CN111461875A - Multi-scenario staged automatic credit method based on decision engine - Google Patents
Multi-scenario staged automatic credit method based on decision engine Download PDFInfo
- Publication number
- CN111461875A CN111461875A CN202010284736.1A CN202010284736A CN111461875A CN 111461875 A CN111461875 A CN 111461875A CN 202010284736 A CN202010284736 A CN 202010284736A CN 111461875 A CN111461875 A CN 111461875A
- Authority
- CN
- China
- Prior art keywords
- user
- credit
- approval
- decision engine
- product
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/103—Workflow collaboration or project management
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- General Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- Finance (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Technology Law (AREA)
- Data Mining & Analysis (AREA)
- Development Economics (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention relates to a multi-scenario staged automatic credit method based on a decision engine, which comprises the following steps: and (2) in stages: A. collecting a user face image and user input information to carry out user real-name authentication; B. the decision engine carries out credit approval according to the personal information of the user; C. obtaining derived data according to basic data of the pedestrian, and judging whether to grant credit to the user; D. the decision engine judges whether the withdrawal application of the user passes or not according to the product information and the user information; E. the overdue users are classified and distributed to the collection urging personnel through the post-loan collection urging model; multi-scene: b, the description of each product is approximately the same, and the rejection conditions of the credit approval are different; products of the same product group are uniformly granted or rejected; and D, individually modeling the personalized products, and using the universal model for the universal products. The invention can automatically approve the user credit application under multiple scenes, greatly reduces manual participation, improves the working efficiency and effectively realizes multi-stage substantive credit.
Description
Technical Field
The invention relates to a data processing and data interaction method in the field of internet finance, in particular to a multi-scenario staged automatic credit method based on a decision engine.
Background
With the rapid development of internet finance, the consumption concept of people is changed, so that the number of the online credit loan population is increased sharply, and the demand of online real-time examination and approval is increased day by day. At present, the flow platform of the internet needs to realize profit through flow showing, business model data accumulation of different flow platforms has great difference, and for internet banks, most of flow platforms need to be contained simultaneously to help the flow platform to show. According to the regulatory requirements of the industry, a large number of P2P flow platforms are transformed into small credit companies, and the small credit companies need to rely on banks for fund management and loan, and also need internet banks to accommodate the platform scenes. Therefore, the integration of multiple scenes and the automatic approval are realized, which is a necessary trend of the internet banking business development. In addition, customer experience is improved, customer viscosity is improved, bank fund safety is guaranteed, and staged control is also needed.
The prior art that has been disclosed mainly aims at explaining the implementation logic inside the decision engine, for example, only the internal components of the decision engine software are listed one by one, or as in the patent application laid open: the merchant loan 721 big data wind control model (application number: 201910750529.8) based on the scene is a technical scheme taking a basic flow of a product as a technical scheme, and has the core points of only data source distribution, no multi-scene mode and unclear stage control.
Disclosure of Invention
The invention provides a multi-scenario staged automatic credit method based on a decision engine, which aims to solve the technical problem of carrying out credit approval simultaneously in multiple scenarios, realize multi-stage substantive credit and improve customer experience.
The invention relates to a multi-scenario staged automatic credit method based on a decision engine, which comprises the following steps:
and (2) in stages:
A. and (3) user real name authentication: the method comprises the steps that facial images of a user are collected through a camera, and the user inputs personal information through input equipment; deploying a real-name authentication model in a server through a decision engine, wherein the real-name authentication model processes a real-name authentication request of a user according to an acquired facial image of the user and personal information of the user, automatically passes or rejects the real-name authentication request of the user, and sends the user information passing the real-name authentication to the next step;
B. approval of credit: intercepting corresponding information from personal information input by a user, sending the intercepted information to a decision engine, setting product information, a credit approval process, a credit approval model and a preset refusal condition of the credit approval corresponding to each product in the decision engine, judging the intercepted information through the credit approval model and the refusal condition of the credit approval corresponding to the product applied by the user, if the judgment result is that the credit approval of the user is refused, ending the credit process, otherwise, entering the next step;
C. according to basic data of a pedestrian to the user, corresponding derivative data are obtained through calculation of a relevant model, the derivative data are transmitted to the corresponding model by a decision engine to judge whether the user is credited, if not, a credit process is ended, and if the user agrees to credit, the next step is carried out;
D. carrying out cash withdrawal and examination and approval: the decision engine judges according to the information of the product applied by the user and the user information, determines whether to pass the withdrawal application of the user or not, or whether to freeze the line of the user, if the user does not pass the withdrawal application or the line is frozen, the credit process is ended, and if the user passes the withdrawal approval, the withdrawal result of the user is determined through a comprehensive evaluation model;
E. post-loan collection: a post-loan collection urging model is deployed through a decision engine, overdue users are divided into different case types and distributed to different collection urging personnel;
multi-scene:
in the step B, the product descriptions of the products in the decision engine are approximately the same, and the rejection conditions of the credit approval of the products are different; some products have more different credit approval conditions and approval processes. According to different scenes and requirements, the trust approval strategies of products can be different, and the same strategy can be shared, so that the requirements of different scenes can be met, and the online iteration speed can be increased.
Products with the same or similar properties are classified into the same product group, and in the step B and the step C, if the product applied by the user is refused to credit the user, the credit of the user is refused to be credited to all other products of the product group where the applied product is located;
in the step D, for the personalized product, the decision engine carries out presentation examination and approval on the user through the individual model of the personalized product, and for the universal product decision engine carries out presentation examination and approval on the user through the universal model; if the user refuses to withdraw the application or freeze the quota, the user refuses to withdraw or freeze the quota for the product that the user applies for withdrawing the current and all other products in the product group where the withdrawal product is located.
The decision engine is an application program developed by IBM company and used for managing business rules, and can realize real-time system automatic decision by issuing various judgment conditions and models for the deployment of the program. When the real-name authentication is carried out on the user, the traditional mode is that the user photos and the identity card photos are compared one by one in a manual mode. And then determining whether the user applies and is granted credit, and the amount and interest rate of the given amount of the user through the credit approval. The derivative data refers to some new data obtained through processing and calculation of basic data of a bank, such as income level of a user deduced according to a user loan and a public deposit record stored by the bank, and further such as latest monthly payment amount of the public deposit, balance of a human business loan, duration of the first public deposit payment before and after the current time, and the derivative data are all not contained in original data of the bank and belong to the derivative data. And determining whether to pass the withdrawal application of the user by a withdrawal approval step, and determining whether to freeze the quota of the user when refusing. And classifying and distributing the collection users in the final post-credit collection stage.
The credit approval method can obviously reduce the manual participation degree in the credit approval process, divides each link of the credit approval, fuses credit approval under multiple scenes, and solves the traditional single-scene credit approval process.
Furthermore, the invention also comprises a step of batch quota adjustment for the user in the loan, and the credit limit or interest rate of the user in single or batch is adjusted for the user which passes the real-name authentication and is the existing quota stock in the preset time period.
Further, when the amount is adjusted in batches in the multi-scenario loan, the adjustment of the credit line or interest rate comprises the adjustment of products distinguished or not distinguished for the user. Each product has a set of independent approval process, but the approval strategies can be shared, or different approval strategies can be deployed in the approval process of different products. After the approval strategies are iterated and on-line, the shared approval strategies can be reused, multi-scene deployment can be completed quickly, and the iteration speed of the approval strategies is increased.
Further, in step a, after the real-name authentication model processes the real-name authentication request of the user, the in-doubt user information is transferred to manual review, and the rest automatically pass or reject the real-name authentication request of the user. Thereby greatly reducing the workload of manpower.
Further, in the step C, the decision engine assembles and stores each derived data into a character string in a JSON format, and transmits the character string to the next approval process; after receiving the character string, the next approval process parses the character string into a structured derived data field, so that the model in the approval process can directly apply the derived data field, for example, corresponding assignment can be directly performed on the derived data field. The JSON character string format derived data assembly form ensures that the meaning of each derived data is not reflected here, and has certain confidentiality.
Further, in step C, the corresponding model corrects the bank credit limit and the bank interest rate corresponding to the user according to the judgment of the user, so as to obtain the final credit limit and the bank interest rate of the user. The credit limit and the pedestrian rate of the user are matched with the current state of the user, and the method is more accurate.
Preferably, for the remaining in-doubt users, the corresponding model sends the trust approval of the user to the corresponding manual approver according to different approval classifications.
And step D, when the user is presented and approved, if the data in other data sources need to be called, judging the data source needing to be called according to the existing user information, and transmitting the identifier of the data source needing to be called to the next sub-approval process for determining the data source needing to be called by the next sub-approval process.
All the models related to the invention can be implemented by using the existing models in the field or by the principle of the existing models by the person skilled in the art, and the part is not the innovation of the invention.
The multi-scene staged automatic credit method based on the decision engine can automatically approve the user credit application in multiple scenes, greatly reduces manual participation, improves the working efficiency, and through tests, compared with the prior art, the multi-scene staged automatic credit method can reduce the manual participation rate in the credit approval process to be below 0.5 percent, effectively realizes multi-stage substantial credit, and can more quickly access more flow platforms through the multi-scene fusion technology, thereby expanding the service scale and reducing the non-systematic risk.
The present invention will be described in further detail with reference to the following examples. This should not be understood as limiting the scope of the above-described subject matter of the present invention to the following examples. Various substitutions and alterations according to the general knowledge and conventional practice in the art are intended to be included within the scope of the present invention without departing from the technical spirit of the present invention as described above.
Drawings
FIG. 1 is a flow chart of a method of multi-scenario phased automated credit based on a decision engine of the present invention.
Detailed Description
The decision engine based multi-scenario phased automated credit method of the present invention as shown in FIG. 1 comprises:
and (2) in stages:
A. and (3) user real name authentication: the camera is used for collecting facial images of a user, and the user inputs personal information through the input equipment. And deploying a real-name authentication model in the server through a decision engine, wherein the real-name authentication model processes a real-name authentication request of the user according to the collected facial image of the user and the personal information of the user, automatically passes or rejects the real-name authentication request of the user, and sends the information of the user passing the real-name authentication to the next step. The residual information of a small amount of doubtful users is transferred to manual work for manual examination, so that the workload of the manual work is greatly reduced, and whether all the examination users are real-name persons or not is avoided.
The decision engine is an application program developed by IBM company and used for managing business rules, and can realize real-time system automatic decision by issuing various judgment conditions and models for the deployment of the program.
B. Approval of credit: corresponding information, such as the age, sex, high risk area, unit information filled by the user, contact information and the like of the user is intercepted from the personal information input by the user. And sending the intercepted information to a decision engine, wherein the decision engine is provided with product information, a credit approval process, a credit approval model and a preset refusal condition of the credit approval corresponding to each product, judging the intercepted information through the credit approval model and the refusal condition of the credit approval corresponding to the product applied by the user, if the judgment result is that the user is refused to be credited, ending the credit process, otherwise, entering the next step.
C. The most important judgment basis for the credit of the user is the pedestrian data, if the user has more credit records, the pedestrian report information is usually very rich, so that useful information needs to be mined from the pedestrian report information to judge whether credit can be granted to the user, corresponding credit line and interest rate, and more derivative data can be processed from the credit. The derivative data refers to some new data obtained through processing and calculation of basic data of a bank, such as income level of a user deduced according to a user loan and a public deposit record stored by the bank, and further such as latest monthly payment amount of the public deposit, balance of a human business loan, duration of the first public deposit payment from the present time and the like, which are not included in the original data of the bank, and belong to the derivative data. And according to the basic data of the user by the pedestrian, calculating through a relevant model to obtain corresponding derivative data, assembling and storing each derivative data into a character string in a JSON format by a decision engine, and transmitting the JSON character string to a model corresponding to the next approval process by the decision engine to judge whether to grant credit to the user. The JSON character string format derived data assembly form ensures that the meaning of each derived data is not reflected here, and has certain confidentiality.
And after receiving the character string, the next approval process resolves the character string into a structured derivative data field, so that a model in the approval process can directly apply the derivative data field, the method comprises the steps of directly performing corresponding assignment and calculation on the derivative data field, judging whether to give credit to the user, if not, ending the credit process, and if so, correcting the pedestrian credit limit and the pedestrian interest rate corresponding to the user according to the judgment on the user to obtain the final credit limit and interest rate of the user, and then entering the next step.
And finally, for the remaining few suspicious users, the corresponding model sends the credit approval of the user to corresponding manual approving personnel according to different approval classifications.
For users, real-name authentication and authorization are integrated operations, but the real-name authentication and authorization are decoupled at the back end of the system because the real-name authentication is a necessary condition for authorization and needs to be completed at the back end. However, if the front end separates real-name authentication from trust, the operation steps of the user are increased, and the conversion rate of the client is reduced.
D. Carrying out cash withdrawal and examination and approval: and judging the credit investigation condition when the user is prompted during the cash withdrawal approval, wherein a data source needing to be called is determined. If the user is brought up after credit granting for a long time, the credit status may have changed greatly, and therefore other data sources need to be queried again for determination, and the decision engine determines whether to call and query other data sources again currently by determining information such as the last query time of other data sources of the user. And if the data in other data sources need to be called, judging the data source needing to be called according to the existing user information, and transmitting the identifier of the data source needing to be called to the next sub-approval process for determining the data source needing to be called in the next sub-approval process. The decision engine judges according to the information of the product applied by the user and the user information, determines whether to pass the withdrawal application of the user or not, or whether to freeze the line of the user, if the user does not pass the withdrawal application or the line is frozen, the credit process is ended, and if the user passes the withdrawal approval, the withdrawal result of the user is determined through a comprehensive evaluation model.
E. Post-loan collection: and (4) deploying a post-loan collection model through a decision engine, dividing overdue users into different case types, and distributing the case types to different collectors.
The invention also has a batch quota adjusting step in the user's credit, in order to stimulate the user's use of the quota, or train the user's viscosity, or change the user's quota freezing state in time, will carry on the single or batch adjustment to the user's quota and/or interest rate to the existing quota storing user, can be the user initiated quota or interest rate application, can also finish the quota or interest rate adjustment automatically under the situation that the user does not participate in.
Multi-scene:
in specific implementation, one scene usually corresponds to one or more products, common judgment conditions and models can be used for common information, the products are classified, and different types of products commonly use different judgment conditions and common models. The personalized information can then be modeled separately.
In the step B, the product descriptions of the products in the decision engine are approximately the same, and the rejection conditions of the credit approval of the products are different. Some products have more different credit approval conditions and approval processes. According to different scenes and requirements, the trust approval strategies of products can be different, and the same strategy can be shared, so that the requirements of different scenes can be met, and the online iteration speed can be increased.
And in the step B and the step C, if the product applied by the user is refused to credit the user, refusing to credit the user for all other products in the product group where the applied product is located.
And D, for the personalized product, the decision engine carries out presentation examination and approval on the user through the individual model of the personalized product, and for the universal product decision engine carries out presentation examination and approval on the user through the universal model. If the user refuses to withdraw application or freeze the quota, the user is refused to withdraw or freeze the quota for the product which the user applies for withdrawing and other all products of the product group where the withdrawal product is located, so that the fund safety under each product can be ensured.
When making batch adjustments in credits, adjustments to the line of credit or interest rate include making adjustments to the user's differentiated or non-differentiated products.
The above steps may be further divided or combined, and data interaction between the steps is realized, for example, step C may be embedded into step B, and the derived data calculated in step C is transmitted to step B for corresponding application. In practical application, the process design and model deployment in each step can be performed respectively, so as to ensure controllable influence range of each change and ensure on-line stability.
The invention realizes automatic authentication by using the decision engine through comprehensively processing the information input by the user and image acquisition. And then determining whether to grant credit through the application of the user and the amount of the amount and interest rate given to the user through credit approval. And determining whether to pass the withdrawal application of the user by a withdrawal approval step, and determining whether to freeze the quota of the user when refusing. And classifying and distributing the collection users in the final post-credit collection stage.
Meanwhile, the invention also realizes the division and combination of the approval stages, realizes the independent and data interaction of each process, controls the system risk at a very low level, improves the online speed to a higher level and controls the cost to a lower level.
The invention also realizes staged automatic approval and part-to-manual case distribution, in the process, high-risk users are eliminated step by the system, the data cost is reasonably controlled, different quota and interest rate of each user are accurately given, automatic on-line approval is realized, a small number of users needing to be manually transferred are distributed to professional manual approval personnel in a case distribution mode, the approval efficiency is greatly improved, the actual interaction with the users is reduced, and the customer experience is improved.
Through tests, the invention can reduce the manual participation rate in the credit approval process to be below 0.5 percent, effectively realize multi-stage substantive credit, and can more quickly access more flow platforms through the multi-scene fusion technology, thereby enlarging the service scale and reducing the non-systematic risk.
All the models related to the invention can be implemented by using the existing models in the field or by the principle of the existing models by the person skilled in the art, and the part is not the innovation of the invention.
Claims (8)
1. A multi-scenario staged automatic credit method based on a decision engine is characterized by comprising the following steps:
and (2) in stages:
A. and (3) user real name authentication: the method comprises the steps that facial images of a user are collected through a camera, and the user inputs personal information through input equipment; deploying a real-name authentication model in a server through a decision engine, wherein the real-name authentication model processes a real-name authentication request of a user according to an acquired facial image of the user and personal information of the user, automatically passes or rejects the real-name authentication request of the user, and sends the user information passing the real-name authentication to the next step;
B. approval of credit: intercepting corresponding information from personal information input by a user, sending the intercepted information to a decision engine, setting product information, a credit approval process, a credit approval model and a preset refusal condition of the credit approval corresponding to each product in the decision engine, judging the intercepted information through the credit approval model and the refusal condition of the credit approval corresponding to the product applied by the user, if the judgment result is that the credit approval of the user is refused, ending the credit process, otherwise, entering the next step;
C. according to basic data of a pedestrian to the user, corresponding derivative data are obtained through calculation of a relevant model, the derivative data are transmitted to the corresponding model by a decision engine to judge whether the user is credited, if not, a credit process is ended, and if the user agrees to credit, the next step is carried out;
D. carrying out cash withdrawal and examination and approval: the decision engine judges according to the information of the product applied by the user and the user information, determines whether to pass the withdrawal application of the user or not, or whether to freeze the line of the user, if the user does not pass the withdrawal application or the line is frozen, the credit process is ended, and if the user passes the withdrawal approval, the withdrawal result of the user is determined through a comprehensive evaluation model;
E. post-loan collection: a post-loan collection urging model is deployed through a decision engine, overdue users are divided into different case types and distributed to different collection urging personnel;
multi-scene:
in the step B, the product descriptions of the products in the decision engine are approximately the same, and the rejection conditions of the credit approval of the products are different;
products with the same or similar properties are classified into the same product group, and in the step B and the step C, if the product applied by the user is refused to credit the user, the credit of the user is refused to be credited to all other products of the product group where the applied product is located;
in the step D, for the personalized product, the decision engine carries out presentation examination and approval on the user through the individual model of the personalized product, and for the universal product decision engine carries out presentation examination and approval on the user through the universal model; if the user refuses to withdraw the application or freeze the quota, the user refuses to withdraw or freeze the quota for the product that the user applies for withdrawing the current and all other products in the product group where the withdrawal product is located.
2. The decision engine-based multi-scenario phased automated credit method of claim 1, characterized by: and adjusting the credit limit or interest rate of the single or batch users for the users who pass real-name authentication and have the existing limit stock in a preset time period.
3. The decision engine-based multi-scenario phased automated credit method of claim 2, characterized by: in multi-scenario, the adjustment of the credit line or interest rate includes adjusting for differentiated or non-differentiated products of the user.
4. The decision engine-based multi-scenario phased automated credit method of claim 1, characterized by: in the step A, after the real-name authentication model processes the real-name authentication request of the user, the in-doubt user information is transferred to manual examination, and the rest automatically pass or reject the real-name authentication request of the user.
5. The decision engine-based multi-scenario phased automated credit method of claim 1, characterized by: in the step C, the decision engine assembles and stores each derived data into a character string in a JSON format, and transmits the character string to the next approval process; and after receiving the character string, the next examination and approval process analyzes the character string into a structured derived data field, so that the model in the examination and approval process can directly apply the derived data field.
6. The decision engine-based multi-scenario phased automated credit method of claim 1, characterized by: in step C, the corresponding model corrects the pedestrian credit line and the pedestrian interest rate corresponding to the user according to the judgment of the user to obtain the final credit line and interest rate of the user.
7. The decision engine-based multi-scenario phased automated credit method of claim 6, characterized by: and for the rest in-doubt users, the corresponding model sends the credit approval of the user to corresponding manual approving personnel according to different approval classifications.
8. The decision engine-based multi-scenario phased automated credit method of claim 1, characterized by: and D, when the user is subjected to presentation approval, if data in other data sources need to be called, judging the data source needing to be called according to the existing user information, and transmitting the identifier of the data source needing to be called to the next sub-approval process for determining the data source needing to be called in the next sub-approval process.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010284736.1A CN111461875A (en) | 2020-04-13 | 2020-04-13 | Multi-scenario staged automatic credit method based on decision engine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010284736.1A CN111461875A (en) | 2020-04-13 | 2020-04-13 | Multi-scenario staged automatic credit method based on decision engine |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111461875A true CN111461875A (en) | 2020-07-28 |
Family
ID=71685265
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010284736.1A Pending CN111461875A (en) | 2020-04-13 | 2020-04-13 | Multi-scenario staged automatic credit method based on decision engine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111461875A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112037013A (en) * | 2020-08-25 | 2020-12-04 | 成都榕慧科技有限公司 | Pedestrian credit variable derivation method and device |
| CN113409133A (en) * | 2021-06-25 | 2021-09-17 | 搜易热技术有限公司 | Intelligent credit granting system and method for scientific and medium-sized enterprises |
| CN113919937A (en) * | 2021-09-22 | 2022-01-11 | 北京睿知图远科技有限公司 | KS monitoring system based on loan assessment wind control |
| CN114358519A (en) * | 2021-12-15 | 2022-04-15 | 四川新网银行股份有限公司 | Intelligent credit limit interest rate adjusting method and device |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070022027A1 (en) * | 2003-08-27 | 2007-01-25 | Sandeep Gupta | Application processing and decision systems and processes |
| CN107464183A (en) * | 2017-07-03 | 2017-12-12 | 广州帝隆科技股份有限公司 | Debt-credit method, electronic equipment, storage medium and system based on internet |
| CN108335189A (en) * | 2017-09-19 | 2018-07-27 | 平安普惠企业管理有限公司 | Loan processing method, server and readable storage medium storing program for executing on line |
| CN109670936A (en) * | 2018-09-26 | 2019-04-23 | 深圳壹账通智能科技有限公司 | Loan examination & approval processing method, platform, equipment and computer readable storage medium |
| CN110020786A (en) * | 2019-03-11 | 2019-07-16 | 阿里巴巴集团控股有限公司 | Business processing, air control recognition methods, device and equipment |
| CN110610413A (en) * | 2019-09-03 | 2019-12-24 | 福建省农村信用社联合社 | Loan transaction risk control method and system |
-
2020
- 2020-04-13 CN CN202010284736.1A patent/CN111461875A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070022027A1 (en) * | 2003-08-27 | 2007-01-25 | Sandeep Gupta | Application processing and decision systems and processes |
| CN107464183A (en) * | 2017-07-03 | 2017-12-12 | 广州帝隆科技股份有限公司 | Debt-credit method, electronic equipment, storage medium and system based on internet |
| CN108335189A (en) * | 2017-09-19 | 2018-07-27 | 平安普惠企业管理有限公司 | Loan processing method, server and readable storage medium storing program for executing on line |
| CN109670936A (en) * | 2018-09-26 | 2019-04-23 | 深圳壹账通智能科技有限公司 | Loan examination & approval processing method, platform, equipment and computer readable storage medium |
| CN110020786A (en) * | 2019-03-11 | 2019-07-16 | 阿里巴巴集团控股有限公司 | Business processing, air control recognition methods, device and equipment |
| CN110610413A (en) * | 2019-09-03 | 2019-12-24 | 福建省农村信用社联合社 | Loan transaction risk control method and system |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112037013A (en) * | 2020-08-25 | 2020-12-04 | 成都榕慧科技有限公司 | Pedestrian credit variable derivation method and device |
| CN113409133A (en) * | 2021-06-25 | 2021-09-17 | 搜易热技术有限公司 | Intelligent credit granting system and method for scientific and medium-sized enterprises |
| CN113919937A (en) * | 2021-09-22 | 2022-01-11 | 北京睿知图远科技有限公司 | KS monitoring system based on loan assessment wind control |
| CN114358519A (en) * | 2021-12-15 | 2022-04-15 | 四川新网银行股份有限公司 | Intelligent credit limit interest rate adjusting method and device |
| CN114358519B (en) * | 2021-12-15 | 2024-04-05 | 四川新网银行股份有限公司 | Intelligent credit line interest rate adjusting method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111461875A (en) | Multi-scenario staged automatic credit method based on decision engine | |
| DE69828306T2 (en) | SYSTEM WITH OPEN ARCHITECTURE FOR REAL-TIME CONSOLIDATION OF THE INFORMATION OF MULTIPLE FINANCIAL SYSTEMS | |
| CN111967910A (en) | User passenger group classification method and device | |
| CN105787794A (en) | System and method based on consumption load service management mode | |
| DE112013001379T5 (en) | Pre-assignment of a merchant ID in a system of a credit card processor by a major merchant | |
| CN106127571A (en) | A kind of lightness operation processing method and processing device | |
| CN111400272B (en) | Dynamic cost allocation method and system thereof | |
| CN115730966A (en) | Intelligent product optimization method and system based on customer demands | |
| KR102367098B1 (en) | Mediating platform apparatus for making of design project using artificial intelligence curation | |
| CN110428340A (en) | A kind of service system and its implementation of full-automatic aviation class insurance | |
| CN110310419A (en) | A kind of intelligence based on recognition of face sells cigarette method | |
| CN112308698A (en) | WeChat end loan product management method and system supporting second-level legal person | |
| KR101848753B1 (en) | The apparatus and method of real-time cash management by receipt image in smartphone cloud computiong environment | |
| CN111258750B (en) | Data volume processing method and system, and credit allocation method and system | |
| CN112634016A (en) | Community property data-based credit granting system and method | |
| CN113919937B (en) | KS monitoring system based on loan assessment wind control | |
| CN113327159B (en) | Bank end loan transaction system and method thereof | |
| CN112565064B (en) | Service processing method, device, equipment and medium based on remote multimedia | |
| EP1081665B1 (en) | Expert system | |
| CN113269064A (en) | Riding method and device | |
| CN106980838A (en) | A kind of personal identification method and system | |
| CN113469801A (en) | Method and device for determining audit result | |
| CN112766871A (en) | Capital issuing system | |
| CN112365143B (en) | Middle platform system applied to financial enterprises | |
| CN113792872B (en) | Neural network training container and managed training method based on block chain |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200728 |
|
| RJ01 | Rejection of invention patent application after publication |