CN117635317A - Method and device for determining article migration information, electronic equipment and storage medium - Google Patents

Abstract

The invention discloses a method, a device, electronic equipment and a storage medium for determining article migration information, and relates to the technical field of data processing, wherein the method comprises the following steps: determining article demand information and historical article migration information of a user; determining the article returning risk of the user based on the target risk determining model, the initial article cost, the initial article returning moment and the historical article transferring information; and determining target item migration information of the user based on the item migration risk, the initial item cost and the initial item migration time. According to the method and the device for determining the article migration risk of the user, the article migration risk of the user is determined according to the risk determination model, the initial article cost, the initial article migration time and the historical article migration information, and then the target article migration information is determined according to the article migration risk, the initial article cost and the initial article migration time in a targeted mode, the article migration information corresponding to the current article demand information can be determined efficiently, quickly and accurately, the evaluation efficiency of the article demand is improved, and manpower resources are saved.

Description

Method and device for determining article migration information, electronic equipment and storage medium

Technical Field

The present invention relates to the field of data processing technologies, and in particular, to a method and apparatus for determining migration information of an article, an electronic device, and a storage medium.

Background

With the development of society, agricultural borrowing such as small amount, medium and small amount is more common, and banks also release corresponding loan business for the agricultural borrowing so as to maintain the construction of the fund-melting market.

When a bank examines and approves agricultural borrowing, the credit information and repayment capability of the borrower are required to be evaluated, and business details of a loan business, such as whether to carry out the loan business, the loan amount, the repayment period and the like, are determined according to the evaluation result. Currently, the evaluation mode of the credit information and repayment capability of the borrower is determined by a technician based on the credit file and the historical loan information of the borrower, for example, the credit file and the historical loan information of the borrower are called, the technician formulates a credit rating index and a repayment capability measurement index according to rating experience, and analyzes the credit file and the historical loan information of the borrower based on the credit rating index and the repayment capability measurement index according to rating experience to determine the loan credit and repayment capability of the borrower.

However, the credit information of the borrower who needs the agricultural loan is limited, the accuracy of the evaluation result of the credit information and repayment capability of the borrower is affected by the smaller information amount, so that the bank performs the loan business with lower security, the technician evaluates the loan credit and repayment capability of the borrower according to the credit file and the historical loan information, a great deal of manpower resources and time resources are required, once the evaluation capability of the technician is limited or doped with subjective consciousness, the evaluation result of the loan credit and repayment capability is not representative, and cannot be used as guiding data for whether the loan business is performed.

Disclosure of Invention

The invention provides a method, a device, electronic equipment and a storage medium for determining article migration information, which are used for efficiently, quickly and accurately determining the article migration information corresponding to current article demand information, indicating whether a bank is borrower to carry out loan business, determining detailed information such as the amount and the term of the loan business, improving the evaluation efficiency and accuracy of the article demand and saving human resources.

According to an aspect of the present invention, there is provided a method of determining migration information of an article, the method comprising:

Determining article demand information and historical article migration information of a user, wherein the article demand information comprises initial article cost and initial article migration time;

determining the article returning risk of the user based on the target risk determining model, the initial article cost, the initial article returning moment and the historical article transferring information;

and determining target item migration information of the user based on the item migration risk, the initial item cost and the initial item migration time, wherein the target item migration information comprises the target item cost and the target item migration time.

Optionally, determining the item migration risk of the user based on the target risk determination model, the initial item cost, the initial item migration time and the historical item migration information includes: determining at least one candidate feature information of the user based on the initial item cost, the initial item return time and the historical item migration information; and determining the item migration risk based on the initial item cost, the initial item migration time, the historical item migration information, the at least one candidate feature information and the target risk determination model.

Optionally, determining at least one candidate feature information of the user based on the initial item cost, the initial item return time and the historical item migration information includes: determining at least one migration data model based on the initial item cost, the initial item return time and the historical item migration information; determining at least one piece of initial characteristic information, wherein the initial characteristic information corresponds to the candidate characteristic information one by one; and determining at least one candidate feature information based on the fitness of each migration data model and at least one initial feature information, wherein the candidate feature information is the initial feature information after deleting the invalid information.

Optionally, the method further comprises: determining an initial risk determination model before determining an item return risk based on the initial item cost, the initial item return time, the historical item migration information, the at least one candidate feature information, and the target risk determination model; training the initial risk determination model based on the initial item cost, the initial item returning time, the historical item transferring information and the at least one candidate feature information to obtain a target risk determination model.

Optionally, determining the target item migration information of the user based on the item migration risk, the initial item cost and the initial item migration time includes: determining whether the article reversion risk is less than or equal to a first risk threshold; if the article returning risk is smaller than or equal to the first risk threshold, determining that the target article cost is the initial article cost, and determining that the target article returning time is the initial article returning time; and if the article returning risk is greater than the first risk threshold, determining target article transferring information based on a second risk threshold, the article returning risk, the initial article cost and the initial article returning time, wherein the second risk threshold is greater than the first risk threshold.

Optionally, determining the target item migration information based on the second risk threshold, the item migration risk, the initial item cost, and the initial item migration time includes: determining whether the article reversion risk is less than or equal to a second risk threshold; if the article returning risk is smaller than or equal to the second risk threshold, determining target article transferring information based on a preset transferring information determining rule, initial article cost and initial article returning time; and if the article returning risk is greater than the second risk threshold, determining that the migration information of the target article is migration inhibition information.

Optionally, the migration information determining rule includes an item cost determining rule and a returning time determining rule.

Optionally, determining the target item migration information based on a preset migration information determining rule, an initial item cost and an initial item return time includes: determining a target item cost based on the item cost determination rule and the initial item cost; and determining the target article returning time based on the returning time determining rule and the initial article returning time.

According to another aspect of the present invention, there is provided an apparatus for determining migration information of an article, where the apparatus for determining migration information of an article is used to implement a method for determining migration information of an article in any embodiment of the present invention, the apparatus includes:

The acquisition module is used for determining article demand information and historical article migration information of a user, wherein the article demand information comprises initial article cost and initial article migration time;

the determining module is used for determining the article returning risk of the user based on the target risk determining model, the initial article cost, the initial article returning moment and the historical article transferring information;

the execution module is used for determining target article migration information of the user based on the article migration risk, the initial article cost and the initial article migration time, wherein the target article migration information comprises the target article cost and the target article migration time.

According to another aspect of the present invention, there is provided an electronic device including:

at least one processor; and a memory communicatively coupled to the at least one processor;

the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to perform the method for determining the migration information of the article according to any one of the embodiments of the present invention.

According to another aspect of the present invention, there is provided a computer readable storage medium storing computer instructions for causing a processor to perform a method of determining item migration information in any one of the embodiments of the present invention.

According to the technical scheme, the article demand information and the historical article migration information of the user are determined, wherein the article demand information comprises initial article cost and initial article migration time; determining the article returning risk of the user based on the target risk determining model, the initial article cost, the initial article returning moment and the historical article transferring information; and determining target item migration information of the user based on the item migration risk, the initial item cost and the initial item migration time, wherein the target item migration information comprises the target item cost and the target item migration time. According to the method and the device, the article returning risk of the user is determined according to the risk determining model, the initial article cost, the initial article returning time and the historical article transferring information, and the target article transferring information is determined according to the article returning risk, the initial article cost and the initial article returning time in a targeted mode, so that the target article transferring information corresponding to the current article demand information can be determined efficiently, quickly and accurately by combining the historical article transferring information of the user, whether a bank carries out loan business for borrowers or not is indicated, the detailed information such as the limit and the term of the loan business is determined, the evaluation efficiency and the accuracy of the article demand are improved, and the manpower resources are saved. The method solves the problems that the credit information of borrowers needing agricultural loans is limited, the accuracy of the evaluation results of the credit information and repayment capability of the borrowers is affected by less information, the banks develop loan businesses with lower safety, a great deal of manpower resources and time resources are required for evaluating the loan credit and repayment capability of the borrowers according to credit files and historical loan information, once the evaluation capability of the technicians is limited or subjective consciousness is doped, the evaluation results of the loan credit and repayment capability are not representative, and the like, and the borrow credit and repayment capability cannot be used as guiding data for developing loan businesses.

It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the invention or to delineate the scope of the invention. Other features of the present invention will become apparent from the description that follows.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

Fig. 1 is a flow chart of a method for determining migration information of an article according to a first embodiment of the present invention;

fig. 2 is a flow chart of a method for determining migration information of an article according to a second embodiment of the present invention;

FIG. 3 is a schematic diagram of a migration data model according to a second embodiment of the present invention;

fig. 4 is a schematic structural diagram of an apparatus for determining migration information of an article according to a third embodiment of the present invention;

fig. 5 is a schematic structural diagram of an electronic device according to a fourth embodiment of the present invention.

Detailed Description

In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.

It should be noted that the terms "first," "second," and the like in the description and the claims of the present invention and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

Example 1

Fig. 1 is a flow chart of a method for determining article migration information according to an embodiment of the present invention, where the embodiment is applicable to a credit check of a farmer, a rural small loan, a medium and small loan, and approval of an agricultural loan, and the method may be performed by an apparatus for determining article migration information according to the present invention, where the apparatus may be implemented in hardware and/or software, and in a specific embodiment, the apparatus may be integrated in an electronic device. The following embodiment will be described taking the example of the integration of the apparatus in an electronic device, and referring to fig. 1, the method specifically includes the following steps:

s101, determining article demand information and historical article migration information of a user.

The information about the demand for the article may be understood as information including the demand for the borrower for the borrowing of the user, including the cost of the initial article and the time of returning the initial article, and the information about the migration of the historical article may be understood as a history borrowing record of the user, including the number of borrowings, the amount of borrowing, the purpose of borrowing, the time of repayment, the rate of bad loan, the information of bad loan, etc., which are not limited in this embodiment.

Specifically, the initial item cost may be understood as the amount that the user currently needs to borrow, and the initial item return time may be understood as the time when the user expects to return the current borrow amount.

For example, determining the item demand information and the historical item migration information of the user may be understood as determining the item demand information such as the current loan amount of the user, the return time of the current loan amount, and the historical item migration information such as the number of loans, the loan amount, the use of the loan, the repayment time, the bad loan rate, and the bad loan information of the user.

The advantage of this is that the user's overall loan data can be determined so that the bank's technician measures the user's loan credit and repayment capabilities and determines whether the user should be loaned.

S102, determining the article returning risk of the user based on the target risk determining model, the initial article cost, the initial article returning time and the historical article transferring information.

The target risk determination model can be understood as an algorithm capable of determining the repayment risk of the user, information such as initial article cost, initial article returning time and historical article transferring information is input into the target risk determination model to be processed, article returning risk (an output result of the model can be regarded as indicative data of the article returning risk) of the user can be obtained, the article returning risk can be understood as the repayment risk of the user, and specifically, the higher the article returning risk is, the lower the repayment probability of the user in time (referring to the initial article returning time) and in quantity (referring to the initial article cost) is.

The determining of the item migration risk of the user based on the target risk determining model, the initial item cost, the initial item migration time and the historical item migration information can be understood as that data such as the initial item cost, the initial item migration time and the historical item migration information are input into the target risk determining model to be processed, and the repayment risk of the user is determined according to the output result of the target risk determining model.

The advantage of this arrangement is that the payment risk of the user can be determined according to the lending data and the lending requirements of the user, and data support is provided for the lending amateur of the bank, so that the bank can further measure whether the borrowing requirements of the user should be approved or not.

S103, determining target article migration information of the user based on the article migration risk, the initial article cost and the initial article migration time.

The target article migration information may be understood as payment information of the bank to the user, including target article cost and target article returning time, the target article cost may be understood as loan amount approved by the bank to the user, and the target article returning time may be understood as payment time specified by the bank to the user.

Determining the target item migration information for the user based on the item migration risk, the initial item cost, and the initial item migration time may be understood as determining a loan amount and a repayment time based on the repayment risk and the item demand information for the user. Specifically, if the repayment risk of the user is low, the user is considered to pay back the repayment on time and in an amount, the user may pay back the repayment for the user according to the article requirement information of the user, that is, the target article migration information is determined to be the initial article cost and the initial article returning time, if the repayment risk of the user is high, the user is considered to not pay back the repayment on time and in an amount, the user may be refused to apply for the repayment or pay back the repayment for the user according to the percentage of the article requirement information of the user, for example, the target article migration information is determined to be refused to pay back, the target article cost is determined to be half of the initial article cost, the target article cost is determined to be one third of the initial article cost, the target article returning time is determined to be a certain time between the initial article returning time and the current time, and the like.

Further, the judgment of the repayment risk can be determined and adjusted according to the lending logic of the bank, which is not limited in this embodiment.

For example, assuming that the repayment risk is less than or equal to 30%, the repayment risk of the user is considered to be low, and assuming that the repayment risk is greater than 30%, the repayment risk of the user is considered to be high, the cost of the initial article of the user is 10 ten thousand, and the initial article returning time is 2022, 7 months and 10 days. If the repayment risk of the user is less than or equal to 30%, determining that the cost of the target article is 10 ten thousand, and the returning time of the target article is 2022, 7 months and 10 days; if the repayment risk of the user is greater than 30%, the user is refused to pay out the credit or the cost of the target article is 5 ten thousand (the payment amount is reduced), and the returning time of the target article is 2022, 6 and 10 days (the payment time is shortened).

It should be noted that the reduction scale of the loan amount and the reduction scale of the loan time may be set and adjusted according to the business requirement of the bank, and the article returning time may be accurate to time-division seconds or specific dates, which is not limited in this embodiment.

The method has the advantages that the payment information can be determined according to the credit risk and the repayment capability of the user, the bank payment risk is reduced, and the safety and feasibility of the lending business are improved.

According to the technical scheme, article demand information and historical article migration information of a user are determined, wherein the article demand information comprises initial article cost and initial article migration time; determining the article returning risk of the user based on the target risk determining model, the initial article cost, the initial article returning moment and the historical article transferring information; and determining target item migration information of the user based on the item migration risk, the initial item cost and the initial item migration time, wherein the target item migration information comprises the target item cost and the target item migration time. According to the method and the device, the article returning risk of the user is determined according to the risk determining model, the initial article cost, the initial article returning time and the historical article transferring information, and the target article transferring information is determined according to the article returning risk, the initial article cost and the initial article returning time in a targeted mode, so that the target article transferring information corresponding to the current article demand information can be determined efficiently, quickly and accurately by combining the historical article transferring information of the user, whether a bank carries out loan business for borrowers or not is indicated, the detailed information such as the limit and the term of the loan business is determined, the evaluation efficiency and the accuracy of the article demand are improved, and the manpower resources are saved. The method solves the problems that the credit information of borrowers needing agricultural loans is limited, the accuracy of the evaluation results of the credit information and repayment capability of the borrowers is affected by less information, the banks develop loan businesses with lower safety, a great deal of manpower resources and time resources are required for evaluating the loan credit and repayment capability of the borrowers according to credit files and historical loan information, once the evaluation capability of the technicians is limited or subjective consciousness is doped, the evaluation results of the loan credit and repayment capability are not representative, and the like, and the borrow credit and repayment capability cannot be used as guiding data for developing loan businesses.

Example two

Fig. 2 is a flow chart of a method for determining article migration information according to a second embodiment of the present invention, where the present embodiment is applicable to the credit check of farmers, small loans in rural areas, medium and small loans, and approval of agricultural loans, and the method may be performed by an apparatus for determining article migration information according to the present invention, where the apparatus may be implemented in hardware and/or software, and in a specific embodiment, the apparatus may be integrated in an electronic device. The following embodiment will be described taking the example of the integration of the device in an electronic apparatus, and referring to fig. 2, the method specifically includes the following steps:

s201, determining article demand information and historical article migration information of a user.

In this embodiment, the user may understand that there is a borrower with an agricultural loan requirement, and the article requirement information may be understood as information including the borrowing requirement of the user, including an initial article cost, an article use category, and an initial article returning time; the historical item migration information may be understood as a historical loan record of the user, including a number of loans, a historical loan amount, a repayment time of each historical loan amount, a loan use, a proportion of each loan category to all previous loan categories, a bad loan rate, bad loan information, a user home property, a user past repayment duration, a user home member, a loan credit of the user home member, repayment capability of the user home member, a crop collection rate of the user location, an extreme weather occurrence frequency of the user location, a climate of the user location, and the like, which is not limited in this embodiment.

Specifically, the initial item cost may be understood as the amount of the present debit required by the user, the initial item return time may be understood as the expected return time of the present debit, the item use category may be understood as the purpose of use of the debit, including purchasing seeds, purchasing farm tools, etc., and the historical item migration information is used to measure the repayment capability and credit risk of the user.

S202, determining at least one candidate feature information of a user based on initial item cost, initial item returning time and historical item transferring information.

Candidate feature information may be understood as feature data constructed based on what the user really is, such as feature vectors constructed based on initial item cost, initial item return time, and historical item migration information, which can represent lending data of the user.

It is worth noting that the number of candidate feature information is not limited, the candidate feature information is constructed to enrich the lending data of the user, strengthen the influence degree of accurate features on the sample, avoid the interference of noise data, and effectively prevent the influence of the noise data on the prediction result of credit risk. Secondly, the benefit of this arrangement is that the data set can be enlarged, improving the accuracy of assessment of the credit risk and repayment capabilities of the user.

In an embodiment, S202 may specifically include: determining at least one migration data model based on the initial item cost, the initial item return time and the historical item migration information; determining at least one piece of initial characteristic information, wherein the initial characteristic information corresponds to the candidate characteristic information one by one; and determining at least one candidate feature information based on the fitness of each migration data model and at least one initial feature information, wherein the candidate feature information is the initial feature information after deleting the invalid information.

The migration data model may be understood as a decision tree constructed based on initial item cost, initial item return time and historical item migration information, the initial feature information may be understood as a feature vector constructed based on user real data and capable of representing user lending data, the fitness of the migration data model may be understood as the importance degree of the migration data model, the fitness is determined based on an objective function of the migration data model, and the candidate feature information may be understood as initial feature information after invalid information is deleted (essentially, deleting data corresponding to a decision tree with lower fitness degree in the initial feature information).

The migration data model is a decision tree generated after clustering and dividing the initial article cost, the initial article returning time and the historical article migration information. Assuming that the user data includes a family class, a past class and a natural class, where the past class and the natural class each include a plurality of factors, the decision tree is divided into left and right nodes based on characteristics of each factor in turn until all the factors are divided, fig. 3 is a schematic diagram of a migration data model provided in the second embodiment of the present invention, fig. 3 shows a classification result, T in the diagram represents the decision tree, 1 represents the past class, 2 represents the family class (in the diagram, no leaf factor can be seen in the family class), 3 represents the natural class, and data such as 1.1, 1.2, 1.1.1, 1.2, 3.1.1, 3.2, 3.1.1.2, 3.1.3, etc. all represent factors.

It should be noted that different clustering methods may present different decision trees, and thus, multiple migration data models may be constructed based on the initial item cost, the initial item return time and the historical item migration information, and the objective function of each migration data model is different. Migrating objective functions of a data modelWherein j represents the number of the decision treeJ is equal to or greater than 1 and equal to or less than N, j is an integer, N represents the number of migration data models, lambda represents a random system, G represents a first order derivative of benefits of the migration data models, H represents a first order derivative of benefits of the migration data models, and the benefits of the migration data models are the sum of the benefits of all nodes of the migration data models.

The initial feature information is a vector with a length X, each element of the vector corresponds to a leaf node of a tree in the migration data model, the length is equal to the sum of leaf nodes of all model spanning trees, specifically, when a sample point finally falls onto one leaf node of a tree through a certain tree (decision tree), the element value corresponding to the leaf node in the vector of the initial feature information is 1, and the element values corresponding to other leaf nodes of the tree are 0. Describing the determination of the vector information of the decision tree by taking fig. 3 as an example, the decision tree in fig. 3 has 8 leaf nodes, and the sample points are assumed to fall on the 8 th leaf node, the decision tree has a representation form of 00000001 in the vector of the initial feature information, and the vector of the initial feature informationWhere L represents the number of leaf nodes of the decision tree.

It should be noted that, a part of the migration data model (i.e. decision tree) is useless or even harmful in determining the candidate feature information, so that it is necessary to determine decision tree retention vectors (essentially selecting a decision tree with high fitness and deleting relevant data of a decision tree with low fitness), the length of the decision tree retention vectors is the number of decision trees, when a certain column value of the decision tree retention vectors is 1, the vector representing the candidate feature information will select all leaf nodes of the decision tree, and when a certain column value of the decision tree retention vectors is 0, the vector representing the candidate feature information will not select all leaf nodes of the decision tree. The invention can select the preset number of decision trees with higher fitness from a plurality of decision trees through a genetic algorithm and a balance optimizer algorithm to serve as retention decision trees, and the retention vectors of the decision trees are vectors corresponding to the retention decision trees. The advantage of this arrangement is that the data throughput is reduced and the accuracy of the feature information is improved. It should be noted that the decision trees are updated in real time, that is, the present invention determines the fitness of each decision tree in real time to adjust the retention decision tree, the retention vector of the decision tree, and the candidate feature information.

The preset number can be set and adjusted according to the data screening requirement, including 4, 5, 6, etc., which is not limited in this embodiment.

And S203, determining the item migration risk based on the initial item cost, the initial item migration time, the historical item migration information, the at least one candidate feature information and the target risk determination model.

The target risk determination model may be understood as an algorithm capable of determining a payment risk of the user, and the initial item cost, the initial item return time, the item use category, the historical item migration information and at least one candidate feature information are input into the target risk determination model for processing, so that the item return risk of the user can be obtained, the item return risk may be understood as a return borrowing risk of the user, and specifically, the higher the item return risk, the lower the probability of the user returning the borrowing on time.

For example, determining the item return risk of the user based on the target risk determination model, the initial item cost, the initial item return time, the historical item migration information and the at least one candidate feature information may be understood as that the data of the initial item cost, the item use category, the initial item return time, the historical item migration information, the at least one candidate feature information and the like are input into the target risk determination model to be processed, and the repayment risk of the user is determined according to the output result of the target risk determination model.

Optionally, before determining the item return risk based on the initial item cost, the initial item return time, the historical item migration information, the at least one candidate feature information, and the target risk determination model, the method further includes: determining an initial risk determination model; training the initial risk determination model based on the initial item cost, the initial item returning time, the historical item transferring information and the at least one candidate feature information to obtain a target risk determination model.

The initial risk determination model may be understood as a predetermined model capable of determining a repayment risk of the user according to user data, and the target risk determination model is a risk determination model obtained by training the initial risk determination model based on an initial article cost, an initial article returning time, historical article transferring information and at least one candidate feature information of a borrower of a current lending task. The target risk determination model contains real data and constructed feature vectors of the borrower, has higher adaptation degree with the borrower, and can improve the accuracy of the determined credit risk.

S204, determining whether the article returning risk is smaller than or equal to a first risk threshold.

The first risk threshold can be understood as a basis for the user to return borrowing on time and on quantity, when the article returning risk is smaller than or equal to the first risk threshold, the user is considered to be able to return borrowing on time and on quantity, when the article returning risk is larger than the first risk threshold, the user is considered to be not necessarily able to return borrowing on time and the repayment risk of the user needs to be further checked.

Specifically, if the item return risk is less than or equal to the first risk threshold, S205 is executed, otherwise S206 is executed.

For example, assuming that the first risk threshold is 30%, if the item return risk is less than or equal to 30%, the user is considered to be able to return the borrowing on time and quantity, S205 is executed, and if the item return risk is greater than 30%, the user is considered to be not able to return the borrowing on time and quantity, and further checking of the repayment capability and repayment risk of the user is required, S206 is executed.

The advantage of this arrangement is that the assessment criteria for the user's repayment capability and repayment credit are quantified, so that the payment information of the bank can be determined quickly, accurately and efficiently.

S205, determining that the target item cost is the initial item cost, and the target item returning time is the initial item returning time.

Specifically, the target article cost is determined to be the initial article cost, and the target article returning time is the initial article returning time, which can be understood as that the bank completely approves the borrowing requirement of the user according to the amount and the repayment time applied by the user.

For example, assuming that the initial item cost of the user is 10 ten thousand, the initial item returning time is 2022, 7 months and 10 days, the target item cost is determined to be 10 ten thousand, and the target item returning time is 2022, 7 months and 10 days, namely the bank completely agrees with the item demand information of the user, and the repayment time is 2022, 7 months and 10 days and 10 ten thousand yuan are borrowed to the user.

S206, determining target item migration information based on the second risk threshold, the item migration risk, the initial item cost and the initial item migration time.

The second risk threshold is greater than the first risk threshold, and the second risk threshold can be understood as a basis for whether the user can not return the borrowing on time and on quantity.

In an embodiment, S206 may specifically include: determining whether the article reversion risk is less than or equal to a second risk threshold; if the article returning risk is smaller than or equal to the second risk threshold, determining target article transferring information based on a preset transferring information determining rule, initial article cost and initial article returning time; and if the article returning risk is greater than the second risk threshold, determining that the migration information of the target article is migration inhibition information.

The migration prohibition information is used for indicating that a staff member of the bank refuses the loan application of the user, because the user cannot return the borrowing on time according to the quantity. The migration information determining rule may be understood as a determining manner of borrowing information of a bank, and includes an article cost determining rule and a returning time determining rule, where the article cost determining rule is used for indicating a staff of the bank to determine a credit limit of borrowing to the user, and the returning time determining rule is used for indicating a staff of the bank to determine a credit limit of borrowing to the user.

For example, assuming that the first risk threshold is 30% and the second risk threshold is 50%, if the item return risk is greater than or equal to 50%, then lending to the user is refused, and if the item return risk is greater than 30% and less than 50%, then the target item migration information is determined based on the item cost determination rule, the return time determination rule, the initial item cost, and the initial item return time.

Further, determining the target item migration information based on a preset migration information determining rule, an initial item cost and an initial item return time, including: determining a target item cost based on the item cost determination rule and the initial item cost; and determining the target article returning time based on the returning time determining rule and the initial article returning time.

The article cost determining rule may be to determine that one half of the initial article cost is the target article cost, determine that one third of the initial article cost is the target article cost, determine that three quarters of the initial article cost is the target article cost, determine that one quarter of the initial article cost is the target article cost, and the like, and the returning time determining rule may be to determine the target article returning time based on a preset proportion of a time length of the current time to the initial article returning time, for example, determine that a time corresponding to a half of a time length of the initial article returning time is the target article returning time, determine that a time corresponding to a third of a time length of the initial article returning time is the target article returning time, and the like, which is not limited in this embodiment.

For example, assuming that the item cost determination rule is to determine that one half of the initial item cost is the target item cost, the return time determination rule is to determine that a time corresponding to one half of the time length of the initial item return time at the current time is the target item return time. The current time is 2022, 5 months and 10 days, the initial article cost of the user is 10 ten thousand, the initial article returning time is 2022, 7 months and 10 days, the target article cost is 5 ten thousand, and the target article returning time is 2022, 6 months and 10 days.

According to the technical scheme, article demand information and historical article migration information of a user are determined, wherein the article demand information comprises initial article cost and initial article migration time; determining at least one candidate feature information of the user based on the initial item cost, the initial item return time and the historical item migration information; determining an item migration risk based on the initial item cost, the initial item migration time, the historical item migration information, the at least one candidate feature information and the target risk determination model; determining whether the article reversion risk is less than or equal to a first risk threshold; if the article returning risk is smaller than or equal to the first risk threshold, determining that the target article cost is the initial article cost, and determining that the target article returning time is the initial article returning time; and if the article returning risk is greater than the first risk threshold, determining target article transferring information based on a second risk threshold, the article returning risk, the initial article cost and the initial article returning time, wherein the second risk threshold is greater than the first risk threshold. According to the method and the device, the article returning risk of the user is determined according to the risk determining model, the initial article cost, the initial article returning time, at least one candidate characteristic information and the historical article transferring information, and the target article transferring information is determined according to the article returning risk, the initial article cost, the initial article returning time and the first risk threshold pertinence, so that the target article transferring information such as the target article cost and the target article returning time corresponding to the current article demand information can be effectively, quickly and accurately determined by combining the historical article transferring information of the user, and the bank can be indicated whether to develop loan service for borrowers or not and the detailed information such as the limit and the deadline of the loan service is determined, the evaluation efficiency and the accuracy of the article demand are improved, and the manpower resources are saved. The method solves the problems that the credit information of borrowers needing agricultural loans is limited, the accuracy of the evaluation results of the credit information and repayment capability of the borrowers is affected by less information, the banks develop loan businesses with lower safety, a great deal of manpower resources and time resources are required for evaluating the loan credit and repayment capability of the borrowers according to credit files and historical loan information, once the evaluation capability of the technicians is limited or subjective consciousness is doped, the evaluation results of the loan credit and repayment capability are not representative, and the like, and the borrow credit and repayment capability cannot be used as guiding data for developing loan businesses.

Example III

Fig. 4 is a schematic structural diagram of an apparatus for determining migration information of an article according to a third embodiment of the present invention. As shown in fig. 4, the apparatus includes: an acquisition module 401, a determination module 402 and an execution module 403.

The obtaining module 401 is configured to determine item requirement information and historical item migration information of a user, where the item requirement information includes an initial item cost and an initial item migration time.

The determining module 402 is configured to determine an item migration risk of the user based on the target risk determining model, the initial item cost, the initial item migration time, and the historical item migration information.

The execution module 403 is configured to determine target item migration information of the user based on the item migration risk, the initial item cost, and the initial item migration time, where the target item migration information includes the target item cost and the target item migration time.

Optionally, the determining module 402 is specifically configured to determine at least one candidate feature information of the user based on the initial item cost, the initial item return time and the historical item migration information; and determining the item migration risk based on the initial item cost, the initial item migration time, the historical item migration information, the at least one candidate feature information and the target risk determination model.

Optionally, the determining module 402 is specifically configured to determine at least one migration data model based on the initial item cost, the initial item return time and the historical item migration information; determining at least one piece of initial characteristic information, wherein the initial characteristic information corresponds to the candidate characteristic information one by one; and determining at least one candidate feature information based on the fitness of each migration data model and at least one initial feature information, wherein the candidate feature information is the initial feature information after deleting the invalid information.

Optionally, the determining module 402 is further configured to determine an initial risk determining model before determining the item migration risk based on the initial item cost, the initial item migration time, the historical item migration information, the at least one candidate feature information, and the target risk determining model; training the initial risk determination model based on the initial item cost, the initial item returning time, the historical item transferring information and the at least one candidate feature information to obtain a target risk determination model.

Optionally, the execution module 403 is specifically configured to determine whether the risk of article reversion is less than or equal to a first risk threshold; if the article returning risk is smaller than or equal to the first risk threshold, determining that the target article cost is the initial article cost, and determining that the target article returning time is the initial article returning time; and if the article returning risk is greater than the first risk threshold, determining target article transferring information based on a second risk threshold, the article returning risk, the initial article cost and the initial article returning time, wherein the second risk threshold is greater than the first risk threshold.

Optionally, the executing module 403 is specifically configured to determine whether the risk of article returning is less than or equal to a second risk threshold; if the article returning risk is smaller than or equal to the second risk threshold, determining target article transferring information based on a preset transferring information determining rule, initial article cost and initial article returning time; and if the article returning risk is greater than the second risk threshold, determining that the migration information of the target article is migration inhibition information.

Optionally, the migration information determining rule includes an item cost determining rule and a returning time determining rule.

Optionally, the executing module 403 is specifically configured to determine the target item cost based on the item cost determining rule and the initial item cost; and determining the target article returning time based on the returning time determining rule and the initial article returning time.

The device for determining the article migration information provided by the embodiment of the invention can execute the method for determining the article migration information provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.

Example IV

Fig. 5 is a schematic structural diagram of an electronic device according to a fourth embodiment of the present invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. Electronic equipment may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.

As shown in fig. 5, the electronic device 10 includes at least one processor 11, and a Memory communicatively connected to the at least one processor 11, such as a Read Only Memory (ROM) 12, a random access Memory (also referred to as a random access Memory, random Access Memory, RAM) 13, etc., in which a computer program executable by the at least one processor is stored, and the processor 11 may perform various suitable actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from the storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 may also be stored. The processor 11, the ROM 12 and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to bus 14.

Various components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, etc.; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.

The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, digital Signal Processors (DSPs), and any suitable processor, controller, microcontroller, etc. The processor 11 performs the various methods and processes described above, such as the determination of item migration information.

In some embodiments, the method of determining item migration information may be implemented as a computer program tangibly embodied on a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM 12 and/or the communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the method of determining item migration information described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the method of determining the item migration information in any other suitable manner (e.g., by means of firmware).

Various implementations of the systems and techniques described here above can be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.

A computer program for carrying out methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be implemented. The computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on 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.

To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server) or that includes a middleware component (e.g., an application server) or that includes a front-end component through which a user can interact with an implementation of the systems and techniques described here, or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.

The computing system may include clients and servers. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service are overcome.

It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution of the present invention are achieved, and the present invention is not limited herein.

The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.

Claims (10)

1. A method for determining migration information of an article, comprising:

determining article demand information and historical article migration information of a user, wherein the article demand information comprises initial article cost and initial article migration time;

determining the article returning risk of the user based on a target risk determining model, the initial article cost, the initial article returning moment and the historical article transferring information;

And determining target item migration information of the user based on the item migration risk, the initial item cost and the initial item migration time, wherein the target item migration information comprises the target item cost and the target item migration time.

2. The method of claim 1, wherein the determining the item migration risk for the user based on the target risk determination model, the initial item cost, the initial item migration time, and the historical item migration information comprises:

determining at least one candidate feature information of the user based on the initial item cost, the initial item return time and the historical item migration information;

and determining the article return risk based on the initial article cost, the initial article return time, the historical article migration information, the at least one candidate feature information and the target risk determination model.

3. The method of claim 2, wherein the determining at least one candidate feature information for the user based on the initial item cost, the initial item return time, and the historical item migration information comprises:

Determining at least one migration data model based on the initial item cost, the initial item return time and the historical item migration information;

determining at least one piece of initial characteristic information, wherein the initial characteristic information corresponds to the candidate characteristic information one by one;

and determining at least one candidate feature information based on the fitness of each migration data model and the at least one initial feature information, wherein the candidate feature information is the initial feature information after invalid information is deleted.

4. The method of claim 2, further comprising, prior to determining the item migration risk based on the initial item cost, the initial item migration time, the historical item migration information, the at least one candidate feature information, and the target risk determination model:

determining an initial risk determination model;

and training the initial risk determination model based on the initial item cost, the initial item returning time, the historical item migration information and the at least one candidate feature information to obtain the target risk determination model.

5. The method of claim 1, wherein the determining the target item migration information for the user based on the item migration risk, the initial item cost, and the initial item migration time comprises:

Determining whether the article reversion risk is less than or equal to a first risk threshold;

if the article returning risk is smaller than or equal to the first risk threshold, determining that the target article cost is the initial article cost, wherein the target article returning moment is the initial article returning moment;

and if the article returning risk is greater than the first risk threshold, determining the target article transferring information based on a second risk threshold, the article returning risk, the initial article cost and the initial article returning time, wherein the second risk threshold is greater than the first risk threshold.

6. The method of claim 5, wherein the determining the target item migration information based on a second risk threshold, the item migration risk, the initial item cost, and the initial item migration time comprises:

determining whether the article reversion risk is less than or equal to a second risk threshold;

if the article returning risk is smaller than or equal to the second risk threshold, determining the target article transferring information based on a preset transferring information determining rule, the initial article cost and the initial article returning time;

And if the article returning risk is greater than the second risk threshold, determining that the target article migration information is migration inhibition information.

7. The method of claim 6, wherein the migration information determination rules include an item cost determination rule and a return time determination rule;

the determining the target article migration information based on a preset migration information determining rule, the initial article cost and the initial article returning time comprises the following steps:

determining the target item cost based on the item cost determination rule and the initial item cost;

and determining the target article returning time based on the returning time determining rule and the initial article returning time.

8. An apparatus for determining migration information of an article, comprising:

the acquisition module is used for determining article demand information and historical article migration information of a user, wherein the article demand information comprises initial article cost and initial article migration time;

the determining module is used for determining the article returning risk of the user based on the target risk determining model, the initial article cost, the initial article returning moment and the historical article transferring information;

And the execution module is used for determining target article migration information of the user based on the article migration risk, the initial article cost and the initial article migration time, wherein the target article migration information comprises the target article cost and the target article migration time.

9. An electronic device, the electronic device comprising:

at least one processor; and a memory communicatively coupled to the at least one processor;

wherein the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the method of determining item migration information of any one of claims 1 to 7.

10. A computer readable storage medium storing computer instructions for causing a processor to perform the method of determining item migration information according to any one of claims 1 to 7.