CN114677207A

CN114677207A - Personal operation credit granting evaluation method based on Bayesian learning and related products

Info

Publication number: CN114677207A
Application number: CN202210269303.8A
Authority: CN
Inventors: 许卫; 欧阳张鹏; 赵彦晖; 耿心伟; 曾源
Original assignee: Shenzhen Weizhong Credit Technology Co ltd
Current assignee: Shenzhen Weizhong Credit Technology Co ltd
Priority date: 2022-03-18
Filing date: 2022-03-18
Publication date: 2022-06-28

Abstract

The application provides a personal operation credit evaluation method based on Bayesian learning and a related product, wherein the method comprises the following steps: receiving a loan application from a target user requesting a guaranteed loan for a target business entity; acquiring business plan information of a target business subject, credit evaluation information of a target user and historical operating condition information of other business subjects under a target user name; analyzing the business association between the business plan information of the target business subject and the historical business condition information of other business subjects to determine a first business risk value; inputting the credit evaluation information of the target user and the business plan information of the target business subject into a Bayesian learning model to obtain a second operation risk value; and determining the evaluation result of the loan application according to the first operating risk value and the second operating risk value. By adopting the method of the embodiment of the application, credit assessment is accurately carried out on the personal business loan, and further the loan risk is avoided.

Description

Personal business credit granting evaluation method based on Bayesian learning and related products

Technical Field

The application relates to the technical field of data processing, in particular to a personal operation credit and credit granting evaluation method based on Bayesian learning and a related product.

Background

With the rapid development of social economy and the continuous improvement of productivity level, the market operation activity is increasingly active, and loan guarantee behaviors conditioned on repayment and payment are also explosively increased in number in order to promote further development of economy to meet the demand of each business entity on the market for expanding productivity to funds.

In a huge amount of loan security activities, there are several different loan categories, and one of the loan categories is personal loan. When a financial institution issues a personal business loan, the financial institution needs to know the operation condition of the borrower operation enterprise in detail besides needs to know the condition of the borrower. Because the information used for credit granting evaluation is more, the financial institution is difficult to carry out comprehensive and accurate credit granting evaluation on the personal business loan, so the risk control difficulty of the personal business loan is higher, and the financial institution has certain loan risk when issuing the personal business loan.

Disclosure of Invention

The embodiment of the application provides a personal business loan credit granting assessment method based on Bayesian learning and related products.

In a first aspect, an embodiment of the present application provides a personal operation credit and credit authorization evaluation method based on bayesian learning, where the method includes:

receiving a loan application from a target user, wherein the loan application is used for requesting a guarantee loan for a target business subject;

acquiring business plan information of a target business subject, credit evaluation information of a target user and historical operation condition information of other business subjects under a target user name;

analyzing the business association between the business plan information of the target business subject and the historical business condition information of other business subjects to determine a first business risk value;

inputting the credit evaluation information of the target user and the business plan information of the target business subject as input items into the Bayesian learning model to obtain a second operation risk value;

and determining an evaluation result of the loan application according to the first operating risk value and the second operating risk value, wherein the evaluation result of the loan application comprises the passing loan application or the not passing loan application.

In one possible example, the user evaluation condition includes a first condition indicating that the number of intellectual property rights under the historical user name is greater than a preset number, the business entity evaluation condition includes a second condition indicating that the development cost duty of the business entity is greater than a preset duty, and the obtaining at least one combined condition event according to the at least one user evaluation condition and the at least one business entity evaluation condition includes:

obtaining a combined condition event according to the first condition occurrence and the second condition occurrence; and/or deriving a combined conditional event based on the first condition not occurring and the second condition not occurring.

In a second aspect, an embodiment of the present application provides a personal operation credit granting evaluation apparatus based on bayesian learning, where the apparatus includes:

a receiving unit for receiving a loan application from a target user, the loan application being for requesting a secured loan for a target business entity;

the system comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring business plan information of a target business main body, credit evaluation information of a target user and historical operation condition information of other business main bodies under a target user name;

the analysis unit is used for analyzing the operation relevance between the business plan information of the target business body and the historical operation condition information of other business bodies to determine a first operation risk value;

The model unit is used for inputting credit evaluation information of a target user and business plan information of a target business main body into the Bayesian learning model as input items to obtain a second operation risk value;

and the evaluation unit is used for determining the evaluation result of the loan application according to the first operation risk value and the second operation risk value, and the evaluation result of the loan application comprises the loan application passing or not passing.

In a third aspect, embodiments of the present application provide an electronic device, which includes a processor, a memory, and computer executable instructions stored on the memory and executable on the processor, and when the computer executable instructions are executed, the electronic device is caused to perform some or all of the steps described in any one of the methods of the first aspect of the embodiments of the present application.

In a fourth aspect, embodiments of the present application provide a computer-readable storage medium having stored thereon computer instructions, which, when executed on a communication apparatus, cause the communication apparatus to perform some or all of the steps as described in any one of the methods of the first aspect of the embodiments of the present application.

In a fifth aspect, the present application provides a computer program product, where the computer program product includes a computer program operable to cause a computer to perform some or all of the steps as described in any one of the methods of the first aspect of the embodiments of the present application. The computer program product may be a software installation package.

It can be seen that, in the embodiment of the application, the first operation risk value is determined by analyzing the operation relevance between the business plan information of the target business subject and the historical operation condition information of other business subjects, the credit evaluation information of the target user and the business plan information of the target business subject are used as input items and input into the bayesian learning model to obtain the second operation risk value, and then the evaluation result of the loan application is determined according to the first operation risk value and the second operation risk value. By adopting the method of the embodiment of the application, when facing various and huge information of users and business bodies, financial institutions can also comprehensively and accurately carry out credit granting evaluation on individual business loans, thereby avoiding loan risks and ensuring sustainable development of loan services.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.

FIG. 1 is a schematic diagram of an exemplary trust evaluation system;

fig. 2 is a schematic flowchart of a personal operation credit and credit assessment method based on bayesian learning according to an embodiment of the present application;

fig. 3 is a schematic structural diagram of a bayesian learning model according to an embodiment of the present application;

fig. 4 is a schematic structural diagram of a personal operation credit and credit authorization evaluation system based on bayesian learning according to an embodiment of the present application;

fig. 5 is a schematic diagram illustrating an example of a personal operation credit and credit assessment method based on bayesian learning according to an embodiment of the present application;

fig. 6 is a schematic structural diagram of a personal operation credit and credit authorization evaluation device based on bayesian learning according to an embodiment of the present application;

fig. 7 is a schematic server structure diagram of a hardware operating environment of an electronic device according to an embodiment of the present application.

Detailed Description

In order to make the technical solutions of the present application better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

The terms "first," "second," and the like in the description and claims of the present application and in the foregoing drawings are used for distinguishing between different objects and not for describing a particular sequential order. Furthermore, the terms "include" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, system, article, or apparatus that comprises a list of steps is not limited to only those steps recited, but may alternatively include other steps not recited, or may alternatively include other steps inherent to such process, method, article, or apparatus.

Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.

The following describes an application scenario related to an embodiment of the present application with reference to the drawings.

Fig. 1 is a schematic diagram of an exemplary trust evaluation system. As shown in fig. 1, the system includes a target user terminal, a financial institution terminal, and a risk assessment model.

The target user terminal has a loan guarantee requirement, so that a loan application is submitted to the financial institution terminal to request for obtaining a guarantee loan, and the loan application comprises credit granting evaluation information of the target user;

the credit assessment information may include credit assessment information of the target user, and when the guarantee loan is a personal business loan, the credit assessment information may further include business plan information or other information of a business subject to which the target user intends to invest;

the financial institution terminal receives a loan application from a target user terminal, inputs credit granting evaluation information in the loan application into the risk evaluation model to obtain an evaluation result for the target user, and determines whether to grant a guarantee loan to the target user according to the evaluation result;

the risk evaluation model is used for evaluating the credit granting evaluation information input into the risk evaluation model, determining the loan default risk corresponding to the credit granting evaluation information and outputting an evaluation result.

It can be seen that, in the process of the system performing credit granting evaluation, because the risk evaluation model only uses the traditional evaluation mechanism to predict the loan default risk corresponding to the credit granting evaluation information, if the loan type applied by the target user is a loan with a large content of the credit granting evaluation information, such as a personal operation loan, the process cannot perform further and more accurate evaluation analysis according to the information relevance between a plurality of information items in the credit granting evaluation information, and therefore, the process cannot perform the credit granting evaluation on the loan comprehensively and accurately, may cause the financial institution to lose the potential customer, and may also cause the potential customer to get the loan to have a certain loan risk, which is very unfavorable for the development continuity of the loan service.

Based on this, an embodiment of the present application provides a personal business credit and credit assessment method based on bayesian learning, please refer to fig. 2, fig. 2 is a schematic flow diagram of the personal business credit and credit assessment method based on bayesian learning provided in the embodiment of the present application, as shown in fig. 2, the method includes the following steps:

101: a loan application is received from a target user, the loan application for requesting a secured loan for a target business entity.

The target business subject can be an individual industrial business, an enterprise or other business subjects.

The guarantee loan is a personal business loan. The personal business loan refers to a loan which is issued by a financial institution to a borrowed user and is used for legal production and operation activities such as the turnover of mobile funds of a business entity to be invested, the purchase or update of operating equipment, the payment of rent of a lease operating place, the decoration of commercial houses and the like.

102: business plan information of the target business main body, credit evaluation information of the target user and historical operation condition information of other business main bodies under the target user name are obtained.

The business planning information of the target business entity may include information such as a business scope planned by the target business entity, a target customer group, and strategic positioning.

The credit evaluation information of the target user may include personal credit information, tax payment information, judicial information (including executed person information and legal litigation information), black-gray list information (a court black-gray list, a commission committee black-gray list, a network credit black-gray list), and the like of the target user.

In a specific implementation, before obtaining the credit evaluation information of the target user, authorization operation of the target user is required for part of the information, which is not facing the social disclosure, in the credit evaluation information, and the authorization operation is used for indicating that the target user agrees to obtain the part of the information, which is not facing the social disclosure, in the credit evaluation information of the target user by a financial institution so as to process a loan guarantee transaction.

The historical operation condition information of other business entities under the target user name may include the operation range, the operation place information, the profit capacity and other information of other business entities. Other business entities, which may be individual industrial businesses, or other forms of business entities.

The business plan information of the target business subject, the credit evaluation information of the target user and the historical operating condition information of other business subjects under the target user name can be included in the loan application in the specific implementation, so that the information can be obtained in the loan application; or may be separately acquired in the respective corresponding information channels.

103: and analyzing the business planning information of the target business subject and the historical business condition information of other business subjects to determine a first business risk value.

In a specific implementation, the business plan information of the target business entity and the historical business situation information of the other business entities may be analyzed based on information items of the same nature.

In specific implementation, due to the business planning information of the target business subject and the historical business situation information of other business subjects, the business capacity of the target user in the corresponding business field can be often reflected, and the business capacity of the target user in the corresponding business field is an extremely important influence factor for the business situation of the target business subject, which can greatly influence the business development potential and the profitability of the target business subject. Therefore, the accuracy of loan application risk assessment can be remarkably improved by analyzing the business plan information of the target business body and the historical business situation information of other business bodies to determine the first business risk value.

