CN113554505A - Bank wind control method and device based on block chain - Google Patents
Bank wind control method and device based on block chain Download PDFInfo
- Publication number
- CN113554505A CN113554505A CN202110696871.1A CN202110696871A CN113554505A CN 113554505 A CN113554505 A CN 113554505A CN 202110696871 A CN202110696871 A CN 202110696871A CN 113554505 A CN113554505 A CN 113554505A
- Authority
- CN
- China
- Prior art keywords
- wind control
- data
- sample data
- sample
- bank
- 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
- 238000000034 method Methods 0.000 title claims abstract description 64
- 238000012545 processing Methods 0.000 claims abstract description 66
- 238000012549 training Methods 0.000 claims abstract description 47
- 238000013507 mapping Methods 0.000 claims description 36
- 230000008569 process Effects 0.000 claims description 29
- 238000004422 calculation algorithm Methods 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 13
- 238000003860 storage Methods 0.000 claims description 12
- 230000006870 function Effects 0.000 description 25
- 238000010586 diagram Methods 0.000 description 14
- 238000004891 communication Methods 0.000 description 7
- 230000002776 aggregation Effects 0.000 description 4
- 238000004220 aggregation Methods 0.000 description 4
- 239000000872 buffer Substances 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000007781 pre-processing Methods 0.000 description 4
- 230000007246 mechanism Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013501 data transformation Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000006116 polymerization reaction Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/602—Providing cryptographic facilities or services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/62—Protecting access to data via a platform, e.g. using keys or access control rules
- G06F21/6218—Protecting access to data via a platform, e.g. using keys or access control rules to a system of files or objects, e.g. local or distributed file system or database
- G06F21/6245—Protecting personal data, e.g. for financial or medical purposes
-
- 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06Q10/067—Enterprise or organisation modelling
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Marketing (AREA)
- Bioethics (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Operations Research (AREA)
- Computer Hardware Design (AREA)
- Quality & Reliability (AREA)
- Finance (AREA)
- Software Systems (AREA)
- Accounting & Taxation (AREA)
- Data Mining & Analysis (AREA)
- Computer Security & Cryptography (AREA)
- Tourism & Hospitality (AREA)
- Game Theory and Decision Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Educational Administration (AREA)
- Technology Law (AREA)
- Medical Informatics (AREA)
- Databases & Information Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
Abstract
The invention provides a bank wind control method and a bank wind control device based on a block chain, which relate to the field of finance, and the method comprises the following steps: receiving sample data provided by each sample data participant through a block chain; carrying out data alignment processing on the received sample data of each sample data participant; carrying out model training on a preset bank wind control prediction model by using sample data after data alignment processing; and processing the received bank wind control data by using the bank wind control prediction model after the model training to generate a bank wind control result. The method comprises the steps of carrying out data alignment processing on received sample data of each sample data participant, realizing more accurate wind control by utilizing financial data of a user, carrying out model training on a preset bank wind control prediction model by utilizing the sample data after the data alignment processing, carrying out model training more accurately on the premise that the participants do not expose respective financial data, generating a more accurate wind control model, and solving the problem of accurate wind control of internet companies and bank users.
Description
Technical Field
The invention relates to a data processing technology, in particular to a bank wind control method and device based on a block chain.
Background
With the development of the internet, the business of each large internet company gradually relates to the financial field, and small amount of loan business is introduced, and the amount of the loan amount is used for analyzing the purchasing power and the use habits of users by using large data to credit the amount, which is different from the wind control mode of bank loan credit investigation and flow investigation. The banking business is licensed, while the p2p business of the internet company is unlicensed, and the risk of explosion exists.
The user loan data of the internet company and the user loan data of the bank are not shared, the line credit of the user is obtained by means of big data analysis and the traditional wind control mode of the bank, and the risk that the user is difficult to be precisely controlled by wind exists.
Disclosure of Invention
Aiming at the defects of bank wind control in the prior art, the invention provides a bank wind control method based on a block chain, which comprises the following steps:
receiving sample data provided by each sample data participant through a block chain;
carrying out data alignment processing on the received sample data of each sample data participant;
carrying out model training on a preset bank wind control prediction model by using sample data after data alignment processing;
and processing the received bank wind control data by using the bank wind control prediction model after the model training to generate a bank wind control result.
In the embodiment of the present invention, before receiving sample data provided by each sample data participant through the block chain, the method includes:
generating a public key and a private key by using a preset encryption algorithm;
and sending the generated public key to each sample data participant through the block chain.
In an embodiment of the present invention, before receiving sample data provided by each sample data participant through a block chain, the method further includes:
carrying out Hash mapping processing on the sample ID;
and encrypting the sample ID after the Hash mapping process by using the public key.
In this embodiment of the present invention, the performing data alignment processing on the received sample data of each sample data participant includes:
decrypting the received sample data by using the private key to generate a sample ID after Hash mapping;
and matching the sample data of each participant according to the decrypted sample ID after the Hash mapping process so as to finish the data alignment process.
In the embodiment of the present invention, the performing model training on the preset bank wind control prediction model by using the sample data after the data alignment processing includes:
and carrying out federal training on a preset bank wind control prediction model by using the sample data after alignment processing to generate a trained bank wind control prediction model.
Meanwhile, the invention also provides a bank wind control device based on the block chain, which comprises the following components:
the data receiving and sending module is used for receiving the sample data provided by each sample data participant through the block chain;
the sample alignment module is used for carrying out data alignment processing on the received sample data of each sample data participant;
the model training module is used for performing model training on a preset bank wind control prediction model by using the sample data after the data alignment processing;
and the prediction module is used for processing the received bank wind control data by using the bank wind control prediction model after the model training to generate a bank wind control result.
In the embodiment of the present invention, the apparatus further includes:
the key generation module is used for generating a public key and a private key by utilizing a preset encryption algorithm;
and the generated public key is sent to each sample data participant through the block chain by the data transceiver module.
In the embodiment of the present invention, the apparatus further includes:
the Hash mapping module is used for carrying out Hash mapping processing on the sample ID;
and the encryption module is used for encrypting the sample ID after the Hash mapping process by using the public key.
In an embodiment of the present invention, the sample alignment module includes:
the decryption unit is used for decrypting the received sample data by using the private key to generate a sample ID after Hash mapping;
and the matching alignment unit is used for matching the sample data of each participant according to the decrypted sample ID after the Hash mapping processing so as to finish the data alignment processing.
In the embodiment of the invention, the model training module utilizes the sample data after the alignment processing to carry out federal training on a preset bank wind control prediction model so as to generate the trained bank wind control prediction model.
Meanwhile, the invention also provides computer equipment which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor realizes the method when executing the computer program.
Meanwhile, the invention also provides a computer readable storage medium, and a computer program for executing the method is stored in the computer readable storage medium.
The bank wind control method based on the block chain receives the sample data provided by each sample data participant through the block chain, the data alignment processing is carried out on the received sample data of each sample data participant, the problem that the data of an internet company and the data of a bank user are not shared mutually in the prior art is solved on the premise that the participant does not expose the financial data of the user, the financial data of the user is utilized to carry out more accurate wind control, the sample data after the data alignment processing is utilized to carry out model training on a preset bank wind control prediction model, the received bank wind control data are processed to generate a bank wind control result, model training is more accurately carried out on the premise that the participants do not expose respective financial data, a more accurate wind control model is generated, and the problem of accurate wind control of internet companies and bank users is solved.
In order to make the aforementioned and other objects, features and advantages of the invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flow chart of a method for banking wind control based on a block chain according to the present invention;
FIG. 2 is a block diagram of an embodiment of the present invention;
FIG. 3 is a schematic flow chart of an embodiment of the present invention;
FIG. 4 is a block diagram of a banking wind control device based on a block chain according to the present invention;
fig. 5 is a schematic diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be described clearly and completely with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
At present, user loan data of an internet company and user loan data of a bank are not shared, and the line credit of the user is obtained by means of large data analysis and the traditional wind control mode of the bank, so that the risk of difficulty in accurate wind control of the user exists. Therefore, how to share the internet company user loan data and the bank user loan data to achieve the effect of accurately controlling the users through wind is a problem to be solved urgently.
In view of the above, the present invention provides a bank wind control method based on a block chain, as shown in fig. 1, including:
step S101, receiving sample data provided by each sample data participant through a block chain;
step S102, carrying out data alignment processing on the received sample data of each sample data participant;
step S103, performing model training on a preset bank wind control prediction model by using sample data after data alignment processing;
and step S104, processing the received bank wind control data by using the bank wind control prediction model after model training to generate a bank wind control result.
The bank wind control method based on the block chain provided by the invention receives the sample data provided by each sample data participant through the block chain, ensures the safety of the sample data provided by each participant by utilizing the non-falsification characteristic of the block chain, carries out data alignment treatment on the received sample data of each sample data participant, realizes more accurate wind control on the financial data of users by an internet company and a bank in the prior art on the premise that the participants do not expose the financial data of the users, carries out model training on a preset bank wind control prediction model by utilizing the sample data after the data alignment treatment, processes the received bank wind control data to generate a bank wind control result, and more accurately carries out the model training to generate a more accurate wind control model on the premise that the participants do not expose the financial data of each participant, the problem of accurate wind accuse of internet company and bank user is solved.
In the embodiment of the present invention, before receiving sample data provided by each sample data participant through the block chain, the method includes:
generating a public key and a private key by using a preset encryption algorithm;
and sending the generated public key to each sample data participant through the block chain.
Specifically, in the embodiment of the present invention, the RSA algorithm is used to generate the private key and the public key, and the public key of the private key and the public key of the participant are simultaneously issued, and the public key is used to encrypt data to be transmitted.
The generated public key is sent to each sample data participant through the block chain, and each sample data participant encrypts the transmitted data by using the public key, so that the user ID is not transmitted by a plaintext, and the safety is further improved.
In an embodiment of the present invention, before receiving sample data provided by each sample data participant through a block chain, the method further includes:
carrying out Hash mapping processing on the sample ID;
and encrypting the sample ID after the Hash mapping process by using the public key.
In this embodiment of the present invention, the performing data alignment processing on the received sample data of each sample data participant includes:
decrypting the received sample data by using the private key to generate a sample ID after Hash mapping;
and matching the sample data of each participant according to the decrypted sample ID after the Hash mapping process so as to finish the data alignment process.
Specifically, in an embodiment of the present invention, a participant a locally generates a public key and a private key pair required for encrypting a sample ID according to an RSA algorithm, then stores the private key locally, sends the sample set ID and the public key to a blockchain node, the blockchain node then sends the sample set ID and the public key to the participant B, then the participant B performs hash mapping on the original local sample ID by using an agreed hash function to generate a sample set ID, which ensures that the user ID is not transmitted in the clear, then encrypts the mapped sample set ID by using the public key of the participant a to generate an encrypted B-side sample set ID, and sends the encrypted B-side sample set ID to the blockchain node, the blockchain node sends the encrypted B-side sample set ID to the participant a, the participant a decrypts the B-side sample set after hash mapping, and then maps the local sample by using the same mapping function, and matching with the sample ID from the B party, finally sending the matched sample set ID to the block chain node, and sending the matched sample set ID to the B party by the block chain node to complete the sample alignment process.
According to the embodiment of the invention, the sample data is aligned on the premise of not exposing the user ID of the participant by carrying out Hash mapping processing on the sample ID, the model training is carried out on the preset bank wind control prediction model by utilizing the sample data of each participant to carry out bank wind control prediction, the model training is carried out more accurately on the premise of not exposing respective financial data of all the participants to generate a more accurate wind control model, and the problem of accurate wind control of an internet company and a bank user is solved.
In the embodiment of the present invention, the performing model training on the preset bank wind control prediction model by using the sample data after the data alignment processing includes:
and carrying out federal training on a preset bank wind control prediction model by using the sample data after alignment processing to generate a trained bank wind control prediction model.
Generating a private key and a public key by utilizing an RSA algorithm;
simultaneously issuing a public key of the participant, wherein the public key is used for encrypting data to be transmitted;
each participant calculates a characteristic intermediate result on a data set of the participant;
each participant respectively obtains the gradient, and the gradient is transmitted to the participants after gradient polymerization;
and iterating the steps until the loss function is converged, and finishing the whole training process.
The embodiment of the invention provides a method for applying federal study based on a block chain to bank wind control, which solves the problem of accurate wind control of an internet company and a bank user on the premise that the internet company and the bank do not expose financial data of the user.
As shown in fig. 2, a block diagram of a system provided in an embodiment of the present invention includes:
the system comprises a heterogeneous data processing module 1, a data preprocessing module 2, a sample alignment module 3, a federal learning module 4 and a block chain module 5.
In the embodiment of the present invention, the heterogeneous data processing module 1 is configured to perform data description and data transformation on original data in a unified manner.
Specifically, the heterogeneous data processing module 1 converts the original data format into JSON representation, and then performs distributed analysis uniformly through a Spark computing framework to generate a Hive table structure. Heterogeneous data access does not perform preprocessing operation of sample data, and only provides conversion operation of basic field types.
The data preprocessing module 2, the user has already vectorized all available data, so that the upper layer application only needs to be dedicated to the implementation of the algorithm model, and the disordered data preprocessing operation is not needed.
In a real scene, there are a large number of character string type fields, such as gender (male, female), location of household (beijing city, shanghai city, guangzhou city, etc.), nature of location (business unit, civil business, foreign enterprise, etc.), and the like. Such string formats are primarily for human understanding, but cannot be directly entered into the machine learning model. Aiming at the processing of the character string type data, the embodiment of the invention carries out one-hot coding processing after carrying out numerical mapping on the character string through code conversion.
And the sample alignment module 3 ensures that the samples participating in training are consistent among all the participants.
As shown in fig. 3, it is a flowchart of the sample alignment processing performed by the sample alignment module in this embodiment.
In the embodiment of the invention, the RSA encryption algorithm is used for encrypting the sample data.
T1, party A generates the public key and private key pair needed by the encrypted sample ID locally according to RSA algorithm;
t2, storing the private key locally, and sending the sample set ID and the public key to the blockchain node;
t3, the block chain node sends the sample set ID and the public key to the participant B;
t4, the participant B performs hash mapping on the original ID of the local sample by using an agreed hash function to ensure that the user ID is not transmitted by the plaintext;
t5, then encrypting the mapped sample set ID with the public key of party a to generate an encrypted B-party sample set ID;
t6, sending the encrypted B-side sample set ID to the blockchain node;
t7, the block chain node sends the encrypted B-party sample set ID to the participant A;
t8, party A decrypts and obtains the B party sample set after hash mapping;
t9, mapping the local sample by the same mapping function;
t10, matching with the sample ID from the B party;
t11, finally, sending the matched sample set ID to the block chain node;
t12, the chunk chain node sends the matched sample set ID to party B, completing the sample alignment process.
The federal learning module 4 performs an overall process of federal modeling by two participants after sample alignment, wherein a central server is responsible for gradient summarization and updating models of the participants, and the central server is used for realizing the function of the federal learning module, distributing a public key to the participants, performing aggregation processing on the gradients of the participants, and transmitting the aggregated public key to the participants until a loss function is converged.
The specific overall training process is shown as follows:
1. firstly, the central server utilizes RSA algorithm to generate private key and public key
2. The central server simultaneously issues own public keys to the two participants, and the public keys are used for encrypting data to be transmitted;
3. two participants respectively calculate characteristic intermediate results on own data sets;
4. the two participants respectively obtain the gradient (see formula 4.8 and formula 4.9), and transmit the gradient to the central server after encrypting by using the public key
5. The central server decrypts by using the private key;
6. the central server carries out gradient aggregation (the following formula is 4.12)0 and then transmits the gradient aggregation to the two participants;
7. and iterating the steps until the loss function is converged, and finishing the whole training process.
The participants update the local model:
assuming that there are two participants for federal training and the training model is LR model, assuming that two participants have completed the sample alignment process, the aligned sample set of A is used
Indicating, for B aligned sample sets
Note that the number of samples for A and B are both m, and DAThe real label y of the sample is not included in the list, that is, in the credit federation scenario, only one participant has the real label of the sample.
Suppose that the model parameters of the participants A and B are initialized to theta respectivelyA，θBThe optimized original objective function is:
wherein, betaAAnd betaBThe two-norm regular coefficients of the local model parameters of the participator A and the participator B are respectively, and the target is to find out the optimal parameter { thetaA，θBThe set holds the following:
will be provided with
And
respectively record as
And
in order to protect data privacy and perform gradient aggregation after decryption, a homomorphic encryption process needs to be performed on an original target function, the encryption mode allows both encryption parties to perform algebraic operation on a ciphertext to obtain an encrypted result, but ensures that the decrypted result is consistent with a result obtained by performing the same operation on a plaintext. Since the privacy of the user can be effectively protected, the method is widely used for the privacy protection problem when data is hosted as a third party.
In the embodiment of the present invention, the encrypted function may be written as:
wherein Enc [. cndot.) represents the encryption process, and then the encrypted target function is expanded, so that three sub-functions can be obtained:
wherein Enc [ L ]A(DA,DB；θA,θB)]Represents the fraction of the loss involved by party a only;
Enc[LB(DA,DB；θA,θB)]represents the fraction of the loss involved by party B only;
Enc[LA∩B(DA,DB；θA,θB)]indicates that A and B together involve a loss part;
the formula is shown in 4.5 and 4.6:
according to the formulas 4.4, 4.5 and 4.6, the following results can be obtained:
Enc[L(DA,DB；θA,θB)]＝Enc[LA(DA,DB；θA,θB)]+Enc[LB(DA,DB；θA,θB)]+ Enc[LA∩B(DA,DB；θA,θB)] (4.7)
let Enc [ L (D)A,DB；θA,θB)]To thetaACalculating partial derivatives, we can get:
same pair of thetaBDerivation, as shown in equation 4.9
Note that for thetaAAnd thetaBAll rely on their common part for the calculation of the partial derivatives
Thus, it is possible to provideWhen updating the gradient, party B will calculate the local gradient first, then send the common portion to party a, and party a can then calculate the pair θAOf the gradient of (c).
In addition, because the calculation processes are all in an encryption state, final loss and decryption of the gradient are all carried out on the central server.
The client sends the sample data to be predicted to the central server, the central server copies the request and respectively transmits the request to each participant, then each participant calculates local results and transmits the local results back to the central server, and the central server decrypts the local results to obtain the credit score of the user.
Specifically, the user-related data transmitted by the client is represented by Enc [ y ];
wherein,
representing a data dimension belonging to party a;
the end-side model inference process of party a can be represented by equation 4.10:
wherein,
representing the private parameters of party a.
The peer-side reasoning process of the participant B in the same way is as follows in formula 4.11:
finally, each participant will reason the end-side reasoning result, namely Enc [ u ]A]And Enc [ u ]B]And transmitting to the central server. The summary process of the central server is shown in equation 4.12:
the decoding of the credit score is then achieved by Dec [ y ] (Dec [ y ] refers to decrypting the Enc [ y ] data). And finally, transmitting the credit score to the client, and making a final credit decision by the client according to the credit score.
Gradient data (formula 4.8, formula 4.9, formula 4.12) of local training of the participants and data processed by the federal learning module 4 are sent to the blockchain module 5.
And the block chain module 5 is used for storing the result of the federal learning module training to a block chain, calculating the participating party with a high contribution degree by using a workload certification algorithm of the block chain, exciting the prediction effect of the model on the participating party with the high contribution degree by using a reward mechanism of the block chain, checking the prediction result of the model at each stage by the participating party with the high contribution degree, and ensuring that a mechanism with more data can obtain a better model effect so as to embody the contribution degree of the mechanism to the model.
The system provided by the embodiment of the invention realizes the sharing of the user loan data of the internet company and the bank user loan data, and achieves the effect of carrying out accurate wind control on the user.
Meanwhile, the invention also provides a bank wind control device based on the block chain, as shown in fig. 4, comprising:
a data transceiver module 401, configured to receive sample data provided by each sample data participant through a block chain;
a sample alignment module 402, configured to perform data alignment processing on the received sample data of each sample data participant;
the model training module 403 is configured to perform model training on a preset bank wind control prediction model by using sample data after data alignment processing;
and the prediction module 404 is configured to process the received bank wind control data by using the bank wind control prediction model after the model training to generate a bank wind control result.
In the embodiment of the present invention, the apparatus further includes:
the key generation module is used for generating a public key and a private key by utilizing a preset encryption algorithm;
and the generated public key is sent to each sample data participant through the block chain by the data transceiver module.
In the embodiment of the present invention, the apparatus further includes:
the Hash mapping module is used for carrying out Hash mapping processing on the sample ID;
and the encryption module is used for encrypting the sample ID after the Hash mapping process by using the public key.
In an embodiment of the present invention, the sample alignment module includes:
the decryption unit is used for decrypting the received sample data by using the private key to generate a sample ID after Hash mapping;
and the matching alignment unit is used for matching the sample data of each participant according to the decrypted sample ID after the Hash mapping processing so as to finish the data alignment processing.
In the embodiment of the invention, the model training module utilizes the sample data after the alignment processing to carry out federal training on a preset bank wind control prediction model so as to generate the trained bank wind control prediction model.
For those skilled in the art, the implementation of the bank wind control device based on the blockchain provided by the present invention can be clearly understood through the description of the foregoing embodiments, and details are not repeated herein.
It should be noted that the bank wind control method and device based on the block chain disclosed by the invention can be used for bank wind control in the financial field and can also be used for wind control in any field except the financial field, and the application field of the bank wind control method and device based on the block chain disclosed by the invention is not limited.
The present embodiment also provides an electronic device, which may be a desktop computer, a tablet computer, a mobile terminal, and the like, but is not limited thereto. In this embodiment, the electronic device may refer to the embodiments of the method and the apparatus, and the contents thereof are incorporated herein, and repeated descriptions are omitted.
Fig. 5 is a schematic block diagram of a system configuration of an electronic apparatus 600 according to an embodiment of the present invention. As shown in fig. 5, the electronic device 600 may include a central processor 100 and a memory 140; the memory 140 is coupled to the central processor 100. Notably, this diagram is exemplary; other types of structures may also be used in addition to or in place of the structure to implement telecommunications or other functions.
In one embodiment, the bank wind control function based on block chains may be integrated into the central processor 100. The central processor 100 may be configured to control as follows:
receiving sample data provided by each sample data participant through a block chain;
carrying out data alignment processing on the received sample data of each sample data participant;
carrying out model training on a preset bank wind control prediction model by using sample data after data alignment processing;
and processing the received bank wind control data by using the bank wind control prediction model after the model training to generate a bank wind control result.
In another embodiment, the bank wind control device based on the block chain may be configured separately from the central processor 100, for example, the bank wind control device based on the block chain may be configured as a chip connected to the central processor 100, and the bank wind control function based on the block chain is realized by the control of the central processor.
As shown in fig. 5, the electronic device 600 may further include: communication module 110, input unit 120, audio processing unit 130, display 160, power supply 170. It is worthy to note that electronic device 600 is also not required to include all of the components shown in FIG. 5; furthermore, the electronic device 600 may also comprise components not shown in fig. 5, which may be referred to in the prior art.
As shown in fig. 5, the central processor 100, sometimes referred to as a controller or operational control, may include a microprocessor or other processor device and/or logic device, the central processor 100 receiving input and controlling the operation of the various components of the electronic device 600.
The memory 140 may be, for example, one or more of a buffer, a flash memory, a hard drive, a removable media, a volatile memory, a non-volatile memory, or other suitable device. The information relating to the failure may be stored, and a program for executing the information may be stored. And the cpu 100 may execute the program stored in the memory 140 to realize information storage or processing, etc.
The input unit 120 provides input to the cpu 100. The input unit 120 is, for example, a key or a touch input device. The power supply 170 is used to provide power to the electronic device 600. The display 160 is used to display an object to be displayed, such as an image or a character. The display may be, for example, an LCD display, but is not limited thereto.
The memory 140 may be a solid state memory such as Read Only Memory (ROM), Random Access Memory (RAM), a SIM card, or the like. There may also be a memory that holds information even when power is off, can be selectively erased, and is provided with more data, an example of which is sometimes called an EPROM or the like. The memory 140 may also be some other type of device. Memory 140 includes buffer memory 141 (sometimes referred to as a buffer). The memory 140 may include an application/function storage section 142, and the application/function storage section 142 is used to store application programs and function programs or a flow for executing the operation of the electronic device 600 by the central processing unit 100.
The memory 140 may also include a data store 143, the data store 143 for storing data, such as contacts, digital data, pictures, sounds, and/or any other data used by the electronic device. The driver storage portion 144 of the memory 140 may include various drivers of the electronic device for communication functions and/or for performing other functions of the electronic device (e.g., messaging application, address book application, etc.).
The communication module 110 is a transmitter/receiver 110 that transmits and receives signals via an antenna 111. The communication module (transmitter/receiver) 110 is coupled to the central processor 100 to provide an input signal and receive an output signal, which may be the same as in the case of a conventional mobile communication terminal.
Based on different communication technologies, a plurality of communication modules 110, such as a cellular network module, a bluetooth module, and/or a wireless local area network module, may be provided in the same electronic device. The communication module (transmitter/receiver) 110 is also coupled to a speaker 131 and a microphone 132 via an audio processor 130 to provide audio output via the speaker 131 and receive audio input from the microphone 132 to implement general telecommunications functions. Audio processor 130 may include any suitable buffers, decoders, amplifiers and so forth. In addition, the audio processor 130 is also coupled to the central processor 100, so that it is possible to record sound locally through the microphone 132, and so that sound stored locally can be played through the speaker 131.
Embodiments of the present invention further provide a computer-readable program, where when the program is executed in an electronic device, the program causes a computer to execute the bank wind control method based on a block chain in the electronic device according to the above embodiments.
An embodiment of the present invention further provides a storage medium storing a computer readable program, where the computer readable program enables a computer to execute the bank wind control based on the blockchain in an electronic device.
The preferred embodiments of the present invention have been described above with reference to the accompanying drawings. The many features and advantages of the embodiments are apparent from the detailed specification, and thus, it is intended by the appended claims to cover all such features and advantages of the embodiments that fall within the true spirit and scope thereof. Further, since numerous modifications and changes will readily occur to those skilled in the art, it is not desired to limit the embodiments of the invention to the exact construction and operation illustrated and described, and accordingly, all suitable modifications and equivalents may be resorted to, falling within the scope thereof.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The principle and the implementation mode of the invention are explained by applying specific embodiments in the invention, and the description of the embodiments is only used for helping to understand the method and the core idea of the invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (12)
1. A bank wind control method based on a block chain is characterized by comprising the following steps:
receiving sample data provided by each sample data participant through a block chain;
carrying out data alignment processing on the received sample data of each sample data participant;
carrying out model training on a preset bank wind control prediction model by using sample data after data alignment processing;
and processing the received bank wind control data by using the bank wind control prediction model after the model training to generate a bank wind control result.
2. The banking wind control method based on the blockchain according to claim 1, wherein before receiving the sample data provided by each sample data participant through the blockchain, the banking wind control method comprises:
generating a public key and a private key by using a preset encryption algorithm;
and sending the generated public key to each sample data participant through the block chain.
3. The banking wind control method based on the blockchain according to claim 2, wherein before receiving the sample data provided by each sample data participant through the blockchain, the banking wind control method further comprises:
carrying out Hash mapping processing on the sample ID;
and encrypting the sample ID after the Hash mapping process by using the public key.
4. The banking wind control method based on the block chain according to claim 3, wherein the performing data alignment processing on the received sample data of each sample data participant comprises:
decrypting the received sample data by using the private key to generate a sample ID after Hash mapping;
and matching the sample data of each participant according to the decrypted sample ID after the Hash mapping process so as to finish the data alignment process.
5. The method for bank wind control based on the block chain according to claim 1, wherein the model training of the preset bank wind control prediction model by using the sample data after the data alignment process comprises:
and carrying out federal training on a preset bank wind control prediction model by using the sample data after alignment processing to generate a trained bank wind control prediction model.
6. A bank wind control device based on a block chain is characterized by comprising:
the data receiving and sending module is used for receiving the sample data provided by each sample data participant through the block chain;
the sample alignment module is used for carrying out data alignment processing on the received sample data of each sample data participant;
the model training module is used for carrying out model training on a preset bank wind control prediction model by using the sample data after the data alignment processing;
and the prediction module is used for processing the received bank wind control data by using the bank wind control prediction model after the model training to generate a bank wind control result.
7. The blockchain-based bank wind control device according to claim 6, wherein the device further comprises:
the key generation module is used for generating a public key and a private key by utilizing a preset encryption algorithm;
and the generated public key is sent to each sample data participant through the block chain by the data transceiver module.
8. The blockchain-based bank wind control apparatus of claim 7, wherein the apparatus further comprises:
the Hash mapping module is used for carrying out Hash mapping processing on the sample ID;
and the encryption module is used for encrypting the sample ID after the Hash mapping process by using the public key.
9. The blockchain-based bank wind control device according to claim 8, wherein the sample alignment module includes:
the decryption unit is used for decrypting the received sample data by using the private key to generate a sample ID after Hash mapping;
and the matching alignment unit is used for matching the sample data of each participant according to the decrypted sample ID after the Hash mapping processing so as to finish the data alignment processing.
10. The bank wind control device based on the block chain according to claim 6, wherein the model training module performs federal training on a preset bank wind control prediction model by using the sample data after the alignment processing to generate the trained bank wind control prediction model.
11. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method of any of claims 1 to 5 when executing the computer program.
12. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program for executing the method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110696871.1A CN113554505A (en) | 2021-06-23 | 2021-06-23 | Bank wind control method and device based on block chain |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110696871.1A CN113554505A (en) | 2021-06-23 | 2021-06-23 | Bank wind control method and device based on block chain |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113554505A true CN113554505A (en) | 2021-10-26 |
Family
ID=78102356
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110696871.1A Pending CN113554505A (en) | 2021-06-23 | 2021-06-23 | Bank wind control method and device based on block chain |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113554505A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111461874A (en) * | 2020-04-13 | 2020-07-28 | 浙江大学 | Credit risk control system and method based on federal mode |
| CN112685783A (en) * | 2021-01-05 | 2021-04-20 | 西安电子科技大学 | Data sharing method supporting privacy protection in financial permission block chain |
| CN112949760A (en) * | 2021-03-30 | 2021-06-11 | 平安科技（深圳）有限公司 | Model precision control method and device based on federal learning and storage medium |
-
2021
- 2021-06-23 CN CN202110696871.1A patent/CN113554505A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111461874A (en) * | 2020-04-13 | 2020-07-28 | 浙江大学 | Credit risk control system and method based on federal mode |
| CN112685783A (en) * | 2021-01-05 | 2021-04-20 | 西安电子科技大学 | Data sharing method supporting privacy protection in financial permission block chain |
| CN112949760A (en) * | 2021-03-30 | 2021-06-11 | 平安科技（深圳）有限公司 | Model precision control method and device based on federal learning and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 胡方: "《互联网金融创新创业教程》", 31 May 2021, 武汉大学出版社, pages: 58 - 69 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113159327B (en) | Model training method and device based on federal learning system and electronic equipment | |
| CN110245510B (en) | Method and apparatus for predicting information | |
| CN113032840B (en) | Data processing method, device, equipment and computer readable storage medium | |
| KR102145701B1 (en) | Prevent false display of input data by participants in secure multi-party calculations | |
| CN110955907A (en) | Model training method based on federal learning | |
| CN111989893A (en) | Chain of proof and decomposition | |
| US11410081B2 (en) | Machine learning with differently masked data in secure multi-party computing | |
| CN112347500B (en) | Machine learning method, device, system, equipment and storage medium of distributed system | |
| CN113127916A (en) | Data set processing method, data processing device and storage medium | |
| CN113609781A (en) | Automobile production mold optimization method, system, equipment and medium based on federal learning | |
| CN113722753B (en) | Private data processing method, device and system based on blockchain | |
| CN111709051A (en) | Data processing method, device and system, computer storage medium and electronic equipment | |
| CN112818369A (en) | Combined modeling method and device | |
| CN114971841A (en) | Risk management method, risk model training method, device, equipment and medium | |
| CN114547658A (en) | Data processing method, device, equipment and computer readable storage medium | |
| CN114301677A (en) | Key negotiation method, device, electronic equipment and storage medium | |
| CN114006769A (en) | Model training method and device based on horizontal federal learning | |
| CN112949866A (en) | Poisson regression model training method and device, electronic equipment and storage medium | |
| CN116502732B (en) | Federal learning method and system based on trusted execution environment | |
| CN113807157A (en) | Method, device and system for training neural network model based on federal learning | |
| CN109472149B (en) | Data operation method based on block chain | |
| CN116032639A (en) | Message pushing method and device based on privacy calculation | |
| CN113554505A (en) | Bank wind control method and device based on block chain | |
| CN115225367A (en) | Data processing method, device, computer equipment, storage medium and product | |
| CN113487423A (en) | Personal credit risk prediction model training method and 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 |