CN110532755A - A kind of method and device of computer implemented risk identification - Google Patents
A kind of method and device of computer implemented risk identification Download PDFInfo
- Publication number
- CN110532755A CN110532755A CN201910736167.7A CN201910736167A CN110532755A CN 110532755 A CN110532755 A CN 110532755A CN 201910736167 A CN201910736167 A CN 201910736167A CN 110532755 A CN110532755 A CN 110532755A
- Authority
- CN
- China
- Prior art keywords
- sliding trace
- user
- slide
- track
- identification
- 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.)
- Granted
Links
Classifications
-
- 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
- G06F21/36—User authentication by graphic or iconic representation
-
- 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
- G06F21/45—Structures or tools for the administration of authentication
Landscapes
- Engineering & Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
Subject description discloses a kind of method and devices of computer implemented risk identification, it in the method can be according to the business operation of user, sliding verifying is initiated to the user, the user can be acquired and carry out the current sliding trace for executing slide when sliding verifying, according to the history sliding trace of the user, determine that the user executes the reference sliding trace of slide, and to deserving front slide track and this is compared referring to sliding trace, and then according to obtained comparison result, risk identification is carried out to the slide.Due to can be according to the history sliding trace of the user, determine the reference sliding trace for being able to reflect out sliding feature when the user executes slide, to by this referring to sliding trace with deserve by way of front slide track is compared, identify the currently performed slide of the user with the presence or absence of risk, service platform is prevented by the malicious attack of undesirable, the safe operation of service platform not to be effectively guaranteed.
Description
Technical field
This specification is related to field of computer technology more particularly to a kind of method and dress of computer implemented risk identification
It sets.
Background technique
Malicious registration is executed in order to reduce undesirable, the behaviors adverse effect such as frequently logs on, in reality
In the application of border, the mode that service platform generallys use setting identifying code carries out the behaviors such as registration, login, the business execution of user
Verifying, to ensure that the executor of these behaviors is normal users and the equipment such as non-computer.
Currently, the form of the identifying code of service platform setting is varied, the form of these identifying codes includes: that input type is tested
It demonstrate,proves code, problem identifying code, picture and chooses formula identifying code etc..And in the identifying code of numerous forms, slidingtype identifying code is due to it
It is easy to operate, it has been increasingly becoming a kind of more welcome identifying code form.Service platform using slidingtype identifying code to
When family is verified, user need to only complete specified slide as requested and (e.g., be moved to sliding block according to prompt specified
In position), corresponding verifying can be completed.
However in practical applications, undesirable can pass through machine simulation user by tools such as some softwares, programs
The slide executed in sliding verification process, so, it will face service platform by the risk of malicious attack.
Risk identification is carried out to slide of the user in sliding verification process so how effectively to realize,
It is then a urgent problem to be solved.
Summary of the invention
This specification provides a kind of method and device of computer implemented risk identification, with the solution prior art of part
The existing above problem.
This specification adopts the following technical solutions:
Present description provides a kind of methods of computer implemented risk identification, comprising:
According to the business operation of user, sliding verifying is initiated to user；
It acquires the user and carries out the current sliding trace for executing slide when sliding verifying；
Reference sliding trace associated with the user is obtained, it is described that cunning is executed based on the user referring to sliding trace
The history sliding trace of dynamic operation is determining；
Compare the current sliding trace and described referring to sliding trace, and according to obtained comparison result to the cunning
Dynamic operation carries out risk identification.
Optionally, according to the history sliding trace of the user, determine that the user executes the reference sliding of slide
The step of track includes:
Determine the starting point coordinate of track starting point and the terminal point coordinate of final on trajectory in the current sliding trace；
The starting point coordinate and the terminal point coordinate are input to the pre- history sliding trace training for first passing through the user
Trajectory generative model out executes the reference sliding trace of slide with the determination user.
Optionally, before the step of comparing the current sliding trace and the reference sliding trace, further includes:
It acquires the user and carries out the behavioral data for executing slide when sliding verifying；
According to the behavioral data, the corresponding track characteristic of the current sliding trace is determined；
Include: to the step of slide progress risk identification according to obtained comparison result
According to the track characteristic and the comparison result, risk identification is carried out to the slide.
Optionally, according to the behavioral data, the step of determining the track characteristic of the current sliding trace, includes:
Several sampled points are determined in the current sliding trace；
For each sampled point, according at least to the behavioral data, the corresponding sampling point feature of the sampled point is determined, it is described
Sampling point feature includes: that user executes the slide and slides into the gliding cable structure of the sampled point, the current sliding trace
At least one of slope at the sampled point；
According to several sampled points the current sliding trace sequencing, several sampled points are corresponding
Sampling point feature is ranked up, and obtains sampled point characteristic sequence；
The sampled point characteristic sequence is determined as to the track characteristic of the current sliding trace.
Optionally, according to the track characteristic and the comparison result, risk identification is carried out to the slide
Step includes:
Determine the current sliding trace and the track difference referring between sliding trace；
According to the track characteristic and the track difference, risk identification is carried out to the slide.
Optionally, according to the track characteristic and the track difference, risk identification is carried out to the slide
Step includes:
The track characteristic and the track difference are input to identification model trained in advance, to pass through the identification
Model carries out risk identification to the slide.
Optionally, the identification model includes: at least one of the first identification model and the second identification model, and described
One identification model is obtained by predefining each negative sample training, and second identification model is by predefining
What each positive sample and negative sample training out obtained, the positive sample is sliding according to there are the history of risk in each user's history
The sample that dynamic rail mark and historical behavior data are determined, the negative sample are according to going through there is no risk in each user's history
The sample that history sliding trace and historical behavior data are determined.
Optionally, the track characteristic and the track difference are input to identification model trained in advance, to pass through
The identification model, to the slide carry out risk identification the step of include:
It is input in first identification model, obtains using the track characteristic and the track difference as initial data
The reconstruct data rebuild to first identification model based on the initial data；
By the way that the reconstruct data and the initial data are compared, risk identification is carried out to the slide.
