CN115601157A

CN115601157A - Quota processing method, device, electronic equipment and computer readable medium

Info

Publication number: CN115601157A
Application number: CN202211371245.6A
Authority: CN
Inventors: 陈龙; 赖永旺; 陈杨杨; 吕思运; 王伟; 曾欣
Original assignee: China Construction Bank Corp; CCB Finetech Co Ltd
Current assignee: China Construction Bank Corp; CCB Finetech Co Ltd
Priority date: 2022-11-03
Filing date: 2022-11-03
Publication date: 2023-01-13

Abstract

The application discloses a method and a device for processing a limit, electronic equipment and a computer readable medium, which relate to the field of big data processing.A specific embodiment comprises the steps of receiving a limit processing request, and acquiring corresponding user identification, mechanism identification and limit evaluation data; obtaining historical admittance user data, and then calling a single classification model to generate an optimal hypersphere according to the historical admittance user data; performing admission verification on the quota evaluation data based on the optimal hypersphere, and determining a target workflow according to the user identification and the mechanism identification in response to successful verification; and executing the target workflow to generate a corresponding credit line. The generalization capability of the limit processing scheme can be improved, the access judgment under multiple scenes can be realized, and the limit credit automation can be realized.

Description

Quota processing method, device, electronic equipment and computer readable medium

Technical Field

The present application relates to the field of big data processing technologies, and in particular, to a method and an apparatus for processing a quota, an electronic device, and a computer-readable medium.

Background

The financial business combines the conditions of production, operation, development, fund and the like of the small and micro enterprise users to carry out comprehensive evaluation and risk assessment on the users. At present, most of the existing automatic credit granting schemes for financial services have a specific use scene, and the generalization capability is low.

Disclosure of Invention

In view of this, embodiments of the present application provide a method and an apparatus for processing an amount, an electronic device, and a computer-readable medium, which can solve the problem that most of the existing automatic credit granting schemes for financial services have a specific usage scenario and low generalization capability.

In order to achieve the above object, according to an aspect of the embodiments of the present application, there is provided a credit processing method, including:

receiving a limit processing request, and acquiring corresponding user identification, mechanism identification and limit evaluation data;

obtaining historical admittance user data, and then calling a single classification model to generate an optimal hypersphere according to the historical admittance user data;

performing admission verification on the quota evaluation data based on the optimal hypersphere, and determining a target workflow according to the user identification and the mechanism identification in response to successful verification;

and executing the target workflow to generate a corresponding credit line.

Optionally, performing admission verification based on the optimal hypersphere quota evaluation data includes:

determining a data type corresponding to the optimal hypersphere;

converting the quota evaluation data into data corresponding to the data type;

and judging whether the data is in the optimal hypersphere, if so, determining that the verification is successful, and if not, determining that the verification fails.

Optionally, determining a target workflow comprises:

acquiring a registered user list corresponding to the mechanism identification;

and judging whether the user identification is in the registered user list, if so, determining the credit granting regulating workflow not containing the mean value computing node as a target workflow, and otherwise, determining the credit granting regulating workflow containing the mean value computing node as the target workflow.

Optionally, executing the target workflow to generate a corresponding credit line, including:

calling a regression model to generate a corresponding initial quota according to the quota evaluation data;

and in response to the fact that the target workflow is a credit line regulation workflow which does not contain the mean value calculation node, displaying an initial credit line, and in response to the fact that first regulation data aiming at the initial credit line are detected, determining the credit line according to the initial credit line and the first regulation data.

responding to the target workflow as a credit-providing regulation workflow containing a mean value calculation node, and calling a mean value model to generate a preset amount of quota according to quota evaluation data;

determining a pre-credit line based on the initial line and the line with the preset quantity;

and displaying the pre-granted credit line, responding to the second adjustment data aiming at the pre-granted credit line, and determining the granted credit line according to the pre-granted credit line and the second adjustment data.

Optionally, after performing admission verification based on the optimal hypersphere quota evaluation data, the method further comprises:

responding to the verification failure, sending the quota evaluation data to an offline rechecking node to carry out offline rechecking, and acquiring offline rechecking result data;

and determining the target workflow according to the offline rechecking result data, the user identification and the mechanism identification.

Optionally, before performing admission verification on the credit evaluation data based on the optimal hypersphere, the method further includes:

respectively converting the date and the period in the quota evaluation data into time stamps by adopting a regular expression;

deleting the special symbol in the amount evaluation data, converting the amount of money in the amount evaluation data into a numerical value, and converting the letters in the amount evaluation data into a preset unified format.

In addition, this application still provides a limit processing apparatus, includes:

the receiving unit receives the quota processing request and acquires the corresponding user identification, the mechanism identification and the quota evaluation data;

an optimal hypersphere generating unit configured to obtain historical admitted user data, then, calling a single classification model to generate an optimal hypersphere according to historical admittance user data;

a target workflow determination unit configured to perform admission verification based on the optimal hyperspectral quota evaluation data, and in response to successful verification, determine a target workflow according to the user identification and the organization identification;

and the credit line generating unit is configured to execute the target workflow to generate a corresponding credit line.

Optionally, the target workflow determination unit is further configured to:

determining the data type corresponding to the optimal hypersphere;

converting the quota evaluation data into data corresponding to the data type;

and judging whether the data is in the optimal hypersphere, if so, determining that the verification is successful, and otherwise, determining that the verification fails.

Optionally, the target workflow determination unit is further configured to:

acquiring a registered user list corresponding to the mechanism identification;

Optionally, the credit line generation unit is further configured to:

determining a pre-granted credit limit based on the initial limit and the preset number of limits;

Optionally, the apparatus further comprises an offline review unit configured to:

Optionally, the credit processing device further comprises a data processing unit configured to:

In addition, this application still provides an amount processing electronic equipment, includes: one or more processors; the storage device is used for storing one or more programs, and when the one or more programs are executed by one or more processors, the one or more processors realize the credit processing method.

In addition, the application also provides a computer readable medium, wherein a computer program is stored on the computer readable medium, and when the computer program is executed by a processor, the computer program realizes the quota processing method.

To achieve the above object, according to still another aspect of embodiments of the present application, there is provided a computer program product.

The computer program product of the embodiment of the application comprises a computer program, and the program is executed by a processor to realize the quota processing method provided by the embodiment of the application.

One embodiment of the above invention has the following advantages or benefits: the method comprises the steps of receiving an amount processing request, and obtaining corresponding user identification, mechanism identification and amount evaluation data; obtaining historical admittance user data, and then calling a single classification model to generate an optimal hypersphere according to the historical admittance user data; performing admission verification on the quota evaluation data based on the optimal hypersphere, and determining a target workflow according to the user identification and the mechanism identification in response to successful verification; and executing the target workflow to generate a corresponding credit line. The generalization capability of the limit processing scheme can be improved, the access judgment under multiple scenes can be realized, and the limit credit automation can be realized.

Further effects of the above-mentioned non-conventional alternatives will be described below in connection with the embodiments.

Drawings

The drawings are included to provide a further understanding of the application and are not to be construed as limiting the application. Wherein:

FIG. 1 is a schematic diagram of a main flow of a credit processing method according to an embodiment of the application;

FIG. 2 is a schematic diagram illustrating a main flow of a credit handling method according to an embodiment of the application;

FIG. 3 is a schematic diagram of a main flowchart of a credit handling method according to an embodiment of the application;

FIG. 4 is a schematic main flowchart of a credit handling method according to an embodiment of the application;

FIG. 5 is a schematic diagram of the main units of the credit line processing device according to the embodiment of the application;

FIG. 6 is an exemplary system architecture diagram to which embodiments of the present application may be applied;

fig. 7 is a schematic structural diagram of a computer system suitable for implementing the terminal device or the server according to the embodiment of the present application.

Detailed Description

The following description of the exemplary embodiments of the present application, taken in conjunction with the accompanying drawings, includes various details of the embodiments of the application for the understanding of the same, which are to be considered exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present application. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness. It should be noted that, in the technical solution of the present application, the aspects of collecting, analyzing, using, transmitting, storing, etc. of the related user personal information all conform to the regulations of relevant laws and regulations, are used for legal and reasonable purposes, are not shared, leaked or sold outside the aspects of legal use, etc., and are under the supervision and management of the supervision department. Necessary measures should be taken for the personal information of the user to prevent illegal access to such personal information data, ensure that personnel who have access to the personal information data comply with the regulations of relevant laws and regulations, and ensure the security of the personal information of the user. Once these user personal information data are no longer needed, the risk should be minimized by limiting or even prohibiting data collection and/or deleting data.

User privacy is protected by de-identifying data when used, including in certain related applications, such as by removing a particular identifier, controlling the amount or specificity of stored data, controlling how data is stored, and/or other methods of de-identifying when used.

FIG. 1 is a schematic diagram of a main flow of a credit line processing method according to an embodiment of the present application, as shown in FIG. 1, the credit line processing method includes:

step S101, receiving the quota processing request, and acquiring the corresponding user identification, mechanism identification and quota evaluation data.

In this embodiment, the execution subject (for example, a server) of the quota processing method may receive the quota processing request through a wired connection or a wireless connection. The credit line processing request may be, for example, a request for processing a credit line of a small-sized corporation. After receiving the request for processing the quota, the execution main body may obtain the user identifier corresponding to the request. The user identifier is a user name or a number and the like corresponding to the user who initiates the limit processing request, and the user identifier is not specifically limited in the embodiment of the application. The execution main body can also obtain an organization identifier carried in the quota processing request, wherein the organization identifier can be a number or a name corresponding to an organization for which the quota processing request initiated by the user is directed. The amount evaluation data may be, for example, asset data, transaction flow data, tax data, and agency wage data submitted by the user, and it should be noted that, in the technical solution of the embodiment of the present application, the acquisition, storage, and application of the related personal information of the user all meet the regulations of related laws and regulations, and do not violate the customs of the public order.

Step S102, historical admittance user data are obtained, and then a single classification model is called, so that an optimal hypersphere is generated according to the historical admittance user data.

The historical admittance user data can comprise user information of a user with a historical acquired quota, held asset data, running data, tax data and agency wage data. The single classification Support Vector machine, also called Support Vector Domain Description (SVDD), is aimed at determining the boundary of the target class, and data outside the boundary is unified into a non-target class. The single-classification support vector machine can be actually regarded as an anomaly detection algorithm and is suitable for the situation that the characteristics of non-target samples are disordered and not easy to obtain. Under the condition of only target class, training an optimal hypersphere (hypersphere refers to a sphere in a space with more than 3 dimensions), wrapping all target class data, and classifying new data points when needed. It is only necessary to see if it falls within the hypersphere. The single classification model, namely the single classification support vector machine, can generate an optimal hypersphere according to the input data. And training an optimal hypersphere by using a certain amount of user information data meeting the credit access condition. Then, when it is necessary to determine whether a new user meets the admission condition of credit granting, it is only necessary to see whether the user information characteristic data is located on the trained hypersphere to determine whether the admission condition is met.

And S103, performing admission verification on the quota evaluation data based on the optimal hypersphere, and determining a target workflow according to the user identification and the mechanism identification in response to successful verification.

The quota evaluation data is matched with the optimal hypersphere, so that the quota evaluation data is subjected to admission verification, specifically, the matching mode can be that whether the quota evaluation data is on the optimal hypersphere or in the optimal hypersphere is judged, if yes, the quota evaluation data is matched with the optimal hypersphere, namely, the verification is successful, and if not, the quota evaluation data is not matched with the optimal hypersphere. I.e. the authentication is unsuccessful. When the executing agent determines that the verification is successful, the target workflow may be determined according to whether the user identifier is in a registered user list corresponding to the organization identifier.

Specifically, before performing admission verification on the credit evaluation data based on the optimal hypersphere, the method further comprises the following steps:

respectively converting the date and the period in the quota evaluation data into time stamps by adopting a regular expression; deleting the special symbol in the amount evaluation data, converting the amount of money in the amount evaluation data into a numerical value, and converting the letters in the amount evaluation data into a preset unified format.

For example, after data is imported, the data needs to be verified and converted in terms of format, and the main steps are as follows:

and (3) data format processing: and (4) verifying and processing one by one, and adopting a regular expression to respectively change the date and the period into a time stamp, delete special symbols (.

And (3) data content inspection: and checking the content of the quota evaluation data one by one, and generating prompt information for the repeated data to prompt the user to delete. And counting the integrity of the data, and popping up prompt information when the data is missing. And (4) for numerical data such as money amount, carrying out abnormal value detection and elimination according to a method of mean value +3 standard deviation.

Specifically, after performing admission verification based on the optimal hypersphere quota assessment data, the method further comprises the following steps: responding to the verification failure, sending the quota evaluation data to an offline rechecking node to carry out offline rechecking, and acquiring offline rechecking result data; and determining the target workflow according to the offline rechecking result data, the user identification and the mechanism identification.

When the verification fails, namely the line evaluation data of the user is far away from the hypersphere, manual secondary access can be performed according to actual conditions, the line evaluation data is sent to the offline rechecking node to perform offline rechecking, and offline rechecking result data is obtained, and the offline rechecking result data can correspond to offline rechecking success or offline rechecking failure. When the offline rechecking is successful, the execution main body can continue to execute the process of determining the target workflow, and when the offline rechecking fails, namely the target workflow is empty, namely the rechecking fails, the limit processing process is ended.

And step S104, executing the target workflow to generate a corresponding credit line.

And sequentially executing corresponding node logics according to the sequence of each node of the target workflow to obtain the final credit line.

In the embodiment, by receiving the quota processing request, the corresponding user identifier, mechanism identifier and quota evaluation data are obtained; obtaining historical admittance user data, and then calling a single classification model to generate an optimal hypersphere according to the historical admittance user data; performing admission verification on the quota evaluation data based on the optimal hypersphere, and determining a target workflow according to the user identification and the mechanism identification in response to successful verification; and executing the target workflow to generate a corresponding credit line. The generalization capability of the limit processing scheme can be improved, the access judgment under multiple scenes can be realized, and the limit credit automation can be realized.

FIG. 2 is a schematic view of a main flow of a credit processing method according to an embodiment of the present application, and as shown in FIG. 2, the credit processing method includes:

step S201, receiving the quota processing request, and acquiring the corresponding user identifier, mechanism identifier and quota evaluation data.

The credit line processing request may be, for example, a request for processing a credit card credit line application. After receiving the request for processing the quota, the execution main body may obtain the user identifier corresponding to the request. The user identifier is a user name or a number and the like corresponding to the user who initiates the limit processing request, and the user identifier is not specifically limited in the embodiment of the application. The execution main body can also obtain an organization identifier carried in the quota processing request, wherein the organization identifier can be a number or a name corresponding to an organization for which the quota processing request initiated by the user is directed. The amount evaluation data may be, for example, asset data, transaction flow data, tax data, and agency wage data submitted by the user, and it should be noted that, in the technical solution of the embodiment of the present application, the acquisition, storage, and application of the related personal information of the user all meet the regulations of related laws and regulations, and do not violate the customs of the public order.

Step S202, historical admittance user data are obtained, and then a single classification model is called, so that an optimal hypersphere is generated according to the historical admittance user data.

Specifically, an optimal hypersphere can be obtained by training a single-classification support vector machine according to historical access user data. When a new user needs to be judged whether to meet the admission condition of credit granting, whether the admission condition is met can be judged only by looking at whether the user information characteristic data of the new user is positioned on the trained hypersphere.

And step S203, determining the data type corresponding to the optimal hypersphere.

In the process of matching the quota evaluation data with the optimal hypersphere, the quota evaluation data needs to be converted into the data type same as the optimal hypersphere. First, a data type corresponding to the optimal hypersphere, for example, a binary number, a hexadecimal number, etc., needs to be determined.

Step S204, the data for evaluating the quota is converted into the data corresponding to the data type.

Taking the data type of the optimal hypersphere as a binary number, and converting the quota evaluation data into the binary number as an example, the execution subject may convert the quota evaluation data into a corresponding vector in a word embedding manner, and then call a binary conversion command to convert the vector into the corresponding binary number.

And S205, judging whether the data is in the optimal hypersphere, if so, determining that the verification is successful, and otherwise, determining that the verification fails.

For example, the execution main body may match the credit evaluation data converted into the binary number with data on the optimal hypersphere and in the optimal hypersphere, if there is matched data, the verification is successful, and if there is no matched data, the verification fails.

And step S206, responding to successful verification, and determining the target workflow according to the user identification and the mechanism identification.

If the verification is successful, the mechanism corresponding to the mechanism identification approves the user corresponding to the user identification to enter, namely, the mechanism corresponding to the mechanism identification applies for the user open limit corresponding to the user identification. Further, the target workflow may be determined according to whether the user identifier is in a registered user list corresponding to the organization identifier. Wherein the candidate workflow may include: the method comprises the steps of a credit granting adjustment workflow comprising a mean value computing node and a credit granting adjustment workflow not comprising the mean value computing node. Specifically, a target workflow is determined from the candidate workflows.

Step S207, executing the target workflow to generate a corresponding credit line.

The embodiment of the application can provide automatic access judgment for different scenes, and can perform manual secondary intervention after automatic access failure, so that the accuracy and efficiency of limit processing are improved, and omission is avoided.

FIG. 3 is a schematic main flow chart of a credit line processing method according to an embodiment of the present application, and as shown in FIG. 3, the credit line processing method includes:

step S301, receiving the quota processing request, and acquiring the corresponding user identifier, mechanism identifier and quota evaluation data.

The credit line processing request may be, for example, a request for processing a universal credit amount issued by a bank. After receiving the request for processing the quota, the execution main body may obtain the user identifier corresponding to the request. The user identifier is a user name or a number and the like corresponding to the user who initiates the limit processing request, and the user identifier is not specifically limited in the embodiment of the application. The execution main body can also obtain an organization identifier carried in the quota processing request, wherein the organization identifier can be a number or a name corresponding to an organization for which the quota processing request initiated by the user is directed. The amount evaluation data may be, for example, asset data, transaction flow data, tax data, and agency wage data submitted by the user, and it should be noted that, in the technical solution of the embodiment of the present application, the acquisition, storage, and application of the related personal information of the user all meet the regulations of related laws and regulations, and do not violate the customs of the public order.

Step S302, historical admittance user data are obtained, and then a single classification model is called, so that an optimal hypersphere is generated according to the historical admittance user data.

The historical admittance user data can comprise user information, held asset data, running data, tax data and agency wage data of the user which historically obtains the universal fund amount. A single classification model is invoked to identify target class boundaries to generate an optimal hypersphere based on historical admissible user data. The target category can be good credit, deposit, no liability, and annual tax rate exceeding a preset threshold, and the target category is not specifically limited in the embodiment of the application.

And step S303, performing admission verification on the quota evaluation data based on the optimal hypersphere.

And matching the quota evaluation data with the optimal hypersphere, thereby performing access verification on the quota evaluation data.

And step S304, responding to successful verification, and acquiring a registered user list corresponding to the mechanism identification.

When the verification is successful, that is, the quota evaluation data is matched with the optimal hypersphere, the access condition is reached, and further the next operation can be continued, namely, the registered user list corresponding to the mechanism identification is obtained.

Step S305, judging whether the user identification is in the registered user list, if so, determining the credit granting regulation workflow not containing the mean value calculation node as the target workflow, and if not, determining the credit granting regulation workflow containing the mean value calculation node as the target workflow.

For example, whether the user corresponding to the user identifier is an intra-organization user may be determined by whether the user identifier is in a registered user list corresponding to the organization identifier. When the user identification is in a registered user list corresponding to the mechanism identification, the mean value does not need to be calculated, the credit granting adjustment workflow which does not contain the mean value calculation node is determined as a target workflow, a credit granting adjustment model is directly called, and the credit granting adjustment workflow which does not contain the mean value calculation node is executed; and when the user identification is not in the registered user list corresponding to the mechanism identification, k mean value calculation is needed, the credit granting adjustment workflow containing the mean value calculation node is determined as a target workflow, a mean value model is called to calculate the k mean value, and then the final credit granting amount is calculated based on the k mean value.

Step S306, executing the target workflow to generate a corresponding credit line.

Specifically, executing the target workflow to generate a corresponding credit line includes:

calling a regression model, such as an ELM model, to generate a corresponding initial quota according to the quota evaluation data; and in response to the fact that the target workflow is a credit line regulation workflow which does not contain the mean value calculation node, displaying an initial credit line, and in response to the fact that first regulation data aiming at the initial credit line are detected, determining the credit line according to the initial credit line and the first regulation data.

Specifically, the preset adjusting node (e.g. expert node) may perform fine adjustment on the initial credit line obtained through the regression model, and when the executing entity detects the fine adjustment data (i.e. the first adjustment data), the executing entity may adjust the initial credit line according to the fine adjustment data (i.e. the first adjustment data) to obtain the credit line.

responding to the target workflow as a credit regulation workflow containing a mean value calculation node, calling a mean value model, such as a KNN model, to generate a preset amount of quota, such as quota A, according to quota evaluation data ₁ ，A ₂ ,…,A _k (ii) a Based on an initial amount, e.g. A, and a predetermined amount of amount, e.g. amount A ₁ ，A ₂ ,…,A _k Determining the pre-credit limit M = (A + A) ₁ +A ₂ +…+A _k ) V (k + 1); and displaying the pre-granted credit line, responding to the second adjustment data aiming at the pre-granted credit line, and determining the granted credit line according to the pre-granted credit line and the second adjustment data.

Specifically, the preset adjustment node (e.g., an expert node) may perform fine adjustment on the pre-credit line calculated based on the line obtained by the regression model and the mean model, and when the execution subject detects the fine adjustment data (i.e., the second adjustment data), the pre-credit line may be adjusted according to the fine adjustment data (i.e., the second adjustment data) to obtain the credit line.

The embodiment of the application can improve the accuracy of the credit line processing, improve the generalization capability of the credit line processing scheme, realize the access judgment under multiple scenes and realize the credit line authorization automation.

FIG. 4 is a schematic main flowchart of a credit processing method according to an embodiment of the application. The quota processing method can be applied to occasions where quota is applied under different scenes. As shown in fig. 4, the framework specifically is an automatic admission trust model framework, and the framework logic includes data import, admission judgment, establishment of a trust model, and a trust adjustment model. Specifically, the method comprises the following steps:

user data import and processing: after the user data is imported, the user data needs to be verified and converted in format, and the method mainly comprises the following steps: processing data formats, verifying and processing one by one, and adopting a regular expression to respectively change dates and periods into timestamps, delete special symbols (; and (4) data content inspection, wherein the data contents are inspected one by one, and for the repeated sample data, a user can be prompted to delete the repeated sample data. And counting the integrity of the data, and popping up prompt information when the data is missing. And (4) for numerical data such as money amount, carrying out abnormal value detection and elimination according to a method of mean value +3 standard deviation.

And (3) admission judgment: according to the imported user data, after checking and processing, according to the six types of characteristics of the users ready to be admitted: user information, assets in the organization, public (private) running water, tax information and agency wage information, and training list classification SVM model. After training, an optimal hypersphere is obtained, and the hypersphere wraps all the data of the access user. When new user data points need to be subjected to access classification, if the user information characteristic data are located in the hypersphere and manual rechecking is not needed, the user is subjected to credit granting and access admission. If the user data is far away from the hypersphere, manual secondary access can be performed according to the actual situation, namely manual rechecking.

Establishing a trust model: according to the situation of different scenes, aiming at the users outside the mechanism in the mechanism, two frames are provided: ELM frameworks and KNN frameworks.

The ELM framework corresponds to an ELM model, an initial quota is obtained through the ELM model by adopting an ELM regression method, and the following steps are executed:

(1) Feature preparation

Six categories of features ready to receive users: user information, assets in the organization, running water to public (private), tax information, and surcharge information.

(2) And training an ELM model, and acquiring a quota by a KNN mean method.

And inputting the training data sample set into the ELM model, obtaining the trained model after the model is converged, and performing data regression by using the trained ELM model to obtain the initial limit of the new user.

The KNN framework corresponds to the KNN model, the nearest K adjacent data quota is obtained through the KNN model, and the following steps are executed:

(1) Feature preparation

(2) And training the KNN model to obtain the quota.

If the user is an outside-agency user, an initial quota A can be obtained after the user passes through the ELM model, then the user data is put into the KNN model, and the quota A of the K nearest adjacent data is obtained ₁ ，A ₂ ,…,A _k . The credit line M of the user is:

M＝(A+A ₁ +A ₂ +…+A _k )/(k+1)

and (3) adjusting a trust model: after different processing frames are adopted for users in and out of the mechanism, initial limit is obtained, the initial limit is displayed to a user (namely a preset adjusting node), if the user suspects the credit line, an artificial secondary credit function can be provided, namely artificial rechecking is carried out, and finally the final credit line is obtained.

The automatic limit credit granting frame provided by the embodiment of the application can provide multi-scene rapid modeling and automatic credit granting functions for internal and external clients downlink in different scenes, and customized development is not needed.

FIG. 5 is a schematic diagram of the main units of the credit line processing device according to the embodiment of the application. As shown in FIG. 5, the amount processing device 500 includes a receiving unit 501, an optimal hypersphere generating unit 502, a target workflow determining unit 503, and an credit amount generating unit 504.

The receiving unit 501 receives the quota processing request, and obtains the corresponding user identifier, mechanism identifier and quota evaluation data;

an optimal hypersphere generating unit 502 configured to obtain historical admissible user data and then invoke the single classification model to generate an optimal hypersphere according to the historical admissible user data;

a target workflow determination unit 503 configured to perform admission verification on the quota evaluation data based on the optimal hypersphere, and in response to successful verification, determine a target workflow according to the user identifier and the organization identifier;

a credit limit generating unit 504 configured to execute the target workflow to generate a corresponding credit limit

In some embodiments, the target workflow determination unit 503 is further configured to: determining the data type corresponding to the optimal hypersphere; converting the quota evaluation data into data corresponding to the data type; and judging whether the data is in the optimal hypersphere, if so, determining that the verification is successful, and otherwise, determining that the verification fails.

In some embodiments, the target workflow determination unit 503 is further configured to: acquiring a registered user list corresponding to the mechanism identification; and judging whether the user identification is in the registered user list, if so, determining the credit granting regulating workflow not containing the mean value computing node as a target workflow, and otherwise, determining the credit granting regulating workflow containing the mean value computing node as the target workflow.

In some embodiments, the credit line generation unit 504 is further configured to: calling a regression model to generate a corresponding initial quota according to the quota evaluation data; and in response to the fact that the target workflow is a credit line regulation workflow which does not contain the mean value calculation node, displaying an initial amount, and in response to the fact that first regulation data aiming at the initial amount are detected, determining a credit line according to the initial amount and the first regulation data.

In some embodiments, the credit line generation unit 504 is further configured to: responding to the target workflow as a credit-providing regulation workflow containing a mean value calculation node, and calling a mean value model to generate a preset amount of quota according to quota evaluation data; determining a pre-granted credit limit based on the initial limit and the preset number of limits; and displaying the pre-granted credit line, responding to the second adjustment data aiming at the pre-granted credit line, and determining the granted credit line according to the pre-granted credit line and the second adjustment data.

In some embodiments, the credit processing device further includes an offline review unit, not shown in fig. 5, configured to: responding to the verification failure, sending the quota evaluation data to an offline rechecking node to carry out offline rechecking, and acquiring offline rechecking result data; and determining the target workflow according to the offline rechecking result data, the user identification and the mechanism identification.

In some embodiments, the credit processing device further comprises a data processing unit not shown in fig. 5, and is configured to: respectively converting the date and the period in the quota evaluation data into time stamps by adopting a regular expression; deleting the special symbol in the amount evaluation data, converting the amount of money in the amount evaluation data into a numerical value, and converting the letters in the amount evaluation data into a preset unified format.

The credit line processing method and the credit line processing device of the present application have corresponding relation in the specific implementation contents, and therefore the repeated contents are not described again.

FIG. 6 shows an exemplary system architecture 600 to which the credit processing method or the credit processing device of the embodiment of the application can be applied.

As shown in fig. 6, the system architecture 600 may include

terminal devices

601, 602, 603, a network 604, and a server 605. The network 604 serves to provide a medium for communication links between the

terminal devices

601, 602, 603 and the server 605. Network 604 may include various types of connections, such as wire, wireless communication links, or fiber optic cables, to name a few.

A user may use the

terminal devices

601, 602, 603 to interact with the server 605 via the network 604 to receive or send messages or the like. Various communication client applications, such as shopping applications, web browser applications, search applications, instant messaging tools, mailbox clients, social platform software, etc. (for example only) may be installed on the

terminal devices

601, 602, 603.

The

terminal devices

601, 602, 603 may be various electronic devices having credit handling screens and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like.

Server 605 may be a server providing various services, such as a background management server (for example only) supporting credit line processing requests submitted by users using

terminal devices

601, 602, 603. The background management server can receive the quota processing request and acquire corresponding user identification, mechanism identification and quota evaluation data; obtaining historical admittance user data, and then calling a single classification model to generate an optimal hypersphere according to the historical admittance user data; performing admission verification on the quota evaluation data based on the optimal hypersphere, and determining a target workflow according to the user identification and the mechanism identification in response to successful verification; and executing the target workflow to generate a corresponding credit line. The generalization capability of the limit processing scheme can be improved, the access judgment under multiple scenes can be realized, and the limit credit automation can be realized.

It should be noted that the method for processing the quota provided in the embodiment of the present application is generally executed by the server 605, and accordingly, the quota processing apparatus is generally disposed in the server 605.

It should be understood that the number of terminal devices, networks, and servers in fig. 6 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.

Referring now to FIG. 7, shown is a block diagram of a computer system 700 suitable for use in implementing a terminal device of an embodiment of the present application. The terminal device shown in fig. 7 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present application.

As shown in fig. 7, the computer system 700 includes a Central Processing Unit (CPU) 701, which can perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM) 702 or a program loaded from a storage section 708 into a Random Access Memory (RAM) 703. In the RAM703, various programs and data necessary for the operation of the computer system 700 are also stored. The CPU701, the ROM702, and the RAM703 are connected to each other via a bus 704. An input/output (I/O) interface 705 is also connected to bus 704.

The following components are connected to the I/O interface 705: an input portion 706 including a keyboard, a mouse, and the like; an output section 707 including a signal processing section such as a Cathode Ray Tube (CRT), a liquid crystal credit authorization query processor (LCD), and the like, and a speaker; a storage section 708 including a hard disk and the like; and a communication section 709 including a network interface card such as a LAN card, a modem, or the like. The communication section 709 performs communication processing via a network such as the internet. A drive 710 is also connected to the I/O interface 705 as needed. A removable medium 711 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 710 as necessary, so that a computer program read out therefrom is mounted into the storage section 708 as necessary.

In particular, according to embodiments disclosed herein, the processes described above with reference to the flow diagrams may be implemented as computer software programs. For example, embodiments disclosed herein include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated by the flow chart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication section 709, and/or installed from the removable medium 711. The computer program executes the above-described functions defined in the system of the present application when executed by the Central Processing Unit (CPU) 701.

It should be noted that the computer readable medium shown in the present application may be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may include, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present application, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In this application, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units described in the embodiments of the present application may be implemented by software or hardware. The described units may also be provided in a processor, and may be described as: a processor comprises a receiving unit, an optimal hypersphere generating unit, a target workflow determining unit and a credit limit generating unit. Wherein the names of the elements do not in some way constitute a limitation on the elements themselves.

As another aspect, the present application also provides a computer-readable medium, which may be contained in the apparatus described in the above embodiments; or may be separate and not incorporated into the device. The computer readable medium carries one or more programs, and when the one or more programs are executed by the equipment, the equipment receives the quota processing request and acquires the corresponding user identification, the mechanism identification and the quota evaluation data; obtaining historical admittance user data, and then calling a single classification model to generate an optimal hypersphere according to the historical admittance user data; performing admission verification on the quota evaluation data based on the optimal hypersphere, and determining a target workflow according to the user identification and the mechanism identification in response to successful verification; and executing the target workflow to generate a corresponding credit line.

The computer program product of the application comprises a computer program, and the computer program realizes the quota processing method in the embodiment of the application when being executed by a processor.

According to the technical scheme of the embodiment of the application, the generalization capability of the limit processing scheme can be improved, the access judgment under multiple scenes can be realized, and the limit credit automation can be realized.

The above-described embodiments should not be construed as limiting the scope of the present application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for processing a quota, comprising:

performing admission verification on the quota evaluation data based on the optimal hypersphere, and determining a target workflow according to the user identifier and the mechanism identifier in response to successful verification;

and executing the target workflow to generate a corresponding credit line.

2. The method of claim 1, wherein the performing admission verification on the credit evaluation data based on the optimal hypersphere comprises:

determining the data type corresponding to the optimal hypersphere;

converting the quota evaluation data into data corresponding to the data type;

3. The method of claim 1, wherein determining a target workflow comprises:

acquiring a registered user list corresponding to the mechanism identification;

and judging whether the user identification is in the registered user list, if so, determining the credit granting regulation workflow not containing the mean value calculation node as a target workflow, and if not, determining the credit granting regulation workflow containing the mean value calculation node as the target workflow.

4. The method of claim 3, wherein the executing the target workflow to generate a corresponding credit line comprises:

and in response to the fact that the target workflow is a credit adjustment workflow which does not contain a mean value calculation node, displaying the initial amount, and in response to the fact that first adjustment data aiming at the initial amount are detected, determining a credit amount according to the initial amount and the first adjustment data.

5. The method of claim 4, wherein the executing the target workflow to generate a corresponding credit line comprises:

responding to the target workflow as a credit regulation workflow containing a mean value calculation node, and calling a mean value model to generate a preset amount of credit according to the credit evaluation data;

determining a pre-credit line based on the initial line and the line of the preset quantity;

and displaying the pre-credit line, and determining the credit line according to the pre-credit line and second adjustment data in response to the detection of the second adjustment data aiming at the pre-credit line.

6. The method of claim 1, wherein after the verifying the admission of the credit evaluation data based on the optimal hypersphere, the method further comprises:

and determining a target workflow according to the offline rechecking result data, the user identification and the mechanism identification.

7. The method of claim 1, wherein prior to said verifying admission of said credit evaluation data based on said optimal hypersphere, said method further comprises:

respectively converting the date and the period in the quota evaluation data into time stamps by adopting regular expressions;

deleting the special symbol in the amount evaluation data, converting the amount in the amount evaluation data into a numerical value, and converting the letter in the amount evaluation data into a preset unified format.

8. A credit line processing device, comprising:

the receiving unit is used for receiving the quota processing request and acquiring the corresponding user identification, mechanism identification and quota evaluation data;

the optimal hypersphere generating unit is configured to acquire historical admittance user data and further call a single classification model to generate an optimal hypersphere according to the historical admittance user data;

a target workflow determination unit configured to perform admission verification on the credit evaluation data based on the optimal hypersphere, and in response to successful verification, determine a target workflow according to the user identifier and the organization identifier;

9. The apparatus of claim 8, wherein the target workflow determination unit is further configured to:

determining the data type corresponding to the optimal hypersphere;

converting the quota evaluation data into data corresponding to the data type;

10. The apparatus of claim 8, wherein the target workflow determination unit is further configured to:

acquiring a registered user list corresponding to the mechanism identification;

11. The apparatus of claim 10, wherein the credit line generating unit is further configured to:

12. The apparatus of claim 11, wherein the credit line generating unit is further configured to:

responding to the target workflow as a credit regulation workflow containing a mean value calculation node, and calling a mean value model to generate a preset amount of quota according to the quota evaluation data;

and displaying the pre-granted credit line, responding to the detection of second adjustment data aiming at the pre-granted credit line, and determining the granted credit line according to the pre-granted credit line and the second adjustment data.

13. The apparatus of claim 8, further comprising an offline review unit configured to:

responding to the verification failure, sending the limit evaluation data to an offline rechecking node to carry out offline rechecking, and acquiring offline rechecking result data;

14. An electronic device for processing credit, comprising:

one or more processors;

a storage device to store one or more programs,

when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-7.

15. A computer-readable medium, on which a computer program is stored, which program, when being executed by a processor, is adapted to carry out the method of any one of claims 1-7.

16. A computer program product comprising a computer program, characterized in that the computer program realizes the method according to any of claims 1-7 when executed by a processor.