WO2022100382A1 - 一种基于区块链的信贷推荐方法、设备及存储介质 - Google Patents

一种基于区块链的信贷推荐方法、设备及存储介质 Download PDF

Info

Publication number
WO2022100382A1
WO2022100382A1 PCT/CN2021/124735 CN2021124735W WO2022100382A1 WO 2022100382 A1 WO2022100382 A1 WO 2022100382A1 CN 2021124735 W CN2021124735 W CN 2021124735W WO 2022100382 A1 WO2022100382 A1 WO 2022100382A1
Authority
WO
WIPO (PCT)
Prior art keywords
credit
user
product
label
recommended
Prior art date
Application number
PCT/CN2021/124735
Other languages
English (en)
French (fr)
Inventor
李思毅
Original Assignee
深圳壹账通智能科技有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 深圳壹账通智能科技有限公司 filed Critical 深圳壹账通智能科技有限公司
Publication of WO2022100382A1 publication Critical patent/WO2022100382A1/zh

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/27—Replication, distribution or synchronisation of data between databases or within a distributed database system; Distributed database system architectures therefor
    • 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
    • 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
    • G06Q20/00—Payment architectures, schemes or protocols
    • G06Q20/04—Payment circuits
    • G06Q20/06—Private payment circuits, e.g. involving electronic currency used among participants of a common payment scheme
    • G06Q20/065—Private payment circuits, e.g. involving electronic currency used among participants of a common payment scheme using e-cash
    • 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
    • G06Q20/00—Payment architectures, schemes or protocols
    • G06Q20/38—Payment protocols; Details thereof
    • G06Q20/382—Payment protocols; Details thereof insuring higher security of transaction
    • G06Q20/3829—Payment protocols; Details thereof insuring higher security of transaction involving key management
    • 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
    • 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
    • G06Q40/04—Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange

Definitions

  • the present application belongs to the field of blockchain technology, and specifically relates to a method, device and storage medium for credit recommendation based on blockchain.
  • the main way to realize the credit business is: the user prepares sufficient materials to negotiate with the business personnel in the business hall of the bank, and submits the materials; and then waits for the bank's approval.
  • the approval process takes about several working days and the delay is long. ; After the approval is successful, the user will go through the loan contract signing and other procedures, and carry out capital turnover; finally, the user will repay according to the selected repayment method, and after the repayment is completed, go to the loan bank to go through the procedures such as taking back the mortgage materials.
  • the entire loan process is complicated, the review time is long, and the labor cost is high, and the final approval result sometimes does not match the facts.
  • This application proposes a blockchain-based credit recommendation method, equipment and storage medium, which can improve the approval speed of credit products and reduce labor costs in the approval process.
  • the embodiment of the first aspect of this application proposes a blockchain-based credit recommendation method, which is applied to a blockchain node device, including: acquiring a user's credit request, where the credit request includes the user's credit index, credit screening conditions and User identity information; according to the credit index, the user identity information and the credit screening conditions, the credit product to be recommended and the credit application conditions corresponding to the credit product are matched from the preset credit product library; Whether the user identity information meets the credit application conditions; if so, recommend the credit product to the user.
  • An embodiment of the second aspect of the present application provides a block chain node device, including: an acquisition module for acquiring a user's credit request, where the credit request includes the user's credit index, credit screening conditions and user identity information; matching a module for matching the credit product to be recommended and the credit application conditions corresponding to the credit product from the preset credit product library according to the credit index, the user identity information and the credit screening conditions; the judgment module, It is used for judging whether the user identity information satisfies the credit application condition; the recommendation module is used for the judging module to determine that the user identity information satisfies the credit application condition, and then recommend the credit product to the user.
  • An embodiment of the third aspect of the present application provides a computer device, including a memory and a processor, where computer-readable instructions are stored in the memory, and when the computer-readable instructions are executed by the processor, cause the processing
  • the device executes the blockchain-based credit recommendation method described in the first aspect, the method includes: obtaining a user's credit request, where the credit request includes the user's credit index, credit screening conditions and user identity information; index, the user identity information and the credit screening conditions, match the credit product to be recommended and the credit application conditions corresponding to the credit product from the preset credit product library; determine whether the user identity information satisfies the credit Application conditions; if yes, recommend the credit product to the user.
  • Embodiments of the fourth aspect of the present application provide a storage medium storing computer-readable instructions, and when the computer-readable instructions are executed by one or more processors, cause the one or more processors to execute the above-mentioned first aspect
  • the blockchain-based credit recommendation method includes: acquiring a user's credit request, the credit request including the user's credit index, credit screening conditions and user identity information; according to the credit index, the user identity information and the credit screening conditions, match the credit product to be recommended and the credit application conditions corresponding to the credit product from the preset credit product library; determine whether the user identity information meets the credit application conditions; if so, The credit product is then recommended to the user.
  • the embodiment of the present application realizes automatic recommendation of credit products in the blockchain system, and the matching speed is fast.
  • the transaction volume of credit products is increased, the lending process is automated, the review time is shortened, and the final approval result is less than the fact.
  • FIG. 1 shows a schematic flowchart of a blockchain-based credit recommendation method provided by an embodiment of the present application.
  • FIG. 2 shows a schematic structural diagram of a blockchain-based credit recommendation device provided by an embodiment of the present application.
  • FIG. 3 shows a schematic structural diagram of a computer device provided by an embodiment of the present application.
  • FIG. 4 shows a schematic diagram of a storage medium provided by an embodiment of the present application.
  • This application may relate to the field of artificial intelligence technology, for example, relevant data may be acquired and processed based on artificial intelligence technology.
  • the technical solution of the present application can be applied to various credit product recommendation scenarios, such as credit product recommendation in a digital medical scenario, or credit product recommendation in a financial technology scenario.
  • the user to be recommended involved in this application may be a user in a medical system, or may be a user in a financial system, or other users.
  • Some embodiments of the present application provide a blockchain-based credit recommendation method.
  • the user Before a user conducts a credit product transaction in a blockchain system, the user first needs to register in the blockchain node device of the system. During the registration process The blockchain node device will assign a private key and a public key to the user. Users identify one or more of their account identification (name or nickname, etc.), household registration information, age, occupation information, real estate information, car information, insurance policy information, debt information, credit card information, legal action information, loan information, etc. As its own user identity information, upload the user identity information to the blockchain node device, and the blockchain node device stores the user identity information. Before storing the user identity information, encryption can be performed first, and the ciphertext of the user identity information is stored in the blockchain node device.
  • the product label selected by the user is set as the user's preference label, and the preference label is stored in the user identity information.
  • the product label can be investment risk level (low, medium or high), the field to which the credit product belongs, product type, term (short-term, medium-term or long-term, etc.), amount, credit service method (mortgage or pledge, etc.), loan object Wait.
  • the preference label can include a label name and a preference index, where the label name can include the investment risk level, the field to which the credit product belongs, product type, term, amount, credit service method, loan object, etc.
  • the preference index corresponding to the label name is used to indicate that the user chooses The proportion of the factor corresponding to the label name in the credit product.
  • the preference index is related to parameters such as whether to conclude a transaction, the transaction amount, and the repetition of the screening tags within a certain period of time. The higher the preference index is.
  • the blockchain node device also sets a credit index for the user, and sets the value of the credit index as a preset initial value, which can be 60 or 65. Then, the correspondence between the user's credit index and the user's identity information is stored.
  • the value range of the credit index may be 0-100, and the user's credit index may be updated subsequently according to the user's transaction record of the credit product.
  • the user After the user registers in the blockchain credit trading system, when the user wants to select a credit product for trading, the user sends a credit browsing request to the blockchain node device through a terminal such as his mobile phone or computer, and the credit request includes the user's name. or account identifiers such as nicknames and credit screening criteria submitted by the user.
  • the credit screening conditions include demand conditions such as the loan amount, interest rate, term, and field to which the credit product belongs, etc. entered by the user.
  • account identifiers such as the user's name or nickname belong to the user's private data.
  • the embodiment of the present application uses the user's public key to The user's name or nickname and other account identifiers are encrypted, and the encrypted ciphertext, the user's public key and the credit screening conditions are carried in the above credit request.
  • the blockchain node device recommends credit products for the user through the following steps 101-104.
  • Step 101 Acquire a user's credit request, where the credit request includes the user's credit index, credit screening conditions and user identity information.
  • the blockchain node device obtains the user identity information and credit index corresponding to the account identifier according to the account identifier included in the credit request.
  • the credit request includes the ciphertext of the account identifier such as the user's name or nickname, the user's public key, and credit screening conditions.
  • the blockchain node device After the blockchain node device obtains the user's credit request, it first verifies whether the user is a legitimate user based on the user's public key. Specifically, the blockchain node device operates on the user's public key through a preset asymmetric encryption algorithm to obtain the user address corresponding to the public key.
  • the asymmetric encryption algorithm may be RSA, ECC (Elliptic Curve Cryptography, elliptic curve encryption algorithm) and the like.
  • the blockchain node device encrypts the user's account ID with the public key of the blockchain node device to obtain the ciphertext, and the blockchain node device is called the first blockchain node device, the first blockchain node device.
  • the node device can be a server corresponding to a supplier that provides credit products such as a bank or a credit company. Then the first blockchain node device sends the ciphertext and the public key of the first blockchain node device to the second blockchain node device of the block storing the user-related information, and the user-related information may include the user's account ID , user identity information, user history related to credit products, etc.
  • the second blockchain node device first verifies whether the first blockchain node device has the authority to view user-related information according to the public key of the first blockchain node device. Specifically, the second blockchain node device performs an operation on the public key of the first blockchain node device through a preset asymmetric encryption algorithm to obtain a node address corresponding to the first blockchain node device. Determine whether the address of the node corresponding to the public key is the same as the address of the node that sent the ciphertext and public key. If not, it is determined that the first blockchain node device does not have the authority to view user-related information, and will not respond to the first block. The query request of the chain node device.
  • the first blockchain node device determines that the first blockchain node device has the authority to view user-related information, obtain the private key corresponding to the public key, and obtain the user's account by decrypting the ciphertext sent by the first blockchain node device through the private key.
  • ID according to the account ID, obtain the user identity information and credit index corresponding to the account ID from the block storing the user-related information, and return the obtained user ID information and credit index to the first blockchain node device.
  • Step 102 According to the credit index, user identity information and credit screening conditions, match the credit product to be recommended and the credit application conditions corresponding to the credit product from the preset credit product library.
  • steps 1021-1024 are used to match credit products.
  • Step 1021 Obtain the user's preference tag from the user identity information.
  • the preference label can include a label name and a preference index, where the label name can include the investment risk level, the field to which the credit product belongs, product type, term, amount, credit service method, loan object, etc.
  • the preference index corresponding to the label name is used to indicate that the user chooses The proportion of the factor corresponding to the label name in the credit product.
  • Step 1022 Determine the user's demand label according to the credit screening conditions.
  • the credit screening conditions include demand conditions such as the loan amount, interest rate, term, and field to which the credit product belongs, etc. entered by the user.
  • the blockchain node device obtains the keywords in the credit screening conditions set by the user, and determines the user's demand label according to these keywords.
  • the demand label may include the investment risk level, the field to which the credit product belongs, the product type, the term, the amount, the credit service method, the loan object, and the like.
  • Step 1023 Acquire a plurality of candidate credit products corresponding to the credit index from the preset credit product library according to the credit index and the data authority level of each credit product in the preset credit product library.
  • the blockchain node device is preconfigured with a preset credit product library
  • the preset credit product library includes a large number of credit products
  • each credit product includes product introduction, credit company image, credit manager Information, corresponding credit application conditions, product labels and data permission levels, etc.
  • the credit application conditions are used to judge whether the user meets the requirements of the credit product.
  • the product label includes the investment risk level, the field to which the credit product belongs, product type, term, amount, credit service method, loan object, etc.
  • the data authority level specifies the scope of the credit index applicable to credit products.
  • the data authority level is related to the loan cost, lending interest rate, repayment method, expected return, and term. The lower the loan cost, the lower the lending rate, and the longer the term, the data High permission level.
  • the blockchain node device determines the credit index range specified by the data authority level includes multiple credit products of the user's credit index, and the determined multiple credit products. Credit products are multiple candidate credit products corresponding to the user's credit index. The higher the user's credit index, the higher the corresponding data permission level, and the more credit products that can be accessed or selected.
  • Step 1024 According to the preference tag, the demand tag and the product tag of each candidate credit product, screen out the credit product to be recommended from the multiple candidate credit products.
  • each product label of the credit product is compared with the user's preference label and demand label respectively, and the user's preference label or demand is determined from the product label of the credit product.
  • For product labels with consistent labels count the number of labels corresponding to the consistent product labels, and determine the number of labels as the label matching degree corresponding to the credit product. In this way, the label matching degree corresponding to each candidate credit product is obtained respectively.
  • One or more to-be-recommended credit products whose tag matching degree is greater than a preset value are selected from the plurality of candidate credit products.
  • the preset value can be 4, 5 or 6 etc.
  • Step 103 Determine whether the user identity information satisfies the credit application conditions.
  • step 102 After screening out one or more credit products to be recommended from the preset credit product library through step 102, for each credit product to be recommended, it is determined whether the user satisfies the credit product to be recommended through the following operations of steps 1031 and 1032 Corresponding credit application conditions.
  • Step 1031 Obtain the user's identity attribute information from the user's identity information.
  • the identity attribute information includes household registration information, age, occupation information, real estate information, automobile information, insurance policy information, debt information, credit card information, legal action information, and loan information. one or more.
  • the loan information may include online loan information or private loan information.
  • the identity attribute information may also include credit report information, credit card information, sesame score information, and the like.
  • Step 1032 Determine whether the identity attribute information satisfies the credit application conditions; if so, determine that the user identity information satisfies the credit application conditions.
  • the credit attributes can include household registration, age, occupation, real estate, automobile, insurance policy, credit report, debt, credit card, legal proceedings, sesame points, online loan , private lending, etc.
  • the blockchain node device compares each identity attribute information in the user identity information with the corresponding credit attributes in the credit application conditions corresponding to the credit product to be recommended, and determines whether each identity attribute information meets the corresponding credit application conditions. Requirements for credit attributes, such as determining whether the user's age meets the age requirements in the credit application conditions, and determining whether the user's credit report meets the relevant requirements for credit reporting in the credit application conditions, etc.
  • the user's user identity information is determined to meet the credit application conditions.
  • Step 104 If yes, recommend the credit product to the user.
  • the credit product whose user identity information determined in step 103 meets the credit application conditions is recommended to the user.
  • the blockchain node device obtains the product introduction, credit company image, credit manager information and other credit product information of these credit products from the preset credit product library, and sends the obtained credit product information to the user's terminal.
  • the terminal receives the credit product information sent by the blockchain node device, and displays the credit product information, so that the user can select the credit product that needs to be traded from these credit products.
  • the multiple credit products are sorted through the operations of the following steps 1041 and 1042 .
  • Step 1041 Calculate the label matching degree corresponding to each credit product to be recommended according to the product label of each credit product to be recommended and the user's preference label and demand label.
  • the calculation method of the label matching degree of each credit product is the same as that described in step S1024, and is not repeated here.
  • Step 1042 Rank each credit product to be recommended according to the label matching degree of each credit product to be recommended.
  • the multiple credit products to be recommended are sorted according to the order of the label matching degree from the smallest, and then the sorted multiple credit products are recommended to the user.
  • the ranking may also be based on the preference index of the preference label included in the product label of the credit product to be recommended, and the credit product with a higher preference index will be prioritized for ranking.
  • sorting multiple credit products according to the matching degree between the credit products and the user's preferences and needs can make the credit products in the front more in line with the user's preferences and needs. , which is more informative to users and can increase the transaction volume of credit products.
  • the user can select one or more credit products to apply for transaction.
  • the blockchain node device receives an application request for a credit product sent by the user's terminal, the blockchain node device will send the user
  • the user identity information is sent to the credit manager corresponding to the credit product for review.
  • the higher the user's credit index the more likely the data of the user's identity information is hidden.
  • the credit product manager reviews only whether the application conditions are met is displayed, which is more conducive to protecting the user's identity information. The lower the user's credit index is, during transaction review, it may be necessary to display some credit data and some data of historical transactions for review and evaluation.
