CN106296391A - A kind of assessment exceeds the time limit the method and apparatus of probability - Google Patents
A kind of assessment exceeds the time limit the method and apparatus of probability Download PDFInfo
- Publication number
- CN106296391A CN106296391A CN201610643696.9A CN201610643696A CN106296391A CN 106296391 A CN106296391 A CN 106296391A CN 201610643696 A CN201610643696 A CN 201610643696A CN 106296391 A CN106296391 A CN 106296391A
- Authority
- CN
- China
- Prior art keywords
- information
- party
- assessed
- time limit
- user
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present embodiments relate to financial field, the Internet, particularly relate to a kind of assessment and exceed the time limit the method and apparatus of probability, for making lending agency user is exceeded the time limit probability risk index be estimated.In the embodiment of the present invention, according to the authorization message of user, from multiple third-party application, obtain third party's information respectively；The information to be verified that predefined option is corresponding is extracted from each third party's information；Using third party's information consistent for information to be verified as third party's information to be assessed；Impose a condition, then using the information to be verified in third party's information to be assessed as effective information if the quantity of third party's information to be assessed meets；Effective information is inputted assessment models of exceeding the time limit, obtain the probability score that exceeds the time limit of user, assessment models of exceeding the time limit is that the result training that exceeds the time limit of the third party's information according to known users and known users obtains, so that lending agency assesses the probability risk index that exceeds the time limit of user according to the probability score that exceeds the time limit of user.
Description
Technical field
The present embodiments relate to financial field, the Internet, particularly relate to a kind of assessment and exceed the time limit the method and apparatus of probability.
Background technology
The financial institutions such as traditional bank, when passing judgment on the credit situation of client, can go out with reference to the working condition of client and unit
The financial institutions such as the income of tool proves economic level and the later repaying ability of this client are carried out comprehensive assessment, traditional bank
Judge whether this client is carried out credit and offers loans with this.Visible, the working condition of client is for gold such as traditional banks
Melting mechanism when passing judgment on the credit rating of client is non-the normally off key.
In prior art, financial institution mainly examines the information such as unit and the position of client's offer before loan, works as client
After obtaining loan, just cannot follow the trail of the information change of client the most in time, the most easily there is problems of, provide loan to client
After money, it is most likely that the phenomenon and the increase that produce promise breaking exceed the time limit the difficulty demanded.
In sum, prior art exists it is difficult to follow the tracks of customer information and then user cannot be obtained exceeds the time limit the asking of probability
Topic.
Summary of the invention
The embodiment of the present invention is difficult to follow the tracks of customer information and then cannot obtain user exceed the time limit for solving to exist in prior art
The problem of probability, it is provided that a kind of assessment exceeds the time limit the method and apparatus of probability, for obtaining according to from multiple third-party application
User's third party's information in each third-party application is comprehensively assessed, and obtains the probability score that exceeds the time limit of user.
The embodiment of the present invention provides a kind of method that assessment exceeds the time limit probability, including:
According to the authorization message of user, from multiple third-party application, obtain user respectively in each third-party application
Third party's information；
The information to be verified that predefined option is corresponding is extracted from each third party's information；
Using third party's information consistent for information to be verified as third party's information to be assessed；
Impose a condition, then by the letter to be verified in third party's information to be assessed if the quantity of third party's information to be assessed meets
Breath is as effective information；
Effective information is inputted assessment models of exceeding the time limit, obtains the probability score that exceeds the time limit of user, according to assessment models of exceeding the time limit
Third party's information of known users and known users exceed the time limit what result training obtained.
Alternatively, impose a condition, then by third party's information to be assessed if the quantity of third party's information to be assessed meets
Information to be verified as effective information, including:
Judge that the quantity of third party's information to be assessed is the most equal with the quantity of third-party application；
If equal, the information to be verified in third party's information the most to be assessed is as effective information.
Alternatively, impose a condition, then by third party's information to be assessed if the quantity of third party's information to be assessed meets
Information to be verified as effective information, including:
Determine the quantity of final updating time third party's information to be assessed in the first preset time period；
If the quantity of third party's information to be assessed that the final updating time is in the first preset time period and third-party application
The ratio of quantity exceed first threshold, then by final updating time third party's information to be assessed in the first preset time period
Information to be verified as effective information.
Alternatively, impose a condition, then by third party's information to be assessed if the quantity of third party's information to be assessed meets
Information to be verified as effective information, including:
Determine each third party's information to be assessed in the second preset time period by number of operations；
If number of operations exceedes the quantity of third party's information to be assessed of set point number and the ratio of the quantity of third-party application
Example exceedes Second Threshold, then number of operations exceedes the information to be verified of third party's information to be assessed of set point number as effectively
Information.
Alternatively, assessment models that effective information input is exceeded the time limit, obtain the probability score that exceeds the time limit of user, method includes:
The number of times that number of times effective information, third party's information to be assessed being queried and third party's information to be assessed are downloaded
It is input to assessment models of exceeding the time limit, obtains the probability score that exceeds the time limit of user.
Alternatively, assessment models of effective information input being exceeded the time limit, after obtaining the probability score that exceeds the time limit of user, method is also wrapped
Include:
If the probability score that exceeds the time limit of user is higher than the mark set, then using user as excessive risk user；Or
If the probability score that exceeds the time limit of user exceedes the probability score that exceeds the time limit last time of user reaches the 3rd threshold value, then user is made
For excessive risk user.
Alternatively, third party's information is user's biographic information in third-party application；
Predefined option includes following at least one or combination in any: unit, position, expection salary and resume state.
The embodiment of the present invention provides the device that a kind of assessment exceeds the time limit probability, including:
Acquiring unit: for the authorization message according to user, obtains user respectively each from multiple third-party application
Third party's information in third-party application, extracts the information to be verified that predefined option is corresponding from each third party's information；
Screening unit: be used for third party's information consistent for information to be verified as third party's information to be assessed；
Determine unit: if the quantity being used for third party's information to be assessed meets impose a condition, then third party to be assessed believed
Information to be verified in breath is as effective information；
Output unit: for assessment models that effective information input is exceeded the time limit, obtain the probability score that exceeds the time limit of user, exceed the time limit and comment
Estimate the result training that exceeds the time limit that model is the third party's information according to known users and known users to obtain.
Optionally it is determined that unit specifically for:
Judge that the quantity of third party's information to be assessed is the most equal with the quantity of third-party application；
If equal, the information to be verified in third party's information the most to be assessed is as effective information.
Optionally it is determined that unit specifically for:
Determine the quantity of final updating time third party's information to be assessed in the first preset time period；
If the quantity of third party's information to be assessed that the final updating time is in the first preset time period and third-party application
The ratio of quantity exceed first threshold, by final updating time third party's information to be assessed in the first preset time period
Information to be verified is as effective information.
Optionally it is determined that unit specifically for:
Determine each third party's information to be assessed in the second preset time period by number of operations；
If number of operations exceedes the quantity of third party's information to be assessed of set point number and the ratio of the quantity of third-party application
Example exceedes Second Threshold, then number of operations exceedes the information to be verified of third party's information to be assessed of set point number as effectively
Information.
Alternatively, output unit specifically for:
The number of times that number of times effective information, third party's information to be assessed being queried and third party's information to be assessed are downloaded
It is input to assessment models of exceeding the time limit, obtains the probability score that exceeds the time limit of user.
Optionally it is determined that unit is additionally operable to:
If the probability score that exceeds the time limit of user is higher than the mark set, then using user as excessive risk user；Or
If the probability score that exceeds the time limit of user exceedes the probability score that exceeds the time limit last time of user reaches the 3rd threshold value, then user is made
For excessive risk user.
Alternatively, third party's information is user's biographic information in third-party application；
Predefined option includes following at least one or combination in any: unit, position, expection salary and resume state.
The embodiment of the present invention provides a kind of assessment exceed the time limit the method and apparatus of probability, according to the authorization message of user,
User's third party's information in each third-party application is obtained respectively from multiple third-party application；From each third party's information
Middle extraction predefines the information to be verified that option is corresponding；Using third party's information consistent for information to be verified as third party to be assessed
Information；Impose a condition, then by the information to be verified in third party's information to be assessed if the quantity of third party's information to be assessed meets
As effective information；Effective information being inputted assessment models of exceeding the time limit, obtains the probability score that exceeds the time limit of user, assessment models of exceeding the time limit is
Third party's information according to known users and known users exceed the time limit what result training obtained.By from many in the embodiment of the present invention
Individual third-party application obtains in user's third party's information in each third-party application rather than prior art according to client
The information such as the unit provided and position, on the one hand ensure that the real-time update to customer information, on the other hand it also avoid a lot
Deceptive information；The information to be verified that predefined option is corresponding is extracted from each third party's information, each to be tested by extract
Third party's information to be assessed that card information is consistent meet impose a condition as effective information, by the way can be according to commenting
Estimate and need to set imposing a condition of predefined option and effective information, it is ensured that the assessment probability score that exceeds the time limit is more reasonable.The present invention is real
Execute example by obtaining the information to be verified of predefined option from third-party application, select effective information defeated according to imposing a condition
Enter and obtain, in assessment models of exceeding the time limit, the probability score that exceeds the time limit, may be implemented in the real-time assessment during loan, effectively obtain loan
The information of person.
Accompanying drawing explanation
For the technical scheme being illustrated more clearly that in the embodiment of the present invention, in embodiment being described below required for make
Accompanying drawing briefly introduce.
Fig. 1 is to embodiments provide a kind of assessment to exceed the time limit the method flow schematic diagram of probability；
Fig. 2 exceeds the time limit for a kind of assessment that the embodiment of the present invention provides the apparatus structure schematic diagram of probability.
Detailed description of the invention
In order to make the purpose of the present invention, technical scheme and beneficial effect clearer, below in conjunction with accompanying drawing and enforcement
Example, is further elaborated to the present invention.Should be appreciated that specific embodiment described herein is only in order to explain this
Bright, it is not intended to limit the present invention.
A kind of assessment that Fig. 1 illustrates the embodiment of the present invention and provides exceeds the time limit the method flow schematic diagram of probability, as
Shown in Fig. 1, comprise the following steps:
Step 101: according to the authorization message of user, obtains user respectively each third party from multiple third-party application
Third party's information in application；
Step 102: extract the information to be verified that predefined option is corresponding from each third party's information；
Step 103: using third party's information consistent for information to be verified as third party's information to be assessed；
Step 104: impose a condition, then by third party's information to be assessed if the quantity of third party's information to be assessed meets
Information to be verified is as effective information；
Step 105: assessment models of effective information input being exceeded the time limit, obtains the probability score that exceeds the time limit of user, and exceed the time limit assessment mould
Type is that the result training that exceeds the time limit of the third party's information according to known users and known users obtains.
In being embodied as, according to the authorization message of user, can join with the single major key information of user or major key information
The form closing single major key information obtains user often by multiple third-party application interfaces or third-party application reptile mode
Third party's information in individual third-party application.Wherein, single major key information can be the identification card number of user, cell-phone number, mailbox,
Any one information or multinomial combined information in single major key information can be used；Major key information can be user name,
Sex, the major key information such as name, sex needs to coordinate single major key information to use.Multiple third-party application can be multiple recruitment
Website, such as intelligence connection recruitment, future is carefree, recruitment of going to market, hunt and engage net, China HR etc.；Third party's letter in third-party application
Breath can be resume.
In the embodiment of the present invention, for example, it can be set to 5 third-party application: intelligence connection recruitment, future is carefree, recruitment of going to market,
Hunting and engage net, China HR, third party's information that 5 third-party application are corresponding is respectively resume 1, resume 2, individual
Resume 3, resume 4, resume 5.
According to the authorization message of user, from multiple third-party application, obtain user respectively in each third-party application
Third party's information, alternatively, according to the authorization message of user, obtains user respectively each 3rd from multiple third-party application
Third party's information in Fang Yingyong, multiple third-party application once monitor the third party's information that occurs in that, i.e. acquisition and occur in many
Third party's information in individual third-party application, it is also possible to periodically obtain third party's information, the most respectively should from multiple third parties
The user of acquisition in each month third party's information in each third-party application in.
The information to be verified that predefined option is corresponding is extracted from each third party's information.Specifically, predefined option
Unit, position, expection salary, resume state can be included.
It is to say, from resume extract unit, position, expection salary, resume state information as individual letter
The predefined option gone through and using information corresponding for this predefined option as information to be verified.
Table 1: show and obtain corresponding to be verified of predefined option according to the third party's information in each third-party application
The example of information
Using third party's information consistent for information to be verified as third party's information to be assessed.Specifically, if at each
On recruitment website, at least one information in corresponding information to be verified is consistent, then can be using this information as to be assessed
Third party's information.Such as, the unit 1 in intelligence connection recruitment, unit 2 on future is carefree, the unit 3 gone to market in recruitment,
Hunt engage online unit 4, the information of unit 5 in China HR is all consistent, then can be by information to be verified
Unit as third party's information to be assessed；Can also be that each information to be verified on each third-party application is consistent
Time, using information to be verified as third party's information to be assessed, as unit, position, expection salary, resume state information at five
Third-party application is the most consistent.In being embodied as, input the factor in assessment models of exceeding the time limit the fewest, it is meant that the effective information of user
The fewest, this user there may be deceptive information, thus the probability that exceeds the time limit of user is the highest.
Impose a condition, then by the letter to be verified in third party's information to be assessed if the quantity of third party's information to be assessed meets
Breath is as effective information.Specifically, impose a condition if the quantity of third party's information to be assessed meets, then by consistent to be tested
Card information is as effective information.
Effective information is inputted assessment models of exceeding the time limit, obtains the probability score that exceeds the time limit of user, according to assessment models of exceeding the time limit
Third party's information of known users and known users exceed the time limit what result training obtained.Specifically, by the unit of effective information,
Position, expection salary, resume state carry out model training respectively, can obtain unit, position, expection salary, letter after training
The each self-corresponding mark of state of going through, then is input to exceed by unit, position, expection salary, each self-corresponding mark of resume state
Phase assessment models, will obtain the probability score that exceeds the time limit of user.If job information is inconsistent in each third-party application, then duty
Position mark corresponding to information could be arranged to zero.
By said method, respectively to multiple third-party application obtain user third party in each third-party application
Information is comprehensively assessed, and obtains the probability score that exceeds the time limit of user, and lending agency can be made to comment according to the probability that exceeds the time limit of user
Point judge the risk index that exceeds the time limit of this user, for the risk index that exceeds the time limit high can take measures further control its possibility
The default risk produced, it is ensured that the safety of loan, therefore, it is possible to effectively reduce the situation of promise breaking.
Alternatively, impose a condition, then by third party's information to be assessed if the quantity of third party's information to be assessed meets
Information to be verified as effective information, including: whether judge the quantity of the quantity of third party's information to be assessed and third-party application
Equal；If equal, the information to be verified in third party's information the most to be assessed is as effective information.
In being embodied as, in order to whether more clearly introduce the information to be verified judged in third party's information to be assessed for having
Effect information, is introduced in the embodiment of the present invention as a example by the content shown in table 1:
Third party's information to be assessed in any two third-party application in multiple third-party application is compared, will
In a set that what comparative result was consistent be put into, compare if any five third party's information of abcde, sequentially to ab, ac, ad,
Ae compares, if ab with ac is consistent, is then put into by abc in the first set, d and e is respectively put into the second set with
3rd set；Then the information in other set in addition to the first set is compared, as compared by de, if de is consistent, then
De is combined into a set.Specifically, third party's information to be assessed of any two recruitment website is compared, through than
After relatively, such as in intelligence connection recruitment, hunt that to engage the third party's information to be assessed in net, China HR be consistent, then this is treated
Assessment third party's information is put in set 1, and third party's information to be assessed carefree in future, that go to market in recruitment is consistent, then
This third party's information to be assessed being put in set 2, the quantity that then can be obtained by third party's information to be assessed is i.e. gathered in 1
The quantity of third party's information to be assessed, if the quantity of third party's information to be assessed meets the condition of setting, then by be evaluated
Estimate the information to be verified in third party's information as effective information.
Alternatively, impose a condition, then by third party's information to be assessed if the quantity of third party's information to be assessed meets
Information to be verified, as effective information, comprises determining that final updating time third party to be assessed in the first preset time period
The quantity of information；If the quantity of third party's information to be assessed that the final updating time is in the first preset time period should with third party
The ratio of quantity exceed first threshold, then by final updating time third party to be assessed letter in the first preset time period
The information to be verified of breath is as effective information.
Determine the most respectively intelligence connection recruitment, future is carefree, recruitment of going to market, hunt engage net, China HR's final updating time
Between the quantity of resume to be assessed in the first preset time period be 3, be respectively carefree in intelligence connection recruitment, future, in
The final updating time of the resume to be assessed that a China outstanding person is online, then the final updating time existed in the first preset time period
The quantity of the resume to be assessed in the first preset time period is 3 and exceedes with the ratio that quantity is 5 of recruitment website
First threshold, therefore, in intelligence connection recruitment, future is carefree, the information to be verified of resume to be assessed in China HR is
Effective information.Wherein, the first preset time period can be one month, and first threshold can be more than or equal to 1/2nd.
Alternatively, impose a condition, then by third party's information to be assessed if the quantity of third party's information to be assessed meets
Information to be verified, as effective information, comprises determining that each third party's information to be assessed is operated in the second preset time period
Number of times；If it is super with the ratio of the quantity of third-party application that number of operations exceedes the quantity of third party's information to be assessed of set point number
Cross Second Threshold, then number of operations is exceeded the information to be verified of third party's information to be assessed of set point number as effectively letter
Breath.
Determine the most respectively intelligence connection recruitment, future is carefree, recruitment of going to market, hunt engage in net, China HR pre-second
If the number of times that the resume to be assessed in the time period is operated is respectively 20 times, 30 times, 8 times, 25 times, 11 times, it is then determined that
In intelligence connection recruitment, future is carefree, recruitment of going to market, hunt the number of times engaging the resume to be assessed in net, China HR to be operated
The quantity of the resume to be assessed exceeding set point number is 4, be respectively in intelligence connection recruitment, future is carefree, hunt and engage net, China
The number of times that the online resume to be assessed of an outstanding person is operated exceedes set point number, then number of operations exceedes treating of set point number
The quantity of assessment resume is 4 and has exceeded Second Threshold, therefore, in intelligence with the ratio that quantity is 5 of third-party application
Connection recruitment, future is carefree, hunt and engage in net, China HR the information to be verified of resume to be assessed as effective information.Its
In, the second preset time period can be two weeks, and it can be the resume behaviour that is queried and is downloaded that resume is operated
Making, set point number can be 10 times, and Second Threshold can be equal with first threshold.
In above-described embodiment, by predefined corresponding the treating of option can be extracted from each third party's information with upper type
Checking information, third party's information to be assessed consistent for the information each to be verified extracted is met impose a condition as effective
Information, therefore, it is possible to correctly judge whether the resume of user is effective information, wherein it is possible to set according to assessment needs
Surely imposing a condition of option and effective information is predefined.When obtaining the resume of user and being effective information, then according to single
The number of times classification that number of times that position, position, expection salary, resume state, resume are queried, resume are downloaded is saved in memory module
In, can be as the input source of next part, it is ensured that the assessment probability score that exceeds the time limit is more reasonable.
Alternatively, assessment models that effective information input is exceeded the time limit, obtain the probability score that exceeds the time limit of user, method includes: will
Number of times that effective information, third party's information to be assessed are queried and the number of times that third party's information to be assessed is downloaded are input to exceed the time limit
Assessment models, obtains the probability score that exceeds the time limit of user.
In being embodied as, user included unit, position, expection salary, the effective information of resume state, to be assessed
Number of times that tripartite's information is queried and the number of times that third party's information to be assessed is downloaded are input to assessment models of exceeding the time limit, and obtain user
The probability score that exceeds the time limit.Wherein, third party's information to be assessed be include unit, position, expection salary, resume state to be verified
The resume that information is consistent.
The number of times being queried for the unit in effective information, position, resume state and resume and the number of times of download are made
Description below:
Unit: giving a mark according to factors such as type, scale, industries, company is the biggest, such as listed company, 500 tops of the world public affairs
Department, unit is the most stable, and such as government bodies, public institution, the scoring that exceeds the time limit is the lowest；
Position: giving a mark according to height, position is the highest, the scoring that exceeds the time limit is the lowest；
Expection salary: general user will not reveal the salary of existing company in resume, so its income can be by pre-
Phase salary judges, basic expection salary is the highest, and the scoring that exceeds the time limit is the lowest；
Resume state: typically at least have three kinds of states: be look for work, prepare to look for a chance or opportunity, the most do not prepare to jump
Groove, represents stability indicator and the job-hopping wish of work at present, respectively if user is chronically at job search state, then
The unemployment risk of this user can strengthen, and the scoring that exceeds the time limit is the highest；
The number of times that resume is queried: industry that this user of basic representation is engaged in and the position popular degree in market, if
The number of times being queried is a lot, illustrates that the occupation of this user is relatively popular in market, and the scoring that exceeds the time limit is the lowest；
The number of times that resume is downloaded: whether the passing experience of this user of basic representation and self-ability meet employing unit
Basic demand, the number of times that resume is downloaded is the most, illustrates that the overall qualities of this user are higher, and the scoring that exceeds the time limit is the lowest.
In order to more clearly describe the probability score that exceeds the time limit obtaining user, make to illustrate.The unit of such as user is
Listed company, position is software engineer, it is contemplated that salary is 15k, and resume state is not for the most preparing job-hopping, and resume is queried
Number of times is 30 times, and the number of times that resume is downloaded is 25 times.Each item is given a mark by the information according to user, each of which item
Mark all obtains through the probabilistic model training that exceeds the time limit, and after training, unit is that the mark that listed company beats is
20 points, position be the mark that software engineer makes be 30 scores, it is contemplated that salary be the mark that 15k makes be 15 scores, resume state is
It is near that not prepare the mark that job-hopping makes be 10 scores, the number of times that resume is queried be the mark made for 30 times be 12 scores, resume is downloaded
Number of times be the mark made for 25 times be 11 scores.Can the probability score that exceed the time limit of this user it be 98 points through statistical computation.Wherein, at tool
During body is implemented, model, after one section is put into practice, can be adjusted, particularly as being the people passed judgment on during this period of time and they are last
The original data set of addition that the most really exceeds the time limit carries out re-training, and after training, model there may be change.Model is repaiied
After changing, front and back, the scoring in model is likely to change same person, and this belongs to normal.
Alternatively, assessment models of effective information input being exceeded the time limit, after obtaining the probability score that exceeds the time limit of user, method is also wrapped
Include:
If the probability score that exceeds the time limit of user is higher than the mark set, then using user as excessive risk user；Or
If the probability score that exceeds the time limit of user exceedes the probability score that exceeds the time limit last time of user reaches the 3rd threshold value, then user is made
For excessive risk user.
In being embodied as, the mark of setting can set according to concrete business, and the mark such as set is as 400 points；
3rd threshold value can be determined according to specific circumstances, is such as certain ratio, is specifically as follows 1/2nd.
If being 98 points through calculating the probability score that exceeds the time limit of this user, it is not above the mark 400 points set, then should
User is not as excessive risk user.If being 420 points through calculating the probability score that exceeds the time limit of this user, higher than the mark set
400 divide, then this user is as excessive risk user.
If the probability score that exceeds the time limit of user exceedes last time, expected probability scoring reaches 1/2nd, then this user's conduct
Excessive risk user；If the probability score that exceeds the time limit of user exceedes last time, expected probability scoring is not reaching to 1/2nd, then should
User is not as excessive risk user.
The probability score that exceeds the time limit according to user judges the risk index that exceeds the time limit of user, according to the height of the risk index that exceeds the time limit
Can take measures to control possible default risk further, thus the safety of loan on guarantee.
Alternatively, third party's information is user's biographic information in third-party application；
Predefined option includes following at least one or combination in any: unit, position, expection salary and resume state.
Can be seen that in the embodiment of the present invention method and apparatus providing a kind of assessment to exceed the time limit probability from the discussion above, according to
The authorization message of user, obtains user's third party's information in each third-party application respectively from multiple third-party application；
The information to be verified that predefined option is corresponding is extracted from each third party's information；By third party's information consistent for information to be verified
As third party's information to be assessed；Impose a condition if the quantity of third party's information to be assessed meets, then third party to be assessed is believed
Information to be verified in breath is as effective information；Effective information is inputted assessment models of exceeding the time limit, and the probability that exceeds the time limit obtaining user is commented
Point, assessment models of exceeding the time limit is that the result training that exceeds the time limit of the third party's information according to known users and known users obtains.Pass through
Basis in user's third party's information in each third-party application rather than prior art is obtained from multiple third-party application
The information such as the unit of client's offer and position, on the one hand ensure that the real-time update to customer information, on the other hand it also avoid
A lot of deceptive information；The information to be verified that predefined option is corresponding is extracted from each third party's information, each by extract
Third party's information to be assessed that information to be verified is consistent meet impose a condition as effective information, by the way can root
Need to set imposing a condition of predefined option and effective information according to assessment, it is ensured that the assessment probability score that exceeds the time limit is more reasonable.This
Bright embodiment, by obtaining the information to be verified of predefined option from third-party application, selects effective information according to imposing a condition
And the assessment models that is input to exceed the time limit obtains the probability score that exceeds the time limit, on the one hand, may be implemented in the real-time assessment during loan, have
Effect obtains the information of money-lender.On the other hand, judge the risk index that exceeds the time limit of this user according to the probability score that exceeds the time limit of user, right
Can take measures further to control its issuable default risk in the user that the risk index that exceeds the time limit is high, it is ensured that loan
Safety such that it is able to effectively reduce the situation of promise breaking.
A kind of assessment that Fig. 2 illustrates the embodiment of the present invention and provides exceeds the time limit the apparatus structure schematic diagram of probability.
Based on same idea, a kind of assessment that the embodiment of the present invention provides exceeds the time limit the device of probability, as in figure 2 it is shown, this dress
Put and include acquiring unit 201, screening unit 202, determine unit 203 and output unit 204.Wherein:
Acquiring unit: for the authorization message according to user, obtains user respectively each from multiple third-party application
Third party's information in third-party application, extracts the information to be verified that predefined option is corresponding from each third party's information；
Screening unit: be used for third party's information consistent for information to be verified as third party's information to be assessed；
Determine unit: if the quantity being used for third party's information to be assessed meets impose a condition, then third party to be assessed believed
Information to be verified in breath is as effective information；
Output unit: for assessment models that effective information input is exceeded the time limit, obtain the probability score that exceeds the time limit of user, exceed the time limit and comment
Estimate the result training that exceeds the time limit that model is the third party's information according to known users and known users to obtain.
Optionally it is determined that unit specifically for:
Judge that the quantity of third party's information to be assessed is the most equal with the quantity of third-party application；
If equal, the information to be verified in third party's information the most to be assessed is as effective information.
Optionally it is determined that unit specifically for:
Determine the quantity of final updating time third party's information to be assessed in the first preset time period；
If the quantity of third party's information to be assessed that the final updating time is in the first preset time period and third-party application
The ratio of quantity exceed first threshold, by final updating time third party's information to be assessed in the first preset time period
Information to be verified is as effective information.
Optionally it is determined that unit specifically for:
Determine each third party's information to be assessed in the second preset time period by number of operations；
If number of operations exceedes the quantity of third party's information to be assessed of set point number and the ratio of the quantity of third-party application
Example exceedes Second Threshold, then number of operations exceedes the information to be verified of third party's information to be assessed of set point number as effectively
Information.
Alternatively, output unit specifically for:
The number of times that number of times effective information, third party's information to be assessed being queried and third party's information to be assessed are downloaded
It is input to assessment models of exceeding the time limit, obtains the probability score that exceeds the time limit of user.
Optionally it is determined that unit is additionally operable to:
If the probability score that exceeds the time limit of user is higher than the mark set, then using user as excessive risk user；Or
If the probability score that exceeds the time limit of user exceedes the probability score that exceeds the time limit last time of user when reaching three threshold values, then by user
As excessive risk user.
Alternatively, third party's information is user's biographic information in third-party application；
Predefined option includes following at least one or combination in any: unit, position, expection salary and resume state.
Can be seen that in the embodiment of the present invention method and apparatus providing a kind of assessment to exceed the time limit probability from the discussion above, according to
The authorization message of user, obtains user's third party's information in each third-party application respectively from multiple third-party application；
The information to be verified that predefined option is corresponding is extracted from each third party's information；By third party's information consistent for information to be verified
As third party's information to be assessed；Impose a condition if the quantity of third party's information to be assessed meets, then third party to be assessed is believed
Information to be verified in breath is as effective information；Effective information is inputted assessment models of exceeding the time limit, and the probability that exceeds the time limit obtaining user is commented
Point, assessment models of exceeding the time limit is that the result training that exceeds the time limit of the third party's information according to known users and known users obtains.This
In bright embodiment by obtain from multiple third-party application user's third party's information in each third-party application rather than
The information such as the unit provided according to client in prior art and position, on the one hand ensure that the real-time update to customer information, separately
On the one hand it also avoid a lot of deceptive information；The information to be verified that predefined option is corresponding is extracted from each third party's information,
Third party's information to be assessed consistent for the information each to be verified extracted is met impose a condition as effective information, pass through
Aforesaid way can need to set imposing a condition of predefined option and effective information according to assessment, it is ensured that the assessment probability that exceeds the time limit is commented
It is more reasonable to divide.The embodiment of the present invention is by obtaining the information to be verified of predefined option from third-party application, according to setting bar
Part is selected effective information being input to and is exceeded the time limit and obtain the probability score that exceeds the time limit in assessment models, and may be implemented in during loan is real-time
Assessment, effectively obtains the information of money-lender.
Those skilled in the art are it should be appreciated that embodiments of the invention can be provided as method or computer program.
Therefore, the embodiment in terms of the present invention can use complete hardware embodiment, complete software implementation or combine software and hardware
Form.And, the present invention can use can be with depositing at one or more computers wherein including computer usable program code
The shape of the upper computer program implemented of storage media (including but not limited to disk memory, CD-ROM, optical memory etc.)
Formula.
The present invention is with reference to method, equipment (system) and the flow process of computer program according to embodiments of the present invention
Figure and/or block diagram describe.It should be understood that can the most first-class by computer program instructions flowchart and/or block diagram
Flow process in journey and/or square frame and flow chart and/or block diagram and/or the combination of square frame.These computer programs can be provided
Instruction arrives the processor of general purpose computer, special-purpose computer, Embedded Processor or other programmable data processing device to produce
A raw machine so that the instruction performed by the processor of computer or other programmable data processing device is produced for real
The device of the function specified in one flow process of flow chart or multiple flow process and/or one square frame of block diagram or multiple square frame now.
These computer program instructions may be alternatively stored in and computer or other programmable data processing device can be guided with spy
Determine in the computer-readable memory that mode works so that the instruction being stored in this computer-readable memory produces and includes referring to
Make the manufacture of device, this command device realize at one flow process of flow chart or multiple flow process and/or one square frame of block diagram or
The function specified in multiple square frames.
These computer program instructions also can be loaded in computer or other programmable data processing device so that at meter
Perform sequence of operations step on calculation machine or other programmable devices to produce computer implemented process, thus at computer or
The instruction performed on other programmable devices provides for realizing at one flow process of flow chart or multiple flow process and/or block diagram one
The step of the function specified in individual square frame or multiple square frame.
Although preferred embodiments of the present invention have been described, but those skilled in the art once know basic creation
Property concept, then can make other change and amendment to these embodiments.So, claims are intended to be construed to include excellent
Select embodiment and fall into all changes and the amendment of the scope of the invention.
Obviously, those skilled in the art can carry out various change and the modification essence without deviating from the present invention to the present invention
God and scope.So, if these amendments of the present invention and modification belong to the scope of the claims in the present invention and equivalent technologies thereof
Within, then the present invention is also intended to comprise these change and modification.
Claims (14)
1. an assessment exceeds the time limit the method for probability, it is characterised in that described method includes:
According to the authorization message of user, from multiple third-party application, obtain described user respectively in each third-party application
Third party's information；
The information to be verified that predefined option is corresponding is extracted from each third party's information；
Using third party's information consistent for described information to be verified as third party's information to be assessed；
Impose a condition if the quantity of described third party's information to be assessed meets, then to be tested by described third party's information to be assessed
Card information is as effective information；
The input of described effective information is exceeded the time limit assessment models, obtains the probability score that exceeds the time limit of described user, described in exceed the time limit assessment mould
Type is that the result training that exceeds the time limit of the third party's information according to known users and described known users obtains.
2. the method for claim 1, it is characterised in that if the quantity of described third party's information to be assessed meets sets bar
Part, then using the information to be verified in described third party's information to be assessed as effective information, including:
Judge that the quantity of described third party's information to be assessed is the most equal with the quantity of described third-party application；
If equal, the information to be verified in the most described third party's information to be assessed is as effective information.
3. the method for claim 1, it is characterised in that if the quantity of described third party's information to be assessed meets sets bar
Part, then using the information to be verified in described third party's information to be assessed as effective information, including:
Determine the quantity of final updating time third party's information to be assessed in the first preset time period；
If the quantity of third party's information to be assessed that the described final updating time is in the first preset time period and described third party
The ratio of quantity of application exceedes first threshold, then by the described final updating time in the first preset time period to be assessed the
The information to be verified of tripartite's information is as described effective information.
4. the method for claim 1, it is characterised in that if the quantity of described third party's information to be assessed meets sets bar
Part, then using the information to be verified in described third party's information to be assessed as effective information, including:
Determine each third party's information to be assessed in the second preset time period by number of operations；
If number of operations exceedes the quantity of third party's information to be assessed of set point number and the ratio of the quantity of described third-party application
Example exceedes Second Threshold, then described number of operations is exceeded set point number third party's information to be assessed information to be verified as
Described effective information.
5. the method as described in any one of Claims 1-4, it is characterised in that exceed the time limit assessment mould by the input of described effective information
Type, obtains the probability score that exceeds the time limit of described user, and described method includes:
Number of times that described effective information, described third party's information to be assessed are queried and described third party's information to be assessed by under
The number of times carried exceeds the time limit assessment models described in being input to, and obtains the probability score that exceeds the time limit of described user.
6. method as claimed in claim 5, it is characterised in that assessment models of the input of described effective information being exceeded the time limit, obtains institute
After stating the probability score that exceeds the time limit of user, described method also includes:
If the probability score that exceeds the time limit of described user is higher than the mark set, then using described user as excessive risk user；Or
If the probability score that exceeds the time limit of described user exceedes the probability score that exceeds the time limit last time of described user reaches the 3rd threshold value, then by institute
State user as excessive risk user.
7. the method as described in any one of Claims 1-4, it is characterised in that described third party's information is that described user is
Biographic information in tripartite's application；
Described predefined option includes following at least one or combination in any: unit, position, expection salary and resume state.
8. an assessment exceeds the time limit the device of probability, it is characterised in that described device includes:
Acquiring unit: for the authorization message according to user, obtain described user respectively from multiple third-party application each
Third party's information in third-party application, extracts the information to be verified that predefined option is corresponding from each third party's information；
Screening unit: be used for third party's information consistent for described information to be verified as third party's information to be assessed；
Determine unit: if the quantity being used for described third party's information to be assessed meets impose a condition, then by the described to be assessed 3rd
Information to be verified in side's information is as effective information；
Output unit: for assessment models of the input of described effective information being exceeded the time limit, obtain the probability score that exceeds the time limit of described user, institute
State the result training that exceeds the time limit that assessment models of exceeding the time limit is the third party's information according to known users and described known users to obtain.
9. device as claimed in claim 8, it is characterised in that
Described determine unit, the quantity of quantity Yu described third-party application specifically for judging described third party's information to be assessed
The most equal；
If equal, the information to be verified in the most described third party's information to be assessed is as effective information.
10. device as claimed in claim 8, it is characterised in that
Described determine unit, specifically for determining final updating time third party's information to be assessed in the first preset time period
Quantity；
If the quantity of third party's information to be assessed that the described final updating time is in the first preset time period and described third party
The ratio of quantity of application exceedes first threshold, by the described final updating time in the first preset time period the to be assessed 3rd
The information to be verified of side's information is as described effective information.
11. devices as claimed in claim 8, it is characterised in that
Described determine unit, specifically for determine each third party's information to be assessed in the second preset time period by operation time
Number；
If number of operations exceedes the quantity of third party's information to be assessed of set point number and the ratio of the quantity of described third-party application
Example exceedes Second Threshold, then described number of operations is exceeded set point number third party's information to be assessed information to be verified as
Described effective information.
12. devices as described in any one of claim 8 to 11, it is characterised in that
Described output unit, specifically for the number of times described effective information, described third party's information to be assessed being queried and institute
State the number of times that third party's information to be assessed is downloaded be input to described in exceed the time limit assessment models, the probability that exceeds the time limit obtaining described user is commented
Point.
13. devices as claimed in claim 12, it is characterised in that described determine that unit is additionally operable to: if described user's exceeds the time limit
Probability score is higher than the mark set, then using described user as excessive risk user；Or
If the probability score that exceeds the time limit of described user exceedes the probability score that exceeds the time limit last time of described user when reaching three threshold values, then will
Described user is as excessive risk user.
14. devices as described in any one of claim 8 to 11, it is characterised in that described third party's information is that described user exists
Biographic information in third-party application；
Described predefined option includes following at least one or combination in any: unit, position, expection salary and resume state.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610643696.9A CN106296391A (en) | 2016-08-08 | 2016-08-08 | A kind of assessment exceeds the time limit the method and apparatus of probability |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610643696.9A CN106296391A (en) | 2016-08-08 | 2016-08-08 | A kind of assessment exceeds the time limit the method and apparatus of probability |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106296391A true CN106296391A (en) | 2017-01-04 |
Family
ID=57666845
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610643696.9A Pending CN106296391A (en) | 2016-08-08 | 2016-08-08 | A kind of assessment exceeds the time limit the method and apparatus of probability |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106296391A (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107908740A (en) * | 2017-11-15 | 2018-04-13 | 百度在线网络技术（北京）有限公司 | Information output method and device |
| CN108389125A (en) * | 2018-02-27 | 2018-08-10 | 挖财网络技术有限公司 | The overdue Risk Forecast Method and device of credit applications |
| CN108446925A (en) * | 2018-02-11 | 2018-08-24 | 深圳市快付通金融网络科技服务有限公司 | A kind of trade company's scoring system, terminal and computer readable storage medium |
| CN109117976A (en) * | 2018-06-22 | 2019-01-01 | 重庆小雨点小额贷款有限公司 | A kind of loan loss prediction technique, device, server and storage medium |
| CN109509086A (en) * | 2018-11-28 | 2019-03-22 | 上海点融信息科技有限责任公司 | The method, apparatus and storage medium of processing collection business based on artificial intelligence |
| CN110070430A (en) * | 2019-03-12 | 2019-07-30 | 平安科技（深圳）有限公司 | Assess method and device, the storage medium, electronic equipment of refund risk |
| CN110175109A (en) * | 2019-05-31 | 2019-08-27 | 北京北信源软件股份有限公司 | A kind of determination method, determining device, equipment and the medium of user type |
| CN110197074A (en) * | 2018-04-11 | 2019-09-03 | 腾讯科技（深圳）有限公司 | A kind of user authority control method and device |
| CN110415102A (en) * | 2019-06-28 | 2019-11-05 | 上海上湖信息技术有限公司 | User credit methods of risk assessment and device, computer readable storage medium |
| CN110674491A (en) * | 2019-09-29 | 2020-01-10 | 上海淇玥信息技术有限公司 | Method and device for real-time evidence obtaining of android application and electronic equipment |
| WO2020042290A1 (en) * | 2018-08-28 | 2020-03-05 | 卫盈联信息技术（深圳）有限公司 | Risk management method, and apparatus and computer-readable storage medium |
| CN111127191A (en) * | 2019-12-25 | 2020-05-08 | 北京百度网讯科技有限公司 | Risk assessment method and device |
| CN111583011A (en) * | 2019-02-18 | 2020-08-25 | 北京奇虎科技有限公司 | Data processing method, device, equipment and storage medium |
| CN117035985A (en) * | 2023-07-31 | 2023-11-10 | 浙江孚临科技有限公司 | Trusted overdue risk control method and system |
-
2016
- 2016-08-08 CN CN201610643696.9A patent/CN106296391A/en active Pending
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107908740A (en) * | 2017-11-15 | 2018-04-13 | 百度在线网络技术（北京）有限公司 | Information output method and device |
| CN108446925A (en) * | 2018-02-11 | 2018-08-24 | 深圳市快付通金融网络科技服务有限公司 | A kind of trade company's scoring system, terminal and computer readable storage medium |
| CN108389125A (en) * | 2018-02-27 | 2018-08-10 | 挖财网络技术有限公司 | The overdue Risk Forecast Method and device of credit applications |
| CN110197074B (en) * | 2018-04-11 | 2023-02-28 | 腾讯科技（深圳）有限公司 | User authority control method and device |
| CN110197074A (en) * | 2018-04-11 | 2019-09-03 | 腾讯科技（深圳）有限公司 | A kind of user authority control method and device |
| CN109117976A (en) * | 2018-06-22 | 2019-01-01 | 重庆小雨点小额贷款有限公司 | A kind of loan loss prediction technique, device, server and storage medium |
| CN109117976B (en) * | 2018-06-22 | 2021-05-11 | 重庆小雨点小额贷款有限公司 | Loan loss prediction method, loan loss prediction device, loan loss server and storage medium |
| WO2020042290A1 (en) * | 2018-08-28 | 2020-03-05 | 卫盈联信息技术（深圳）有限公司 | Risk management method, and apparatus and computer-readable storage medium |
| CN109509086A (en) * | 2018-11-28 | 2019-03-22 | 上海点融信息科技有限责任公司 | The method, apparatus and storage medium of processing collection business based on artificial intelligence |
| CN111583011A (en) * | 2019-02-18 | 2020-08-25 | 北京奇虎科技有限公司 | Data processing method, device, equipment and storage medium |
| CN110070430A (en) * | 2019-03-12 | 2019-07-30 | 平安科技（深圳）有限公司 | Assess method and device, the storage medium, electronic equipment of refund risk |
| CN110175109A (en) * | 2019-05-31 | 2019-08-27 | 北京北信源软件股份有限公司 | A kind of determination method, determining device, equipment and the medium of user type |
| CN110415102A (en) * | 2019-06-28 | 2019-11-05 | 上海上湖信息技术有限公司 | User credit methods of risk assessment and device, computer readable storage medium |
| CN110674491A (en) * | 2019-09-29 | 2020-01-10 | 上海淇玥信息技术有限公司 | Method and device for real-time evidence obtaining of android application and electronic equipment |
| CN110674491B (en) * | 2019-09-29 | 2022-02-01 | 上海淇玥信息技术有限公司 | Method and device for real-time evidence obtaining of android application and electronic equipment |
| CN111127191A (en) * | 2019-12-25 | 2020-05-08 | 北京百度网讯科技有限公司 | Risk assessment method and device |
| CN117035985A (en) * | 2023-07-31 | 2023-11-10 | 浙江孚临科技有限公司 | Trusted overdue risk control method and system |
| CN117035985B (en) * | 2023-07-31 | 2024-04-23 | 浙江孚临科技有限公司 | Trusted overdue risk control method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106296391A (en) | A kind of assessment exceeds the time limit the method and apparatus of probability | |
| CN107316198B (en) | Account risk identification method and device | |
| WO2021147486A1 (en) | Data processing method and apparatus | |
| Kadri | Arab development denied: Dynamics of accumulation by wars of encroachment | |
| Serageldin | Sustainability as opportunity and the problem of social capital | |
| Kutlay | The politics of state capitalism in a post-liberal international order: The case of Turkey | |
| CN108665159A (en) | A kind of methods of risk assessment, device, terminal device and storage medium | |
| CN107767263A (en) | A kind of measures and procedures for the examination and approval of consumptive credit, device and server | |
| Ebaidalla et al. | Performance of Intra‐COMESA trade integration: A comparative study with ASEAN's trade integration | |
| US10567374B2 (en) | Information processing method and server | |
| CN112418274A (en) | Decision tree generation method and device | |
| CN110675017A (en) | Performance evaluation method and device based on artificial intelligence | |
| CN107292785A (en) | One kind is set a question method and system | |
| CN110276621A (en) | Data card is counter to cheat recognition methods, electronic device and readable storage medium storing program for executing | |
| CN106534228A (en) | Information processing method, client and server | |
| Moccia et al. | Fintech strategy: e-reputation | |
| CN111950625A (en) | Risk identification method and device based on artificial intelligence, computer equipment and medium | |
| CN111611786B (en) | Text similarity calculation method and device | |
| CN109614496B (en) | Low security identification method based on knowledge graph | |
| CN114398685A (en) | Government affair data processing method and device, computer equipment and storage medium | |
| CN112488163A (en) | Abnormal account identification method and device, computer equipment and storage medium | |
| DE102014116982A1 (en) | Self-aware token | |
| CN115545088B (en) | Model construction method, classification method, device and electronic equipment | |
| CN107305662A (en) | Recognize the method and device of violation account | |
| CN110245985A (en) | A kind of information processing method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170104 |
|
| RJ01 | Rejection of invention patent application after publication |