Credit evaluation index processing method and device
Technical field
This specification embodiment be related to Internet technical field more particularly to a kind of credit evaluation index processing method and
Device.
Background technique
Personal credit refers to the letter that natural person (and its family) is supplied to based on trust, by certain agreement or contract
With so that the individual for receiving credit, which does not have to pay in cash, is obtained with commodity or service, it not only includes disappearing as personal or family
The transaction with credit on expense way also includes the credit as personal investment, foundation and production and operation.Personal credit scoring refers to letter
Quantization point is carried out to the personal credit of user using various data, complicated algorithm model and business rule with appraisal agency
The personal credit of user is stated in analysis in the form of score value.How to improve the credit score of user is each user's concern.
Summary of the invention
The offer of this specification embodiment and a kind of credit evaluation index processing method and device.
In a first aspect, this specification embodiment provides a kind of credit evaluation index processing method, comprising:
All interpretable indexs are extracted from all credit evaluation indexs of target user;
The corresponding Ranking Information of each interpretable index is obtained respectively, and the Ranking Information is for characterizing the same institute
State the current credit data of the target user under interpretable index present position, institute in the current credit data of all users
Stating all users is the credit consuming group where the target user;
According to the corresponding Ranking Information of each interpretable index, from all interpretable indexs of the target user
Extract more than one target indicator;
The prompt information for prompting the target user to promote credit score, the prompt are sent to the target user
Information includes the target indicator.
Second aspect, this specification embodiment provide a kind of credit evaluation index processing unit, comprising:
First extraction module, for extracting all interpretable indexs from all credit evaluation indexs of target user;
Ranking Information obtains module, for obtaining the corresponding Ranking Information of each interpretable index, the row respectively
Position information is used to characterize current credit data the working as in all users of the target user under the same interpretable index
Present position in preceding credit data, all users are the credit consuming group where the target user;
Second extraction module, for according to the corresponding Ranking Information of each interpretable index, from the target user
All interpretable indexs in extract more than one target indicator;
Sending module, for sending the prompt for prompting the target user to promote credit score to the target user
Information, the prompt information include the target indicator.
The third aspect, this specification embodiment provide a kind of server, including memory, processor and are stored in described
On memory and the computer program that can run on the processor, the processor are realized when executing the computer program
The step of above-mentioned credit evaluation index processing method.
Fourth aspect, this specification embodiment provide a kind of computer readable storage medium, are stored thereon with computer journey
The step of sequence, the computer program realizes above-mentioned credit evaluation index processing method when being executed by the processor.
This specification embodiment has the beneficial effect that:
In this specification embodiment, the corresponding Ranking Information of index can be explained according to each of target user, from the mesh
It marks in all interpretable indexs of user and extracts more than one target indicator.Since the corresponding ranking letter of index can be explained in some
Breath characterizes the current credit data that the target user under index can be explained institute in the current credit data of all users
Locate position, represents the current credit number that this can be explained to the current credit data of the target user and other users under index
According to comparing as a result, the i.e. described target indicator is using other users as with reference to determining, the institute under the target indicator
The current credit data for stating target user can will wrap compared with the current credit data of certain customers with fast lifting, therefore
The prompt information for including the target indicator is sent to the target user, and the target user can be allowed to understand credit evaluation reference
Part credit evaluation index, allow the target user to receive new credit evaluation index or ignored credit evaluation refer to
Mark allows the target user to understand the feasible way for promoting personal credit score value, allows the target user according to described
Prompt information promotes the credit score of oneself, to be conducive to that the target user is made to convince credit evaluation as a result, described in reduction
Target user carries out the behavior of inquiry or complaint to credit evaluation system, and then advantageously reduces the additional money of credit evaluation system
Source consumption.
Detailed description of the invention
Fig. 1 is the application scenarios schematic diagram that the credit evaluation index of this specification embodiment is handled;
Fig. 2 is the flow chart of the credit evaluation index processing method of this specification embodiment;
Fig. 3 is the structural schematic diagram of the credit evaluation index processing unit of this specification embodiment;
Fig. 4 is the structural schematic diagram of the credit evaluation index processing server of this specification embodiment.
Specific embodiment
Above-mentioned technical proposal in order to better understand, below by attached drawing and specific embodiment to this specification embodiment
Technical solution elaborate, it should be understood that the specific features in this specification embodiment and embodiment are to this specification
The detailed description of embodiment technical solution, rather than the restriction to this specification technical solution.In the absence of conflict, this theory
Technical characteristic in bright book embodiment and embodiment can be combined with each other.
Referring to Figure 1, application scenarios schematic diagram is handled for the credit evaluation index of this specification embodiment.Wherein, credit
Assessment system 100 is used for according to each dimension user data, with technologies such as cloud computing and machine learning, by logistic regression,
The model algorithms such as decision tree and random forest carry out integrated treatment and assessment to each dimension user data, go through in user credit
The synthesis of the objective presentation user's credit standing of the dimensions such as history, Behavior preference, contractual capacity, identity speciality and relationship among persons is commented
Point.The credit for each user that the credit evaluation index processing unit 200 is used to be obtained according to the credit evaluation system 100 is commented
Estimate index, obtained from all credit evaluation indexs of target user can fast lifting credit score index, allow the target to use
Family understands the feasible way for promoting personal credit score value, and the target user is allow to promote oneself according to the prompt information
Credit score.
In a first aspect, this specification embodiment provides a kind of credit evaluation index processing method.Fig. 2 is the credit evaluation
The flow chart of index processing method, the credit evaluation index processing method include step S201 to step S204.
S201 extracts all interpretable indexs from all credit evaluation indexs of target user.
The credit evaluation index is the audit data of each small label in credit evaluation, spy usually relevant to credit
Sign.The each credit evaluation index of user can reflect the local credit standing of user, the current letter of user from certain angle respectively
It is then to be obtained according to the current credit score of each credit evaluation index of user for characterizing user's entirety letter of credit with score value
The characterization value of condition.Generally, the current credit score of user is higher, indicates that the current credit of user is better.The credit evaluation
Index specifically can be feature relevant to user identity, such as schooling, occupation, work unit, native place, residence, money
Occurrence condition, social networks, contractual capacity, identity speciality etc.;The credit evaluation index is specifically also possible to and user behavior phase
Feature of pass, such as refund history, the condition of consumption, Behavior preference etc..All credit evaluation indexs can be divided into interpretable index and
It can not explain that index two major classes, the interpretable index are that can be easily absorbed on a cognitive level by the user, user can be promoted certainly according to such index
Oneself credit score is the credit evaluation index for capableing of transparent transmission;On the contrary, described can not explain index as that cannot be managed by user
Solution, user cannot promote the credit score of oneself according to such index, be can not transparent transmission credit evaluation index.
The target user is the lower user of current credit score, and current credit score is lower than credit full marks with per family
It can be used as the target user.The credit evaluation system 100, can basis when assessing the current credit score of each user
The corresponding index value of each each credit evaluation index of user, according to certain evaluation criteria to each credit evaluation of each user
Index is given a mark, and the current credit score of each credit evaluation index of each user is obtained, then each according to each user
The corresponding current credit score for calculating each user of the current credit score of credit evaluation index.It therefore, can be from the credit
In all evaluation indexes for the target user that assessment system 100 obtains, all interpretable fingers of the target user are extracted
Mark.It gives a mark, can be realized using existing scoring model to each credit evaluation index of each user;Calculate each user
Current credit score, can be the algebraical sum for calculating the current credit score of each each credit evaluation index of user, can also
To be the weighted sum for calculating the current credit score of each each credit evaluation index of user.It should be noted that each use
The current credit score of each user is given a mark and calculated to each credit evaluation index in family, however it is not limited to it is above-mentioned enumerate it is several
Kind implementation, this specification embodiment is to this without limiting.
S202, obtains the corresponding Ranking Information of each interpretable index respectively, and the Ranking Information is same for characterizing
The current credit data of the target user is locating in the current credit data of all users under one interpretable index
Position, all users are the credit consuming group where the target user.
According to the difference of credit application scenarios, such as credit card, the consumer finance, financing lease, hotel, rents a house, goes on a journey, wedding
The credits application scenarios such as love, classification information, student's service and public utilities service, the credit evaluation system 100 will be each
User is referred to different credit consuming groups, generallys use identical letter to each user in the same credit consuming group
Use evaluation index.
In a kind of optional implementation, directly it is ranked up and is obtained by the current credit score to each interpretable index
The corresponding Ranking Information of each interpretable index.Specifically, interpretable to i-th of each user in all users
For the current credit score of index according to being ranked up from small to large, obtaining i-th of the target user can be explained the current of index
The corresponding serial number of credit score, i-th of the target user corresponding serial number of current credit score that index can be explained is institute
Stating i-th of target user can be explained the corresponding Ranking Information of index, and 1≤i≤N and i are integer, and N is all interpretable fingers
Target quantity.As previously mentioned, the credit evaluation system 100, when assessing the current credit score of each user, meeting is according to each
The corresponding index value of a each credit evaluation index of user, refers to each credit evaluation of each user according to certain evaluation criteria
Mark is given a mark, and the current credit score of each credit evaluation index of each user is obtained.It therefore, can be from the credit evaluation
In the current credit score for each credit evaluation index of each user that system 100 obtains, extract each in all users
The current credit score of index can be explained for i-th of user.Further, interpretable to i-th of each user in all users
The current credit score of index can be realized according to being ranked up from small to large using quicksort method.
5 users, all interpretable fingers of target user are shared with the credit consuming group where the target user
It is designated as shared bicycle to give back, for credit card repayment and schooling, obtains shared bicycle respectively and give back corresponding ranking letter
Breath, the corresponding Ranking Information of credit card repayment and the corresponding Ranking Information of schooling.It can if giving back this in shared bicycle
It explains under index, the current credit score of the target user is 20, the current credit score of other 4 users is respectively 22,
30,32 and 18, then shared bicycle is given back the current credit score of this interpretable lower 5 user of index by from small to large into
Row sequence, one group of data of acquisition: 18,20,22,30 and 32, then 20 corresponding serial number " 2 " of score value is that shared bicycle gives back this
The corresponding Ranking Information of one interpretable index.Obtain the corresponding Ranking Information of credit card repayment and the corresponding ranking of schooling
Information, similar with the Ranking Information that shared bicycle is given back is obtained, details are not described herein.
It, can also be by calculating the hundred of the current credit score of each interpretable index in another optional implementation
Quartile obtains the corresponding Ranking Information of each interpretable index.Specifically, to i-th of each user in all users
The current credit score of interpretable index calculates i-th of the target user and interpretable refers to according to being ranked up from small to large
The corresponding percentile of the current credit score of target, the current credit score that index can be explained for i-th of the target user are corresponding
Percentile is that the corresponding Ranking Information of index can be explained for i-th of the target user, 1≤i≤N and i is integer, and N is described
The quantity of all interpretable indexs.Percentile is the popularization of median, by n data by obtaining after being ranked up from small to large
Data be x1、x2、…、xn, for 0≤p < 1, its p quantile is defined as: mp=x([np]+1), when np is not integer;When np is integer.Wherein, [np] is the integer part of np.
5 users are still shared with the credit consuming group where the target user, the target user is all interpretable
Index is that shared bicycle is given back, for credit card repayment and schooling, obtains shared bicycle respectively and gives back corresponding ranking
The corresponding Ranking Information of information, credit card repayment and the corresponding Ranking Information of schooling.If giving back this in shared bicycle
Under interpretable index, the current credit score of the target user is 20, the current credit score of other 4 users is respectively
22,30,32 and 18, then shared bicycle is given back the current credit score of this interpretable lower 5 user of index by from it is small to
It is ranked up greatly, one group of data of acquisition: 18,20,22,30 and 32;Above-mentioned percentile calculation formula is substituted into, the value of n is 5, x1
Value be 18, x2Value be 20, x3Value be 22, x4Value be 30, x5Value be 32, mpValue be 20, due to no adjacent two
The sum of number is 40, thus np is not integer, therefore according to mp=x([np]+1)Calculating and obtaining the value of p is 0.3, then score value 20 is corresponding
Percentage 0.3 is that shared bicycle gives back this interpretable corresponding Ranking Information of index.Obtain the corresponding row of credit card repayment
Position information and the corresponding Ranking Information of schooling, it is similar with the Ranking Information that shared bicycle is given back is obtained, it is no longer superfluous herein
It states.
S203, according to the corresponding Ranking Information of each interpretable index, from all interpretable of the target user
More than one target indicator is extracted in index.
If being directly ranked up by the current credit score to each interpretable index and obtaining each interpretable finger
Corresponding Ranking Information is marked, then extracts the corresponding serial number of current credit score from all interpretable indexs of the target user
Less than the interpretable index of the first preset threshold, first preset threshold is not more than N.First preset threshold can be according to tool
Body situation and set, as long as it can ensure that extract at least one described target indicator from all interpretable indexs,
This specification embodiment is to this without limiting.It, can also be from all of the target user in a kind of optional implementation
The smallest interpretable index of the corresponding serial number of current credit score is extracted in interpretable index.
If obtaining each interpretable index by the percentile for the current credit score for calculating each interpretable index
Corresponding Ranking Information, it is small from all interpretable indexs of the target user to extract the corresponding percentile of current credit score
In the interpretable index of the second preset threshold, second preset threshold is not more than 1.Second preset threshold can be according to specific
Situation and set, as long as it can ensure that extract at least one described target indicator from all interpretable indexs, this
Specification embodiment is to this without limiting.It, can also can from all of the target user in a kind of optional implementation
It explains in index and extracts the smallest interpretable index of the corresponding percentile of current credit score.
Since the corresponding Ranking Information of index can be explained in some, represents and the target user under index is can be explained into this
It is that current credit data and the current credit data of other users compare as a result, thus the target indicator be with other use
Family is as reference determination, the current letter of the current credit data of the target user and certain customers under the target indicator
Being compared with data can be with fast lifting.It is that shared bicycle is given back and the target user shares bicycle and returns with the target indicator
For the locating percentile in all users of current credit score also is 25%, represents the shared bicycle of the target user and give back
Current credit score be lower than 75% other users.
S204, Xiang Suoshu target user send the prompt information for prompting the target user to promote credit score, institute
Stating prompt information includes the target indicator.
In a kind of optional implementation, the prompt information can also include described in addition to including the target indicator
The corresponding percentile of current credit score of target indicator, to the description of the target indicator (such as the tool of the target indicator
Body defines, the current credit score of the target indicator etc.), promote according to the target indicator suggestion and the institute of credit score
Any one or more in the current credit score of target user is stated to combine.Tool of this specification embodiment to the prompt information
The body form of expression without limiting, for example, the prompt information can it is a kind of with text, animation, video, audio, table etc. or
Diversified forms indicate, and can will be described by one or more combinations such as mail, short message, dialog box and instant messaging
Prompt information is sent to the target user.
It is in the prior art usually that target user's credit score will be caused to rise in default historical period (such as one week in the past)
The target user is informed in the behavior fallen, although the target user is realised that the concrete reason for leading to oneself credit ups and downs,
Extended meeting causes the puzzlement of the target user front behavior faithlessness income afterwards.For example, when the target user knows that last month makes
After causing credit score to go up with credit card repayment, rear extended meeting reinforces utilizing the behavior of credit card repayment, but if credit card is also
The bottleneck that the credit that money had arrived at rises point, the target user can not reach letter because of long-term front credit card repayment behavior
Puzzlement is generated with the purpose of promotion.
It is that the mesh is determined according to the corresponding Ranking Information of each interpretable index and in this specification embodiment
Index is marked, since the corresponding Ranking Information of index can be explained in some, characterizes working as the target user under the interpretable index
Preceding credit data present position in the current credit data of all users represents this target use under index can be explained
It is that the current credit data at family and the current credit data of other users compare as a result, the i.e. described target indicator is with other
User is as with reference to determining, and the current credit data of the target user and certain customers' is current under the target indicator
Credit data, which is compared, to be sent to the target with fast lifting, therefore for the prompt information including the target indicator and use
Family can allow the target user to understand the part credit evaluation index of credit evaluation reference, allow the target user to receive new
Credit evaluation index or ignored credit evaluation index, allow the target user understand promote personal credit score value can
Row sexual approach allows the target user to promote the credit score of oneself according to the prompt information, to be conducive to make institute
It states target user and convinces credit evaluation as a result, reducing the row that the target user carries out inquiry or complaint to credit evaluation system
For, and then advantageously reduce the additional resource consumption of credit evaluation system.
Second aspect, based on the same inventive concept, this specification embodiment provide a kind of credit evaluation index processing unit.
Fig. 3 is the structural schematic diagram of the credit evaluation index processing unit, and the credit evaluation index processing unit includes:
First extraction module 301, for extracting all interpretable indexs from all credit evaluation indexs of target user;
Ranking Information obtains module 302, described for obtaining the corresponding Ranking Information of each interpretable index respectively
Ranking Information is used to characterize the current credit data of the target user under the same interpretable index all users'
Present position in current credit data, all users are the credit consuming group where the target user;
Second extraction module 303, for being used from the target according to the corresponding Ranking Information of each interpretable index
More than one target indicator is extracted in all interpretable indexs at family;
Sending module 304, for sending to the target user for prompting the target user to promote credit score
Prompt information, the prompt information include the target indicator.
In a kind of optional implementation, the Ranking Information obtains module 302 and includes:
Sorting module, for being pressed to i-th of each user current credit score that index can be explained in all users
According to being ranked up from small to large, i-th of the target user corresponding serial number of current credit score that index can be explained is obtained, 1
≤ i≤N and i are integer, and N is the quantity of all interpretable indexs.
In a kind of optional implementation, second extraction module is used for all interpretable fingers from the target user
Interpretable index of the corresponding serial number of current credit score less than the first preset threshold is extracted in mark, first preset threshold is not
Greater than N;Or
Second extraction module is for extracting current credit score from all interpretable indexs of the target user
The corresponding the smallest interpretable index of serial number.
In a kind of optional implementation, the prompt information further includes the description to the target indicator, according to
Target indicator promotes any one or more combination in the suggestion of credit score and the current credit score of the target user.
In a kind of optional implementation, the Ranking Information obtains module 302 and includes:
Sorting module, for being pressed to i-th of each user current credit score that index can be explained in all users
According to being ranked up from small to large, 1≤i≤N and i is integer, N is the quantity of all interpretable indexs;
Percentile computing module is corresponded to for calculating the current credit score that i-th of the target user can be explained index
Percentile.
In a kind of optional implementation, second extraction module is used for all interpretable fingers from the target user
Interpretable index of the corresponding percentile of current credit score less than the second preset threshold, second preset threshold are extracted in mark
No more than 1;Or
Second extraction module is for extracting current credit score from all interpretable indexs of the target user
The corresponding the smallest interpretable index of percentile.
In a kind of optional implementation, the prompt information further includes that the current credit score of the target indicator is corresponding
Percentile, promote to the description of the target indicator, according to the target indicator suggestion and the target of credit score
Any one or more in the current credit score of user combines.
The third aspect is based on inventive concept same as credit evaluation index processing method in previous embodiment, the present invention
A kind of server is also provided.With reference to Fig. 4, the server includes memory 404, processor 402 and is stored in the memory
On 404 and the computer program that can be run on the processor 402, when the processor 402 executes the computer program
The step of realizing either credit evaluation index processing method described previously method.
In Fig. 4, bus architecture (is represented) with bus 400, and the bus 400 may include any number of interconnection
Bus and bridge, the bus 400 will include the one or more processors represented by the processor 402 and the memory
The various circuits of 404 memories represented link together.The bus 400 can also will such as peripheral equipment, voltage-stablizer and
Various other circuits of management circuit or the like link together, and these are all it is known in the art, therefore, herein not
It is described further again.Bus interface 405 is provided between the bus 400 and receiver 401 and transmitter 403 and is connect
Mouthful.The receiver 401 and the transmitter 403 can be the same element, i.e. transceiver, provide for over a transmission medium
The unit communicated with various other devices.The processor 402 is responsible for managing the bus 400 and common processing, and described
Memory 404 can be used to store the processor 402 used data when executing operation.
Fourth aspect is based on inventive concept same as credit evaluation index processing method in previous embodiment, the present invention
A kind of computer readable storage medium is also provided, is stored thereon with computer program, the computer program is by the processor
The step of credit evaluation index processing method described previously is realized when execution.
This specification is referring to the method, equipment (system) and computer program product according to this specification embodiment
Flowchart and/or the block diagram describes.It should be understood that can be realized by computer program instructions every in flowchart and/or the block diagram
The combination of process and/or box in one process and/or box and flowchart and/or the block diagram.It can provide these computers
Processor of the program instruction to general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices
To generate a machine, so that generating use by the instruction that computer or the processor of other programmable data processing devices execute
In setting for the function that realization is specified in one or more flows of the flowchart and/or one or more blocks of the block diagram
It is standby.
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 equipment, the commander equipment 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.
Although the preferred embodiment of this specification has been described, once a person skilled in the art knows basic wounds
The property made concept, then additional changes and modifications may be made to these embodiments.So the following claims are intended to be interpreted as includes
Preferred embodiment and all change and modification for falling into this specification range.
Obviously, those skilled in the art can carry out various modification and variations without departing from this specification to this specification
Spirit and scope.In this way, if these modifications and variations of this specification belong to this specification claim and its equivalent skill
Within the scope of art, then this specification is also intended to include these modifications and variations.