  • the blockchain node device After completing the transaction, the blockchain node device will generate a corresponding transaction record, which includes the user's private key, public key, signature, encrypted user identity information, encrypted transaction information, timestamp and other basic information, as well as user requirements. , credit screening conditions, credit cost, interest rate, income, whether to repay, repayment time, repayment method, whether on time and other transaction information. This transaction record is stored in the blockchain node device.
  • the user's preference label is also adjusted according to the credit product for which the transaction is concluded.
  • the preference label may be adjusted through the operations of the following steps S1-S4.
  • Step S1 Obtain the product label of the credit product for which the user has reached a transaction.
  • the blockchain node device obtains the product label of the credit product that has reached the transaction from the user's corresponding transaction record.
  • Step S2 Determine a product label matching the user's demand label from the obtained product label.
  • a product label consistent with the user's demand label is determined from the product labels of the credit product for which the transaction is concluded.
  • Step S3 Set the determined product label as the user's preference label.
  • Step S4 Store the set preference tag in the user identity information corresponding to the user.
  • the user's preference tag is adjusted according to the credit products that the user has reached a transaction with, so that the subsequent credit products are recommended and the credit products to be recommended are sorted according to the user's preference tag, which can make the recommended credit products more in line with the user's preference.
  • the user's preference tag may also be adjusted through the operations of the following steps S5-S7.
  • Step S5 within a preset time period, record the repeatability of each product label that matches the user's demand label.
  • the preset duration can be one week, one month or one quarter, etc.
  • Step S6 Set the product label whose repetition degree is greater than the preset threshold as the user's temporary preference label.
  • the preset threshold can be 8, 10 or 20, etc.
  • the embodiment of the present application does not limit the specific value of the preset threshold, and in practical applications, the value of the preset threshold may be set according to requirements.
  • the blockchain node device stores the set temporary preference tag in the user's corresponding user identity information.
  • the setting of the temporary preference tag has a certain timeliness, the duration of validity corresponding to the temporary preference tag is set, and the utility time of the temporary preference tag is timed.
  • Step S7 when the time period corresponding to the temporary preference label arrives, remove the temporary preference label from all preference labels of the user.
  • the temporary preference label is removed from all preference labels included in the user identity information.
  • the product labels with high repetition in the preset time period are selected as the temporary preference labels of users, and the characteristics of user preferences changing with time are fully combined to make the preference labels set more in line with the actual preferences of users, thereby improving the relationship between recommended credit products and credit products.
  • the matching degree of user's actual preference is selected as the temporary preference labels of users, and the characteristics of user preferences changing with time are fully combined to make the preference labels set more in line with the actual preferences of users, thereby improving the relationship between recommended credit products and credit products.
  • the value of the credit index corresponding to the user is a preset initial value, and then the value of the credit index can be adjusted according to the user's credit transaction situation , and the credit index is adjusted specifically through the operations of the following steps S8 and S9.
  • Step S8 Acquire a plurality of credit parameters from the transaction records of the credit product.
  • the above-mentioned credit parameters include whether to repay, the repayment time, whether the repayment is on time, etc.
  • Step S9 Reset the user's credit index according to the multiple credit parameters and the weight corresponding to each credit parameter.
  • the weight corresponding to each credit parameter is preset in the blockchain node device. According to each credit parameter obtained from the transaction record, the corresponding value of each credit parameter is determined. If the user has not repaid, the value of the credit parameter "repayment or not” can be 0. If the user has repaid, then The value of the credit parameter "repayment or not” can be 1; if the user's repayment time is earlier than the specified time, the value of the credit parameter "repayment time” can be 8. If the user's repayment time is exactly the specified time, then The value of the credit parameter "repayment time” can be 5. If the user's repayment time is later than the specified time, the value of the credit parameter "repayment time” can be 2 and so on.
  • each credit parameter After the value of each credit parameter is determined, according to the value and weight of each credit parameter, weighted summation is performed on all credit parameters to obtain the user's new credit index, and the previously stored credit index of the user is replaced by the new credit index.
  • the embodiment of the present application realizes automatic recommendation of credit products in the blockchain system, and the matching speed is fast. Screening and recommending credit products based on the user's credit index, preferences, needs, etc., improves the matching accuracy of the final recommended credit products with the user's preferences and needs.
  • the blockchain can automatically determine whether the user meets the credit application conditions for credit products based on the user's household registration, age, occupation, assets, liabilities and other identity information, which can improve the approval speed of credit products and reduce labor costs in the approval process.
  • an embodiment of the present application provides a blockchain node device, which is used to execute the blockchain-based credit recommendation method described in any of the foregoing embodiments, including: an acquisition module 201, used to obtain the user's credit request, the credit request includes the user's credit index, credit screening conditions and user identity information; the matching module 202 is used for obtaining a credit product library from a preset credit product library according to the credit index, user identity information and credit screening conditions The credit product to be recommended and the credit application conditions corresponding to the credit product are matched in the process; the judgment module 203 is used for judging whether the user identity information meets the credit application conditions; the recommendation module 204 is used for the judgment module to judge that the user identity information meets the credit application conditions, Then recommend credit products to users.
  • an acquisition module 201 used to obtain the user's credit request, the credit request includes the user's credit index, credit screening conditions and user identity information
  • the matching module 202 is used for obtaining a credit product library from a preset credit product library according to the credit index, user
  • the matching module 202 is used to obtain the user's preference label from the user identity information; determine the user's demand label according to the credit screening conditions; Obtain multiple candidate credit products corresponding to the credit index in the product library; according to the preference label, the demand label and the product label of each candidate credit product, the credit product to be recommended is selected from the multiple candidate credit products.
  • the judgment module 203 is used to obtain the user's identity attribute information from the user's identity information, and the identity attribute information includes household registration information, age, occupation information, real estate information, automobile information, insurance policy information, debt information, credit card information, legal action information, loan information One or more of the information; determine whether the identity attribute information meets the credit application conditions; if so, determine that the user identity information meets the credit application conditions.
  • the device further includes: a sorting module, configured to calculate each credit product to be recommended according to the product label of each credit product to be recommended and the user's preference label and demand label if there are multiple credit products to be recommended Corresponding label matching degree; sort each credit product to be recommended according to the label matching degree of each credit product to be recommended.
  • a sorting module configured to calculate each credit product to be recommended according to the product label of each credit product to be recommended and the user's preference label and demand label if there are multiple credit products to be recommended Corresponding label matching degree; sort each credit product to be recommended according to the label matching degree of each credit product to be recommended.
  • the device further includes: a preference label setting module for acquiring the product label of the credit product that the user has reached a transaction; determining the product label matching the user's demand label from the product label; setting the determined product label as the user's preference label ; Store the preference tag in the user's corresponding user identity information.
  • a preference label setting module for acquiring the product label of the credit product that the user has reached a transaction; determining the product label matching the user's demand label from the product label; setting the determined product label as the user's preference label ; Store the preference tag in the user's corresponding user identity information.
  • the device further includes: a temporary label management module, used for recording the repetition degree of each product label matching the user's demand label within a preset time period; setting the product label whose repetition degree is greater than a preset threshold as the user's temporary preference label; when the aging time corresponding to the temporary preference label arrives, remove the temporary preference label from all preference labels of the user.
  • a temporary label management module used for recording the repetition degree of each product label matching the user's demand label within a preset time period; setting the product label whose repetition degree is greater than a preset threshold as the user's temporary preference label; when the aging time corresponding to the temporary preference label arrives, remove the temporary preference label from all preference labels of the user.
  • the device further includes: a reset module for acquiring multiple credit parameters from the transaction records of the credit product; and resetting the user's credit index according to the multiple credit parameters and the corresponding weight of each credit parameter.
  • the embodiment of the present application realizes automatic recommendation of credit products in the blockchain system, and the matching speed is fast. Screening and recommending credit products based on the user's credit index, preferences, needs, etc., improves the matching accuracy of the final recommended credit products with the user's preferences and needs.
  • the blockchain can automatically determine whether the user meets the credit application conditions for credit products based on the user's household registration, age, occupation, assets, liabilities and other identity information, which can improve the approval speed of credit products and reduce labor costs in the approval process.
  • the computer device includes a processor, a non-volatile storage medium, a memory, and a network interface connected through a system bus.
  • the non-volatile storage medium of the computer device stores an operating system, a database and computer-readable instructions
  • the database may store a sequence of control information.
  • the processor can realize a A blockchain-based credit recommendation method.
  • the processor of the computer device is used to provide computing and control capabilities and support the operation of the entire computer device.
  • the computer device may have computer readable instructions stored in the memory which, when executed by the processor, cause the processor to perform a blockchain-based credit recommendation method.
  • the network interface of the computer equipment is used for communication with the terminal connection.
  • FIG. 3 is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer equipment to which the solution of the present application is applied. Include more or fewer components than shown in the figures, or combine certain components, or have a different arrangement of components.
  • the computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor.
  • the processor executes the computer program, the processor implements the following steps: acquiring a user's credit request, where the credit request includes the user's credit index, Credit screening conditions and user identity information; according to the credit index, the user identity information and the credit screening conditions, the credit product to be recommended and the credit application conditions corresponding to the credit product are matched from the preset credit product library ; determine whether the user identity information satisfies the credit application conditions; if so, recommend the credit product to the user.
  • the processor executes the computer program, the following steps may also be implemented: obtaining the user's preference tag from the user identity information; determining the user's demand tag according to the credit screening condition; according to the credit index and preset credit The data authority level of each credit product in the product library, obtain a plurality of candidate credit products corresponding to the credit index from the preset credit product library; according to the preference tag, the demand tag and each candidate for selection The product label of the credit product, and the credit product to be recommended is selected from the plurality of candidate credit products.
  • the processor executes the computer program, the following steps may also be implemented: obtaining the user's identity attribute information from the user identity information, where the identity attribute information includes household registration information, age, occupation information, real estate information, car information, and insurance policy information One or more of , debt information, credit card information, legal action information, and loan information; determine whether the identity attribute information meets the credit application conditions; if so, determine that the user identity information satisfies the credit application conditions Application conditions.
  • the processor executes the computer program, the following steps may also be implemented: if there are multiple credit products to be recommended, calculate each credit product separately according to the product label of each credit product to be recommended and the user's preference label and demand label. The label matching degree corresponding to the recommended credit product; according to the label matching degree of each credit product to be recommended, the credit products to be recommended are sorted.
  • the processor executes the computer program, the following steps may also be implemented: obtaining the product label of the credit product for which the user has reached a transaction; determining a product label matching the user's demand label from the product label; The product label is set as the user's preference label; the preference label is stored in the user identity information corresponding to the user.
  • the processor executes the computer program, the following steps may also be implemented: within a preset period of time, record the repeatability of each product label that matches the user's demand label; set the product label whose repeatability is greater than a preset threshold as the The temporary preference tag of the user; when the time period corresponding to the temporary preference tag arrives, the temporary preference tag is removed from all preference tags of the user.
  • the processor executes the computer program, the following steps may also be implemented: acquiring multiple credit parameters from transaction records of the credit product; and resetting the user's credit index according to the multiple credit parameters and the weight corresponding to each credit parameter.
  • An embodiment of the present application further provides a storage medium storing computer-readable instructions.
  • the one or more processors when the computer-readable instructions are executed by one or more processors, the one or more processors perform the following steps : Obtain the user's credit request, the credit request includes the user's credit index, credit screening conditions and user identity information; Matching the credit product to be recommended and the credit application condition corresponding to the credit product; judging whether the user identity information satisfies the credit application condition; if so, recommending the credit product to the user.
  • the processor may further perform the following steps: obtaining the user's preference tag from the user identity information; determining the user's demand tag according to the credit screening conditions; The data permission level of each credit product, obtain a plurality of candidate credit products corresponding to the credit index from the preset credit product library; according to the preference tag, the demand tag and the product of each candidate credit product tag, and screen out the credit product to be recommended from the plurality of candidate credit products.
  • the processor may also perform the following steps: obtaining the user's identity attribute information from the user identity information, where the identity attribute information includes household registration information, age, occupation information, real estate information, car information, insurance policy information, debt information, One or more of credit card information, legal action information, and loan information; determine whether the identity attribute information satisfies the credit application conditions; if so, determine that the user identity information satisfies the credit application conditions.
  • the processor may further perform the following steps: if there are multiple credit products to be recommended, calculate each credit product to be recommended according to the product label of each credit product to be recommended and the user's preference label and demand label. Corresponding label matching degree; according to the label matching degree of each credit product to be recommended, sort each credit product to be recommended.
  • the processor may further perform the following steps: obtaining the product label of the credit product with which the user has entered into a transaction; determining a product label matching the user's demand label from the product label; setting the determined product label as the preference tag of the user; the preference tag is stored in the user identity information corresponding to the user.
  • the processor may further perform the following steps: within a preset period of time, record the repeatability of each product label that matches the user's demand label; set product labels with repeatability greater than a preset threshold as the user's temporary preference label; when the time period corresponding to the temporary preference label arrives, remove the temporary preference label from all preference labels of the user.
  • the processor may further perform the following steps: acquiring multiple credit parameters from the transaction records of the credit product; and resetting the user's credit index according to the multiple credit parameters and the weight corresponding to each credit parameter.
  • the storage medium involved in this application may be non-volatile or volatile.
  • the aforementioned storage medium may be a non-volatile storage medium such as a magnetic disk, an optical disk, a read-only memory (Read-Only Memory, ROM), or a random storage memory (Random Access Memory, RAM), etc.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Accounting & Taxation (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Finance (AREA)
  • Databases & Information Systems (AREA)
  • Strategic Management (AREA)
  • General Business, Economics & Management (AREA)
  • General Engineering & Computer Science (AREA)
  • Marketing (AREA)
  • Development Economics (AREA)
  • Computer Security & Cryptography (AREA)
  • Technology Law (AREA)
  • Economics (AREA)
  • Data Mining & Analysis (AREA)
  • Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • Bioethics (AREA)
  • General Health & Medical Sciences (AREA)
  • Computer Hardware Design (AREA)
  • Software Systems (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

一种基于区块链的信贷推荐方法、设备及存储介质，该方法包括：获取用户的信贷请求，信贷请求包括用户的信用指数、信贷筛选条件及用户身份信息（101）；根据信用指数、用户身份信息及信贷筛选条件，从预设信贷产品库中匹配出待推荐的信贷产品及信贷产品对应的信贷申请条件（102）；判断用户身份信息是否满足信贷申请条件（103）；如果是，则将信贷产品推荐给用户（104）。该方法在区块链系统中自动推荐信贷产品，匹配速度快，根据用户信用指数、偏好、需求等推荐信贷产品，提高推荐的信贷产品与用户偏好及需求的匹配度，减少了最终审批结果与事实不符的情况，能够提高信贷产品的审批速度，减少审批过程中的人力成本。

Description

一种基于区块链的信贷推荐方法、设备及存储介质
本申请要求于2020年11月16日提交中国专利局、申请号为202011281830.8，发明名称为“一种基于区块链的信贷推荐方法、设备及存储介质”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请属于区块链技术领域，具体涉及一种基于区块链的信贷推荐方法、设备及存储介质。
 背景技术
目前，实现信贷业务的主要方式为：由用户准备充足的材料到银行营业厅与业务人员进行洽谈，并提交材料；然后等待银行审批，审批流程大约需要多个工作日的时间，时延较长；审批成功之后用户办理贷款合同签约等手续，并进行资金周转；最后用户根据选取的还款方式进行还款，并在还款结束后，去贷款银行办理收回抵押材料等手续。整个借贷流程复杂、审核时间长、人力成本投入较高，而最终的审批结果有时还会存在与事实不符的情况。
发明人发现，相关技术中也提供了一些线上的借贷系统：用户将准备充足的材料上传到银行的系统中，由业务人员审批，并将审批结果通过网络发送给用户。但这种线上借贷过程还是需要很大的人力成本，主要依赖人工进行，网络只起到了数据传输的作用。
 技术问题
本申请提出一种基于区块链的信贷推荐方法、设备及存储介质，能够提高信贷产品的审批速度，减少审批过程中的人力成本。
 技术解决方案
本申请第一方面实施例提出了一种基于区块链的信贷推荐方法，应用于区块链节点设备，包括：获取用户的信贷请求，所述信贷请求包括用户的信用指数、信贷筛选条件及用户身份信息；根据所述信用指数、所述用户身份信息及所述信贷筛选条件，从预设信贷产品库中匹配出待推荐的信贷产品及所述信贷产品对应的信贷申请条件；判断所述用户身份信息是否满足所述信贷申请条件；如果是，则将所述信贷产品推荐给所述用户。
本申请第二方面的实施例提供了一种区块链节点设备，包括：获取模块，用于获取用户的信贷请求，所述信贷请求包括用户的信用指数、信贷筛选条件及用户身份信息；匹配模块，用于根据所述信用指数、所述用户身份信息及所述信贷筛选条件，从预设信贷产品库中匹配出待推荐的信贷产品及所述信贷产品对应的信贷申请条件；判断模块，用于判断所述用户身份信息是否满足所述信贷申请条件；推荐模块，用于所述判断模块判定所述用户身份信息满足所述信贷申请条件，则将所述信贷产品推荐给所述用户。
本申请第三方面的实施例提供了一种计算机设备，包括存储器和处理器，所述存储器中存储有计算机可读指令，所述计算机可读指令被所述处理器执行时，使得所述处理器执行上述第一方面所述的基于区块链的信贷推荐方法，该方法包括：获取用户的信贷请求，所述信贷请求包括用户的信用指数、信贷筛选条件及用户身份信息；根据所述信用指数、所述用户身份信息及所述信贷筛选条件，从预设信贷产品库中匹配出待推荐的信贷产品及所述信贷产品对应的信贷申请条件；判断所述用户身份信息是否满足所述信贷申请条件；如果是，则将所述信贷产品推荐给所述用户。
本申请第四方面的实施例提供了一种存储有计算机可读指令的存储介质，所述计算机可读指令被一个或多个处理器执行时，使得一个或多个处理器执行上述第一方面所述的基于区块链的信贷推荐方法，该方法包括：获取用户的信贷请求，所述信贷请求包括用户的信用指数、信贷筛选条件及用户身份信息；根据所述信用指数、所述用户身份信息及所述信贷筛选条件，从预设信贷产品库中匹配出待推荐的信贷产品及所述信贷产品对应的信贷申请条件；判断所述用户身份信息是否满足所述信贷申请条件；如果是，则将所述信贷产品推荐给所述用户。
 有益效果
本申请实施例在区块链系统中实现信贷产品的自动推荐，匹配速度快。提高了信贷产品的成交量，借贷流程自动化，缩短了审核时间，减少了最终的审批结果与事实不符的情况。
本申请附加的方面和优点将在下面的描述中部分给出，部分将从下面的描述中变的明显，或通过本申请的实践了解到。
 附图说明
通过阅读下文优选实施方式的详细描述，各种其他的优点和益处对于本领域普通技术人员将变得清楚明了。附图仅用于示出优选实施方式的目的，而并不认为是对本申请的限制。而且在整个附图中，用相同的参考符号表示相同的部件。图1示出了本申请一实施例所提供的一种基于区块链的信贷推荐方法的流程示意图。
图2示出了本申请一实施例所提供的一种基于区块链的信贷推荐装置的结构示意图。
图3示出了本申请一实施例所提供的一种计算机设备的结构示意图。
图4示出了本申请一实施例所提供的一种存储介质的示意图。
 本发明的实施方式
为了使本申请的目的、技术方案及优点更加清楚明白，以下结合附图及实施例，对本申请进行进一步详细说明。应当理解，此处所描述的具体实施例仅仅用以解释本申请，并不用于限定本申请。
可以理解，本申请所使用的术语“第一”、“第二”等可在本文中用于描述各种元件，但这些元件不受这些术语限制。这些术语仅用于将第一个元件与另一个元件区分。
本申请可涉及人工智能技术领域，如可以基于人工智能技术对相关的数据进行获取和处理。可选的，本申请的技术方案可应用于各种信贷产品推荐场景，如数字医疗场景下的信贷产品推荐，又如金融科技场景下的信贷产品推荐。例如，本申请涉及的待推荐的用户可以为医疗系统中的用户，又如可以为金融系统中的用户，还可以其他用户。
本申请的一些实施例提供了一种基于区块链的信贷推荐方法，用户在区块链系统中进行信贷产品交易之前，首先用户需要在该系统的区块链节点设备中注册，注册过程中区块链节点设备会为用户分配私钥和公钥。用户将自己的账号标识（姓名或昵称等）、户籍信息、年龄、职业信息、房产信息、汽车信息、保单信息、负债信息、信用卡信息、法律诉讼信息、借贷信息等中的一种或多种作为自己的用户身份信息，将用户身份信息上传给区块链节点设备，区块链节点设备存储该用户身份信息。在存储该用户身份信息之前可以先进行加密，将用户身份信息的密文存储在区块链节点设备中。
在用户注册时还可以提供多个产品标签给用户选择，将用户选择的产品标签设置为用户的偏好标签，将偏好标签存储在用户身份信息中。其中，产品标签可以为投资风险等级（低、中或高等）、信贷产品所属的领域、产品类型、期限（短期、中期或长期等）、金额、信贷服务方式（抵押或质押等）、贷款对象等。偏好标签可以包括标签名和偏好指数，其中标签名可以包括投资风险等级、信贷产品所属的领域、产品类型、期限、金额、信贷服务方式、贷款对象等，标签名对应的偏好指数用于表示用户挑选信贷产品时该标签名对应的因素所占的比重。偏好指数与是否达成交易、交易金额、一定时间内筛选标签重复度等参数相关，偏好指数越高。
在注册过程中，区块链节点设备还为用户设置了信用指数，并将该信用指数的取值设置为预设初始值，该预设初始值可以为60或65。然后存储用户的信用指数与用户身份信息的对应关系。其中，信用指数的取值范围可以是0-100，后续可以根据用户对信贷产品的交易记录来更新用户的信用指数。
用户在区块链信贷交易系统中注册之后，当用户想要挑选信贷产品进行交易时，用户通过自己的手机或电脑等终端发送信贷浏览请求给区块链节点设备，该信贷请求包括用户的姓名或昵称等账号标识以及用户提交的信贷筛选条件。信贷筛选条件中包括用户输入的贷款金额、利率、期限、信贷产品所属的领域等需求条件。
在本申请的另一些实施例中，用户的姓名或昵称等账号标识属于用户的隐私数据，为了提高用户的隐私数据在数据传输过程中的安全性，本申请实施例通过用户的公钥对用户的姓名或昵称等账号标识进行加密，在上述信贷请求中携带加密得到的密文、用户的公钥及信贷筛选条件。
如图1所示，区块链节点设备接收到该信贷请求之后，通过如下步骤101-104的操作来为用户推荐信贷产品。
步骤101：获取用户的信贷请求，该信贷请求包括用户的信用指数、信贷筛选条件及用户身份信息。
区块链节点设备根据上述信贷请求包括的账号标识，获取该账户标识对应的用户身份信息和信用指数。
在本申请的另一些实施例中，信贷请求中包括用户的姓名或昵称等账号标识的密文、用户的公钥及信贷筛选条件。区块链节点设备获取用户的信贷请求之后，首先根据用户的公钥验证该用户是否为合法用户。具体地，区块链节点设备通过预设非对称加密算法对用户的公钥进行运算，得到该公钥对应的用户地址。其中，非对称加密算法可以为RSA、ECC（Elliptic Curve Cryptography，椭圆曲线加密算法）等。
判断该公钥对应的用户地址与发送该信贷请求的用户地址是否一致，如果否，则确定该用户不是合法用户，则丢弃该信贷请求，不对其进行响应。如果是，则确定该用户为合法用户，获取该公钥对应的私钥，通过该私钥对信贷请求中的密文进行解密得到用户的账号标识。然后该区块链节点设备通过该区块链节点设备的公钥对用户的账号标识进行加密得到密文，将该区块链节点设备称为第一区块链节点设备，第一区块链节点设备可以为银行或信贷公司等提供信贷产品的供应商对应的服务器。则第一区块链节点设备发送该密文及第一区块链节点设备的公钥给存储有用户相关信息的区块的第二区块链节点设备，用户相关信息可以包括用户的账号标识、用户身份信息、与信贷产品相关的用户历史记录等。
第二区块链节点设备根据第一区块链节点设备的公钥先验证第一区块链节点设备是否具有查看用户相关信息的权限。具体地，第二区块链节点设备通过预设非对称加密算法对及第一区块链节点设备的公钥进行运算，得到及第一区块链节点设备对应的节点地址。判断该公钥对应的节点地址与发送上述密文及公钥的节点地址是否一致，如果否，则确定第一区块链节点设备不具有查看用户相关信息的权限，则不对响应第一区块链节点设备的查询请求。
如果是，则确定第一区块链节点设备具有查看用户相关信息的权限，获取该公钥对应的私钥，通过该私钥对第一区块链节点设备发送的密文解密得到用户的账号标识，根据该账号标识，从存储有用户相关信息的区块中获取该账号标识对应的用户身份信息和信用指数，将获取的用户身份信息和信用指数返回给第一区块链节点设备。
步骤102：根据信用指数、用户身份信息及信贷筛选条件，从预设信贷产品库中匹配出待推荐的信贷产品及信贷产品对应的信贷申请条件。
具体通过如下步骤1021-1024的操作来匹配信贷产品。
步骤1021：从用户身份信息中获取用户的偏好标签。
偏好标签可以包括标签名和偏好指数，其中标签名可以包括投资风险等级、信贷产品所属的领域、产品类型、期限、金额、信贷服务方式、贷款对象等，标签名对应的偏好指数用于表示用户挑选信贷产品时该标签名对应的因素所占的比重。
步骤1022：根据信贷筛选条件确定用户的需求标签。
信贷筛选条件中包括用户输入的贷款金额、利率、期限、信贷产品所属的领域等需求条件。区块链节点设备获取用户所设置的信贷筛选条件中的关键词，根据这些关键词确定用户的需求标签。
需求标签可以包括投资风险等级、信贷产品所属的领域、产品类型、期限、金额、信贷服务方式、贷款对象等。
步骤1023：根据信用指数及预设信贷产品库中每个信贷产品的数据权限级别，从预设信贷产品库中获取信用指数对应的多个待选信贷产品。
在本申请实施例中，区块链节点设备中预先配置有预设信贷产品库，该预设信贷产品库中包括大量信贷产品，每个信贷产品中均包括产品介绍、信贷公司形象、信贷经理信息、对应的信贷申请条件、产品标签及数据权限级别等。其中，信贷申请条件用于判断用户是否满足信贷产品的要求。产品标签包括投资风险等级、信贷产品所属的领域、产品类型、期限、金额、信贷服务方式、贷款对象等。数据权限级别规定了信贷产品适用的信用指数范围，数据权限级别与贷款成本、放贷利率、还款方式、预期收益、期限等相关，贷款成本越低、放贷利率越低、期限越长，则数据权限级别高。
区块链节点设备根据用户的信用指数及设信贷产品库中每个信贷产品的数据权限级别，确定数据权限级别规定的信用指数范围包含用户的信用指数的多个信贷产品，确定出的多个信贷产品即为用户的信用指数对应的多个待选信贷产品。用户的信用指数越高，对应的数据权限级别越高，可访问或可选择的信贷产品越多。
步骤1024：根据偏好标签、需求标签及每个待选信贷产品的产品标签，从多个待选信贷产品中筛选出待推荐的信贷产品。
通过步骤1023根据用户的信用指数筛选出符合用户的信用水平的多个待选信贷产品之后，将用户的偏好标签和需求标签分别与每个待选信贷产品的产品标签进行比较。具体地，对于某个待选信贷产品，将该信贷产品的每个产品标签分别与用户的偏好标签和需求标签进行比对，从该信贷产品的产品标签中确定出与用户的偏好标签或需求标签一致的产品标签，统计一致的产品标签对应的标签数目，将该标签数目确定为该信贷产品对应的标签匹配度。通过该方式分别获得每个待选信贷产品对应的标签匹配度。从这多个待选信贷产品中选择标签匹配度大于预设数值的一个或多个待推荐的信贷产品。预设数值可以为4、5或6等。
步骤103：判断用户身份信息是否满足信贷申请条件。
通过步骤102从预设信贷产品库中筛选出一个或多个待推荐的信贷产品之后，对于每个待推荐的信贷产品，通过如下步骤1031和1032的操作来判断用户是否满足待推荐的信贷产品对应的信贷申请条件。
步骤1031：从用户身份信息中获取用户的身份属性信息，身份属性信息包括户籍信息、年龄、职业信息、房产信息、汽车信息、保单信息、负债信息、信用卡信息、法律诉讼信息、借贷信息中的一种或多种。
其中，借贷信息可以包括网贷信息或民间借贷信息等。身份属性信息还可以包括征信报告信息、信用卡信息、芝麻分信息等。
步骤1032：判断身份属性信息是否均满足信贷申请条件；如果是，则判定用户身份信息满足信贷申请条件。
待推荐的信贷产品对应的信贷申请条件中设置有多个信贷属性，信贷属性可以包括户籍、年龄、职业、房产、汽车、保单、征信报告、负债、信用卡、法律诉讼、芝麻分、网贷、民间借贷等。
区块链节点设备将用户身份信息中的每个身份属性信息分别与待推荐的信贷产品对应的信贷申请条件中相应的信贷属性进行比对，确定每个身份属性信息是否符合信贷申请条件中相应信贷属性的要求，如确定用户的年龄是否符合信贷申请条件中年龄的要求，以及确定用户的征信报告是否符合信贷申请条件中征信报告的相关要求等。
对于任意一个待推荐的信贷产品，只有当确定用户的所有身份属性信息均符合该待推荐的信贷产品对应的信贷申请条件的要求，才判定该用户的用户身份信息满足其信贷申请条件。
步骤104：如果是，则将信贷产品推荐给用户。
将步骤103判断的用户身份信息符合信贷申请条件的信贷产品推荐给用户。具体地，区块链节点设备从预设信贷产品库中获取这些信贷产品的产品介绍、信贷公司形象、信贷经理信息等信贷产品信息，将获取的信贷产品信息发送给用户的终端。终端接收区块链节点设备发送的信贷产品信息，显示这些信贷产品信息，以便用户从这些信贷产品中选择需要达成交易的信贷产品。
在本申请的一些实施例中，若最终确定出的需要推荐给用户的信贷产品的数目为多个，则通过如下步骤1041和1042的操作对这多个信贷产品进行排序。
步骤1041：根据每个需推荐的信贷产品的产品标签及用户的偏好标签和需求标签，分别计算每个需推荐的信贷产品对应的标签匹配度。
每个信贷产品的标签匹配度的计算方式与步骤S1024中记述的方式相同，在此不再赘述。
步骤1042：根据每个需推荐的信贷产品的标签匹配度，对每个需推荐的信贷产品进行排序。
根据每个需推荐的信贷产品的标签匹配度，按照标签匹配度从大道小的顺序对需推荐的多个信贷产品进行排序，然后将排序后的多个信贷产品推荐给用户。
在本申请实施例中，还可以根据需推荐的信贷产品的产品标签中包括偏好标签的偏好指数来排序，偏好指数越高的信贷产品的排序越优先。
在将审批通过的多个信贷产品推荐给用户之前，根据信贷产品和用户的偏好及需求的匹配程度，对多个信贷产品进行排序，能够使得排在前面的信贷产品更加符合用户的偏好及需求，给用户的参考性更强，能够提高信贷产品的成交量。
将信贷产品推荐给用户之后，用户可以从中选择一个或多个信贷产品申请进行交易，区块链节点设备接收到用户的终端发送的某个信贷产品的申请请求时，区块链节点设备将用户的用户身份信息发送给该信贷产品对应的信贷经理进行审核。在本申请实施例中，用户的信用指数越高，用户身份信息的数据越趋于隐藏，在信贷产品经理审核时，仅显示是否满足申请条件，更有利于保护用户身份信息。用户的信用指数越低，在交易审核时，可能需展示部分信用数据和历史交易的部分数据用于审核与评估。
完成交易之后区块链节点设备会生成对应的交易记录，该交易记录中包括用户私钥、公钥、签名、加密的用户身份信息、加密的交易信息、时间戳等基本信息，以及包括用户需求、信贷筛选条件、信贷成本、利率、收益、是否还款、还款时间、还款方式、是否准时等交易信息。将该交易记录存储在区块链节点设备中。
在本申请的一些实施例中，还根据达成交易的信贷产品来调整用户的偏好标签，具体可以通过如下步骤S1-S4的操作来调整偏好标签。
步骤S1：获取用户达成交易的信贷产品的产品标签。
区块链节点设备从用户对应的交易记录中获取达成交易的信贷产品的产品标签。
步骤S2：从获取的产品标签中确定出与用户的需求标签匹配的产品标签。
从达成交易的信贷产品的产品标签中确定出与用户的需求标签一致的产品标签。
步骤S3：将确定的产品标签设置为用户的偏好标签。
将与用户的需求标签一致的产品标签设置为用户的偏好标签。
步骤S4：将设置的偏好标签存储在用户对应的用户身份信息中。
根据用户达成交易的信贷产品来调整用户的偏好标签，以便根据用户的偏好标签进行后续的信贷产品的推荐及待推荐信贷产品的排序，能够使得推荐的信贷产品更加符合用户偏好。
在本申请的实施例中，还可以通过如下步骤S5-S7的操作来调整用户的偏好标签。
步骤S5：在预设时长内，记录与用户的需求标签匹配的每个产品标签的重复度。
预设时长可以为一个星期、一个月或一个季度等。在步骤S1024中匹配出与用户的需求标签一致的产品标签时，将该产品标签的重复度加1，产品标签的重复度表示在预设时长内该产品标签被匹配到与用户的需求标签一致的总次数。
步骤S6：将重复度大于预设阈值的产品标签设置为用户的临时偏好标签。
预设阈值可以为8、10或20等。本申请实施例并不限制预设阈值的具体取值，实际应用中可根据需求来设置预设阈值的取值。
区块链节点设备将设置的临时偏好标签存储在用户对应的用户身份信息中。本申请实施例中设定临时偏好标签具有一定的时效性，设置了临时偏好标签对应的时效时长，并对该临时偏好标签的效用时间进行计时。
步骤S7：在临时偏好标签对应的时效时长到达时，从用户的所有偏好标签中剔除临时偏好标签。
当临时偏好标签对应的计时时间大于或等于临时偏好标签对应的时效时长时，从用户身份信息中包括的所有偏好标签中剔除该临时偏好标签。
将预设时长内筛选重复度较高的产品标签作为用户的临时偏好标签，充分结合用户偏好随时间变化的特性，使设置的偏好标签更加符合用户的实际偏好情况，进而提高推荐的信贷产品与用户实际偏好的匹配度。
在本申请实施例中，用户刚在区块链信贷交易系统中注册时，用户对应的信用指数的取值为预设初始值，之后可以根据用户的信贷交易情况对信用指数的取值进行调整，具体通过如下步骤S8和S9的操作来调整信用指数。
步骤S8：从信贷产品的交易记录中获取多个信用参数。
上述信用参数包括是否还款、还款时间、还款是否准时等。
步骤S9：根据多个信用参数及每个信用参数对应的权重，重置用户的信用指数。
区块链节点设备中预先设置了每个信用参数对应的权重。根据从交易记录中获取的每个信用参数，确定每个信用参数对应的取值，如若用户未还款，则信用参数“是否还款”的取值可以为0，若用户还款了，则信用参数“是否还款”的取值可以为1；若用户还款时间早于规定时间，则信用参数“还款时间”的取值可以为8，若用户还款时间恰好为规定时间，则信用参数“还款时间”的取值可以为5，若用户还款时间晚于规定时间，则信用参数“还款时间”的取值可以为2等。
确定出每个信用参数的取值之后，根据每个信用参数的取值及权重，对所有信用参数进行加权求和，得到用户的新的信用指数，将之前存储的该用户的信用指数替换为该新的信用指数。
本申请实施例在区块链系统中实现信贷产品的自动推荐，匹配速度快。根据用户的信用指数、偏好、需求等进行信贷产品的筛选与推荐，提高了最终推荐的信贷产品与用户偏好及需求的匹配精度，推荐的信贷产品的可参考性很高，提高了信贷产品的成交量，借贷流程自动化，缩短了审核时间，减少了最终的审批结果与事实不符的情况。通过区块链自动根据用户的户籍、年龄、职业、资产、负债等身份信息，判定该用户是否符合信贷产品的信贷申请条件，能够提高信贷产品的审批速度，减少审批过程中的人力成本。
如图2所示，本申请实施例提供了一种区块链节点设备，该区块链节点设备用于执行上述任一实施例所述的基于区块链的信贷推荐方法，包括：获取模块201，用于获取用户的信贷请求，信贷请求包括用户的信用指数、信贷筛选条件及用户身份信息；匹配模块202，用于根据信用指数、用户身份信息及信贷筛选条件，从预设信贷产品库中匹配出待推荐的信贷产品及信贷产品对应的信贷申请条件；判断模块203，用于判断用户身份信息是否满足信贷申请条件；推荐模块204，用于判断模块判定用户身份信息满足信贷申请条件，则将信贷产品推荐给用户。
匹配模块202，用于从用户身份信息中获取用户的偏好标签；根据信贷筛选条件确定用户的需求标签；根据信用指数及预设信贷产品库中每个信贷产品的数据权限级别，从预设信贷产品库中获取信用指数对应的多个待选信贷产品；根据偏好标签、需求标签及每个待选信贷产品的产品标签，从多个待选信贷产品中筛选出待推荐的信贷产品。
判断模块203，用于从用户身份信息中获取用户的身份属性信息，身份属性信息包括户籍信息、年龄、职业信息、房产信息、汽车信息、保单信息、负债信息、信用卡信息、法律诉讼信息、借贷信息中的一种或多种；判断身份属性信息是否均满足信贷申请条件；如果是，则判定用户身份信息满足信贷申请条件。
该设备还包括：排序模块，用于若存在多个需推荐的信贷产品时，根据每个需推荐的信贷产品的产品标签及用户的偏好标签和需求标签，分别计算每个需推荐的信贷产品对应的标签匹配度；根据每个需推荐的信贷产品的标签匹配度，对每个需推荐的信贷产品进行排序。
该设备还包括：偏好标签设置模块，用于获取用户达成交易的信贷产品的产品标签；从产品标签中确定出与用户的需求标签匹配的产品标签；将确定的产品标签设置为用户的偏好标签；将偏好标签存储在用户对应的用户身份信息中。
该设备还包括：临时标签管理模块，用于在预设时长内，记录与用户的需求标签匹配的每个产品标签的重复度；将重复度大于预设阈值的产品标签设置为用户的临时偏好标签；在临时偏好标签对应的时效时长到达时，从用户的所有偏好标签中剔除临时偏好标签。
该设备还包括：重置模块，用于从信贷产品的交易记录中获取多个信用参数；根据多个信用参数及每个信用参数对应的权重，重置用户的信用指数。
本申请实施例在区块链系统中实现信贷产品的自动推荐，匹配速度快。根据用户的信用指数、偏好、需求等进行信贷产品的筛选与推荐，提高了最终推荐的信贷产品与用户偏好及需求的匹配精度，推荐的信贷产品的可参考性很高，提高了信贷产品的成交量，借贷流程自动化，缩短了审核时间，减少了最终的审批结果与事实不符的情况。通过区块链自动根据用户的户籍、年龄、职业、资产、负债等身份信息，判定该用户是否符合信贷产品的信贷申请条件，能够提高信贷产品的审批速度，减少审批过程中的人力成本。
本申请实施例提供了一种计算机设备，如图3所示，该计算机设备包括通过系统总线连接的处理器、非易失性存储介质、存储器和网络接口。其中，该计算机设备的非易失性存储介质存储有操作系统、数据库和计算机可读指令，数据库中可存储有控件信息序列，该计算机可读指令被处理器执行时，可使得处理器实现一种基于区块链的信贷推荐方法。该计算机设备的处理器用于提供计算和控制能力，支撑整个计算机设备的运行。该计算机设备的存储器中可存储有计算机可读指令，该计算机可读指令被处理器执行时，可使得处理器执行一种基于区块链的信贷推荐方法。该计算机设备的网络接口用于与终端连接通信。本领域技术人员可以理解，图3中示出的结构，仅仅是与本申请方案相关的部分结构的框图，并不构成对本申请方案所应用于其上的计算机设备的限定，具体的计算机设备可以包括比图中所示更多或更少的部件，或者组合某些部件，或者具有不同的部件布置。
该计算机设备包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，处理器执行计算机程序时实现以下步骤：获取用户的信贷请求，所述信贷请求包括用户的信用指数、信贷筛选条件及用户身份信息；根据所述信用指数、所述用户身份信息及所述信贷筛选条件，从预设信贷产品库中匹配出待推荐的信贷产品及所述信贷产品对应的信贷申请条件；判断所述用户身份信息是否满足所述信贷申请条件；如果是，则将所述信贷产品推荐给所述用户。
处理器执行计算机程序时还可以实现以下步骤：从所述用户身份信息中获取所述用户的偏好标签；根据所述信贷筛选条件确定所述用户的需求标签；根据所述信用指数及预设信贷产品库中每个信贷产品的数据权限级别，从所述预设信贷产品库中获取所述信用指数对应的多个待选信贷产品；根据所述偏好标签、所述需求标签及每个待选信贷产品的产品标签，从所述多个待选信贷产品中筛选出待推荐的信贷产品。
处理器执行计算机程序时还可以实现以下步骤：从所述用户身份信息中获取所述用户的身份属性信息，所述身份属性信息包括户籍信息、年龄、职业信息、房产信息、汽车信息、保单信息、负债信息、信用卡信息、法律诉讼信息、借贷信息中的一种或多种；判断所述身份属性信息是否均满足所述信贷申请条件；如果是，则判定所述用户身份信息满足所述信贷申请条件。
处理器执行计算机程序时还可以实现以下步骤：若存在多个需推荐的信贷产品时，根据每个需推荐的信贷产品的产品标签及所述用户的偏好标签和需求标签，分别计算每个需推荐的信贷产品对应的标签匹配度；根据每个需推荐的信贷产品的标签匹配度，对所述每个需推荐的信贷产品进行排序。
处理器执行计算机程序时还可以实现以下步骤：获取所述用户达成交易的信贷产品的产品标签；从所述产品标签中确定出与所述用户的需求标签匹配的产品标签；将确定的所述产品标签设置为所述用户的偏好标签；将所述偏好标签存储在所述用户对应的用户身份信息中。
处理器执行计算机程序时还可以实现以下步骤：在预设时长内，记录与所述用户的需求标签匹配的每个产品标签的重复度；将重复度大于预设阈值的产品标签设置为所述用户的临时偏好标签；在所述临时偏好标签对应的时效时长到达时，从所述用户的所有偏好标签中剔除所述临时偏好标签。
处理器执行计算机程序时还可以实现以下步骤：从信贷产品的交易记录中获取多个信用参数；根据所述多个信用参数及每个信用参数对应的权重，重置所述用户的信用指数。
本申请实施例还提出了一种存储有计算机可读指令的存储介质，如图4所示，该计算机可读指令被一个或多个处理器执行时，使得一个或多个处理器执行以下步骤：获取用户的信贷请求，所述信贷请求包括用户的信用指数、信贷筛选条件及用户身份信息；根据所述信用指数、所述用户身份信息及所述信贷筛选条件，从预设信贷产品库中匹配出待推荐的信贷产品及所述信贷产品对应的信贷申请条件；判断所述用户身份信息是否满足所述信贷申请条件；如果是，则将所述信贷产品推荐给所述用户。
处理器还可以执行以下步骤：从所述用户身份信息中获取所述用户的偏好标签；根据所述信贷筛选条件确定所述用户的需求标签；根据所述信用指数及预设信贷产品库中每个信贷产品的数据权限级别，从所述预设信贷产品库中获取所述信用指数对应的多个待选信贷产品；根据所述偏好标签、所述需求标签及每个待选信贷产品的产品标签，从所述多个待选信贷产品中筛选出待推荐的信贷产品。
处理器还可以执行以下步骤：从所述用户身份信息中获取所述用户的身份属性信息，所述身份属性信息包括户籍信息、年龄、职业信息、房产信息、汽车信息、保单信息、负债信息、信用卡信息、法律诉讼信息、借贷信息中的一种或多种；判断所述身份属性信息是否均满足所述信贷申请条件；如果是，则判定所述用户身份信息满足所述信贷申请条件。
处理器还可以执行以下步骤：若存在多个需推荐的信贷产品时，根据每个需推荐的信贷产品的产品标签及所述用户的偏好标签和需求标签，分别计算每个需推荐的信贷产品对应的标签匹配度；根据每个需推荐的信贷产品的标签匹配度，对所述每个需推荐的信贷产品进行排序。
处理器还可以执行以下步骤：获取所述用户达成交易的信贷产品的产品标签；从所述产品标签中确定出与所述用户的需求标签匹配的产品标签；将确定的所述产品标签设置为所述用户的偏好标签；将所述偏好标签存储在所述用户对应的用户身份信息中。
处理器还可以执行以下步骤：在预设时长内，记录与所述用户的需求标签匹配的每个产品标签的重复度；将重复度大于预设阈值的产品标签设置为所述用户的临时偏好标签；在所述临时偏好标签对应的时效时长到达时，从所述用户的所有偏好标签中剔除所述临时偏好标签。
处理器还可以执行以下步骤：从信贷产品的交易记录中获取多个信用参数；根据所述多个信用参数及每个信用参数对应的权重，重置所述用户的信用指数。
可选的，本申请涉及的存储介质可以是非易失性的，也可以是易失性的。
本领域普通技术人员可以理解实现上述实施例方法中的全部或部分流程，是可以通过计算机程序来指令相关的硬件来完成，该计算机程序可存储于一计算机可读取存储介质中，该程序在执行时，可包括如上述各方法的实施例的流程。其中，前述的存储介质可为磁碟、光盘、只读存储记忆体（Read-Only Memory，ROM）等非易失性存储介质，或随机存储记忆体（Random Access Memory，RAM）等。
以上所述实施例的各技术特征可以进行任意的组合，为使描述简洁，未对上述实施例中的各个技术特征所有可能的组合都进行描述，然而，只要这些技术特征的组合不存在矛盾，都应当认为是本说明书记载的范围。
以上所述实施例仅表达了本申请的几种实施方式，其描述较为具体和详细，但并不能因此而理解为对本申请专利范围的限制。应当指出的是，对于本领域的普通技术人员来说，在不脱离本申请构思的前提下，还可以做出若干变形和改进，这些都属于本申请的保护范围。因此，本申请专利的保护范围应以所附权利要求为准。

Claims (20)

  1. 一种基于区块链的信贷推荐方法，其中，应用于区块链节点设备，包括：
    获取用户的信贷请求，所述信贷请求包括用户的信用指数、信贷筛选条件及用户身份信息；
    根据所述信用指数、所述用户身份信息及所述信贷筛选条件，从预设信贷产品库中匹配出待推荐的信贷产品及所述信贷产品对应的信贷申请条件；
    判断所述用户身份信息是否满足所述信贷申请条件；
    如果是，则将所述信贷产品推荐给所述用户。
  2. 根据权利要求1所述的方法，其中，所述根据所述信用指数、所述用户身份信息及所述信贷筛选条件，从预设信贷产品库中匹配出待推荐的信贷产品及所述信贷产品对应的信贷申请条件，包括：
    从所述用户身份信息中获取所述用户的偏好标签；
    根据所述信贷筛选条件确定所述用户的需求标签；
    根据所述信用指数及预设信贷产品库中每个信贷产品的数据权限级别，从所述预设信贷产品库中获取所述信用指数对应的多个待选信贷产品；
    根据所述偏好标签、所述需求标签及每个待选信贷产品的产品标签，从所述多个待选信贷产品中筛选出待推荐的信贷产品。
  3. 根据权利要求1所述的方法，其中，所述判断所述用户身份信息是否满足所述信贷申请条件，包括：
    从所述用户身份信息中获取所述用户的身份属性信息，所述身份属性信息包括户籍信息、年龄、职业信息、房产信息、汽车信息、保单信息、负债信息、信用卡信息、法律诉讼信息、借贷信息中的一种或多种；
    判断所述身份属性信息是否均满足所述信贷申请条件；
    如果是，则判定所述用户身份信息满足所述信贷申请条件。
  4. 根据权利要求2所述的方法，其中，所述将所述信贷产品推荐给所述用户之前，还包括：
    若存在多个需推荐的信贷产品时，根据每个需推荐的信贷产品的产品标签及所述用户的偏好标签和需求标签，分别计算每个需推荐的信贷产品对应的标签匹配度；
    根据每个需推荐的信贷产品的标签匹配度，对所述每个需推荐的信贷产品进行排序。
  5. 根据权利要求2所述的方法，其中，所述方法还包括：
    获取所述用户达成交易的信贷产品的产品标签；
    从所述产品标签中确定出与所述用户的需求标签匹配的产品标签；
    将确定的所述产品标签设置为所述用户的偏好标签；
    将所述偏好标签存储在所述用户对应的用户身份信息中。
  6. 根据权利要求2所述的方法，其中，所述方法还包括：
    在预设时长内，记录与所述用户的需求标签匹配的每个产品标签的重复度；
    将重复度大于预设阈值的产品标签设置为所述用户的临时偏好标签；
    在所述临时偏好标签对应的时效时长到达时，从所述用户的所有偏好标签中剔除所述临时偏好标签。
  7. 根据权利要求1-6任一项所述的方法，其中，所述方法还包括：
    从信贷产品的交易记录中获取多个信用参数；
    根据所述多个信用参数及每个信用参数对应的权重，重置所述用户的信用指数。
  8. 一种区块链节点设备，其中，包括：
    获取模块，用于获取用户的信贷请求，所述信贷请求包括用户的信用指数、信贷筛选条件及用户身份信息；
    匹配模块，用于根据所述信用指数、所述用户身份信息及所述信贷筛选条件，从预设信贷产品库中匹配出待推荐的信贷产品及所述信贷产品对应的信贷申请条件；
    判断模块，用于判断所述用户身份信息是否满足所述信贷申请条件；
    推荐模块，用于所述判断模块判定所述用户身份信息满足所述信贷申请条件，则将所述信贷产品推荐给所述用户。
  9. 一种计算机设备，包括存储器和处理器，所述存储器中存储有计算机可读指令，所述计算机可读指令被所述处理器执行时，使得所述处理器执行以下方法：
    获取用户的信贷请求，所述信贷请求包括用户的信用指数、信贷筛选条件及用户身份信息；
    根据所述信用指数、所述用户身份信息及所述信贷筛选条件，从预设信贷产品库中匹配出待推荐的信贷产品及所述信贷产品对应的信贷申请条件；
    判断所述用户身份信息是否满足所述信贷申请条件；
    如果是，则将所述信贷产品推荐给所述用户。
  10. 根据权利要求9所述的计算机设备，其中，执行所述根据所述信用指数、所述用户身份信息及所述信贷筛选条件，从预设信贷产品库中匹配出待推荐的信贷产品及所述信贷产品对应的信贷申请条件，包括：
    从所述用户身份信息中获取所述用户的偏好标签；
    根据所述信贷筛选条件确定所述用户的需求标签；
    根据所述信用指数及预设信贷产品库中每个信贷产品的数据权限级别，从所述预设信贷产品库中获取所述信用指数对应的多个待选信贷产品；
    根据所述偏好标签、所述需求标签及每个待选信贷产品的产品标签，从所述多个待选信贷产品中筛选出待推荐的信贷产品。
  11. 根据权利要求10所述的计算机设备，其中，所述将所述信贷产品推荐给所述用户之前，所述处理器还执行：
    若存在多个需推荐的信贷产品时，根据每个需推荐的信贷产品的产品标签及所述用户的偏好标签和需求标签，分别计算每个需推荐的信贷产品对应的标签匹配度；
    根据每个需推荐的信贷产品的标签匹配度，对所述每个需推荐的信贷产品进行排序。
  12. 根据权利要求10所述的计算机设备，其中，所述处理器还执行：
    获取所述用户达成交易的信贷产品的产品标签；
    从所述产品标签中确定出与所述用户的需求标签匹配的产品标签；
    将确定的所述产品标签设置为所述用户的偏好标签；
    将所述偏好标签存储在所述用户对应的用户身份信息中。
  13. 根据权利要求10所述的计算机设备，其中，所述处理器还执行：
    在预设时长内，记录与所述用户的需求标签匹配的每个产品标签的重复度；
    将重复度大于预设阈值的产品标签设置为所述用户的临时偏好标签；
    在所述临时偏好标签对应的时效时长到达时，从所述用户的所有偏好标签中剔除所述临时偏好标签。
  14. 根据权利要求9-13任一项所述的计算机设备，其中，所述处理器还执行：
    从信贷产品的交易记录中获取多个信用参数；
    根据所述多个信用参数及每个信用参数对应的权重，重置所述用户的信用指数。
  15. 一种存储有计算机可读指令的存储介质，所述计算机可读指令被一个或多个处理器执行时，使得一个或多个处理器执行以下方法：
    获取用户的信贷请求，所述信贷请求包括用户的信用指数、信贷筛选条件及用户身份信息；
    根据所述信用指数、所述用户身份信息及所述信贷筛选条件，从预设信贷产品库中匹配出待推荐的信贷产品及所述信贷产品对应的信贷申请条件；
    判断所述用户身份信息是否满足所述信贷申请条件；
    如果是，则将所述信贷产品推荐给所述用户。
  16. 根据权利要求15所述的存储介质，其中，执行所述根据所述信用指数、所述用户身份信息及所述信贷筛选条件，从预设信贷产品库中匹配出待推荐的信贷产品及所述信贷产品对应的信贷申请条件，包括：
    从所述用户身份信息中获取所述用户的偏好标签；
    根据所述信贷筛选条件确定所述用户的需求标签；
    根据所述信用指数及预设信贷产品库中每个信贷产品的数据权限级别，从所述预设信贷产品库中获取所述信用指数对应的多个待选信贷产品；
    根据所述偏好标签、所述需求标签及每个待选信贷产品的产品标签，从所述多个待选信贷产品中筛选出待推荐的信贷产品。
  17. 根据权利要求16所述的存储介质，其中，所述将所述信贷产品推荐给所述用户之前，所述计算机可读指令被一个或多个处理器时还执行：
    若存在多个需推荐的信贷产品时，根据每个需推荐的信贷产品的产品标签及所述用户的偏好标签和需求标签，分别计算每个需推荐的信贷产品对应的标签匹配度；
    根据每个需推荐的信贷产品的标签匹配度，对所述每个需推荐的信贷产品进行排序。
  18. 根据权利要求16所述的存储介质，其中，所述处理器还执行：
    获取所述用户达成交易的信贷产品的产品标签；
    从所述产品标签中确定出与所述用户的需求标签匹配的产品标签；
    将确定的所述产品标签设置为所述用户的偏好标签；
    将所述偏好标签存储在所述用户对应的用户身份信息中。
  19. 根据权利要求16所述的存储介质，其中，所述计算机可读指令被一个或多个处理器时还执行：
    在预设时长内，记录与所述用户的需求标签匹配的每个产品标签的重复度；
    将重复度大于预设阈值的产品标签设置为所述用户的临时偏好标签；
    在所述临时偏好标签对应的时效时长到达时，从所述用户的所有偏好标签中剔除所述临时偏好标签。
  20. 根据权利要求15-19任一项所述的存储介质，其中，所述计算机可读指令被一个或多个处理器时还执行：
    从信贷产品的交易记录中获取多个信用参数；
    根据所述多个信用参数及每个信用参数对应的权重，重置所述用户的信用指数。
PCT/CN2021/124735 2020-11-16 2021-10-19 一种基于区块链的信贷推荐方法、设备及存储介质 WO2022100382A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202011281830.8A CN112328886A (zh) 2020-11-16 2020-11-16 一种基于区块链的信贷推荐方法、设备及存储介质
CN202011281830.8 2020-11-16

Publications (1)

Publication Number Publication Date
WO2022100382A1 true WO2022100382A1 (zh) 2022-05-19

Family

ID=74317854

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/124735 WO2022100382A1 (zh) 2020-11-16 2021-10-19 一种基于区块链的信贷推荐方法、设备及存储介质

Country Status (2)

Country Link
CN (1) CN112328886A (zh)
WO (1) WO2022100382A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116527230A (zh) * 2023-07-03 2023-08-01 湖南君创融信科技有限公司 一种金融信贷征信数据防泄露方法及系统
CN118172145A (zh) * 2024-05-13 2024-06-11 北京大学 信贷产品推荐方法、装置、存储介质和电子设备

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112328886A (zh) * 2020-11-16 2021-02-05 深圳壹账通智能科技有限公司 一种基于区块链的信贷推荐方法、设备及存储介质
CN113298633A (zh) * 2021-02-08 2021-08-24 中国银联股份有限公司 数据处理方法、实施该方法的系统和计算机可读介质
CN113177843A (zh) * 2021-05-28 2021-07-27 中国银行股份有限公司 基于区块链的跨行贷款业务处理方法及装置
CN113436023A (zh) * 2021-07-06 2021-09-24 中国银行股份有限公司 基于区块链的理财产品推荐方法及装置
CN113434771A (zh) * 2021-07-09 2021-09-24 中国银行股份有限公司 基于区块链的金融资讯推荐方法及区块链中的参与方节点
CN117670423A (zh) * 2023-10-20 2024-03-08 香港中文大学（深圳） 一种奖励分配方法及相关装置

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109656960A (zh) * 2018-09-27 2019-04-19 深圳壹账通智能科技有限公司 信贷业务的智能推荐方法、装置、终端设备及存储介质
CN110033357A (zh) * 2019-04-27 2019-07-19 深圳全信投资管理有限公司 信贷产品推荐方法及系统
CN110969521A (zh) * 2018-09-30 2020-04-07 重庆小雨点小额贷款有限公司 一种贷款方法、装置、服务器及存储介质
CN112328886A (zh) * 2020-11-16 2021-02-05 深圳壹账通智能科技有限公司 一种基于区块链的信贷推荐方法、设备及存储介质

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109767318A (zh) * 2018-12-15 2019-05-17 深圳壹账通智能科技有限公司 贷款产品推荐方法、装置、设备及存储介质

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109656960A (zh) * 2018-09-27 2019-04-19 深圳壹账通智能科技有限公司 信贷业务的智能推荐方法、装置、终端设备及存储介质
CN110969521A (zh) * 2018-09-30 2020-04-07 重庆小雨点小额贷款有限公司 一种贷款方法、装置、服务器及存储介质
CN110033357A (zh) * 2019-04-27 2019-07-19 深圳全信投资管理有限公司 信贷产品推荐方法及系统
CN112328886A (zh) * 2020-11-16 2021-02-05 深圳壹账通智能科技有限公司 一种基于区块链的信贷推荐方法、设备及存储介质

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116527230A (zh) * 2023-07-03 2023-08-01 湖南君创融信科技有限公司 一种金融信贷征信数据防泄露方法及系统
CN116527230B (zh) * 2023-07-03 2023-09-15 湖南君创融信科技有限公司 一种金融信贷征信数据防泄露方法及系统
CN118172145A (zh) * 2024-05-13 2024-06-11 北京大学 信贷产品推荐方法、装置、存储介质和电子设备

Also Published As

Publication number Publication date
CN112328886A (zh) 2021-02-05

Similar Documents

Publication Publication Date Title
WO2022100382A1 (zh) 一种基于区块链的信贷推荐方法、设备及存储介质
US11665072B2 (en) Parallel computational framework and application server for determining path connectivity
US20200005189A1 (en) Cognitive blockchain automation and management
US11676087B2 (en) Systems and methods for vulnerability assessment and remedy identification
WO2019205325A1 (zh) 确定用户风险等级的方法、终端设备及计算机可读存储介质
US10366085B2 (en) System, method, and computer program for audit scoring
CN112465627B (zh) 基于区块链和机器学习的金融借贷审核方法及系统
US20200175403A1 (en) Systems and methods for expediting rule-based data processing
US20190236607A1 (en) Transaction Aggregation and Multiattribute Scoring System
CA3168992A1 (en) Machine-learning techniques to generate recommendations for risk mitigation
CN115080858A (zh) 多方协作场景下的数据推荐方法及装置
US20240211630A1 (en) Data privacy management
US9548996B2 (en) Hybrid engine for generating a recommended security tier
US20210011923A1 (en) Systems and methods for retrieval and qualification of data items and entities in support of retail transactions
CN115914363A (zh) 消息推送方法、装置、计算机设备和存储介质
CN113822704A (zh) 计算优惠费用的方法、装置、电子设备及可读存储介质
CN111401395A (zh) 一种数据处理方法、终端设备及存储介质
US20200402161A1 (en) System and methods for transparent underwriting
US20230419344A1 (en) Attribute selection for matchmaking
CN116611910A (zh) 风险评估方法、装置、计算机设备和存储介质
US20230237572A1 (en) Structuring a Multi-Segment Operation
CN113961766A (zh) 基于联邦学习的数据特征查询方法、装置、设备及介质
CN116911892A (zh) 目标客群识别及竞价方法、装置、计算机设备和存储介质
CN116821479A (zh) 审计程序推荐方法、装置和计算机可读存储介质
CN114820001A (zh) 一种目标客户筛选方法、装置、设备及介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21890909

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 230823)

122 Ep: pct application non-entry in european phase

Ref document number: 21890909

Country of ref document: EP

Kind code of ref document: A1