CN112950095A - Loan case division management method, system, device and storage medium - Google Patents
Loan case division management method, system, device and storage medium Download PDFInfo
- Publication number
- CN112950095A CN112950095A CN202110440452.1A CN202110440452A CN112950095A CN 112950095 A CN112950095 A CN 112950095A CN 202110440452 A CN202110440452 A CN 202110440452A CN 112950095 A CN112950095 A CN 112950095A
- Authority
- CN
- China
- Prior art keywords
- case
- loan
- target
- divisional
- information
- 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
- 238000007726 management method Methods 0.000 title claims abstract description 70
- 238000007781 pre-processing Methods 0.000 claims abstract description 18
- 239000013598 vector Substances 0.000 claims description 30
- 238000000034 method Methods 0.000 claims description 20
- 238000004422 calculation algorithm Methods 0.000 claims description 11
- 238000012706 support-vector machine Methods 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000012417 linear regression Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 230000008094 contradictory effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 238000000926 separation method 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
- 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
-
- 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
Abstract
The embodiment of the invention provides a loan case divisional management method, which comprises the steps of obtaining information of a plurality of cases of loan cases to be distributed; preprocessing the plurality of case information; acquiring a weight value corresponding to each case information based on a current case period, and extracting a plurality of target case division characteristics from the preprocessed plurality of case information according to the weight values; inputting the target divisional characteristics into a loan case divisional model so as to output a target company matched with the loan case to be distributed through the loan case divisional model; through the multiple target case division characteristics and the loan case division model, the efficient and reasonable allocation of the accepting companies can be performed for each loan case, and the prediction conclusion of the accepting companies allocated to each loan case is more accurate.
Description
Technical Field
The embodiment of the invention relates to the field of big data, in particular to a loan case divisional management method, a loan case divisional management system, a loan case divisional management computer device and a loan case divisional management computer storage medium.
Background
Most of the existing collection management systems generally distribute cases according to the current case quantity of collection companies or collection staff when distributing loan cases. However, as the business development needs, the business has higher requirements for refined loan case division, and the division method for allocating loan cases only from the current loan case amount of the hasty company or hasty person generally has the following defects: the difference of each loan case is not considered, and a proper prediction collection company cannot be obtained; the demand for collection management which becomes more refined cannot be met, the loan cases cannot be more reasonably distributed, and the collection efficiency and the collection completion degree of the loan cases are further influenced.
Disclosure of Invention
In view of this, embodiments of the present invention provide a loan case division management method, system, computer device, and computer-readable storage medium, which are used to solve the problem of low accuracy of the forecast procurement company in a case division manner in which loan cases are distributed according to the amount of cases.
The embodiment of the invention solves the technical problems through the following technical scheme:
a loan case divisional management method comprises the following steps:
acquiring information of a plurality of cases of loan cases to be distributed;
preprocessing the plurality of case information;
acquiring a weight value corresponding to each case information based on a current case period, and extracting a plurality of target case division characteristics from the preprocessed plurality of case information according to the weight values;
inputting the target divisional characteristics into a loan case divisional model so as to output a target company matched with the loan case to be distributed through the loan case divisional model;
and distributing the loan case to be distributed to the target company.
Optionally, the loan case divisional management method further includes obtaining the loan case divisional model through pre-training, and the training step includes:
obtaining a plurality of case sample information and a plurality of case receiving company data of a plurality of sample loan cases;
setting a plurality of first hyperplanes supporting a vector machine model, wherein the first hyperplanes represent pick-up companies;
converting the plurality of case sample information of the plurality of sample loan cases into a plurality of corresponding sample vectors;
calculating a first sample projection distance corresponding to the plurality of sample vectors relative to each first hyperplane;
respectively determining the maximum first sample projection distance corresponding to each sample vector as the target sample projection distance corresponding to each sample vector in the plurality of first sample projection distances corresponding to each sample vector;
and adjusting a plurality of first hyperplane model parameters of the support vector machine model according to the target sample projection distance corresponding to each sample vector to obtain the trained loan case divisional model.
Optionally, the step of preprocessing the plurality of case information further includes:
carrying out correlation calculation on the plurality of case information through a correlation method to obtain correlation coefficients among the plurality of case information;
and deleting the case information with collinearity according to the correlation coefficient among the plurality of case information to obtain the plurality of preprocessed case information.
Optionally, the weight values include a plurality of first weight values and a plurality of second weight values; the step of obtaining a weight value corresponding to each case information according to the current case cycle and extracting a plurality of target case division characteristics from the plurality of case information according to the weight values includes:
extracting a plurality of first case characteristics from the plurality of case information according to a linear regression algorithm;
extracting a plurality of second case characteristics from the plurality of case information according to a support vector machine algorithm;
according to the current case cycle, first weight values corresponding to the first case features respectively are obtained, second weight values corresponding to the second case features respectively are obtained, and a plurality of target case features are determined and extracted from the first case features and the second case features according to the first weight values and the second weight values.
Optionally, the step of inputting the plurality of target division characteristics into a loan case division model to output a target company matching the loan case to be allocated through the loan case division model further includes:
inputting the target division characteristics into a loan case division model so as to output a first projection distance of the loan case to be distributed relative to each case receiving company through the loan case division model;
determining the maximum first projection distance from the plurality of first projection distances as a target projection distance;
and determining the case receiving company corresponding to the target projection distance as a target company.
Optionally, after the distributing the to-be-distributed loan case to the target company, further comprising:
calculating to obtain a target risk score of the loan case to be allocated according to the information of the plurality of cases;
determining the target risk level of the loan case to be allocated according to the target risk score; and determining a target execution strategy according to the target risk level.
Optionally, the method further comprises:
and according to the target risk level of the loan cases to be distributed, carrying out list classification on the loan cases to be distributed through a preset list management rule so as to update the list identification of the loan cases to be distributed.
In order to achieve the above object, an embodiment of the present invention further provides a loan case division management system, including:
the system comprises an acquisition module, a loan case allocation module and a loan case allocation module, wherein the acquisition module is used for acquiring information of a plurality of cases of loan cases to be allocated;
the preprocessing module is used for preprocessing the plurality of case information;
the extraction module is used for acquiring a weight value corresponding to each case information based on the current case cycle, and extracting a plurality of target case division characteristics from the preprocessed case information according to the weight values;
the output module is used for inputting the target divisional characteristics into a loan case divisional model so as to output a target company matched with the loan case to be distributed through the loan case divisional model;
and the distribution module is used for distributing the loan cases to be distributed to the target company.
In order to achieve the above object, an embodiment of the present invention further provides a computer device, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, and the processor implements the steps of the loan case divisional management method as described above when executing the computer program.
In order to achieve the above object, an embodiment of the present invention further provides a computer-readable storage medium, which stores therein a computer program, which is executable by at least one processor to cause the at least one processor to execute the steps of the loan case divisional management method as described above.
According to the loan case divisional management method, the loan case divisional management system, the loan case divisional management computer device and the computer-readable storage medium, the weight value corresponding to each case information is obtained through the current case period, and a plurality of target divisional characteristics are extracted from the preprocessed plurality of case information according to the weight value; inputting the target divisional characteristics into a loan case divisional model so as to output a target company matched with the loan case to be distributed through the loan case divisional model; through the multiple target case division characteristics and the loan case division model, the efficient and reasonable allocation of the accepting companies can be performed for each loan case, and the prediction conclusion of the accepting companies allocated to each loan case is more accurate.
The invention is described in detail below with reference to the drawings and specific examples, but the invention is not limited thereto.
Drawings
FIG. 1 is a flowchart illustrating the steps of a loan case division management method according to an embodiment of the invention;
FIG. 2 is a flowchart illustrating a step of preprocessing the case information in the loan case divisional management method according to an embodiment of the present invention;
FIG. 3 is a flowchart illustrating a step of extracting a plurality of target scenario characteristics in a loan scenario management method according to an embodiment of the invention;
FIG. 4 is a flowchart illustrating the steps of a loan case scenario model trained by the loan case scenario management method according to the embodiment of the invention;
FIG. 5 is a flowchart illustrating the steps of determining a target company for the loan case to be distributed in the loan case divisional management method according to the first embodiment of the present invention;
FIG. 6 is a flowchart illustrating the steps of determining a target execution policy in the loan case scenario management method according to one embodiment of the invention;
FIG. 7 is a block diagram of a second exemplary embodiment of the loan case division management system;
fig. 8 is a schematic hardware structure diagram of a computer device according to a third embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit 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.
It should be noted that the descriptions relating to "first", "second", etc. in the embodiments of the present invention are only for descriptive purposes and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In addition, technical solutions between various embodiments may be combined with each other, but must be realized by a person skilled in the art, and when the technical solutions are contradictory or cannot be realized, such a combination should not be considered to exist, and is not within the protection scope of the present invention.
In the description of the present invention, it should be understood that the numerical references before the steps do not identify the order of performing the steps, but merely serve to facilitate the description of the present invention and to distinguish each step, and thus should not be construed as limiting the present invention.
Example one
Referring to fig. 1, a flow chart of steps of a loan case division management method according to an embodiment of the invention is shown. It is to be understood that the flow charts in the embodiments of the present method are not intended to limit the order in which the steps are performed. The following description is given by taking a computer device as an execution subject, specifically as follows:
as shown in FIG. 1, the loan case division management method may include steps S100 to S106, wherein:
step S100, obtaining a plurality of case information of the cases to be distributed with loans.
In an exemplary embodiment, the plurality of case information includes information such as a client risk level, an income hastening stage, whether overdue, the number of overdue days, an income hastening balance, a client occupation type, a client age, a client region, and information of a related person corresponding to the loan case to be distributed. The loan case to be distributed is a loan collection case to be distributed to the corresponding collection company.
Step S102, preprocessing the plurality of case information.
In order to reduce the noise of the data and improve the efficiency of subsequent data processing. In an exemplary embodiment, referring to fig. 2, the step S102 of preprocessing the plurality of case information specifically includes steps S200 to S202: step S200, carrying out correlation calculation on the plurality of case information through a correlation method to obtain correlation coefficients among the plurality of case information; and step S202, deleting the case information with collinearity according to the correlation coefficient among the plurality of case information to obtain the preprocessed plurality of case information.
The correlation coefficient between the plurality of case information may be calculated by a Pearson product moment correlation coefficient (Pearson correlation coefficient), a maximum information coefficient, or the like. The degree of correlation among the plurality of pieces of case information is determined by the correlation coefficient, and if the absolute value of the correlation coefficient r is more than 0.8, it indicates that there is strong correlation among the pieces of case information. If the absolute value of the correlation coefficient r is between 0.3 and 0.8, it indicates that there is weak correlation between the case information. If the absolute value of the correlation coefficient r is 0.3 or less, it indicates that there is no correlation between the case information. Therefore, the case information with the correlation coefficient r below 0.3 can be removed, and the case information with collinearity can also be removed, namely, one of the case information is kept in the two case information with the correlation coefficient above 0.8, and the other case information is removed. By preprocessing the information of a plurality of cases, the subsequent data calculation amount is effectively reduced while the case division of the loan to be distributed is not influenced.
Step S104, acquiring a weight value corresponding to each case information based on the current case cycle, and extracting a plurality of target case division characteristics from the plurality of preprocessed case information according to the weight values.
Wherein the weight values include a plurality of first weight values and a plurality of second weight values.
To further improve the data processing efficiency, in an exemplary embodiment, as shown in fig. 3, the step 104 can be further obtained by the following steps S300 to S304, wherein: step S300, extracting a plurality of first case characteristics from the plurality of case information according to a linear regression algorithm; step S302, extracting a plurality of second case characteristics from the plurality of case information according to a support vector machine algorithm; and step S304, according to the current case cycle, obtaining first weight values corresponding to the first case features respectively, obtaining second weight values corresponding to the second case features respectively, and determining and extracting a plurality of target case features from the first case features and the second case features according to the first weight values and the second weight values.