Optionally, the track characteristic and the track difference are input in identification model trained in advance, with logical
Crossing the step of identification model carries out risk identification to the slide includes:
The track characteristic and the track difference are input to first identification model, obtain the first identification knot
The track characteristic and the track difference are input to the second identification model, obtain the second recognition result by fruit；
According to first recognition result, the second recognition result, corresponding first weight of first identification model and
Corresponding second weight of second identification model carries out risk identification to the slide.
Present description provides a kind of devices of risk identification, comprising:
Initiation module initiates sliding verifying to user for the business operation according to user；
Acquisition module carries out the current sliding trace that slide is executed when sliding verifying for acquiring the user；
Module is obtained, it is associated with the user referring to sliding trace for obtaining, it is described to be based on referring to sliding trace
The history sliding trace that the user executes slide is determining；
Identification module, for comparing the current sliding trace and the reference sliding trace, and according to obtained ratio
Risk identification is carried out to the slide to result.
Present description provides a kind of computer readable storage medium, the storage medium is stored with computer program, institute
State the method that above-mentioned risk identification is realized when computer program is executed by processor.
Present description provides a kind of electronic equipment, including memory, processor and storage on a memory and can located
The computer program run on reason device, the processor execute the method for realizing above-mentioned risk identification when described program.
This specification use at least one above-mentioned technical solution can reach it is following the utility model has the advantages that
A kind of method for risk identification that this specification provides can be initiated according to the business operation of user to the user
Sliding verifying then can acquire the user and carry out the current sliding trace for executing slide when sliding verifying, according to the use
The history sliding trace at family, determine the user execute slide reference sliding trace, and to deserve front slide track and should
It is compared referring to sliding trace, and then according to obtained comparison result, risk identification is carried out to the slide.
In from the above as can be seen that due to that can determine to be able to reflect according to the history sliding trace of the user
The reference sliding trace of sliding feature when the user executes slide out, thus by the reference sliding trace, to collecting
The user currently carry out executing the current sliding trace of slide when sliding verifying and be compared, and then can be according to obtaining
Comparison result, identify that the currently performed slide of the user with the presence or absence of risk, prevents service platform not by illegal
The safe operation of service platform is effectively guaranteed in the malicious attack of one's share of expenses for a joint undertaking.
Detailed description of the invention
Attached drawing described herein is used to provide to further understand this specification, forms part of this specification,
The illustrative embodiments and their description of this specification do not constitute the improper restriction to this specification for explaining this specification.
In the accompanying drawings:
Fig. 1 is a kind of flow diagram for computer implemented risk identification that this specification provides；
Fig. 2 is the schematic diagram that the user that this specification provides executes slide；
The schematic diagram of sampled point in the current sliding trace that Fig. 3 provides for this specification；
Fig. 4 is a kind of schematic device for risk identification that this specification provides；
Fig. 5 is the electronic equipment schematic diagram corresponding to Fig. 1 that this specification provides.
Specific embodiment
To keep the purposes, technical schemes and advantages of this specification clearer, it is embodied below in conjunction with this specification
This specification technical solution is clearly and completely described in example and corresponding attached drawing.Obviously, described embodiment is only this
Specification a part of the embodiment, instead of all the embodiments.The embodiment of base in this manual, ordinary skill people
Member's every other embodiment obtained without making creative work, belongs to the range of this specification protection.
Below in conjunction with attached drawing, the technical solution that each embodiment of this specification provides is described in detail.
Fig. 1 is a kind of flow diagram for computer implemented risk identification that this specification provides, and is specifically included following
Step:
S101: according to the business operation of user, sliding verifying is initiated to user.
In the present specification, user is when carrying out business execution, can execute corresponding business operation, and service platform can be with
According to the business operation monitored, sliding verifying is initiated to the user.For example, user can execute and step on when business executes
Record operation, service platform can initiate the user using the verification mode of sliding identifying code when monitoring the register
Sliding verifying, with verify the register be by the user initiate, or by machine by analog subscriber login behaviour
The mode of work and initiate.
S102: it acquires the user and carries out the current sliding trace for executing slide when sliding verifying.
When the sliding verifying that user initiates according to service platform executes slide, service platform can collect the user
The current sliding trace of currently performed slide.In practical applications, user executes the obtained sliding of slide
Track can reflect the characteristic of the slide to a certain extent, and in general, slide that machine simulation goes out and
The performed slide of user, obtained sliding trace characteristically often have a certain difference.So at this
In specification, service platform can deserve front slide track based on collected, be somebody's turn to do to user's execution in the follow-up process
Slide carries out risk identification.
S103: obtaining reference sliding trace associated with the user, described to be based on the user referring to sliding trace
The history sliding trace for executing slide is determining.
The available user of service platform carries out each history that history slide is executed when sliding verifying in history
Sliding trace, and then according to these history sliding traces, determine that the user executes the reference sliding trace of slide.
Wherein, the personalization spy mentioned herein being able to reflect out referring to sliding trace when the user executes slide
Point, referring to sliding trace can not only distinguish to a certain extent user execution slide and machine simulation go out
Slide, moreover, can also distinguish different user referring to sliding trace carries out slide performed when sliding is verified.
In the present specification, service platform can be determined offline and be somebody's turn to do previously according to the history sliding trace got
User is associated each referring to sliding trace and to be saved.It, can be with when the slide that executes to the user carries out risk identification
From each reference sliding trace pre-saved, the reference sliding trace that front slide track matches is determined and deserves, in turn
In such a way that the two tracks are compared, risk identification is carried out to the slide that the user executes.
Wherein, service platform can determine different tracks starting point and different rails according to the history sliding trace got
It is each referring to sliding trace made of mark endpoint composite.So mentioned above each referring to true in sliding trace from what is pre-saved
The reference sliding trace that front slide track matches is made and deserved, is actually referred to, by each referring in sliding trace, track is risen
Point and final on trajectory with deserve that front slide track matches referring to sliding trace, be determined as and deserve front slide track and match
Reference sliding trace.
Certainly, in the present specification, service platform can also be determined associated with the user referring to sliding rail in real time
Mark.Specifically, service platform can determine to deserve the starting point coordinate and final on trajectory of track starting point in front slide track
Terminal point coordinate, and then the starting point coordinate and terminal point coordinate are input in trajectory generative model trained in advance, the obtained ginseng
According to sliding trace.
Trajectory generative model mentioned above is that service platform is instructed according to the history sliding trace obtained for the user
It practises.So service platform pre-save it is each referring to sliding trace can also according to the trajectory generative model trained and
It obtains.Due to the corresponding trajectory generative model of different user be all trained by respective history sliding trace, so, it is different
The corresponding trajectory generative model of user is different.Specifically, in the present specification, service platform can be directed to all users
Account configures unified trajectory generative model, the unified trajectory generative model be it is unbred, be based on identical input
Being exported is identical referring to sliding trace.And service platform passes through the history sliding trace of each user got to each rail
After mark generation model is trained, the reference sliding trace that the corresponding trajectory generative model of different user account is exported can be anti-
Mirror personalization features of the different user when executing slide, that is, with the continuous training to these trajectory generative models,
What each trajectory generative model was exported gradually shows otherness referring to sliding trace.
In the present specification, for service platform after getting above-mentioned current sliding trace, can be executed according to the user should
The user account that slide is based on, determine it is pre- first pass through the user account and correspond to the history sliding trace of user train
Trajectory generative model determine the associated reference of user corresponding with the user account and then according to the trajectory generative model
Sliding trace.
Wherein, the coordinate system that starting point coordinate mentioned above and terminal point coordinate are based on can be by used by a user
The coordinate system that the screen of terminal constructs is also possible to based on the coordinate system gone out constructed by sliding verifying interface, or is to be based on
User's coordinate system that related business interface is constructed when carrying out business execution, as shown in Figure 2.
Fig. 2 is the schematic diagram that the user that this specification provides executes slide.
When user carries out business execution, service platform can initiate sliding verifying to the user.User can used
Terminal interface in be referenced to for carry out sliding verifying sliding verify interface, and then can the sliding verify interface in
Execute slide.Wherein, the interface, sliding verifying interface and business interface of terminal are respectively illustrated in Fig. 2.So clothes
The coordinate system being based on when above-mentioned starting point coordinate and terminal point coordinate that business platform is determined, can be based on above-mentioned arbitrary interface institute
The coordinate system constructed.
S104: comparing the current sliding trace and described referring to sliding trace, and according to obtained comparison result pair
The slide carries out risk identification.
After determining above-mentioned reference sliding trace, service platform can be by collected current sliding trace and the reference
Sliding trace is compared, and obtains corresponding comparison result, and then according to the comparison result to the currently performed sliding of the user
Operation carries out risk identification.
Specifically, service can be determined to deserve the similarity between front slide track and the reference sliding trace, if really
The fixed similarity is more than setting similarity, it is determined that deserve out otherness between front slide track and the reference sliding trace compared with
Greatly, it and then determines the currently performed slide of the user there are risk, and if it is determined that the similarity is no more than the setting
Similarity, it is determined that the otherness deserved between front slide track and the reference sliding trace out is smaller, and then determines the use
Risk is not present in the currently performed slide in family.
It is wherein, mentioned herein that there are risks can be divided into following several situations:
First: if above-mentioned current sliding trace is that the slide that user acquisition machine simulates is formed by sliding
Track, then can by the way that the user determined is referring to sliding trace and to deserve otherness between front slide track excessive,
Identify that there are risks for the currently performed slide of the user, that is, identify the currently performed slide of the user
The slide gone out for machine simulation.
Second: for slide performed by the user implemented based on the user account for the other users stolen
For situation, the slide as performed by different user has a certain difference on sliding trace, so, if service is flat
Platform determine this is according to sliding trace and to deserve otherness between front slide track excessive, then identify that the slide exists
Risk is stolen and the loss of user's bring of the user account to effectively prevent user account.
In from the above as can be seen that due to that can determine to be able to reflect according to the history sliding trace of the user
The reference sliding trace of sliding feature when the user executes slide out, thus by the reference sliding trace, to collecting
The user currently carry out executing the current sliding trace of slide when sliding verifying and be compared, and then can be according to obtaining
Comparison result, identify that the currently performed slide of the user with the presence or absence of risk, prevents service platform not by illegal
The safe operation of service platform is effectively guaranteed in the malicious attack of one's share of expenses for a joint undertaking.
It should be noted that service platform is in addition to that can grasp the sliding that the user executes in such a way that track compares
Make outside carry out risk identification, can be combined with other modes to carry out risk identification.Specifically, in the present specification, service is flat
Platform can also acquire behavioral data of the user when executing slide while acquiring above-mentioned current sliding trace.Its
In, behavior data are for reflecting mode of operation of the user when executing slide, for example, executing the fast of slide
Slowly, whether there is pause etc. when executing slide.Service platform can be based on collected behavioral data, determine to deserve advancing slip
The track characteristic of dynamic rail mark, and then by the track characteristic, risk identification is carried out to the slide that the user executes.
After service platform collects above-mentioned current sliding trace, several sampled points are determined in sliding trace in this prior,
The form of sampled point is as shown in Figure 3.
The schematic diagram of sampled point in the current sliding trace that Fig. 3 provides for this specification.
It is assumed that service platform requires user to need each mark point in sliding verifying interface according to top-down sequence
Verifying can be passed through by connecting.After user executes slide according to the requirement of service platform, service platform is available such as
Current sliding trace shown in Fig. 3.Service platform can determine each sampling as shown in Figure 3 in sliding trace in this prior
Point, and then in the follow-up process, by the sampling point feature of each sampled point of determination, determine that the track for deserving front slide track is special
Sign.
