CN111784513A - Case collection prompting and case dividing method and device and electronic equipment - Google Patents
Case collection prompting and case dividing method and device and electronic equipment Download PDFInfo
- Publication number
- CN111784513A CN111784513A CN202010734460.2A CN202010734460A CN111784513A CN 111784513 A CN111784513 A CN 111784513A CN 202010734460 A CN202010734460 A CN 202010734460A CN 111784513 A CN111784513 A CN 111784513A
- Authority
- CN
- China
- Prior art keywords
- collected
- case
- collection
- cases
- 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 65
- 238000011084 recovery Methods 0.000 claims abstract description 12
- 230000000875 corresponding effect Effects 0.000 claims description 15
- 230000008569 process Effects 0.000 claims description 14
- 238000012549 training Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 6
- 230000002596 correlated effect Effects 0.000 claims description 5
- 238000013145 classification model Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 abstract description 5
- 230000003197 catalytic effect Effects 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000001737 promoting effect Effects 0.000 description 2
- 238000000638 solvent extraction Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000000411 inducer Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000006467 substitution reaction 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
- 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
-
- 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
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
Abstract
The invention provides a case collection prompting and case division method, a case collection prompting and case division device and electronic equipment, and relates to the technical field of data processing; determining the rate of money return success of the Cartesian product of a case set to be urged to be collected and an urging collector set based on a binary prediction model; determining the number of cases to be collected of each type which are to be processed by each collector in the collector collection; and determining the collector of each case to be collected based on the rate of success of refund of Cartesian product and the number of cases to be collected of each type which are processed by each collector. The method utilizes a two-classification prediction model to predict the cash recovery success rate of all the cash collection combinations, and distributes the cash collectors for each to-be-collected case by combining the prediction result and the number of each type of to-be-collected case to be processed by each cash collector, thereby ensuring the fairness of case distribution, improving the working enthusiasm of staff and relieving the technical problem of low cash recovery success rate of the cash recovery promotion method in the prior art.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a method and a device for urging collection of cases and case division and electronic equipment.
Background
With the rapid development of economy in recent years, the consumption modes of people are more and more diversified, various modern financial services such as small credit, consumption finance, credit card business and the like are developed vigorously, and the problem that how to develop effective collection urging work on overdue repayment cases is generally concerned by the financial industry is solved. When arrears are charged, cases to be charged are required to be distributed to charging staff for charging, in the prior art, the most common case distribution mode is to evenly distribute the cases to be charged, but the case distribution mode is difficult to ensure fair distribution in the difficulty degree of case charging when the number of cases is large, so that the working enthusiasm of staff is reduced, and the technical problem of low success rate of charging and charging is caused.
Disclosure of Invention
The invention aims to provide a case collection and case division method, a case collection and case division device and electronic equipment, which are used for solving the technical problem that the success rate of collection and payment collection is low in the case collection and case division method in the prior art.
In a first aspect, an embodiment of the present invention provides a catalytic recovery case partitioning method, including: acquiring a case set to be collected and a collector set; determining the cash withdrawal success rate of the Cartesian product of the case set to be urged to; determining the number of cases to be collected of each type which are processed by each collector in the collector collection; and determining the collection urging persons of each case to be urged based on the money return success rate of the Cartesian product and the number of the cases to be urged of each type to be handled by each collection urging person.
In an alternative embodiment, determining the number of each type of case to be collected that each acquirer in the acquirer set should handle includes: acquiring the performance of each receiver hasten in the receiver hasten set; grouping all the receivers based on the performance of each receiver, and obtaining a preset number of receiver groups, wherein the performance difference of the receivers in each receiver group is smaller than a preset threshold value; the number of the cases to be hastened for each type that the hastened receipts person of each group should handle is determined based on the average performance that each hastened receipts person is grouped, wherein the number of the cases to be hastened for each type that the hastened receipts person of each group should handle is positively correlated with the average performance.
In an alternative embodiment, determining the number of each type of case to be collected that each acquirer in the acquirer set should handle includes: acquiring the total number of cases to be hastened for each type in the case set to be hastened; and calculating the total number of the cases to be collected of each type by utilizing an average distribution rule to obtain the number of the cases to be collected of each type to be treated by each collector.
In an optional embodiment, the determining the collector of each case to be collected on the basis of the rate of success of the money return by the cartesian product and the number of the cases to be collected of each type that each collector should process includes: sorting all fund-urging combinations of the target case to be urged to be collected based on the fund withdrawal success rate of the Cartesian product, wherein the target case to be urged to be collected is any case in the case set to be urged to be collected; if the to-be-selected combination is unique, judging whether the distributed total amount of the cases to be collected of the target types of the to-be-selected collectors meets the number of the cases to be collected of the target types to be processed by the to-be-selected collectors, wherein the to-be-selected combination is the money collection combination with the highest money collection success rate in all money collection combinations of the cases to be collected, and the target type is the case type of the case to be collected; and if not, distributing the target to-be-hastened case to the to-be-hastened collector.
In an alternative embodiment, the method further comprises: if so, judging whether the distributed total amount of the target type to-be-collected cases of the alternative collection urging member in the alternative combination meets the number of the target type to-be-collected cases to be processed by the alternative collection urging member, wherein the alternative combination is the money urging combination with the highest money return success rate in all the money urging combinations of the target to-be-collected cases except the combination to be selected; and if not, distributing the target case to be collected to the alternative collector.
In an alternative embodiment, the method further comprises: if the combinations to be selected are not unique, selecting target combinations from the combinations to be selected, wherein the target combinations are any money urging combinations in the combinations to be selected; and if the distributed total amount of the target type to-be-collected cases of the target collector in the target combination does not meet the quantity of the target type to-be-collected cases to be processed by the target collector, distributing the target to-be-collected cases to the target collector.
In an alternative embodiment, the method further comprises: acquiring a plurality of historical fund collection combinations and the collection information of each historical fund collection combination; determining a corresponding refund target value for each historical refund combination based on the refund information and a preset value-taking rule; and training an initial two-classification model according to the collection urging information of the historical money urging combination and the corresponding money return target value to obtain the two-classification prediction model.
In a second aspect, an embodiment of the present invention provides a device for collecting and splitting cases, including: the first acquisition module is used for acquiring a case set to be collected and a collector set; the first determining module is used for determining the rate of money return success of the Cartesian product of the case set to be urged to be; the second determining module is used for determining the number of the cases to be collected of each type to be processed by each collector in the collector collection; and the third determining module is used for determining the collector of each case to be collected based on the money recovery success rate of the Cartesian product and the number of the cases to be collected of each type which are to be treated by each collector.
In a third aspect, an embodiment of the present invention provides an electronic device, including a memory and a processor, where the memory stores a computer program operable on the processor, and the processor executes the computer program to implement the steps of the method in any one of the foregoing embodiments.
In a fourth aspect, an embodiment of the present invention provides a computer-readable medium having non-volatile program code executable by a processor, the program code causing the processor to perform the method of any one of the foregoing embodiments.
The invention provides a case collection and case division method, which comprises the following steps: acquiring a case set to be collected and a collector set; determining the rate of money return success of the Cartesian product of a case set to be urged to be collected and an urging collector set based on a binary prediction model; determining the number of cases to be collected of each type which are to be processed by each collector in the collector collection; and determining the collector of each case to be collected based on the rate of success of refund of Cartesian product and the number of cases to be collected of each type which are processed by each collector.
The mode of equally dividing the case for collection in the prior art is difficult to ensure the fair distribution of the difficulty of case collection, reduces the working enthusiasm of staff and leads to low success rate of collection and withdrawal. Compared with the prior art, the collection-urging case dividing method provided by the invention deeply excavates the potential relation between the collection-urging combination and the collection result of a collection-urging case and a collection-urging person, predicts the collection success rate of all collection-urging combinations by utilizing a two-classification prediction model, allocates the collection-urging persons for each collection-urging case by combining the prediction result and the number of the cases to be treated by each collection-urging person, realizes the optimal collection-urging allocation combination, further ensures the fairness of case allocation, improves the working enthusiasm of employees, and allocates the appropriate cases to the appropriate collection-urging persons, thereby improving the success rate of collection-urging, and effectively relieving the technical problem of low collection success rate of collection-urging cases in the collection-urging case dividing method in the prior art.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flow chart of a case allocation method for catalytic recovery according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating an embodiment of the present invention for determining the number of cases to be collected of each type that each of the plurality of collectors should process;
FIG. 3 is a functional block diagram of a catalytic case partitioning apparatus according to an embodiment of the present invention;
fig. 4 is a schematic diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Some embodiments of the invention are described in detail below with reference to the accompanying drawings. The embodiments described below and the features of the embodiments can be combined with each other without conflict.
The development of various modern financial services is vigorous, how to effectively control the credit risk and the fraud risk of a client is a ubiquitous problem of the financial industry, the improvement of the bad account rate brought by the method is a difficult thing of the industry, and for overdue cases, how to effectively urge to accept the overdue cases is a common concern of the financial industry. When the arrearage is carried out, the cases to be collected need to be distributed to collection personnel for collection, the most common case distribution mode is to evenly distribute the cases to be collected, but the case distribution mode is difficult to ensure the fair distribution of the difficulty degree of case collection when the number of the cases is large, so that the working enthusiasm of staff is reduced, and the technical problem of low success rate of collection and collection is caused. In view of the above, the present invention provides a method for catalyzing case splitting to alleviate the above-mentioned technical problems.
Example one
Fig. 1 is a flowchart of a catalytic case splitting method according to an embodiment of the present invention, and as shown in fig. 1, the method specifically includes the following steps:
and step S12, acquiring a case set to be collected and a collector set.
Before the case division is carried out, a case set to be collected and a collection of collection urging members need to be acquired, wherein the case set to be collected includes all cases to be collected, and the detailed information of each case to be collected is stored in the case set to be collected as a label of the case to be collected, and the detailed information includes: treat that the collection case belongs to online/offline, treat that the account age of collection case urges, if there is historical collection operation urging to the case of treating urging collection, then still should include urging collection information and urge collection follow-up information, urge collection information to include: urging receipt of the number of the receipts, the amount of the receipts, the overdue amount, the remaining amount of the payments, the deducting bank, the average amount of the receipts in March, and the like, wherein the urging receipt follow-up information comprises: the dialing times, the number of dialed numbers, the number of dialing-through times of the user, whether the user is lost or not, and the like of the previous month case.
In the embodiment of the present invention, the collector collection includes all distributable collectors, and the basic information of each collector is also stored as a collector tag in the collector collection, where the basic information includes: the system comprises information of professional experience, information of earning membership cities and regions, money return amount of previous months, number of completed cases, dialing times and other performance information.
And step S14, determining the rate of success of the returned money of the Cartesian product of the case set to be urged and the acquirer urging set based on the two-classification prediction model.
After a case set to be collected and a collection of collection urging members are obtained, calculating Cartesian products of the case set to be collected and the collection urging members, and further obtaining all possible combinations of all cases to be collected and collection urging members, for example, if there are 10 cases to be collected and 5 collection urging members, then after the calculation of the Cartesian products is finished, obtaining 50 total combinations of each case to be collected and 5 collection urging members, and then predicting the money recovery success rate of all the combinations of urging members by using a trained two-classification prediction model.
Step S16, determining the number of cases to be collected, which each collector should process.
When the collection is performed, the reason for influencing the success rate of collection of the collection-urging person is the number of the cases to be collected, which need to be processed, on the one hand, and the types of the cases to be collected, which can reflect the difficulty level of collection urging of the cases to be collected, on the other hand, the cases to be collected, which are large in account age, are more difficult to collect than the cases to be collected, which are small in account age, on the line, and the cases to be collected, which are on the line, are more difficult to collect than the cases to be collected, which are off the line. Therefore, in order to ensure fairness of case allocation as much as possible, the number of cases to be collected for urging of each type to be processed by each urging collector needs to be determined, cases are divided according to the number standard when case allocation is carried out, cases with high urging difficulty are prevented from concentrating on task queues of partial urging collectors, and success rate of urging collection of money is not affected.
And step S18, determining the collector of each case to be collected based on the rate of success of money withdrawal by Cartesian product and the number of cases to be collected of each type which are processed by each collector.
After the recovery success rate of all the collection combinations and the number of the cases to be collected, which are to be processed by each collection urging member, of each type are obtained, the two data are integrated, the corresponding collection urging members are distributed to the cases to be collected, the optimization of collection urging of the recovery money is realized, and the recovery success rate of collection urging of the cases is improved.
The invention provides a case collection and case division method, which comprises the following steps: acquiring a case set to be collected and a collector set; determining the rate of money return success of the Cartesian product of a case set to be urged to be collected and an urging collector set based on a binary prediction model; determining the number of cases to be collected of each type which are to be processed by each collector in the collector collection; and determining the collector of each case to be collected based on the rate of success of refund of Cartesian product and the number of cases to be collected of each type which are processed by each collector.
The mode of equally dividing the case for collection in the prior art is difficult to ensure the fair distribution of the difficulty of case collection, reduces the working enthusiasm of staff and leads to low success rate of collection and withdrawal. Compared with the prior art, the collection-urging case dividing method provided by the invention deeply excavates the potential relation between the collection-urging combination and the collection result of a collection-urging case and a collection-urging person, predicts the collection success rate of all collection-urging combinations by utilizing a two-classification prediction model, allocates the collection-urging persons for each collection-urging case by combining the prediction result and the number of the cases to be treated by each collection-urging person, realizes the optimal collection-urging allocation combination, further ensures the fairness of case allocation, improves the working enthusiasm of employees, and allocates the appropriate cases to the appropriate collection-urging persons, thereby improving the success rate of collection-urging, and effectively relieving the technical problem of low collection success rate of collection-urging cases in the collection-urging case dividing method in the prior art.
The above is a brief description of the case allocation method for hasty receipts provided by the embodiment of the present invention, and the following is a detailed description of how to determine the number of each type of case to be hasty received that each hasty receiver in the hasty receiver set should process.
In an alternative embodiment, as shown in fig. 2, the step S16 of determining the number of cases to be collected of each type that each of the collectors in the collector collection should process includes the following steps:
step S161, obtain the performance of each receiver in the receiver collection.
And step S162, grouping all the collectors based on the performance of each collector to obtain a preset number of collector groups.
Optionally, when a task index is formulated for each acquirer hastening, the hastening capability of the acquirer hastening is used as a reference condition, and the hastening capability of the acquirer hastening is mainly reflected on performance, so that when the number of various cases to be hastened and processed by each acquirer in the acquirer hastening set is determined, the performance of each acquirer is firstly obtained, and then the acquirer is grouped according to the performance to obtain a preset number of acquirer groups. The embodiment of the invention does not specifically limit the grouping number, and the user can set according to the actual requirement, but needs to ensure that the performance difference of the receivers in each receiver group is smaller than the preset threshold value, in other words, the receiver-urging capability of the receivers in each receiver-urging group is basically the same.
In step S163, the number of cases to be managed of each type to be managed by the collector in each group is determined based on the average performance of each collector group.
After the grouping of the receivers is divided, the average performance of each receiver group is calculated firstly, the average receiving capacity of each receiver group can be reflected, and then the quantity of the cases to be received, which are to be processed by each group of the receivers, is determined according to the principle that the stronger the receiving capacity is, the more the receiving index is. That is, the number of cases to be managed of each type that each group of the manager should manage is positively correlated to the average performance.
For ease of understanding, it is assumed, by way of example, that the set of the acquirer is divided into 3 groups in total, the average performance is arranged in descending order A, B, C, in order to ensure that the number of cases to be hastened to be collected is in positive correlation with the average performance, the basic case quantity of each type of cases to be hastened to be collected when the cases to be hastened to be collected are divided into three groups can be calculated firstly, then assigning different performance coefficients to the groups of the receivers with different performances, assuming that the basic case quantity of a certain type of case to be subjected to the collection is X, considering that the group A has the best performance, therefore, the performance coefficient can be set to 1.2, the group B has general performance, the performance coefficient can be set to 1.0, the group C has relatively poor performance, so set up its performance coefficient to 0.8, it is 1.2X to determine the quantity of this kind of case of waiting to urge to receive that every urges the receipts person to handle in A group at last, and the quantity of this kind of case of waiting to urge to receive that every urges the receipts person to handle in B group is X, and the quantity of this kind of case of waiting to urge to receive that every urges the receipts person to handle in C group is 0.8X.
An alternative embodiment for determining the number of cases to be collected, which each promoter should process, is provided above, in this embodiment, the number of cases to be collected, which each promoter should process, is positively correlated to the average performance, that is, all promoters are not the same number of cases to be processed, the better promoter has stronger promoter ability and is capable of undertaking more promotion tasks, and the less promoter has weaker promoter ability, which also appropriately reduces the promotion tasks that they need to undertake, that is, the case quantity is distributed by non-equipartition method.
In another alternative embodiment, the step S16 of determining the number of the cases to be induced for each of the collectors in the collector collection includes the following steps:
step S16a, acquiring the total number of the cases to be hastened for each type in the case set to be hastened.
Step S16b, calculating the total number of cases to be collected by each type according to the average distribution rule, and obtaining the number of cases to be collected by each collector.
The steps S161 to S163 describe a non-average case division manner, and the steps S16a to S16b describe an average case division manner, that is, the cases to be collected can be controlled to receive the same number of cases to be collected by all the collectors without considering the performance of the collectors during case division, and the number of the cases to be collected processed by each collector is ensured to be consistent, so that the case division manner can also avoid the problem of poor working enthusiasm of the staff due to uneven distribution of the difficulty level of the cases.
For example, the collection of cases to be collected contains 100 cases to be collected for Y categories, and the collection of collectors has 20 collectors, and then the total number of cases to be collected for Y categories is calculated according to the principle of average distribution, so that the number of cases to be collected for Y categories to be treated by each collector is 5.
In the above, how to determine the number of each type of case to be hastened to be handled by each hastener in the hastener collection is described in detail, and the process of determining the hastener of each case to be hastened is described in detail below.
In an optional embodiment, in the step S18, the determining the collector of each case to be collected based on the rate of success of the reimbursement by cartesian product and the number of cases to be collected of each type that each collector should process specifically includes the following steps:
and step S181, sorting all the payment urging combinations of the target to-be-urged case based on the money withdrawal success rate of Cartesian product, wherein the target to-be-urged case is any case in the collection of to-be-urged cases.
As can be seen from the above description, the money return success rate of the cartesian product represents the money return success rate of all cases to be collected and all possible money return combinations of the collection staff, so that in case division, for each case to be collected, the money return combination with the high money return success rate is definitely higher than the money return combination with the low money return success rate, so that all the money return combinations of the target cases to be collected need to be sorted according to the money return success rate.
If the combination to be selected is unique, step S182 is executed, and if the combination to be selected is not unique, step S186 is executed.
Step S182, judging whether the distributed total amount of the cases to be collected of the target types of the to-be-collected cases of the to-be-collected persons in the to-be-collected combinations meets the number of the cases to be collected of the target types to be collected which are to be processed by the to-be-collected persons, wherein the to-be-collected combinations are money collection combinations with the highest money collection success rate in all money collection combinations of the cases to be collected, and the target types are case types of the cases to be collected.
If not, executing step S183; if yes, go to step S184.
And step S183, distributing the target case to be collected to the person to be collected.
Specifically, if the combination to be selected is unique in all the fund urging combinations of the target case to be urged to be collected, the target case to be urged to be collected is preferentially allocated to the urging person to be selected, but before division, whether the allocated total amount of the case to be urged to be collected of the target type of the urging person to be selected reaches a pre-specified index or not is judged. For example, the number of cases to be collected of the target type to be processed by the selected collector is predetermined to be 10, and the cases to be collected of the 8 target types have been allocated to the selected collector, obviously, the cases to be collected of the target type can be allocated to the selected collector when the requirements are not met; however, if 10 cases of target type to be collected have been allocated to the candidate, the following step S184 needs to be executed.
Step S184, judging whether the allocated total amount of the target type to-be-collected cases of the alternative collection promoter in the alternative combinations meets the number of the target type to-be-collected cases to be processed by the alternative collection promoter, wherein the alternative combinations are the money collection combinations with the highest money return success rate in all the money collection combinations of the target to-be-collected cases except the combinations to be selected.
If not, step S185 is executed.
And step S185, distributing the target case to be collected to the alternative collector.
Specifically, in order to ensure the success rate of the withdrawal of each case to be collected, when the case to be collected in the collection to be collected (the collection to be collected) with the highest success rate of the withdrawal cannot be accepted because the task amount has reached the limit, the alternative collection with the second success rate of the withdrawal is considered in a delayed manner, and similarly, before the alternative collection is split, whether the total amount of the cases to be collected of the target types of the alternative collection to be collected meets the number of the cases to be collected of the target types to be treated by the alternative collection is also considered, if the total amount of the cases to be collected of the target types of the alternative collection to be collected meets the number of the cases to be collected, the case to be collected of the target collection to be collected can be distributed to the alternative collection, but if the alternative collection to be collected also cannot accept the case to be collected because the task amount requirement is reached, the combination with the highest withdrawal success rate is preferentially searched according to the sorting of the success rates of the withdrawal, and judging the task amount until the most suitable money urging combination is determined for the target case to be urged to be collected.
In the above, when selecting the collection combination for the target collection case, the collection success rate of each collection combination is different, and if there are multiple collection combinations for the target collection case, that is, the collection success rates of the multiple collection combinations are the same, the following step S186 is executed.
And step S186, selecting a target combination from the combinations to be selected, wherein the target combination is any one of the money-drawing combinations to be selected.
In step S187, if the total allocated amount of the cases to be collected of the target type of the target collector in the target combination does not satisfy the number of the cases to be collected of the target type to be collected that the target collector should handle, the cases to be collected of the target are allocated to the target collector.
Specifically, if the success rate of money recovery when the target case to be collected corresponds to a plurality of collectors is the same, considering to avoid unfairness of sequential case division, the target case to be collected is randomly distributed to any collector (target collector) in a plurality of combinations to be selected, and similarly, whether the distributed total amount of the target type case to be collected of the target collector meets the number of the target type case to be collected which the target collector should process needs to be considered, and the target collector is distributed only when the distributed total amount does not meet the number of the target type case to be collected; if the combination is satisfied, other money urging combinations can be selected from the combinations to be selected, if the combinations to be selected cannot be distributed, the alternative combinations are considered, and the like, the above judgment principle is repeated until the optimal money urging combination is determined for the target case to be urged to be received.
The process of how to assign corresponding inducers to the cases to be induced is described in detail above, and the process of how to obtain the binary prediction model is described below.
In an alternative embodiment, the method of the present invention further comprises the steps of:
in step S21, a plurality of historical fund collection combinations and the collection information of each historical fund collection combination are obtained.
When model training is carried out, firstly, a plurality of historical collection combinations and collection information of each historical collection combination are required to be obtained, the historical collection combinations comprise historical collection cases and corresponding collectors, detailed information of each historical collection case is stored in the historical collection combinations as labels of the historical collection cases, and basic information of each collector is stored in the historical collection combinations as labels of the collectors. In an embodiment of the present invention, the collection information of the historical collection combination includes: the collection prompting information comprises collection prompting information (the number of the collection prompting the collection, the amount of the collection, the overdue amount, the remaining amount of the collection, whether the collection is clear, draw out banks, the average amount of the collection in about March and the like) and collection prompting follow-up information (the number of times of dialing the monthly case, the number of numbers dialed, the number of times of dialing through by the user, whether the user is lost or not and the like).
And step S22, determining corresponding refund target values for each historical refund combination based on the refund information and preset value-taking rules.
Further, it is necessary to determine a corresponding reimbursement target value for each historical reimbursement promoting combination according to the collection promoting information and a preset value-taking rule, in an embodiment of the present invention, the preset value-taking rule may be: and counting the situation of the returned money which is hasten in one hasten period of the historical hasten case, if the returned money which is hasten in the current period of the case is larger than a certain hasten amount of the returned money or the returned money is settled after the hasten period is over, determining that the returned money target value of the historical hasten combination is 1, otherwise, determining that the returned money target value is 0. And obtaining a refund target value corresponding to each historical fund-urging combination according to the value-taking rules. The embodiment of the invention does not specifically limit the value rule of the refund target value as long as a clear refund target value (0 or 1) can be obtained.
And step S23, training the initial binary classification model through the collection information of the historical collection combination and the corresponding money return target value to obtain a binary classification prediction model.
And finally, taking the collection urging information of all historical money urging combinations and the corresponding money return target values as training data, training an initial binary model, and finishing the training to obtain a binary prediction model, wherein the initial binary model comprises but is not limited to lightgbm, xgboost, depefm and other models capable of performing binary probability prediction.
The inventor also verifies the performance of the method, divides a model case-dividing test group (the method of the invention) and a random case-dividing comparison group (average case division in the prior art), and performs a 3-month collection fee test under the condition of ensuring that the case type, the case quantity, the collector urging ability and the collector number are basically consistent, wherein the month-average fee collection rate (the collection urging amount/the overdue amount), the model case-dividing test group is more than 15% higher than the random case-dividing comparison group on average, the month-average household fee collection rate (the number of collection cases/the number of overdue cases) is more than 17% higher than the random case-dividing comparison group.
To sum up, the collection urging case division method provided by the embodiment of the invention can deeply dig the potential relation between collection urging combination and collection return result of collection urging case and collector, train the model with collection urging as a target, realize the optimal collection urging combination of collector urging case and case to be collected, and the two-classification prediction model can be updated by training iteration, so that the latest change collection influence factor can be found, and more scientific and fair division can be realized.
Example two
The embodiment of the invention also provides a case collection and case division device, which is mainly used for executing the case collection and case division method provided by the embodiment of the invention, and the case collection and case division device provided by the embodiment of the invention is specifically described below.
Fig. 3 is a functional block diagram of a catalytic case splitting apparatus according to an embodiment of the present invention, as shown in fig. 3, the apparatus mainly includes: the first obtaining module 10, the first determining module 20, the second determining module 30, and the third determining module 40, wherein:
the first acquiring module 10 is configured to acquire a case set to be collected and a collector set.
The first determining module 20 is configured to determine a money return success rate of a cartesian product of the case set to be urged.
The second determining module 30 is configured to determine the number of cases to be collected of each type that each collector in the collector collection should handle.
And the third determining module 40 is used for determining the collector of each case to be collected based on the rate of success of money withdrawal by Cartesian product and the number of the cases to be collected of each type which are processed by each collector.
The invention provides a device for urging collection of cases and dividing cases, which comprises: the first acquisition module 10 is used for acquiring a case set to be collected and a collector set; the first determining module 20 is configured to determine a money return success rate of a cartesian product of a case set to be urged to be received and an urging member set based on a binary prediction model; the second determining module 30 is configured to determine the number of cases to be collected, which are to be processed by each collector in the collector collection; and the third determining module 40 is used for determining the collector of each case to be collected based on the rate of success of money withdrawal by Cartesian product and the number of the cases to be collected of each type which are processed by each collector.
The mode of equally dividing the case for collection in the prior art is difficult to ensure the fair distribution of the difficulty of case collection, reduces the working enthusiasm of staff and leads to low success rate of collection and withdrawal. Compared with the prior art, the collection urging case dividing device provided by the invention deeply excavates the potential relation between the collection urging combination and the collection return result of collection urging cases and collection urging persons, predicts the collection return success rate of all collection urging combinations by utilizing a two-classification prediction model, allocates collection urging persons for each collection urging case by combining the prediction result and the number of various types of cases to be collected which are to be processed by each collection urging person, realizes the optimal collection urging allocation combination, further ensures the fairness of case allocation, improves the working enthusiasm of employees, and allocates appropriate cases to appropriate collection urging persons, thereby improving the success rate of collection urging, and effectively solving the technical problem of low collection urging success rate in the collection urging case dividing method in the prior art.
Optionally, the second determining module 30 includes:
the first acquisition unit is used for acquiring the performance of each acquirer in the acquirer set.
And the grouping unit is used for grouping all the receivers based on the performance of each receiver, so as to obtain a preset number of receiver groups, wherein the performance difference of the receivers in each receiver group is smaller than a preset threshold value.
And the determining unit is used for determining the number of the cases to be managed of each type to be managed, which are processed by the collectors of each group, based on the average performance of each collector group, wherein the number of the cases to be managed of each type, which are processed by the collectors of each group, is positively correlated with the average performance.
Optionally, the second determining module 30 further includes:
and the second acquisition unit is used for acquiring the total number of the cases to be hastened for receiving in each type in the case set to be hastened.
And the calculating unit is used for calculating the total number of the cases to be managed of each type by utilizing the average distribution rule to obtain the number of the cases to be managed of each type to be managed by each manager.
Optionally, the third determining module 40 includes:
and the sorting unit is used for sorting all the payment urging combinations of the target to-be-urged-to-be-urged cases based on the money withdrawal success rate of the Cartesian product, wherein the target to-be-urged-to-be-urged case is.
The first judging unit judges whether the distributed total amount of the target type to-be-collected cases of the to-be-collected persons in the to-be-collected combinations meets the number of the target type to-be-collected cases to be processed by the to-be-collected persons or not if the to-be-collected combinations are unique, wherein the to-be-collected combinations are money collection combinations with the highest money collection success rate in all money collection combinations of the target to-be-collected cases, and the target types are case types of the target to-be-collected cases.
And the first distribution unit is used for distributing the target to-be-managed case to the to-be-managed member if the target to-be-managed case does not meet the requirement.
Optionally, the third determining module 40 further includes:
and the second judgment unit judges whether the distributed total amount of the cases to be collected of the target types of the alternative collectors in the alternative combinations meets the number of the cases to be collected of the target types to be processed by the alternative collectors, if so, wherein the alternative combinations are the money collection combinations with the highest money return success rate in all the money collection combinations of the cases to be collected of the target except the combinations to be collected.
And the second distribution unit distributes the target case to be collected to the alternative collector if the target case to be collected is not met.
Optionally, the third determining module 40 further includes:
and the selecting unit is used for selecting a target combination from the combinations to be selected if the combinations to be selected are not unique, wherein the target combination is any money urging combination in the combinations to be selected.
And the third distribution unit is used for distributing the target case to be hastened to the target acquirer if the distributed total amount of the target case to be hastened of the target type of the target acquirer in the target combination does not meet the quantity of the target case to be hastened of the target type to be processed by the target acquirer.
Optionally, the apparatus further comprises:
and the second acquisition module is used for acquiring a plurality of historical fund collection combinations and the fund collection information of each historical fund collection combination.
And the fourth determining module is used for determining a corresponding reimbursement target value for each historical reimbursement combination based on the collection urging information and the preset value-taking rule.
And the training module is used for training the initial binary classification model through the collection urging information of the historical money urging combination and the corresponding money return target value to obtain a binary classification prediction model.
EXAMPLE III
Referring to fig. 4, an embodiment of the present invention provides an electronic device, including: a processor 60, a memory 61, a bus 62 and a communication interface 63, wherein the processor 60, the communication interface 63 and the memory 61 are connected through the bus 62; the processor 60 is arranged to execute executable modules, such as computer programs, stored in the memory 61.
The memory 61 may include a high-speed Random Access Memory (RAM) and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory. The communication connection between the network element of the system and at least one other network element is realized through at least one communication interface 63 (which may be wired or wireless), and the internet, a wide area network, a local network, a metropolitan area network, and the like can be used.
The bus 62 may be an ISA bus, PCI bus, EISA bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one double-headed arrow is shown in FIG. 4, but that does not indicate only one bus or one type of bus.
The memory 61 is used for storing a program, the processor 60 executes the program after receiving an execution instruction, and the method executed by the apparatus defined by the flow process disclosed in any of the foregoing embodiments of the present invention may be applied to the processor 60, or implemented by the processor 60.
The processor 60 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware or instructions in the form of software in the processor 60. The Processor 60 may be a general-purpose Processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; the device can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA) or other Programmable logic device, a discrete Gate or transistor logic device, or a discrete hardware component. The various methods, steps and logic blocks disclosed in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present invention may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software module may be located in ram, flash memory, rom, prom, or eprom, registers, etc. storage media as is well known in the art. The storage medium is located in a memory 61, and the processor 60 reads the information in the memory 61 and, in combination with its hardware, performs the steps of the above method.
The computer program product for urging collection of cases and case division, the apparatus and the electronic device provided in the embodiments of the present invention includes a computer readable storage medium storing a nonvolatile program code executable by a processor, where instructions included in the program code may be used to execute the method described in the foregoing method embodiments, and specific implementation may refer to the method embodiments, and will not be described herein again.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a non-volatile computer-readable storage medium executable by a processor. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures.
In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings or the orientations or positional relationships that the products of the present invention are conventionally placed in use, and are only used for convenience in describing the present invention and simplifying the description, but do not indicate or imply that the devices or elements referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus, should not be construed as limiting the present invention. Furthermore, the terms "first," "second," "third," and the like are used solely to distinguish one from another and are not to be construed as indicating or implying relative importance.
Furthermore, the terms "horizontal", "vertical", "overhang" and the like do not imply that the components are required to be absolutely horizontal or overhang, but may be slightly inclined. For example, "horizontal" merely means that the direction is more horizontal than "vertical" and does not mean that the structure must be perfectly horizontal, but may be slightly inclined.
In the description of the present invention, it should also be noted that, unless otherwise explicitly specified or limited, the terms "disposed," "mounted," "connected," and "connected" are to be construed broadly and may, for example, be fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. A case collection and case division method is characterized by comprising the following steps:
acquiring a case set to be collected and a collector set;
determining the cash withdrawal success rate of the Cartesian product of the case set to be urged to;
determining the number of cases to be collected of each type which are processed by each collector in the collector collection;
and determining the collection urging persons of each case to be urged based on the money return success rate of the Cartesian product and the number of the cases to be urged of each type to be handled by each collection urging person.
2. The method of claim 1, wherein determining the number of each type of case to be hastened that each of the set of hasteners should handle comprises:
acquiring the performance of each receiver hasten in the receiver hasten set;
grouping all the receivers based on the performance of each receiver, and obtaining a preset number of receiver groups, wherein the performance difference of the receivers in each receiver group is smaller than a preset threshold value;
the number of the cases to be hastened for each type that the hastened receipts person of each group should handle is determined based on the average performance that each hastened receipts person is grouped, wherein the number of the cases to be hastened for each type that the hastened receipts person of each group should handle is positively correlated with the average performance.
3. The method of claim 1, wherein determining the number of each type of case to be hastened that each of the set of hasteners should handle comprises:
acquiring the total number of cases to be hastened for each type in the case set to be hastened;
and calculating the total number of the cases to be collected of each type by utilizing an average distribution rule to obtain the number of the cases to be collected of each type to be treated by each collector.
4. The method as claimed in claim 1, wherein determining the collector of each case to be collected based on the rate of return success of the cartesian product and the number of the types of cases to be collected that each collector should process comprises:
sorting all fund-urging combinations of the target case to be urged to be collected based on the fund withdrawal success rate of the Cartesian product, wherein the target case to be urged to be collected is any case in the case set to be urged to be collected;
if the to-be-selected combination is unique, judging whether the distributed total amount of the cases to be collected of the target types of the to-be-selected collectors meets the number of the cases to be collected of the target types to be processed by the to-be-selected collectors, wherein the to-be-selected combination is the money collection combination with the highest money collection success rate in all money collection combinations of the cases to be collected, and the target type is the case type of the case to be collected;
and if not, distributing the target to-be-hastened case to the to-be-hastened collector.
5. The method of claim 4, further comprising:
if so, judging whether the distributed total amount of the target type to-be-collected cases of the alternative collection urging member in the alternative combination meets the number of the target type to-be-collected cases to be processed by the alternative collection urging member, wherein the alternative combination is the money urging combination with the highest money return success rate in all the money urging combinations of the target to-be-collected cases except the combination to be selected;
and if not, distributing the target case to be collected to the alternative collector.
6. The method of claim 4, further comprising:
if the combinations to be selected are not unique, selecting target combinations from the combinations to be selected, wherein the target combinations are any money urging combinations in the combinations to be selected;
and if the distributed total amount of the target type to-be-collected cases of the target collector in the target combination does not meet the quantity of the target type to-be-collected cases to be processed by the target collector, distributing the target to-be-collected cases to the target collector.
7. The method of claim 1, further comprising:
acquiring a plurality of historical fund collection combinations and the collection information of each historical fund collection combination;
determining a corresponding refund target value for each historical refund combination based on the refund information and a preset value-taking rule;
and training an initial two-classification model according to the collection urging information of the historical money urging combination and the corresponding money return target value to obtain the two-classification prediction model.
8. A device for urging collection of cases and dividing cases is characterized by comprising:
the first acquisition module is used for acquiring a case set to be collected and a collector set;
the first determining module is used for determining the rate of money return success of the Cartesian product of the case set to be urged to be;
the second determining module is used for determining the number of the cases to be collected of each type to be processed by each collector in the collector collection;
and the third determining module is used for determining the collector of each case to be collected based on the money recovery success rate of the Cartesian product and the number of the cases to be collected of each type which are to be treated by each collector.
9. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the method of any of claims 1 to 7 when executing the computer program.
10. A computer-readable medium having non-volatile program code executable by a processor, the program code causing the processor to perform the method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010734460.2A CN111784513A (en) | 2020-07-27 | 2020-07-27 | Case collection prompting and case dividing method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010734460.2A CN111784513A (en) | 2020-07-27 | 2020-07-27 | Case collection prompting and case dividing method and device and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111784513A true CN111784513A (en) | 2020-10-16 |
Family
ID=72765089
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010734460.2A Pending CN111784513A (en) | 2020-07-27 | 2020-07-27 | Case collection prompting and case dividing method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111784513A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112396325A (en) * | 2020-11-19 | 2021-02-23 | 平安普惠企业管理有限公司 | Case processing method, case processing device, case processing medium, and electronic apparatus |
| CN112734243A (en) * | 2021-01-13 | 2021-04-30 | 零犀(北京)科技有限公司 | Method for determining contribution degree of payment case and intelligent terminal |
| CN113240352A (en) * | 2021-07-09 | 2021-08-10 | 建元和光(北京)科技有限公司 | Intelligent case division method based on case prediction value and special person image |
| CN113487239A (en) * | 2021-08-05 | 2021-10-08 | 重庆颂车网络科技有限公司 | Intelligent case division method and system |
| CN113642908A (en) * | 2021-08-20 | 2021-11-12 | 上海通联金融服务有限公司 | Multi-dimensional case allocation method based on credit card post-credit collection service |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109359797A (en) * | 2018-08-21 | 2019-02-19 | 平安科技（深圳）有限公司 | Electronic device, loan collection case division method and storage medium |
| CN109685336A (en) * | 2018-12-10 | 2019-04-26 | 深圳市小牛普惠投资管理有限公司 | Collection task distribution method, device, computer equipment and storage medium |
| CN110807699A (en) * | 2019-10-12 | 2020-02-18 | 上海上湖信息技术有限公司 | Overdue event payment collection method and device and computer readable storage medium |
| CN111062518A (en) * | 2019-11-22 | 2020-04-24 | 成都铂锡金融信息技术有限公司 | Method, device and storage medium for processing hastening service based on artificial intelligence |
| CN111163072A (en) * | 2019-12-24 | 2020-05-15 | 五八有限公司 | Method and device for determining characteristic value in machine learning model and electronic equipment |
| CN111383093A (en) * | 2020-03-06 | 2020-07-07 | 北京网众共创科技有限公司 | Intelligent overdue bill collection method and system |
-
2020
- 2020-07-27 CN CN202010734460.2A patent/CN111784513A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109359797A (en) * | 2018-08-21 | 2019-02-19 | 平安科技（深圳）有限公司 | Electronic device, loan collection case division method and storage medium |
| CN109685336A (en) * | 2018-12-10 | 2019-04-26 | 深圳市小牛普惠投资管理有限公司 | Collection task distribution method, device, computer equipment and storage medium |
| CN110807699A (en) * | 2019-10-12 | 2020-02-18 | 上海上湖信息技术有限公司 | Overdue event payment collection method and device and computer readable storage medium |
| CN111062518A (en) * | 2019-11-22 | 2020-04-24 | 成都铂锡金融信息技术有限公司 | Method, device and storage medium for processing hastening service based on artificial intelligence |
| CN111163072A (en) * | 2019-12-24 | 2020-05-15 | 五八有限公司 | Method and device for determining characteristic value in machine learning model and electronic equipment |
| CN111383093A (en) * | 2020-03-06 | 2020-07-07 | 北京网众共创科技有限公司 | Intelligent overdue bill collection method and system |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112396325A (en) * | 2020-11-19 | 2021-02-23 | 平安普惠企业管理有限公司 | Case processing method, case processing device, case processing medium, and electronic apparatus |
| CN112396325B (en) * | 2020-11-19 | 2022-08-26 | 平安普惠企业管理有限公司 | Case processing method, case processing device, case processing medium, and electronic apparatus |
| CN112734243A (en) * | 2021-01-13 | 2021-04-30 | 零犀(北京)科技有限公司 | Method for determining contribution degree of payment case and intelligent terminal |
| CN113240352A (en) * | 2021-07-09 | 2021-08-10 | 建元和光(北京)科技有限公司 | Intelligent case division method based on case prediction value and special person image |
| CN113487239A (en) * | 2021-08-05 | 2021-10-08 | 重庆颂车网络科技有限公司 | Intelligent case division method and system |
| CN113642908A (en) * | 2021-08-20 | 2021-11-12 | 上海通联金融服务有限公司 | Multi-dimensional case allocation method based on credit card post-credit collection service |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111784513A (en) | Case collection prompting and case dividing method and device and electronic equipment | |
| CN109389431B (en) | Method and device for distributing coupons, electronic equipment and readable storage medium | |
| CN111523748B (en) | Case distribution method, device and system | |
| CN106156092B (en) | Data processing method and device | |
| CN111062518A (en) | Method, device and storage medium for processing hastening service based on artificial intelligence | |
| CN111176840A (en) | Distributed task allocation optimization method and device, storage medium and electronic device | |
| CN113642908A (en) | Multi-dimensional case allocation method based on credit card post-credit collection service | |
| CN101770626A (en) | Method, device and system for identifying agents with card-laundering behavior | |
| CN106657058B (en) | Event resource allocation method and device | |
| CN111105306A (en) | Resource transaction strategy determination method and device and server | |
| CN110991901A (en) | Task allocation method, computer storage medium and electronic device | |
| CN110765110A (en) | Generalization capability processing method, device, equipment and storage medium | |
| CN115239114A (en) | Case distribution method and device, electronic equipment and readable storage medium | |
| CN111651249B (en) | Task allocation method and device, readable storage medium and electronic equipment | |
| CN111815186B (en) | Strategy configuration and strategy case dispatching method based on collection urging system | |
| CN114625957A (en) | Payment method, device and equipment based on personalized recommendation of payment mode | |
| CN112927003A (en) | Member management method and system for consumption management platform | |
| CN109345219B (en) | Collection control method, device, server and readable storage medium | |
| CN110880101A (en) | Data processing method, device, server and storage medium thereof | |
| CN111369336A (en) | Method for prompting borrowing in bank | |
| CN115578007B (en) | Method and system for integrating calculation and task overall in tax industry | |
| CN113610621A (en) | Overdue collection method and device, computer equipment and storage medium | |
| CN115860957A (en) | Financing and purchasing method and device and electronic equipment | |
| CN106878169A (en) | A kind of service routing method and device | |
| CN117952741A (en) | Order distribution method, order distribution device, computer equipment and 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 |