Illustratively, a plurality of first case characteristics are preferentially screened out from a plurality of case information through a linear regression algorithm, useless characteristics are deleted, and the accuracy of case division of the loan to be distributed is improved. Based on a linear regression algorithm, first split features A, B and C associated with urge recovery are calculated. And preferentially extracting a plurality of second case characteristics from the case information through the support vector machine, deleting useless characteristics, and further improving the accuracy of the case division of the loan to be distributed. And calculating the characteristics D and E related to collection based on a support vector machine algorithm. Combining the importance degrees of the plurality of first sectional features and the plurality of second sectional features relative to the loan case classification to obtain a plurality of target sectional features; namely, a plurality of target case characteristics are determined according to a first weight value corresponding to each of the plurality of first case characteristics and a second weight value corresponding to each of the plurality of second case characteristics. The weight values can be set according to actual requirements of the service, for example, the weight values of each case characteristic can be set according to actual requirements such as a current period focus direction, a case located time node and the like. For example, if the effect of urging collection of the attribution is added at the current time, the weight value corresponding to the case classification characteristic of the attribution is set to be larger.
Step S106, inputting the target divisional characteristics into a loan case divisional model, and outputting a target company matched with the loan case to be distributed through the loan case divisional model.
In order to improve the case division effect of the loan case division model, the loan case division management method further comprises the step of obtaining the loan case division model through pre-training. In an exemplary embodiment, as shown in fig. 4, the training step specifically includes steps S400 to S410, where: step S400, obtaining a plurality of case sample information and a plurality of receiving company data of a plurality of sample loan cases; step S402, setting a plurality of first hyperplanes supporting a vector machine model, wherein the first hyperplanes represent a pick-up company; step S404, converting the sample information of the plurality of cases of the sample loan case into a plurality of corresponding sample vectors; step S406, calculating a first sample projection distance corresponding to the plurality of sample vectors relative to each first hyperplane; step S408, respectively determining the maximum first sample projection distance corresponding to each sample vector as the target sample projection distance corresponding to each sample vector in the plurality of first sample projection distances corresponding to each sample vector; and step S410, adjusting a plurality of first hyperplane model parameters of the support vector machine model according to the target sample projection distance corresponding to each sample vector to obtain the trained loan case division model.
Wherein, a plurality of first hyperplanes are used for representing collection reception companies. The processing process of the loan case division model is as follows:
assuming that x is a point, i.e., x represents a loan case to be allocated, the equation for the first hyperplane may be described by a linear equation: w is aTx + b is 0, where w is a normal vector on the first hyperplane, determines the direction of the hyperplane, T represents the transpose of the normal vector, and b is the displacement, determines the distance between the hyperplane and the origin.
The distance of point x to each first hyperplane is calculated. Assuming that there are two points x' and x "on the plane, then:
wTx′+b＝0w^Tx'+b＝0wTx’+b＝0
wTx”+b＝0w^Tx”+b＝0wTx”+b＝0
i.e. wT(x”-x′)+b＝0w^T(x”-x')+b＝0wT(x "-x') + b ═ 0. The distance from the perpendicular can be obtained by finding the length of the two points x and x' and then finding the projection of the two points in the perpendicular direction.
The following equation can be obtained by calculation:
In an exemplary embodiment, referring to fig. 5, the target company output matching the to-be-distributed loan case through the loan case classification model may also be obtained by the following operations: step S500, inputting the target divisional characteristics into a loan case divisional model so as to output a first projection distance of the loan case to be distributed relative to each pick-up company through the loan case divisional model; step S502, determining the maximum first projection distance as a target projection distance from the plurality of first projection distances; and step S504, determining the case receiving company corresponding to the target projection distance as the target company.
Illustratively, a first projected distance of the loan case to be allocated from each first hyperplane is calculated. And selecting the maximum distance from the plurality of first projection distances as the target projection distance. And determining the company represented by the first hyperplane corresponding to the target projection distance as a target company according to the target sample projection distance.
And step S108, distributing the loan case to be distributed to the target company.
In order to more finely divide the loan cases, the method further comprises matching the loan cases to be distributed with the corresponding loan case acceptance strategies after determining the target company for the loan cases to be distributed, and evaluating the optimal loan case acceptance strategies (namely target execution strategies). In an exemplary embodiment, as shown in fig. 6, matching the to-be-distributed loan case with the corresponding loan case acceptance policy further includes steps S600 to S602, where: step S600, calculating to obtain target risk scores of the loan cases to be allocated according to the information of the cases; step S602, determining the target risk level of the loan case to be allocated according to the target risk score; and determining a target execution strategy according to the target risk level.
Wherein each target company has a plurality of customized enforcement policies regarding loan case collection, wherein each enforcement policy has a corresponding risk level; determining a corresponding execution strategy according to the corresponding risk level; the execution efficiency of the loan case collection hastening is effectively improved. By the characteristics of different collection companies, the optimal distribution strategy is realized, and the refined post-credit collection management is realized.
In an exemplary embodiment, the method further comprises: and according to the target risk level of the loan cases to be distributed, carrying out list classification on the loan cases to be distributed through a preset list management rule so as to update the list identification of the loan cases to be distributed.
After a target company is determined, traversing the characteristics of the loan cases to be distributed, judging whether a name list identifier exists or not, if not, endowing the loan cases to be distributed with a specific name list identifier according to the target risk level of the loan cases to be distributed, and determining a corresponding execution strategy for the loan cases to be distributed according to the specific name list identifier; and after the periodic collection is finished, updating the list identification of the loan case to be distributed according to the collection conclusion data.
The method further comprises the following steps: and visualizing the collection urging effect curves corresponding to the data of each collection urging company, and dynamically adjusting the collection urging effect curves of a plurality of collection urging companies.
According to the loan case divisional management method, the loan case divisional management system, the loan case divisional management computer device and the loan case divisional management computer-readable storage medium, the loan case divisional management method, the loan case divisional management system, the loan case divisional management computer device and the loan case divisional management computer-readable storage medium can effectively and reasonably distribute the loan cases to the receiving companies, and the prediction conclusion of the receiving companies distributed to the loan cases is more accurate. Compared with a simple fixed rule distribution collection urging company, the collection urging efficiency is further improved according to the multi-dimensional target case distribution characteristics of each loan case, the collection urging success rate is improved, and the effect that each loan case obtains the maximum collection urging amount is achieved.
Example two
Referring still to FIG. 7, a block diagram of the process of the loan case division management system of the present invention is shown. In this embodiment, the loan case divisional management system 20 may include or be divided into one or more program modules, which are stored in a storage medium and executed by one or more processors to implement the present invention and implement the loan case divisional management method described above. The program modules referred to in the embodiments of the present invention refer to a series of computer program instruction segments that can perform specific functions, and are more suitable than the program itself for describing the execution process of the loan case scenario divisional management system 20 in a storage medium. The following description will specifically describe the functions of the program modules of the present embodiment:
the obtaining module 700 is used for obtaining a plurality of case information of the cases to be loan-allocated.
A preprocessing module 702, configured to preprocess the plurality of case information.
An extracting module 704, configured to obtain a weight value corresponding to each piece of case information according to a current case cycle, and extract a plurality of target case separation features from the plurality of pieces of case information according to the weight values.
An output module 706, configured to input the multiple target scenario division characteristics into a loan scenario division model, so as to output, through the loan scenario division model, a target company matched with the loan scenario to be allocated.
A distribution module 708, configured to distribute the to-be-distributed loan case to the target company.
In an exemplary embodiment, the loan case scenario management system 20 further comprises a training module 710, wherein the training module 710 is configured to pre-train the loan case scenario model. The training module 710 is further configured to: obtaining a plurality of case sample information and a plurality of case receiving company data of a plurality of sample loan cases; setting a plurality of first hyperplanes supporting a vector machine model, wherein the first hyperplanes represent pick-up companies; converting the plurality of case sample information of the plurality of sample loan cases into a plurality of corresponding sample vectors; calculating a first sample projection distance corresponding to the plurality of sample vectors relative to each first hyperplane; respectively determining the maximum first sample projection distance corresponding to each sample vector as the target sample projection distance corresponding to each sample vector in the plurality of first sample projection distances corresponding to each sample vector; and adjusting a plurality of first hyperplane model parameters of the support vector machine model according to the target sample projection distance corresponding to each sample vector to obtain the trained loan case division model.
In an exemplary embodiment, the loan case divisional management system 20 further comprises a data preprocessing module 712, wherein the data preprocessing module 712 is configured to: the data preprocessing module 712 is further configured to: carrying out correlation calculation on the plurality of case information through a correlation method to obtain correlation coefficients among the plurality of case information; and deleting the case information with collinearity according to the correlation coefficient among the plurality of case information to obtain the plurality of preprocessed case information.