Service platform determines that the mode of several sampled points can have very much, for example, service platform can slide in this prior
The sampled point of setting quantity is determined in track, in this prior in sliding trace, the track spacing between each sampled point is identical；Again
For example, service platform can uniformly mark off each sampled point in sliding verifying interface, then, can further determine
Deserve which sampled point front slide track has passed through, and then advancing slip as deserving using the sampled point that front slide track is passed through is deserved
Sampled point in dynamic rail mark.Other modes just different one have been illustrated herein.
After determining each sampled point in above-mentioned current sliding trace, service platform can be directed to each sampled point, at least
According to collected behavioral data, the corresponding sampling point feature of the sampled point is determined, wherein sampling point feature mentioned herein
It include: that user executes gliding cable structure of slide when sliding into the sampled point, deserves front slide track and be located at the sampled point
The dimensions such as slope data.
Wherein, it may include each instantaneous behaviour when user executes slide in the collected behavioral data of service platform
Make rate, be based on these momentary operation rates, service platform can be directed to each sampled point, determine that user executes slide
Slide into the gliding cable structure when sampled point.Service platform can determine in this prior according to collected current sliding trace
The slope being located at the sampled point in sliding trace.
In the present specification, service platform can also be above-mentioned referring to each sampled point determining in sliding trace, for current
The each sampled point for including in sliding trace is determined at this referring to the sampled point to be matched in sliding trace with the sampled point
(as at a distance of nearest sampled point) makees as matching sampled point, and then by the spacing between the sampled point and the matching sampled point
For a sampling point feature of the sampled point.
Service platform can in the manner described above, determine the sampling point feature of each sampled point in current sliding trace,
Then, the sampling point feature of each sampled point can be ranked up according to the sequence in each sampled point in this prior sliding trace,
Sampled point characteristic sequence is obtained, and then using the sampled point characteristic sequence as the track characteristic for deserving front slide track.
It is not to deserve front slide track from entire upper reflection that track characteristic from here, which can be seen that the track characteristic,
Feature, but can reflect the characteristics of deserving different location in front slide track to a certain extent.Based on this, service platform
It can be based on the track characteristic and comparison result obtained above, risk identification is carried out to the slide that the user executes.
Specifically, in the present specification, service platform can deserve front slide track and reference sliding by comparing
Track is determined to deserve the track difference between front slide track and the reference sliding trace.Wherein, track mentioned herein is poor
Different manifestation mode can have very much, e.g., can also pass through the two directly using the similarity of the two as the track difference
Similarity and preset algorithm, determine the track difference.Other modes just do not have been illustrated in detail herein.
The track difference and track characteristic mentioned above can be input to identification mould trained in advance by service platform
In type, to carry out risk identification to the slide by the identification model.Wherein, the identification model that this specification is mentioned can
To include the first identification model and the second identification model.First identification model can be by predefining each negative sample training
It obtains.And what the second identification model can be obtained by predetermined each positive sample and negative sample training out.Here it mentions
To positive sample can refer to that each user has the history sliding trace and historical behavior data of risk in history, and negative sample
This then refers to that the history sliding trace and historical behavior data of risk is not present in each user in history.First identification model
It can be trained by the way of unsupervised learning, and the second identification model can be instructed by the way of supervised learning
Practice.
In the present specification, above-mentioned track characteristic and track difference can be input to the first identification mould by service platform
Type, to identify that the sliding trace that user executes whether there is risk by first identification model.Wherein, due to first knowledge
Other model is only obtained using negative sample training in the training process, so, the first identification model can use such as length
The restructing algorithms such as memory network-automatic coding machine (LSTM-AutoEncoder) are constructed.First identification model can be by
The initial data (i.e. track characteristic and track difference) of input is reconstructed according to certain mode, obtains reconstruct data, and right
Reconstruct data and initial data are compared, if the two is closer to, then can determine that when the user executes slide not
There are risks, otherwise, it determines there are risks when user execution slide.
Service platform can also be identified when the user executes slide by the second identification model with the presence or absence of risk.
Certainly, in the present specification, both identification models can also be used together by service platform, the sliding executed to the user
Operation carries out risk identification.Specifically, the track characteristic and track difference can be input to the first identification mould by service platform
In type, the first recognition result is obtained, meanwhile, the track characteristic and track difference can be input in the second identification model, be obtained
To the second recognition result.Then, service platform can be according to first recognition result, the second recognition result, the first identification model
Corresponding first weight and corresponding second weight of the second identification model, determine final recognition result, and then most according to this
Whole recognition result carries out risk identification to the slide that the user executes.
In addition, in the present specification, in the identification model that above-mentioned track characteristic can also be only input to by service platform, obtaining
To recognition result, and then according to the recognition result, and by being compared by current sliding trace and referring to sliding trace
The comparison result arrived determines that the slide that the user executes whether there is risk.
In other words, risk identification is carried out to the slide by track characteristic, and by by current sliding trace and
It is compared referring to sliding trace to carry out risk identification and can be considered as two ways.Both can be respectively adopted in service platform
Mode to carry out the slide risk identification, and then the recognition result of both comprehensive modes, determines that user executes the cunning
It whether there is risk when dynamic operation.
Certainly, other than above two mode, service platform can also carry out risk identification using other modes.Example
Such as, the hardware information (such as device id) and software being based on when service platform can also execute slide by identification user are believed
It ceases (software version number, system identifier etc.), risk identification is carried out to the slide that the user executes.Wherein, in service platform
The blacklist of hardware information and software information is preserved, whether it includes to collect that service platform can be inquired in the blacklist
Hardware information and software information, come when determining that the user executes slide with the presence or absence of risk.