Further, since the same user has experience with a certain operating range, it is easier to succeed in operating the same operating range again. Therefore, the first operation risk value is in a negative correlation with the business plan information of the target business main body and the historical operation condition information of other business main bodies, that is, the greater the business correlation between the business plan information of the target business main body and the historical operation condition information of other business main bodies, the lower the first operation risk value.

In an exemplary implementation, the business plan information of the target business entity and the historical business situation information of the other business entities are analyzed to determine whether business relations exist between the business ranges in the business plan information of the target business entity and the business ranges in the historical business situation information of the other business entities, and if the business ranges are similar, the business relations are determined to exist, and the first business risk value of the loan application is lower.

104: and inputting the credit evaluation information of the target user and the business plan information of the target business subject as input items into the Bayesian learning model to obtain a second operation risk value.

Wherein, Bayesian learning is to directly calculate the overall distribution by using the prior distribution of parameters and the posterior distribution obtained from the sample information. The result of bayesian learning is represented as a probability distribution of random variables, which can be understood as our degree of confidence in different possibilities.

In the concrete implementation, because the credit evaluation information of the target user and the business plan information of the target business main body have huge and scattered information quantity, and the traditional risk evaluation model is difficult to find out whether the specific information has joint influence on the loan application risk or not, in order to establish an information association mechanism between the personal reputation of the user and the business plan implementation so as to accurately evaluate the loan application risk, the embodiment of the application analyzes and processes the association relationship between the credit evaluation information of the target user and the business plan information of the target business main body through the Bayesian learning model, and further can extract the key information influencing the loan application risk from the huge and scattered information quantity so as to ensure the reliability of the loan application risk evaluation.

In a specific implementation, the bayesian learning model includes a bayesian learning formula, and the bayesian learning formula may be in the form of: p (X | a, B, C, D … …) ═ P (X | a) × P (X | B) × P (X | C) × P (X | D) … …, where X is the event to occur, A, B, C, D … … is the condition event that has occurred, and P (X | a) represents the probability value that the event X will occur if an a condition event has occurred.

Illustratively, the loan application risk value is X, the information item in the credit evaluation information of the target user is A, B, C, and the information item in the business plan information of the target business entity is a ', B ', and C ', where a has information correlation with a ', B and B ', and C ', so that the loan application risk value X is taken as an event to be occurred, and a ', B and B ', C and C ' are taken as conditional events that have occurred, so that the bayesian learning formula followed by the bayesian learning model when obtaining the second business risk value is: the second business risk value P (X | a, a ')/P (X | B, B ')/P (X | C, C '), where P (X | a, a ') represents the loan application risk value X in the case where both a and a ' conditional events have occurred.

The Bayesian learning model can comprise an input layer, a formula layer and an output layer.

Based on the foregoing exemplary embodiment, please refer to fig. 3, fig. 3 is a schematic structural diagram of a bayesian learning model provided in the embodiment of the present application, and as shown in fig. 3, the bayesian learning model includes the following layers:

the input layer is used for receiving the credit evaluation information of the target user and the business plan information of the target business subject, and correspondingly substituting the information item A, B, C in the credit evaluation information of the target user and the information items A ', B ' and C ' in the business plan information of the target business subject into each parameter in the Bayesian learning formula included in the formula layer;

the formula layer comprises a Bayesian learning formula: the second business risk value P (X | a, a ')/P (X | B, B')/P (X | C, C ') is calculated based on the information items A, B, C, A', B ', C' substituted into the input layer and the bayesian learning formula.

And the output layer is used for outputting the second operation risk value obtained by calculation of the formula layer.

It should be noted that the bayesian learning model shown in fig. 3 is only an example of a bayesian learning model, and in a specific application, the bayesian learning model may also exist in other hierarchical forms.

105: and determining an evaluation result of the loan application according to the first operation risk value and the second operation risk value, wherein the evaluation result of the loan application comprises the passing loan application or the not passing loan application.

In a specific implementation, the first operation risk value and the second operation risk value are both smaller than the preset operation risk value, the sum of the first operation risk value and the second operation risk value is smaller than the preset operation risk value, and the product of the first operation risk value and the second operation risk value is smaller than the preset operation risk value.

For example, referring to fig. 4, fig. 4 is a schematic diagram of an architecture of a personal operation credit authorization evaluation system based on bayesian learning according to an embodiment of the present application, as shown in fig. 4, the system includes a server and a bayesian learning model. In order to obtain a personal business loan from a financial institution for the business activity of a target business entity, a target user submits a loan application to a financial institution terminal by using the target user terminal, the financial institution terminal acquires business plan information of the target business entity, credit evaluation information of the target user and historical business condition information of other business entities under the target user name, and then sends the information to a personal business loan credit granting evaluation system based on Bayesian learning, a server in the system receives the information and analyzes the business association between the business plan information of the target business entity and the historical business condition information of other business entities to determine a first business risk value, and simultaneously, the server inputs the credit evaluation information of the target user and the business plan information of the target business entity into a Bayesian learning model in the system, and the Bayesian learning model outputs a second operation risk value to be fed back to the server, and the server determines that the evaluation result of the loan application is that the target user applies for the loan and feeds back the evaluation result to the financial institution terminal because the first operation risk value and the second operation risk value are both smaller than the preset operation risk value.

It can be seen that, in the embodiment of the application, the first operation risk value is determined by analyzing the operation relevance between the business plan information of the target business subject and the historical operation condition information of other business subjects, the credit evaluation information of the target user and the business plan information of the target business subject are used as input items and input into the bayesian learning model to obtain the second operation risk value, and then the evaluation result of the loan application is determined according to the first operation risk value and the second operation risk value. By adopting the method of the embodiment of the application, when facing to the information of a user and a business subject with various aspects and huge amount, the financial institution can also comprehensively and accurately carry out credit granting evaluation on the personal business loan, thereby avoiding loan risks and ensuring the sustainable development of loan business.

In one possible example, the method further comprises:

and if the first operation risk value and the second operation risk value are lower than the preset operation risk value, determining that the evaluation result of the loan application is a passing loan application.

The value ranges of the first operation risk value and the second operation risk value can be 0-1, and the preset operation risk value can be 0.6, 0.8 or other operation risk values.

It can be seen that, in the embodiment of the application, when both the first operational risk value and the second operational risk value are lower than the preset operational risk value, the evaluation result of the loan application is determined to be the loan application, so that it is ensured that the default risk of the target user who can obtain a loan is lower, and further, the loan risk is avoided, and the sustainable development of the loan service is ensured.

In one possible example, the training process of the bayesian learning model described above is as follows:

acquiring a training data set, wherein the training data set comprises credit evaluation information of historical users in a plurality of historical loan applications and business plan information of historical business subjects;

inputting the training data set into an initial learning model to obtain the predicted operation risk values of a plurality of historical loan applications;

comparing the predicted operation risk values of the plurality of historical loan applications with the historical operation risk values corresponding to the plurality of historical loan applications, and determining that the prediction of the initial learning model is accurate if the error between the predicted operation risk value and the historical operation risk value is within a preset error range;

determining the prediction accuracy of the initial learning model, wherein the prediction accuracy represents the proportion of the historical loan application which is predicted accurately in the training data set to the training data set;

And under the condition that the prediction accuracy is less than the preset accuracy, performing iterative training on the initial learning model, and if the prediction accuracy of the initial learning model is higher than or equal to the preset accuracy, determining that the training of the initial learning model is finished to obtain the Bayesian learning model.

In one possible example, the method further includes:

obtaining at least one user evaluation condition and at least one business subject evaluation condition according to credit evaluation information of historical users and business plan information of historical business subjects;

obtaining at least one combined condition event according to at least one user evaluation condition and at least one business subject evaluation condition;

generating a conditional probability factor according to at least one combined conditional event, wherein the occurred conditional event in the conditional probability factor corresponds to an expected second risk value and/or an unexpected second risk value, the expected second risk value is the second risk value when the evaluation result of the historical loan application is applied for passing the loan, the unexpected second risk value is the second risk value when the evaluation result of the historical loan application is not applied for passing the loan, and the event to be occurred in the conditional probability factor corresponds to at least one combined conditional event;

And logically combining at least one conditional probability factor to generate an initial learning model.

The value ranges of the predicted operation risk value and the historical operation risk value can be 0-1, and the preset error range can be +/-0.05.

In a specific implementation, the initial learning model is iteratively trained, and the specific information items of the credit evaluation information of the historical user and the business plan information of the historical business subject, which are included in the training data set input into the initial learning model, may be adjusted, or the specific evaluation condition included in at least one combined condition event in the condition probability factor may be adjusted.

The preset accuracy can be represented by a numerical value form of 0-1 or a percentage system form of 0-100%. If the numerical form of 0-1 is adopted for representation, the preset accuracy can be 0.8, 0.9 or other accuracy; if the percentage system form of 0-100% is adopted, the preset accuracy can be 80%, 90% or other accuracy.

The user evaluation condition is a specific information item in the credit evaluation information of the historical user; the business subject evaluation condition is a specific information item in the business plan information of the historical business subject.

Exemplarily, please refer to fig. 5, fig. 5 is a schematic diagram illustrating an example of a personal business loan credit granting evaluation method based on bayesian learning according to an embodiment of the present application, and as shown in fig. 5, in order to generate an initial learning model, first, user evaluation conditions 1-N and business entity evaluation conditions 1-N are obtained according to credit evaluation information of a historical user and business plan information of a historical business entity, respectively; then, correspondingly combining the user evaluation conditions 1-N and the business subject evaluation conditions 1-N respectively to obtain combined condition events 1-N, wherein the combined condition event 1 represents that the user evaluation condition 1 and the business subject evaluation condition 1 occur simultaneously … … and the combined condition event N represents that the user evaluation condition N and the business subject evaluation condition N occur simultaneously; generating conditional probability factors 1-N according to the combined conditional events 1-N, wherein the to-be-occurred events of the conditional probabilities factors 1-N are all the expected second risk values, where the conditional probability factor 1 can be represented as P-1 (the expected second risk value | combined conditional event 1) ═ P-1 (the expected second risk value | user evaluation condition 1, business subject evaluation condition 1) … …, and the conditional probability factor N can be represented as P-N (the expected second risk value | combined conditional event N) ═ P-N (the expected second risk value | user evaluation condition N, business subject evaluation condition N); finally, the conditional probabilities of the formula 1-N are logically combined, and the product of the conditional probabilities of the formula 1-N is used as a second operational risk value, that is, the second operational risk value is a conditional probability of the formula 1 × … …, and the conditional probability of the formula N is P-1 (the second expected risk value | user evaluation condition 1, business entity evaluation condition 1) × … … × P-N (the second expected risk value | combined condition event N), so as to complete the initial learning model generation process.

It should be noted that the initial learning model generation process shown in fig. 5 is only an example of an initial learning model generation process, and in a specific application, the initial learning model generation process may also be implemented in other ways.

It can be seen that in the training process of the bayesian learning model provided in the embodiment of the present application, the initial learning model is generated by obtaining at least one user evaluation condition and at least one business entity evaluation condition according to the credit evaluation information of the historical users and the business plan information of the historical business entities, obtaining at least one combined condition event according to the at least one user evaluation condition and the at least one business entity evaluation condition, generating a conditional probability factor according to the at least one combined condition event, and finally performing a logical combination on the at least one conditional probability factor, and only when the prediction accuracy of the initial learning model is higher than or equal to the preset accuracy, it is determined that the training of the initial learning model is successful, so as to obtain the bayesian learning model. Furthermore, the second operation risk value of the individual operation type loan application is predicted by using the Bayesian learning model trained in the training process provided by the embodiment of the application, so that the accuracy of the financial institution for predicting the loan risk can be improved while the manpower of the financial institution personnel is liberated.

In one possible example, the user evaluation condition includes a first condition indicating that a rate of tax payment completion of the historical user is greater than a preset completion rate, the business entity evaluation condition includes a second condition indicating that a proportion of user responsibility of the historical user in the business entity is greater than a preset proportion, and the obtaining at least one combined condition event according to the at least one user evaluation condition and the at least one business entity evaluation condition includes:

obtaining a combined condition event according to the first condition occurrence and the second condition occurrence; and/or a combined conditional event is derived based on the first condition not occurring and the second condition not occurring.

The rate of completing the tax payment of the historical user refers to the completion condition of completing the tax payment declaration of the historical user.

In the concrete implementation, the credit ability of the historical user is good due to the fact that the rate of completion of tax payment of the historical user is good, and when the proportion of responsibility of the historical user in the business subject is large, the participation degree of the historical user in business decision of the business subject is higher, and the good credit ability of the historical user can be better exerted, namely, if the rate of completion of tax payment of the historical user is larger than the preset rate of completion and the proportion of responsibility of the historical user in the business subject is larger than the preset rate, the default risk of the loan application is lower, otherwise, the same is true, and therefore, the combined condition event is obtained according to the occurrence of the first condition and the occurrence of the second condition; and/or a combined conditional event is derived based on the first condition not occurring and the second condition not occurring.

The preset completion rate can be represented by a numerical value form of 0-1 or a percentage system form of 0-100%. If the numerical form of 0-1 is adopted for representation, the preset completion rate can be 0.8, 0.9 or other accuracy degrees; if the percentage system form of 0-100% is adopted, the preset completion rate can be 80%, 90% or other accuracy.

The user responsibility ratio of the historical user in the business subject can refer to the stock holding ratio of the historical user in the business subject, and can also refer to the registered capital investment ratio of the historical user to the business subject.

Illustratively, if a combined conditional event is obtained according to the first conditional occurrence and the second conditional occurrence, and a conditional probability factor is generated according to the combined conditional event, the conditional probability factor is equal to (the second risk value | the first conditional occurrence, and the second conditional occurrence) (the second risk value | the rate of completion of taxation of the historical user is expected to be greater than the preset rate, and the proportion of user responsibility of the historical user in the business entity is greater than the preset proportion).

Based on the above exemplary embodiment, in a specific implementation, the second operation risk value corresponding to the case where the rate of completing the tax payment of the historical user is greater than the preset rate and the proportion of the user responsibility of the historical user in the business entity is greater than the preset rate may be set according to the second operation risk value corresponding to the historical loan application in which the same combination condition event occurs, for example, if the rate of completing the tax payment of all the historical users is greater than the preset rate and the proportion of the user responsibility of the historical user in the business entity is greater than the preset rate is 0.2, the second operation risk value corresponding to the loan application in which the combination condition event occurs is determined to be 0.2.

It can be seen that, in the embodiment of the present application, for a first condition and a second condition with a certain information relevance or a certain causal relationship, a combined condition event is obtained according to occurrence of both the first condition and the second condition, and/or a combined condition event is obtained according to non-occurrence of the first condition and non-occurrence of the second condition, so that the combined condition event used by the bayesian learning model in the training process has a joint decision function on the second operation risk value, and further, the bayesian learning model trained by the training process provided in the embodiment of the present application can comprehensively and accurately predict the second operation risk value of the personal operation type loan application, thereby improving the accuracy of the financial institution in predicting the loan risk.

It should be noted that, in the above embodiment, the first condition represents that the rate of tax payment completion of the historical user is greater than the preset rate of completion, and the second condition represents that the proportion of user responsibility of the historical user in the business subject is greater than the preset proportion, which is only an example of content of the first condition and the second condition.

Based on this, in one possible example, the user evaluation condition includes a first condition, the first condition indicates that the number of intellectual property rights under the historical user name is greater than a preset number, the business entity evaluation condition includes a second condition, the second condition indicates that the research and development cost proportion of the business entity is greater than a preset proportion, and at least one combined condition event is obtained according to at least one user evaluation condition and at least one business entity evaluation condition, which includes:

Wherein the intellectual property may comprise at least one of: trademark rights, copyright rights, patent rights.

The research and development cost ratio refers to the proportion of research and development cost to sales income, and the higher the research and development cost ratio is, the higher the science and technology content in the product of the business subject is, and the business is a science and technology type enterprise.

In one possible example, the analyzing the business relationship between the business plan information of the target business entity and the historical business condition information of the other business entities to determine the first business risk value includes:

Analyzing the operation range of the target business main body and the operation ranges of other business main bodies, and determining the operation range association relationship between the operation range of the target business main body and the operation ranges of other business main bodies, wherein the operation range association relationship comprises different industries, the same coverage range of the same industry and different coverage ranges of the same industry;

determining a business association index between the business plan information and the historical business condition information according to the business range association relation;

and determining a first operation risk value according to the operation association index, wherein the operation association index and the first operation risk value are in a negative correlation relationship.

In one possible example, the business plan information of the target business entity further includes business place information of the target business entity, and the historical business situation information further includes business place information of other business entities, and the method further includes:

if the correlation relationship of the operation ranges is the same coverage range of the same industry or different coverage ranges of the same industry, analyzing the distance between the operation place information of the target business main body and the operation place information of other business main bodies, and determining the operation place distance between the target business main body and the other business main bodies;

The determining of the business association index between the business plan information and the historical business situation information according to the business scope association relationship includes:

and determining a first operation risk value of the target business subject according to the operation range association relation and the operation place distance, wherein the first operation risk value is in positive correlation with the operation place distance when the operation range association relation is different coverage ranges of the same industry, and the first operation risk value is in negative correlation with the operation place distance when the operation range association relation is the same coverage range of the same industry.

The operation scope refers to the production operation and service project that the business entity can do.

The method comprises the steps of analyzing the operation range of a target business main body and the operation ranges of other business main bodies, determining the operation range incidence relation between the operation range of the target business main body and the operation ranges of the other business main bodies, and in specific implementation, realizing the operation range incidence relation by taking 'national economy industry classification' as a basis.

For example, if the operation range of the target business entity is "retail specialized for food and beverage", and the operation ranges of the other business entities are "retail specialized for household appliances and electronic products", the operation range association relationship between the operation range of the target business entity and the operation ranges of the other business entities is determined to be different industries.

For another example, if the operation ranges of the target business entity and the other business entities are both "retail of beverages and tea" under "retail of foods and beverages, the operation range association relationship between the operation range of the target business entity and the operation ranges of the other business entities is determined to be the same coverage range of the same industry.

For example, if the operation range of the target business entity is "retail of beverage and tea" under "retail of food and beverage speciality", and the operation ranges of the other business entities are "retail of cake and bread" under "retail of food and beverage speciality", the operation range association relationship between the operation range of the target business entity and the operation ranges of the other business entities is determined to be different coverage ranges of the same industry.

The business plan information and the historical business condition information are determined according to the business scope association relation, and in specific implementation, the business association index can be the situation when the business scope association relation is different industries and is smaller than the situations of the other two same industries, so that the first business risk value is larger than the situations of the other two same industries when the business scope association relation is different industries.

In a specific implementation, as can be seen from the aggregate economic effect, when a consumer consumes a certain commodity at a certain place, the consumer often consumes the complement or accessories of the commodity, for example, if the consumer purchases a cake at a cake shop, the consumer also has a high possibility of purchasing a beverage at a nearby beverage shop, so that the first operational risk value and the business place distance have a positive correlation when the business area correlation is different coverage areas of the same industry.

In a specific implementation, since commodities within the same coverage range of the same industry belong to substitutes, most consumers only choose to consume the commodities, that is, the commodities within the same coverage range of the same industry belong to a mutual competition relationship in the same place or nearby places, and therefore, when the correlation relationship of the operation range is the same coverage range of the same industry, the first operated risk value and the operation place distance are in a negative correlation relationship.

It can be seen that, in the embodiment of the present application, the business plan information of the target business entity includes the operation range and the operation place information of the target business entity, the historical operation condition information includes the operation range and the operation place information of other business entities, the operation range association relationship between the operation range of the target business entity and the operation range of other business entities is determined by analyzing the operation range of the target business entity and the operation range of other business entities, the operation association index between the business plan information and the historical operation condition information is determined according to the operation range association relationship, and finally the first operation risk value is determined according to the operation association index. Therefore, when the operation range association relationship is different industries, the first operation risk value is higher, and when the operation range association relationship is the same industry, the first operation risk value is determined according to the further condition of the same-row coverage range and the distance between the operation places, because the operation association index and the first operation risk value are in a negative correlation relationship, specifically, when the operation range association relationship is the same coverage range of the same industry, the closer the operation place distance between the target business main body and other business main bodies, the larger the first operation risk value is, and when the operation range association relationship is different coverage ranges of the same industry, the closer the operation place distance between the target business main body and other business main bodies, the smaller the first operation risk value is. By adopting the method of the embodiment of the application, the financial institution can accurately analyze the business plan information of the target business main body and the historical operating condition information of other business main bodies, thereby accurately performing credit granting evaluation on the individual business loan, further avoiding loan risks and ensuring the sustainable development of loan business.

In accordance with the embodiment shown in fig. 2, please refer to fig. 6, fig. 6 is a schematic structural diagram of a personal operation credit and credit authorization evaluation apparatus based on bayesian learning according to an embodiment of the present application, as shown in fig. 6:

a personal operation credit and credit evaluation device based on Bayesian learning comprises:

201: the receiving unit is used for receiving a loan application from a target user, and the loan application is used for requesting a guarantee loan for a target business main body.

202: the acquisition unit is used for acquiring business plan information of the target business main body, credit evaluation information of the target user and historical operation condition information of other business main bodies under the target user name.

203: and the analysis unit is used for analyzing the operation relevance between the business plan information of the target business body and the historical operation condition information of other business bodies to determine a first operation risk value.

204: and the model unit is used for inputting the credit evaluation information of the target user and the business plan information of the target business main body as input items into the Bayesian learning model to obtain a second operation risk value.

205: and the evaluation unit is used for determining the evaluation result of the loan application according to the first operating risk value and the second operating risk value, and the evaluation result of the loan application comprises the loan application passing or not passing.

It can be seen that, in the apparatus provided in the embodiment of the present application, the analysis unit analyzes the business association between the business plan information of the target business entity and the historical business situation information of other business entities, determines the first operation risk value, and the model unit inputs the credit evaluation information of the target user and the business plan information of the target business entity as input items into the bayesian learning model to obtain the second operation risk value, and then the evaluation unit determines the evaluation result of the loan application according to the first operation risk value and the second operation risk value. By adopting the device of the embodiment of the application, when facing various and huge information of users and business bodies, financial institutions can also comprehensively and accurately carry out credit granting evaluation on individual business loans, thereby avoiding loan risks and ensuring sustainable development of loan services.

Specifically, in the embodiment of the present application, the personal operation credit and credit granting evaluation apparatus based on the bayesian learning may be divided into the functional units according to the above method example, for example, each functional unit may be divided according to each function, or two or more functions may be integrated into one processing unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit. It should be noted that the division of the unit in the embodiment of the present application is schematic, and is only a logic function division, and there may be another division manner in actual implementation.

In accordance with the embodiment shown in fig. 2, an electronic device is provided in an embodiment of the present application, please refer to fig. 7, fig. 7 is a schematic diagram illustrating a server structure of a hardware operating environment of an electronic device provided in an embodiment of the present application, and as shown in fig. 7, the electronic device includes a processor, a memory, and computer-executable instructions stored in the memory and operable on the processor, and when the computer-executable instructions are executed, the electronic device executes instructions including any steps of the personal business credit assessment method based on bayesian learning.

Wherein, the processor is a CPU (Central Processing Unit).

The memory may be a high-speed RAM memory, or may be a stable memory, such as a disk memory.

Those skilled in the art will appreciate that the configuration of the server shown in fig. 7 is not intended to be limiting and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components.

As shown in fig. 7, the memory may include an operating system, a network communication module, and computer-executable instructions for a personal business credit assessment method based on bayesian learning. The operating system is used for managing and controlling hardware and software resources of the server and supporting the operation of executing instructions by the computer. The network communication module is used for realizing communication between each component in the memory and communication with other hardware and software in the server, and the communication may use any communication standard or protocol, including but not limited to GSM (Global System of Mobile communication), GPRS (General Packet Radio Service), CDMA2000(Code Division Multiple Access 2000), WCDMA (Wideband Code Division Multiple Access), TD-SCDMA (Time Division-Synchronous Code Division Multiple Access), etc.

In the server shown in fig. 7, the processor is configured to execute computer-executable instructions for personnel management stored in the memory, and to implement the following steps: receiving a loan application from a target user, wherein the loan application is used for requesting a guarantee loan for a target business subject; acquiring business plan information of a target business subject, credit evaluation information of a target user and historical operating condition information of other business subjects under a target user name; analyzing the business association between the business plan information of the target business subject and the historical business condition information of other business subjects to determine a first business risk value; inputting the credit evaluation information of the target user and the business plan information of the target business subject as input items into the Bayesian learning model to obtain a second operation risk value; and determining an evaluation result of the loan application according to the first operating risk value and the second operating risk value, wherein the evaluation result of the loan application comprises the passing loan application or the not passing loan application.

For specific implementation of the server according to the present application, reference may be made to the above embodiments of the personal business credit granting evaluation method based on bayesian learning, which are not described herein again.

An embodiment of the present application provides a computer-readable storage medium, in which computer instructions are stored, and when the computer instructions are executed on a communication apparatus, the communication apparatus is caused to perform the following steps: receiving a loan application from a target user, wherein the loan application is used for requesting a guarantee loan for a target business subject; acquiring business plan information of a target business subject, credit evaluation information of a target user and historical operating condition information of other business subjects under a target user name; analyzing the business association between the business plan information of the target business subject and the historical business condition information of other business subjects to determine a first business risk value; inputting the credit evaluation information of the target user and the business plan information of the target business subject as input items into the Bayesian learning model to obtain a second operation risk value; and determining an evaluation result of the loan application according to the first operating risk value and the second operating risk value, wherein the evaluation result of the loan application comprises the passing loan application or the not passing loan application. The computer includes an electronic device.

The electronic terminal equipment comprises a mobile phone, a tablet computer, a personal digital assistant, wearable equipment and the like.

The computer-readable storage medium may be an internal storage unit of the electronic device according to the above embodiments, for example, a hard disk or a memory of the electronic device. The computer readable storage medium may also be an external storage device of the electronic device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like provided on the electronic device. Further, the computer readable storage medium may also include both an internal storage unit and an external storage device of the electronic device. The computer readable storage medium is used to store computer executable instructions and other computer executable instructions and data which are needed by the electronic device. The computer-readable storage medium may also be used to temporarily store data that has been output or is to be output.

For specific implementation of the computer-readable storage medium according to the present application, reference may be made to the embodiments of the personal business credit assessment method based on bayesian learning, which are not described herein again.

Embodiments of the present application provide a computer program product, wherein the computer program product comprises a computer program operable to cause a computer to perform some or all of the steps of any one of the bayesian learning based personal operation credit assessment methods described in the above method embodiments, and the computer program product may be a software installation package.

It should be noted that any of the foregoing embodiments of the personal business credit assessment method based on bayesian learning have been described as a series of action combinations for simplicity of description, but those skilled in the art should understand that the present application is not limited by the described action sequence, as some steps may be performed in other sequences or simultaneously according to the present application. Further, those skilled in the art will appreciate that the embodiments described in the specification are presently preferred and that no particular act is required to implement the invention.

The foregoing embodiments of the present application are introduced in detail, and the specific examples are applied herein to explain the principle and implementation of the personal business loan credit authorization evaluation method based on bayesian learning and related products, and the description of the foregoing embodiments is only used to help understand the method and core ideas of the present application; meanwhile, for those skilled in the art, according to the personal business credit assessment method based on bayesian learning and the thought of the related products, the specific implementation and the application scope may be changed, and in summary, the content of the present specification should not be construed as a limitation to the present application.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, hardware products and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

While the present application has been described in connection with various embodiments, other variations to the disclosed embodiments can be understood and effected by those skilled in the art in practicing the claimed application, from a review of the drawings, the disclosure, and the appended claims. In the claims, the word "comprising" does not exclude other elements or steps, and the word "a" or "an" does not exclude a plurality. The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage.

It is apparent that those skilled in the art can make various changes and modifications to the personal business credit assessment method based on bayesian learning and related products provided by the present application without departing from the spirit and scope of the present application. Thus, if such modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include such modifications and variations as well.

Claims

1. A personal operation credit granting evaluation method based on Bayesian learning is characterized by comprising the following steps:

obtaining business plan information of the target business subject, credit evaluation information of the target user and historical operation condition information of other business subjects under the target user name;

analyzing the business plan information of the target business subject and the historical business condition information of other business subjects to determine a first business risk value;

inputting the credit evaluation information of the target user and the business plan information of the target business subject as input items into a Bayesian learning model to obtain a second business risk value;

And determining an evaluation result of the loan application according to the first operation risk value and the second operation risk value, wherein the evaluation result of the loan application comprises the loan application or the loan application without the loan application.

2. The method of claim 1, further comprising:

and if the first operation risk value and the second operation risk value are both lower than a preset operation risk value, determining that the evaluation result of the loan application is the passing loan application.

3. The method according to claim 1 or 2, wherein the Bayesian learning model is trained as follows:

comparing the predicted operation risk values of the plurality of historical loan applications with the historical operation risk values corresponding to the plurality of historical loan applications, and if the error between the predicted operation risk values and the historical operation risk values is within a preset error range, determining that the prediction of the initial learning model is accurate;

Determining a prediction accuracy of the initial learning model, the prediction accuracy representing a proportion of the historical loan applications in the training data set that are predicted to be accurate;

and under the condition that the prediction accuracy is smaller than the preset accuracy, performing iterative training on the initial learning model, and if the prediction accuracy of the initial learning model is higher than or equal to the preset accuracy, determining that the training of the initial learning model is finished to obtain the Bayesian learning model.

4. The method of claim 3, further comprising:

obtaining at least one user evaluation condition and at least one business subject evaluation condition according to the credit evaluation information of the historical user and the business plan information of the historical business subject;

obtaining at least one combined condition event according to the at least one user evaluation condition and the at least one business subject evaluation condition;

generating a conditional probability factor according to the at least one combined conditional event, wherein the occurred conditional event in the conditional probability factor corresponds to an expected second risk value and/or an unexpected second risk value, the expected second risk value is the second risk value when the evaluation result of the historical loan application is applied for passing the loan, the unexpected second risk value is the second risk value when the evaluation result of the historical loan application is not applied for passing the loan, and the event to be occurred in the conditional probability factor corresponds to the at least one combined conditional event;

And logically combining the at least one conditional probability factor to generate the initial learning model.

5. The method according to claim 4, wherein the user evaluation condition includes a first condition indicating that the rate of tax payment completion of the historical user is greater than a preset rate, the business entity evaluation condition includes a second condition indicating that the user responsibility ratio of the historical user in the business entity is greater than a preset ratio, and the deriving at least one combined condition event according to the at least one user evaluation condition and the at least one business entity evaluation condition includes:

obtaining the combined condition event according to the first condition occurrence and the second condition occurrence; and/or deriving the combined conditional event based on the absence of the first condition and the absence of the second condition.

6. The method of claim 1, wherein the business plan information of the target business entity includes a business scope of the target business entity, the historical business situation information includes a business scope of the other business entity, and analyzing the business association between the business plan information of the target business entity and the historical business situation information of the other business entity to determine a first business risk value comprises:

Analyzing the operation range of the target business main body and the operation ranges of the other business main bodies, and determining the operation range association relationship between the operation range of the target business main body and the operation ranges of the other business main bodies, wherein the operation range association relationship comprises different industries, the same coverage range of the same industry and the different coverage ranges of the same industry;

determining a business association index between the business plan information and the historical business condition information according to the business scope association relation;

and determining the first operational risk value according to the business association index, wherein the business association index and the first operational risk value are in a negative correlation relationship.

7. The method of claim 6, wherein the business plan information of the target business entity further includes business place information of the target business entity, the historical business condition information further includes business place information of the other business entities, the method further comprising:

if the operation range association relationship is the same coverage range of the same industry or different coverage ranges of the same industry, analyzing the distance between the operation place information of the target business main body and the operation place information of the other business main bodies, and determining the operation place distance between the target business main body and the other business main bodies;

The determining the business association index between the business plan information and the historical business situation information according to the business scope association relationship comprises the following steps:

and determining the first operation risk value of the target business subject according to the operation range association relationship and the operation place distance, wherein the first operation risk value is in positive correlation with the operation place distance when the operation range association relationship is different coverage ranges of the same industry, and the first operation risk value is in negative correlation with the operation place distance when the operation range association relationship is the same coverage range of the same industry.

8. A personal operation credit and credit evaluation device based on Bayesian learning is characterized in that the device comprises:

a receiving unit, configured to receive a loan application from a target user, where the loan application is used to request a secured loan for a target business entity;

the acquisition unit is used for acquiring business plan information of the target business main body, credit evaluation information of the target user and historical operation condition information of other business main bodies under the target user name;

The analysis unit is used for analyzing the operation relevance between the business plan information of the target business body and the historical operation condition information of the other business bodies to determine a first operation risk value;

the model unit is used for inputting the credit evaluation information of the target user and the business plan information of the target business main body as input items into the Bayesian learning model to obtain a second operation risk value;

and the evaluation unit is used for determining the evaluation result of the loan application according to the first operation risk value and the second operation risk value, and the evaluation result of the loan application comprises the loan application or the loan application without the loan application.

9. An electronic device comprising a processor, a memory, and computer-executable instructions stored on the memory and executable on the processor, which when executed cause the electronic device to perform the method of any of claims 1-7.

10. A computer readable storage medium having stored thereon computer instructions which, when run on a communication device, cause the communication device to perform the method of any one of claims 1-7.