CN110362981B - Method and system for judging abnormal behavior based on trusted device fingerprint - Google Patents
Method and system for judging abnormal behavior based on trusted device fingerprint Download PDFInfo
- Publication number
- CN110362981B CN110362981B CN201910581340.0A CN201910581340A CN110362981B CN 110362981 B CN110362981 B CN 110362981B CN 201910581340 A CN201910581340 A CN 201910581340A CN 110362981 B CN110362981 B CN 110362981B
- Authority
- CN
- China
- Prior art keywords
- user
- equipment
- attribution
- behavior
- fingerprint
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
- G06F18/2155—Generating training patterns; Bootstrap methods, e.g. bagging or boosting characterised by the incorporation of unlabelled data, e.g. multiple instance learning [MIL], semi-supervised techniques using expectation-maximisation [EM] or naïve labelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/31—User authentication
- G06F21/32—User authentication using biometric data, e.g. fingerprints, iris scans or voiceprints
-
- 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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Finance (AREA)
- General Engineering & Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- Data Mining & Analysis (AREA)
- Accounting & Taxation (AREA)
- Computer Hardware Design (AREA)
- Development Economics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention discloses a method and a system for judging abnormal behaviors based on trusted device fingerprints. The method comprises the steps of obtaining attribute data of user operation behaviors; based on the user operation behavior attribute data, obtaining a trusted device fingerprint corresponding to the user through the operation of a user device attribution judgment model; and if the user equipment is found to be subjected to specific operation by other users through the user trusted equipment fingerprint, sending a prompt of abnormal behavior. According to the method and the device, the credible equipment fingerprint corresponding to the user is obtained through the user equipment attribution model according to the user operation behavior attribute data, so that abnormal behaviors can be found, and if the obtained user equipment attribution result is input into other anti-fraud models as a variable, the fraud risk of a client can be judged in an auxiliary mode.
Description
Technical Field
The invention relates to the field of computers, in particular to a method and a system for judging abnormal behaviors based on fingerprints of trusted equipment.
Background
With the vigorous development of internet consumption and finance, people use more and more online platforms to apply for services, and the mobile devices such as mobile phones/PADs and the like are enabled to be important media between users and platforms and between users as main application tools due to fast operation and simple process. Fraud risk is one of the main risks faced by the internet financial industry and is an important link of credit risk management.
The one-to-one correspondence relationship between the mobile devices and the users is always a difficult point of anti-fraud analysis, and some users reduce the information acquisition and increase the fraud risk by using other users' devices, so that it is necessary to determine the trusted devices of the users according to the operation behavior attributes of the users and perform anti-fraud application according to the results of the trusted devices.
The above information disclosed in this background section is only for enhancement of understanding of the background of the disclosure and therefore it may contain information that does not form the prior art that is already known to a person of ordinary skill in the art.
Disclosure of Invention
In view of the above, the present specification has been developed to provide a solution that overcomes, or at least partially solves, the above-mentioned problems.
Additional features and advantages of the present disclosure will be set forth in the detailed description which follows, and in part will be obvious from the description, or may be learned by practice of the present disclosure.
2. In a first aspect, the present specification discloses a method for determining abnormal behavior based on a fingerprint of a trusted device, comprising,
acquiring attribute data of user operation behaviors;
based on the user operation behavior attribute data, obtaining a trusted device fingerprint corresponding to the user through the operation of a user device attribution judgment model;
and if the user equipment is found to be subjected to specific operation by other users through the user trusted equipment fingerprint, sending out a prompt of abnormal behavior.
In an exemplary embodiment of the disclosure, the obtaining, by a user equipment attribution determination model operation based on the user operation behavior attribute data, a trusted device fingerprint corresponding to the user further includes,
and storing the fingerprint of the trusted device in the relationship network information corresponding to the user.
In an exemplary embodiment of the disclosure, the obtaining, by a user equipment attribution determination model operation based on the user operation behavior attribute data, a trusted device fingerprint corresponding to the user further includes,
and taking the fingerprint of the credible equipment and the real-time user information of the equipment as input variables of a loan anti-fraud model.
In an exemplary embodiment of the disclosure, the issuing of the prompt for the abnormal behavior when the user device is found to be operated by other users specifically through the user trusted device fingerprint further includes,
if the particular action is associated with a loan, further verification of the identity of the user using the device is performed.
In an exemplary embodiment of the disclosure, the trusted device is defined as a commonly used device of the user, and the device has no abnormal behavior.
In an exemplary embodiment of the disclosure, the method for obtaining the trusted device fingerprint corresponding to the user through the user device attribution judgment model operation based on the user operation behavior attribute data includes,
constructing a user equipment attribution judgment model based on the user operation behavior attribute data;
acquiring input variables required by the user equipment attribution judgment model; the input variables comprise user operation behaviors;
and calculating by using the user equipment attribution judgment model to obtain a user equipment attribution result.
In an exemplary embodiment of the disclosure, the constructing the user equipment attribution judgment model includes,
and training the user equipment attribution judgment model by adopting a mode of combining supervised learning and semi-supervised learning according to the user operation behavior attribute data.
In an exemplary embodiment of the disclosure, the constructing the user equipment attribution judgment model further comprises,
acquiring user operation sample data;
dividing the user operation sample data into a first labeled sample and a non-labeled sample;
performing supervised learning on the first labeled sample to obtain a first judgment model based on user operation behaviors;
performing semi-supervised learning on the unlabeled sample by using a first judgment model to obtain a second labeled sample;
and performing supervised learning on the first labeled sample and the second labeled sample to obtain a user equipment attribution judgment model based on user operation behaviors.
