CN111210332A - Method and device for generating post-loan management strategy and electronic equipment - Google Patents
Method and device for generating post-loan management strategy and electronic equipment Download PDFInfo
- Publication number
- CN111210332A CN111210332A CN201911271320.XA CN201911271320A CN111210332A CN 111210332 A CN111210332 A CN 111210332A CN 201911271320 A CN201911271320 A CN 201911271320A CN 111210332 A CN111210332 A CN 111210332A
- Authority
- CN
- China
- Prior art keywords
- user
- repayment
- users
- data
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 57
- 238000012216 screening Methods 0.000 claims abstract description 12
- 238000012549 training Methods 0.000 claims description 62
- 238000012795 verification Methods 0.000 claims description 42
- 238000012360 testing method Methods 0.000 claims description 22
- 238000002790 cross-validation Methods 0.000 claims description 17
- 238000010200 validation analysis Methods 0.000 claims description 17
- 238000003860 storage Methods 0.000 claims description 16
- 238000010801 machine learning Methods 0.000 claims description 14
- 238000004422 calculation algorithm Methods 0.000 claims description 11
- 238000012163 sequencing technique Methods 0.000 claims description 8
- 238000012821 model calculation Methods 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 230000006399 behavior Effects 0.000 abstract description 5
- 239000002699 waste material Substances 0.000 abstract description 5
- 238000012545 processing Methods 0.000 description 19
- 238000010586 diagram Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 8
- 238000004891 communication Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 5
- 230000003287 optical effect Effects 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000012946 outsourcing Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 239000013307 optical fiber Substances 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 238000011084 recovery Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000005111 flow chemistry technique Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000010238 partial least squares regression Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000000638 stimulation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The disclosure relates to a method and a device for generating a post-loan management policy, electronic equipment and a computer readable medium. The method comprises the following steps: obtaining financial data for a plurality of users, the financial data comprising: the system comprises user borrowing data, user characteristic data and user basic data; screening a plurality of users based on the user loan number to extract at least one target user; inputting the financial data of the at least one target user into a user repayment model to generate at least one user repayment probability, wherein the user repayment probability is used for representing the probability of repayment of the user at a specific time; and determining a post-credit management strategy corresponding to the at least one target user based on the at least one user repayment probability. The method, the device, the electronic equipment and the computer readable medium for generating the post-loan management strategy can evaluate repayment behaviors of the user based on the current financial data of the user, further determine the optimal post-loan management strategy and reduce the waste of human resources of financial service enterprises.
Description
Technical Field
The present disclosure relates to the field of computer information processing, and in particular, to a method and an apparatus for generating a post-loan management policy, an electronic device, and a computer-readable medium.
Background
For companies offering financial services, the greatest risk it faces is that users will default for failing to pay for debts or bank loans in time, due to various reasons. In the prior art, after a user borrows money by a financial service company, a financial company tracks the repayment condition of the user, and within a first time threshold value of overdue repayment of the user (the user is in an M2 stage), various strategies are started by evaluating the repayment condition of the user, so that the user is urged to repay money.
Currently, owing users have a repayment rate of about 12% -14% during M2, and most users will overdue the owing to a higher credit. Currently, the user at time M2 will be subjected to manual post-loan management, such as collection of arrears by means of a manual telephone, the post-loan management will continue until the user's debt time reaches the second time threshold (the user is at stage M3), and if the user still does not pay, the user will be subjected to outsourcing processing, and the post-loan management for payment is performed by a third-party company.
Because the user arrears mainly need to carry out post-loan management through manual work, for managers, a large amount of time is spent for communication coordination work, the recovery of the arrears is influenced once the communication coordination is reduced, and the current post-loan management mode of the user arrears needs to occupy a large amount of human resources for processing if a large amount of communication coordination work is carried out, so that a large amount of operation cost is increased for financial service companies. How to save manpower and other resource cost as much as possible on the premise of not influencing the recovery of the debt is a problem to be solved urgently at present.
The above information disclosed in this background section is only for enhancement of understanding of the background of the disclosure and therefore it may contain information that does not constitute prior art that is already known to a person of ordinary skill in the art.
Disclosure of Invention
In view of this, the present disclosure provides a method, an apparatus, an electronic device, and a computer readable medium for generating a post-loan management policy of a user, which can evaluate a repayment behavior of the user based on current financial data of the user, so as to determine an optimal post-loan management policy, and reduce waste of human resources of a financial service enterprise.
Additional features and advantages of the disclosure will be set forth in the detailed description which follows, or in part will be obvious from the description, or may be learned by practice of the disclosure.
According to an aspect of the present disclosure, a method for generating a post-loan management policy is provided, the method including: obtaining financial data for a plurality of users, the financial data comprising: the system comprises user borrowing data, user characteristic data and user basic data; screening a plurality of users based on the user loan number to extract at least one target user; inputting the financial data of the at least one target user into a user repayment model to generate at least one user repayment probability, wherein the user repayment probability is used for representing the probability of repayment of the user at a specific time; and determining a post-credit management strategy corresponding to the at least one target user based on the at least one user repayment probability.
Optionally, the method further comprises: and generating the user repayment model based on the financial data of a plurality of historical users and a machine learning algorithm.
Optionally, generating the user payment model based on financial data of a plurality of historical users and a machine learning algorithm comprises: preprocessing financial data of a plurality of historical users to generate a training data set, a testing data set and a verification data set; training the extreme gradient lifting model through the training data set to generate an initial user repayment model; performing k-fold cross validation on the initial user repayment model through the test data set and the validation data set to generate a validation result; and when the verification result meets a preset strategy, generating the user payment model.
Optionally, screening a plurality of users based on the user loan number to extract at least one target user, including: extracting user arrearage time of the plurality of users; and when the debt time of the user is greater than a time threshold, determining the user as a target user.
Optionally, determining a post-credit management policy corresponding to the at least one target user based on the at least one user repayment probability includes: grouping the users based on user repayment probability; and determining the post-credit management strategy corresponding to the target user based on the grouping result.
Optionally, grouping the users based on the user repayment probability includes: comparing the user repayment probability with a threshold range so as to group the users corresponding to the user repayment probability; or sorting the users according to the repayment probability of the users, and grouping the users based on the sorting.
Optionally, training the extreme gradient lifting model through the training data set to generate an initial user repayment model, including: inputting the training data set into the extreme gradient lifting model to generate initial training parameters; adjusting the parameters of the initial training parameters based on a network search parameter adjusting mode; and generating the training parameters based on the optimal solution for the parameter adjustment.
Optionally, generating the training parameters based on the optimal solution of parameter adjustment comprises: and fitting the extreme gradient lifting model again based on the optimal solution of the parameter adjustment to generate the training parameters.
Optionally, performing k-fold cross validation on the initial user repayment model through the test data set and the validation data set to generate a validation result, including: performing multiple K-fold cross validation on the initial user repayment model through the test data set and the validation data set to generate a receiver operation characteristic curve; and generating the verification result when the parameters of the receiver operating characteristic curve are steady.
Optionally, when the verification result meets a preset policy, generating a user payment model, including: calculating the area of the enclosing city of the receiver operation characteristic curve and the coordinate axis in the verification result; and generating the user payment model when the area meets a threshold value.
According to an aspect of the present disclosure, a post-loan management policy generation apparatus is provided, the apparatus including: a data acquisition module for acquiring financial data of a plurality of users, the financial data comprising: the system comprises user borrowing data, user characteristic data and user basic data; the user screening module is used for screening a plurality of users to extract at least one target user based on the user loan number; the model calculation module is used for inputting the financial data of the at least one target user into a user repayment model and generating at least one user repayment probability, and the user repayment probability is used for representing the probability of repayment of the user at a specific time; and the post-loan management strategy module is used for determining the post-loan management strategy corresponding to the at least one target user based on the at least one user repayment probability.
Optionally, the method further comprises: and the model generation module is used for generating the user repayment model based on the financial data of a plurality of historical users and a machine learning algorithm.
Optionally, the model generation module includes: the data processing unit is used for preprocessing the financial data of a plurality of historical users to generate a training data set, a testing data set and a verification data set; the data training unit is used for training the extreme gradient lifting model through the training data set to generate an initial user repayment model; the model verification unit is used for performing k-fold cross verification on the initial user repayment model through the test data set and the verification data set to generate a verification result; and the model establishing unit is used for generating the user payment model when the verification result meets a preset strategy.
Optionally, the user filtering module includes: the extraction unit is used for extracting the user arrearage time of the plurality of users; and the threshold unit is used for determining the user as a target user when the arrearage time of the user is greater than a time threshold.
Optionally, the post-loan management policy module includes: the grouping unit is used for grouping the users based on the user repayment probability; and the strategy unit is used for determining the post-credit management strategy corresponding to the target user based on the grouping result.
Optionally, the grouping unit includes: the comparing subunit is used for comparing the user repayment probability with a threshold range so as to group the users corresponding to the user repayment probability; or the sequencing subunit is used for sequencing the users according to the repayment probability of the users and grouping the users based on the sequencing.
Optionally, the data training unit includes: an input subunit, configured to input the training data set into the extreme gradient lifting model, so as to generate an initial training parameter; the searching subunit is used for carrying out parameter adjustment on the initial training parameters based on a network searching parameter adjustment mode; and an adjustment subunit for generating the training parameters based on the optimal solution for parameter adjustment.
Optionally, the adjusting subunit is further configured to fit the extreme gradient lifting model again based on the optimal solution of the parameter adjustment, so as to generate the training parameter.
Optionally, the model verification unit includes: the verification subunit is used for performing multiple K-fold cross verification on the initial user repayment model through the test data set and the verification data set to generate a receiver operation characteristic curve; and a steady state subunit configured to generate the verification result when a parameter of the recipient operating characteristic curve is steady state.
Optionally, the model building unit includes: the calculation subunit is used for calculating the area of the enclosing city between the receiver operation characteristic curve and the coordinate axis in the verification result; and the probability subunit is used for generating the user repayment model when the area meets a threshold value.
According to an aspect of the present disclosure, an electronic device is provided, the electronic device including: one or more processors; storage means for storing one or more programs; when executed by one or more processors, cause the one or more processors to implement a method as above.
According to an aspect of the disclosure, a computer-readable medium is proposed, on which a computer program is stored, which program, when being executed by a processor, carries out the method as above.
According to the method, the device, the electronic equipment and the computer readable medium for generating the post-loan management strategy, the plurality of users are screened and at least one target user is extracted based on the user loan number; inputting the financial data of the at least one target user into a user repayment model to generate at least one user repayment probability; and determining a mode of the post-loan management strategy corresponding to the at least one target user based on the repayment probability of the at least one user, and evaluating the repayment behavior of the user based on the current financial data of the user, so as to determine the optimal post-loan management strategy and reduce the waste of human resources of financial service enterprises.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
The above and other objects, features and advantages of the present disclosure will become more apparent by describing in detail exemplary embodiments thereof with reference to the attached drawings. The drawings described below are merely some embodiments of the present disclosure, and other drawings may be derived from those drawings by those of ordinary skill in the art without inventive effort.
Fig. 1 is a system block diagram illustrating a method and apparatus for generating a post-loan management policy according to an exemplary embodiment.
FIG. 2 is a flow chart illustrating a method for post-loan management policy generation in accordance with an exemplary embodiment.
Fig. 3 is a flow chart illustrating a method of post-loan management policy generation according to another exemplary embodiment.
Fig. 4 is a flow chart illustrating a method of post-loan management policy generation according to another exemplary embodiment.
Fig. 5 is a block diagram illustrating a post-loan management policy generation apparatus according to an example embodiment.
Fig. 6 is a block diagram illustrating a post-loan management policy generation apparatus according to another exemplary embodiment.
FIG. 7 is a block diagram illustrating an electronic device in accordance with an example embodiment.
FIG. 8 is a block diagram illustrating a computer-readable medium in accordance with an example embodiment.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art. The same reference numerals denote the same or similar parts in the drawings, and thus, a repetitive description thereof will be omitted.
Furthermore, the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the disclosure. One skilled in the relevant art will recognize, however, that the subject matter of the present disclosure can be practiced without one or more of the specific details, or with other methods, components, devices, steps, and so forth. In other instances, well-known methods, devices, implementations, or operations have not been shown or described in detail to avoid obscuring aspects of the disclosure.
The block diagrams shown in the figures are functional entities only and do not necessarily correspond to physically separate entities. I.e. these functional entities may be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor means and/or microcontroller means.
The flow charts shown in the drawings are merely illustrative and do not necessarily include all of the contents and operations/steps, nor do they necessarily have to be performed in the order described. For example, some operations/steps may be decomposed, and some operations/steps may be combined or partially combined, so that the actual execution sequence may be changed according to the actual situation.
It will be understood that, although the terms first, second, third, etc. may be used herein to describe various components, these components should not be limited by these terms. These terms are used to distinguish one element from another. Thus, a first component discussed below may be termed a second component without departing from the teachings of the disclosed concept. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
It is to be understood by those skilled in the art that the drawings are merely schematic representations of exemplary embodiments, and that the blocks or processes shown in the drawings are not necessarily required to practice the present disclosure and are, therefore, not intended to limit the scope of the present disclosure.
Fig. 1 is a system block diagram illustrating a method and apparatus for generating a post-loan management policy according to an exemplary embodiment.
As shown in fig. 1, the system architecture 10 may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 serves as a medium for providing communication links between the terminal devices 101, 102, 103 and the server 105. Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.
The user may use the terminal devices 101, 102, 103 to interact with the server 105 via the network 104 to receive or send messages or the like. The terminal devices 101, 102, 103 may have various communication client applications installed thereon, such as a financial services application, a shopping application, a web browser application, an instant messaging tool, a mailbox client, social platform software, and the like.
The terminal devices 101, 102, 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like.
The server 105 may be a server that provides various services, such as a background management server that supports financial services websites browsed by the user using the terminal apparatuses 101, 102, and 103. The background management server can analyze and process the received user data, and feed back the processing result (such as the user repayment probability) to the administrator of the financial service website.
The server 105 may, for example, obtain financial data for a plurality of users, including: the system comprises user borrowing data, user characteristic data and user basic data; the server 105 may filter a plurality of users to extract at least one target user, for example, based on the user loan number; server 105 may, for example, input financial data of the at least one target user into a user payment model, generate at least one user payment probability, the user payment probability being used to characterize a probability that the user will pay at a particular time; server 105 may determine a post-credit management policy corresponding to the at least one target user, e.g., based on the at least one user repayment probability.
The server 105 may also generate the user payment model based on financial data and machine learning algorithms of a plurality of historical users.
The server 105 may be a single entity server, or may be composed of a plurality of servers, for example, it should be noted that the method for generating a post-loan management policy provided by the embodiment of the present disclosure may be executed by the server 105, and accordingly, the post-loan management policy generating apparatus may be disposed in the server 105. And the web page end provided for the user to browse the financial service platform is generally positioned in the terminal equipment 101, 102 and 103.
FIG. 2 is a flow chart illustrating a method for post-loan management policy generation in accordance with an exemplary embodiment. The post-loan management policy generation method 20 includes at least steps S202 to S208.
As shown in fig. 2, in S202, financial data of a plurality of users is acquired, the financial data including: the system comprises user borrowing data, user characteristic data and user basic data. . The user financial data may include, for example, basic information of the user, professional information, age, and work status of the user, and may also include common contact information of the user, and the like.
In one embodiment, the user data may be filtered through keywords, and more specifically, data related to arrears of the user may be used as the keywords, and features related to arrears are extracted from the user data based on the keywords.
In one embodiment, the user characteristics may also be characterized to generate user financial data. The feature processing may include, for example, normalizing the user's features, which is a dimensionless processing means for making the absolute value of the physical system value into a relative value relationship. The calculation is simplified, the effective method of the magnitude is reduced, and the financial data calculation of the user can be more efficient through normalization processing.
In S204, a plurality of users are screened based on the user loan number to extract at least one target user. Can include the following steps: extracting user arrearage time of the plurality of users; and when the debt time of the user is greater than a time threshold, determining the user as a target user.
The state of the user can be determined according to the borrowing time of the user, and the financial data of the user in the M2 state can be used as the target user, wherein the arrearage time corresponding to the M2 state can be set by an administrator. More specifically, a user of a day with a debt due and an overdue may be defined as an M2 status client.
In S206, inputting the financial data of the at least one target user into a user payment model, and generating at least one user payment probability, where the user payment probability is used to represent the probability that the user pays at a specific time.
The user financial data of the M2 state is calculated through a user repayment model, and a user repayment probability is generated, wherein the user repayment probability can be a probability representing the repayment of the user before the M3 state. More specifically, a user with a debt of more than one month may be defined as an M3 status user. The user payment probability represents the probability that the user pays within one month of arrears.
In S208, a post-credit management policy corresponding to the at least one target user is determined based on the at least one user repayment probability. The method comprises the following steps: grouping the users based on user repayment probability; and determining the post-credit management strategy corresponding to the target user based on the grouping result.
In one embodiment, grouping the users based on user repayment probability comprises: comparing the user repayment probability with a threshold range so as to group the users corresponding to the user repayment probability; or sorting the users according to the repayment probability of the users, and grouping the users based on the sorting.
In one embodiment, comparing the user repayment probability to a threshold range, users below the threshold may be screened out to generate a group of commissioned users. In one embodiment, the users are sorted according to the user repayment probability, and users with a preset proportion after sorting are screened out to generate an outsourcing user group.
More specifically, the users in the group of the clients can be subjected to the outsourcing process, and the third-party company can manage the debt and credit of the users.
According to the method for generating the post-loan management strategy, the problem of optimization of the M2 strategy can be solved, customers with low repayment probability are commissioned, and then part of manpower problems are solved, and manpower resources are released; the administrator can also select a priority case for processing based on the repayment probability of the user.
It should be clearly understood that this disclosure describes how to make and use particular examples, but the principles of this disclosure are not limited to any details of these examples. Rather, these principles can be applied to many other embodiments based on the teachings of the present disclosure.
Fig. 3 is a flow chart illustrating a method of post-loan management policy generation according to another exemplary embodiment. The flow shown in figure 3 is a detailed description of "generating the user payment model based on financial data of a plurality of historical users and a machine learning algorithm",
as shown in FIG. 3, in S302, financial data of a plurality of historical users is preprocessed to generate a training data set, a testing data set, and a validation data set.
In one embodiment, pre-processing the plurality of user financial data comprises: acquiring user data of a plurality of users; and performing screening processing and characteristic processing on the user data to generate the user financial data. The user data may include, for example, basic information of the user, professional information, age, work status of the user, and may also include common contact information of the user, and the like.
In one embodiment, the user data may be filtered through keywords, and more specifically, data related to arrears of the user may be used as the keywords, and features related to arrears are extracted from the user data based on the keywords.
In S304, the extreme gradient lifting model is trained through the training data set, and an initial user repayment model is generated.
In one embodiment, training a machine learning model through the training data set to generate an initial user payment model comprises: training an extreme gradient boost (XGboost) model through the training data set to generate training parameters; and generating an initial user repayment model when the training parameters meet preset conditions.
The XGboost is an optimized distributed gradient enhancement library and aims to achieve high efficiency, flexibility and portability. The method can realize a machine learning algorithm under a Gradient Boosting framework. The idea of Boosting is to integrate many weak classifiers together to form one strong classifier. And XGboost is a lifting tree model, so that the XGboost can integrate a plurality of tree models together to form a more strengthened classifier.
The idea of the XGboost algorithm is to continuously add trees, continuously perform feature splitting to grow a tree, and each time a tree is added, actually learn a new function to fit the residual error predicted last time. When the training is completed to obtain k trees, the score of a sample is to be predicted, namely, according to the characteristics of the sample, a corresponding leaf node is fallen in each tree, each leaf node corresponds to a score, and finally, the predicted value of the sample is obtained by only adding the scores corresponding to each tree.
The details of "training the machine learning model through the training data set to generate the initial user payment model" will be described in the embodiment corresponding to fig. 4.
In S306, k-fold cross-validation is performed on the initial user repayment model through the test data set and the validation data set, so as to generate a validation result.
The verification result may be generated, for example, by performing K-fold cross-validation on the initial user repayment model through the test data set and the verification data set.
Cross Validation (Cross Validation), sometimes referred to as cycle estimation (rota estimation), is a practical method to statistically cut data samples into smaller subsets. Cross-validation is mainly used in modeling applications, such as PCR, PLS regression modeling. In a given modeling sample, most samples are taken out to build a model, a small part of samples are reserved to be forecasted by the just built model, forecasting errors of the small part of samples are solved, and the sum of squares of the forecasting errors is recorded.
In one embodiment, performing K-fold cross validation on the initial user payment model through the test data set and the validation data set to generate a validation result, includes: performing multiple K-fold cross validation on the initial user repayment model through the test data set and the validation data set to generate a receiver operation characteristic curve; and generating the verification result when the parameters of the receiver operating characteristic curve are steady.
Wherein GridSearchCV is a network search parameter adjusting mode with cross validation.
In S308, when the verification result satisfies a preset policy, the user payment model is generated. The area of the outline of the receiver operation characteristic curve and the coordinate axis in the verification result can be calculated, for example; and generating the user payment model when the area meets a threshold value.
Wherein, receiver operating characteristic curve (ROC): under the specific stimulation condition, the virtual report probability P (y/N) obtained by the tested under different judgment standards is taken as an abscissa, the hit probability P (y/SN) is taken as an ordinate, and the connection line of all points is drawn.
ROC is a tool for measuring the imbalance in classification, and the ROC curve and AUC are often used to evaluate the merits of a binary classifier. The area Under the ROC curve and around the coordinate axis is called AUC (area Under cut), and in one embodiment, the user payment model can be generated when the AUC satisfies a threshold.
According to the method for generating the post-loan management strategy, the financial data of a plurality of users are preprocessed, and a training data set, a test data set and a verification data set are generated; training a machine learning model through the training data set to generate an initial user repayment model; performing cross validation on the initial user repayment model through the test data set and the validation data set to generate a validation result; and when the verification result meets the preset strategy, a user repayment model is generated, so that an accurate and efficient user repayment model can be established, the behavior of the user can be evaluated based on the user repayment model, and the waste of human resources of financial service enterprises is reduced.
Fig. 4 is a flow chart illustrating a method of post-loan management policy generation according to another exemplary embodiment. The flow shown in fig. 4 is a detailed description of the flow shown in fig. 2.
As shown in fig. 4, in S402, the training data set is input into the extreme gradient boost model, and initial training parameters are generated.
In one embodiment, the XGBboost may be regarded as an improved version of the gradient lifting algorithm, the XGBboost defines that the CART regression tree is necessarily used in the machine learning process, and the output of the machine learning is a score rather than a category, which is helpful for the XGBboost to integrate the output results (simple addition) of all the base CART regression trees, and the XGBboost introduces parallelization, so that the speed is faster, and at the same time, the XGBboost also introduces a second-order partial derivative of a loss function, and the calculation effect is generally better. The learning of XGBboost is serial, i.e. when the kth learner is to be learned, the learning target is the residual of the first k-1 learners from the target output.
In one embodiment, the training data set is input into the extreme gradient lifting model, the training data are trained and learned by k learners in sequence, and when target output residuals of the k learners of the extreme gradient lifting model satisfy a function condition, an initial user repayment model is generated through parameters of the current extreme gradient lifting model.
In S404, the initial training parameters are adjusted based on a network search parameter adjusting manner. The grid search parameter adjustment is a means for adjusting parameters by utilizing exhaustive search. In all candidate parameter selections, each possibility is tried through loop traversal, and the best performing parameter is the final result.
More specifically, in the user payment model of the present disclosure, 5 model parameters, parameters a, b, c, d, e, may be included, where parameter a has 3 possibilities, parameter b has 4 possibilities, parameter c has 2 possibilities, parameter d has 3 possibilities, and parameter e has 2 possibilities. The grid searching parameter lists all the possibilities, and can be represented as multidimensional matrix data of 3 × 4 × 2 × 3, wherein each cell is a grid, and the grid searching parameter performs cyclic search in the multidimensional matrix data to calculate the performance of the initial user payment model corresponding to the current parameters.
In S406, the extreme gradient boost model is fit again based on the optimal solution of the parameter adjustment, and the training parameters are generated.
In S408, performing multiple K-fold cross validation on the initial user payment model through the test data set and the validation data set, and generating a receiver operation characteristic curve. The K-fold cross validation mainly comprises the following steps: the initial sample is divided into K sub-samples, one individual sub-sample is retained as data for the verification model, and the other K-1 samples are used for training. Cross validation is repeated K times, each sub-sample is validated once, the K results are averaged or other combinations are used, and a single estimate is obtained. This method has the advantage that training and validation are performed repeatedly using randomly generated subsamples at the same time, with the results validated once each time, with 10-fold cross validation being the most common.
In S410, the verification result is generated when the parameters of the recipient operating characteristic curve are steady-state. And gradually determining the optimal parameters of the main parameters of the model by utilizing GridSearchCV, finally re-fitting the model by utilizing the optimal parameter combination, respectively predicting the test set and the verification set, and comparing the prediction results until the results are relatively stable.
In S412, the area of the recipient operating characteristic curve and the coordinate axis enclosing city in the verification result is calculated.
ROC is a tool for measuring the imbalance in classification, and the ROC curve and AUC are often used to evaluate the quality of a binary classifier. A class imbalance, i.e., many more negative samples than positive samples (or vice versa), often occurs in an actual dataset, and the distribution of positive and negative samples in the test data may also change over time. In this case, the ROC curve can be kept constant.
The area Under the ROC curve and around the coordinate axis is called AUC (area Under cut), and in one embodiment, the user payment model can be generated when the AUC satisfies a threshold. Because the ROC curve is generally located above the line of y-x, the value range is between 0.5 and 1, the AUC is used as an evaluation index because the ROC curve cannot clearly indicate which classifier has a better effect in many cases, and the AUC is used as a numerical value, and the larger the value is, the better the classifier has.
In S414, when the area satisfies a threshold, the user payment model is generated.
Those skilled in the art will appreciate that all or part of the steps implementing the above embodiments are implemented as computer programs executed by a CPU. When executed by the CPU, performs the functions defined by the above-described methods provided by the present disclosure. The program may be stored in a computer readable storage medium, which may be a read-only memory, a magnetic or optical disk, or the like.
Furthermore, it should be noted that the above-mentioned figures are only schematic illustrations of the processes involved in the methods according to exemplary embodiments of the present disclosure, and are not intended to be limiting. It will be readily understood that the processes shown in the above figures are not intended to indicate or limit the chronological order of the processes. In addition, it is also readily understood that these processes may be performed synchronously or asynchronously, e.g., in multiple modules.
The following are embodiments of the disclosed apparatus that may be used to perform embodiments of the disclosed methods. For details not disclosed in the embodiments of the apparatus of the present disclosure, refer to the embodiments of the method of the present disclosure.
Fig. 5 is a block diagram illustrating a post-loan management policy generation apparatus according to an example embodiment. As shown in fig. 5, the post-loan management policy generation apparatus 50 includes: a data acquisition module 502, a user screening module 504, a model calculation module 506, a post-loan management module 508, and a model generation module 510.
The data acquisition module 502 is configured to acquire financial data of a plurality of users, the financial data including: the system comprises user borrowing data, user characteristic data and user basic data;
the user screening module 504 is configured to screen a plurality of users to extract at least one target user based on the user loan number; the user filtering module 504 includes: the extraction unit is used for extracting the user arrearage time of the plurality of users; and the threshold unit is used for determining the user as a target user when the arrearage time of the user is greater than a time threshold.
The model calculation module 506 is used for inputting the financial data of the at least one target user into a user payment model and generating at least one user payment probability, wherein the user payment probability is used for representing the probability of payment of the user at a specific time; and
the post-loan management module 508 is configured to determine a post-loan management policy corresponding to the at least one target user based on the at least one user repayment probability. The post-loan management module 508 includes: the grouping unit is used for grouping the users based on the user repayment probability; and the strategy unit is used for determining the post-credit management strategy corresponding to the target user based on the grouping result.
Wherein the grouping unit includes: the comparing subunit is used for comparing the user repayment probability with a threshold range so as to group the users corresponding to the user repayment probability; or the sequencing subunit is used for sequencing the users according to the repayment probability of the users and grouping the users based on the sequencing.
The model generation module 510 is configured to generate a payment model for a plurality of historical users based on financial data of the users and a machine learning algorithm.
Fig. 6 is a block diagram illustrating a post-loan management policy generation apparatus according to another exemplary embodiment. As shown in fig. 6, the model generation module 510 further includes: a data processing unit 5102, a data training unit 5104, a model verification unit 5106, and a model establishment unit 5108.
The data processing unit 5102 is configured to preprocess financial data of a plurality of historical users, and generate a training data set, a test data set, and a verification data set;
the data training unit 5104 is configured to train the extreme gradient lifting model through the training data set, and generate an initial user repayment model; the data training unit 5104 includes: an input subunit, configured to input the training data set into the extreme gradient lifting model, so as to generate an initial training parameter; the searching subunit is used for carrying out parameter adjustment on the initial training parameters based on a network searching parameter adjustment mode; and an adjustment subunit for generating the training parameters based on the optimal solution for parameter adjustment. The adjusting subunit is further configured to fit the extreme gradient lifting model again based on the optimal solution for parameter adjustment, and generate the training parameter.
The model verifying unit 5106 is configured to perform k-fold cross verification on the initial user repayment model through the test data set and the verification data set, and generate a verification result; the model verification unit 5106 includes: the verification subunit is used for performing multiple K-fold cross verification on the initial user repayment model through the test data set and the verification data set to generate a receiver operation characteristic curve; and a steady state subunit configured to generate the verification result when a parameter of the recipient operating characteristic curve is steady state.
The model establishing unit 5108 is configured to generate the user payment model when the verification result meets a preset policy. The model establishing unit 5108 includes: the calculation subunit is used for calculating the area of the enclosing city between the receiver operation characteristic curve and the coordinate axis in the verification result; and the probability subunit is used for generating the user repayment model when the area meets a threshold value.
According to the post-loan management strategy generation device, a plurality of users are screened and at least one target user is extracted based on the user loan number; inputting the financial data of the at least one target user into a user repayment model to generate at least one user repayment probability; and determining a mode of the post-loan management strategy corresponding to the at least one target user based on the repayment probability of the at least one user, and evaluating the repayment behavior of the user based on the current financial data of the user, so as to determine the optimal post-loan management strategy and reduce the waste of human resources of financial service enterprises.
FIG. 7 is a block diagram illustrating an electronic device in accordance with an example embodiment.
An electronic device 700 according to this embodiment of the disclosure is described below with reference to fig. 7. The electronic device 700 shown in fig. 7 is only an example and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.
As shown in fig. 7, electronic device 700 is embodied in the form of a general purpose computing device. The components of the electronic device 700 may include, but are not limited to: at least one processing unit 710, at least one memory unit 720, a bus 730 that connects the various system components (including the memory unit 720 and the processing unit 710), a display unit 740, and the like.
Wherein the storage unit stores program codes executable by the processing unit 710 to cause the processing unit 710 to perform the steps according to various exemplary embodiments of the present disclosure described in the above-mentioned electronic prescription flow processing method section of the present specification. For example, the processing unit 710 may perform the steps as shown in fig. 2, 3, 4.
The memory unit 720 may include readable media in the form of volatile memory units, such as a random access memory unit (RAM)7201 and/or a cache memory unit 7202, and may further include a read only memory unit (ROM) 7203.
The memory unit 720 may also include a program/utility 7204 having a set (at least one) of program modules 7205, such program modules 7205 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may comprise an implementation of a network environment.
The electronic device 700 may also communicate with one or more external devices 700' (e.g., keyboard, pointing device, bluetooth device, etc.), with one or more devices that enable a user to interact with the electronic device 700, and/or with any devices (e.g., router, modem, etc.) that enable the electronic device 700 to communicate with one or more other computing devices. Such communication may occur via an input/output (I/O) interface 750. Also, the electronic device 700 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network such as the internet) via the network adapter 760. The network adapter 760 may communicate with other modules of the electronic device 700 via the bus 730. It should be appreciated that although not shown in the figures, other hardware and/or software modules may be used in conjunction with the electronic device 700, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.
Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein may be implemented by software, or by software in combination with necessary hardware. Therefore, as shown in fig. 8, the technical solution according to the embodiment of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (which may be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which may be a personal computer, a server, or a network device, etc.) to execute the above method according to the embodiment of the present disclosure.
The software product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, 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.
The computer readable storage medium may include a propagated data signal with readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A readable storage medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Program code for carrying out operations for the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., through the internet using an internet service provider).
The computer readable medium carries one or more programs which, when executed by a device, cause the computer readable medium to perform the functions of: obtaining financial data for a plurality of users, the financial data comprising: the system comprises user borrowing data, user characteristic data and user basic data; screening a plurality of users based on the user loan number to extract at least one target user; inputting the financial data of the at least one target user into a user repayment model to generate at least one user repayment probability, wherein the user repayment probability is used for representing the probability of repayment of the user at a specific time; and determining a post-credit management strategy corresponding to the at least one target user based on the at least one user repayment probability.
Those skilled in the art will appreciate that the modules described above may be distributed in the apparatus according to the description of the embodiments, or may be modified accordingly in one or more apparatuses unique from the embodiments. The modules of the above embodiments may be combined into one module, or further split into multiple sub-modules.
Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein may be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solution according to the embodiments of the present disclosure may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (which may be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which may be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the embodiments of the present disclosure.
Exemplary embodiments of the present disclosure are specifically illustrated and described above. It is to be understood that the present disclosure is not limited to the precise arrangements, instrumentalities, or instrumentalities described herein; on the contrary, the disclosure is intended to cover various modifications and equivalent arrangements included within the spirit and scope of the appended claims.
Claims (10)
1. A method for generating a post-loan management policy, comprising:
obtaining financial data for a plurality of users, the financial data comprising: the system comprises user borrowing data, user characteristic data and user basic data;
screening a plurality of users based on the user loan number to extract at least one target user;
inputting the financial data of the at least one target user into a user repayment model to generate at least one user repayment probability, wherein the user repayment probability is used for representing the probability of repayment of the user at a specific time; and
and determining a post-credit management strategy corresponding to the at least one target user based on the at least one user repayment probability.
2. The method of claim 1, further comprising:
and generating the user repayment model based on the financial data of a plurality of historical users and a machine learning algorithm.
3. The method of claims 1-2, wherein generating the user payment model based on financial data and a machine learning algorithm for a plurality of historical users comprises:
preprocessing financial data of a plurality of historical users to generate a training data set, a testing data set and a verification data set;
training the extreme gradient lifting model through the training data set to generate an initial user repayment model;
performing k-fold cross validation on the initial user repayment model through the test data set and the validation data set to generate a validation result; and
and when the verification result meets a preset strategy, generating the user payment model.
4. The method of claims 1-3, wherein filtering the plurality of users for at least one target user based on the user debit number comprises:
extracting user arrearage time of the plurality of users; and
and when the debt time of the user is greater than a time threshold value, determining the user as a target user.
5. The method of claims 1-4, wherein determining the post-loan management policy for the at least one target user based on the at least one user repayment probability comprises:
grouping the users based on user repayment probability; and
and determining the post-credit management strategy corresponding to the target user based on the grouping result.
6. The method of claims 1-5, wherein grouping the users based on user repayment probabilities comprises:
comparing the user repayment probability with a threshold range so as to group the users corresponding to the user repayment probability; or
And sequencing the users according to the repayment probability of the users, and grouping the users based on the sequencing.
7. The method of claims 1-6, wherein training an extreme gradient boosting model through the training data set, generating an initial user payment model, comprises:
inputting the training data set into the extreme gradient lifting model to generate initial training parameters;
adjusting the parameters of the initial training parameters based on a network search parameter adjusting mode; and
generating the training parameters based on the optimal solution for the parameter adjustment.
8. A post-loan management policy generation apparatus, comprising:
a data acquisition module for acquiring financial data of a plurality of users, the financial data comprising: the system comprises user borrowing data, user characteristic data and user basic data;
the user screening module is used for screening a plurality of users to extract at least one target user based on the user loan number;
the model calculation module is used for inputting the financial data of the at least one target user into a user repayment model and generating at least one user repayment probability, and the user repayment probability is used for representing the probability of repayment of the user at a specific time; and
and the post-loan management strategy module is used for determining a post-loan management strategy corresponding to the at least one target user based on the at least one user repayment probability.
9. An electronic device, comprising:
one or more processors;
storage means for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-7.
10. A computer-readable medium, on which a computer program is stored, which, when being executed by a processor, carries out the method according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911271320.XA CN111210332A (en) | 2019-12-12 | 2019-12-12 | Method and device for generating post-loan management strategy and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911271320.XA CN111210332A (en) | 2019-12-12 | 2019-12-12 | Method and device for generating post-loan management strategy and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111210332A true CN111210332A (en) | 2020-05-29 |
Family
ID=70789278
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911271320.XA Pending CN111210332A (en) | 2019-12-12 | 2019-12-12 | Method and device for generating post-loan management strategy and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111210332A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111738846A (en) * | 2020-07-27 | 2020-10-02 | 北京淇瑀信息科技有限公司 | Method and device for generating post-loan management strategy and electronic equipment |
| CN112766899A (en) * | 2021-01-14 | 2021-05-07 | 内蒙古蒙商消费金融股份有限公司 | Post-loan management method and device |
| CN113191821A (en) * | 2021-05-20 | 2021-07-30 | 北京大米科技有限公司 | Data processing method and device |
| EP4109377A1 (en) * | 2021-06-23 | 2022-12-28 | Affirm, Inc. | System, method and apparatus for modeling loan transitions |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108416669A (en) * | 2018-03-13 | 2018-08-17 | 腾讯科技（深圳）有限公司 | User behavior data processing method, device, electronic equipment and computer-readable medium |
| CN109034658A (en) * | 2018-08-22 | 2018-12-18 | 重庆邮电大学 | A kind of promise breaking consumer's risk prediction technique based on big data finance |
-
2019
- 2019-12-12 CN CN201911271320.XA patent/CN111210332A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108416669A (en) * | 2018-03-13 | 2018-08-17 | 腾讯科技（深圳）有限公司 | User behavior data processing method, device, electronic equipment and computer-readable medium |
| CN109034658A (en) * | 2018-08-22 | 2018-12-18 | 重庆邮电大学 | A kind of promise breaking consumer's risk prediction technique based on big data finance |
Non-Patent Citations (1)
| Title |
|---|
| 吴锦华等: "特征选择方法在信用评分系统中的应用", 《信息与电脑(理论版)》, no. 8, 25 April 2019 (2019-04-25), pages 119 - 120 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111738846A (en) * | 2020-07-27 | 2020-10-02 | 北京淇瑀信息科技有限公司 | Method and device for generating post-loan management strategy and electronic equipment |
| CN112766899A (en) * | 2021-01-14 | 2021-05-07 | 内蒙古蒙商消费金融股份有限公司 | Post-loan management method and device |
| CN113191821A (en) * | 2021-05-20 | 2021-07-30 | 北京大米科技有限公司 | Data processing method and device |
| EP4109377A1 (en) * | 2021-06-23 | 2022-12-28 | Affirm, Inc. | System, method and apparatus for modeling loan transitions |
| US20220414763A1 (en) * | 2021-06-23 | 2022-12-29 | Affirm, Inc. | System, Method and Apparatus for Modeling Loan Transitions |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112270545A (en) | Financial risk prediction method and device based on migration sample screening and electronic equipment | |
| CN106095942B (en) | Strong variable extracting method and device | |
| CN111210332A (en) | Method and device for generating post-loan management strategy and electronic equipment | |
| CN111145009A (en) | Method and device for evaluating risk after user loan and electronic equipment | |
| CN112270547A (en) | Financial risk assessment method and device based on feature construction and electronic equipment | |
| CN111199469A (en) | User payment model generation method and device and electronic equipment | |
| CN111181757B (en) | Information security risk prediction method and device, computing equipment and storage medium | |
| CN111210335A (en) | User risk identification method and device and electronic equipment | |
| CN111738331A (en) | User classification method and device, computer-readable storage medium and electronic device | |
| CN110490304B (en) | Data processing method and device | |
| US10678821B2 (en) | Evaluating theses using tree structures | |
| CN111192133A (en) | Method and device for generating risk model after user loan and electronic equipment | |
| CN113177700B (en) | Risk assessment method, system, electronic equipment and storage medium | |
| CN111179051A (en) | Financial target customer determination method and device and electronic equipment | |
| CN114219360A (en) | Monitoring safety prediction method and system based on model optimization | |
| CN111598494A (en) | Resource limit adjusting method and device and electronic equipment | |
| CN111191825A (en) | User default prediction method and device and electronic equipment | |
| CN111582645B (en) | APP risk assessment method and device based on factoring machine and electronic equipment | |
| CN116503158A (en) | Enterprise bankruptcy risk early warning method, system and device based on data driving | |
| CN112529477A (en) | Credit evaluation variable screening method, device, computer equipment and storage medium | |
| CN112884569A (en) | Credit assessment model training method, device and equipment | |
| CN115545886A (en) | Overdue risk identification method, overdue risk identification device, overdue risk identification equipment and storage medium | |
| CN114092230A (en) | Data processing method and device, electronic equipment and computer readable medium | |
| CN113610625A (en) | Overdue risk warning method and device and electronic equipment | |
| CN111582649B (en) | Risk assessment method and device based on user APP single-heat coding and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |