Summary of the invention
The purpose of this specification one or more embodiment is to provide a kind of question pushing method and device, asks to improve
Push-mechanism is inscribed, so that more specific aim the problem of push.
In order to solve the above technical problems, this specification one or more embodiment is achieved in that
On the one hand, this specification one or more embodiment provides a kind of question pushing method, comprising:
Determine the characteristic attribute of the validation problem of target user;Wherein, the characteristic attribute includes: the answer of validation problem
Accuracy, safe coefficient, in degree of privacy at least one of;
According to the characteristic attribute of the validation problem, the push score value of the validation problem is determined;
According to the push score value of each validation problem, the target verification problem pushed to the target user is determined.
Optionally, the characteristic attribute according to the validation problem determines the push score value of the validation problem, packet
It includes:
Determine the weight of the characteristic attribute of the validation problem, and, determine the category of the characteristic attribute of the validation problem
Property value;
The weighted value of the weight of the characteristic attribute of the validation problem and attribute value is determined as the validation problem
Push score value.
Optionally, the weight of the characteristic attribute of the determination validation problem, comprising:
According to the scene of the service for checking credentials corresponding to the target user and/or type of service, the validation problem is determined
Characteristic attribute weight.
Optionally, the characteristic attribute includes the answer accuracy of the validation problem;
Correspondingly, determining the attribute value of the characteristic attribute of the validation problem, comprising:
Obtain historical behavior data of the target user in the corresponding business of current authentication service, the history row
It include to the history usage behavior information of the business, for the history answer behavioural information of the validation problem, institute for data
State at least one in the answer percent of pass score of validation problem;
Construct specified two disaggregated models;
It is trained the historical behavior data as the sample data of specified two disaggregated models, obtains described test
The answer accuracy of card problem.
Optionally, the history answer behavioural information includes answer as a result, the answer result includes correct result or mistake
Accidentally result;
The method also includes:
Obtain the answer result that the target user is directed to the target verification problem in current authentication service;
According to the answer for the target verification problem as a result, updating the answer accuracy of the target verification problem.
Optionally, the characteristic attribute includes the safe coefficient;
Correspondingly, determining the attribute value of the characteristic attribute of the validation problem, comprising:
According to the keyword for including in the validation problem, information content entrained by the validation problem is determined;
The safe coefficient of the validation problem is determined according to the information content, wherein the information content and the safe journey
It spends directly proportional.
Optionally, the characteristic attribute includes the degree of privacy;
Correspondingly, determining the attribute value of the characteristic attribute of the validation problem, comprising:
Determine the degree of correlation between the validation problem and the personal information of the target user;
The degree of privacy of the validation problem is determined according to the degree of correlation, wherein the degree of correlation and the privacy journey
It spends directly proportional.
Optionally, according to the push score value of each validation problem, determination is tested to the target that the target user pushes
Card problem, comprising:
The push highest validation problem of score value is determined as the target verification problem pushed to the target user;
Or,
It is up to validation problem corresponding to the push score value of preset threshold and is determined as the mesh pushed to the target user
Mark validation problem.
On the other hand, this specification one or more embodiment provides a kind of problem driving means, comprising:
First determining module determines the characteristic attribute of the validation problem of target user;Wherein, the characteristic attribute includes:
The answer accuracy of validation problem, safe coefficient, in degree of privacy at least one of;
Second determining module determines the push score value of the validation problem according to the characteristic attribute of the validation problem;
Third determining module is pushed according to the push score value of each validation problem, determination to the target user
Target verification problem.
Optionally, second determining module includes:
First determination unit determines the weight of the characteristic attribute of the validation problem, and, determine the validation problem
The attribute value of characteristic attribute;
The weighted value of the weight of the characteristic attribute of the validation problem and attribute value is determined as institute by the second determination unit
State the push score value of validation problem.
Optionally, first determination unit, according to the scene of the service for checking credentials corresponding to the target user and/or industry
Service type determines the weight of the characteristic attribute of the validation problem.
Optionally, the characteristic attribute includes the answer accuracy of the validation problem;
First determination unit obtains history row of the target user in the corresponding business of current authentication service
For data, the historical behavior data include to the history usage behavior information of the business, going through for the validation problem
At least one of in history answer behavioural information, the answer percent of pass score of the validation problem;Construct specified two disaggregated models;It will
The historical behavior data are trained as the sample data of specified two disaggregated models, obtain answering for the validation problem
Inscribe accuracy.
Optionally, the history answer behavioural information includes answer as a result, the answer result includes correct result or mistake
Accidentally result;
Described device further include:
Module is obtained, the answer knot that the target user is directed to the target verification problem in current authentication service is obtained
Fruit;
Update module, according to the answer for the target verification problem as a result, updating answering for the target verification problem
Inscribe accuracy.
Optionally, the characteristic attribute includes the safe coefficient;
First determination unit determines that the validation problem is taken according to the keyword for including in the validation problem
The information content of band;The safe coefficient of the validation problem is determined according to the information content, wherein the information content and the safety
Degree is directly proportional.
Optionally, the characteristic attribute includes the degree of privacy;
First determination unit, determines the correlation between the validation problem and the personal information of the target user
Degree;The degree of privacy of the validation problem is determined according to the degree of correlation, wherein the degree of correlation and the degree of privacy are at just
Than.
Optionally, the third determining module includes:
The push highest validation problem of score value is determined as the mesh pushed to the target user by third determination unit
Mark validation problem;Or,
4th determination unit is up to validation problem corresponding to the push score value of preset threshold and is determined as to the target
The target verification problem of user's push.
In another aspect, this specification one or more embodiment provides a kind of problem pushing equipment, comprising:
Processor;And
It is arranged to the memory of storage computer executable instructions, the executable instruction makes the place when executed
Manage device:
Determine the characteristic attribute of the validation problem of target user;Wherein, the characteristic attribute includes: the answer of validation problem
Accuracy, safe coefficient, in degree of privacy at least one of;
According to the characteristic attribute of the validation problem, the push score value of the validation problem is determined;
According to the push score value of each validation problem, the target verification problem pushed to the target user is determined.
In another aspect, this specification one or more embodiment provides a kind of storage medium, can be held for storing computer
Row instruction, the executable instruction realize following below scheme when executed:
Determine the characteristic attribute of the validation problem of target user;Wherein, the characteristic attribute includes: the answer of validation problem
Accuracy, safe coefficient, in degree of privacy at least one of;
According to the characteristic attribute of the validation problem, the push score value of the validation problem is determined;
According to the push score value of each validation problem, the target verification problem pushed to the target user is determined.
Using the technical solution of this specification one or more embodiment, the spy of the validation problem of target user can determine
At least one of sign attribute (in answer accuracy, safe coefficient, degree of privacy including validation problem), it is true according to characteristic attribute
Determine the push score value of validation problem, and then is determined according to the push score value of each validation problem to the target that target user pushes and tested
Card problem.Therefore, which can take into account the answer of the validation problem of target user when pushing validation problem to user
Accuracy, safe coefficient and/or degree of privacy, thus can more targetedly when carrying out authentication using question and answer mode
Ground neatly to user pushes validation problem, the perfect push-mechanism of validation problem, and promoted the answer percent of pass of user with
And safety and the privacy of the service for checking credentials, and then user is promoted to the Experience Degree of the service for checking credentials.
Specific embodiment
This specification one or more embodiment provides a kind of question pushing method and device, to improve problem pusher
System, so that more specific aim the problem of push.
In order to make those skilled in the art more fully understand the technical solution in this specification one or more embodiment,
Below in conjunction with the attached drawing in this specification one or more embodiment, to the technology in this specification one or more embodiment
Scheme is clearly and completely described, it is clear that and described embodiment is only this specification a part of the embodiment, rather than
Whole embodiments.Based on this specification one or more embodiment, those of ordinary skill in the art are not making creativeness
The model of this specification one or more embodiment protection all should belong in every other embodiment obtained under the premise of labour
It encloses.
Fig. 1 be according to a kind of schematic flow chart of question pushing method of one embodiment of this specification, as shown in Figure 1,
This method comprises:
Step S102 determines the characteristic attribute of the validation problem of target user.
Wherein, characteristic attribute includes at least one in the answer accuracy, safe coefficient, degree of privacy of validation problem.
Step S104 determines the push score value of validation problem according to the characteristic attribute of validation problem.
Step S106 determines the target verification problem pushed to target user according to the push score value of each validation problem.
Using the technical solution of this specification one or more embodiment, the spy of the validation problem of target user can determine
At least one of sign attribute (in answer accuracy, safe coefficient, degree of privacy including validation problem), it is true according to characteristic attribute
Determine the push score value of validation problem, and then is determined according to the push score value of each validation problem to the target that target user pushes and tested
Card problem.Therefore, which can take into account the answer of the validation problem of target user when pushing validation problem to user
Accuracy, safe coefficient and/or degree of privacy, thus can more targetedly when carrying out authentication using question and answer mode
Ground neatly to user pushes validation problem, the perfect push-mechanism of validation problem, and promoted the answer percent of pass of user with
And safety and the privacy of the service for checking credentials, and then user is promoted to the Experience Degree of the service for checking credentials.
In one embodiment, when determining the push score value of validation problem according to the characteristic attribute of validation problem, first really
Determine the weight of the characteristic attribute of validation problem, and, determine the attribute value of the characteristic attribute of validation problem;In turn by validation problem
The weight of characteristic attribute and the weighted value of attribute value be determined as the push score value of validation problem.
In the present embodiment, the weight of the characteristic attribute of validation problem can be according to the field of the service for checking credentials corresponding to target user
Scape and/or type of service determine.Wherein, the scene of the service for checking credentials such as logged in using account, modification information;Verifying clothes
The type of service of business is such as done shopping class, game class, financial class.It, can according to the scene of the service for checking credentials and/or the difference of type of service
For the characteristic attribute of validation problem, different weights is set.For example, when the scene of the service for checking credentials is modification information, it can be to spy
Safe coefficient and degree of privacy are respectively provided with higher weight in sign attribute;When the type of service of the service for checking credentials belongs to financial class,
Higher weight can be set to safe coefficient in characteristic attribute;It, can be to spy when the type of service of the service for checking credentials belongs to shopping class
It levies in attribute and higher weight is arranged to the answer accuracy of validation problem;Etc..
Under normal conditions, same user can correspond to multiple and different validation problems.Therefore, the multiple of target user are tested
Card problem, the weight of the characteristic attribute of each validation problem may be configured as identical, may be alternatively provided as difference.
In the present embodiment, the forms such as score value, probability are can be used in the characteristic manner of attribute value.For example, user is to each problem
The corresponding attribute value of answer accuracy can be answer accuracy itself, and the corresponding attribute value of the safe coefficient of each problem can be
Safe score, the corresponding attribute value of the degree of privacy of each problem can be privacy score value.Each characteristic attribute of same validation problem
Corresponding weight and be 1.
The attribute value of the characteristic attribute described in detail below for how determining validation problem.
When characteristic attribute includes the answer accuracy of validation problem, the answer of validation problem can be determined as follows
Accuracy (i.e. the attribute value of answer accuracy):
Firstly, obtaining historical behavior data of the target user in the corresponding business of current authentication service, the history row
It include to the history usage behavior information of the business, for the history answer behavioural information of validation problem, validation problem for data
Answer percent of pass score at least one of.
Wherein, history answer behavioural information includes answer as a result, answer result includes correct result or error result.
Table 1 schematically illustrates the answer percent of pass scoring event of some validation problem.The verifying is asked as seen from Table 1
Corresponding relationship between the answer percent of pass and answer percent of pass score of topic, for example, if the answer percent of pass of the validation problem is
50%, then its corresponding answer percent of pass is scored at 50 points;If the answer percent of pass of the validation problem is 60%, corresponding
Answer percent of pass is scored at 70 points;If the answer percent of pass of the validation problem is 90%, corresponding answer percent of pass score
It is 98 points;Etc..
Table 1
Answer percent of pass |
Answer percent of pass score |
50% |
50 points |
60% |
70 points |
90% |
98 points |
The answer percent of pass scoring event of each validation problem can be identical, can not also be identical.In one embodiment, it is
When each validation problem presets answer percent of pass score, the complexity, safe coefficient, privacy journey of each validation problem can be comprehensively considered
The factors such as degree can be asked according to the difference of the factors such as the complexity, safe coefficient or degree of privacy of each validation problem for each verifying
Topic sets different answer percent of pass scores.For example, can be arranged if the difficulty of validation problem is higher for the validation problem higher
Answer percent of pass score.
Secondly, constructing specified two disaggregated models.
Again, it is trained historical behavior data as the sample data of specified two disaggregated models, is verified problem
Answer accuracy.
Wherein, two disaggregated models are specified to can be bis- disaggregated model of xgboost, using bis- disaggregated model of xgboost to sample
The process that notebook data is trained is the prior art, therefore is repeated no more.Certainly, two disaggregated models are specified to can also be other classes
Two disaggregated models of type, the present embodiment do not limit this.
When characteristic attribute includes the safe coefficient of validation problem, the safe journey of validation problem can be determined as follows
Degree (i.e. the attribute value of safe coefficient): firstly, according to the keyword for including in validation problem, letter entrained by validation problem is determined
Breath amount;Secondly, determining the safe coefficient of validation problem according to information content, wherein information content is directly proportional to safe coefficient.
Specifically, the keyword for including in validation problem is more, entrained by information content it is bigger, then the validation problem
Safe coefficient it is also higher.For example, for validation problem 1 --- " what the most expensive commodity that you bought in the recent period are? ",
In include keyword include " most expensive ", " what is ";For validation problem 2 --- " commodity that you bought in the recent period are assorted
? ", keyword wherein included only includes " what is ";Obviously, it contains much information entrained by validation problem 1 in validation problem 2
Entrained information content, the safe coefficient of validation problem 1 are higher than the safe coefficient of validation problem 2.
When characteristic attribute includes the degree of privacy of validation problem, the privacy journey of validation problem can be determined as follows
It spends (i.e. the attribute value of degree of privacy): firstly, determining the degree of correlation between validation problem and the personal information of target user;Its
It is secondary, the degree of privacy of validation problem is determined according to the degree of correlation, wherein the degree of correlation is directly proportional to degree of privacy.
Specifically, the degree of correlation between validation problem and the personal information of target user is higher, the privacy of the validation problem
Degree is higher;Conversely, the degree of correlation the end of month between validation problem and the personal information of target user, then the validation problem is hidden
Private degree is lower.Wherein, the personal information of target user may include name, the pet name, account information, binding bank's card number,
Phone number etc..For example, for validation problem 3 --- " which is bank's card number bound in your current account? ", and verifying
Problem 4 --- " which is the wifi that you use? ", due to the personal information (i.e. bank's card number) of validation problem 3 and target user
The degree of correlation is very high, and validation problem 4 is not related to the personal information of target user, therefore the degree of privacy of validation problem 3 is higher than and tests
The degree of privacy of card problem 4.
For example, the service for checking credentials is carried out in Taobao.When target user logs in Taobao's account every time, server can be used
Problem core body mode verifies user identity, that is, to target user show one or two validation problem relevant to Taobao for
Family answer.So, it can determine that target is used using the usage behavior information of Taobao using multiple authentication process and target user
Answer percent of pass of the family to each problem.
Historical behavior data of the target user in Taobao are obtained first.Wherein, which includes user couple
The history usage behavior information of Taobao passes through the history answer behavioural information of each validation problem and the answer of each validation problem
Rate score.History usage behavior information of the target user to Taobao and the history answer behavioural information to each validation problem can be pre-
It is first recorded and is counted, server end can be pre-stored within for the answer percent of pass score of each validation problem.For example, target
User to the history usage behavior information of Taobao such as: the user bought commodity A, commodity B and commodity in nearest one month
C, the wifi used when logging in Taobao's account in the user nearest half a year are " 12345678 ";Target user is to each validation problem
History answer behavioural information is such as: having 3 correct results and 2 error results for problem a, has 10 correct knots for problem b
Fruit;The answer percent of pass score of each validation problem is as shown in table 1.For concise explanation, the answer of each validation problem in the present embodiment
Percent of pass scoring event can be identical.
After getting historical behavior data of the target user in Taobao, bis- disaggregated model of xgboost is constructed.
After constructing bis- disaggregated model of xgboost, using historical behavior data as the sample number of bis- disaggregated model of xgboost
According to being trained, it is verified the answer accuracy of problem.For example, target user is 70% to the answer accuracy of problem a, it is right
The answer accuracy of problem b is 98%, and the answer accuracy to problem c is 80%, etc..
Continue to use the example above determine validation problem characteristic attribute attribute value and weight.Wherein, the category of characteristic attribute
Property value use and score value and/or Probability Forms characterize, specifically may include the answer accuracy verified user to validation problem, verifying
The safe score and privacy score value of problem.For concise explanation, three validation problems are only enumerated in the present embodiment, such as problem a, are asked
B and problem c is inscribed, the validation problem quantity in practical application in problem base is typically much deeper than three.
Table 2- table 4 illustratively respectively illustrates the corresponding category of each characteristic attribute of problem a, problem b and problem c
Property value and weight.Wherein, the corresponding weight of each characteristic attribute of each problem and be 1.
Table 2
The characteristic attribute of problem a |
Attribute value |
Weight |
Answer percent of pass |
80% |
40% |
Safe score |
80 points |
40% |
Privacy score value |
50 points |
20% |
Table 3
The characteristic attribute of problem b |
Attribute value |
Weight |
Answer percent of pass |
98% |
50% |
Safe score |
60 points |
30% |
Privacy score value |
50 points |
20% |
Table 4
The characteristic attribute of problem c |
Attribute value |
Weight |
Answer percent of pass |
70% |
30% |
Safe score |
40 points |
10% |
Privacy score value |
80 points |
60% |
The problem of being shown based on table 2- table 4 a, the corresponding attribute value of each characteristic attribute of problem b and problem c and power
Value, is weighted summation for the corresponding attribute value of each characteristic attribute and weight of each problem, can calculate each problem
Push score value.
Specifically, the push score value Ta=80%*40%+80*40%+50*20%=42.32 of problem a;Problem b's pushes away
Send score value Tb=98%*50%+60*30%+50*20%=28.49;The push score value Tc=70%*30%+40* of problem c
10%+80*60%=52.21.
After the push score value for calculating go wrong a, problem b and problem c, according to the push score value of each validation problem
Each validation problem is ranked up.In the present embodiment, push score value sequence from high to low according to each validation problem is to respectively testing
Card problem is ranked up, and due to the push score value highest of problem c, the push score value time of problem a is high, and the push score value of problem b is most
It is low, therefore ranking results are problem c > problem a > problem b.
In one embodiment, to when pushing target verification problem with target user, the highest verifying of score value will can be pushed
Problem is determined as the target verification problem pushed to target user;It is tested or, being up to corresponding to the push score value of preset threshold
Card problem is determined as the target verification problem pushed to target user.
The example above is continued to use, after obtaining ranking results, target verification problem can be pushed to Taobao according to ranking results.
Assuming that target verification problem is the push highest validation problem of score value, then can push to problem c as target verification problem
Target user.
As seen from the above embodiment, the answer accuracy of validation problem and target user are in current authentication service corresponding
Historical behavior data in business are related, the safe coefficient of validation problem with its entrained by information content it is related, the information content and
Historical behavior of the target user in the business is information-related, the degree of privacy and the personal information phase of target user of validation problem
It closes.Since different user is corresponding with respective different historical behavior data and different personal information, for different
The characteristic attribute of target user, validation problem are different, when this to push validation problem for different target users, phase
It is also different with the corresponding push score value of validation problem.
In one embodiment, after target verification problem being pushed to target user, target user asks target verification
Topic carries out answer.By obtaining answer of the target user in current authentication service for target verification problem as a result, can basis
The answer result updates the answer accuracy of target verification problem, and then updates target verification according to updated answer accuracy
The push score value of problem.For example, target verification problem is problem c.Assuming that target user is to target verification problem --- problem c's
Answer result is correct as a result, being then updated according to answer accuracy of the answer result to problem c, at this point, target user
It increases after being updated to the answer accuracy of problem c.
In the present embodiment, target verification problem can be answered based on answer result of the target user to target verification problem
Topic accuracy be updated, and then update target verification problem push score value, enable the push score value of validation problem with
Target user the answer result of validation problem is updated in time, to make the target verification problem for pushing to target user
It is more in line with the answer demand of target user, that is, reduces the error rate of target user's answer.
To sum up, the specific embodiment of this theme is described.Other embodiments are in the appended claims
In range.In some cases, the movement recorded in detail in the claims can execute and still in a different order
Desired result may be implemented.In addition, process depicted in the drawing not necessarily requires the particular order shown or continuous suitable
Sequence, to realize desired result.In some embodiments, multitasking and parallel processing can be advantageous.
The problem of the above are the offers of this specification one or more embodiment method for pushing, is based on same thinking, this theory
Bright book one or more embodiment also provides a kind of problem driving means.
Fig. 2 is the schematic block diagram according to a kind of problem driving means of one embodiment of this specification.As shown in Fig. 2, should
Device includes:
First determining module 210, determines the characteristic attribute of the validation problem of target user;Wherein, characteristic attribute includes: to test
The answer accuracy of card problem, safe coefficient, in degree of privacy at least one of;
Second determining module 220 determines the push score value of validation problem according to the characteristic attribute of validation problem;
Third determining module 230, according to the push score value of each validation problem, determination is tested to the target that target user pushes
Card problem.
Optionally, the second determining module 220 includes:
First determination unit determines the weight of the characteristic attribute of validation problem, and, determine the characteristic attribute of validation problem
Attribute value;
The weighted value of the weight of the characteristic attribute of validation problem and attribute value is determined as verifying and asked by the second determination unit
The push score value of topic.
Optionally, the first determination unit, the scene and/or type of service of the service for checking credentials according to corresponding to target user,
Determine the weight of the characteristic attribute of validation problem.
Optionally, characteristic attribute includes the answer accuracy of validation problem;
First determination unit obtains historical behavior data of the target user in the corresponding business of current authentication service,
Historical behavior data include the history usage behavior information to business, the history answer behavioural information for validation problem, verifying
At least one of in the answer percent of pass score of problem;Construct specified two disaggregated models;Using historical behavior data as specified two
The sample data of disaggregated model is trained, and is verified the answer accuracy of problem.
Optionally, history answer behavioural information includes answer as a result, answer result includes correct result or error result;
Above-mentioned apparatus further include:
Module is obtained, the answer result that target user is directed to target verification problem in current authentication service is obtained;
Update module, according to the answer for target verification problem as a result, updating the answer accuracy of target verification problem.
Optionally, characteristic attribute includes safe coefficient;
First determination unit determines information content entrained by validation problem according to the keyword for including in validation problem;Root
The safe coefficient of validation problem is determined according to information content, wherein information content is directly proportional to safe coefficient.
Optionally, characteristic attribute includes degree of privacy;
First determination unit determines the degree of correlation between validation problem and the personal information of target user;According to the degree of correlation
Determine the degree of privacy of validation problem, wherein the degree of correlation is directly proportional to degree of privacy.
Optionally, third determining module 230 includes:
Third determination unit will push the highest validation problem of score value and be determined as asking to the target verification that target user pushes
Topic;Or,
4th determination unit is up to validation problem corresponding to the push score value of preset threshold and is determined as to target user
The target verification problem of push.
Using the device of this specification one or more embodiment, the feature category of the validation problem of target user can determine
At least one of property (in answer accuracy, safe coefficient, degree of privacy including validation problem), it is tested according to characteristic attribute determination
The push score value of card problem, and then determined according to the push score value of each validation problem to the target verification that target user pushes and asked
Topic.Therefore, for the technical solution when pushing validation problem to user, the answer that can take into account the validation problem of target user is correct
Rate, safe coefficient and/or degree of privacy, thus using question and answer mode carry out authentication when can more targetedly,
Neatly push validation problem, the perfect push-mechanism of validation problem to user, and promoted user answer percent of pass and
The safety of the service for checking credentials and privacy, and then user is promoted to the Experience Degree of the service for checking credentials.
It should be understood that the problems in Fig. 2 driving means can be used to realize previously described ask
Inscribe method for pushing, datail description therein should be described with method part above it is similar, it is cumbersome to avoid, do not repeat separately herein.
Based on same thinking, this specification one or more embodiment also provides a kind of problem pushing equipment, such as Fig. 3 institute
Show.Problem pushing equipment can generate bigger difference because configuration or performance are different, may include one or more
Processor 301 and memory 302 can store one or more storage application programs or data in memory 302.Its
In, memory 302 can be of short duration storage or persistent storage.Be stored in memory 302 application program may include one or
More than one module (diagram is not shown), each module may include executable to the series of computation machine in problem pushing equipment
Instruction.Further, processor 301 can be set to communicate with memory 302, execute memory on problem pushing equipment
Series of computation machine executable instruction in 302.Problem pushing equipment can also include one or more power supplys 303, one
A or more than one wired or wireless network interface 304, one or more input/output interfaces 305, one or one with
Upper keyboard 306.
Specifically in the present embodiment, problem pushing equipment includes memory and one or more program,
In one perhaps more than one program is stored in memory and one or more than one program may include one or one
With upper module, and each module may include and being configured to the series of computation machine executable instruction in problem pushing equipment
With by one or more than one processor execute this or more than one program include can for carrying out following computer
It executes instruction:
Determine the characteristic attribute of the validation problem of target user;Wherein, the characteristic attribute includes: the answer of validation problem
Accuracy, safe coefficient, in degree of privacy at least one of;
According to the characteristic attribute of the validation problem, the push score value of the validation problem is determined;
According to the push score value of each validation problem, the target verification problem pushed to the target user is determined.
Optionally it is determined that the weight of the characteristic attribute of the validation problem, and, determine the feature category of the validation problem
The attribute value of property;
The weighted value of the weight of the characteristic attribute of the validation problem and attribute value is determined as the validation problem
Push score value.
Optionally, computer executable instructions when executed, can also make the processor:
According to the scene of the service for checking credentials corresponding to the target user and/or type of service, the validation problem is determined
Characteristic attribute weight.
Optionally, the characteristic attribute includes the answer accuracy of the validation problem;Computer executable instructions are in quilt
When execution, the processor can also be made:
Obtain historical behavior data of the target user in the corresponding business of current authentication service, the history row
It include to the history usage behavior information of the business, for the history answer behavioural information of the validation problem, institute for data
State at least one in the answer percent of pass score of validation problem;
Construct specified two disaggregated models;
It is trained the historical behavior data as the sample data of specified two disaggregated models, obtains described test
The answer accuracy of card problem.
Optionally, the history answer behavioural information includes answer as a result, the answer result includes correct result or mistake
Accidentally result;Computer executable instructions when executed, can also make the processor:
Obtain the answer result that the target user is directed to the target verification problem in current authentication service;
According to the answer for the target verification problem as a result, updating the answer accuracy of the target verification problem.
Optionally, the characteristic attribute includes the safe coefficient;Computer executable instructions when executed, can be with
Make the processor:
According to the keyword for including in the validation problem, information content entrained by the validation problem is determined;
The safe coefficient of the validation problem is determined according to the information content, wherein the information content and the safe journey
It spends directly proportional.
Optionally, the characteristic attribute includes the degree of privacy;Computer executable instructions when executed, can be with
Make the processor:
Determine the degree of correlation between the validation problem and the personal information of the target user;
The degree of privacy of the validation problem is determined according to the degree of correlation, wherein the degree of correlation and the privacy journey
It spends directly proportional.
Optionally, computer executable instructions when executed, can also make the processor:
The push highest validation problem of score value is determined as the target verification problem pushed to the target user;
Or,
It is up to validation problem corresponding to the push score value of preset threshold and is determined as the mesh pushed to the target user
Mark validation problem.
This specification one or more embodiment also proposed a kind of computer readable storage medium, this is computer-readable to deposit
Storage media stores one or more programs, which includes instruction, and it is included multiple application programs which, which works as,
Electronic equipment execute when, can make the electronic equipment execute above problem method for pushing, and be specifically used for execute:
Determine the characteristic attribute of the validation problem of target user;Wherein, the characteristic attribute includes: the answer of validation problem
Accuracy, safe coefficient, in degree of privacy at least one of;
According to the characteristic attribute of the validation problem, the push score value of the validation problem is determined;
According to the push score value of each validation problem, the target verification problem pushed to the target user is determined.
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 specification one or more embodiment.
It should be understood by those skilled in the art that, this specification one or more embodiment can provide for method, system or
Computer program product.Therefore, complete hardware embodiment can be used in this specification one or more embodiment, complete software is implemented
The form of example or embodiment combining software and hardware aspects.Moreover, this specification one or more embodiment can be used one
It is a or it is multiple wherein include computer usable program code computer-usable storage medium (including but not limited to disk storage
Device, CD-ROM, optical memory etc.) on the form of computer program product implemented.
This specification one or more embodiment is referring to according to the method for the embodiment of the present application, equipment (system) and meter
The flowchart and/or the block diagram of calculation machine program product describes.It should be understood that can be realized by computer program instructions flow chart and/
Or the combination of the process and/or box in each flow and/or block and flowchart and/or the block diagram in block diagram.It can
These computer program instructions are provided at general purpose computer, special purpose computer, Embedded Processor or other programmable datas
The processor of equipment is managed to generate a machine, so that holding by the processor of computer or other programmable data processing devices
Capable instruction generates for realizing in one or more flows of the flowchart and/or one or more blocks of the block diagram
The device of specified function.
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.
This specification one or more embodiment can computer executable instructions it is general on
It hereinafter describes, such as program module.Generally, program module includes executing particular task or realization particular abstract data type
Routine, programs, objects, component, data structure etc..The application can also be practiced in a distributed computing environment, at these
In distributed computing environment, by executing task by the connected remote processing devices of communication network.In distributed computing
In environment, program module can 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 this specification one or more embodiments, are not limited to this specification.For this
For the technical staff of field, this specification one or more embodiment can have various modifications and variations.It is all in this specification one
Any modification, equivalent replacement, improvement and so within the spirit and principle of a or multiple embodiments, should be included in this explanation
Within the scope of the claims of book one or more embodiment.