In an exemplary embodiment, the weight values include a plurality of first weight values and a plurality of second weight values; the extracting module 704 is further configured to: extracting a plurality of first case characteristics from the plurality of case information according to a linear regression algorithm; extracting a plurality of second case characteristics from the plurality of case information according to a support vector machine algorithm; and according to the current case cycle, acquiring first weight values corresponding to the first case features respectively, acquiring second weight values corresponding to the second case features respectively, and determining and extracting a plurality of target case features from the first case features and the second case features according to the first weight values and the second weight values.
In an exemplary embodiment, the output module 706 is further configured to: inputting the target division characteristics into a loan case division model so as to output a first projection distance of the loan case to be distributed relative to each case receiving company through the loan case division model; determining the maximum first projection distance from the plurality of first projection distances as a target projection distance; and determining the case receiving company corresponding to the target projection distance as a target company.
In an exemplary embodiment, the loan case divisional management system 20 further comprises a policy matching module 714, wherein the policy matching module 714 is configured to: calculating to obtain a target risk score of the loan case to be allocated according to the information of the plurality of cases; determining the target risk level of the loan case to be allocated according to the target risk score; and determining a target execution strategy according to the target risk level.
In an exemplary embodiment, the loan case divisional management system 20 further includes: a list management module 716, wherein the list management module 716 is configured to: and according to the target risk level of the loan cases to be distributed, carrying out list classification on the loan cases to be distributed through a preset list management rule so as to update the list identification of the loan cases to be distributed.
EXAMPLE III
Fig. 8 is a schematic diagram of a hardware architecture of a computer device according to a third embodiment of the present invention. In the present embodiment, the computer device 2 is a device capable of automatically performing numerical calculation and/or information processing in accordance with a preset or stored instruction. The computer device 2 may be a rack server, a blade server, a tower server or a rack server (including an independent server or a server cluster composed of a plurality of servers), and the like. As shown in FIG. 8, the computer device 2 includes, but is not limited to, at least a memory 21, a processor 22, a network interface 23, and a loan case divisional management system 20, which are communicatively connected to each other through a system bus. Wherein:
in this embodiment, the memory 21 includes at least one type of computer-readable storage medium including a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a Read Only Memory (ROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), a Programmable Read Only Memory (PROM), a magnetic memory, a magnetic disk, an optical disk, and the like. In some embodiments, the storage 21 may be an internal storage unit of the computer device 2, such as a hard disk or a memory of the computer device 2. In other embodiments, the memory 21 may also be an external storage device of the computer device 2, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), or the like provided on the computer device 2. Of course, the memory 21 may also comprise both internal and external memory units of the computer device 2. In this embodiment, the memory 21 is generally used for storing an operating system installed on the computer device 2 and various application software, such as the program codes of the loan case scenario division management system 20 of the above-mentioned embodiment. Further, the memory 21 may also be used to temporarily store various types of data that have been output or are to be output.
The network interface 23 may comprise a wireless network interface or a wired network interface, and the network interface 23 is generally used for establishing communication connection between the computer device 2 and other electronic apparatuses. For example, the network interface 23 is used to connect the computer device 2 to an external terminal through a network, establish a data transmission channel and a communication connection between the computer device 2 and the external terminal, and the like. The network may be a wireless or wired network such as an Intranet (Intranet), the Internet (Internet), a Global System of Mobile communication (GSM), Wideband Code Division Multiple Access (WCDMA), a 4G network, a 5G network, Bluetooth (Bluetooth), Wi-Fi, and the like.
It is noted that fig. 8 only shows the computer device 2 with components 20-23, but it is to be understood that not all shown components are required to be implemented, and that more or less components may be implemented instead.
In this embodiment, the loan case scenario management system 20 stored in the memory 21 may also be divided into one or more program modules, which are stored in the memory 21 and executed by one or more processors (in this embodiment, the processor 22) to complete the present invention.
For example, fig. 8 shows a schematic diagram of program modules of the second embodiment implementing the loan case scenario division management system 20, in this embodiment, the loan case division management-based system 20 may be divided into an acquisition module 700, a preprocessing module 702, an extraction module 704, an output module 706, and a distribution module 708. The program modules referred to herein are a series of computer program instruction segments that can perform specific functions, and are more suitable than programs for describing the execution of the loan case divisional management system 20 in the computer device 2. The specific functions of the program modules 700 and 708 have been described in detail in the second embodiment, and are not described herein again.
Example four
The present embodiment also provides a computer-readable storage medium, such as a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, a server, an App application mall, etc., on which a computer program is stored, which when executed by a processor implements corresponding functions. The computer-readable storage medium of the embodiment is used for storing the loan case scenario management system 20, and when being executed by the processor, the computer-readable storage medium implements the loan case scenario management method of the embodiment.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A loan case divisional management method is characterized by comprising the following steps:
acquiring information of a plurality of cases of loan cases to be distributed;
preprocessing the plurality of case information;
acquiring a weight value corresponding to each case information based on a current case period, and extracting a plurality of target case division characteristics from the preprocessed plurality of case information according to the weight values;
inputting the target divisional characteristics into a loan case divisional model so as to output a target company matched with the loan case to be distributed through the loan case divisional model;
and distributing the loan case to be distributed to the target company.
2. The method of claim 1, wherein the method further comprises pre-training the loan case scenario management model, the training step comprising:
obtaining a plurality of case sample information and a plurality of case receiving company data of a plurality of sample loan cases;
setting a plurality of first hyperplanes supporting a vector machine model, wherein the first hyperplanes represent pick-up companies;
converting the plurality of case sample information of the plurality of sample loan cases into a plurality of corresponding sample vectors;
calculating a first sample projection distance corresponding to the plurality of sample vectors relative to each first hyperplane;
respectively determining the maximum first sample projection distance corresponding to each sample vector as the target sample projection distance corresponding to each sample vector in the plurality of first sample projection distances corresponding to each sample vector;
and adjusting a plurality of first hyperplane model parameters of the support vector machine model according to the target sample projection distance corresponding to each sample vector to obtain the trained loan case divisional model.
3. The loan case divisional management method according to claim 1, wherein the step of preprocessing the plurality of case information further comprises:
carrying out correlation calculation on the plurality of case information through a correlation method to obtain correlation coefficients among the plurality of case information;
and deleting the case information with collinearity according to the correlation coefficient among the plurality of case information to obtain the plurality of preprocessed case information.
4. The loan case divisional management method according to claim 1, wherein the weight values include a plurality of first weight values and a plurality of second weight values; the step of obtaining a weight value corresponding to each case information according to the current case cycle and extracting a plurality of target case division characteristics from the plurality of case information according to the weight values includes:
extracting a plurality of first case characteristics from the plurality of case information according to a linear regression algorithm;
extracting a plurality of second case characteristics from the plurality of case information according to a support vector machine algorithm;
according to the current case cycle, first weight values corresponding to the first case features respectively are obtained, second weight values corresponding to the second case features respectively are obtained, and a plurality of target case features are determined and extracted from the first case features and the second case features according to the first weight values and the second weight values.
5. The method of claim 2, wherein the step of inputting the plurality of target divisional characteristics into a loan case divisional model to output target companies matching the loan cases to be distributed through the loan case divisional model further comprises:
inputting the target division characteristics into a loan case division model so as to output a first projection distance of the loan case to be distributed relative to each case receiving company through the loan case division model;
determining the maximum first projection distance from the plurality of first projection distances as a target projection distance;
and determining the case receiving company corresponding to the target projection distance as a target company.
6. The loan case divisional management method according to claim 5, further comprising, after said distributing the to-be-distributed loan case to the target company:
calculating to obtain a target risk score of the loan case to be allocated according to the information of the plurality of cases;
determining the target risk level of the loan case to be allocated according to the target risk score; and determining a target execution strategy according to the target risk level.
7. The loan case divisional management method according to claim 6, the method further comprising:
and according to the target risk level of the loan cases to be distributed, carrying out list classification on the loan cases to be distributed through a preset list management rule so as to update the list identification of the loan cases to be distributed.
8. A loan case divisional management system, comprising:
the system comprises an acquisition module, a loan case allocation module and a loan case allocation module, wherein the acquisition module is used for acquiring information of a plurality of cases of loan cases to be allocated;
the preprocessing module is used for preprocessing the plurality of case information;
the extraction module is used for acquiring a weight value corresponding to each case information based on the current case cycle, and extracting a plurality of target case division characteristics from the preprocessed case information according to the weight values;
the output module is used for inputting the target divisional characteristics into a loan case divisional model so as to output a target company matched with the loan case to be distributed through the loan case divisional model;
and the distribution module is used for distributing the loan cases to be distributed to the target company.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the computer program implements the steps of the loan case divisional management method according to any one of claims 1 to 7.
10. A computer-readable storage medium having stored thereon a computer program executable by at least one processor to cause the at least one processor to perform the steps of the loan case divisional management method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110440452.1A CN112950095A (en) | 2021-04-23 | 2021-04-23 | Loan case division management method, system, device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110440452.1A CN112950095A (en) | 2021-04-23 | 2021-04-23 | Loan case division management method, system, device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112950095A true CN112950095A (en) | 2021-06-11 |
Family
ID=76233290
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110440452.1A Pending CN112950095A (en) | 2021-04-23 | 2021-04-23 | Loan case division management method, system, device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112950095A (en) |
Citations (5)
| 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 |
| CN111177367A (en) * | 2019-11-11 | 2020-05-19 | 腾讯科技（深圳）有限公司 | Case classification method, classification model training method and related products |
| CN111192133A (en) * | 2019-12-12 | 2020-05-22 | 北京淇瑀信息科技有限公司 | Method and device for generating risk model after user loan and electronic equipment |
| CN112488156A (en) * | 2020-11-11 | 2021-03-12 | 山大地纬软件股份有限公司 | Endowment insurance compensation information reminding method and system |
-
2021
- 2021-04-23 CN CN202110440452.1A patent/CN112950095A/en active Pending
Patent Citations (5)
| 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 |
| CN111177367A (en) * | 2019-11-11 | 2020-05-19 | 腾讯科技（深圳）有限公司 | Case classification method, classification model training method and related products |
| CN111192133A (en) * | 2019-12-12 | 2020-05-22 | 北京淇瑀信息科技有限公司 | Method and device for generating risk model after user loan and electronic equipment |
| CN112488156A (en) * | 2020-11-11 | 2021-03-12 | 山大地纬软件股份有限公司 | Endowment insurance compensation information reminding method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110060144B (en) | Method for training credit model, method, device, equipment and medium for evaluating credit | |
| CN110610431B (en) | Intelligent claim settlement method and intelligent claim settlement system based on big data | |
| CN110599354B (en) | Online checking method, online checking system, computer device and computer readable storage medium | |
| CN111523748B (en) | Case distribution method, device and system | |
| CN110503566B (en) | Wind control model building method and device, computer equipment and storage medium | |
| WO2020244230A1 (en) | Resource transfer method, apparatus and device, and red packet issuing method, apparatus and device | |
| CN111259137A (en) | Method and system for generating knowledge graph abstract | |
| CN110706092B (en) | Risk user identification method and device, storage medium and electronic equipment | |
| CN111444226B (en) | Method and system for pushing service reservation network point data | |
| CN110503507B (en) | Insurance product data pushing method and system based on big data and computer equipment | |
| CN111414528B (en) | Method and device for determining equipment identification, storage medium and electronic equipment | |
| CN114219497A (en) | Account information determination method and device and server | |
| CN112148880A (en) | Customer service dialogue corpus clustering method, system, equipment and storage medium | |
| CN112132476A (en) | Case allocation method, device, equipment and storage medium | |
| CN112950095A (en) | Loan case division management method, system, device and storage medium | |
| CN112650940A (en) | Recommendation method and device of application program, computer equipment and storage medium | |
| CN109885710B (en) | User image depicting method based on differential evolution algorithm and server | |
| CN113468886B (en) | Work order processing method and device and computer equipment | |
| CN112650741B (en) | Method, system, equipment and readable storage medium for identifying and correcting abnormal data | |
| CN112597162B (en) | Data set acquisition method, system, equipment and storage medium | |
| CN113988670A (en) | Comprehensive enterprise credit risk early warning method and system | |
| CN110033309B (en) | Method and device for predicting result based on historical data and terminal equipment | |
| CN113421118B (en) | Data pushing method, system, computer equipment and computer readable storage medium | |
| CN112836827A (en) | Model training method and device and computer equipment | |
| CN113723522B (en) | Abnormal user identification method and device, electronic 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 |