CN115345734A - Industrial chain financial wind control model construction method based on block chain - Google Patents
Industrial chain financial wind control model construction method based on block chain Download PDFInfo
- Publication number
- CN115345734A CN115345734A CN202211279044.3A CN202211279044A CN115345734A CN 115345734 A CN115345734 A CN 115345734A CN 202211279044 A CN202211279044 A CN 202211279044A CN 115345734 A CN115345734 A CN 115345734A
- Authority
- CN
- China
- Prior art keywords
- data
- wind control
- financial
- financial data
- chain
- 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
- 238000010276 construction Methods 0.000 title claims abstract description 20
- 238000007405 data analysis Methods 0.000 claims abstract description 66
- 238000012795 verification Methods 0.000 claims abstract description 38
- 238000000034 method Methods 0.000 claims abstract description 36
- 230000008569 process Effects 0.000 claims abstract description 19
- 238000012549 training Methods 0.000 claims description 22
- 238000011156 evaluation Methods 0.000 claims description 21
- 230000001105 regulatory effect Effects 0.000 claims description 6
- 238000012502 risk assessment Methods 0.000 claims description 6
- 239000000284 extract Substances 0.000 claims description 3
- 238000012545 processing Methods 0.000 abstract description 8
- 238000004458 analytical method Methods 0.000 abstract description 3
- 238000006243 chemical reaction Methods 0.000 description 4
- 238000011161 development Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
Images
Landscapes
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention relates to a block chain-based industrial chain financial wind control model construction method, which relates to the technical field of financial risk management and comprises a block chain construction module, a block chain management module and a data processing module, wherein the block chain construction module is used for constructing a block chain based on an industrial chain; the data acquisition module acquires financial data generated in an industrial chain and uploads the financial data to a block chain; the data analysis module analyzes the financial data on the block chain, and the construction module constructs a wind control model corresponding to the financial data when the data analysis module completes the analysis of the financial data; the data acquisition module acquires the financial data of the front end of the industrial chain with a preset data volume in the big data and determines whether the financial data of the front end of the industrial chain is qualified or not; the verification module inputs the associated financial data into the wind control model to carry out model verification; and when the verification is completed, generating a wind control model on the corresponding block chain. The identification capability of the user data in the credit process and the efficiency of the credit business data processing process are improved.
Description
Technical Field
The invention relates to the technical field of financial risk management, in particular to a block chain-based industrial chain financial wind control model construction method.
Background
The credit business is one of the important business links of the financial institution, which has great contribution to the social and economic development, but the financial institution, as a node for providing the credit business, provides more convenience for the general public while promoting the economic development.
In addition, the development of the internet does not provide a financial institution with better guarantee for the convenience of credit extension business, but various information and data in the internet are relatively complex, and for the financial institution, a great amount of information and data can cause heavy burden on one hand and can cause inaccurate identification of a user in the credit process on the other hand.
Chinese patent publication no: CN109949148A discloses an automatic wind control configuration system and method for financial credit business, which is composed of a system logic unit, a management unit, a logic unit, a data unit and a data middleware unit, and realizes an automatic big data wind control full flow by data analysis, data ETL, model characteristic engineering, data model configuration and model output configuration; the method has the advantages of fitting with customer requirements, interpretability and strong transparency of the wind control process, configuration of a differentiated customized model and the like; therefore, the automatic wind control configuration system and method for the financial credit business have the problems that the data of a user cannot be accurately identified in the credit process, so that the efficiency of the credit business data processing process is low, errors occur and the like.
Disclosure of Invention
Therefore, the invention provides a block chain-based construction method of a financial wind control model of an industrial chain, which is used for solving the problems that in the prior art, the data of a user cannot be accurately identified in a credit process, so that the efficiency of a credit service data processing process is low and errors occur.
In order to achieve the purpose, the invention provides a block chain-based industrial chain financial wind control model construction method, which comprises the following steps:
s1, a block chain building module builds a block chain based on an industrial chain;
s2, a data acquisition module acquires industrial chain financial data and uploads the industrial chain financial data to the block chain;
s3, analyzing the financial data of the industrial chain on the block chain by a data analysis module, and constructing a wind control model corresponding to the financial data of the industrial chain by a construction module when the financial data is analyzed by the data analysis module;
s4, the data acquisition module acquires the financial data of the front end of the industrial chain with a preset data volume in the big data and determines whether the financial data of the front end of the industrial chain is qualified or not;
s5, when the data acquisition module determines that the financial data at the front end of the industrial chain is qualified, determining the related financial data of the financial data and the financial data at the front end of the industrial chain, and inputting the related financial data into the wind control model by a verification module for model verification;
and S6, generating the wind control model on the corresponding block chain when the verification is completed.
Further, in the step S1, when the block chain building module builds a block chain based on an industry chain, the block chain building module uploads financial data of a plurality of nodes on the industry chain to the block chain to form a plurality of data blocks corresponding to the nodes, and sets encryption for the data blocks corresponding to the nodes, respectively.
Further, in the step S3, when the data analysis module analyzes the industry chain financial data on the blockchain, the user financial data characteristic value G, the user industry risk index Fa, the user credit evaluation index W, the current savings amount Ej of the financial institution, the risk resistance coefficient r of the financial institution, and the annual average savings amount Ep of the financial institution in the industry chain financial data of the plurality of nodes are extracted, and the wind control evaluation value T for the user is calculated, and the setting is performed to set the wind control evaluation value T
Wherein G0 is a preset user financial data characteristic value.
Further, in the step S3, when the construction of the wind control model corresponding to the industrial chain financial data is completed, the industrial chain financial data of the plurality of nodes is used as the input of the wind control model, the corresponding user wind control evaluation value is used as the output of the wind control model, and the wind control model is trained, and during the training, the iteration number of the wind control model is set to be N, and the learning rate is set to be a.
Further, in step S4, when the data analysis module determines the associated financial data, the data analysis module extracts the same data amount S of the front-end financial data and the front-end financial data of the industry chain and calculates an association degree Y of the front-end financial data of the industry chain and the financial data, and sets Y = S/Sz, where Sz is a total data amount of the front-end financial data of the industry chain.
Further, when the data analysis module finishes calculating the association degree, the association degree Y is compared with a preset association degree Y0, whether the financial data at the front end of the industrial chain is qualified or not is determined according to a comparison result,
if Y is larger than Y0, the data analysis module determines that the financial data at the front end of the industrial chain is qualified;
and if Y is less than or equal to Y0, the data analysis module determines that the financial data at the front end of the industry chain is unqualified.
Further, in step S5, when the data analysis module determines that the financial data at the front end of the industrial chain is qualified, the qualified financial data at the front end of the industrial chain is used as an input of the wind control model, the data analysis module compares the wind control evaluation value Ta of the financial data at the front end of the industrial chain with the output value Tb of the wind control model, calculates a difference C between the wind control evaluation value Ta of the financial data at the front end of the industrial chain and the output value Tb of the wind control module, sets C = | Ta-Tb |, and the verification module compares the difference C with a preset difference, where the verification module is provided with a first preset difference C1 and a second preset difference C2, C1 is less than C2,
when C is less than or equal to C1, the verification module determines that the wind control model is completely trained;
when C1 is larger than C and smaller than or equal to C2, the verification module determines that the training of the wind control model is not finished, and judges that the user financial data characteristic value G and a preset user financial data characteristic value G0 are adjusted;
and when C is larger than C2, the verification module determines that the training of the wind control model is not finished, and judges that the iteration times are adjusted.
Further, when the verification module determines that the wind control model training is not completed and C1 is greater than C and is not greater than C2, the data analysis module calculates a first ratio Ba of the difference C and a first preset difference C1, sets Ba = C/C1, compares the first ratio Ba with a preset ratio, and selects a corresponding compensation coefficient according to a comparison result to compensate the iteration number, the data analysis module sets the compensated iteration number to N1, and sets N1= N × Xi, where Xi is a compensation coefficient of the iteration number.
Further, when the verification module determines that the wind control model training is not completed and C > C2, the data analysis module calculates a second ratio Bb of the difference C to a second preset difference C2, sets Ba = C/C2, and compares the second ratio Bb with a preset ratio,
if Bb is less than or equal to B1, the data analysis module sets the adjusted characteristic value of the user financial data to G1= G x (Kg 1/n) 2 Setting the adjusted preset user financial data characteristic value as G01= G0 x (Kg 1/n) 2 ；
If B1 is more than Bb and less than or equal to B2, the data analysis module sets the adjusted characteristic value of the user financial data to G2= Gx (Kg 2/n) 2 Setting the adjusted preset user financial data characteristic value to G02= G0 × (Kg 2/n) 2 ；
If Bb is larger than B2, the data analysis module sets the adjusted characteristic value of the user financial data to G3= G x (Kg 2/n) 2 Setting the adjusted preset user financial data characteristic value to G03= G0 × (Kg 1/n) 2 ；
In the formula, kg1 is a first characteristic value adjusting coefficient, kg2 is a second characteristic value adjusting coefficient, kg3 is a third characteristic value adjusting coefficient, n is a positive integer, and 1 & ltKg 1 & lt Kg2 & lt Kg3 & lt 2 are set.
Further, in step S6, when the generation of the wind control model on the corresponding blockchain is completed, the user is linked, the data acquisition module acquires financial data of the user, and the blockchain automatically identifies the risk assessment value of the user and shares the risk assessment value of the user on each node of the blockchain.
Compared with the prior art, the method has the advantages that the financial institution and the credit user in the credit process are uploaded to the block chain, the financial data of the credit user and the financial data of the financial institution are acquired in the block chain, the wind control model is set and trained through the acquired financial data, the wind control model based on the block chain is obtained, when the financial institution carries out credit business, the related data of the credit user are acquired and uploaded to the block chain, the data analysis module analyzes the data which can be subjected to wind control evaluation by the wind control model and transmits the data to the wind control model, so that the wind control model evaluates the credit user, the identification capability of the user data in the credit process is improved, and the efficiency of the credit business data processing process is further improved.
Further, the invention further improves the identification capability of the user data in the credit process by acquiring various credit-related data of a plurality of nodes on the blockchain and calculating the evaluation value used for training the wind control model according to the extracted various credit-related data when the building of the wind control model is completed, and enables the wind control model to be more accurate in wind control identification and lower in error rate by extracting only the credit-related data.
Furthermore, when the wind control model is trained, the data acquisition module is used for acquiring the relevant credit data in the big data, the acquired relevant credit data is compared with the financial data used for training the wind control model, the association degree of the relevant credit data and the financial data used for training the wind control model is determined, the preset association degree is set, and the relevant credit data with the association degree larger than the preset association degree is reserved for verifying the wind control model, so that the identification capability of the user data in the credit process is further improved, and the efficiency of the credit business data processing process is further improved.
Furthermore, when the wind control model is verified, the difference value between the wind control evaluation value obtained by calculating verification data and the wind control evaluation value output by the wind control model is calculated, a plurality of preset difference values are set, the calculated difference value is compared with the preset difference values to determine the verification result of the wind control model, and when the verification result of the wind control model is determined to be unqualified, the obtained training data is determined to be expanded or the hyper-parameter of the wind control model is adjusted according to the comparison result of the actually calculated difference value and the preset difference value to enable the model to be optimal, so that the identification precision of user data in the credit process is further improved, and the efficiency of the credit business data processing process is further improved.
Further, when the training data are determined to be expanded to enable the wind control model to be optimal, the data conversion adjustment coefficient for performing data conversion on corresponding financial data is determined according to the comparison result of the first ratio and a plurality of preset ratios, and when the data conversion adjustment coefficient is determined to be expanded according to the comparison result of the first ratio and the preset ratios, the identification precision of user data in the credit process is further improved by performing data conversion expansion on the financial data, and therefore the efficiency of the credit business data processing process is further improved.
Drawings
FIG. 1 is a flowchart of a block chain-based industrial chain financial wind control model building method according to an embodiment of the present invention;
fig. 2 is a structural block diagram of each module in the block chain-based industrial chain financial wind control model construction method according to the embodiment of the invention.
Detailed Description
In order that the objects and advantages of the invention will be more clearly understood, the invention is further described below with reference to examples; it should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only for explaining the technical principle of the present invention, and do not limit the scope of the present invention.
Furthermore, it should be noted that, in the description of the present invention, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, and may be, for example, fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.
Referring to fig. 1 and fig. 2, fig. 1 is a flowchart of a block chain-based industry chain financial wind control model building method according to an embodiment of the present invention; fig. 2 is a structural block diagram of each module in the block chain-based industrial chain financial wind control model construction method according to the embodiment of the invention.
The invention discloses a block chain-based industrial chain financial wind control model construction method, which comprises the following steps:
s1, a block chain building module builds a block chain based on an industrial chain;
s2, a data acquisition module acquires industrial chain financial data and uploads the industrial chain financial data to the block chain;
s3, analyzing the financial data of the industrial chain on the block chain by a data analysis module, and constructing a wind control model corresponding to the financial data of the industrial chain by a construction module when the financial data is analyzed by the data analysis module;
s4, the data acquisition module acquires the financial data of the front end of the industrial chain with a preset data volume in the big data and determines whether the financial data of the front end of the industrial chain is qualified or not;
s5, when the data acquisition module determines that the financial data at the front end of the industrial chain is qualified, determining the related financial data of the financial data and the financial data at the front end of the industrial chain, and inputting the related financial data into the wind control model by a verification module for model verification;
and S6, generating the wind control model on the corresponding block chain when the verification is completed.
Specifically, in step S1, when the blockchain building module builds an industry chain-based blockchain, the blockchain building module uploads financial data of a plurality of nodes on the industry chain to the blockchain to form a plurality of data blocks corresponding to the nodes, and sets encryption for the data blocks corresponding to the nodes, respectively.
Specifically, in the embodiment of the invention, each module in the industrial chain financial wind control model building method based on the block chain is provided, wherein,
a block chain construction module for constructing a block chain based on an industrial chain; the data acquisition module is connected with the block chain construction module and used for acquiring industrial chain financial data and uploading the industrial chain financial data to the block chain; the building module is connected with the data analysis module and used for analyzing industrial chain financial data on the block chain, and the building module builds a wind control model corresponding to the industrial chain financial data when the data analysis module completes the analysis of the financial data; and the verification module is respectively connected with the data analysis module and the construction module and is used for verifying the wind control model when the data analysis module determines that the financial data at the front end of the industrial chain is qualified.
Specifically, in the embodiment of the present invention, the front-end financial data of the industry chain is the financial data of the front-end user related to the industry chain, which is obtained from the big data.
In an embodiment of the present invention, the industry chain financial data is all financial data generated in an industry chain, and the industry chain financial data includes data of a front-end lending user of a financial institution, data of the financial institution, and data of a back-end depositor of the financial institution.
Specifically, the data of the front-end lending user comprises user financial data, user industry risk data and a user existing credit evaluation index; the financial institution data comprises the existing loan data of the financial institution, the corresponding risk coefficient, the existing deposit data and the risk resistance coefficient; the back-end depositor data comprises annual average reserves.
Specifically, in step S3, when the data analysis module analyzes the industry chain financial data on the block chain, the user financial data characteristic value G, the user industry risk index Fa, the user credit evaluation index W, the financial institution existing deposit amount Ej, the financial institution anti-risk coefficient r, and the annual average deposit amount Ep in the industry chain financial data of a plurality of the nodes are extracted, and the wind control evaluation value T for the user is calculated to set
Wherein G0 is a preset user financial data characteristic value.
Specifically, in step S3, when the construction of the wind control model corresponding to the industry chain financial data is completed, the industry chain financial data of a plurality of nodes is used as the input of the wind control model, the corresponding user wind control evaluation value is used as the output of the wind control model, and the wind control model is trained, and during the training, the iteration number of the wind control model is set to N, and the learning rate is set to a.
Specifically, in step S4, when the data analysis module determines the associated financial data, the data analysis module extracts the same data amount S of the front-end financial data and the financial data of the industry chain, and calculates a degree of association Y of the front-end financial data and the financial data of the industry chain, and sets Y = S/Sz, where Sz is a total data amount of the financial data of the industry chain.
Specifically, when the data analysis module finishes calculating the association degree, the association degree Y is compared with a preset association degree Y0, whether the financial data at the front end of the industrial chain is qualified or not is determined according to a comparison result,
if Y is larger than Y0, the data analysis module determines that the financial data at the front end of the industrial chain is qualified;
and if Y is less than or equal to Y0, the data analysis module determines that the financial data at the front end of the industry chain is unqualified.
Specifically, when the data analysis module determines that the financial data at the front end of the industrial chain is qualified, the data in the qualified financial data at the front end of the industrial chain is used as the input of the wind control model, the data analysis module compares the wind control evaluation value Ta of the financial data at the front end of the industrial chain with the output value Tb of the wind control model, calculates the difference C between the wind control evaluation value Ta of the financial data at the front end of the industrial chain and the output value Tb of the wind control module, sets C = | Ta-Tb |, and the verification module compares the difference C with a preset difference, wherein the verification module is provided with a first preset difference C1 and a second preset difference C2, C1 is less than C2,
when C is less than or equal to C1, the verification module determines that the training of the wind control model is finished;
when C1 is larger than C and smaller than or equal to C2, the verification module determines that the training of the wind control model is not finished, and judges that the user financial data characteristic value G and a preset user financial data characteristic value G0 are adjusted;
and when C is larger than C2, the verification module determines that the training of the wind control model is not finished, and judges that the iteration times are adjusted.
Specifically, when the verification module determines that the wind control model training is not completed and C1 is greater than C and is not greater than C2, the data analysis module calculates a first ratio Ba of the difference C and a first preset difference C1, sets Ba = C/C1, compares the first ratio Ba with a preset ratio, and selects a corresponding compensation coefficient to compensate the iteration number according to a comparison result, wherein the data analysis module is provided with a first preset ratio B1 and a second preset ratio B2, wherein B1 is greater than B2, sets 1 is greater than X2 is greater than X3 is less than 1.5,
if Ba is less than or equal to B1, the data analysis module selects a first compensation coefficient X1 to compensate the iteration times;
if B1 is larger than Ba and is not larger than B2, the data analysis module selects a second compensation coefficient X2 to compensate the iteration times;
if Ba is larger than B2, the data analysis module selects a third compensation coefficient X3 to compensate the iteration times;
when the data analysis module selects the ith compensation coefficient Xi to compensate the iteration times, i =1,2,3 is set, the data analysis module sets the compensated iteration times as N1, and N1= N × Xi is set.
Specifically, when the verification module determines that the wind control model training is not completed and C > C2, the data analysis module calculates a second ratio Bb of the difference C to a second preset difference C2, sets Ba = C/C2, and compares the second ratio Bb with a preset ratio,
if Bb is less than or equal to B1, the data analysis module sets the adjusted characteristic value of the user financial data to G1= G x (Kg 1/n) 2 Setting the adjusted preset user financial data characteristic value to G01= G0 × (Kg 1/n) 2 ；
If B1 is more than Bb and less than or equal to B2, the data analysis module sets the adjusted characteristic value of the user financial data to G2= Gx (Kg 2/n) 2 Setting the adjusted preset user financial data characteristic value to G02= G0 × (Kg 2/n) 2 ；
If Bb is larger than B2, the data analysis module sets the adjusted characteristic value of the user financial data to G3= G x (Kg 2/n) 2 Setting the adjusted preset user financial data characteristic value to G03= G0 × (Kg 1/n) 2 ；
In the formula, kg1 is a first characteristic value regulating coefficient, kg2 is a second characteristic value regulating coefficient, kg3 is a third characteristic value regulating coefficient, n is a positive integer, and 1 & ltKg 1 & lt Kg2 & lt Kg3 & lt 2 are set.
Specifically, when the adjustment of the user financial data characteristic value G and the preset user financial data characteristic value G0 is completed, if the verification module determines that the wind control model training is still completed, the data analysis and analysis module selects a corresponding learning rate adjustment coefficient to adjust the learning rate according to the comparison result of the difference C and the preset difference,
wherein the data analysis module is also provided with a first learning rate adjustment coefficient Ka1, a second learning rate adjustment coefficient Ka2 and a third learning rate adjustment coefficient Ka3, wherein Ka1 is more than 1 and more than Ka2 and more than Ka3 and less than 1.2,
when C is less than or equal to C1, the data analysis module selects a first learning rate adjustment coefficient Ka1 to adjust the learning rate;
when C1 is larger than C and is smaller than or equal to C2, the data analysis module selects a second learning rate adjustment coefficient Ka2 to adjust the learning rate;
when C is larger than C2, the data analysis module selects a third learning rate adjustment coefficient Ka3 to adjust the learning rate;
when the data analysis module selects the mth learning rate adjustment coefficient Kam to adjust the learning rate; setting m =1,2,3, the data analysis module sets the learning rate after adjustment to A1, setting A1= a × Kam.
Specifically, in step S6, when the generation of the wind control model on the corresponding blockchain is completed, the user is linked, the data acquisition module acquires financial data of the user, and the blockchain automatically identifies a risk assessment value of the user and shares the user risk assessment value on each node of the blockchain.
So far, the technical solutions of the present invention have been described in connection with the preferred embodiments shown in the drawings, but it is easily understood by those skilled in the art that the scope of the present invention is obviously not limited to these specific embodiments. Equivalent changes or substitutions of related technical features can be made by those skilled in the art without departing from the principle of the invention, and the technical scheme after the changes or substitutions can be within the protection scope of the invention.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention; various modifications and alterations to this invention will become apparent to those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A block chain-based industrial chain financial wind control model building method is characterized by comprising the following steps: s1, a block chain building module builds a block chain based on an industrial chain; s2, a data acquisition module acquires industrial chain financial data and uploads the industrial chain financial data to the block chain; s3, analyzing the financial data of the industrial chain on the block chain by a data analysis module, and constructing a wind control model corresponding to the financial data of the industrial chain by a construction module when the financial data is analyzed by the data analysis module; s4, the data acquisition module acquires the financial data of the front end of the industrial chain with a preset data volume in the big data and determines whether the financial data of the front end of the industrial chain is qualified or not; s5, when the data acquisition module determines that the financial data at the front end of the industrial chain is qualified, determining the related financial data of the financial data and the financial data at the front end of the industrial chain, and inputting the related financial data into the wind control model by a verification module for model verification; and S6, generating the wind control model on the corresponding block chain when the verification is completed.
2. The method for constructing the financial wind control model of the block chain-based industry chain according to claim 1, wherein in the step S1, when the block chain constructing module constructs the block chain based on the industry chain, the block chain constructing module uploads financial data of a plurality of nodes on the industry chain to the block chain to form a plurality of data blocks corresponding to the nodes, and sets encryption for the data blocks corresponding to the nodes respectively.
3. The method for constructing a financial wind control model of block chain-based industry chain according to claim 2, wherein in step S3, when the data analysis module analyzes the financial data of industry chain on the block chain, a user financial data characteristic value G, a user industry risk index Fa, a user credit evaluation index W, an existing savings amount Ej of a financial institution, a risk resistance coefficient r of a financial institution and an average annual storage amount Ep of the financial institution in the financial data of industry chain of a plurality of the nodes are extracted, and a wind control evaluation value T for the user is calculated, and set
Wherein G0 is a preset user financial data characteristic value.
4. The method according to claim 3, wherein in step S3, when building a wind control model corresponding to the industry chain financial data is completed, the industry chain financial data of a plurality of nodes is used as an input of the wind control model, a corresponding user wind control evaluation value is used as an output of the wind control model, the wind control model is trained, and in the training process, the number of iterations of the wind control model is set to N, and the learning rate is set to A.
5. The method for building block chain-based industry chain financial wind control model according to claim 4, wherein in the step S4, when the data analysis module determines the associated financial data, the data analysis module extracts the same data volume S of the industry chain front end financial data and the industry chain financial data, and calculates the association degree Y of the industry chain front end financial data and the financial data, and sets Y = S/Sz, wherein Sz is the total data volume of the industry chain financial data.
6. The method for constructing the financial wind control model of the industry chain based on the block chain as claimed in claim 5, wherein when the data analysis module calculates the association degree, the association degree Y is compared with a preset association degree Y0, and whether the financial data of the front end of the industry chain is qualified is determined according to the comparison result, if Y > Y0, the data analysis module determines that the financial data of the front end of the industry chain is qualified; and if Y is less than or equal to Y0, the data analysis module determines that the financial data at the front end of the industry chain is unqualified.
7. The method according to claim 6, wherein in step S5, when the data analysis module determines that the financial data at the front end of the industrial chain is qualified, the qualified financial data at the front end of the industrial chain is used as an input of the wind control model, the data analysis module compares a wind control evaluation value Ta of the financial data at the front end of the industrial chain with an output value Tb of the wind control model, calculates a difference C between the wind control evaluation value Ta of the financial data at the front end of the industrial chain and the output value Tb of the wind control module, and sets C = | Ta-Tb |, and the verification module compares the difference C with a preset difference, wherein the verification module is provided with a first preset difference C1 and a second preset difference C2, C1 < C2, and when C ≦ C1, the verification module determines that the training of the wind control model is completed; when C1 is larger than C and smaller than or equal to C2, the verification module determines that the training of the wind control model is not finished, and judges that the user financial data characteristic value G and a preset user financial data characteristic value G0 are adjusted; and when C is larger than C2, the verification module determines that the training of the wind control model is not finished, and judges that the iteration times are adjusted.
8. The method for constructing the financial wind control model of the industry chain based on the block chain according to claim 7, wherein when the verification module determines that the wind control model is not trained completely and C1 is greater than C and is not greater than C2, the data analysis module calculates a first ratio Ba of the difference C and a first preset difference C1, sets Ba = C/C1, compares the first ratio Ba with a preset ratio, selects a corresponding compensation coefficient according to a comparison result to compensate the iteration number, sets the compensated iteration number as N1, and sets N1= N × Xi, where Xi is the compensation coefficient of the iteration number.
9. The method as claimed in claim 8, wherein when the verification module determines that the wind control model training is not completed and C > C2, the data analysis module calculates a second ratio Bb of the difference C to a second predetermined difference C2, sets Ba = C/C2, compares the second ratio Bb to a predetermined ratio, and sets the adjusted characteristic value of the user financial data to G1= gxx (Kg 1/n) if Bb is less than or equal to B1 2 Setting the adjusted preset user financial data characteristic value as G01= G0 x (Kg 1/n) 2 (ii) a If B1 is more than Bb and less than or equal to B2, the data analysis module sets the adjusted characteristic value of the user financial data to G2= Gx (Kg 2/n) 2 Setting the adjusted preset user financial data characteristic value to G02= G0 × (Kg 2/n) 2 (ii) a If Bb is greater than B2, the data analysis module sets the adjusted characteristic value of the user financial data to G3= G x (Kg 2/n) 2 Setting the adjusted preset user financial data characteristic value as G03= G0 x (Kg 1/n) 2 (ii) a In the formula, kg1 is a first characteristic value regulating coefficient, kg2 is a second characteristic value regulating coefficient, kg3 is a third characteristic value regulating coefficient, n is a positive integer, and 1 & ltKg 1 & lt Kg2 & lt Kg3 & lt 2 are set.
10. The method according to claim 9, wherein in step S6, when the generation of the wind control model on the corresponding blockchain is completed, the user is linked, the data acquisition module acquires financial data of the user, and the blockchain automatically identifies the risk assessment value of the user and shares the risk assessment value of the user on each node of the blockchain.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211279044.3A CN115345734A (en) | 2022-10-19 | 2022-10-19 | Industrial chain financial wind control model construction method based on block chain |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211279044.3A CN115345734A (en) | 2022-10-19 | 2022-10-19 | Industrial chain financial wind control model construction method based on block chain |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115345734A true CN115345734A (en) | 2022-11-15 |
Family
ID=83957518
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211279044.3A Pending CN115345734A (en) | 2022-10-19 | 2022-10-19 | Industrial chain financial wind control model construction method based on block chain |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115345734A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116630032A (en) * | 2023-07-17 | 2023-08-22 | 九一金融信息服务(北京)有限公司 | Intelligent post-credit management system based on blockchain |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112541818A (en) * | 2020-12-24 | 2021-03-23 | 四川享宇金信金融科技有限公司 | Block chain-based wind control model construction method |
| CN113435770A (en) * | 2021-07-07 | 2021-09-24 | 中国银行股份有限公司 | Transaction risk assessment method and device based on block chain |
| CN114202413A (en) * | 2022-02-17 | 2022-03-18 | 中云融拓数据科技发展(深圳)有限公司 | Method for establishing financial wind control system based on industrial chain digital scene financial model |
| CN114358907A (en) * | 2022-01-06 | 2022-04-15 | 广东启链科技有限公司 | Financial risk prediction method and system based on block chain federal learning |
| CN115049505A (en) * | 2022-04-22 | 2022-09-13 | 中银金融科技有限公司 | Industrial chain financial risk prevention and control method and device based on block chain |
-
2022
- 2022-10-19 CN CN202211279044.3A patent/CN115345734A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112541818A (en) * | 2020-12-24 | 2021-03-23 | 四川享宇金信金融科技有限公司 | Block chain-based wind control model construction method |
| CN113435770A (en) * | 2021-07-07 | 2021-09-24 | 中国银行股份有限公司 | Transaction risk assessment method and device based on block chain |
| CN114358907A (en) * | 2022-01-06 | 2022-04-15 | 广东启链科技有限公司 | Financial risk prediction method and system based on block chain federal learning |
| CN114202413A (en) * | 2022-02-17 | 2022-03-18 | 中云融拓数据科技发展(深圳)有限公司 | Method for establishing financial wind control system based on industrial chain digital scene financial model |
| CN115049505A (en) * | 2022-04-22 | 2022-09-13 | 中银金融科技有限公司 | Industrial chain financial risk prevention and control method and device based on block chain |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116630032A (en) * | 2023-07-17 | 2023-08-22 | 九一金融信息服务(北京)有限公司 | Intelligent post-credit management system based on blockchain |
| CN116630032B (en) * | 2023-07-17 | 2023-10-31 | 九一金融信息服务(北京)有限公司 | Intelligent post-credit management system based on blockchain |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8195473B2 (en) | Method and system for optimized real estate appraisal | |
| CN104835103A (en) | Mobile network health evaluation method based on neural network and fuzzy comprehensive evaluation | |
| CN108399428A (en) | A kind of triple loss function design method based on mark than criterion | |
| CN107862602A (en) | It is a kind of based on various dimensions index calculate, self study and divide group model apply credit decision-making technique and system | |
| CN115345734A (en) | Industrial chain financial wind control model construction method based on block chain | |
| CN110310199B (en) | Method and system for constructing loan risk prediction model and loan risk prediction method | |
| CN109948920B (en) | Electric power market settlement data risk processing method based on evidence theory | |
| CN108985455A (en) | A kind of computer application neural net prediction method and system | |
| CN110309608A (en) | A kind of blast furnace molten iron silicon content forecasting procedure for time lag uncertain information | |
| CN111639111A (en) | Water transfer engineering-oriented multi-source monitoring data deep mining and intelligent analysis method | |
| CN109086954A (en) | Prediction technique, device, equipment and medium based on cash flow indicated yield | |
| CN113327047B (en) | Power marketing service channel decision method and system based on fuzzy comprehensive model | |
| Bagchi et al. | The real exchange rate in small, open, developed economies: Evidence from cointegration analysis | |
| CN114580940A (en) | Grouting effect fuzzy comprehensive evaluation method based on grey correlation degree analysis method | |
| CN110322342B (en) | Method and system for constructing loan risk prediction model and loan risk prediction method | |
| CN116912016A (en) | Bill auditing method and device | |
| CN109190858A (en) | A kind of power network construction project investment policy making period method | |
| CN116957770A (en) | Method and device for identifying financial fraud | |
| Baldacci et al. | A framework for fiscal debt sustainability analysis in low-income countries | |
| TWI720638B (en) | Deposit interest rate bargaining adjustment system and method thereof | |
| CN114331176A (en) | Evaluation method based on minimum cross entropy criterion fusion subjective and objective evaluation and application thereof | |
| Manchala et al. | Ensembling teaching-learning-based optimization algorithm with analogy-based estimation to predict software development effort | |
| Albani et al. | Local volatility models in commodity markets and online calibration | |
| CN110991252A (en) | Detection method for crowd distribution and counting in unbalanced scene | |
| Popchev et al. | A decision support method for investment preference evaluation |
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 |
Application publication date: 20221115 |
|
| RJ01 | Rejection of invention patent application after publication |