CN117437028A - Multi-head debt-sharing risk identification method and device for clients, electronic equipment and storage medium - Google Patents
Multi-head debt-sharing risk identification method and device for clients, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN117437028A CN117437028A CN202311380202.9A CN202311380202A CN117437028A CN 117437028 A CN117437028 A CN 117437028A CN 202311380202 A CN202311380202 A CN 202311380202A CN 117437028 A CN117437028 A CN 117437028A
- Authority
- CN
- China
- Prior art keywords
- data
- sharing
- credit
- shared
- debt
- 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 66
- 230000007246 mechanism Effects 0.000 claims abstract description 131
- 239000003999 initiator Substances 0.000 claims abstract description 36
- 230000004927 fusion Effects 0.000 claims abstract description 23
- 238000012545 processing Methods 0.000 claims abstract description 23
- 230000001186 cumulative effect Effects 0.000 claims abstract description 16
- 238000009795 derivation Methods 0.000 claims abstract description 16
- 230000008520 organization Effects 0.000 claims description 11
- 238000004458 analytical method Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 7
- 238000004422 calculation algorithm Methods 0.000 claims description 5
- 238000010801 machine learning Methods 0.000 claims description 5
- 238000012795 verification Methods 0.000 claims description 5
- 238000012935 Averaging Methods 0.000 claims description 4
- 230000006399 behavior Effects 0.000 claims description 4
- 230000008014 freezing Effects 0.000 claims description 4
- 238000007710 freezing Methods 0.000 claims description 4
- 238000004519 manufacturing process Methods 0.000 claims description 4
- 230000000977 initiatory effect Effects 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 6
- 238000010586 diagram Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 10
- 238000005516 engineering process Methods 0.000 description 6
- 238000009825 accumulation Methods 0.000 description 5
- 230000004044 response Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 238000013475 authorization Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000012550 audit Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 210000004899 c-terminal region Anatomy 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013524 data verification Methods 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000004451 qualitative analysis Methods 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/04—Network architectures or network communication protocols for network security for providing a confidential data exchange among entities communicating through data packet networks
- H04L63/0428—Network architectures or network communication protocols for network security for providing a confidential data exchange among entities communicating through data packet networks wherein the data content is protected, e.g. by encrypting or encapsulating the payload
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L9/00—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols
- H04L9/50—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols using hash chains, e.g. blockchains or hash trees
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Computer Security & Cryptography (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- General Business, Economics & Management (AREA)
- Technology Law (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- Computer Hardware Design (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The embodiment of the application discloses a client multi-head liability risk identification method, a device, electronic equipment and a storage medium, wherein the method comprises the following steps: a sharing rule for agreeing on a sharing chain participated by a plurality of institutions; when an initiator initiates a data sharing task on the sharing chain, based on the sharing rule, the initiator obtains the cumulative value of each index of each participant, and the initiator is any mechanism; and processing tasks of a credit-in-credit amount adjustment scene and a post-credit early warning scene in the shared chain by utilizing a multi-head shared debt risk recognition strategy, wherein the multi-head shared debt risk recognition strategy is obtained by carrying out feature derivation, modeling and model fusion on the basis of the shared rule and the data of the plurality of institutions, so that shared debt data elements can be acquired more quickly and flexibly without expense, and the shared debt risk recognition effect is improved.
Description
Technical Field
The present application relates to the field of blockchain technologies, and in particular, to a method and apparatus for identifying multiple-head liability risks of clients, an electronic device, and a storage medium.
Background
The original economic plan of borrowers cannot be smoothly realized due to the changes of macro economic environment, industry policy adjustment and the like; meanwhile, due to the fact that excessive loans are burdened, repayment capability of borrowers is insufficient, probability of default of debt of borrowers increases along with the probability, and especially under a mortgage-free scene, default loss is larger, and multiple-head co-debt becomes one of important index items for monitoring default risk after client loan; the pain points of the multi-head co-debt are monitored mainly in two aspects, as follows:
the problem that the frequency of inquiring personal credit reports is limited is solved, the traditional way for a financial institution to acquire multi-head borrowing information of a client is to inquire the personal credit reports to a central row after the client is authorized, however, the frequency of inquiring by the authorization institution is not more than 1 time per quarter in principle, so that after the borrower is authorized, the credit adjustment cannot be timely performed under the multi-head strategy item after the lending, and the bad account risk is possibly increased;
the financial institution cross-domain data sharing compliance and cost problems are solved, because personal lending information belongs to personal privacy, and data output domain sharing has compliance problems, the privacy computing technology is utilized to realize data value sharing among multiple institutions on the premise that data is not output to help the financial institution identify multi-head lending risks of clients, and policy adjustment is timely made. The privacy computing platforms adopted among the banks are different in manufacturer, and the cost of interconnection and intercommunication is extremely high.
In summary, in the context of increased risk of multiple debt-sharing violations of the C-terminal customer, each financial institution is required to strengthen risk awareness, identify risk and take corresponding measures to reduce risk level, to control risk of violations and bad debt.
Disclosure of Invention
The embodiment of the application provides a client multi-head debt sharing risk identification method, device, electronic equipment and storage medium, which can acquire debt sharing data elements faster and more flexibly without cost expense, and promote the debt sharing risk identification effect.
In a first aspect, an embodiment of the present application provides a method for identifying multiple co-debt risk of a client, where the method includes:
a sharing rule for agreeing on a sharing chain participated by a plurality of institutions;
when an initiator initiates a data sharing task on the sharing chain, based on the sharing rule, the initiator obtains the cumulative value of each index of each participant, and the initiator is any mechanism;
and processing tasks of a credit-in-credit quota adjusting scene and a post-credit early warning scene in the shared chain by utilizing a multi-head shared debt risk recognition strategy, wherein the multi-head shared debt risk recognition strategy is obtained by carrying out feature derivation, modeling and model fusion on the basis of the shared rule and the data of the plurality of institutions.
In an optional implementation manner, where the initiator is a first mechanism and the participant includes three mechanisms, when the initiator initiates a data sharing task on the sharing chain, based on the sharing rule, the initiator obtains a cumulative value of each index of each participant, including:
the first mechanism generates a first random number and records the first random number to the local, and the first random number is added to the fields to be shared of the first mechanism to obtain a first field; the encrypted data of the first field is uplink and sent to a second mechanism;
the second mechanism receives the data sent by the first mechanism, generates a second random number, records the second random number to the local, decrypts the first field, and adds the second random number and the first field to the field to be shared of the second mechanism to obtain a second field; the encrypted data of the second field is uplink and sent to a third mechanism;
the third mechanism and the fourth mechanism execute the operation corresponding to the second mechanism, and the fourth mechanism links the obtained data with the fourth field encrypted and sends the data to the first mechanism;
the first mechanism sends the data obtained from the fourth mechanism to the second mechanism;
The second mechanism decrypts the fourth field, subtracts the second random number and obtains a fifth field; the encrypted data of the fifth field is uplink and sent to the third mechanism;
the third mechanism and a fourth mechanism execute operations corresponding to the second mechanism, and the fourth mechanism links and sends the seventh field encrypted data to the first mechanism;
and the first mechanism receives the data sent by the fourth mechanism, decrypts the seventh field, subtracts the first random number to obtain the cumulative value of each index of each participant, and finishes the data sharing task.
In an alternative embodiment, the rule for assigning sharing chains to which the plurality of institutions participate includes:
initializing the sharing chain, and storing a data transceiving address by each mechanism;
when a new mechanism is added, randomly inserting the new mechanism between the two mechanisms, updating the data receiving and transmitting addresses by the mechanisms before and after the new mechanism, and generating a local configuration file by the new mechanism;
the fields of credit limit, deposit amount and overdue amount in the contract sharing effective period;
a random number production range is contracted;
rules for updating the encryption key and the decryption key by the institutions are agreed;
And appointing the upper limit of the task initiation times of each organization.
In an alternative embodiment, before the task of processing the mid-credit rating scenario and post-credit early warning scenario in the shared chain using the multi-headed co-debt risk identification strategy, the method further comprises:
and performing feature derivation, modeling and model fusion by using the obtained credit line, the paying amount and the overdue amount and the data sources of the institutions, and determining the multi-head co-debt risk identification strategy.
In an optional implementation manner, the determining the multi-head liability risk identification policy by performing feature derivation, modeling and model fusion with the obtained credit line, the payable amount and the overdue amount data, and the data sources of the plurality of institutions includes:
screening out sample data of whether the customer debt is overdue or not based on the credit line, the paying amount and the overdue amount data; using intra-row transaction flow data, combining browsing behaviors of an operator financial application program, civil economic disputes, and E-commerce consumption data, and utilizing a machine learning algorithm to perform modeling analysis to obtain target characteristics;
For the target characteristics, a strong early warning rule is formulated according to service interpretability and trigger risk;
converting the experience judgment of the expert into the weight of each layer of characteristics in the target characteristics to obtain an expert scoring card;
and respectively adopting a voting method, an averaging method and a sequencing method to perform multi-model fusion verification on the existing models, selecting a target scheme, and then based on guest group feature clustering, extracting the multi-head co-debt risk identification strategy.
In an alternative embodiment, the task of processing the in-credit quota scenario and the post-credit early warning scenario in the shared chain by using the multi-head co-debt risk identification strategy includes:
and for the credit amount adjustment scene, adjusting the credit amount of the client based on the multi-head co-debt risk identification policy processing.
In an alternative embodiment, the task of processing the in-credit quota scenario and the post-credit early warning scenario in the shared chain by using the multi-head co-debt risk identification strategy includes:
for the post-credit early warning scene, sending a prompt early warning to a client manager; and carrying out measures of freezing or drawing credit on the line of the client triggering the strong early warning rule.
In a second aspect, an embodiment of the present application provides a customer multi-head liability risk identification device, including:
The contract module is used for agreeing the sharing rules of the sharing chains participated by the plurality of institutions;
the processing module is used for acquiring the cumulative value of each index of each participant on the basis of the sharing rule when the initiator initiates the data sharing task on the sharing chain, wherein the initiator is any mechanism;
and the risk identification module is used for processing tasks of a credit-in-credit amount adjustment scene and a post-credit early warning scene in the shared chain by utilizing a multi-head shared debt risk identification strategy, and the multi-head shared debt risk identification strategy is obtained by carrying out feature derivation, modeling and model fusion on the basis of the shared rule and the data of the plurality of institutions.
In a third aspect, an embodiment of the present application further provides an electronic device, including a processor, an input device, an output device, and a memory, where the processor, the input device, the output device, and the memory are connected to each other, and the memory is configured to store a computer program, where the computer program includes program instructions, and where the processor is configured to invoke the program instructions to perform a method according to the first aspect and any possible implementation manner thereof.
In a fourth aspect, the present embodiments provide a computer storage medium storing a computer program comprising program instructions which, when executed by a processor, cause the processor to perform the method of the first aspect and any one of its possible embodiments.
The embodiment of the application is characterized in that the sharing rule of the sharing chains participated by a plurality of mechanisms is agreed; when an initiator initiates a data sharing task on the sharing chain, based on the sharing rule, the initiator obtains the cumulative value of each index of each participant, and the initiator is any mechanism; the tasks of the credit-in-credit quota adjustment scene and the post-credit early warning scene in the shared chain are processed by utilizing a multi-head credit-in-credit risk recognition strategy, the multi-head credit-in-credit risk recognition strategy is obtained by feature derivation, modeling and model fusion based on the shared rule and the data of a plurality of institutions, and the shared-in-credit data elements can be acquired more quickly and flexibly based on blockchain and zero knowledge proof without cost expense, so that the data safety is ensured, the credit-in-credit risk recognition effect is improved, the scheme is easier to reproduce, and the labor cost required to be input is low.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly described below.
Fig. 1 is a schematic flow chart of a customer multi-head co-debt risk identification method according to an embodiment of the present application;
FIG. 2 is a schematic diagram of a structure for initializing a federated shared chain provided in an embodiment of the present application;
FIG. 3 is a schematic diagram of a federation sharing chain with new members added according to an embodiment of the present application;
fig. 4 is a schematic diagram of a risk identification flow architecture according to an embodiment of the present application;
FIG. 5 is a schematic flow chart of a data sharing task according to an embodiment of the present application;
fig. 6 is a schematic structural diagram of a customer multi-head co-debt risk recognition device according to an embodiment of the present application;
fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all, of the embodiments of the present application. Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the present application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.
All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.
The terms first, second and the like in the description and in the claims of the present application and in the above-described figures, are used for distinguishing between different objects and not for describing a particular sequential order. Furthermore, the terms "comprise" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those listed steps or elements but may include other steps or elements not listed or inherent to such process, method, article, or apparatus.
It is also to be understood that the terminology used in the description of the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should be further understood that the term "and/or" as used in this specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations.
As used in this specification and the appended claims, the term "if" may be interpreted as "when..once" or "in response to a determination" or "in response to detection" depending on the context. Similarly, the phrase "if a determination" or "if a [ described condition or event ] is detected" may be interpreted in the context of meaning "upon determination" or "in response to determination" or "upon detection of a [ described condition or event ]" or "in response to detection of a [ described condition or event ]".
In order to better understand the embodiments of the present application, a method for applying the embodiments of the present application will be described below.
The multi-headed co-debt referred to in the embodiments of the present application refers to the case where a plurality of persons or institutions commonly bear a certain debt. In the financial market, multi-headed co-debts often occur in cases where borrowers are unable to pay back the debt on time, where creditors need to discuss the debt to multiple guarantors, where multiple guarantors need to commonly assume liabilities of the debt, i.e., multi-headed co-debts.
The embodiment of the application relates to a blockchain technology, and the blockchain is used as a decentralized distributed database and is mainly characterized by decentralization, transparency, non-falsification and the like, all transaction records are publicly disclosed, data in the blockchain is non-falsified, once written into the blockchain, the data cannot be falsified or deleted, and the blockchain can be used for completing data storage, verification and audit of all parties.
The zero knowledge proof related in the embodiment of the application is a cryptography technology, which allows one party to prove that a statement is correct to the other party without revealing any extra sensitive information, and can help to realize a trust mechanism of decentralization, and has the advantages of zero knowledge, decentralization, high efficiency, easy realization and the like. The method can be realized by programming an idea or a stored frame, has extremely low landing cost, and can solve the problems of cross-domain data sharing compliance and cost of a fusion mechanism; the data sharing mode can initiate calculation at any time, so that the problem of limited inquiry frequency of the personal credit report can be solved.
The terminal devices mentioned in the embodiments of the present application include, but are not limited to, desktop computers, mobile terminals, which may include various handheld devices with wireless communication capabilities, computing devices such as notebook computers, or other processing devices connected to wireless modems, and so forth.
Referring to fig. 1, a schematic flow chart of a method for identifying multiple co-debt risk of a customer according to an embodiment of the present application is shown in fig. 1, where the method may include:
101. a sharing rule for agreeing on a sharing chain participated by a plurality of institutions;
102. when an initiator initiates a data sharing task on the sharing chain, the initiator obtains the cumulative value of each index of each participant based on the sharing rule, and the initiator is any mechanism;
103. and processing tasks of a credit-in-credit quota adjustment scene and a post-credit early warning scene in the shared chain by utilizing a multi-head shared debt risk recognition strategy, wherein the multi-head shared debt risk recognition strategy is obtained by carrying out feature derivation, modeling and model fusion on the basis of the shared rule and the data of the plurality of institutions.
The execution main body of the client multi-head debt-sharing risk identification method in the embodiment of the application can be a client multi-head debt-sharing risk identification device, can be deployed in a data sharing system, can be a financial system or an air control system, and the processing steps can be executed by terminal equipment or a server.
The shared chain (or alliance shared chain) in the embodiment of the application uses the blockchain technology, and an organization acts as a participant, namely a node in the blockchain, and the node on the chain can follow corresponding intelligent contracts and consensus mechanisms.
The intelligent contract mentioned in the embodiment of the application is a computerized agreement, which can execute the terms of a certain contract, and is realized by the code which is deployed on the shared account book and is executed when certain conditions are met, and the code is used for completing automatic transaction according to actual business requirements, such as inquiring the logistics state of goods purchased by a buyer, and transferring the electronic money of the buyer to the address of a merchant after the buyer signs the goods; of course, the smart contract is not limited to executing the contract for the transaction, and may execute a contract that processes the received information.
Each node in the data sharing system has a node identifier corresponding to the node identifier, and each node in the data sharing system can store the node identifiers of other nodes in the data sharing system, so that the generated block can be broadcast to other nodes in the data sharing system according to the node identifiers of other nodes.
First, a participant engagement needs to be made. The information such as the shared chain structure, shared field, key, etc. which mainly can be agreed to participate in multiple parties, is collectively called as the above-mentioned sharing rule.
In an alternative embodiment, the step 101 includes:
Initializing the sharing chain, and storing data transmitting and receiving addresses by each mechanism;
when a new mechanism is added, randomly inserting the new mechanism between the two mechanisms, updating the data receiving and transmitting addresses by the mechanisms before and after the new mechanism, and generating a local configuration file by the new mechanism;
the fields of credit limit, deposit amount and overdue amount in the contract sharing effective period;
a random number production range is contracted;
rules for updating the encryption key and the decryption key by the plurality of institutions are agreed;
an upper limit of the task initiation times of each organization is agreed.
Specifically, the federation shared chain is initialized, and each organization locally stores an address of an organization receiving and transmitting data, and the address is used for indicating a node address for receiving the data and a node address for transmitting the data.
Reference may be made to a schematic diagram of the structure of an initializing federated shared chain as shown in FIG. 2. As shown in FIG. 2, the federated shared chain includes four organizations, organization A, organization B, organization C, and organization D, respectively, where arrows represent their data transmission paths.
Fig. 3 is a schematic structural diagram of a federation sharing chain with new members added according to an embodiment of the present application. As shown in fig. 3, when a new member E joins, it can be understood that it is inserted randomly between 2 nodes, for example, between the mechanism a and the mechanism D in fig. 3, and the front-back mechanism (i.e., the mechanism a and the mechanism D) of the new mechanism locally updates the data transceiving address, and the new mechanism generates the local configuration file.
In the embodiment of the application, the number of the nodes in the shared chain is not limited, and node addition, node deletion, structure adjustment and the like can be performed according to the needs.
Specifically, 3 fields of credit, deposit and overdue amount in the sharing effective period can be agreed, for example, unified fields are named as x 1-x 3, 2-bit effective decimal is reserved, and the default is 0 if no client exists.
Alternatively, a random number production range, for example, an integer of-1000000 to +1000000 may be contracted as needed.
The rules for updating the key may include an update sequence, an update time, an update frequency, etc., and may, for example, agree that each party updates the encryption key and the decryption key file in turn and periodically, with the frequency being one month for updating the encryption decryption key, and synchronize to each party.
In the data sharing scenario, any mechanism in the sharing chain may be a task initiator, and the task initiator may obtain the cumulative value of each index of each participant. The sum value is an accumulation sum, namely the accumulation is that the ≡series data is added to ≡sides of ≡variables, and finally an accumulation result is obtained. The embodiment of the application can be combined with a zero knowledge proof technology to realize safe and rapid data sharing, and detailed examples will be described later.
In the embodiment of the application, a multi-head shared debt risk identification strategy is further set, and risk identification can be performed in data interaction of a shared chain.
Prior to step 103, the method further includes:
and performing feature derivation, modeling and model fusion by using the obtained credit limit, the deposit amount and the overdue amount and the data sources of the institutions to determine the multi-head co-debt risk identification strategy.
Based on a shared chain architecture and a data sharing rule, under the condition of permission, all participants combine data sources accumulated by themselves to conduct feature derivation and modeling by utilizing a large amount of acquired shared data, and a multi-head shared debt risk identification strategy conforming to self quotation is supplemented, so that the method can be used for risk identification management in a credit amount adjustment scene, a post-credit early warning scene and the like.
In an alternative embodiment, the step 103 includes:
and for the credit amount adjustment scene, adjusting the credit amount of the client based on the multi-head co-debt risk identification strategy processing.
Optionally, the step 103 further includes:
for the post-credit early warning scene, a prompting early warning is sent to a client manager; and (5) performing measures of freezing or drawing credit on the line of the client triggering the strong early warning rule.
In the embodiment of the application, the risk identification service requirement can be combined, a proper machine learning algorithm or model can be selected according to the requirement to carry out modeling training, a multi-head co-debt risk identification strategy is obtained to manage the system risk, and an alarm or other management measures are implemented.
In an alternative embodiment, the determining the multi-head liability risk identification policy by performing feature derivation, modeling and model fusion using the obtained credit line, the payable amount, and the overdue amount data, and the data sources of the plurality of institutions includes:
screening out sample data of whether the client debt is overdue or not based on the credit limit, the paying amount and the overdue amount data; using intra-row transaction flow data, combining browsing behaviors of an operator financial application program, civil economic disputes, and E-commerce consumption data, and utilizing a machine learning algorithm to perform modeling analysis to obtain target characteristics;
for the target characteristics, a strong early warning rule is formulated according to service interpretability and trigger risk;
converting the experience judgment of the expert into the weight of each layer of characteristics in the target characteristics to obtain an expert scoring card;
And respectively adopting a voting method, an averaging method and a sequencing method to perform multi-model fusion verification on the existing models, selecting a target scheme, and then based on guest group feature clustering, extracting the multi-head co-debt risk identification strategy.
The above target features can be understood as high-distinction features or combination features, among others. The strong early warning rule is mainly formulated for the characteristics of strong service interpretability and large triggering risk. For multi-model fusion verification, a method for use can be selected according to needs, an optimal scheme is selected, finally, rule strategies are extracted based on guest group feature clustering, and the embodiment of the application is not limited to the method.
Referring to fig. 4, fig. 4 is a schematic diagram of a risk identification flow architecture according to an embodiment of the present application.
Specifically, risk identification in the embodiment of the application mainly includes three aspects of modeling analysis, model fusion and scene application:
modeling analysis: traditional multi-head debt identification often occurs before lending, and strong expert rule interception is used, so that overdue data accumulation of almost no debt sample is caused; based on the structure setting, the Y samples of whether the customer debt is overdue or not can be selected in a crossed mode based on trust, paying and overdue data value sharing of a plurality of institutions, after a certain amount of Y samples are accumulated, on the premise of obtaining authorization, in-line transaction flow data are used, data such as operator financial app browsing behaviors, civil economic disputes, electronic commerce consumption and the like are combined, and machine learning algorithm modeling analysis is utilized to find out high-discrimination features or combination features.
Model fusion: after the characteristics or the combined characteristics with high discrimination are obtained, a strong early warning rule is formulated for the characteristic combination with strong service interpretability and large triggering risk; and the analytic hierarchy process can be adopted to convert the experience judgment of each business expert into the weight of each layer of characteristics to obtain an expert scoring card; and respectively carrying out multi-model fusion verification on the existing models by adopting a voting method, an averaging method, a sorting method and the like, selecting an optimal scheme, and finally extracting a rule strategy based on guest group feature clustering.
Scene application: the credit amount adjusting scene can adjust the credit amount of the clients based on the rule result so as to reduce the default risk caused by the expansion of the money release of the risk clients; and in the post-credit early warning scene, for the clients triggering the quota adjustment rules, prompt early warning can be sent to a client manager, and for the clients triggering the strong early warning rules, measures such as quota freezing, loan drawing and the like can be carried out.
The analytic hierarchy process (Analytic Hierarchy Process, AHP) referred to in the examples of the present application is a systematic, hierarchical analysis method combining qualitative and quantitative analysis. The method is essentially to the complex decision problem, and the thinking process of decision is mathematical by using less quantitative information, so that a simple decision method is provided for the decision problem with multiple targets, multiple criteria or no structural characteristics. The root of the analytic hierarchy process is a scoring process: and determining indexes, scoring indexes of different schemes, determining weights for the indexes, and processing the unknown evaluation of the data.
The data sharing flow related to the foregoing will be exemplified below.
In an alternative embodiment, where the initiator is a first institution and the participant includes three institutions, the step 103 includes:
the first mechanism generates a first random number and records the first random number to the local, and the first random number is added to the fields to be shared of the first mechanism to obtain a first field; the encrypted data of the first field is uplink and sent to a second mechanism;
the second mechanism receives the data sent by the first mechanism, generates a second random number, records the second random number to the local, decrypts the first field, and adds the second random number and the first field to the field to be shared of the second mechanism to obtain a second field; the encrypted data of the second field is uplink and sent to a third mechanism;
the third mechanism and the fourth mechanism execute the operation corresponding to the second mechanism, and the fourth mechanism links the obtained data with the fourth field encrypted and sends the data to the first mechanism;
the first means transmits the data obtained from the fourth means to the second means;
the second mechanism decrypts the fourth field and subtracts the second random number to obtain a fifth field; the data after the encryption of the fifth field is uplink and sent to the third mechanism;
The third mechanism and a fourth mechanism execute operations corresponding to the second mechanism, and the fourth mechanism links and sends the data with the seventh field encrypted to the first mechanism;
and the first mechanism receives the data sent by the fourth mechanism, decrypts the seventh field, subtracts the first random number to obtain the cumulative value of each index of each participant, and finishes the data sharing task.
Fig. 5 is a schematic flow chart of a data sharing task according to an embodiment of the present application. As shown in fig. 5, assume that, for example, a shared chain with four institutions as participants, that is, institutions a to D may correspond to the first institution to the fourth institution, respectively, and a specific data sharing flow is as follows:
data sharing task slave machineMechanism A initiates, mechanism A generates a random number t a And records to the local, the random number x1 is added to the field to be shared a x1+t a 、x2 a +t a 、x3 a +t a Obtain X1 a 、X2 a 、X3 a The method comprises the steps of carrying out a first treatment on the surface of the X1 is to a 、X2 a 、X3 a The encrypted data is sent to institution B.
Mechanism B receives the data sent by mechanism A and generates a random number t b And recorded locally, decrypted to obtain X1 a 、X2 a 、X3 a The fields to be shared are added with random numbers and data x1 of a mechanism A b +t b +X1 a 、x2 b +t b +X2 a 、x3 b +t b +X3 a Obtain X1 b 、X2 b 、X3 b The method comprises the steps of carrying out a first treatment on the surface of the X1 is to b 、X2 b 、X3 b The encrypted data is sent to the institution C.
Mechanism C, D operates as mechanism B, with the final mechanism D encrypting X1 d 、X2 d 、X3 d And uplinked and sent to institution a.
After receiving the data of the structure D, the mechanism A does not do any operation and sends the data to the mechanism B.
Mechanism B receives the data of structure A to obtain X1 d 、X2 d 、X3 d Subtracting the locally recorded random number X1 d -t b 、X2 d -t b 、X3 d -t b Denoted as X1 b 、X2` b 、X3` b The method comprises the steps of carrying out a first treatment on the surface of the X1' is taken as the main component b 、X2` b 、X3` b The encrypted data is sent to the institution C.
Mechanism C, D operates as mechanism B, with final mechanism D encrypting X1 d 、X2` d 、X3` d And uplinked and sent to institution a.
After the mechanism A receives the structure D data, decrypting to obtain X1 d 、X2` d 、X3` d Subtracting the locally recorded random number X1 d -t a 、X2` d -t a 、X3` d -t a Denoted as X1 a 、X2` a 、X3` a The method comprises the steps of carrying out a first treatment on the surface of the Namely X1 a 、X2` a 、X3` a Respectively x1 a +x1 b +x1 c +x1 d 、x2 a +x2 b +x2 c +x2 d 、x3 a +x3 b +x3 c +x3 d The data sharing task ends.
For shared chains of other structures (e.g., different numbers of organizations), the data sharing step may refer to the above step and so on, and will not be described herein.
The multi-head co-debt risk identification method for the clients in the embodiment of the application is innovation in a business mode, and can help each participating mechanism to reduce cost and enhance efficiency; traditionally, the shared debt information is obtained, and only personal credit reports can be inquired through a central row or data purchase data can be obtained from third parties; however, the personal credit report has inquiry limit, and the inquiry is carried out 1 time in each quarter, the third party data is deduced through the calling records of the clients of the third party data, and the credibility and coverage are insufficient; after the data acquisition mode is improved, the more alliance members are, the more rapid, the more complete and flexible the data elements can be acquired, and no data expense is needed.
According to the client multi-head debt sharing risk identification method, the debt sharing risk identification effect is greatly improved; traditional multi-head debt identification often occurs before lending, and strong expert rule interception is used, so that overdue data accumulation of almost no debt sample is caused; and the early warning efficiency is low after the lending is affected by the data query frequency; the credit, paying and overdue data value sharing of the alliance organization after improvement is basically increased, modeling analysis can be carried out, the default risk caused by insufficient customer repayment capability can be greatly reduced, and the post-loan early warning efficiency is improved.
The client multi-head debt sharing risk identification method in the embodiment of the application is easy to reproduce, the labor cost required to be input is extremely low, the problem of interconnection and intercommunication cost caused by different bottom technical routes of privacy calculation system construction of each institution can be avoided, and meanwhile, data value sharing can be realized without additional cost input.
Referring to fig. 6, fig. 6 is a schematic structural diagram of a customer multi-head co-debt risk recognition device according to an embodiment of the present application. As shown in fig. 6, the customer multi-headed co-debt risk recognition apparatus 600 includes:
A contract module 610 for agreeing on sharing rules of a sharing chain in which a plurality of institutions participate;
a processing module 620, configured to, when an initiator initiates a data sharing task on the sharing chain, obtain, based on the sharing rule, a cumulative value of each index of each participant, where the initiator is any mechanism;
the risk recognition module 630 is configured to process tasks of the in-credit quota scenario and the post-credit early warning scenario in the shared chain by using a multi-head co-debt risk recognition policy, where the multi-head co-debt risk recognition policy is obtained by performing feature derivation, modeling and model fusion based on the shared rule and the data of the plurality of institutions.
According to the specific implementation manner of the embodiment of the present application, the relevant steps in the embodiment shown in fig. 1 or fig. 5 may be performed by respective modules in the customer multi-headed co-debt risk recognition device 600 shown in fig. 6, which is not described herein.
Through the client multi-head debt sharing risk identification device 600 in the embodiment of the application, the client multi-head debt sharing risk identification device 600 can agree on sharing rules of sharing chains participated by a plurality of institutions; when an initiator initiates a data sharing task on the sharing chain, based on the sharing rule, the initiator obtains the cumulative value of each index of each participant, and the initiator is any mechanism; the tasks of the credit-in-credit quota adjustment scene and the post-credit early warning scene in the shared chain are processed by utilizing a multi-head credit-in-credit risk recognition strategy, the multi-head credit-in-credit risk recognition strategy is obtained by feature derivation, modeling and model fusion based on the shared rule and the data of a plurality of institutions, and the shared-in-credit data elements can be acquired more quickly and flexibly based on blockchain and zero knowledge proof without cost expense, so that the data safety is ensured, the credit-in-credit risk recognition effect is improved, the scheme is easier to reproduce, and the labor cost required to be input is low.
Referring to fig. 7, fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure. As shown in fig. 7, the electronic device 700 includes a processor 701 and a memory 702, wherein the electronic device 700 may further include a bus 703, the processor 701 and the memory 702 may be connected to each other through the bus 703, and the bus 703 may be a peripheral component interconnect standard (Peripheral Component Interconnect, PCI) bus or an extended industry standard architecture (Extended Industry Standard Architecture, EISA) bus, or the like. The bus 703 may be classified into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one thick line is shown in fig. 7, but not only one bus or one type of bus. The electronic device 700 may further include an input-output device 704, where the input-output device 704 may include a display screen, such as a liquid crystal display screen. Memory 702 is used to store one or more programs that include instructions; the processor 701 is configured to invoke instructions stored in the memory 702 to perform some or all of the steps of a customer multi-headed co-debt risk identification method in the embodiment shown in fig. 1 or the flow of a data sharing task in the embodiment shown in fig. 5.
It should be appreciated that in embodiments of the present application, the processor 701 may be a central processing unit (Central Processing Unit, CPU), which may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), off-the-shelf programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The input device 702 may include a touch pad, a fingerprint sensor (for collecting fingerprint information of a user and direction information of a fingerprint), a microphone, etc., and the output device 703 may include a display (LCD, etc.), a speaker, etc.
The memory 704 may include read only memory and random access memory, and provides instructions and data to the processor 701. A portion of memory 704 may also include non-volatile random access memory. For example, the memory 704 may also store information of device type.
With the electronic device 700 of the embodiment of the present application, the electronic device 700 agrees on the sharing rules of the sharing chains that the plurality of institutions participate in; when an initiator initiates a data sharing task on the sharing chain, based on the sharing rule, the initiator obtains the cumulative value of each index of each participant, and the initiator is any mechanism; the tasks of the credit-in-credit quota adjustment scene and the post-credit early warning scene in the shared chain are processed by utilizing a multi-head credit-in-credit risk recognition strategy, the multi-head credit-in-credit risk recognition strategy is obtained by feature derivation, modeling and model fusion based on the shared rule and the data of a plurality of institutions, and the shared-in-credit data elements can be acquired more quickly and flexibly based on blockchain and zero knowledge proof without cost expense, so that the data safety is ensured, the credit-in-credit risk recognition effect is improved, the scheme is easier to reproduce, and the labor cost required to be input is low.
The present application also provides a computer storage medium storing a computer program for electronic data exchange, the computer program causing a computer to execute part or all of the steps of any one of the customer multi-headed co-debt risk identification methods described in the above method embodiments.
In the foregoing embodiments, the descriptions of the embodiments are emphasized, and for parts of one embodiment that are not described in detail, reference may be made to related descriptions of other embodiments.
In the several embodiments provided in this application, it should be understood that the disclosed apparatus may be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative, such as the division of the modules, merely a logical function division, and there may be additional manners of dividing actual implementations, such as multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or modules, which may be in electrical or other forms.
The modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical modules, i.e., may be located in one place, or may be distributed over a plurality of network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
The integrated modules, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer readable memory. Based on this understanding, the technical solution of the present invention may be embodied essentially or partly in the form of a software product, or all or part of the technical solution, which is stored in a memory, and includes several instructions for causing a computer device (which may be a personal computer, a server, a network device, or the like) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned memory includes: a U-disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a removable hard disk, a magnetic disk, or an optical disk, or other various media capable of storing program codes.
Claims (10)
1. A method for identifying multiple-headed co-debt risk of a customer, the method comprising:
a sharing rule for agreeing on a sharing chain participated by a plurality of institutions;
when an initiator initiates a data sharing task on the sharing chain, based on the sharing rule, the initiator obtains the cumulative value of each index of each participant, and the initiator is any mechanism;
and processing tasks of a credit-in-credit quota adjusting scene and a post-credit early warning scene in the shared chain by utilizing a multi-head shared debt risk recognition strategy, wherein the multi-head shared debt risk recognition strategy is obtained by carrying out feature derivation, modeling and model fusion on the basis of the shared rule and the data of the plurality of institutions.
2. The method according to claim 1, wherein, in the case that the initiator is a first mechanism and the participant includes three mechanisms, when the initiator initiates a data sharing task on the sharing chain, the initiator obtains a cumulative value of each index of each participant based on the sharing rule, including:
the first mechanism generates a first random number and records the first random number to the local, and the first random number is added to the fields to be shared of the first mechanism to obtain a first field; the encrypted data of the first field is uplink and sent to a second mechanism;
The second mechanism receives the data sent by the first mechanism, generates a second random number, records the second random number to the local, decrypts the first field, and adds the second random number and the first field to the field to be shared of the second mechanism to obtain a second field; the encrypted data of the second field is uplink and sent to a third mechanism;
the third mechanism and the fourth mechanism execute the operation corresponding to the second mechanism, and the fourth mechanism links the obtained data with the fourth field encrypted and sends the data to the first mechanism;
the first mechanism sends the data obtained from the fourth mechanism to the second mechanism;
the second mechanism decrypts the fourth field, subtracts the second random number and obtains a fifth field; the encrypted data of the fifth field is uplink and sent to the third mechanism;
the third mechanism and a fourth mechanism execute operations corresponding to the second mechanism, and the fourth mechanism links and sends the seventh field encrypted data to the first mechanism;
and the first mechanism receives the data sent by the fourth mechanism, decrypts the seventh field, subtracts the first random number to obtain the cumulative value of each index of each participant, and finishes the data sharing task.
3. The method of claim 1, wherein the agreeing on the sharing rules of the sharing chain in which the plurality of institutions participate comprises:
initializing the sharing chain, and storing a data transceiving address by each mechanism;
when a new mechanism is added, randomly inserting the new mechanism between the two mechanisms, updating the data receiving and transmitting addresses by the mechanisms before and after the new mechanism, and generating a local configuration file by the new mechanism;
the fields of credit limit, deposit amount and overdue amount in the contract sharing effective period;
a random number production range is contracted;
rules for updating the encryption key and the decryption key by the institutions are agreed;
and appointing the upper limit of the task initiation times of each organization.
4. The method of claim 1, wherein prior to the task of processing the mid-credit rating scenario and post-credit warning scenario in the shared chain with the multi-headed co-debt risk identification strategy, the method further comprises:
and performing feature derivation, modeling and model fusion by using the obtained credit line, the paying amount and the overdue amount and the data sources of the institutions, and determining the multi-head co-debt risk identification strategy.
5. The method of claim 4, wherein the determining the multi-headed co-debt risk identification policy using the obtained credit, the payable amount, and the overdue amount data, and the data sources of the plurality of institutions, comprises:
Screening out sample data of whether the customer debt is overdue or not based on the credit line, the paying amount and the overdue amount data; using intra-row transaction flow data, combining browsing behaviors of an operator financial application program, civil economic disputes, and E-commerce consumption data, and utilizing a machine learning algorithm to perform modeling analysis to obtain target characteristics;
for the target characteristics, a strong early warning rule is formulated according to service interpretability and trigger risk;
converting the experience judgment of the expert into the weight of each layer of characteristics in the target characteristics to obtain an expert scoring card;
and respectively adopting a voting method, an averaging method and a sequencing method to perform multi-model fusion verification on the existing models, selecting a target scheme, and then based on guest group feature clustering, extracting the multi-head co-debt risk identification strategy.
6. The method of claim 3, wherein the task of processing the mid-credit rating scenario and post-credit warning scenario in the shared chain using a multi-headed co-debt risk identification strategy comprises:
and for the credit amount adjustment scene, adjusting the credit amount of the client based on the multi-head co-debt risk identification policy processing.
7. The method of claim 3, wherein the task of processing the mid-credit rating scenario and post-credit warning scenario in the shared chain using a multi-headed co-debt risk identification strategy comprises:
for the post-credit early warning scene, sending a prompt early warning to a client manager; and carrying out measures of freezing or drawing credit on the line of the client triggering the strong early warning rule.
8. A customer multi-headed co-debt risk identification device, comprising:
the contract module is used for agreeing the sharing rules of the sharing chains participated by the plurality of institutions;
the processing module is used for acquiring the cumulative value of each index of each participant on the basis of the sharing rule when the initiator initiates the data sharing task on the sharing chain, wherein the initiator is any mechanism;
and the risk identification module is used for processing tasks of a credit-in-credit amount adjustment scene and a post-credit early warning scene in the shared chain by utilizing a multi-head shared debt risk identification strategy, and the multi-head shared debt risk identification strategy is obtained by carrying out feature derivation, modeling and model fusion on the basis of the shared rule and the data of the plurality of institutions.
9. An electronic device comprising a processor, an input device, an output device, and a memory, the processor, the input device, the output device, and the memory being interconnected, wherein the memory is configured to store a computer program comprising program instructions, the processor being configured to invoke the program instructions to perform the method of any of claims 1-7.
10. A computer storage medium storing a computer program comprising program instructions which, when executed by a processor, cause the processor to perform the method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311380202.9A CN117437028A (en) | 2023-10-23 | 2023-10-23 | Multi-head debt-sharing risk identification method and device for clients, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311380202.9A CN117437028A (en) | 2023-10-23 | 2023-10-23 | Multi-head debt-sharing risk identification method and device for clients, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117437028A true CN117437028A (en) | 2024-01-23 |
Family
ID=89549175
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311380202.9A Pending CN117437028A (en) | 2023-10-23 | 2023-10-23 | Multi-head debt-sharing risk identification method and device for clients, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117437028A (en) |
-
2023
- 2023-10-23 CN CN202311380202.9A patent/CN117437028A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Syed et al. | A comparative analysis of blockchain architecture and its applications: Problems and recommendations | |
| Alam et al. | Blockchain-based Initiatives: Current state and challenges | |
| US11151566B2 (en) | Authentication and fraud prevention in provisioning a mobile wallet | |
| US10142312B2 (en) | System for establishing secure access for users in a process data network | |
| US10026118B2 (en) | System for allowing external validation of data in a process data network | |
| US20180075527A1 (en) | Credit score platform | |
| Andrew et al. | Blockchain for healthcare systems: Architecture, security challenges, trends and future directions | |
| CN108122159A (en) | A kind of factoring information processing method and system based on block chain | |
| CN111164629A (en) | Methods, apparatus, and computer-readable media for compliance-aware tokenization and control of asset value | |
| KR101876674B1 (en) | Method of managing common account using block chain and system performing the same | |
| US20220342958A1 (en) | Distributed systems for intelligent resource protection and validation | |
| Jani | Smart contracts: Building blocks for digital transformation | |
| US11354669B2 (en) | Collaborative analytics for fraud detection through a shared public ledger | |
| CN113568973B (en) | Financial credit investigation data sharing method and device based on blockchain and federal learning | |
| US11227287B2 (en) | Collaborative analytics for fraud detection through a shared public ledger | |
| CN113382405A (en) | Network space information security control method and application | |
| CN111126987B (en) | Resource transfer information processing method and device, storage medium and electronic device | |
| CN110310125A (en) | Solicit contributions donations authentication method, system, block platform chain and storage medium | |
| Dash et al. | Artificial intelligence models for blockchain-based intelligent networks systems: Concepts, methodologies, tools, and applications | |
| CN115080858A (en) | Data recommendation method and device under multi-party collaboration scene | |
| US11831666B2 (en) | Blockchain data breach security and cyberattack prevention | |
| CN112702410B (en) | Evaluation system, method and related equipment based on blockchain network | |
| US20200175562A1 (en) | Gem trade and exchange system and previous-block verification method for block chain transactions | |
| Conley | Blockchain as a decentralized mechanism for financial inclusion and economic mobility | |
| US20230070625A1 (en) | Graph-based analysis and visualization of digital tokens |
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 |