In an exemplary embodiment of the present disclosure, the acquiring user operation sample data further includes,
the user operation sample data comprises operation behaviors of the user on the equipment, the property of the equipment and the associated information of the equipment.
In an exemplary embodiment of the present disclosure, said dividing the user operation sample data into a first labeled sample and an unlabeled sample further comprises,
and manually marking a part of the obtained user operation sample data for user operation and equipment attribution judgment to serve as a first labeled sample, and leaving the rest part as a non-labeled sample.
In an exemplary embodiment of the present disclosure, the performing the manual marking includes,
and manually judging the one-to-one attribution relationship between the equipment and the user according to the operation behavior attribute of the user and marking.
In an exemplary embodiment of the disclosure, the performing supervised learning on the first labeled sample, obtaining a first judgment model based on user operation behavior further includes,
and averagely dividing the first labeled sample which is used for manually marking the affiliation relationship of equipment and the user based on the attribute of the user operation behavior into two parts, wherein one part is used for supervised learning, and a first judgment model based on the user operation behavior is obtained through cross validation modeling.
In an exemplary embodiment of the disclosure, the performing supervised learning on the first labeled sample and the second labeled sample to obtain a user equipment attribution judgment model based on user operation behavior further includes,
and performing supervised learning on the remaining part of the first labeled sample and the second labeled sample.
In an exemplary embodiment of the disclosure, the semi-supervised learning of unlabeled exemplars using a first decision model, obtaining a second labeled exemplar further comprises,
judging the label-free sample by using a first judgment model based on the operation behavior of the user;
and marking the label-free sample by using the judgment result, wherein the label-free sample is subjected to marking of user operation and equipment attribution, and a second labeled sample is obtained.
In an exemplary embodiment of the disclosure, the marking the non-labeled sample by the user operation and the device attribution using the determination result, obtaining the second labeled sample further includes,
setting a threshold value;
and setting the label with the judgment result larger than the threshold value as 1, otherwise, setting the label as 0.
In an exemplary embodiment of the disclosure, the obtaining the input variables required by the user equipment attribution determination model further comprises,
the method comprises the following steps of operating behavior attributes of a user on the equipment, the attributes of the equipment and equipment association information.
In an exemplary embodiment of the disclosure, the obtaining input variables required by the user equipment attribution prediction model further comprises,
and (3) deriving the variables, wherein the derivation comprises automatic variable derivation and manual variable derivation.
In a second aspect, the present specification discloses a system for determining abnormal behavior based on a fingerprint of a trusted device, comprising,
the user registration information acquisition module is used for acquiring user operation behavior attribute data;
the user equipment attribution judging module is used for obtaining a trusted equipment fingerprint corresponding to the user through user equipment attribution judging model operation based on the user operation behavior attribute data;
and the analysis processing module is used for sending out a prompt of abnormal behavior if the user equipment is found to be subjected to specific operation by other users through the user trusted equipment fingerprint.
In an exemplary embodiment of the disclosure, the user equipment attribution judging module further includes,
and the storage module is used for storing the fingerprint of the trusted device in the relationship network information corresponding to the user.
In an exemplary embodiment of the disclosure, the user equipment attribution judging module further includes,
and the variable input module is used for taking the fingerprint of the trusted device and the real-time user information of the device as input variables of the loan anti-fraud model.
In an exemplary embodiment of the present disclosure, the analysis processing module further includes,
and the identity information verification module is used for further verifying the identity information of the user using the equipment if the specific operation is related to loan.
In an exemplary embodiment of the disclosure, the user device attribution judging model module includes a defining module, configured to define a device that is commonly used by the user and has no abnormal behavior as a trusted device.
In an exemplary embodiment of the present disclosure, the device affiliation determination model module is configured to construct a user device affiliation determination model based on user operation behavior attribute data;
an input variable acquisition module, configured to acquire an input variable required by the ue affiliation determination model; the input variables comprise user operation behaviors;
and the operation module is used for performing operation by using the user equipment attribution judgment model to obtain a user equipment attribution judgment result.
In an exemplary embodiment of the present disclosure, the device attribution determination model module includes,
and the learning unit is used for training the user equipment attribution judgment model by adopting a mode of combining supervised learning and semi-supervised learning according to the user operation behavior attribute data.
In an exemplary embodiment of the present disclosure, the user equipment attribution determination model module further comprises,
the user operation sample data acquisition unit is used for acquiring user operation sample data;
the classification unit is used for dividing the user operation sample data into a first labeled sample and a non-labeled sample;
the first judgment model unit is used for performing supervised learning on the first labeled sample to obtain a first judgment model based on user operation behaviors;
the semi-supervised learning unit is used for carrying out semi-supervised learning on the unlabelled sample by using the first judgment model to obtain a second labeled sample;
and the supervised learning unit is used for carrying out supervised learning on the first labeled sample and the second labeled sample to obtain a user equipment attribution judgment model based on user operation behaviors.
In an exemplary embodiment of the present disclosure, the user operation sample data acquiring unit further includes,
the operation behavior subunit is used for acquiring the operation behavior of the user on the equipment;
the device attribute subunit is used for acquiring the attribute of the device;
and the equipment associated information subunit is used for acquiring the equipment associated information.
In an exemplary embodiment of the present disclosure, the classification unit further includes,
and the manual marking subunit is used for performing manual marking of user operation and equipment attribution judgment on one part of the obtained user operation sample data to serve as a first labeled sample, and the rest part of the obtained user operation sample data is a non-labeled sample.
In an exemplary embodiment of the present disclosure, the manual marking subunit includes,
and manually judging the one-to-one attribution relationship between the equipment and the user according to the operation behavior attribute of the user and marking.
In an exemplary embodiment of the present disclosure, the first judgment model unit further includes,
the label sample equipartition sub-unit is used for averagely dividing the first labeled sample manually marked on the attribution relationship of the equipment and the user based on the attribute of the user operation behavior into two parts, wherein one part is used for supervised learning, and a first judgment model based on the user operation behavior is obtained through cross validation modeling.
In an exemplary embodiment of the disclosure, the user equipment attribution determination model further comprises,
and performing supervised learning on the remaining part of the first labeled sample and the second labeled sample.
In an exemplary embodiment of the present disclosure, the semi-supervised learning unit further includes,
the judging subunit is used for judging the unlabeled sample by using a first judging model based on the user operation behavior;
and the marking subunit is used for marking the label-free sample by using the judgment result through user operation and equipment attribution to obtain a second labeled sample.
In an exemplary embodiment of the present disclosure, the marking subunit further includes,
setting a threshold value;
and setting the label with the judgment result larger than the threshold value as 1, otherwise, setting the label as 0.
In an exemplary embodiment of the present disclosure, the input variable acquiring module further includes,
the method comprises the steps of operating behavior attributes of a user on the equipment, the attributes of the equipment and equipment association information.
In one exemplary embodiment of the present disclosure,
the input variable acquisition module further comprises a variable acquisition module,
and the variable derivation unit is used for deriving the variables, and the derivation comprises automatic variable derivation and manual variable derivation.
In a third aspect, the present specification provides a server comprising a processor and a memory: the memory is used for storing a program of any one of the methods; the processor is configured to execute the program stored in the memory to implement the steps of any of the methods described above.
In a fourth aspect, the present specification provides a computer readable storage medium, on which a computer program is stored, which when executed by a processor implements the steps of any of the above methods.
The invention has the positive effects that: the invention judges the credible equipment through the user equipment attribution model, inputs the obtained user equipment attribution result as a variable into other anti-fraud models, and can assist in judging the fraud risk of the client. The judged result can also be used for perfecting the relationship network information of the user; or the core body strategy is strengthened when the user does not use the personal device during borrowing; also, in the anti-fraud model of the borrowing phase, entering a variable as to whether the customer is the owner of the borrowing equipment may assist in assessing the risk of fraud for the user.
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 the disclosure.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a flow diagram illustrating a method for determining anomalous behavior based on a trusted device fingerprint in accordance with an exemplary embodiment.
FIG. 2 is a diagram illustrating supervised learning in user equipment decision model training in the method of FIG. 1.
FIG. 3 is a framework of the model in the method of FIG. 1.
FIG. 4 is a block diagram illustrating an apparatus for determining anomalous behavior based on a trusted device fingerprint in accordance with another exemplary embodiment.
FIG. 5 is a block diagram illustrating a server in accordance with an example embodiment.
Detailed Description
The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.
The example embodiments described below may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art. The same reference numerals denote the same or similar parts in the drawings, and thus, a repetitive description thereof will be omitted.
Furthermore, the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the disclosure. One skilled in the relevant art will recognize, however, that the subject matter of the present disclosure can be practiced without one or more of the specific details, or with other methods, components, devices, steps, and so forth. In other instances, well-known methods, devices, implementations, or operations have not been shown or described in detail to avoid obscuring aspects of the disclosure.
The block diagrams shown in the figures are functional entities only and do not necessarily correspond to physically separate entities. I.e. these functional entities may be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor means and/or microcontroller means.
The flow charts shown in the drawings are merely illustrative and do not necessarily include all of the contents and operations/steps, nor do they necessarily have to be performed in the order described. For example, some operations/steps may be decomposed, and some operations/steps may be combined or partially combined, so that the actual execution sequence may be changed according to the actual situation.
It will be understood that, although the terms first, second, third, etc. may be used herein to describe various components, these components should not be limited by these terms. These terms are used to distinguish one element from another. Thus, a first component discussed below could be termed a second component without departing from the teachings of the disclosed concepts. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
It is to be understood by those skilled in the art that the drawings are merely schematic representations of exemplary embodiments, and that the blocks or processes shown in the drawings are not necessarily required to practice the present disclosure and are, therefore, not intended to limit the scope of the present disclosure.
The invention provides a method for judging abnormal behaviors based on fingerprints of trusted equipment, which is used for solving the problems that the trusted equipment cannot be judged and fraud is prevented according to a judgment result in the prior art, and in order to solve the problems, the general idea of the invention is as follows:
a method for determining abnormal behavior based on a trusted device fingerprint, comprising,
acquiring attribute data of user operation behaviors;
based on the user operation behavior attribute data, obtaining a trusted device fingerprint corresponding to the user through user device attribution judgment model operation;
and if the user equipment is found to be subjected to specific operation by other users through the user trusted equipment fingerprint, sending a prompt of abnormal behavior.
According to the method and the device, the credible device fingerprint corresponding to the user is obtained through the user device attribution model according to the user operation behavior attribute data, so that abnormal behaviors can be found, and if the obtained user device attribution result is input into other anti-fraud models as a variable, the fraud risk of a client can be judged in an auxiliary manner.
In the embodiments of the present invention, the terms referred to are:
the term "and/or" herein is merely an association relationship describing an associated object, and means that there may be three relationships, for example, a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" herein generally indicates that the former and latter related objects are in an "or" relationship.
The technical solution of the present invention will be described and explained in detail by means of several specific examples.
Referring to fig. 1, a method for determining abnormal behavior based on a fingerprint of a trusted device, comprising,
s101, acquiring attribute data of user operation behaviors;user operation behavior attribute data history input variables of the user equipment attribution judgment model comprise behaviors of different equipment used by a user, the attribute of the equipment and the like.
S102, obtaining a pair through the operation of a user equipment attribution judgment model based on the user operation behavior attribute data Should the user's trusted device fingerprint(ii) a The trusted device is defined as a common device of a user, and the device has no abnormal behavior.
One of the applications regarding the derived trusted device fingerprint is: and storing the fingerprint of the trusted device in the relationship network information corresponding to the user for perfecting the relationship network information of the user, so that the user can be more clearly and comprehensively known.
The second application for the derived trusted device fingerprint is: the trusted device fingerprint and the device use the user information in real time as input variables of a loan anti-fraud model, so that the fraud risk of the user can be evaluated in an auxiliary mode.
In this step, the construction of the ue attribution determination model is very important. The construction idea of the model is explained in detail as follows:
firstly, constructing a user equipment attribution judgment model based on user operation behavior attribute data;
in the step, according to the attribute data of the user operation behavior, a mode of combining supervised learning and semi-supervised learning is adopted to train the attribution judgment module of the user equipment. Specifically, the following method may be adopted:
(a) Acquiring user operation sample data; the selection of the user operation sample data is mainly determined according to user operation, and comprises operation behaviors of the user on the equipment, the attribute of the equipment and equipment associated information.
The difference in the user's operational behavior on the device may reflect which device is the device that we are primarily using, i.e., the device that we are looking for to which the user belongs. For example, the operation sequence of the user on different devices, the device where the user first generates the borrowing action is more likely to be the common device; the number of operations of the user on different devices is also an important variable, such as the number of times the user logs in and borrows from different devices, whether the device has the largest number of operations, and the like.
The device attributes refer to: when the user uses the device, the device name may be set as its own name or nickname, or may be used as a feature for determining the device affiliation, and the higher the similarity between the device name and the name is, the more likely it is that the device is affiliated to the user.
The device association information may reflect the relationship of the associated users, e.g., if the relationship network associations of two devices are very similar, then the two devices may be owned by the same user.
(b) Dividing the user operation sample data into a first labeled sample and a non-labeled sample; the specific method comprises the following steps: and manually marking a part of the obtained user operation sample data for user operation and equipment attribution judgment to serve as a first labeled sample, and remaining part of the obtained user operation sample data is a non-labeled sample. Wherein, the mode of artifical mark does: and manually judging the one-to-one attribution relationship between the equipment and the user according to the operation behavior attribute of the user and marking.
(c) Performing supervised learning on the first labeled sample to obtain a first judgment model based on user operation behaviors; specifically, the first labeled sample marked manually is averagely divided into two parts, wherein one part is used for supervised learning, and a first judgment model based on user operation behaviors is obtained through cross validation modeling.
(d) Performing semi-supervised learning on the unlabeled sample by using a first judgment model to obtain a second labeled sample; the method specifically comprises the following steps: judging the label-free sample by using a first judgment model based on the operation behavior of the user; marking the label-free sample by using the judgment result, wherein the marking method comprises the following steps: setting a threshold value; and setting the label with the judgment result larger than the threshold value as 1, otherwise, setting the label as 0, thereby obtaining a second labeled sample.
(e) And performing supervised learning on the remaining part of the first labeled sample and the second labeled sample to obtain a user equipment attribution judgment model based on user operation behaviors.
Secondly, acquiring input variables required by the user equipment attribution judgment model; the input variables comprise user operation behaviors, specifically, operation behavior attributes of a user on the equipment, the equipment attributes and equipment associated information. Besides obtaining the basic variables, variable derivation is an important link for modeling, and deriving more useful variables helps to improve the effect of the model. The derivation method mainly comprises an automatic derivation method and a manual derivation method. The automatic variable derivation method comprises unique coding, namely a process of splitting a discrete variable into a plurality of two-classification variables; new variables for cross term multiplication, etc. can also be generated using some automatic variable derivation tools (e.g., featuretools, polymomialffeatures, etc.). The manual variable derivation method is mainly to discover new effective variables according to business experience, such as the sequencing variable of the operation time of a client on the equipment, whether the equipment is registered when being used for the first time, and the like.
And finally, calculating by using the user equipment attribution judgment model to obtain a user equipment attribution result.
The model algorithm is a combination of supervised learning and semi-supervised learning, and the analysis accuracy can be continuously improved through the stacking iteration of several layers of models.
S103, if the user equipment is found to be subjected to specific operation by other users through the fingerprint of the user trusted equipment, sending the operation Prompting for abnormal behavior. If the particular action is associated with a loan, further verification of the identity of the user using the device is performed.
As shown in fig. 2, a process of supervised learning training of the model in the process of building the user equipment affiliation determination model is shown. The user equipment attribution judging model mainly adopts a method combining supervised learning and semi-supervised learning, firstly, a part of manually marked samples are collected for supervised learning, namely, the one-to-one attribution relationship between the manual judging equipment and a user (according to various information, the user of the equipment is manually judged) is marked as a dependent variable, and the part of samples are firstly used for supervised learning. And (3) folding the manually marked samples into 5 parts for cross validation modeling to form Model1, then performing prediction judgment by using the Model1, inputting the judgment result of the Model1 into Model2, and so on to generate a supervised learning part.
As shown in fig. 3, a supervised learning Model (referred to as Model I) is trained by using a part of samples a marked manually, a sample B not marked manually is predicted by using the trained supervised learning Model I, a threshold value (for example, 0.8) is set, a label with a prediction probability greater than 0.8 is set as 1, otherwise, the label is 0, that is, the sample B without the label is marked by using the supervised Model. Then training a new supervised learning Model (called Model II according to the method) by using the rest of samples A and B to form a final prediction Model, namely inputting variables into the prediction Model for prediction when a new user/equipment relationship exists.
For an application scenario (safe money borrowing and lightning account checking) of the result of the embodiment, a user registers by using a mobile phone number, in the registration process, the system can obtain the operation behavior attribute of the user, check the trusted device can be performed, if the authentication can be passed, the next limit application is carried out, and if the authentication can not be passed, an abnormal warning is sent to request for further identity verification. The follow-up limit application comprises face recognition, real name authentication, bank card authentication, mobile phone number owner identity verification and other credit increasing authentication. And after the payment passes, performing borrowing submission steps including payment password verification, fund party matching and anti-fraud transaction detection, and paying out the payment by the fund party after passing. The subsequent repayment processing is also very convenient, and the client repayment, fund deduction, fund posting and amount real-time recovery are realized.
A second embodiment of the present invention also discloses a system for determining abnormal behavior based on a fingerprint of a trusted device, as shown in fig. 4, including,
a user registration information obtaining module 401, configured to obtain attribute data of a user operation behavior;
a user equipment attribution judging module 402, configured to obtain, based on the user operation behavior attribute data, a trusted device fingerprint corresponding to the user through user equipment attribution judging model operation;
the analysis processing module 403 is configured to send a prompt of an abnormal behavior if it is found that the user device is subjected to a specific operation by another user through the user trusted device fingerprint.
Wherein the user equipment attribution judging module further comprises,
and the storage module is used for storing the fingerprint of the trusted device in the relationship network information corresponding to the user.
And the variable input module is used for taking the fingerprint of the credible equipment and the real-time user information of the equipment as the input variable of the loan anti-fraud model.
And the definition module is used for defining the equipment which is frequently used by the user and has no abnormal behavior as the trusted equipment.
Wherein the analysis processing module further comprises an identity information verification module for further verifying identity information of a user using the apparatus if the specific operation is loan-related.
The following specifically explains a user equipment attribution judging module based on user operation behaviors, which includes;
the equipment attribution judging model module is used for constructing a user equipment attribution judging model based on the user operation behavior attribute data; the equipment attribution judgment model module specifically comprises a learning unit, and is used for training the user equipment attribution judgment model by adopting a mode of combining supervised learning and semi-supervised learning according to the user operation behavior attribute data.
In addition, the method further comprises the following steps: the user operation sample data acquisition unit is used for acquiring user operation sample data; according to the attribute of the user operation behavior, the user sample data acquisition unit is provided with an operation behavior containing subunit and is used for acquiring the operation behavior of the user on the equipment; the device attribute subunit is used for acquiring the attribute of the device; and the equipment associated information subunit is used for acquiring the equipment associated information.
The classification unit is used for dividing the user operation sample data into a first labeled sample and a non-labeled sample; the classification unit specifically comprises an artificial marking subunit, and the artificial marking subunit is used for performing user operation and equipment attribution judgment on one part of the obtained user operation sample data to serve as a first labeled sample, and the rest part of the obtained user operation sample data is a non-labeled sample. And the manual marking subunit judges the one-to-one attribution relationship between the equipment and the user and marks according to the operation behavior attribute of the user.
The first judgment model unit is used for performing supervised learning on the first labeled sample to obtain a first judgment model based on user operation behaviors; the first judgment model unit further comprises a label sample average molecular unit which is used for averagely dividing the first labeled sample which is used for manually marking the attribution relationship of the equipment and the user based on the attribute of the user operation behavior into two parts, wherein one part is used for supervised learning, and the first judgment model based on the user operation behavior is obtained through cross validation modeling.
The semi-supervised learning unit is used for carrying out semi-supervised learning on the unlabelled sample by using the first judgment model to obtain a second labeled sample; the semi-supervised learning unit further comprises a judging subunit, a judging unit and a judging unit, wherein the judging subunit is used for judging the label-free samples by using a first judging model based on the operation behaviors of the user; and the marking subunit is used for marking the label-free sample by using the judgment result through user operation and equipment attribution (setting a threshold value; setting the label with the judgment result larger than the threshold value as 1, otherwise, setting the label as 0) to obtain a second labeled sample.
And the supervised learning unit is used for carrying out supervised learning on the first labeled sample and the second labeled sample to obtain a user equipment attribution judgment model based on user operation behaviors. Specifically, the remaining one of the first labeled exemplars and the second labeled exemplar are subjected to supervised learning.
An input variable acquisition module, configured to acquire an input variable required by the ue affiliation determination model; the input variable comprises a user operation behavior; the input variable acquisition module further comprises an operation behavior attribute of a user on the equipment, an equipment attribute and equipment association information. In addition, the input variable acquisition module further comprises a variable derivation unit for deriving the variables, wherein the derivation comprises automatic variable derivation and manual variable derivation
And the operation module is used for performing operation by using the user equipment attribution judgment model to obtain a user equipment attribution judgment result.
In this embodiment, the user equipment attribution judging model mainly adopts a method combining supervised learning and semi-supervised learning, and first collects a part of manually marked samples for supervised learning, that is, manually judges the one-to-one attribution relationship between the equipment and the user (according to various information, who the user of the equipment is manually judged), marks the samples as dependent variables, and first uses the part of samples for supervised learning. And folding the manually marked samples into 5 sections for cross validation modeling to form a first judgment model, then performing prediction judgment by using the first judgment model, inputting the judgment result of the first judgment model unit into the user equipment attribution judgment model, and so on to generate a supervised learning part. Namely, a supervised learning model (first judgment model) is trained by using a part of the manually marked sample A, and the sample B which is not manually marked is predicted by using the trained first judgment model to mark the label-free sample B. And then training a new supervised learning model by using the rest part of samples A and B to form a final user equipment attribution judgment model.
A third embodiment of the present specification further provides a server comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor executes the program to implement the steps of the method as described above. For convenience of explanation, only the parts related to the embodiments of the present specification are shown, and specific technical details are not disclosed, so that reference is made to the method parts of the embodiments of the present specification. The server may be a server device formed by various electronic devices, a PC computer, a network cloud server, or a server function provided in any electronic device such as a mobile phone, a tablet computer, a PDA (Personal Digital Assistant), a POS (Point of Sales), a vehicle-mounted computer, or a desktop computer.
In particular, the server shown in fig. 5 in connection with the solution provided by the embodiments of the present description constitutes a block diagram, and the bus 500 may comprise any number of interconnected buses and bridges linking together various circuits including one or more processors represented by the processor 501 and a memory represented by the memory 502. The bus 500 may also link together various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further herein. A bus interface 503 provides an interface between the bus 500 and the receiver and/or transmitter 504, and the receiver and/or transmitter 504 may be a separate and independent receiver or transmitter or may be the same element, such as a transceiver, providing a means for communicating with various other apparatus over a transmission medium. The processor 501 is responsible for managing the bus 500 and general processing, and the memory 502 may be used for storing data used by the processor 501 in performing operations.
Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein may be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a computer-readable storage medium (which may be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which may be a personal computer, a server, or a network device, etc.) to execute the above method according to the embodiments of the present disclosure.
The computer readable storage medium may include a propagated data signal with readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A readable storage medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Program code for carrying out operations for the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., through the internet using an internet service provider).
The computer readable medium carries one or more programs which, when executed by a device, cause the computer readable medium to perform the functions of: acquiring a historical credit data set, wherein the historical credit data set comprises multi-dimensional attribute information and overdue information of a user; automatically staging the historical credit data set based on the multi-dimensional attribute information to generate a plurality of sub data sets; calculating the overdue rate corresponding to each subdata set in the plurality of subdata sets according to the overdue information; and generating a credit risk control rule according to the subdata set and the overdue rate corresponding to the subdata set.
Those skilled in the art will appreciate that the modules described above may be distributed in the apparatus according to the description of the embodiments, or may be modified accordingly in one or more apparatuses unique from the embodiments. The modules of the above embodiments may be combined into one module, or further split into multiple sub-modules.
Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein may be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (which may be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which may be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the embodiments of the present disclosure.
While the preferred embodiments of the present specification have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all changes and modifications that fall within the scope of the specification.
Exemplary embodiments of the present disclosure are specifically illustrated and described above. It is to be understood that the present disclosure is not limited to the precise arrangements, instrumentalities, or instrumentalities described herein; on the contrary, the disclosure is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims.
In addition, the structures, the proportions, the sizes, and the like shown in the drawings of the present specification are only used for matching with the contents disclosed in the specification, so as to be understood and read by those skilled in the art, and are not used for limiting the limit conditions which the present disclosure can implement, so that the present disclosure has no technical essence, and any modification of the structures, the change of the proportion relation, or the adjustment of the sizes, should still fall within the scope which the technical contents disclosed in the present disclosure can cover without affecting the technical effects which the present disclosure can produce and the purposes which can be achieved. In addition, the terms "above", "first", "second" and "first" used in the present specification are used for the sake of clarity only, and are not intended to limit the scope of the present disclosure, and changes and modifications of the relative relationship thereof may be regarded as the scope of the present disclosure without substantial technical changes.
Claims (10)
1. A method for determining abnormal behavior based on a fingerprint of a trusted device, comprising,
according to the obtained user operation sample, the operation behavior of the user on the equipment, the attribute of the equipment and the equipment association information, training and constructing a user equipment attribution judgment model by adopting a mode of combining supervised learning and semi-supervised learning:
acquiring user operation sample data;
dividing the user operation sample data into a first labeled sample and a non-labeled sample;
averagely dividing the first labeled sample into two parts, wherein one part is used for supervised learning, and a first judgment model based on user operation behaviors is obtained through cross validation modeling;
performing semi-supervised learning on the unlabeled sample by using the first judgment model to obtain a second labeled sample;
performing supervised learning on the other part of the first labeled sample and the second labeled sample, and determining the constructed attribution judgment model of the user equipment;
acquiring attribute data of user operation behaviors;
obtaining a credible equipment fingerprint corresponding to the user through the operation of the trained user equipment attribution judgment model operation based on the operation behavior of the user on the equipment, the attribute of the equipment, the equipment association information and derived variables in the user operation behavior attribute data;
and if the user equipment is found to be subjected to specific operation by other users through the user trusted equipment fingerprint, sending a prompt of abnormal behavior.
2. The method for determining abnormal behavior based on trusted device fingerprint according to claim 1, wherein the obtaining of the trusted device fingerprint corresponding to the user through the trained operation of the user device attribution determination model based on the user's operation behavior on the device in the user operation behavior attribute data, the device's own attribute, the device association information, and the derived variables further comprises:
and storing the fingerprint of the trusted device in the relationship network information corresponding to the user.
3. The method for determining abnormal behavior based on trusted device fingerprint according to claim 1, wherein the obtaining of the trusted device fingerprint corresponding to the user through the trained operation of the user device attribution determination model based on the user's operation behavior on the device in the user operation behavior attribute data, the device's own attribute, the device association information, and the derived variables further comprises:
and taking the fingerprint of the credible equipment and the real-time user information of the equipment as input variables of a loan anti-fraud model.
4. The method for determining anomalous behavior based on a trusted device fingerprint of claim 1, wherein,
if the user equipment is found to be subjected to specific operation by other users through the user trusted equipment fingerprint, the sending of the prompt of the abnormal behavior further comprises the following steps:
if the particular action is associated with a loan, further verification of the identity of the user using the device is performed.
5. The method for determining anomalous behavior based on a trusted device fingerprint of claim 1, wherein,
the trusted device is defined as a common device of the user, and the device has no abnormal behavior.
6. The method for determining abnormal behavior based on trusted device fingerprint according to claim 1, wherein obtaining the trusted device fingerprint corresponding to the user through the trained operation of the user device attribution determination model based on the user's operation behavior on the device in the user operation behavior attribute data, the device's own attribute, the device association information, and the derived variables further comprises:
acquiring input variables required by the user equipment attribution judgment model;
the input variables comprise the user operation behavior attribute data;
and operating the operation behavior of the user on the equipment in the user operation behavior attribute data, the equipment attribute, the equipment association information and the derived variable by using the trained user equipment attribution judgment model to obtain a user equipment attribution result.
7. The method for determining abnormal behavior based on the trusted device fingerprint according to any one of claims 1 to 6, wherein the operation behavior of the user on the device in the obtained user operation sample comprises: the operation sequence of the user on different devices and the operation times of the user on different devices.
8. A system for determining abnormal behavior based on a trusted device fingerprint, comprising,
the equipment attribution judgment model module is used for training a constructed user equipment attribution judgment model in a mode of combining supervised learning and semi-supervised learning according to the operation behaviors of the user on the equipment in the obtained user operation sample, the attribute of the equipment and the equipment correlation information: acquiring user operation sample data; dividing the user operation sample data into a first labeled sample and a non-labeled sample; averagely dividing the first labeled sample into two parts, wherein one part is used for supervised learning, and a first judgment model based on user operation behaviors is obtained through cross validation modeling; performing semi-supervised learning on the unlabeled sample by using the first judgment model to obtain a second labeled sample; performing supervised learning on the other part of the first labeled sample and the second labeled sample to determine the constructed attribution judgment model of the user equipment;
the user registration information acquisition module is used for acquiring user operation behavior attribute data;
the user equipment attribution judging module is used for obtaining a credible equipment fingerprint corresponding to the user through the operation of the trained user equipment attribution judging model based on the operation behavior of the user on the equipment in the user operation behavior attribute data, the attribute of the equipment, the equipment associated information and derived variables;
and the analysis processing module is used for sending out a prompt of abnormal behavior if the user equipment is found to be subjected to specific operation by other users through the user trusted equipment fingerprint.
9. A server, comprising a processor and a memory:
the memory is used for storing a program for executing the method of any one of claims 1 to 7;
the processor is configured to execute programs stored in the memory.
10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910581340.0A CN110362981B (en) | 2019-06-29 | 2019-06-29 | Method and system for judging abnormal behavior based on trusted device fingerprint |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910581340.0A CN110362981B (en) | 2019-06-29 | 2019-06-29 | Method and system for judging abnormal behavior based on trusted device fingerprint |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110362981A CN110362981A (en) | 2019-10-22 |
| CN110362981B true CN110362981B (en) | 2022-12-02 |
Family
ID=68216172
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910581340.0A Active CN110362981B (en) | 2019-06-29 | 2019-06-29 | Method and system for judging abnormal behavior based on trusted device fingerprint |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110362981B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113989859B (en) * | 2021-12-28 | 2022-05-06 | 江苏苏宁银行股份有限公司 | Fingerprint similarity identification method and device for anti-flashing equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106559213A (en) * | 2015-09-24 | 2017-04-05 | 腾讯科技（深圳）有限公司 | Device management method, equipment and system |
| CN109241711A (en) * | 2018-08-22 | 2019-01-18 | 平安科技（深圳）有限公司 | User behavior recognition method and device based on prediction model |
| CN109300028A (en) * | 2018-09-11 | 2019-02-01 | 上海天旦网络科技发展有限公司 | Real-time anti-fraud method and system and storage medium based on network data |
| CN110348190A (en) * | 2019-06-29 | 2019-10-18 | 上海淇毓信息科技有限公司 | User equipment ownership judgment method and device based on user's operation behavior |
Family Cites Families (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104580091B (en) * | 2013-10-21 | 2019-11-08 | 深圳市腾讯计算机系统有限公司 | A kind of auth method, device, system and storage medium |
| CN104318138B (en) * | 2014-09-30 | 2018-05-08 | 杭州同盾科技有限公司 | A kind of method and apparatus for verifying user identity |
| US9590986B2 (en) * | 2015-02-04 | 2017-03-07 | Aerendir Mobile Inc. | Local user authentication with neuro and neuro-mechanical fingerprints |
| CN106548342B (en) * | 2015-09-22 | 2023-07-04 | 创新先进技术有限公司 | Trusted device determining method and device |
| CN106909545B (en) * | 2015-12-22 | 2020-06-30 | 阿里巴巴集团控股有限公司 | Method and equipment for determining attribution information of user |
| CN105844126A (en) * | 2016-03-16 | 2016-08-10 | 成都信息工程大学 | Automatic identification method of intelligent electronic device user |
| CN107465642B (en) * | 2016-06-02 | 2020-12-11 | 百度在线网络技术（北京）有限公司 | Method and device for judging abnormal login of account |
| CN107066616B (en) * | 2017-05-09 | 2020-12-22 | 京东数字科技控股有限公司 | Account processing method and device and electronic equipment |
| CN107481019A (en) * | 2017-07-28 | 2017-12-15 | 上海携程商务有限公司 | Order fraud recognition methods, system, storage medium and electronic equipment |
| CN107579956B (en) * | 2017-08-07 | 2021-05-11 | 奇安信科技集团股份有限公司 | User behavior detection method and device |
| CN107742068A (en) * | 2017-09-01 | 2018-02-27 | 中国科学院信息工程研究所 | A kind of implicit identity authorization system of the multi-source of smart machine and method |
| CN109922032B (en) * | 2017-12-13 | 2022-04-19 | 百度在线网络技术（北京）有限公司 | Method, device, equipment and storage medium for determining risk of logging in account |
| CN109165940B (en) * | 2018-06-28 | 2022-08-09 | 创新先进技术有限公司 | Anti-theft method and device and electronic equipment |
-
2019
- 2019-06-29 CN CN201910581340.0A patent/CN110362981B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106559213A (en) * | 2015-09-24 | 2017-04-05 | 腾讯科技（深圳）有限公司 | Device management method, equipment and system |
| CN109241711A (en) * | 2018-08-22 | 2019-01-18 | 平安科技（深圳）有限公司 | User behavior recognition method and device based on prediction model |
| CN109300028A (en) * | 2018-09-11 | 2019-02-01 | 上海天旦网络科技发展有限公司 | Real-time anti-fraud method and system and storage medium based on network data |
| CN110348190A (en) * | 2019-06-29 | 2019-10-18 | 上海淇毓信息科技有限公司 | User equipment ownership judgment method and device based on user's operation behavior |
Non-Patent Citations (2)
| Title |
|---|
| 基于多层架构的信用卡反欺诈系统研究;吴雷等;《金融科技时代》;20180110(第01期);第37-41页 * |
| 数字联盟移动设备可信ID概述;杨从安;《网络空间安全》;20181231;第9卷(第12期);第19-24页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110362981A (en) | 2019-10-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110009174B (en) | Risk recognition model training method and device and server | |
| Wang et al. | Ponzi scheme detection via oversampling-based long short-term memory for smart contracts | |
| WO2019196546A1 (en) | Method and apparatus for determining risk probability of service request event | |
| CN108596616B (en) | User data authenticity analysis method and device, storage medium and electronic equipment | |
| CN111681091B (en) | Financial risk prediction method and device based on time domain information and storage medium | |
| US11531987B2 (en) | User profiling based on transaction data associated with a user | |
| US20230023630A1 (en) | Creating predictor variables for prediction models from unstructured data using natural language processing | |
| CN110009297A (en) | A kind of fiduciary qualification signal auditing method, device and equipment | |
| Luo et al. | Overview of intelligent online banking system based on HERCULES architecture | |
| CN115204886A (en) | Account identification method and device, electronic equipment and storage medium | |
| CN115034886A (en) | Default risk prediction method and device | |
| CN110362981B (en) | Method and system for judging abnormal behavior based on trusted device fingerprint | |
| CN117114901A (en) | Method, device, equipment and medium for processing insurance data based on artificial intelligence | |
| CN109636627B (en) | Insurance product management method, device, medium and electronic equipment based on block chain | |
| KR102455414B1 (en) | Method and system for providing online payment service | |
| US20230113118A1 (en) | Data compression techniques for machine learning models | |
| KR102271346B1 (en) | Credit loan platform using atypical-data and its operating method | |
| CN113935738B (en) | Transaction data processing method, device, storage medium and equipment | |
| CN114048330A (en) | Risk conduction probability knowledge graph generation method, device, equipment and storage medium | |
| CN114757497A (en) | Technology trust-increasing method for science and technology enterprise, device, equipment and medium thereof | |
| US11561963B1 (en) | Method and system for using time-location transaction signatures to enrich user profiles | |
| CN110909777A (en) | Multi-dimensional feature map embedding method, device, equipment and medium | |
| CN110348190A (en) | User equipment ownership judgment method and device based on user's operation behavior | |
| CN114565030B (en) | Feature screening method and device, electronic equipment and storage medium | |
| CN117350461B (en) | Enterprise abnormal behavior early warning method, system, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |