CN111383093A - Intelligent overdue bill collection method and system - Google Patents
Intelligent overdue bill collection method and system Download PDFInfo
- Publication number
- CN111383093A CN111383093A CN202010152953.5A CN202010152953A CN111383093A CN 111383093 A CN111383093 A CN 111383093A CN 202010152953 A CN202010152953 A CN 202010152953A CN 111383093 A CN111383093 A CN 111383093A
- Authority
- CN
- China
- Prior art keywords
- data
- collection
- client
- overdue
- collector
- 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 47
- 238000010801 machine learning Methods 0.000 claims abstract description 21
- 230000006399 behavior Effects 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 15
- 230000000694 effects Effects 0.000 claims description 9
- 238000010586 diagram Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 230000008909 emotion recognition Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000011084 recovery Methods 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
- G06Q10/063112—Skill-based matching of a person or a group to a task
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Artificial Intelligence (AREA)
- Marketing (AREA)
- Evolutionary Computation (AREA)
- Operations Research (AREA)
- Technology Law (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Probability & Statistics with Applications (AREA)
- Bioinformatics & Computational Biology (AREA)
- Game Theory and Decision Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Quality & Reliability (AREA)
- Evolutionary Biology (AREA)
- Medical Informatics (AREA)
- Tourism & Hospitality (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention provides a method and a system for intelligently urging overdue bills to be received, wherein the method comprises the following steps: predicting the refund probability of overdue bills clients through machine learning; and matching the returned money collection tasks of different types of customers to corresponding collectors according to the customer figures and collector figures based on big data for the customers with the returned money probability smaller than the preset value. In the invention, the overdue clients of the bill are classified, the user figures with different dimensions are carried out on the clients and the collection urging members, and the collection urging members are matched for the clients with different types for collection urging, so that the rate of the withdrawal of the collection urging cases is improved.
Description
Technical Field
The invention relates to the field of financial credits, in particular to a method and a system for intelligently urging overdue bills to be received.
Background
In the financial credit industry, although the early wind control is the core, the collection of the returned money after the later payment is also a very important link in the industry, so various collection companies are produced by delivery. The existing revenue-urging companies combine the development of the existing big data and artificial intelligence to form a series of high-efficiency intelligent revenue-urging. The intelligent collection can effectively reduce the labor cost and improve the money return rate. An intelligent revenue-hastening company appears abroad, and the domestic banking industry and the P2P enterprises also have the related progress of intelligent revenue-hastening at present.
The existing related technologies mostly adopt robot methods such as intelligent outbound, voice closing and the like aiming at clients. However, the existing robot has good application to specific scenes, but has a diversified scene, and a human-computer interaction process is not ideal when facing various groups of people.
Disclosure of Invention
The embodiment of the invention provides a method and a system for overdue intelligent collection of bills, which are used for at least solving the problem of low collection rate of collection cases due to an unsatisfactory man-machine interaction process in an intelligent robot collection mode in the related technology.
According to an embodiment of the invention, a method for intelligent overdue bill collection is provided, which comprises the following steps: predicting the refund probability of overdue bills clients through machine learning; and matching the returned money collection tasks of different types of customers to corresponding collectors according to the customer figures and collector figures based on big data for the customers with the returned money probability smaller than the preset value.
Optionally, predicting the probability of a refund for a bill overdue client through machine learning may include: acquiring reference data of a client aiming at overdue clients with bills of different account ages, wherein the reference data at least comprises one of the following data: basic data, historical payment overdue data, payment behavior data and payment intention characteristic data during the loan application; predicting a probability of a refund of the customer through the machine learning based on the reference data of the customer.
Optionally, matching the refund collection task of the client to the front of the corresponding collector according to the client and collector figures based on big data, and may further include: establishing a client portrait according to the basic data of the client during the loan application and the historical collection record data; and establishing a drawing of the collector urging person according to the money withdrawing condition of the historical collector urging case of the collector urging person and the character characteristics of the collector urging person.
Optionally, the method may further include: and acquiring the active time period of the user according to the behavior data and the historical repayment data of the client.
Further, matching the refund collection tasks of different types of customers to corresponding collectors according to the customer drawings and the collector drawings can include: and matching the refund collection and collection tasks of different types of clients to corresponding collectors according to the client drawings, the collector drawings and the activity periods of the clients.
Optionally, matching the refund collection prompting task of the different types of customers to the corresponding collectors according to the customer drawings and the collector drawings, and further comprising: and feeding back the returned payment collection status of the customer to the wind control platform before the loan.
Optionally, after predicting the probability of the withdrawal of the overdue bill client through machine learning, the method further includes: and urging the customer with the money return probability larger than the preset value through a short message or an intelligent outbound robot.
According to another embodiment of the invention, a bill overdue intelligent charging system is provided, which comprises: the prediction module predicts the money return probability of the overdue bill client through machine learning; and the matching module is used for matching the refund collection prompting tasks of different types of customers to corresponding collectors according to the customer drawings and the collector drawings based on the big data for the customers with the refund probability smaller than the preset value.
Optionally, the prediction module may include: the acquiring unit is used for acquiring reference data of the client aiming at overdue clients with different account ages, wherein the reference data at least comprises one of the following data: basic data, historical payment overdue data, payment behavior data and payment intention characteristic data during the loan application; and the prediction unit is used for predicting the refund probability of the client through the machine learning based on the reference data of the client.
Optionally, the method may further include: the first image module is used for establishing a client image according to basic data and historical collection urging record data of the client during the loan application; and the second image module is used for establishing the image of the acquirer hasten according to the money withdrawing condition of the historical acquirer hasten the collection case and the character characteristics of the acquirer.
Optionally, the method may further include: and the acquisition module is used for acquiring the active time period of the user according to the behavior data and the historical repayment data of the client.
Further, the matching module may include: and the matching unit is used for matching the refund collection tasks of different types of clients to the corresponding collectors according to the client drawings, the collector drawings and the activity periods of the clients.
Optionally, the method may further include: and the feedback module is used for feeding back the returned payment collection state of the client to the wind control platform before the credit.
Optionally, the method may further include: and the collection urging module is used for urging collection of the customers with the money withdrawal probability larger than the preset value through short messages or the intelligent outbound robot.
According to a further embodiment of the present invention, there is also provided a storage medium having a computer program stored therein, wherein the computer program is arranged to perform the steps of any of the above method embodiments when executed.
According to yet another embodiment of the present invention, there is also provided an electronic device, including a memory in which a computer program is stored and a processor configured to execute the computer program to perform the steps in any of the above method embodiments.
Through the embodiment of the invention, the overdue clients are classified, the user figures with different dimensions are performed on the clients and the acquirer urging, and the acquirer is matched to urge to collect different types of clients, so that the rate of refund of the case urging is improved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:
FIG. 1 is a flow diagram of a method of intelligent overdue bill acquirer, according to an embodiment of the present invention;
FIG. 2 is a flow diagram of a method for intelligent overdue invoicing of bills according to an alternative embodiment of the invention;
FIG. 3 is a block diagram of a system for intelligent overdue bill collection according to an embodiment of the present invention;
FIG. 4 is a block diagram of a system for intelligent overdue bill presentment according to an alternative embodiment of the present invention;
FIG. 5 is a flow diagram of a method for intelligent collection based on customer ratings and portraits, according to an embodiment of the present invention;
FIG. 6 is a flow diagram of a method for intelligent collection based on customer ratings and portrayal in accordance with an alternative embodiment of the present invention.
Detailed Description
The invention will be described in detail hereinafter with reference to the accompanying drawings in conjunction with embodiments. It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order.
Example 1
In this embodiment, a method for intelligently urging to collect a bill overdue is provided, and fig. 1 is a flowchart of the method for intelligently urging to collect a bill overdue according to the embodiment of the present invention, as shown in fig. 1, the flowchart includes the following steps:
step S101, predicting the refund probability of overdue bill clients through machine learning;
and step S102, matching the refund collection tasks of different types of customers to corresponding collectors according to the customer portrait and collector portrait based on big data for the customers with the refund probability smaller than the preset value.
After step S101 of this embodiment, the method may further include: and urging the customer with the money return probability larger than the preset value through a short message or an intelligent outbound robot.
Fig. 2 is a flowchart of a method for intelligent overdue bill charging according to an embodiment of the present invention, and as shown in fig. 2, the flowchart includes the following steps:
step S201, aiming at overdue clients with bills of different account ages, obtaining reference data of the clients, wherein the reference data at least comprises one of the following data: basic data, historical payment overdue data, payment behavior data and payment intention characteristic data during the loan application;
step S202, predicting the money return probability of the client through the machine learning based on the reference data of the client;
step S203, establishing a client portrait according to the basic data and the historical collection urging record data of the client during the loan application;
step S204, establishing a drawing of the acquirer hasten according to the money return condition of the historical acquirer hasten case and the character characteristics of the acquirer;
step S205, obtaining the active time period of the user according to the behavior data and the historical repayment data of the client;
step S206, matching the refund collection tasks of different types of clients to corresponding collectors according to the client figures, the collector figures and the activity periods of the clients;
and step S207, feeding back the returned payment collection status of the customer to a pre-loan wind control platform.
Through the steps, the refund collection urging tasks of the clients of different types are matched to the corresponding collectors based on the big data, so that the problem that the repayment probability of the clients whose bills are overdue and urged to be collected in the related technology is low for the clients with low refund probability under the condition of diversified scenes can be solved, and the effect of improving the refund rate of the bills is achieved.
Through the above description of the embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but the former is a better implementation mode in many cases. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.
Example 2
The embodiment also provides an intelligent overdue bill collection system, which is used for implementing the above embodiments and preferred embodiments, and the description of the system is omitted. As used below, the terms "module" and "unit" may implement a combination of software and/or hardware of predetermined functions. While the system described in the embodiments below is preferably implemented in software, implementations in hardware, or a combination of software and hardware are also possible and contemplated.
Fig. 3 is a block diagram of a system for intelligent overdue bill collection according to an embodiment of the present invention, and as shown in fig. 3, the system includes a prediction module 10 and a matching module 20.
And the prediction module 10 predicts the money return probability of the overdue bill client through machine learning.
And the matching module 20 is used for matching the refund collection prompting tasks of different types of customers to corresponding collectors according to the customer portrait and the collector portrait based on the big data for the customers with the refund probability smaller than the preset value.
Fig. 4 is a block diagram of a bill overdue intelligent charging system according to an alternative embodiment of the present invention, and as shown in fig. 4, the system includes a first image module 30, a second image module 40, an obtaining module 50, a feedback module 60, and a charging module 70 in addition to all the modules shown in fig. 3. The prediction module 10 may further include an obtaining unit 11 and a prediction unit 12. The matching module 20 may further comprise a matching unit 21.
The obtaining unit 11 is configured to obtain reference data of a client for overdue clients with different account ages, where the reference data at least includes one of: basic data, historical payment overdue data, payment behavior data and payment intention characteristic data during the loan application.
A prediction unit 12, configured to predict a money return probability of the customer through the machine learning based on the reference data of the customer.
The first image module 30 is used for establishing a client image according to the basic data of the client during the loan application and the historical collection record data.
And the second image module 40 is used for establishing the image of the collector urging person according to the money withdrawing condition of the historical collector urging case of the collector urging person and the character characteristics of the collector urging person.
An obtaining module 50, configured to obtain the activity period of the user according to the behavior data of the client and the historical repayment data.
And the matching unit 21 is used for matching the refund collection tasks of different types of customers to the corresponding collectors according to the customer drawings, the collector drawings and the activity periods of the customers.
And the feedback module 60 is used for feeding back the returned payment collection status of the customer to the pre-loan wind control platform.
And the collection urging module 70 is used for urging collection of the customers with the money withdrawal probability larger than the preset value through short messages or the intelligent outbound robot.
It should be noted that, the above modules may be implemented by software or hardware, and for the latter, the following may be implemented, but not limited to: the modules are all positioned in the same processor; alternatively, the modules are respectively located in different processors in any combination.
Example 3
In order to facilitate understanding of the technical solutions provided by the present invention, the following detailed description will be made with reference to embodiments of specific scenarios.
The embodiment of the patent relates to an intelligent collection system which is designed by applying a recommendation algorithm and combines an intelligent outbound call and an artificial landline telephone aiming at post-loan collection and utilization to grade cases and draw pictures of borrowed customers and draw pictures of collectors.
The embodiment of the patent is characterized in that customers are divided into two groups, one group is easy-to-collect customers, and the other group is difficult-to-collect customers; the user easy to be charged can be charged in an intelligent outbound mode, and a related charging strategy and related dialogues are set in the customer service robot; the method is characterized in that a user difficult to urge carries out user portrait with different dimensions for a borrowed customer, and a collector is also subjected to characteristic depiction of related dimensions.
The embodiment of the patent classifies overdue users and then adopts different collection urging modes. Fig. 5 is a flowchart of a smart collection method based on customer rating and image according to an embodiment of the present invention, as shown in fig. 5, the flowchart includes the following steps:
in step S501, for overdue users with different account ages, the possibility of the user getting back is predicted by using methods of machine learning lightGBM, LSTM and the like.
The data used in the step comprises basic data of the user when applying for the debit, overdue data or not of each term, repayment behavior data (such as one day before each term of a bill), and repayment willingness characteristic data extracted from the urging (such as extremely poor attitude of calling for three times and calling for two times).
Step S502, according to the basic data and the historical collection record data, the emotion recognition and the regularization are used for user portrait of the user.
The data used in this step is the same as described in step S501, except that the depicting angle is different. Here, to portray the user, the portrayal mainly includes static attributes extracted from basic information and dynamic attributes extracted from payment behavior and collection records of several months. The static attributes include: sex, age, school calendar, character, etc. The dynamic attribute is mainly analyzed from two aspects of repayment capacity and repayment willingness, and indexes in the service application comprise: key follow-up, multi-head loan, intentional repayment, economic difficulty, suspicion of money amount, old dependence and other indexes.
Step S503, establishing the self-portrait of the collector according to the collection condition of the historical collection case of the collector and the character characteristics of the collector.
The data used in the step are the money return condition of the class of the case which is urged by the history of the acquirer and the character and character characteristics of the acquirer: in the case classification prompted by the prompter in the same account age, the case classification prompted by the prompter is still analyzed from two aspects of repayment willingness and repayment capacity, and the index is consistent with the dynamic attribute of the client in the step S502. The character characteristics of the collector are mainly from self evaluation of the collector, and the character characteristics are mainly classified into three types: and flat, power, smart.
And step S504, depicting the active time period of the client according to the user behavior data and the payment data.
The data used in the step is data of operators, APP, repayment time and the like to describe the active time period of the user.
And step S505, dividing the user into an easy-to-return client and a difficult-to-return client according to the corresponding account age of the client and the score obtained by the model.
The data used in this step is the conclusion obtained in step S501, where the easy-to-return client includes a client with a high possibility of returning money at a low account age and a client with a high possibility of returning money at a high account age, otherwise, the easy-to-return client is a difficult-to-return client. The customers easy to return money are approximately distributed to 80% of the low account age stage, and the customers easy to return money in each account age are decreased exponentially along with the increase of the account age.
Step S506, aiming at the clients who easily pay back, short messages or intelligent outbound robots are adopted for urging collection, wherein the intelligent outbound robots are stored with question-answering dialogs in specific scenes.
The internal dialect of the intelligent outbound robot is mainly aimed at relevant clients with payment willingness. The relevant dialogs are from the summoned QA of the proctoring staff.
And step S507, aiming at the difficult-to-recover customers, carrying out intelligent case distribution by applying a recommendation algorithm based on the portrait data of the customers and the collectors.
In this step, based on the borrowed customer figure (index vector), the acquirer promotion figure (index vector) and the activity time period of the borrowed customer obtained in the steps S502, S503 and S504, recommendation algorithm is used for recommendation, and different types of acquirers are recommended to different types of customers.
And step S508, feeding back suspected fraud cases in the collection process to the pre-loan wind control to form a closed loop in the whole credit service.
In the step, aiming at clients with loss of connection, half loss of connection, no repayment capacity and no repayment willingness in the post-loan collection process, cases are abstracted into rules or characteristic indexes to be fed back to the pre-loan wind control fraud prevention, so that a closed loop which promotes the pre-loan wind control from pre-loan to post-loan and collection after loan is formed.
The embodiment of the patent classifies overdue users and then adopts different collection urging modes. FIG. 6 is a flow chart of a smart collection method based on customer rating and portrayal according to an alternative embodiment of the present invention, as shown in FIG. 6, the flow chart comprises the following steps:
step S601, aiming at overdue users with different account ages, predicting the money return possibility of the users by using methods of machine learning lightGBM, LSTM and the like;
step S602, according to the basic data and the historical collection record data, user portrayal is conducted on the user through emotion recognition and regularization;
step S603, establishing a self-portrait of the collector according to the money recovery condition of the historical collection case of the collector and the character characteristics of the collector;
step S604, depicting the active time period of the customer according to the user behavior data and the repayment data;
step S605, dividing the user into an easy-to-return client and a difficult-to-return client according to the corresponding account age of the client and the score obtained by the model;
step S606, aiming at the client with the easy reimbursement, a short message or an intelligent outbound robot is adopted for urging receipt, wherein a question-answering operation with a specific scene is stored in the intelligent outbound robot;
step S607, aiming at the difficult-to-withdraw client, carrying out intelligent case distribution by applying a recommendation algorithm based on the client and the image data of the acquirer;
step S608, feeding back the suspected fraud cases in the collection process to the pre-loan wind control to form a closed loop in the whole credit service.
This patent embodiment mainly urges the case to the difficulty, has carried out one set of intelligence and has divided the case, improves and urges the rate of money of retrieving of case. The case rating and the related portrait work of the borrowed user with different account ages are simulated and used, and the subsequent portrait of the receivable person and the recommendation algorithm are implemented successively, so that the scheme is feasible.
Example 4
Embodiments of the present invention also provide a storage medium having a computer program stored therein, wherein the computer program is arranged to perform the steps of any of the above method embodiments when executed.
Alternatively, in the present embodiment, the storage medium may be configured to store a computer program for executing the steps of:
s1, predicting the refund probability of the overdue bill client through machine learning;
and S2, matching the refund collection tasks of different types of customers to corresponding collectors according to the customer portrait and the collector portrait based on big data for the customers with the refund probability smaller than the preset value.
Optionally, in this embodiment, the storage medium may include, but is not limited to: various media capable of storing computer programs, such as a usb disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic disk, or an optical disk.
Example 5
Embodiments of the present invention also provide an electronic device comprising a memory having a computer program stored therein and a processor arranged to run the computer program to perform the steps of any of the above method embodiments.
Optionally, the electronic apparatus may further include a transmission device and an input/output device, wherein the transmission device is connected to the processor, and the input/output device is connected to the processor.
Optionally, in this embodiment, the processor may be configured to execute the following steps by a computer program:
s1, predicting the refund probability of the overdue bill client through machine learning;
and S2, matching the refund collection tasks of different types of customers to corresponding collectors according to the customer portrait and the collector portrait based on big data for the customers with the refund probability smaller than the preset value.
Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments and optional implementation manners, and this embodiment is not described herein again.
It will be apparent to those skilled in the art that the modules or steps of the present invention described above may be implemented by a general purpose computing device, they may be centralized on a single computing device or distributed across a network of multiple computing devices, and alternatively, they may be implemented by program code executable by a computing device, such that they may be stored in a storage device and executed by a computing device, and in some cases, the steps shown or described may be performed in an order different than that described herein, or they may be separately fabricated into individual integrated circuit modules, or multiple ones of them may be fabricated into a single integrated circuit module. Thus, the present invention is not limited to any specific combination of hardware and software.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the principle of the present invention should be included in the protection scope of the present invention.
Claims (16)
1. An intelligent overdue bill collection method is characterized by comprising the following steps:
predicting the refund probability of overdue bills clients through machine learning;
and matching the returned money collection tasks of different types of customers to corresponding collectors according to the customer figures and collector figures based on big data for the customers with the returned money probability smaller than the preset value.
2. The method of claim 1, wherein predicting the probability of a refund for an overdue customer by machine learning comprises:
acquiring reference data of a client aiming at overdue clients with bills of different account ages, wherein the reference data at least comprises one of the following data: basic data, historical payment overdue data, payment behavior data and payment intention characteristic data during the loan application;
predicting a probability of a refund of the customer through the machine learning based on the reference data of the customer.
3. The method of claim 1, wherein matching the customer's refund collection task to the corresponding collector based on the big data-based representation of the customer and the collector, further comprises:
establishing a client portrait according to the basic data of the client during the loan application and the historical collection record data;
and establishing a drawing of the collector urging person according to the money withdrawing condition of the historical collector urging case of the collector urging person and the character characteristics of the collector urging person.
4. The method of claim 1, further comprising:
and acquiring the active time period of the user according to the behavior data and the historical repayment data of the client.
5. The method of claim 4, wherein matching the refund collection tasks of different types of customers to corresponding collectors according to the customer images and the collector images comprises:
and matching the refund collection and collection tasks of different types of clients to corresponding collectors according to the client drawings, the collector drawings and the activity periods of the clients.
6. The method of claim 1, wherein matching the refund collection tasks of different types of customers to the corresponding collectors according to the customer images and the collector images further comprises:
and feeding back the returned payment collection status of the customer to the wind control platform before the loan.
7. The method of claim 1, further comprising, after predicting the probability of a refund for an overdue customer by machine learning:
and urging the customer with the money return probability larger than the preset value through a short message or an intelligent outbound robot.
8. The utility model provides a bill intelligent system of urging receipt overdue which characterized in that includes:
the prediction module predicts the money return probability of the overdue bill client through machine learning;
and the matching module is used for matching the refund collection prompting tasks of different types of customers to corresponding collectors according to the customer drawings and the collector drawings based on the big data for the customers with the refund probability smaller than the preset value.
9. The system of claim 8, wherein the prediction module comprises:
the acquiring unit is used for acquiring reference data of the client aiming at overdue clients with different account ages, wherein the reference data at least comprises one of the following data: basic data, historical payment overdue data, payment behavior data and payment intention characteristic data during the loan application;
and the prediction unit is used for predicting the refund probability of the client through the machine learning based on the reference data of the client.
10. The system of claim 8, further comprising:
the first image module is used for establishing a client image according to basic data and historical collection urging record data of the client during the loan application;
and the second image module is used for establishing the image of the acquirer hasten according to the money withdrawing condition of the historical acquirer hasten the collection case and the character characteristics of the acquirer.
11. The system of claim 8, further comprising:
and the acquisition module is used for acquiring the active time period of the user according to the behavior data and the historical repayment data of the client.
12. The system of claim 11, wherein the matching module comprises:
and the matching unit is used for matching the refund collection tasks of different types of clients to the corresponding collectors according to the client drawings, the collector drawings and the activity periods of the clients.
13. The system of claim 8, further comprising:
and the feedback module is used for feeding back the returned payment collection state of the client to the wind control platform before the credit.
14. The system of claim 8, further comprising:
and the collection urging module is used for urging collection of the customers with the money withdrawal probability larger than the preset value through short messages or the intelligent outbound robot.
15. A computer-readable storage medium, in which a computer program is stored, wherein the computer program is arranged to perform the method of any of claims 1 to 7 when executed.
16. An electronic device comprising a memory and a processor, wherein the memory has stored therein a computer program, and wherein the processor is arranged to execute the computer program to perform the method of any of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010152953.5A CN111383093A (en) | 2020-03-06 | 2020-03-06 | Intelligent overdue bill collection method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010152953.5A CN111383093A (en) | 2020-03-06 | 2020-03-06 | Intelligent overdue bill collection method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111383093A true CN111383093A (en) | 2020-07-07 |
Family
ID=71217183
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010152953.5A Pending CN111383093A (en) | 2020-03-06 | 2020-03-06 | Intelligent overdue bill collection method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111383093A (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111784513A (en) * | 2020-07-27 | 2020-10-16 | 湖南华威金安企业管理有限公司 | Case collection prompting and case dividing method and device and electronic equipment |
CN112700323A (en) * | 2021-01-04 | 2021-04-23 | 深圳市恒鑫科技服务有限公司 | Method and device for expediting payment by credit card |
CN112734210A (en) * | 2020-12-31 | 2021-04-30 | 深圳银雁数据科技有限公司 | Intelligent case division method and system |
CN113554227A (en) * | 2021-07-23 | 2021-10-26 | 中信银行股份有限公司 | Training method of user loss rate prediction model and user loss rate prediction method |
CN114745472A (en) * | 2022-03-29 | 2022-07-12 | 京东科技控股股份有限公司 | Processing method and system for collection-promoting business |
CN115297212A (en) * | 2022-06-25 | 2022-11-04 | 上海浦东发展银行股份有限公司 | Voice robot collection method, system, device and medium based on machine learning |
CN115393077A (en) * | 2022-10-28 | 2022-11-25 | 深圳市人马互动科技有限公司 | Data processing method based on loan transaction man-machine conversation system and related device |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2014052922A (en) * | 2012-09-07 | 2014-03-20 | Hachijuni Bank Ltd | Bank business processing system, method, and program |
WO2018106187A1 (en) * | 2016-12-06 | 2018-06-14 | Vesl Pte. Ltd. | System and method for reducing fraud in trade insurance and financing |
CN109509086A (en) * | 2018-11-28 | 2019-03-22 | 上海点融信息科技有限责任公司 | The method, apparatus and storage medium of processing collection business based on artificial intelligence |
CN110335135A (en) * | 2019-04-23 | 2019-10-15 | 江苏苏宁银行股份有限公司 | A kind of intelligence collection robot and intelligent collection method |
-
2020
- 2020-03-06 CN CN202010152953.5A patent/CN111383093A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2014052922A (en) * | 2012-09-07 | 2014-03-20 | Hachijuni Bank Ltd | Bank business processing system, method, and program |
WO2018106187A1 (en) * | 2016-12-06 | 2018-06-14 | Vesl Pte. Ltd. | System and method for reducing fraud in trade insurance and financing |
CN109509086A (en) * | 2018-11-28 | 2019-03-22 | 上海点融信息科技有限责任公司 | The method, apparatus and storage medium of processing collection business based on artificial intelligence |
CN110335135A (en) * | 2019-04-23 | 2019-10-15 | 江苏苏宁银行股份有限公司 | A kind of intelligence collection robot and intelligent collection method |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111784513A (en) * | 2020-07-27 | 2020-10-16 | 湖南华威金安企业管理有限公司 | Case collection prompting and case dividing method and device and electronic equipment |
CN112734210A (en) * | 2020-12-31 | 2021-04-30 | 深圳银雁数据科技有限公司 | Intelligent case division method and system |
CN112700323A (en) * | 2021-01-04 | 2021-04-23 | 深圳市恒鑫科技服务有限公司 | Method and device for expediting payment by credit card |
CN113554227A (en) * | 2021-07-23 | 2021-10-26 | 中信银行股份有限公司 | Training method of user loss rate prediction model and user loss rate prediction method |
CN114745472A (en) * | 2022-03-29 | 2022-07-12 | 京东科技控股股份有限公司 | Processing method and system for collection-promoting business |
CN115297212A (en) * | 2022-06-25 | 2022-11-04 | 上海浦东发展银行股份有限公司 | Voice robot collection method, system, device and medium based on machine learning |
CN115393077A (en) * | 2022-10-28 | 2022-11-25 | 深圳市人马互动科技有限公司 | Data processing method based on loan transaction man-machine conversation system and related device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111383093A (en) | Intelligent overdue bill collection method and system | |
US10387536B2 (en) | Computerized data-aware agent systems for retrieving data to serve a dialog between human user and computerized system | |
CN110378575B (en) | Overdue event refund collection method and device and computer readable storage medium | |
CN110428240B (en) | Automatic suspicious transaction identification and processing method, terminal and server | |
CN112102067A (en) | Internet financial management method, system, device and medium | |
CN114398512A (en) | Big data-based voice portrait analysis method for communication operator business customer | |
CN101334885A (en) | Account data processing system based on network | |
CN115082203A (en) | Method and device for pushing living scheme, electronic equipment and storage medium | |
CN116645134A (en) | Method, device, equipment and medium for recommending credit card in stages | |
CN117094764A (en) | Bank integral processing method and device | |
CN117036001A (en) | Risk identification processing method, device and equipment for transaction service and storage medium | |
CN111476657A (en) | Information pushing method, device and system | |
CN111369336A (en) | Method for prompting borrowing in bank | |
CN110428278A (en) | Determine the method and device of resource share | |
CN113807618A (en) | Method, device and equipment for hastening receipt of bad assets based on state machine | |
CN114819947A (en) | Method, system, network device and storage medium for selecting combined payment strategy | |
CN114580898A (en) | Efficient collection system and method, electronic device and readable storage medium | |
CN113095722A (en) | ATM (automatic Teller machine) banning determination method and device | |
Saldžiūnas et al. | The challenges of big data analytics in the mobile communications sector | |
CN112418929A (en) | Data sharing method and device | |
CN107295029A (en) | A kind of information processing method and device | |
TWM599434U (en) | Bookkeeping platform | |
CN111429251A (en) | Method and device for processing data under multiple modes | |
CN115577093B (en) | AI analysis method and system for financial information | |
US20230344938A1 (en) | Call subject determination system, call subject determination method, and information storage medium |
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 | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20230308 Address after: 410000 Room 502, 504, Jiayuan Office Building, No. 369, Yuelu Avenue, Xianjiahu Street, Yuelu District, Changsha City, Hunan Province - 913 Applicant after: Hunan Huawei Jin'an Enterprise Management Co.,Ltd. Address before: 100080 370m south of Huandao, Yanfu Road, Yancun Town, Fangshan District, Beijing Applicant before: BEIJING WANGZHONG GONGCHUANG TECHNOLOGY CO.,LTD. |
|
TA01 | Transfer of patent application right | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200707 |