For another example can determine to deserve front slide track for characterizing after service platform collects above-mentioned behavioral data
The global feature of whole feature, e.g., user execute slide and obtain deserving duration used in front slide track, deserve front slide
The path length of track, execution slide obtain deserving average operation rate of front slide track etc..Service platform can lead to
The global feature determined is crossed, whether there is risk when identifying that the user executes slide.Other modes are herein just not
Illustrated in greater detail.Certainly, service platform can also be in conjunction with these types of mode mentioned above, and comprehensive identifies the user
The slide of execution whether there is risk.
It should be noted that service platform can be respectively required according to the first identification model and the second identification model respectively
Sample is trained the two identification models respectively.Certainly, service platform can also integrate the two identification models
Training.Specifically, the negative sample being previously obtained can be used in service platform when being trained to the first identification model, it is available
The penalty values loss of the loss function of restructing algorithm1.Similarly, service platform is using the positive sample that is previously obtained and negative sample to the
When two identification models are trained, the loss for the loss function that available second identification model uses2And loss3, wherein the
It include loss item and regular terms, loss in loss function used by two identification models2For the damage obtained by the loss item
Mistake value, and loss3For the penalty values obtained by the regular terms.It, can be according to after service platform obtains above three penalty values
Following formula determine comprehensive loss value.
Loss=λ1loss1+λ2loss2+λ3loss3
Wherein, λ1、λ2And λ3It is loss respectively1、loss2And loss3Loss weight.Service platform can the comprehensive loss
Value is optimization aim, is trained to the first identification model and the second identification model.
The above are the methods for the risk identification that one or more embodiments of this specification provide, and are based on same thinking,
This specification additionally provides the device of corresponding risk identification, as shown in Figure 4.
Fig. 4 is a kind of schematic device for risk identification that this specification provides, and is specifically included:
Initiation module 401 initiates sliding verifying to user for the business operation according to user；
Acquisition module 402 carries out the current sliding trace that slide is executed when sliding verifying for acquiring the user；
Module 403 is obtained, it is associated with the user referring to sliding trace for obtaining, it is described referring to sliding trace base
It is determining in the history sliding trace that the user executes slide；
Identification module 404, for comparing the current sliding trace and described referring to sliding trace, and according to obtaining
Comparison result carries out risk identification to the slide.
Optionally, the determining module 403 is specifically used for, and determines that the starting point of track starting point in the current sliding trace is sat
The terminal point coordinate of mark and final on trajectory；The starting point coordinate and the terminal point coordinate are input to and pre- first pass through going through for the user
The trajectory generative model that history sliding trace trains executes the reference sliding trace of slide with the determination user.
Optionally, it is executed in the identification module 404 and compares the current sliding trace and the reference sliding trace
Before, the acquisition module 402 is also used to, and is acquired the user and is carried out the behavioral data for executing slide when sliding verifying；
According to the behavioral data, the corresponding track characteristic of the current sliding trace is determined；
The identification module 404 is specifically used for, and according to the track characteristic and the comparison result, grasps to the sliding
Make carry out risk identification.
Optionally, the acquisition module 402 is specifically used for, and several sampled points are determined in the current sliding trace；Needle
To each sampled point, according at least to the behavioral data, the corresponding sampling point feature of the sampled point, the sampling point feature are determined
It include: that user executes that the slide slides into the gliding cable structure of the sampled point, the current sliding trace is located at the sampling
At least one of slope at point；It, will be described according to several sampled points in the sequencing of the current sliding trace
The corresponding sampling point feature of several sampled points is ranked up, and obtains sampled point characteristic sequence；The sampled point characteristic sequence is true
It is set to the track characteristic of the current sliding trace.
Optionally, the identification module 404 is specifically used for, and determines the current sliding trace and described referring to sliding trace
Between track difference；According to the track characteristic and the track difference, risk identification is carried out to the slide.
Optionally, the identification module 404 is specifically used for, and the track characteristic and the track difference is input to pre-
First trained identification model, to carry out risk identification to the slide by the identification model.
Optionally, the identification model includes: at least one of the first identification model and the second identification model, and described
One identification model is obtained by predefining each negative sample training, and second identification model is by predefining
What each positive sample and negative sample training out obtained, the positive sample is sliding according to there are the history of risk in each user's history
The sample that dynamic rail mark and historical behavior data are determined, the negative sample are according to going through there is no risk in each user's history
The sample that history sliding trace and historical behavior data are determined.
Optionally, the identification module 404 is specifically used for, using the track characteristic and the track difference as original
Data are input in first identification model, obtain the weight that first identification model is rebuild based on the initial data
Structure data；By the way that the reconstruct data and the initial data are compared, risk identification is carried out to the slide.
Optionally, the identification module 404 is specifically used for, and the track characteristic and the track difference are input to institute
The first identification model is stated, the first recognition result is obtained, the track characteristic and the track difference are input to the second identification
Model obtains the second recognition result；According to first recognition result, the second recognition result, first identification model is corresponding
The first weight and corresponding second weight of second identification model, to the slide carry out risk identification.
This specification additionally provides a kind of computer readable storage medium, which is stored with computer program, meter
Calculation machine program can be used for executing the method for the risk identification that above-mentioned Fig. 1 is provided.
This specification additionally provides the schematic configuration diagram of electronic equipment shown in fig. 5.It as described in Figure 5, should in hardware view
Electronic equipment includes processor, internal bus, network interface, memory and nonvolatile memory, is also possible that it certainly
Hardware required for his business.Processor from read in nonvolatile memory corresponding computer program into memory then transport
Row, the method to realize risk identification described in above-mentioned Fig. 1.Certainly, other than software realization mode, this specification is not arranged
Except other implementations, such as logical device or the mode of software and hardware combining etc., that is to say, that following process flow is held
Row main body is not limited to each logic unit, is also possible to hardware or logical device.
In the 1990s, the improvement of a technology can be distinguished clearly be on hardware improvement (for example,
Improvement to circuit structures such as diode, transistor, switches) or software on improvement (improvement for method flow).So
And with the development of technology, the improvement of current many method flows can be considered as directly improving for hardware circuit.
Designer nearly all obtains corresponding hardware circuit by the way that improved method flow to be programmed into hardware circuit.Cause
This, it cannot be said that the improvement of a method flow cannot be realized with hardware entities module.For example, programmable logic device
(Programmable Logic Device, PLD) (such as field programmable gate array (Field Programmable Gate
Array, FPGA)) it is exactly such a integrated circuit, logic function determines device programming by user.By designer
Voluntarily programming comes a digital display circuit " integrated " on a piece of PLD, designs and makes without asking chip maker
Dedicated IC chip.Moreover, nowadays, substitution manually makes IC chip, this programming is also used instead mostly " is patrolled
Volume compiler (logic compiler) " software realizes that software compiler used is similar when it writes with program development,
And the source code before compiling also write by handy specific programming language, this is referred to as hardware description language
(Hardware Description Language, HDL), and HDL is also not only a kind of, but there are many kind, such as ABEL
(Advanced Boolean Expression Language)、AHDL(Altera Hardware Description
Language)、Confluence、CUPL(Cornell University Programming Language)、HDCal、JHDL
(Java Hardware Description Language)、Lava、Lola、MyHDL、PALASM、RHDL(Ruby
Hardware Description Language) etc., VHDL (Very-High-Speed is most generally used at present
Integrated Circuit Hardware Description Language) and Verilog.Those skilled in the art also answer
This understands, it is only necessary to method flow slightly programming in logic and is programmed into integrated circuit with above-mentioned several hardware description languages,
The hardware circuit for realizing the logical method process can be readily available.
Controller can be implemented in any suitable manner, for example, controller can take such as microprocessor or processing
The computer for the computer readable program code (such as software or firmware) that device and storage can be executed by (micro-) processor can
Read medium, logic gate, switch, specific integrated circuit (Application Specific Integrated Circuit,
ASIC), the form of programmable logic controller (PLC) and insertion microcontroller, the example of controller includes but is not limited to following microcontroller
Device: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20 and Silicone Labs C8051F320 are deposited
Memory controller is also implemented as a part of the control logic of memory.It is also known in the art that in addition to
Pure computer readable program code mode is realized other than controller, can be made completely by the way that method and step is carried out programming in logic
Controller is obtained to come in fact in the form of logic gate, switch, specific integrated circuit, programmable logic controller (PLC) and insertion microcontroller etc.
Existing identical function.Therefore this controller is considered a kind of hardware component, and to including for realizing various in it
The device of function can also be considered as the structure in hardware component.Or even, it can will be regarded for realizing the device of various functions
For either the software module of implementation method can be the structure in hardware component again.
System, device, module or the unit that above-described embodiment illustrates can specifically realize by computer chip or entity,
Or it is realized by the product with certain function.It is a kind of typically to realize that equipment is computer.Specifically, computer for example may be used
Think personal computer, laptop computer, cellular phone, camera phone, smart phone, personal digital assistant, media play
It is any in device, navigation equipment, electronic mail equipment, game console, tablet computer, wearable device or these equipment
The combination of equipment.
For convenience of description, it is divided into various units when description apparatus above with function to describe respectively.Certainly, implementing this
The function of each unit can be realized in the same or multiple software and or hardware when application.
It should be understood by those skilled in the art that, the embodiment of the present invention can provide as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the present invention
Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the present invention, which can be used in one or more,
The computer program implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) produces
The form of product.
The present invention be referring to according to the method for the embodiment of the present invention, the process of equipment (system) and computer program product
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real
The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
In a typical configuration, calculating equipment includes one or more processors (CPU), input/output interface, net
Network interface and memory.
Memory may include the non-volatile memory in computer-readable medium, random access memory (RAM) and/or
The forms such as Nonvolatile memory, such as read-only memory (ROM) or flash memory (flash RAM).Memory is computer-readable medium
Example.
Computer-readable medium includes permanent and non-permanent, removable and non-removable media can be by any method
Or technology come realize information store.Information can be computer readable instructions, data structure, the module of program or other data.
The example of the storage medium of computer includes, but are not limited to phase change memory (PRAM), static random access memory (SRAM), moves
State random access memory (DRAM), other kinds of random access memory (RAM), read-only memory (ROM), electric erasable
Programmable read only memory (EEPROM), flash memory or other memory techniques, read-only disc read only memory (CD-ROM) (CD-ROM),
Digital versatile disc (DVD) or other optical storage, magnetic cassettes, tape magnetic disk storage or other magnetic storage devices
Or any other non-transmission medium, can be used for storage can be accessed by a computing device information.As defined in this article, it calculates
Machine readable medium does not include temporary computer readable media (transitory media), such as the data-signal and carrier wave of modulation.
It should also be noted that, the terms "include", "comprise" or its any other variant are intended to nonexcludability
It include so that the process, method, commodity or the equipment that include a series of elements not only include those elements, but also to wrap
Include other elements that are not explicitly listed, or further include for this process, method, commodity or equipment intrinsic want
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including described want
There is also other identical elements in the process, method of element, commodity or equipment.
It will be understood by those skilled in the art that the embodiment of this specification can provide as the production of method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or implementation combining software and hardware aspects can be used in this specification
The form of example.Moreover, it wherein includes the computer of computer usable program code that this specification, which can be used in one or more,
The computer program implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) produces
The form of product.
This specification can describe in the general context of computer-executable instructions executed by a computer, such as journey
Sequence module.Generally, program module include routines performing specific tasks or implementing specific abstract data types, programs, objects,
Component, data structure etc..The application can also be practiced in a distributed computing environment, in these distributed computing environments,
By executing task by the connected remote processing devices of communication network.In a distributed computing environment, program module can
To be located in the local and remote computer storage media including storage equipment.
All the embodiments in this specification are described in a progressive manner, same and similar portion between each embodiment
Dividing may refer to each other, and each embodiment focuses on the differences from other embodiments.Especially for system reality
For applying example, since it is substantially similar to the method embodiment, so being described relatively simple, related place is referring to embodiment of the method
Part explanation.
The foregoing is merely the embodiments of this specification, are not limited to this specification.For art technology
For personnel, this specification can have various modifications and variations.It is all made any within the spirit and principle of this specification
Modification, equivalent replacement, improvement etc., should be included within the scope of the claims of this specification.
Claims (12)
1. a kind of method of computer implemented risk identification, comprising:
According to the business operation of user, sliding verifying is initiated to user；
It acquires the user and carries out the current sliding trace for executing slide when sliding verifying；
Reference sliding trace associated with the user is obtained, it is described to be grasped referring to sliding trace based on user execution sliding
The history sliding trace of work is determining；
It compares the current sliding trace and described referring to sliding trace, and the sliding is grasped according to obtained comparison result
Make carry out risk identification.
2. determining that the user executes the method for claim 1, wherein according to the history sliding trace of the user
Slide includes: referring to the step of sliding trace
Determine the starting point coordinate of track starting point and the terminal point coordinate of final on trajectory in the current sliding trace；
The starting point coordinate and the terminal point coordinate are input to what the pre- history sliding trace for first passing through the user trained
Trajectory generative model executes the reference sliding trace of slide with the determination user.
3. the method for claim 1, wherein comparing the current sliding trace and described referring to sliding trace
Before step, further includes:
It acquires the user and carries out the behavioral data for executing slide when sliding verifying；
According to the behavioral data, the corresponding track characteristic of the current sliding trace is determined；
Include: to the step of slide progress risk identification according to obtained comparison result
According to the track characteristic and the comparison result, risk identification is carried out to the slide.
4. method as claimed in claim 3, wherein according to the behavioral data, determine the track of the current sliding trace
The step of feature includes:
Several sampled points are determined in the current sliding trace；
For each sampled point, according at least to the behavioral data, the corresponding sampling point feature of the sampled point, the sampling are determined
Point feature includes: that user executes that the slide slides into the gliding cable structure of the sampled point, the current sliding trace is located at
At least one of slope at the sampled point；
According to several sampled points the current sliding trace sequencing, by the corresponding sampling of several sampled points
Point feature is ranked up, and obtains sampled point characteristic sequence；
The sampled point characteristic sequence is determined as to the track characteristic of the current sliding trace.
5. method as claimed in claim 3, wherein according to the track characteristic and the comparison result, to the sliding
Operating the step of carrying out risk identification includes:
Determine the current sliding trace and the track difference referring between sliding trace；
According to the track characteristic and the track difference, risk identification is carried out to the slide.
6. method as claimed in claim 5, wherein according to the track characteristic and the track difference, to the sliding
Operating the step of carrying out risk identification includes:
The track characteristic and the track difference are input to identification model trained in advance, to pass through the identification mould
Type carries out risk identification to the slide.
7. method as claimed in claim 6, wherein the identification model includes: the first identification model and the second identification model
At least one of, first identification model is obtained by predefining each negative sample training, and described second knows
Other model is obtained by predefining each positive sample and negative sample training, and the positive sample is to be gone through according to each user
There are the sample that the history sliding trace of risk and historical behavior data are determined in history, the negative sample is according to each user
There is no the samples that the history sliding trace of risk and historical behavior data are determined in history.
8. the method for claim 7, wherein the track characteristic and the track difference are input to preparatory training
Identification model, to include: the step of by the identification model, carrying out risk identification to the slide
It is input in first identification model using the track characteristic and the track difference as initial data, obtains institute
State the reconstruct data that the first identification model is rebuild based on the initial data；
By the way that the reconstruct data and the initial data are compared, risk identification is carried out to the slide.
9. the method for claim 7, wherein the track characteristic and the track difference are input to preparatory training
Identification model in, with by the identification model to the slide carry out risk identification the step of include:
The track characteristic and the track difference are input to first identification model, obtain the first recognition result, it will
The track characteristic and the track difference are input to the second identification model, obtain the second recognition result；
According to first recognition result, the second recognition result, corresponding first weight of first identification model and described
Corresponding second weight of second identification model carries out risk identification to the slide.
10. a kind of device of risk identification, comprising:
Initiation module initiates sliding verifying to user for the business operation according to user；
Acquisition module carries out the current sliding trace that slide is executed when sliding verifying for acquiring the user；
Module is obtained, associated with the user referring to sliding trace for obtaining, the reference sliding trace is based on described
The history sliding trace that user executes slide is determining；
Identification module, for comparing the current sliding trace and the reference sliding trace, and according to obtained comparison knot
Fruit carries out risk identification to the slide.
11. a kind of computer readable storage medium, which is characterized in that the storage medium is stored with computer program, the meter
The described in any item methods of the claims 1~9 are realized when calculation machine program is executed by processor.
12. a kind of electronic equipment including memory, processor and stores the calculating that can be run on a memory and on a processor
Machine program, which is characterized in that the processor realizes the described in any item sides of the claims 1~9 when executing described program
Method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910736167.7A CN110532755B (en) | 2019-08-09 | 2019-08-09 | Computer-implemented risk identification method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910736167.7A CN110532755B (en) | 2019-08-09 | 2019-08-09 | Computer-implemented risk identification method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110532755A true CN110532755A (en) | 2019-12-03 |
| CN110532755B CN110532755B (en) | 2020-11-03 |
Family
ID=68662399
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910736167.7A Active CN110532755B (en) | 2019-08-09 | 2019-08-09 | Computer-implemented risk identification method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110532755B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112016077A (en) * | 2020-07-14 | 2020-12-01 | 北京淇瑀信息科技有限公司 | Page information acquisition method and device based on sliding track simulation and electronic equipment |
| CN112287325A (en) * | 2020-12-31 | 2021-01-29 | 北京明略软件系统有限公司 | Operation verification method, operation verification device, storage medium and electronic device |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103729127A (en) * | 2013-12-24 | 2014-04-16 | 广西大学 | Method for controlling browser by mouse moving trajectory |
| US20170028661A1 (en) * | 2015-07-27 | 2017-02-02 | Chun-Yen Hsieh | Mold and method for getting foot model thereof |
| CN107153786A (en) * | 2017-05-26 | 2017-09-12 | 北京奇点数聚科技有限公司 | A kind of man-machine recognition methods, system and terminal device, readable storage medium storing program for executing |
| CN107704190A (en) * | 2017-11-06 | 2018-02-16 | 广东欧珀移动通信有限公司 | Gesture identification method, device, terminal and storage medium |
| CN108229128A (en) * | 2017-04-10 | 2018-06-29 | 珠海市魅族科技有限公司 | A kind of method and device of information identification |
| CN108594995A (en) * | 2018-04-13 | 2018-09-28 | 广东小天才科技有限公司 | A kind of electronic device method and electronic equipment based on gesture identification |
| CN109033793A (en) * | 2018-07-11 | 2018-12-18 | 北京京东金融科技控股有限公司 | Slide the man-machine recognition methods of identifying code and device, electronic equipment and readable medium |
| CN109902471A (en) * | 2019-01-08 | 2019-06-18 | 平安科技（深圳）有限公司 | Detection method, device, computer equipment and the storage medium of sliding block verifying |
-
2019
- 2019-08-09 CN CN201910736167.7A patent/CN110532755B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103729127A (en) * | 2013-12-24 | 2014-04-16 | 广西大学 | Method for controlling browser by mouse moving trajectory |
| US20170028661A1 (en) * | 2015-07-27 | 2017-02-02 | Chun-Yen Hsieh | Mold and method for getting foot model thereof |
| CN108229128A (en) * | 2017-04-10 | 2018-06-29 | 珠海市魅族科技有限公司 | A kind of method and device of information identification |
| CN107153786A (en) * | 2017-05-26 | 2017-09-12 | 北京奇点数聚科技有限公司 | A kind of man-machine recognition methods, system and terminal device, readable storage medium storing program for executing |
| CN107704190A (en) * | 2017-11-06 | 2018-02-16 | 广东欧珀移动通信有限公司 | Gesture identification method, device, terminal and storage medium |
| CN108594995A (en) * | 2018-04-13 | 2018-09-28 | 广东小天才科技有限公司 | A kind of electronic device method and electronic equipment based on gesture identification |
| CN109033793A (en) * | 2018-07-11 | 2018-12-18 | 北京京东金融科技控股有限公司 | Slide the man-machine recognition methods of identifying code and device, electronic equipment and readable medium |
| CN109902471A (en) * | 2019-01-08 | 2019-06-18 | 平安科技（深圳）有限公司 | Detection method, device, computer equipment and the storage medium of sliding block verifying |
Non-Patent Citations (1)
| Title |
|---|
| 周茜: "基于行为的动态信任量化机制的研究与应用", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112016077A (en) * | 2020-07-14 | 2020-12-01 | 北京淇瑀信息科技有限公司 | Page information acquisition method and device based on sliding track simulation and electronic equipment |
| CN112016077B (en) * | 2020-07-14 | 2024-03-12 | 北京淇瑀信息科技有限公司 | Page information acquisition method and device based on sliding track simulation and electronic equipment |
| CN112287325A (en) * | 2020-12-31 | 2021-01-29 | 北京明略软件系统有限公司 | Operation verification method, operation verification device, storage medium and electronic device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110532755B (en) | 2020-11-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108961174A (en) | A kind of image repair method, device and electronic equipment | |
| CN107679700A (en) | Business flow processing method, apparatus and server | |
| CN109189682A (en) | A kind of script method for recording and device | |
| CN107526667A (en) | A kind of Indexes Abnormality detection method, device and electronic equipment | |
| CN109086961A (en) | A kind of Information Risk monitoring method and device | |
| CN110019903A (en) | Generation method, searching method and terminal, the system of image processing engine component | |
| CN109062782A (en) | A kind of selection method of regression test case, device and equipment | |
| CN109428719A (en) | A kind of auth method, device and equipment | |
| CN109087106A (en) | Identify air control model training, air control method, apparatus and the equipment of secondary account takeover of distributing telephone numbers | |
| CN109784599A (en) | A kind of method, device and equipment of model training, risk identification | |
| CN110262937A (en) | A kind of recognition methods of Indexes Abnormality reason and device | |
| CN110414098A (en) | A kind of generation method and device of Simulation Test Environment | |
| CN110032698A (en) | Information display method and device, information processing method and device | |
| CN109002949A (en) | A kind of method and device of air control strategy configuration and business air control | |
| CN110532755A (en) | A kind of method and device of computer implemented risk identification | |
| CN109947643A (en) | A kind of configuration method, device and the equipment of the experimental program based on A/B test | |
| CN109922298A (en) | Meeting room monitoring method and device | |
| CN110378400A (en) | A kind of model training method and device for image recognition | |
| CN107291222A (en) | Interaction processing method, device, system and the virtual reality device of virtual reality device | |
| CN108537012A (en) | Source code based on variable and code execution sequence obscures method and device | |
| CN109359120A (en) | Data-updating method, device and equipment in a kind of model training | |
| CN110532295A (en) | A kind of method and device of computer-implemented information processing, information inquiry | |
| CN109597678A (en) | Task processing method and device | |
| CN110473319A (en) | A kind of door opening method of access control system, device, equipment and readable medium | |
| CN109034534A (en) | A kind of model score means of interpretation, device and 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |