated, for example, for the 10000 registered accounts counted above, where 100 registered accounts are authenticated accounts and 9900 registered accounts are non-authenticated accounts, the authentication ratio of the 10000 registered accounts is 1%.
S203d, if the authentication ratio does not exceed a preset threshold value, determining that the score combination consisting of the real-time score, the historical score and the health score is available;
with respect to the authentication ratio calculated in S203c, it is determined whether the authentication ratio exceeds a preset threshold, and if the authentication ratio does not exceed the preset threshold, it is determined that a score combination consisting of the real-time score, the history score, and the health score is available, that is, the score combination can be used as one of the identification conditions for identifying the malicious account. For example, if the calculated authentication ratio is 1% and the preset threshold is 1%, it is known that the authentication ratio does not exceed the preset threshold, and a score combination consisting of the real-time score 1, the historical score 1, and the health score 1 is available, then all 10000 registered accounts are identified as malicious accounts, where the accuracy is 99%, and if the real-time score of the account to be identified is 1, the historical score is 1, and the health score is 1, then the account to be identified can be identified as a malicious account.
S203e, integrate all available score combinations consisting of real-time scores, historical scores and health scores into an integrated model.
For all available score combinations composed of real-time scores, historical scores and health scores, such as the score combination composed of the real-time score 1, the historical score 1 and the health score 1, all the available score combinations are constructed into an integration model, namely, if any score combination of the real-time scores, the historical scores and the health scores corresponding to the account to be identified is matched with any score combination in the integration model, the account to be identified is determined to be a malicious account.
Specifically, how to identify a malicious account according to the obtained integration model is as follows:
as shown in fig. 3, a flowchart of a malicious account identification method provided in this specification may specifically include the following steps:
s301, acquiring an account to be identified and an account identifier corresponding to the account to be identified;
and for the registered account in the application system, acquiring the registered account, marking the registered account as the account to be identified, and subsequently classifying the registered account into a normal user or a malicious account according to the identification condition. The account to be identified can be obtained, and at the same time, the corresponding account identifier can be obtained, where the account identifier can be an account name, a registered mobile phone number, and the like, and the technical solution of the embodiment of the present specification is described later in the present specification by taking the registered mobile phone number as an example.
S302, calculating corresponding real-time scores, historical scores and health scores for the account identification by using the real-time score card model, the history score card model and the health score card model;
all the available score combinations are constructed into an integration model, if the score combination consisting of the real-time score, the historical score and the health score corresponding to the account to be identified is matched with any score combination in the integration model, the account to be identified is determined to be a malicious account, so that the real-time score, the historical score and the health score corresponding to the account identification are respectively calculated from the real-time dimension, the historical dimension and the health dimension for the account identification corresponding to the account to be identified, and the calculation of the real-time score, the calculation of the historical score and the calculation of the health score are respectively explained as follows:
s302a, calculation of real-time score:
and determining the aggregation condition of the registration account of the number section of the registration mobile phone number, taking the aggregation condition of the registration account of the number section of the registration mobile phone number as the input characteristic of the real-time scoring card model, and calculating the real-time scoring of the registration mobile phone number. The determined aggregation state of the registration account of the section where the registration mobile phone number is located can be an aggregation state within the last few minutes, namely high-frequency aggregation, an aggregation state within the last few hours, namely medium-frequency aggregation, or an aggregation state within the last few days, namely low-frequency aggregation, and the high-frequency aggregation, the medium-frequency aggregation and the low-frequency aggregation can be used as input features of a real-time scoring card model respectively, so that the real-time high-frequency scoring, the real-time medium-frequency scoring and the real-time low-frequency scoring of the registration mobile phone number are calculated, and the three scoring weights are summed to serve as the real-time scoring of the registration mobile phone number.
S302b, calculation of historical score:
determining the malicious account identification condition of a historical account corresponding to the registered mobile phone number and the malicious account identification condition in the history of the number section where the registered mobile phone number is located; and calculating the historical score of the registered mobile phone number by using a historical score card model according to the malicious account identification condition of the historical account corresponding to the registered mobile phone number and the historical malicious account identification condition in the history of the number section where the registered mobile phone number is located.
Specifically, the malicious account identification status of the history account corresponding to the registered mobile phone number (the history account registered by using the mobile phone number) is input as the feature of the history scoring card model, and the score of the history account corresponding to the registered mobile phone number is calculated, for example, if the history account registered by using the mobile phone number is identified as a normal account, the feature is input as the feature of the history scoring card model, and the score of the history account corresponding to the registered mobile phone number is calculated to be 2.
The identification condition of a historical malicious account of the number segment of the registered mobile phone number is used as the characteristic input of the history scoring card model, the score of the history of the number segment of the registered mobile phone number is calculated, for example, 159 mobile phone number segments are taken as an example, 10000 accounts are registered in the past year, wherein the identification rate of the malicious account is 10% when 1000 accounts are identified as the malicious accounts, the characteristic is used as the characteristic input of the history scoring card model, and the score of the history of the number segment of the registered mobile phone number is calculated as 2.
And weighting and summing the score of the historical account corresponding to the registered mobile phone number and the score in the history of the number segment where the registered mobile phone number is located to serve as the historical score of the registered mobile phone number, wherein the score of the historical account corresponding to the registered mobile phone number is attenuated by 1 point, for example, the original 2 points are attenuated by considering that the mobile phone number may have a secondary number release risk, namely, an owner of the mobile phone number may change, and if the time difference between the registration time of the account to be identified and the registration time of the historical account corresponding to the registered mobile phone number exceeds a certain preset time difference.
S302c, calculating the health degree score:
determining the authentication condition of an account to be identified and the authentication condition of a historical account corresponding to the registered mobile phone number; calculating the health degree score of the registered mobile phone number by using a health degree score card model according to the authentication condition of the account to be identified and the authentication condition of the historical account corresponding to the registered mobile phone number, and further determining the historical authentication condition of the number section where the registered mobile phone number is located if the authentication condition of the account to be identified and the authentication condition of the historical account corresponding to the registered mobile phone number are absent; and calculating the health degree score of the registered mobile phone number by using a health degree score card model according to the historical authentication condition of the number section where the registered mobile phone number is located.
Specifically, the authentication status of the historical account corresponding to the registered mobile phone number is input as the characteristic of the health degree scoring card model, and the health degree score of the historical account corresponding to the registered mobile phone number is calculated, for example, the historical account corresponding to the registered mobile phone number passes real-name authentication, the characteristic is input as the characteristic of the health degree scoring card model, and the health degree score of the historical account corresponding to the registered mobile phone number is calculated to be 2 (the higher the score is, the better the health status is).
The authentication status of the account to be identified is used as the characteristic input of the health degree score card model, and the health degree score of the account to be identified is calculated, for example, the user data perfection of the account to be identified is 20%, and the user data fails the real name authentication, and the characteristic can be used as the characteristic input of the health degree score card model, and the health degree score of the account to be identified is calculated to be 1.
And weighting and summing the health degree score of the account to be identified and the health degree score of the historical account corresponding to the registered mobile phone number to serve as the health degree score of the registered mobile phone number.
In addition, if the authentication condition of the account to be identified and the authentication condition of the historical account corresponding to the registered mobile phone number are missing, determining the historical authentication condition of the number section where the registered mobile phone number is located, inputting the historical authentication condition of the number section where the registered mobile phone number is located as the characteristic of a health degree grading card model, and calculating the health degree grade of the registered mobile phone number, for example, taking a 150 mobile phone number section as an example, in the past year, when only 9000 accounts of 10000 accounts pass real name authentication, the authentication rate is 90%, inputting the characteristic as the characteristic of the health degree grading card model, and calculating the health degree grade of the registered mobile phone number.
So far, the calculation of the real-time score, the historical score and the health degree score of the registered mobile phone number is completed, for example, the real-time score is 1, the historical score is 1 and the health degree score is 1.
And S303, identifying the real-time score, the historical score and the health score of the account identifier by using the integration model so as to determine whether the account to be identified is a malicious account.
And aiming at the real-time score, the historical score and the health degree score calculated in the step S302, identifying the real-time score, the historical score and the health degree score of the registered mobile phone number by using an integration model, namely searching whether a score combination matched with the score combination consisting of the real-time score, the historical score and the health degree score of the registered mobile phone number exists in the integration model so as to determine whether the account to be identified is a malicious account. For example, if the calculated real-time score of the registered mobile phone number is 1, the history score is 1, and the health score is 1, and a score combination of the real-time score of 1, the history score of 1, and the health score of 1 is matched in the integration model, it may be determined that the account to be identified corresponding to the registered mobile phone number is a malicious account.
Through the above description of the technical scheme of the embodiment of the present specification, the obtained registered account and the corresponding account identifier are used as an integration model training sample, a supervised learning algorithm is used for training the sample to obtain an integration model, and the obtained integration model is used for identifying the account to be identified. For an application system, a malicious account can be identified based on three dimensions of real time, history and health.
Corresponding to the above method embodiment, an embodiment of the present specification further provides a score card model integration device and a malicious account identification device, which are shown in fig. 4 and 5, and are described in the following decibels:
the scoring card model integrating device may include: a model determination module 410, an acquisition module 420, and a training module 430.
The model determining module 410 is configured to determine a real-time scoring card model, a history scoring card model, and a health scoring card model to be integrated, where the real-time scoring card model, the history scoring card model, and the health scoring card model each have 1 output value, which are: real-time scoring, historical scoring and health scoring;
an obtaining module 420, configured to obtain, from the registered account history record, a registered account and a corresponding account identifier within a preset time period, where for each account identifier, the obtaining module includes: the real-time scoring card model, the history scoring card model and the health degree scoring card model are used for real-time scoring, historical scoring and health degree scoring of the account identification;
the training module 430 is configured to train the sample by using the acquired registered account and the corresponding account identifier as an integration model training sample and using a supervised learning algorithm to obtain an integration model, where the integration model is used to identify a malicious account.
According to a specific embodiment provided by the present specification, the training module 430 is specifically configured to:
carrying out box separation treatment on value ranges of respective output values of the real-time scoring card model, the history scoring card model and the health degree scoring card model, dividing the value ranges into L, M, N sub-intervals respectively, and dynamically combining L M N point value combinations consisting of real-time scoring, historical scoring and health degree scoring, wherein L is more than or equal to 2, M is more than or equal to 2, and N is more than or equal to 2;
for any score combination consisting of real-time scores, historical scores and health scores, counting the number of registered accounts corresponding to account identifications matched with the score combination;
calculating an authentication ratio of the counted registered accounts;
if the authentication ratio does not exceed a preset threshold value, determining that the score combination consisting of the real-time score, the historical score and the health score is available;
all available score combinations consisting of real-time scores, historical scores and health scores are integrated into an integrated model.
The malicious account identification device comprises: an acquisition module 510, a score calculation module 520, and an identification module 530.
An obtaining module 510, configured to obtain an account to be identified and an account identifier corresponding to the account to be identified;
a score calculating module 520, configured to calculate a corresponding real-time score, a historical score, and a health score for the account identifier by using the real-time score card model, the historical score, and the health score card model;
an identifying module 530, configured to identify, by using the integration model, the real-time score, the historical score, and the health score of the account identifier to determine whether the account to be identified is a malicious account.
According to one embodiment provided in the present specification,
the account identification is a registered mobile phone number.
According to a specific embodiment provided in the present specification, the score calculating module 520 includes:
the real-time scoring calculation submodule 521 is used for determining the aggregation condition of the registered account of the number section where the registered mobile phone number is located;
calculating the real-time score of the registered mobile phone number by using the real-time score card model according to the accumulation condition of the registered account of the number section where the registered mobile phone number is located;
a history score calculating submodule 522, configured to determine a malicious account identification condition of a history account corresponding to the registered mobile phone number and a malicious account identification condition in history of a number segment where the registered mobile phone number is located;
according to the malicious account identification condition of the historical account corresponding to the registered mobile phone number and the historical malicious account identification condition in the history of the number segment where the registered mobile phone number is located, calculating the historical score of the registered mobile phone number by using the historical score card model;
a health score calculating sub-module 523 configured to determine an authentication status of the account to be identified and an authentication status of a historical account corresponding to the registered mobile phone number;
and calculating the health degree score of the registered mobile phone number by using the health degree score card model according to the authentication condition of the account to be identified and the authentication condition of the historical account corresponding to the registered mobile phone number.
According to a specific embodiment provided in the present specification, the historical score calculating submodule 522 is specifically configured to:
calculating the grade of the historical account corresponding to the registered mobile phone number by using the history grade card model according to the malicious account identification condition of the historical account corresponding to the registered mobile phone number;
according to the historical identification condition of the malicious account in the history of the number segment of the registered mobile phone number, calculating the score in the history of the number segment of the registered mobile phone number by using the history scoring card model;
and weighting and summing the scores of the historical accounts corresponding to the registered mobile phone numbers and the scores in the history of the number segments where the registered mobile phone numbers are located to be used as the historical scores of the registered mobile phone numbers.
According to a specific embodiment provided in the present specification, the health score calculating submodule 523 is specifically configured to:
calculating the health degree score of the account to be identified by using the health degree score card model according to the authentication condition of the account to be identified;
calculating the health degree score of the historical account corresponding to the registered mobile phone number by using the health degree score card model according to the authentication condition of the historical account corresponding to the registered mobile phone number;
and weighting and summing the health degree score of the account to be identified and the health degree score of the historical account corresponding to the registered mobile phone number to be used as the health degree score of the registered mobile phone number.
According to a specific embodiment provided in the present specification, the health score calculating sub-module 523 is further configured to:
if the authentication condition of the account to be identified and the authentication condition of the historical account corresponding to the registered mobile phone number are missing, determining the historical authentication condition of the number section where the registered mobile phone number is located;
and calculating the health degree score of the registered mobile phone number by using the health degree score card model according to the historical authentication condition of the number segment where the registered mobile phone number is located.
The implementation process of the functions and actions of each module in the above device is specifically described in the implementation process of the corresponding step in the above method, and is not described herein again.
Through the above description of the technical scheme of the embodiment of the present specification, the obtained registered account and the corresponding account identifier are used as an integration model training sample, a supervised learning algorithm is used for training the sample to obtain an integration model, and the obtained integration model is used for identifying the account to be identified. For an application system, a malicious account can be identified based on three dimensions of real time, history and health.
Embodiments of the present specification further provide a computer device, as shown in fig. 6, the computer device may include: a processor 610, a memory 620, an input/output interface 630, a communication interface 640, and a bus 650. Wherein the processor 610, memory 620, input/output interface 630, and communication interface 640 are communicatively coupled to each other within the device via a bus 650.
The processor 610 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an Application Specific Integrated Circuit (ASIC), or one or more Integrated circuits, and is configured to execute related programs to implement the technical solutions provided in the embodiments of the present specification.
The Memory 620 may be implemented in the form of a ROM (Read Only Memory), a RAM (Random Access Memory), a static storage device, a dynamic storage device, or the like. The memory 620 may store an operating system and other application programs, and when the technical solution provided by the embodiments of the present specification is implemented by software or firmware, the relevant program codes are stored in the memory 620 and called by the processor 610 to be executed.
The input/output interface 630 is used for connecting an input/output module to realize information input and output. The i/o module may be configured as a component in a device (not shown) or may be external to the device to provide a corresponding function. The input devices may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output devices may include a display, a speaker, a vibrator, an indicator light, etc.
The communication interface 640 is used for connecting a communication module (not shown in the figure) to realize communication interaction between the device and other devices. The communication module can realize communication in a wired mode (such as USB, network cable and the like) and also can realize communication in a wireless mode (such as mobile network, WIFI, Bluetooth and the like).
It should be noted that although the above-mentioned devices only show the processor 610, the memory 620, the input/output interface 630, the communication interface 640 and the bus 650, in a specific implementation, the devices may also include other components necessary for normal operation. In addition, those skilled in the art will appreciate that the above-described apparatus may also include only those components necessary to implement the embodiments of the present description, and not necessarily all of the components shown in the figures.
Embodiments of the present specification further provide a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the scoring card model integration method is implemented. The method at least comprises the following steps:
a scoring card model integration method, comprising:
determining a real-time scoring card model, a history scoring card model and a health scoring card model to be integrated, wherein the real-time scoring card model, the history scoring card model and the health scoring card model respectively have 1 output value, which is respectively as follows: real-time scoring, historical scoring and health scoring;
acquiring a registered account and a corresponding account identifier within a preset time period from a registered account history record, wherein each account identifier comprises: the real-time scoring card model, the history scoring card model and the health degree scoring card model are used for real-time scoring, historical scoring and health degree scoring of the account identification;
and taking the obtained registered account and the corresponding account identification as an integration model training sample, and training the sample by using a supervised learning algorithm to obtain an integration model, wherein the integration model is used for identifying a malicious account.
Embodiments of the present specification further provide a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the computer program implements the malicious account identification method described above. The method at least comprises the following steps:
a malicious account identification method, the method comprising:
acquiring an account to be identified and an account identifier corresponding to the account to be identified;
calculating corresponding real-time score, historical score and health score for the account identification by using the real-time score card model, the history score card model and the health score card model;
and identifying the real-time score, the historical score and the health score of the account identifier by using the integration model so as to determine whether the account to be identified is a malicious account.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
From the above description of the embodiments, it is clear to those skilled in the art that the embodiments of the present disclosure can be implemented by software plus necessary general hardware platform. Based on such understanding, the technical solutions of the embodiments of the present specification may be essentially or partially implemented in the form of a software product, which may be stored in a storage medium, such as a ROM/RAM, a magnetic disk, an optical disk, etc., and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments of the present specification.
The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. A typical implementation device is a computer, which may take the form of a personal computer, laptop computer, cellular telephone, camera phone, smart phone, personal digital assistant, media player, navigation device, email messaging device, game console, tablet computer, wearable device, or a combination of any of these devices.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the apparatus embodiment, since it is substantially similar to the method embodiment, it is relatively simple to describe, and reference may be made to some descriptions of the method embodiment for relevant points. The above-described apparatus embodiments are merely illustrative, and the modules described as separate components may or may not be physically separate, and the functions of the modules may be implemented in one or more software and/or hardware when implementing the embodiments of the present disclosure. And part or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of the embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
The foregoing is only a specific embodiment of the embodiments of the present disclosure, and it should be noted that, for those skilled in the art, a plurality of modifications and decorations can be made without departing from the principle of the embodiments of the present disclosure, and these modifications and decorations should also be regarded as the protection scope of the embodiments of the present disclosure.
Claims (14)
1. A scoring card model integration method, comprising:
determining a real-time scoring card model, a history scoring card model and a health scoring card model to be integrated, wherein the real-time scoring card model, the history scoring card model and the health scoring card model respectively have 1 output value, which is respectively as follows: real-time scoring, historical scoring and health scoring;
acquiring a registered account and a corresponding account identifier within a preset time period from a registered account history record, wherein each account identifier comprises: the real-time scoring card model, the history scoring card model and the health degree scoring card model are used for real-time scoring, historical scoring and health degree scoring of the account identification;
wherein the account identification comprises a registered mobile phone number; the real-time score is obtained based on the aggregation condition of the registered account of the number section where the registered mobile phone number is located; the historical score is obtained based on the malicious account identification condition of the historical account corresponding to the registered mobile phone number and the malicious account identification condition in the history of the number segment where the registered mobile phone number is located; the health degree score is obtained based on the authentication condition of the account to be identified and the authentication condition of the historical account corresponding to the registered mobile phone number;
taking the obtained registered account and the corresponding account identification as an integrated model training sample, and training the sample by using a supervised learning algorithm to obtain an integrated model, wherein the integrated model comprises the following steps: carrying out box separation treatment on value ranges of respective output values of the real-time scoring card model, the history scoring card model and the health degree scoring card model, dividing the value ranges into L, M, N sub-intervals respectively, and dynamically combining L M N point value combinations consisting of real-time scoring, historical scoring and health degree scoring, wherein L is more than or equal to 2, M is more than or equal to 2, and N is more than or equal to 2; for any score combination consisting of real-time scores, historical scores and health scores, counting the number of registered accounts corresponding to account identifications matched with the score combination; calculating an authentication ratio of the counted registered accounts; if the authentication ratio does not exceed a preset threshold value, determining that the score combination consisting of the real-time score, the historical score and the health score is available; integrating all available score combinations consisting of real-time scores, historical scores and health scores into an integrated model;
the integration model is used to identify malicious accounts.
2. The scoring card model consolidation method according to claim 1, providing a method for identifying a malicious account, comprising:
acquiring an account to be identified and an account identifier corresponding to the account to be identified;
calculating corresponding real-time score, historical score and health score for the account identification by using the real-time score card model, the history score card model and the health score card model;
and identifying the real-time score, the historical score and the health score of the account identification by using the integration model so as to determine whether the account to be identified is a malicious account.
3. The scoring card model integration method according to claim 2, wherein the calculating of the corresponding real-time score, historical score and health score for the account id by using the real-time scoring card model, the historical scoring card model and the health scoring card model comprises:
determining the aggregation condition of the registered account of the number section where the registered mobile phone number is located;
calculating the real-time score of the registered mobile phone number by using the real-time score card model according to the accumulation condition of the registered account of the number section where the registered mobile phone number is located;
determining the malicious account identification condition of the historical account corresponding to the registered mobile phone number and the malicious account identification condition in the history of the number segment where the registered mobile phone number is located;
according to the malicious account identification condition of the historical account corresponding to the registered mobile phone number and the historical malicious account identification condition in the history of the number segment where the registered mobile phone number is located, calculating the historical score of the registered mobile phone number by using the historical score card model;
determining the authentication condition of the account to be identified and the authentication condition of the historical account corresponding to the registered mobile phone number;
and calculating the health degree score of the registered mobile phone number by using the health degree score card model according to the authentication condition of the account to be identified and the authentication condition of the historical account corresponding to the registered mobile phone number.
4. The scoring card model integrating method according to claim 3, wherein the calculating the historical score of the registered mobile phone number by using the historical scoring card model according to the malicious account identification condition of the historical account corresponding to the registered mobile phone number and the historical malicious account identification condition of the number segment where the registered mobile phone number is located comprises:
calculating the grade of the historical account corresponding to the registered mobile phone number by using the history grade card model according to the malicious account identification condition of the historical account corresponding to the registered mobile phone number;
according to the historical identification condition of the malicious account in the history of the number segment of the registered mobile phone number, calculating the score in the history of the number segment of the registered mobile phone number by using the history scoring card model;
and weighting and summing the scores of the historical accounts corresponding to the registered mobile phone numbers and the scores in the history of the number segments where the registered mobile phone numbers are located to be used as the historical scores of the registered mobile phone numbers.
5. The method for integrating the score card model according to claim 3, wherein the calculating the health score of the registered mobile phone number by using the health score card model according to the authentication status of the account to be identified and the authentication status of the historical account corresponding to the registered mobile phone number comprises:
calculating the health degree score of the account to be identified by using the health degree score card model according to the authentication condition of the account to be identified;
calculating the health degree score of the historical account corresponding to the registered mobile phone number by using the health degree score card model according to the authentication condition of the historical account corresponding to the registered mobile phone number;
and weighting and summing the health degree score of the account to be identified and the health degree score of the historical account corresponding to the registered mobile phone number to be used as the health degree score of the registered mobile phone number.
6. The scoring card model integration method of claim 3, further comprising:
if the authentication condition of the account to be identified and the authentication condition of the historical account corresponding to the registered mobile phone number are missing, determining the historical authentication condition of the number section where the registered mobile phone number is located;
and calculating the health degree score of the registered mobile phone number by using the health degree score card model according to the historical authentication condition of the number segment where the registered mobile phone number is located.
7. A scoring card model integration device, the device comprising:
the model determination module is used for determining a real-time scoring card model, a history scoring card model and a health degree scoring card model to be integrated, wherein the real-time scoring card model, the history scoring card model and the health degree scoring card model respectively have 1 output value, and the output values are as follows: real-time scoring, historical scoring and health scoring;
an obtaining module, configured to obtain, from a history record of registered accounts, registered accounts and corresponding account identifiers within a preset time period, where, for each account identifier, the obtaining module includes: the real-time scoring card model, the history scoring card model and the health degree scoring card model are used for real-time scoring, historical scoring and health degree scoring of the account identification;
wherein the account identification comprises a registered mobile phone number; the real-time score is obtained based on the aggregation condition of the registered account of the number section where the registered mobile phone number is located; the historical score is obtained based on the malicious account identification condition of the historical account corresponding to the registered mobile phone number and the malicious account identification condition in the history of the number segment where the registered mobile phone number is located; the health degree score is obtained based on the authentication condition of the account to be identified and the authentication condition of the historical account corresponding to the registered mobile phone number;
the training module is used for training the sample by using the acquired registered account and the corresponding account identifier as an integrated model training sample and utilizing a supervised learning algorithm to obtain an integrated model, and comprises the following steps: carrying out box separation treatment on value ranges of respective output values of the real-time scoring card model, the history scoring card model and the health degree scoring card model, dividing the value ranges into L, M, N sub-intervals respectively, and dynamically combining L M N point value combinations consisting of real-time scoring, historical scoring and health degree scoring, wherein L is more than or equal to 2, M is more than or equal to 2, and N is more than or equal to 2; for any score combination consisting of real-time scores, historical scores and health scores, counting the number of registered accounts corresponding to account identifications matched with the score combination; calculating an authentication ratio of the counted registered accounts; if the authentication ratio does not exceed a preset threshold value, determining that the score combination consisting of the real-time score, the historical score and the health score is available; integrating all available score combinations consisting of real-time scores, historical scores and health scores into an integrated model; the integration model is used to identify malicious accounts.
8. The scoring card model consolidation device according to claim 7, providing a device for identifying a malicious account, comprising:
the system comprises an acquisition module, a storage module and a processing module, wherein the acquisition module is used for acquiring an account to be identified and an account identifier corresponding to the account to be identified;
the score calculation module is used for calculating corresponding real-time scores, historical scores and health scores for the account identification by utilizing the real-time score card model, the history score card model and the health score card model;
and the identification module is used for identifying the real-time score, the historical score and the health score of the account identifier by using the integration model so as to determine whether the account to be identified is a malicious account.
9. The scoring card model integrating device according to claim 8, wherein the scoring computation module comprises:
the real-time scoring calculation sub-module is used for determining the aggregation condition of the registered account of the number section where the registered mobile phone number is located;
calculating the real-time score of the registered mobile phone number by using the real-time score card model according to the accumulation condition of the registered account of the number section where the registered mobile phone number is located;
the history score calculation sub-module is used for determining the malicious account identification condition of the history account corresponding to the registered mobile phone number and the malicious account identification condition in the history of the number segment where the registered mobile phone number is located;
according to the malicious account identification condition of the historical account corresponding to the registered mobile phone number and the historical malicious account identification condition in the history of the number segment where the registered mobile phone number is located, calculating the historical score of the registered mobile phone number by using the historical score card model;
the health degree score calculation sub-module is used for determining the authentication condition of the account to be identified and the authentication condition of the historical account corresponding to the registered mobile phone number;
and calculating the health degree score of the registered mobile phone number by using the health degree score card model according to the authentication condition of the account to be identified and the authentication condition of the historical account corresponding to the registered mobile phone number.
10. The scoring card model integrating device according to claim 9, wherein the historical scoring computation sub-module is specifically configured to:
calculating the grade of the historical account corresponding to the registered mobile phone number by using the history grade card model according to the malicious account identification condition of the historical account corresponding to the registered mobile phone number;
according to the historical identification condition of the malicious account in the history of the number segment of the registered mobile phone number, calculating the score in the history of the number segment of the registered mobile phone number by using the history scoring card model;
and weighting and summing the scores of the historical accounts corresponding to the registered mobile phone numbers and the scores in the history of the number segments where the registered mobile phone numbers are located to be used as the historical scores of the registered mobile phone numbers.
11. The scoring card model integrating device according to claim 9, wherein the health score calculating sub-module is specifically configured to:
calculating the health degree score of the account to be identified by using the health degree score card model according to the authentication condition of the account to be identified;
calculating the health degree score of the historical account corresponding to the registered mobile phone number by using the health degree score card model according to the authentication condition of the historical account corresponding to the registered mobile phone number;
and weighting and summing the health degree score of the account to be identified and the health degree score of the historical account corresponding to the registered mobile phone number to be used as the health degree score of the registered mobile phone number.
12. The scoring card model integration apparatus of claim 9, the health meter operator module further for:
if the authentication condition of the account to be identified and the authentication condition of the historical account corresponding to the registered mobile phone number are missing, determining the historical authentication condition of the number section where the registered mobile phone number is located;
and calculating the health degree score of the registered mobile phone number by using the health degree score card model according to the historical authentication condition of the number segment where the registered mobile phone number is located.
13. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of claim 1 when executing the program.
14. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of any of claims 2 to 6 when executing the program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810732452.7A CN109191140B (en) | 2018-07-05 | 2018-07-05 | Grading card model integration method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810732452.7A CN109191140B (en) | 2018-07-05 | 2018-07-05 | Grading card model integration method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109191140A CN109191140A (en) | 2019-01-11 |
| CN109191140B true CN109191140B (en) | 2022-04-19 |
Family
ID=64936125
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810732452.7A Active CN109191140B (en) | 2018-07-05 | 2018-07-05 | Grading card model integration method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109191140B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110278241B (en) * | 2019-05-09 | 2021-07-16 | 创新先进技术有限公司 | Registration request processing method and device |
| CN110347566B (en) * | 2019-06-25 | 2023-06-30 | 创新先进技术有限公司 | Method and device for evaluating effectiveness of registration wind control model |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104603808A (en) * | 2012-03-30 | 2015-05-06 | 派欧维森私人有限公司 | Payment apparatus and method |
| CN105931051A (en) * | 2015-12-31 | 2016-09-07 | 中国银联股份有限公司 | Safety payment method and apparatus |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8738334B2 (en) * | 2011-04-29 | 2014-05-27 | International Business Machines Corporation | Anomaly detection, forecasting and root cause analysis of energy consumption for a portfolio of buildings using multi-step statistical modeling |
| CN106034149B (en) * | 2015-03-13 | 2019-06-18 | 阿里巴巴集团控股有限公司 | A kind of account recognition methods and device |
| CN104881783A (en) * | 2015-05-14 | 2015-09-02 | 中国科学院信息工程研究所 | E-bank account fraudulent conduct and risk detecting method and system |
| CN106779271A (en) * | 2015-11-23 | 2017-05-31 | 阿里巴巴集团控股有限公司 | Determine the method and device and account risk score method and device of feature of risk |
| CN106897880B (en) * | 2015-12-18 | 2020-12-18 | 创新先进技术有限公司 | Account risk assessment method and equipment |
| CN107872444B (en) * | 2016-09-28 | 2020-11-10 | 阿里巴巴集团控股有限公司 | Identity verification and authentication method and system for network user |
| CN108171519A (en) * | 2016-12-07 | 2018-06-15 | 阿里巴巴集团控股有限公司 | The processing of business datum, account recognition methods and device, terminal |
| CN106651570A (en) * | 2016-12-27 | 2017-05-10 | 中国建设银行股份有限公司 | System and method for real-time loan approval |
| CN107220867A (en) * | 2017-04-20 | 2017-09-29 | 北京小度信息科技有限公司 | object control method and device |
| CN108053120B (en) * | 2017-12-15 | 2020-09-01 | 阿里巴巴集团控股有限公司 | Model integration method and device |
-
2018
- 2018-07-05 CN CN201810732452.7A patent/CN109191140B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104603808A (en) * | 2012-03-30 | 2015-05-06 | 派欧维森私人有限公司 | Payment apparatus and method |
| CN105931051A (en) * | 2015-12-31 | 2016-09-07 | 中国银联股份有限公司 | Safety payment method and apparatus |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109191140A (en) | 2019-01-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109063920B (en) | Transaction risk identification method and device and computer equipment | |
| CN107563429B (en) | Method and device for classifying network user groups | |
| CN109101989B (en) | Merchant classification model construction and merchant classification method, device and equipment | |
| CN109034583B (en) | Abnormal transaction identification method and device and electronic equipment | |
| CN110163612B (en) | Payment wind control method and device | |
| CN110147967B (en) | Risk prevention and control method and device | |
| CN106682906B (en) | Risk identification and service processing method and equipment | |
| CN105991674B (en) | Information pushing method and device | |
| US20210049721A1 (en) | User security awareness detection method and apparatus | |
| CN110691082B (en) | Risk event processing method and device | |
| CN110310129B (en) | Risk identification method and system thereof | |
| CN110930218B (en) | Method and device for identifying fraudulent clients and electronic equipment | |
| CN109064217B (en) | User level-based core body strategy determination method and device and electronic equipment | |
| CN110929799A (en) | Method, electronic device, and computer-readable medium for detecting abnormal user | |
| CN106886906A (en) | A kind of device identification method and device | |
| CN110020025B (en) | Data processing method and device | |
| CN110334936B (en) | Method, device and equipment for constructing credit qualification scoring model | |
| CN109635953A (en) | A kind of feature deriving method, device and electronic equipment | |
| CN111475853A (en) | Model training method and system based on distributed data | |
| CN109191140B (en) | Grading card model integration method and device | |
| CN108053214B (en) | False transaction identification method and device | |
| WO2019100771A1 (en) | Question pushing method and device | |
| CN109325015B (en) | Method and device for extracting characteristic field of domain model | |
| CN110033276A (en) | It is a kind of for security strategy generation method, device and the equipment transferred accounts | |
| CN108985831B (en) | Offline transaction distinguishing method and device and computer equipment |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20200927 Address after: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman Islands Applicant after: Innovative advanced technology Co.,Ltd. Address before: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman Islands Applicant before: Advanced innovation technology Co.,Ltd. Effective date of registration: 20200927 Address after: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman Islands Applicant after: Advanced innovation technology Co.,Ltd. Address before: A four-storey 847 mailbox in Grand Cayman Capital Building, British Cayman Islands Applicant before: Alibaba Group Holding Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |