CN107944738A - A kind of tax credit score computational methods and device - Google Patents
A kind of tax credit score computational methods and device Download PDFInfo
- Publication number
- CN107944738A CN107944738A CN201711283210.6A CN201711283210A CN107944738A CN 107944738 A CN107944738 A CN 107944738A CN 201711283210 A CN201711283210 A CN 201711283210A CN 107944738 A CN107944738 A CN 107944738A
- Authority
- CN
- China
- Prior art keywords
- index
- evaluation index
- score
- behavior
- credit
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- 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
- G06Q40/10—Tax strategies
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- Finance (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- Educational Administration (AREA)
- Technology Law (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of tax credit score computational methods and device, this method to include：Obtain the tax behavior of credit record data of object to be evaluated；Assessment indicator system model and tax behavior of credit record data based on prebuild, Utilization assessment index temporally decay algorithm, according to evaluation cycle, damped cycle and scoring rule, timing or the index score for calculating each first kind evaluation index for possessing time attenuation characteristic in real time, and according to scoring rule, timing or the index score for calculating non-first kind evaluation index in real time；By radix point-score, multiply value by what the index score of each evaluation index, index weights, dimension multiplied by weight drew each evaluation index, the value that multiplies of each evaluation index is added and draws the tax credit scoring of object to be evaluated.As it can be seen that the application can improve the accuracy and timeliness of tax credit appraisal result so that evaluation index behavior decays the influence degree of credit appraisal result with the time.
Description
Technical field
The present invention relates to tax technical field, more particularly to a kind of tax credit score computational methods and device.
Background technology
At present, the application of reference is concentrated mainly on personal reference field, such as, the personal credit system of Central Bank, and for
Some specific industries, specific transactions item, reference service or seldom.
For Tax, reference of the prior art service is mainly the evaluation of taxpaying credit grade, its process can be with
Specially：Determine which specific evaluation index is first, for example write out falsely invoice behavior to be used as one of evaluation index；
After determining evaluation index, to the behavior of credit of each evaluation index, a situation arises per year, is recorded in due order, for example write out falsely invoice
Behavior, some taxpayer there occurs twice, then record twice in certain year；Per the beginning of the year, all evaluations recorded to upper one year
Index, a situation arises is counted for behavior of credit, and is deducted points with 100 points for best result and initial value, for example some is received
Tax people's last year writes out falsely invoice behavior and occurs 2 times, every time 10 points of button, then will be 20 points by button；Final score is classified, taxpaying credit
Grade is divided into A, B, C, D level Four, wherein more than 90 points for A grades, more than 70 points are B grade, and more than 40 points are C grades, 40 points discontented
For D grades；After the completion of beginning of the year taxpaying credit evaluating hierarchy, issued to society.
But using the method directly deducted points to evaluation index, point system is simple, can cause evaluation result error
Rate is higher, it is impossible to true reflection taxpayer's real credit situation.In this way, when final score differs 1 timesharing, the grade being assessed can
It can differ a grade, such as 89 points and 90/, be exactly the difference of B grades and A grades；And existing taxpaying credit grade is per year
Evaluation, the cycle is too long, can so cause the behavior of credit occurred then, and can only arrive next year can just be included into ranking, nothing
Method reflection in time is evaluated the credit situation of object；Each specific evaluation index, which can not realize credit evaluation result, temporally to decline
Subtract, that is, do not account for each evaluation index behavior and occur over time, the influence evaluated to final credit score
Degree also can be different.
The content of the invention
The object of the present invention is to provide a kind of tax credit score computational methods and device, to improve tax credit appraisal knot
The accuracy and timeliness of fruit so that evaluation index behavior decays the influence degree of credit appraisal result with the time.
To achieve the above object, the present invention provides following technical solution：
A kind of tax credit score computational methods, including：
Obtain the tax behavior of credit record data of object to be evaluated；
Assessment indicator system model and tax behavior of credit record data, Utilization assessment index based on prebuild are pressed
Time decay algorithm, according to evaluation cycle, damped cycle and scoring rule, timing or in real time calculating possess time attenuation characteristic
The index score of each first kind evaluation index, and according to the scoring rule, calculate periodically or in real time non-first kind evaluation and refer to
Target index score；
Wherein, the assessment indicator system model for possess multiple evaluative dimensions, each evaluative dimension has one or more levels
Evaluative dimension and every grade of evaluative dimension have the model of one or more evaluation indexes；The assessment indicator system model includes each
Affiliated dimensional information, dimension weight, index weights, damped cycle, evaluation cycle and the scoring rule of the evaluation index；Institute
Stating evaluation index, temporally decay algorithm is bigger for the difference based on evaluation index behavior date of occurrence and current date, and evaluation refers to
Mark behavior is smaller to the influence degree of credit score, and the difference of evaluation index behavior date of occurrence and current date is smaller, evaluation
The algorithm that the bigger rule of influence degree of the index behavior to credit score is drawn；The scoring rule includes the starting score base
Number, score range and evaluation index behavior subtract/bonus point numerical value；
By radix point-score, the index score of each evaluation index, the index weights, the dimension are weighed
Heavy phase it is multiplied go out each evaluation index multiply value, will multiply described in each evaluation index value addition draw it is described to be evaluated right
The tax credit scoring of elephant.
Alternatively, the assessment indicator system model based on prebuild and tax behavior of credit record data, profit
With evaluation index temporally decay algorithm, according to evaluation cycle, damped cycle and scoring rule, when timing or calculate in real time possesses
Between attenuation characteristic each first kind evaluation index index score, and according to the scoring rule, timing or calculate in real time non-
The index score of first kind evaluation index, including：
Based on the assessment indicator system model and tax behavior of credit record data, pass through formulaTiming or the initial score of index for calculating each first kind evaluation index in real time；
The initial score of the index of each first kind evaluation index is added with corresponding starting score radix and is drawn
The index score of each first kind evaluation index；
And according to the corresponding scoring rule of each non-first kind evaluation index, timing or calculate in real time described
The index score of non-first kind evaluation index；
Wherein, the evaluation index includes the first kind evaluation index and the non-first kind evaluation index；F is described
Subtract/bonus point numerical value, T1For the evaluation cycle, T2For the damped cycle, t1For current date, t2Sent out for evaluation index behavior
Phase birthday.
Alternatively, before the tax behavior of credit record data for obtaining object to be evaluated, further include：
Obtain original tax behavior of credit record data；
The requirement of each evaluation index in the assessment indicator system model, from the original behavior of credit note of the tax
Record data pick-up show that tax behavior of credit records account；
Tax behavior of credit record account is subjected to atomic data item standardization, draws the tax behavior of credit note
Record data.
Alternatively, the building process of the assessment indicator system model is specially：
Obtain history tax behavior of credit record data；
The dimension number of the assessment indicator system model, the dimension series of each dimension and evaluation index are set；
Algorithm is determined using weight, determines the dimension weight of each evaluation index and the index weights；
Algorithm is determined using damped cycle, determines the damped cycle of each first kind evaluation index；
Set up the scoring rule of each evaluation index and the evaluation cycle；
According to the dimension weight, the index weights, the damped cycle and the scoring rule, institute's commentary is constructed
Valency Index System Model.
Alternatively, after the calculating possesses the index score of each first kind evaluation index of time attenuation characteristic,
Further include：
Based on the index score of last each first kind evaluation index, current date and last integral and calculating
The time difference on date is foundation, is calculated when the index score of time each first kind evaluation index.
Alternatively, after the tax behavior of credit record data for obtaining object to be evaluated, further include：
Receive evaluation index custom instruction and scoring rule custom instruction；
According to the evaluation index custom instruction, recorded from the tax behavior of credit in data and calculate corresponding credit
Sub- index；
By the sub- index of the credit according to default rule of combination, self-defined evaluation index is formed；
According to the scoring rule custom instruction, the scoring rule of the setting self-defined evaluation index.
A kind of tax credit score computing device, including：
First acquisition module, the tax behavior of credit for obtaining object to be evaluated record data；
Index points calculating module, remembers for the assessment indicator system model based on prebuild and the tax behavior of credit
Record data, Utilization assessment index temporally decay algorithm, according to evaluation cycle, damped cycle and scoring rule, timing or in real time
Calculate the index score for each first kind evaluation index for possessing time attenuation characteristic, and according to the scoring rule, timing or
The index score of non-first kind evaluation index is calculated in real time；
Wherein, the assessment indicator system model for possess multiple evaluative dimensions, each evaluative dimension has one or more levels
Evaluative dimension and every grade of evaluative dimension have the model of one or more evaluation indexes；The assessment indicator system model includes each
Affiliated dimensional information, dimension weight, index weights, damped cycle, evaluation cycle and the scoring rule of the evaluation index；Institute
Stating evaluation index, temporally decay algorithm is bigger for the difference based on evaluation index behavior date of occurrence and current date, and evaluation refers to
Mark behavior is smaller to the influence degree of credit score, and the difference of evaluation index behavior date of occurrence and current date is smaller, evaluation
The algorithm that the bigger rule of influence degree of the index behavior to credit score is drawn；
Tax credit score computing module, for by radix point-score, the index of each evaluation index to be obtained
Point, the index weights, the dimension multiplied by weight draw each evaluation index multiply value, by the institute of each evaluation index
State and multiply the tax credit scoring that value addition draws the object to be evaluated.
Alternatively, the index points calculating module includes：
The initial score calculating sub module of index, for based on the assessment indicator system model and the tax behavior of credit
Data are recorded, pass through formulaTiming calculates each first kind evaluation index in real time
The initial score of index；
First index score calculating sub module, for by the initial score of the index of each first kind evaluation index
The index score for drawing each first kind evaluation index is added with corresponding starting score radix；
Second index score calculating sub module, by and according to each non-first kind evaluation index it is corresponding it is described based on
Divider then, calculates periodically or in real time the index score of the non-first kind evaluation index；
Wherein, the evaluation index includes the first kind evaluation index and the non-first kind evaluation index；The meter
Divider then includes the starting score radix, score range and every time occurring/subtract/bonus point number when evaluation index behavior not occurring
Value；F subtracts/bonus point numerical value, T to be described1For the evaluation cycle, T2For the damped cycle, t1For current date, t2For evaluation
Index behavior date of occurrence.
Alternatively, further include：
Second acquisition module, for obtaining original tax behavior of credit record data；
Data extraction module, for the requirement of each evaluation index in the assessment indicator system model, from described
The original behavior of credit record data pick-up of the tax show that tax behavior of credit records account；
Standardized module, for tax behavior of credit record account to be carried out atomic data item standardization, draws institute
State tax behavior of credit record data.
Alternatively, further include：
3rd acquisition module, for obtaining history tax behavior of credit record data；
Dimension setup module, for setting dimension number, the dimension level of each dimension of the assessment indicator system model
Number and evaluation index；
Weight determination module, for determining algorithm using weight, determines the dimension weight of each evaluation index
With the index weights；
Damped cycle computing module, for determining algorithm using damped cycle, determines that each first kind evaluation refers to
Target damped cycle；
Scoring rule computing module, for the scoring rule for setting up each evaluation index and the evaluation cycle；
Model construction module, for according to the dimension weight, the index weights, the damped cycle and the score
Rule, constructs the assessment indicator system model.
Using above-mentioned technical proposal, by various dimensions, the assessment indicator system model of multi objective, and each dimension and index
There is a corresponding weight, i.e., clearly each index, and can as needed in real time or timing to the influence degree of tax credit score
Tax credit score is calculated, and sets up bonus point and deduction rule so that credit score scope fluctuates in basis point, in this way,
Realize tax dynamic credit scoring, improve the accuracy and timeliness of tax credit appraisal result；And according to evaluation index row
Difference for date of occurrence and current date is bigger, and evaluation index behavior is smaller to the influence degree of credit score, evaluation index
Behavior date of occurrence and the difference of current date are smaller, the bigger rule of influence degree of the evaluation index behavior to credit score,
The index score of each evaluation index for possessing time attenuation characteristic is calculated, so that evaluation index behavior is to credit appraisal knot
The influence degree of fruit decays with the time.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
There is attached drawing needed in technology description to be briefly described, it should be apparent that, drawings in the following description are only this
The embodiment of invention, for those of ordinary skill in the art, without creative efforts, can also basis
The attached drawing of offer obtains other attached drawings.
Fig. 1 is that a kind of flow of embodiment of tax credit score computational methods provided in an embodiment of the present invention is shown
It is intended to；
Fig. 2 is assessment indicator system model schematic provided in an embodiment of the present invention；
Fig. 3 is starting score cardinal sum score range schematic diagram provided in an embodiment of the present invention；
Fig. 4 generates node schematic diagram for evaluation index provided in an embodiment of the present invention；
Fig. 5 is scoring rule generating process schematic diagram provided in an embodiment of the present invention；
Fig. 6 is the structural schematic block diagram of tax credit score computing device provided in an embodiment of the present invention.
Embodiment
To make the purpose, technical scheme and advantage of the embodiment of the present invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, the technical solution in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is
Part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
All other embodiments obtained without making creative work, belong to the scope of protection of the invention.
Please refer to Fig.1, Fig. 1 is a kind of specific embodiment party of tax credit score computational methods provided in an embodiment of the present invention
The flow diagram of formula, this method comprise the following steps：
Step 101, the tax behavior of credit record data for obtaining object to be evaluated.
It is to be appreciated that above-mentioned tax behavior of credit record data can refer to original behavior of credit record data, the original
Beginning behavior of credit record data can come from each tax information system, for example, core expropriation and management system, anti-false tax-controlled system,
Export tax rebate system and electronic tax office system etc..But during practical application, since data format otherness is big, data are complete
The problems such as whole property, directly carry out tax credit score calculating with original behavior of credit record data, can make it that calculating process is numerous
It is trivial lengthy and jumbled.
Tax behavior of credit record data may also mean that the data after processing, and data are pre-processed, can be made
It is succinctly efficient to obtain follow-up calculating process.Therefore in some embodiments possibles, before this step, it can also include：Obtain former
Beginning tax behavior of credit records data；The requirement of each evaluation index in assessment indicator system model, from the original letter of the tax
Show that tax behavior of credit records account with behavior record data pick-up；Tax behavior of credit record account is subjected to atomic data
Item standardization, show that tax behavior of credit records data.That is, above-mentioned tax behavior of credit record data are referred to original
The data that beginning behavior of credit record data obtain after extracting, standardizing.
Specifically, record in data from original tax behavior of credit, according to the requirement of each evaluation index, extract corresponding
Credit record data, and classification storage can be carried out according to evaluation object, show that behavior of credit records account；Then, from credit row
To record in account, according to the definition of each evaluation index, the normalized by definition of progress atomic data item.
For example, introducing the standardisation process of atomic data item by taking " invoice writes out falsely behavior of credit record " as an example, actually occur
Behavior of credit account be recorded as：2017/08/01 occurs 1 voiding invoice behavior；2017/03/20 occurs 1 voiding invoice
Behavior.Include evaluation index title, time of origin, number according to the normalized by definition of atomic data item, can draw actual standard
Data record after change is as shown in table 1 below.
Table 1
| Evaluation index title | Time of origin | Number |
| Invoice writes out falsely behavior of credit record | 2017/08/01 | 1 |
| Invoice writes out falsely behavior of credit record | 2017/03/20 | 1 |
Further, since the order of magnitude of calculative data volume is larger every time so that the workload of each data pick-up
Become very huge.Therefore, to simplify calculating process, ensure treatment effeciency, incremental number can be used for account extraction process
According to abstracting method.
Step 102, the assessment indicator system model based on prebuild and tax behavior of credit record data, Utilization assessment refer to
Temporally decay algorithm is marked, according to evaluation cycle, damped cycle and scoring rule, timing or in real time calculating possess time decay spy
Property each first kind evaluation index index score, and according to scoring rule, timing or calculate non-first kind evaluation in real time and refer to
Target index score；
Wherein, assessment indicator system model for possess multiple evaluative dimensions, each evaluative dimension has one or more levels evaluation
Dimension and every grade of evaluative dimension have the model of one or more evaluation indexes；Assessment indicator system model includes each evaluation index
Affiliated dimensional information, dimension weight, index weights, damped cycle, evaluation cycle and scoring rule；Evaluation index is temporally
Decay algorithm is bigger for the difference based on evaluation index behavior date of occurrence and current date, and evaluation index behavior is to credit score
Influence degree it is smaller, the difference of evaluation index behavior date of occurrence and current date is smaller, evaluation index behavior to credit accumulate
Point the algorithm that draws of the bigger rule of influence degree；Scoring rule includes starting score radix, score range and evaluation index row
For subtract/bonus point numerical value.
Assessment indicator system model schematic with reference to shown in Fig. 2, is introduced assessment indicator system model.Such as Fig. 2
Shown, which includes dimension 1, dimension 2 ... dimension n, and dimension 1 includes dimension 1.1, dimension 1.2 ... dimension 1.n, and dimension 1.1 is wrapped
Evaluation index 1.1.1, evaluation index 1.1.2 ... evaluation index 1.1.n are included, and each has corresponding weight.Wherein, if Fig. 2
In score value be limited in 0 to 1000 point, then score value shared by dimension 1 is:1000 × weight 1；Score value shared by dimension 1.1 is：1000
1 × weight of × weight 1.1；Score value shared by evaluation index 1.1.1 is：1000 × weight, 1 × weight, 1.1 × weight 1.1.1, successively
Analogize.
It is to be appreciated that assessment indicator system model can set multistage dimension+evaluation index, such as the model shown in Fig. 2 is
Two-stage dimension+evaluation index, still, under normal circumstances, it is only necessary to which level-one dimension+evaluation index can meet needs.
The intrinsic parameter such as dimension weight, index weights, damped cycle in assessment indicator system can be according to corresponding
Algorithm, counts from history high-volume data and draws.
In some embodiments possibles, the structure structure of above-mentioned assessment indicator system model can be specially：Obtain history
Tax behavior of credit records data；The dimension number of assessment indicator system model, the dimension series of each dimension are set and commented
Valency index；Algorithm is determined using weight, determines the dimension weight and index weights of each evaluation index；Determined using damped cycle
Algorithm, determines the damped cycle of each first kind evaluation index；Set up the scoring rule and evaluation cycle of each evaluation index；
According to dimension weight, index weights, damped cycle and scoring rule, assessment indicator system model is constructed.
It can be found from history tax behavior record data, after some behavior of credit occur, may result in tax flowing water, than
Such as, invoice behavior etc. is write out falsely.Algorithm is determined to set weight based on the relationship characteristic between tax revenue business behavior of credit item.
Its weight determines that algorithmic procedure can be specially：Count in some time cycle, the number of paying taxes that tax is lost in occurs
Amount；Statistics occur tax be lost in each taxpayer, evaluation index behavior be participate in credit score calculate each concerning taxes behavior and
The probability of happening of item, for example, 10,000 families occur in the taxpayer that tax is lost in, it is every to occur to open false invoice behavior per family, then should
It is 100% that evaluation index, which writes out falsely invoice behavior probability of happening, for another evaluation index, has 5 one thousand families to occur, then the evaluation
Index probability of happening is 50%；The probability of happening of each evaluation index is calculated according to this, and counts the total of all evaluation indexes
Probability；Total probability by dimension to each evaluation index statistical dimension；The probability of happening of each evaluation index is calculated affiliated
Ratio in dimension, i.e. index weights, and ratio of the probability of happening in all dimensions of dimension, i.e. dimension weight.
Specifically, current tax dynamic credit score evaluation system model includes 100 specific evaluation indexes, and evaluation refers to
The mode probability of mark I is I (I is from 1 to 100), including five dimension K (K is from 1 to 5), each dimension include 20 evaluation indexes,
Wherein, the evaluation index that dimension K is included is evaluation index I (I from 20 × (K-1)+1 to 20K).Then weight calculation formula can represent
For：
Weights of the evaluation index I in dimension K be：
The weight of dimension K is：
Counted and found by historical data, each evaluation index over time, its pass between being lost in tax
Continuous decrease is tied up to, based on this, setting damped cycle determines algorithm.
The damped cycle determines that the detailed process of algorithm can be specially：Count in some time cycle, tax stream occurs
Taxpayer's amount of mistake；Statistics occurs in taxpayer's amount that tax is lost in, and the date of occurrence of evaluation index behavior is with occurring tax
Data distribution relation between taxpayer's amount that money is lost in；By building linear regression algorithm, damped cycle is calculated.
Different evaluation indexes has its various corresponding scoring rule, and the scoring rule of each evaluation index can root
Determined according to actual conditions.Wherein, it is necessary first to determine starting score cardinal sum score range.Starting score radix can according to demand into
Row setting, score range can include bonus point section and deduction section, may be such that index score in basis point by positive or negative points
Lower floating.The specific starting score cardinal sum score range schematic diagram that may refer to shown in Fig. 3,0 point is set to by starting score radix, will
Starting score radix is multiplied by the basis point that evaluation index can be drawn after weight.
In this way, some intrinsic parameters that assessment indicator system model is counted from historical data, you can needed for constructing
Assessment indicator system model.
For possessing the first kind evaluation index of time attenuation characteristic, using evaluation index, temporally decay algorithm calculates
Index score.For non-first kind evaluation index, addition and subtraction parameter score can be fixed according to scoring rule.
In some embodiments possibles, this step can be specially：Based on assessment indicator system model and tax credit
Behavior record data, pass through formulaTiming calculates each first kind evaluation index in real time
The initial score of index；The initial score of index of each first kind evaluation index and corresponding starting score radix are added draw it is each
The index score of first kind evaluation index；And according to the corresponding scoring rule of each non-first kind evaluation index, timing or in real time
Calculate the index score of non-first kind evaluation index；Wherein, evaluation index includes first kind evaluation index and the non-first kind is commented
Valency index；F is to subtract/bonus point numerical value, T1For evaluation cycle, T2For damped cycle, t1For current date, t2For evaluation index behavior
Date of occurrence.
Calculated it is to be appreciated that the parameter on date involved in above-mentioned calculation formula is convertible into number of days, when remainder not
When 30 days full, being calculated by 30 days equal to 15 days is will be greater than, being calculated by 0 day less than 15 days.
It will be introduced below using the index calculating process of " invoice writes out falsely behavior of credit record " as example.
Index name：Invoice writes out falsely behavior of credit record；Index definition：In nearest 1 year situation is write out falsely with the presence or absence of invoice；
Affiliated dimension:History behavior of credit；Index weights：15%；Dimension weight：50%；Starting score radix：0 point；Top score：
1000 points；Minimum score：- 2000 points；
Code of points：The meter 1000 that situation is write out falsely without invoice in nearest 1 year divides, and there are invoice in nearest 1 year to write out falsely situation
Each -1000 points of meter, at most meter 2 times, damped cycle are 30 days.And current date is 2017/09/10, is occurred in nearest 1 year
Invoice situation is write out falsely twice, and respectively in 2017/08/01 and 2017/03/20, then the final score of the index is：
It is appreciated that if evaluation generation behavior occurs repeatedly in evaluation cycle, can calculate respectively repeatedly, for example, it is above-mentioned
Example twice, can also be calculated only once, and what is calculated is from the recent evaluation index behavior of current date.
For non-first kind evaluation index, positive or negative points rule that can be based on scoring rule, is fixed and point adds and subtracts.Example
Such as, to Mr. Yu's evaluation index, when generation, adds 1000 points, and 0 point is added when not occurring.In this way, also may be used for non-first kind evaluation index
To realize that dynamic is scored.
In addition, before evaluation index calculating is carried out, after obtaining behavior of credit record data, behavior can be not only carried out
The atomic data item standardization of data, can also carry out the standardization of evaluation index atomic data item.
For example, being based on above-mentioned example, to " invoice writes out falsely behavior of credit record ", this evaluation index carries out atomic data item
Standardization, can show that the data record of standardization is as shown in table 2 below,
Table 2
Step 103, by radix point-score, the index score of each evaluation index, index weights, dimension multiplied by weight are obtained
Go out each evaluation index multiplies value, by the tax credit scoring for multiplying value addition and drawing object to be evaluated of each evaluation index.
Specifically, after the index score for calculating each evaluation index, using formulaThe tax credit that the object to be evaluated is calculated is commented
Point.
Further, since the credit score of object to be evaluated can in real time or be periodically calculated, but the required order of magnitude calculated every time
Very big, treatment effeciency cannot be guaranteed.Therefore, to ensure treatment effeciency, a large amount of fully calculating is avoided, last institute can be made full use of
The index score of calculating works as secondary index score to calculate.
Therefore in some embodiments possibles, possess each first kind evaluation index of time attenuation characteristic in above-mentioned calculating
Index score after, can also include：Based on the index score of last each first kind evaluation index, current date with
The time difference on last integral and calculating date is foundation, is calculated when the index score of time each first kind evaluation index.
For example, the 2017/08/01 voiding invoice record occurred, is scored at -916.7 points, it is assumed that carry out credit after 10 days again
Integral and calculating, damped cycle are 30 days, and evaluation cycle is 365 days, and single standard of deducting point is 1000 points, then when secondary index score
For：Last time score-(standard of deducting point × ((time difference number of days+last time remainder number of days)/damped cycle)/(evaluation cycle/decay week
Phase))=- 916.7- (- 1000 × ((10+10)/30)/(365/30))=- 833.4.
In addition, in some embodiments possibles, evaluation index and scoring rule can be with self-defined.It is i.e. to be evaluated in acquisition
After the tax behavior of credit record data of valency object, it can also include：Receive evaluation index custom instruction and scoring rule
Custom instruction；According to evaluation index custom instruction, recorded from tax behavior of credit and calculate corresponding credit in data and refer to
Mark；By the sub- index of credit according to default rule of combination, self-defined evaluation index is formed；According to scoring rule custom instruction, if
The scoring rule of fixed self-defined evaluation index.
Specifically, it is self-defined can to carry out evaluation index by evaluation index user-defined visual interface by user, passes through meter
Then defined interface progress scoring rule is self-defined for divider.
System can respond the operational order of user, and the sub- index of corresponding credit is extracted from behavior of credit record data, and
The sub- index of credit is synthesized to new self-defined evaluation index.
Evaluation index generating process is introduced with reference to the evaluation index generation node schematic diagram shown in Fig. 4.Such as
Shown in Fig. 4, it includes atomic data item A, B, C, sub- index A, B of credit.Wherein, atomic data item is calculated as credit index
Minimum particle size variable, it corresponds generally to a certain item data in credit account data table, or is carried out simply based on this data item
Computing；The sub- index of credit refers to using semantic formula by used atomic data item, constant, function and other credits
Sub- indicator combination together, forms the expression formulas such as similar " A+B/C ", " Math.abs (A-B) ", then parses and transports by semanteme
Calculate, substitute into the variate-value in expression formula, you can calculate credit and refer to target value；The sub- index of credit is carried out using rule model
Combinatorial operation, obtains new evaluation index.
Scoring rule generating process is introduced with reference to the scoring rule generating process schematic diagram shown in Fig. 5.Such as
Shown in Fig. 4, by taking " invoice writes out falsely behavior of credit record " this index as an example, it includes the sub- index node (ellipse) of credit, filtering
Condition (connecting line) and score node (rectangle).
Wherein, the sub- index node (ellipse) of credit：The model node is that credit included required for evaluation index refers to
Mark, is the basis of evaluation index score." invoice is whether there is in nearest 1 year and writes out falsely situation " " the row of invoice voiding twice recently in upper example
For date of occurrence " it is the sub- index of crucial credit write out falsely from true invoice and processed in record.
Filter condition (connecting line)：The different branch conditions met needed for the sub- index of credit are defined by expression formula, are used
In distinguishing different scoring conditions paths.Distinguish whether " whether there is invoice and write out falsely situation " " and is in 1 year in upper example
Invoice write out falsely situation (date difference whether be more than 365 days) ", according to the difference of filter condition, be directed toward different score sections
Point.
Score node (rectangle)：Score node, defines the evaluation index scoring rule met in the case of preamble path.Such as
Fruit scores there are multiple details and records, then in final evaluation index score node, detailed score based on preamble records, into
Row secondary calculating, and bound control, so as to calculate final evaluation index score.
As it can be seen that by above-mentioned custom feature, can facilitate assessment indicator system model is carried out it is self-defined, to continue to optimize
Assessment indicator system model.
In the present embodiment, by various dimensions, the assessment indicator system model of multi objective, and each dimension and index have phase
The weight answered, i.e., clearly each index, and can as needed in real time or timing calculates tax to the influence degree of tax credit score
Business credit score, and set up bonus point and deduction rule so that credit score scope fluctuates in basis point, in this way, realizing tax
Business dynamic credit scoring, improves the accuracy and timeliness of tax credit appraisal result；And occurred according to evaluation index behavior
The difference of date and current date is bigger, and evaluation index behavior is smaller to the influence degree of credit score, evaluation index behavior hair
The difference of phase birthday and current date is smaller, the bigger rule of influence degree of the evaluation index behavior to credit score, calculates every
The index score of a evaluation index for possessing time attenuation characteristic, so that shadow of the evaluation index behavior to credit appraisal result
The degree of sound decays with the time.
Tax credit score computing device provided in an embodiment of the present invention is introduced below, tax letter described below
With integral and calculating device reference can be corresponded with above-described tax credit score computational methods.
Fig. 6 is refer to, Fig. 6 is the structural schematic block diagram of tax credit score computing device provided in an embodiment of the present invention,
The device includes：
First acquisition module 61, the tax behavior of credit for obtaining object to be evaluated record data；
Index points calculating module 62, records for the assessment indicator system model based on prebuild and tax behavior of credit
Data, Utilization assessment index temporally decay algorithm, according to evaluation cycle, damped cycle and scoring rule, in real time timing or meter
Calculator for each first kind evaluation index of time attenuation characteristic index score, and according to scoring rule, timing or in real time meter
Calculate the index score of non-first kind evaluation index；
Wherein, assessment indicator system model for possess multiple evaluative dimensions, each evaluative dimension has one or more levels evaluation
Dimension and every grade of evaluative dimension have the model of one or more evaluation indexes；Assessment indicator system model includes each evaluation index
Affiliated dimensional information, dimension weight, index weights, damped cycle, evaluation cycle and scoring rule；Evaluation index is temporally
Decay algorithm is bigger for the difference based on evaluation index behavior date of occurrence and current date, and evaluation index behavior is to credit score
Influence degree it is smaller, the difference of evaluation index behavior date of occurrence and current date is smaller, evaluation index behavior to credit accumulate
Point the algorithm that draws of the bigger rule of influence degree；
Tax credit score computing module 63, for by radix point-score, by index score, the index of each evaluation index
What weight, dimension multiplied by weight drew each evaluation index multiplies value, is added and draws object to be evaluated the value that multiplies of each evaluation index
Tax credit scoring.
Alternatively, index points calculating module includes：
The initial score calculating sub module of index, for based on assessment indicator system model and tax behavior of credit record number
According to passing through formulaTiming or calculate in real time each first kind evaluation index index it is initial
Point；
First index score calculating sub module, for by the initial score of index of each first kind evaluation index with it is corresponding
Starting score radix is added the index score for drawing each first kind evaluation index；
Second index score calculating sub module, is used for and according to the corresponding scoring rule of each non-first kind evaluation index,
Timing or the index score for calculating non-first kind evaluation index in real time；
Wherein, evaluation index includes first kind evaluation index and non-first kind evaluation index；Scoring rule includes starting score
Radix, score range and occur every time/subtract/bonus point numerical value when evaluation index behavior not occurring；F is to subtract/bonus point numerical value, T1For
Evaluation cycle, T2For damped cycle, t1For current date, t2For evaluation index behavior date of occurrence.
Alternatively, further include：
Second acquisition module, for obtaining original tax behavior of credit record data；
Data extraction module, it is original from the tax for the requirement of each evaluation index in assessment indicator system model
Behavior of credit record data pick-up show that tax behavior of credit records account；
Standardized module, for tax behavior of credit record account to be carried out atomic data item standardization, show that the tax is believed
With behavior record data.
Alternatively, further include：
3rd acquisition module, for obtaining history tax behavior of credit record data；
Dimension setup module, for set the dimension number of assessment indicator system model, the dimension series of each dimension with
And evaluation index；
Weight determination module, for determining algorithm using weight, determines the dimension weight and index power of each evaluation index
Weight；
Damped cycle computing module, for determining algorithm using damped cycle, determines each first kind evaluation index
Damped cycle；
Scoring rule computing module, for setting up the scoring rule and evaluation cycle of each evaluation index；
Model construction module, for according to dimension weight, index weights, damped cycle and scoring rule, constructing evaluation
Index System Model.
In the present embodiment, by various dimensions, the assessment indicator system model of multi objective, and each dimension and index have phase
The weight answered, i.e., clearly each index, and can as needed in real time or timing calculates tax to the influence degree of tax credit score
Business credit score, and set up bonus point and deduction rule so that credit score scope fluctuates in basis point, in this way, realizing tax
Business dynamic credit scoring, improves the accuracy and timeliness of tax credit appraisal result；And occurred according to evaluation index behavior
The difference of date and current date is bigger, and evaluation index behavior is smaller to the influence degree of credit score, evaluation index behavior hair
The difference of phase birthday and current date is smaller, the bigger rule of influence degree of the evaluation index behavior to credit score, calculates every
The index score of a evaluation index for possessing time attenuation characteristic, so that shadow of the evaluation index behavior to credit appraisal result
The degree of sound decays with the time.
Each embodiment is described by the way of progressive in specification, and what each embodiment stressed is and other realities
Apply the difference of example, between each embodiment identical similar portion mutually referring to.For device disclosed in embodiment
Speech, since it is corresponded to the methods disclosed in the examples, so description is fairly simple, related part is referring to method part illustration
.
Professional further appreciates that, with reference to each exemplary unit of the embodiments described herein description
And algorithm steps, can be realized with electronic hardware, computer software or the combination of the two, in order to clearly demonstrate hardware and
The interchangeability of software, generally describes each exemplary composition and step according to function in the above description.These
Function is performed with hardware or software mode actually, application-specific and design constraint depending on technical solution.Specialty
Technical staff can realize described function to each specific application using distinct methods, but this realization should not
Think beyond the scope of this invention.
Can directly it be held with reference to the step of method or algorithm that the embodiments described herein describes with hardware, processor
Capable software module, or the two combination are implemented.Software module can be placed in random access memory (RAM), memory, read-only deposit
Reservoir (ROM), electrically programmable ROM, electrically erasable ROM, register, hard disk, moveable magnetic disc, CD-ROM or technology
In any other form of storage medium well known in field.
Tax credit score computational methods provided by the present invention and device are described in detail above.Herein should
The principle of the present invention and embodiment are set forth with specific case, the explanation of above example is only intended to help to manage
Solve the method and its core concept of the present invention.It should be pointed out that for those skilled in the art, do not departing from
On the premise of the principle of the invention, some improvement and modification can also be carried out to the present invention, these are improved and modification also falls into this hair
In bright scope of the claims.
Claims (10)
- A kind of 1. tax credit score computational methods, it is characterised in that including：Obtain the tax behavior of credit record data of object to be evaluated；Assessment indicator system model and tax behavior of credit record data based on prebuild, Utilization assessment index is temporally Decay algorithm, according to evaluation cycle, damped cycle and scoring rule, timing or in real time calculating possess each of time attenuation characteristic The index score of first kind evaluation index, and according to the scoring rule, calculate periodically or in real time non-first kind evaluation index Index score；Wherein, the assessment indicator system model for possess multiple evaluative dimensions, each evaluative dimension has one or more levels evaluation Dimension and every grade of evaluative dimension have the model of one or more evaluation indexes；The assessment indicator system model includes each described Affiliated dimensional information, dimension weight, index weights, damped cycle, evaluation cycle and the scoring rule of evaluation index；Institute's commentary Temporally decay algorithm is bigger for the difference based on evaluation index behavior date of occurrence and current date for valency index, evaluation index row Smaller for the influence degree to credit score, the difference of evaluation index behavior date of occurrence and current date is smaller, evaluation index The algorithm that the bigger rule of influence degree of the behavior to credit score is drawn；The scoring rule include the starting score radix, Score range and evaluation index behavior subtract/bonus point numerical value；By radix point-score, by the index score of each evaluation index, the index weights, the dimension weight phase It is multiplied go out each evaluation index multiply value, value will be multiplied described in each evaluation index be added and draw the object to be evaluated Tax credit scoring.
- 2. the method as described in claim 1, it is characterised in that the assessment indicator system model based on prebuild and described Tax behavior of credit records data, and Utilization assessment index temporally decay algorithm, is advised according to evaluation cycle, damped cycle and score Then, timing or calculating in real time possess the index score of each first kind evaluation index of time attenuation characteristic, and according to the meter Divider then, calculates periodically or in real time the index score of non-first kind evaluation index, including：Based on the assessment indicator system model and tax behavior of credit record data, pass through formula Timing or the initial score of index for calculating each first kind evaluation index in real time；The initial score of the index of each first kind evaluation index and corresponding starting score radix are added draw it is each The index score of the first kind evaluation index；And according to the corresponding scoring rule of each non-first kind evaluation index, timing or calculate described non-the in real time The index score of a kind of evaluation index；Wherein, the evaluation index includes the first kind evaluation index and the non-first kind evaluation index；F for it is described subtract/ Bonus point numerical value, T1For the evaluation cycle, T2For the damped cycle, t1For current date, t2Day occurs for evaluation index behavior Phase.
- 3. method as claimed in claim 2, it is characterised in that in the tax behavior of credit record for obtaining object to be evaluated Before data, further include：Obtain original tax behavior of credit record data；The requirement of each evaluation index in the assessment indicator system model, from the original behavior of credit record number of the tax Show that tax behavior of credit records account according to extraction；Tax behavior of credit record account is subjected to atomic data item standardization, draws the tax behavior of credit record number According to.
- 4. such as claims 1 to 3 any one of them method, it is characterised in that the structure of the assessment indicator system model Journey is specially：Obtain history tax behavior of credit record data；The dimension number of the assessment indicator system model, the dimension series of each dimension and evaluation index are set；Algorithm is determined using weight, determines the dimension weight of each evaluation index and the index weights；Algorithm is determined using damped cycle, determines the damped cycle of each first kind evaluation index；Set up the scoring rule of each evaluation index and the evaluation cycle；According to the dimension weight, the index weights, the damped cycle and the scoring rule, construct the evaluation and refer to Mark system model.
- 5. the method as described in claim 1, it is characterised in that in each first kind for calculating and possessing time attenuation characteristic After the index score of evaluation index, further include：Based on the index score of last each first kind evaluation index, current date and last integral and calculating date Time difference be foundation, calculate the index score when time each first kind evaluation index.
- 6. the method as described in claim 1, it is characterised in that in the tax behavior of credit record for obtaining object to be evaluated After data, further include：Receive evaluation index custom instruction and scoring rule custom instruction；According to the evaluation index custom instruction, recorded from the tax behavior of credit and calculate corresponding credit in data and refer to Mark；By the sub- index of the credit according to default rule of combination, self-defined evaluation index is formed；According to the scoring rule custom instruction, the scoring rule of the setting self-defined evaluation index.
- A kind of 7. tax credit score computing device, it is characterised in that including：First acquisition module, the tax behavior of credit for obtaining object to be evaluated record data；Index points calculating module, for the assessment indicator system model based on prebuild and tax behavior of credit record number According to, Utilization assessment index temporally decay algorithm, according to evaluation cycle, damped cycle and scoring rule, timing or calculate in real time Possess the index score of each first kind evaluation index of time attenuation characteristic, and according to the scoring rule, timing or real-time Calculate the index score of non-first kind evaluation index；Wherein, the assessment indicator system model for possess multiple evaluative dimensions, each evaluative dimension has one or more levels evaluation Dimension and every grade of evaluative dimension have the model of one or more evaluation indexes；The assessment indicator system model includes each described Affiliated dimensional information, dimension weight, index weights, damped cycle, evaluation cycle and the scoring rule of evaluation index；Institute's commentary Temporally decay algorithm is bigger for the difference based on evaluation index behavior date of occurrence and current date for valency index, evaluation index row Smaller for the influence degree to credit score, the difference of evaluation index behavior date of occurrence and current date is smaller, evaluation index The algorithm that the bigger rule of influence degree of the behavior to credit score is drawn；The scoring rule include the starting score radix, Score range and evaluation index behavior subtract/bonus point numerical value；Tax credit score computing module, for by radix point-score, by the index score of each evaluation index, institute State index weights, the dimension multiplied by weight draws each evaluation index multiplies value, will multiply described in each evaluation index Value is added the tax credit scoring for drawing the object to be evaluated.
- 8. device as claimed in claim 7, it is characterised in that the index points calculating module includes：The initial score calculating sub module of index, for based on the assessment indicator system model and tax behavior of credit record Data, pass through formulaTiming or the index for calculating each first kind evaluation index in real time Initial score；First index score calculating sub module, for by the initial score of the index of each first kind evaluation index with it is right The starting score radix answered is added the index score for drawing each first kind evaluation index；Second index score calculating sub module, is used for and is advised according to the corresponding score of each non-first kind evaluation index Then, timing or the index score of the non-first kind evaluation index is calculated in real time；Wherein, the evaluation index includes the first kind evaluation index and the non-first kind evaluation index；F for it is described subtract/ Bonus point numerical value, T1For the evaluation cycle, T2For the damped cycle, t1For current date, t2Day occurs for evaluation index behavior Phase.
- 9. device as claimed in claim 8, it is characterised in that further include：Second acquisition module, for obtaining original tax behavior of credit record data；Data extraction module, for the requirement of each evaluation index in the assessment indicator system model, from the tax Original behavior of credit record data pick-up show that tax behavior of credit records account；Standardized module, for tax behavior of credit record account to be carried out atomic data item standardization, draws the tax Business behavior of credit record data.
- 10. such as claim 7 to 9 any one of them device, it is characterised in that further include：3rd acquisition module, for obtaining history tax behavior of credit record data；Dimension setup module, for set the dimension number of the assessment indicator system model, the dimension series of each dimension with And evaluation index；Weight determination module, for determining algorithm using weight, determines the dimension weight and the institute of each evaluation index State index weights；Damped cycle computing module, for determining algorithm using damped cycle, determines each first kind evaluation index Damped cycle；Scoring rule computing module, for the scoring rule for setting up each evaluation index and the evaluation cycle；Model construction module, for being advised according to the dimension weight, the index weights, the damped cycle and the score Then, the assessment indicator system model is constructed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711283210.6A CN107944738A (en) | 2017-12-07 | 2017-12-07 | A kind of tax credit score computational methods and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711283210.6A CN107944738A (en) | 2017-12-07 | 2017-12-07 | A kind of tax credit score computational methods and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107944738A true CN107944738A (en) | 2018-04-20 |
Family
ID=61945141
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711283210.6A Pending CN107944738A (en) | 2017-12-07 | 2017-12-07 | A kind of tax credit score computational methods and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107944738A (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108961023A (en) * | 2018-06-19 | 2018-12-07 | 阿里巴巴集团控股有限公司 | A kind of credit refund method, apparatus, system and electronic equipment |
| CN109637000A (en) * | 2018-10-23 | 2019-04-16 | 深圳壹账通智能科技有限公司 | The invoice method of inspection and device, storage medium, electric terminal |
| CN109711732A (en) * | 2018-12-27 | 2019-05-03 | 税友软件集团股份有限公司 | A kind of storage method, device, equipment and the storage medium of index integral |
| CN110222997A (en) * | 2019-06-14 | 2019-09-10 | 山东浪潮商用系统有限公司 | A kind of enterprise does tax personnel credit assessment method and system |
| CN110222129A (en) * | 2019-06-17 | 2019-09-10 | 山东浪潮商用系统有限公司 | A kind of credit appraisal algorithm based on relevant database |
| CN110264343A (en) * | 2019-06-21 | 2019-09-20 | 山东浪潮商用系统有限公司 | A kind of credit estimation method based on tax big data analysis |
| CN110751403A (en) * | 2019-10-21 | 2020-02-04 | 中国民航信息网络股份有限公司 | Credit scoring method and device |
| CN111459820A (en) * | 2020-03-31 | 2020-07-28 | 北京九章云极科技有限公司 | Model application method and device and data analysis processing system |
| CN112529626A (en) * | 2020-12-15 | 2021-03-19 | 深圳市快付通金融网络科技服务有限公司 | Method, device and equipment for clearing integral data and storage medium |
| CN113344610A (en) * | 2021-05-18 | 2021-09-03 | 网易（杭州）网络有限公司 | Block chain-based virtual object allocation method, device and readable storage medium |
| CN113570257A (en) * | 2021-07-30 | 2021-10-29 | 北京房江湖科技有限公司 | Index data evaluation method and device based on scoring model, medium and equipment |
| CN114548523A (en) * | 2022-01-26 | 2022-05-27 | 深圳市傲天科技股份有限公司 | User viewing information prediction method, device, equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104680297A (en) * | 2013-12-03 | 2015-06-03 | 航天信息股份有限公司 | Evaluation system and evaluation method for credit rating |
| CN106127363A (en) * | 2016-06-12 | 2016-11-16 | 腾讯科技（深圳）有限公司 | A kind of user credit appraisal procedure and device |
| CN106779457A (en) * | 2016-12-29 | 2017-05-31 | 深圳微众税银信息服务有限公司 | A kind of rating business credit method and system |
| US20170293873A1 (en) * | 2016-03-24 | 2017-10-12 | Www.Trustscience.Com Inc. | Learning an entity's trust model and risk tolerance to calculate a risk score |
-
2017
- 2017-12-07 CN CN201711283210.6A patent/CN107944738A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104680297A (en) * | 2013-12-03 | 2015-06-03 | 航天信息股份有限公司 | Evaluation system and evaluation method for credit rating |
| US20170293873A1 (en) * | 2016-03-24 | 2017-10-12 | Www.Trustscience.Com Inc. | Learning an entity's trust model and risk tolerance to calculate a risk score |
| CN106127363A (en) * | 2016-06-12 | 2016-11-16 | 腾讯科技（深圳）有限公司 | A kind of user credit appraisal procedure and device |
| CN106779457A (en) * | 2016-12-29 | 2017-05-31 | 深圳微众税银信息服务有限公司 | A kind of rating business credit method and system |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019242342A1 (en) * | 2018-06-19 | 2019-12-26 | 阿里巴巴集团控股有限公司 | Credit tax refund method, device and system and electronic device |
| CN108961023A (en) * | 2018-06-19 | 2018-12-07 | 阿里巴巴集团控股有限公司 | A kind of credit refund method, apparatus, system and electronic equipment |
| CN109637000A (en) * | 2018-10-23 | 2019-04-16 | 深圳壹账通智能科技有限公司 | The invoice method of inspection and device, storage medium, electric terminal |
| CN109637000B (en) * | 2018-10-23 | 2021-12-28 | 深圳壹账通智能科技有限公司 | Invoice detection method and device, storage medium and electronic terminal |
| CN109711732A (en) * | 2018-12-27 | 2019-05-03 | 税友软件集团股份有限公司 | A kind of storage method, device, equipment and the storage medium of index integral |
| CN110222997A (en) * | 2019-06-14 | 2019-09-10 | 山东浪潮商用系统有限公司 | A kind of enterprise does tax personnel credit assessment method and system |
| CN110222129A (en) * | 2019-06-17 | 2019-09-10 | 山东浪潮商用系统有限公司 | A kind of credit appraisal algorithm based on relevant database |
| CN110222129B (en) * | 2019-06-17 | 2023-09-22 | 浪潮软件科技有限公司 | Credit evaluation algorithm based on relational database |
| CN110264343A (en) * | 2019-06-21 | 2019-09-20 | 山东浪潮商用系统有限公司 | A kind of credit estimation method based on tax big data analysis |
| CN110751403A (en) * | 2019-10-21 | 2020-02-04 | 中国民航信息网络股份有限公司 | Credit scoring method and device |
| CN111459820A (en) * | 2020-03-31 | 2020-07-28 | 北京九章云极科技有限公司 | Model application method and device and data analysis processing system |
| CN112529626A (en) * | 2020-12-15 | 2021-03-19 | 深圳市快付通金融网络科技服务有限公司 | Method, device and equipment for clearing integral data and storage medium |
| CN113344610A (en) * | 2021-05-18 | 2021-09-03 | 网易（杭州）网络有限公司 | Block chain-based virtual object allocation method, device and readable storage medium |
| CN113344610B (en) * | 2021-05-18 | 2023-08-08 | 网易（杭州）网络有限公司 | Block chain-based virtual object allocation method, device and readable storage medium |
| CN113570257A (en) * | 2021-07-30 | 2021-10-29 | 北京房江湖科技有限公司 | Index data evaluation method and device based on scoring model, medium and equipment |
| CN114548523A (en) * | 2022-01-26 | 2022-05-27 | 深圳市傲天科技股份有限公司 | User viewing information prediction method, device, equipment and storage medium |
| CN114548523B (en) * | 2022-01-26 | 2023-11-07 | 深圳市傲天科技股份有限公司 | User viewing information prediction method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107944738A (en) | A kind of tax credit score computational methods and device | |
| Chinn et al. | Global current account imbalances: American fiscal policy versus East Asian savings | |
| CN104462059B (en) | Trade company's address information recognition methods and device | |
| Boss et al. | Systemic risk monitor: A model for systemic risk analysis and stress testing of banking systems | |
| CN111126828A (en) | Knowledge graph-based multilayer fund abnormal flow direction monitoring method | |
| CN107894953A (en) | A kind of generation method and device of Bank application test data | |
| CN110895758B (en) | Screening method, device and system for credit card account with cheating transaction | |
| CN106557971A (en) | Based on the financial data processing method of speech recognition technology, system and terminal | |
| CN110264342A (en) | A kind of business audit method and device based on machine learning | |
| CN103258388A (en) | Automatic transaction device, server and method for predicting quantity demanded of cash | |
| CN104616198A (en) | P2P (peer-to-peer) network lending risk prediction system based on text analysis | |
| CN110659961A (en) | Method and device for identifying off-line commercial tenant | |
| CN110796539A (en) | Credit investigation evaluation method and device | |
| Wiryono et al. | Islamic bank credit risk: Macroeconomic and bank specific factors | |
| CN112052385A (en) | Investment and financing project recommendation method and device, electronic equipment and readable storage medium | |
| CN112927071A (en) | Post-loan behavior feature processing method and device | |
| CN102393945B (en) | Data processing method and system for risk weighted asset calculation | |
| CN112365352A (en) | Anti-cash-out method and device based on graph neural network | |
| Fang et al. | Endogenous cyclical corporate tax burden in China: The role of tax quotas and growth targets | |
| Al-Halabi et al. | The impact of designing accounting information systems on the level of accounting conservatism-a field study | |
| CN111429251A (en) | Method and device for processing data under multiple modes | |
| CN108711073A (en) | Customer analysis method, apparatus and terminal | |
| CN116611914A (en) | Salary prediction method and device based on grouping statistics | |
| CN109615232A (en) | A kind of method, system and the relevant apparatus of credit score prediction | |
| CN112101950B (en) | Suspicious transaction monitoring model feature extraction method and suspicious transaction monitoring model feature extraction device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180420 |