CN117273945A - Asset processing method and device, storage medium and electronic equipment - Google Patents
Asset processing method and device, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN117273945A CN117273945A CN202311119130.2A CN202311119130A CN117273945A CN 117273945 A CN117273945 A CN 117273945A CN 202311119130 A CN202311119130 A CN 202311119130A CN 117273945 A CN117273945 A CN 117273945A
- Authority
- CN
- China
- Prior art keywords
- asset
- value
- risk assessment
- processed
- determining
- 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
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
- G06Q40/06—Asset management; Financial planning or analysis
-
- 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0283—Price estimation or determination
-
- 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
- G06Q40/02—Banking, e.g. interest calculation or account maintenance
-
- 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
- G06Q40/08—Insurance
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- Technology Law (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Human Resources & Organizations (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses an asset processing method, an asset processing device, a storage medium and electronic equipment. Relates to the field of artificial intelligence, and the method comprises the following steps: acquiring a plurality of assets of a target enterprise, determining a life cycle of each asset, and judging whether the life cycle is greater than or equal to a life cycle threshold value; determining an asset with a life cycle greater than or equal to a life cycle threshold as an asset to be processed, and acquiring a risk assessment factor of the asset to be processed; inputting a risk assessment factor into a target model to obtain a risk assessment value of an asset to be processed, wherein the target model is trained by a plurality of groups of training samples, and each group of training samples comprises a historical risk assessment value and a historical risk assessment value; and determining a risk assessment value threshold, and transferring the assets to be processed with the risk assessment value greater than or equal to the risk assessment value threshold to a target customer group. By the method and the device, the problem of inaccurate risk assessment value in the asset processing scheme in the related art is solved.
Description
Technical Field
The present application relates to the field of artificial intelligence, and in particular, to an asset processing method, an apparatus, a storage medium, and an electronic device.
Background
In the related art, when a financial institution processes bad assets, the financial institution can mainly select to process the bad assets in such modes as debt reduction, account checking, batch transfer and the like. Bulk transfer is an important means for banks to dispose of bad assets, and funds can be quickly recovered by disposing of bad assets through bulk transfer, so that the quick improvement of the asset structure of a financial institution is realized, and the asset quality is improved. Various tax fees, intermediary fees, legal fees, etc. generated in the process of disposing bad assets can also be saved. The bad assets generally have the 'ice sucker effect', and for the bad assets generated by bad enterprise operation, the asset value of the bad assets can be continuously reduced along with the time, and the loss caused by the time can be reduced by batch transfer and quick disposal.
The bad assets are disposed of by batch transfer, and the subsequent equity of the bad assets after sale no longer belongs to the financial institution, so the price of the bad asset pack determines the total income of the financial institution, and the pricing of the asset pack by the financial institution is very important. Too high a price will affect the rate of the bad asset, too low a price will impair the financial institution's own interests, and only having a price close to the most likely price to be traded will bring as much revenue to the financial institution as possible. The pricing method in the related art is determined through manual experience, and the subjective randomness is high.
Aiming at the problem of inaccurate risk assessment values in the treatment scheme of the assets in the related technology, no effective solution is proposed at present.
Disclosure of Invention
The main object of the present application is to provide an asset processing method, apparatus, storage medium and electronic device, so as to solve the problem of inaccurate risk assessment value in the asset processing scheme in the related art.
To achieve the above object, according to one aspect of the present application, there is provided an asset processing method. The method comprises the following steps: acquiring a plurality of assets of a target enterprise, determining a life cycle of each asset, and judging whether the life cycle is greater than or equal to a life cycle threshold value; determining an asset with a life cycle greater than or equal to a life cycle threshold as an asset to be processed, and acquiring a risk assessment factor of the asset to be processed; inputting a risk assessment factor into a target model to obtain a risk assessment value of an asset to be processed, wherein the target model is trained by a plurality of groups of training samples, and each group of training samples comprises a historical risk assessment value and a historical risk assessment value; and determining a risk assessment value threshold, and transferring the assets to be processed with the risk assessment value greater than or equal to the risk assessment value threshold to a target customer group.
Optionally, acquiring the risk assessment factor for the asset to be processed includes: extracting a plurality of asset correlation factors from the assets to be processed, and calculating the pearson correlation coefficient of each asset correlation factor and the risk assessment value; judging whether the pearson correlation coefficient is larger than or equal to a correlation coefficient threshold value for each asset correlation factor; calculating a significance evaluation value of the asset correlation factor based on the pearson correlation coefficient under the condition that the pearson correlation coefficient is greater than or equal to a correlation coefficient threshold; and determining the asset correlation factor with the saliency assessment value being greater than or equal to the saliency assessment value threshold as the risk assessment factor of the asset to be processed.
Optionally, extracting the plurality of asset-related factors from the asset to be processed includes: determining a type of the asset to be processed, wherein the type includes at least one of: overtime loans, debt property resisting, account sales; and extracting a plurality of asset-related factors corresponding to the types from the assets to be processed based on the types.
Optionally, calculating the saliency assessment value of the asset-related factor based on the pearson correlation coefficient comprises: determining a sample number of asset correlation factors; calculating the difference value between the number of samples and a first preset value, calculating a first open square value of the difference value, and calculating the product of the pearson correlation coefficient and the first open square value to obtain a target product value; calculating the square value of the pearson correlation coefficient, calculating the difference value between a second preset value and the square value, and calculating a second open square value of the difference value; and calculating the ratio of the target product value to the second open square value to obtain the saliency assessment value of the asset correlation factor.
Alternatively, the object model is obtained by: acquiring a history asset processing record, and extracting a history risk evaluation value risk evaluation factor and a history risk evaluation value of each history asset from the history asset processing record; determining a historical risk assessment value and a historical risk assessment value of each historical asset as a group of training samples to obtain a plurality of groups of training samples; and training the neural network model through a plurality of groups of training samples to obtain a target model.
Optionally, after transferring the pending asset having a risk assessment value greater than or equal to the risk assessment value threshold to the target customer group, the method further comprises: determining a target risk evaluation value of the target customer group for evaluating the asset to be processed, and calculating an evaluation value difference value between the target risk evaluation value and the risk evaluation value; judging whether the difference value of the evaluation values is larger than or equal to a difference value threshold value; under the condition that the difference value of the evaluation values is smaller than a difference value threshold value, storing a transfer scheme of the asset to be processed into a sample database; under the condition that the difference value of the evaluation values is larger than or equal to a difference value threshold value, determining a risk evaluation factor and a target risk evaluation value of the asset to be processed as a new training sample; and adding the newly added training samples into a plurality of groups of training samples to obtain updated groups of training samples, and training the neural network model based on the updated groups of training samples to obtain an updated target model.
Optionally, transferring the asset to be processed having the risk assessment value greater than or equal to the risk assessment value threshold to the target customer group includes: determining an evaluation value range to which the risk evaluation value belongs, and determining a target customer group and an assignment channel based on the evaluation value range; and publishing asset transfer information to the target customer group and transferring the to-be-processed asset to the target customer group through a transfer channel.
To achieve the above object, according to another aspect of the present application, there is provided an asset processing device. The device comprises: the acquisition unit is used for acquiring a plurality of assets of the target enterprise, determining the life cycle of each asset and judging whether the life cycle is greater than or equal to a life cycle threshold value or not; the determining unit is used for determining the asset with the life cycle being more than or equal to the life cycle threshold value as the asset to be processed and acquiring the risk assessment factor of the asset to be processed; the input unit is used for inputting the risk assessment factors into a target model to obtain a risk assessment value of the asset to be processed, wherein the target model is trained by a plurality of groups of training samples, and each group of training samples comprises a historical risk assessment value risk assessment factor and a historical risk assessment value; and the transfer unit is used for determining a risk evaluation value threshold and transferring the assets to be processed with the risk evaluation value greater than or equal to the risk evaluation value threshold to the target customer group.
Through the application, the following steps are adopted: acquiring a plurality of assets of a target enterprise, determining a life cycle of each asset, and judging whether the life cycle is greater than or equal to a life cycle threshold value; determining an asset with a life cycle greater than or equal to a life cycle threshold as an asset to be processed, and acquiring a risk assessment factor of the asset to be processed; inputting a risk assessment factor into a target model to obtain a risk assessment value of an asset to be processed, wherein the target model is trained by a plurality of groups of training samples, and each group of training samples comprises a historical risk assessment value and a historical risk assessment value; and determining a risk evaluation value threshold, transferring the assets to be processed with the risk evaluation value greater than or equal to the risk evaluation value threshold to a target customer group, and solving the problem of inaccurate risk evaluation values in the asset processing scheme in the related art. The risk assessment factors of the assets to be processed are extracted by training the target model, and the risk assessment factors are input into the target model to obtain a risk assessment value, so that the effect of improving the accuracy of the risk assessment value is achieved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application, illustrate and explain the application and are not to be construed as limiting the application. In the drawings:
FIG. 1 is a flow chart of an asset processing method provided according to an embodiment of the present application;
FIG. 2 is a flowchart of a method for acquiring risk assessment factors provided according to an embodiment of the present application;
FIG. 3 is a schematic diagram of an asset processing device provided according to an embodiment of the present application;
fig. 4 is a schematic diagram of an electronic device provided according to an embodiment of the present application.
Detailed Description
It should be noted that, in the case of no conflict, the embodiments and features in the embodiments may be combined with each other. The present application will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
In order to make the present application solution better understood by those skilled in the art, the following description will be made in detail and with reference to the accompanying drawings in the embodiments of the present application, it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, shall fall within the scope of the present application.
It should be noted that the terms "first," "second," and the like in the description and claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate in order to describe the embodiments of the present application described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
It should be noted that, the user information (including, but not limited to, user equipment information, user personal information, etc.) and the data (including, but not limited to, data for presentation, analyzed data, etc.) related to the present disclosure are information and data authorized by the user or sufficiently authorized by each party.
For convenience of description, the following will describe some terms or terms related to the embodiments of the present application:
batch transfer: the method realizes the package transfer of bad loans, liabilities, account and sales deposit assets and other bad assets, including the processes of asset group package, investigation valuation, scheme formulation, scheme examination, interrogation, approval, scheme execution, maintenance and handover situations and the like.
The invention will now be described in connection with preferred embodiments, and FIG. 1 is a flow chart of a method of asset processing according to an embodiment of the present application, as shown in FIG. 1, comprising the steps of:
step S101, a plurality of assets of a target enterprise are acquired, the life cycle of each asset is determined, and whether the life cycle is greater than or equal to a life cycle threshold is judged.
Specifically, the target enterprise may be a financial institution, the assets may be various types of assets owned by the financial institution, and the life cycle threshold may be set to one year, and the assets to be processed are screened by determining whether the life cycle of each asset of the target enterprise is greater than or equal to the life cycle threshold.
And step S102, determining the asset with the life cycle greater than or equal to the life cycle threshold as the asset to be processed, and acquiring a risk assessment factor of the asset to be processed.
Specifically, the property to be processed may be a bad property with a life cycle greater than or equal to a life cycle threshold, such as an out-of-date loan, a liability property, and a billing case, where the billing case refers to storing the account sales case in a specific place for subsequent processing and tracking. The risk assessment factor may be a factor related to the transfer price of the bad property, such as a bad loan principal balance extracted from the bad loan. After determining the to-be-processed assets, the types of the to-be-processed assets are acquired, and then risk assessment factors of the to-be-processed assets are extracted based on the types.
Step S103, inputting a risk assessment factor into a target model to obtain a risk assessment value of the asset to be processed, wherein the target model is trained by a plurality of groups of training samples, and each group of training samples comprises a historical risk assessment value risk assessment factor and a historical risk assessment value.
Specifically, the target model may be a neural network model, multiple sets of training samples are extracted based on the history-processed bad asset records, and training is performed through the multiple sets of training samples, so as to obtain the target model capable of outputting the risk assessment value based on the risk assessment factor.
Step S104, determining a risk evaluation value threshold value, and transferring the assets to be processed with the risk evaluation value greater than or equal to the risk evaluation value threshold value to a target customer group.
Specifically, bad assets needing to transfer the assets are screened by setting a risk evaluation value threshold, an evaluation value range is determined according to the risk evaluation value, a target customer group is selected according to the evaluation value range, and transfer information of the assets to be processed is transferred to the target customer group. And transfers the asset to be processed to the target customer group in accordance with a preset transfer channel, for example, by means of an on-site transaction or an on-line transaction.
According to the asset processing method provided by the embodiment of the application, the life cycle of each asset is determined by acquiring a plurality of assets of a target enterprise, and whether the life cycle is greater than or equal to the life cycle threshold value is judged; determining an asset with a life cycle greater than or equal to a life cycle threshold as an asset to be processed, and acquiring a risk assessment factor of the asset to be processed; inputting a risk assessment factor into a target model to obtain a risk assessment value of an asset to be processed, wherein the target model is trained by a plurality of groups of training samples, and each group of training samples comprises a historical risk assessment value and a historical risk assessment value; and determining a risk evaluation value threshold, transferring the assets to be processed with the risk evaluation value greater than or equal to the risk evaluation value threshold to a target customer group, and solving the problem of inaccurate risk evaluation values in the asset processing scheme in the related art. The risk assessment factors of the assets to be processed are extracted by training the target model, and the risk assessment factors are input into the target model to obtain a risk assessment value, so that the effect of improving the accuracy of the risk assessment value is achieved.
The risk assessment factors are extracted from a plurality of asset correlation factors, and fig. 2 is a flowchart of a method for acquiring risk assessment factors according to an embodiment of the present application, as shown in fig. 2, optionally, in an asset processing method provided in an embodiment of the present application, acquiring risk assessment factors of an asset to be processed includes: step S201, extracting a plurality of asset correlation factors from the assets to be processed, and calculating the pearson correlation coefficient of each asset correlation factor and the risk assessment value; step S202, judging whether the Pearson correlation coefficient is larger than or equal to a correlation coefficient threshold value for each asset correlation factor; step S203, calculating a saliency evaluation value of the asset correlation factor based on the pearson correlation coefficient under the condition that the pearson correlation coefficient is larger than or equal to a correlation coefficient threshold; and step S204, determining an asset correlation factor with the saliency evaluation value being greater than or equal to the saliency evaluation value threshold as a risk evaluation factor of the asset to be processed.
Specifically, the risk assessment factor may be a factor for assessing the asset value of the bad asset, by assessing the current asset value of the bad asset, comparing the current asset value with the historical asset value, determining that the asset has a risk when the current asset value is lower than the historical asset value, selecting a risk assessment factor most relevant to the transfer price from the plurality of asset correlation factors, for example, determining the type of the asset to be processed, extracting all asset correlation factors corresponding to the type based on the type, calculating pearson correlation coefficients of the risk assessment value for each asset correlation factor, and calculating the following formula:
Wherein r is the pearson correlation coefficient of the asset correlation factor and the risk assessment value, n is the sample number, y i Is the borrower's refund for each sample,is the average borrower refund, x for all samples i Value of asset-related factor for each sample, +.>Asset correlation for all samplesThe average value of the factors is calculated by comparing the pearson correlation coefficient of each asset correlation factor with the magnitude of the correlation coefficient threshold, e.g., set the correlation coefficient threshold to 0.5 for |r|>And 0.5, namely, the asset correlation factors have stronger correlation with the risk assessment values, calculating the saliency assessment values of all the asset correlation factors with stronger correlation, and determining the asset correlation factors with the saliency assessment values being greater than or equal to the saliency assessment value threshold as the risk assessment factors of the assets to be processed. The present embodiment provides predictive data for risk assessment values by determining risk assessment factors.
Optionally, in the asset processing method provided in the embodiment of the present application, extracting a plurality of asset correlation factors from the asset to be processed includes: determining a type of the asset to be processed, wherein the type includes at least one of: overtime loans, debt property resisting, account sales; and extracting a plurality of asset-related factors corresponding to the types from the assets to be processed based on the types.
For example, assets to be processed are largely divided into three types: bad loans, liabilities, account sales. For bad loans and account sales, the following property-related factors can be extracted: the bad loan principal balance, the in-table interest amount of the reference day, the out-of-table interest amount of the reference day, the peak time loan balance, the first time loan balance, the principal cleared before the first time loan is transferred into the bad, the mortgage amount of the reference day, the guarantee amount of the reference day, the credit amount of the reference day, the secondary class amount, the suspicious class amount, the lost class amount, the short-term amount, the medium-term amount, the mobile fund amount, the project loan amount, the other loan variety amount, the liability total amount, the other bank loan amount and the like.
For liability assets, the following asset-related factors may be extracted: escrow market value, against wager guarantee contract amount, against wager priority current value, general creditor current value, guarantee person current value, other payable current value, paid disposal cost, disposal cost to pay, check-up security fee, lawyer proxy fee, litigation fee, execution fee, consultation, assessment fee, auction fee, disposal asset transit fee, management fee, etc. The implementation screens risk assessment factors by extracting asset-related factors.
Optionally, in the asset processing method provided in the embodiment of the present application, calculating the saliency assessment value of the asset correlation factor based on the pearson correlation coefficient includes: determining a sample number of asset correlation factors; calculating the difference value between the number of samples and a first preset value, calculating a first open square value of the difference value, and calculating the product of the pearson correlation coefficient and the first open square value to obtain a target product value; calculating the square value of the pearson correlation coefficient, calculating the difference value between a second preset value and the square value, and calculating a second open square value of the difference value; and calculating the ratio of the target product value to the second open square value to obtain the saliency assessment value of the asset correlation factor.
Specifically, the saliency assessment value of the asset-related factor is calculated by the following formula:
wherein t is a saliency evaluation value of the asset correlation factor, r is a pearson correlation coefficient of the asset correlation factor, n is the number of samples, the first preset value may be 1, the second preset value may be 2, and after the saliency evaluation value of the asset correlation factor is calculated, a p value is obtained by referring to a t distribution table. If p is less than 0.05, the asset correlation factor and the risk assessment value are considered to have a correlation relationship, and the asset correlation factor with the pearson correlation coefficient being greater than or equal to the correlation coefficient threshold and the significance assessment value being greater than or equal to the significance assessment value threshold is determined to be the risk assessment factor.
Optionally, in the asset processing method provided in the embodiment of the present application, the object model is obtained by: acquiring a history asset processing record, and extracting a history risk evaluation value risk evaluation factor and a history risk evaluation value of each history asset from the history asset processing record; determining a historical risk evaluation value risk evaluation factor and a historical risk evaluation value of each historical asset as a group of training samples to obtain a plurality of groups of training samples; and training the neural network model through a plurality of groups of training samples to obtain a target model.
Specifically, the target model may be a convolutional neural network model, by extracting a historical risk assessment value and a historical risk assessment value risk assessment factor of each historical bad asset when transferring from a historical asset processing record, taking the historical risk assessment value risk assessment factor and the historical risk assessment value of each historical bad asset as a set of training samples, extracting a plurality of sets of training samples from the historical asset processing record, and training the convolutional neural network model through the plurality of sets of training samples, so that the target model obtained after training can automatically output the risk assessment value of the asset to be processed according to the input risk assessment factor. According to the method and the device, the accuracy of the risk assessment value for predicting the asset to be processed is improved through training the target model.
It should be noted that, in addition to the risk assessment value of the asset to be processed through the target model, a regression analysis method may be used to assess the risk assessment value of the asset to be processed. For example, the risk assessment factor obtained by screening by the above method is denoted as a 1 、a 2 、a 3 .. the borrower compensation amount is set as y, and each factor coefficient is b 1 、b 2 、b 3 .., a regression equation is constructed: y=e+b 1 a 1 +b 2 a 2 +b 3 a 3 +.... The risk assessment value is obtained by regression calculation of the historical sample data. And substituting each dimension factor of the bad loan and account sales property into the regression equation for the customer bad loan and account sales property to be predicted, and finally predicting the price of the customer bad loan and account sales property. And (3) adopting the same screening factors for the client liability assets and carrying out regression, and finally summarizing the total price of the bad asset pack.
In the method for processing assets provided in the embodiment of the present application, optionally, after transferring the assets to be processed with risk assessment values greater than or equal to the risk assessment value threshold to the target customer group, the method further includes: determining a target risk evaluation value of the target customer group for evaluating the asset to be processed, and calculating an evaluation value difference value between the target risk evaluation value and the risk evaluation value; judging whether the difference value of the evaluation values is larger than or equal to a difference value threshold value; under the condition that the difference value of the evaluation values is smaller than a difference value threshold value, storing a transfer scheme of the asset to be processed into a sample database; under the condition that the difference value of the evaluation values is larger than or equal to a difference value threshold value, determining a risk evaluation factor and a target risk evaluation value of the asset to be processed as a new training sample; and adding the newly added training samples into a plurality of groups of training samples to obtain updated groups of training samples, and training the neural network model based on the updated groups of training samples to obtain an updated target model.
Specifically, since the risk assessment value is affected by various factors such as a transaction scenario and a transaction scheme, there is a certain deviation between the risk assessment value and the target risk assessment value. If the deviation is within a certain range, namely, if the difference value of the evaluation values is smaller than the difference value threshold value, the risk evaluation value is accurate, if the difference value of the evaluation values is larger than or equal to the difference value threshold value, the risk evaluation value in the processing scheme of the to-be-processed asset is inaccurate, the target model needs to be adjusted, namely, the target risk evaluation value and the risk evaluation factor of the to-be-processed asset with larger price deviation are used as newly added training samples and added into a plurality of groups of training samples of the target model, the neural network model is retrained, and the updated target model is obtained. The method and the device ensure the accuracy of the target model risk evaluation value by updating the target model in real time based on the target risk evaluation value of the asset to be processed.
Optionally, in the asset processing method provided in the embodiment of the present application, transferring the asset to be processed having the risk assessment value equal to or greater than the risk assessment value threshold to the target customer group includes: determining an evaluation value range to which the risk evaluation value belongs, and determining a target customer group and an assignment channel based on the evaluation value range; and publishing asset transfer information to the target customer group and transferring the to-be-processed asset to the target customer group through a transfer channel.
Specifically, the different to-be-processed assets and the different transfer client groups to which the transfer prices face are different, so after the risk assessment value of the to-be-processed assets is determined, the transfer client groups can be screened based on the assessment value range to which the risk assessment value belongs, and corresponding transfer channels when the transfer client groups transfer the assets are determined, for example, part of the transfer client groups only accept off-line face-to-face transactions, and part of the transfer client groups need to conduct transactions through an on-line network. A transfer scheme is generated for the target customer group based on the target customer group and the transfer channel, and the to-be-processed asset is transferred to the target customer group based on the transfer scheme. The present embodiment ensures efficient transfer of assets to be processed by generating transfer schemes.
It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer executable instructions, and that although a logical order is illustrated in the flowcharts, in some cases the steps illustrated or described may be performed in an order other than that illustrated herein.
The embodiment of the application also provides an asset processing device, and it should be noted that the asset processing device of the embodiment of the application can be used for executing the asset processing method provided by the embodiment of the application. The asset processing device provided in the embodiment of the present application is described below.
FIG. 3 is a schematic diagram of an asset processing device provided according to an embodiment of the present application. As shown in fig. 3, the apparatus includes:
an acquiring unit 10, configured to acquire a plurality of assets of a target enterprise, determine a life cycle of each asset, and determine whether the life cycle is greater than or equal to a life cycle threshold;
a determining unit 20, configured to determine an asset whose life cycle is greater than or equal to a life cycle threshold as an asset to be processed, and acquire a risk assessment factor of the asset to be processed;
the input unit 30 is configured to input a risk assessment factor into a target model to obtain a risk assessment value of an asset to be processed, where the target model is obtained by training multiple sets of training samples, and each set of training samples includes a historical risk assessment value risk assessment factor and a historical risk assessment value;
transfer unit 40 is configured to determine a risk assessment value threshold, and transfer the asset to be processed with the risk assessment value greater than or equal to the risk assessment value threshold to the target customer group.
According to the asset processing device provided by the embodiment of the application, through the acquisition unit 10, a plurality of assets of a target enterprise are acquired, the life cycle of each asset is determined, and whether the life cycle is greater than or equal to a life cycle threshold value is judged; a determining unit 20 that determines an asset whose life cycle is equal to or greater than a life cycle threshold as an asset to be processed, and acquires a risk assessment factor of the asset to be processed; the input unit 30 inputs the risk assessment factors into a target model to obtain a risk assessment value of the asset to be processed, wherein the target model is trained by a plurality of groups of training samples, and each group of training samples comprises a historical risk assessment value risk assessment factor and a historical risk assessment value; the transfer unit 40 determines a risk evaluation value threshold, transfers the to-be-processed asset with the risk evaluation value greater than or equal to the risk evaluation value threshold to the target customer group, solves the problem of inaccurate risk evaluation value in the asset processing scheme in the related art, and inputs the risk evaluation factor into the target model to obtain the risk evaluation value by training the target model and extracting the risk evaluation factor of the to-be-processed asset, thereby achieving the effect of improving the accuracy of the risk evaluation value.
Optionally, in the asset processing device provided in the embodiment of the present application, the determining unit 20 includes: the extraction module is used for extracting a plurality of asset correlation factors from the assets to be processed and calculating the pearson correlation coefficient of each asset correlation factor and the risk evaluation value; the judging module is used for judging whether the pearson correlation coefficient is larger than or equal to a correlation coefficient threshold value for each asset correlation factor; the computing module is used for computing the saliency evaluation value of the asset correlation factor based on the pearson correlation coefficient under the condition that the pearson correlation coefficient is larger than or equal to the correlation coefficient threshold; and the first determining module is used for determining the asset correlation factor with the saliency evaluation value being greater than or equal to the saliency evaluation value threshold as the risk evaluation factor of the asset to be processed.
Optionally, in the asset processing device provided in the embodiment of the present application, the extracting module includes: a first determination submodule for determining a type of the asset to be processed, wherein the type at least comprises one of the following: overtime loans, debt property resisting, account sales; and the extraction sub-module is used for extracting a plurality of asset correlation factors corresponding to the types from the assets to be processed based on the types.
Optionally, in the asset processing device provided in the embodiment of the present application, the calculation module includes: a second determination submodule for determining a sample number of the asset-related factors; the first calculating sub-module is used for calculating the difference value between the number of samples and a first preset value, calculating a first open square value of the difference value, and calculating the product of the pearson correlation coefficient and the first open square value to obtain a target product value; the second computing sub-module is used for computing the square value of the pearson correlation coefficient, computing the difference value between a second preset value and the square value, and computing a second open square value of the difference value; and the third calculation sub-module is used for calculating the ratio of the target product value to the second open square value to obtain the saliency assessment value of the asset correlation factor.
Optionally, in the asset processing device provided in the embodiment of the present application, the object model is obtained by: acquiring a history asset processing record, and extracting a history risk evaluation value risk evaluation factor and a history risk evaluation value of each history asset from the history asset processing record; determining a historical risk evaluation value risk evaluation factor and a historical risk evaluation value of each historical asset as a group of training samples to obtain a plurality of groups of training samples; and training the neural network model through a plurality of groups of training samples to obtain a target model.
Optionally, in the asset processing device provided in the embodiment of the present application, the device further includes: the computing unit is used for determining a target risk evaluation value of the target customer group for evaluating the asset to be processed and computing an evaluation value difference value between the target risk evaluation value and the risk evaluation value; the judging unit is used for judging whether the difference value of the evaluation value is larger than or equal to a difference value threshold value; the storage unit is used for storing the transfer scheme of the asset to be processed into the sample database under the condition that the difference value of the evaluation values is smaller than the difference value threshold value; the newly added training sample determining unit is used for determining a risk evaluation factor and a target risk evaluation value of the asset to be processed as newly added training samples under the condition that the difference value of the evaluation values is larger than or equal to a difference value threshold value; the adding unit is used for adding the newly added training samples to a plurality of groups of training samples to obtain updated groups of training samples, and training the neural network model based on the updated groups of training samples to obtain an updated target model.
Optionally, in the asset processing device provided in the embodiment of the present application, the transfer unit 40 includes: the second determining module is used for determining an evaluation value range to which the risk evaluation value belongs and determining a target customer group and an assignment channel based on the evaluation value range; and the transfer module is used for publishing asset transfer information to the target client group and transferring the to-be-processed asset to the target client group through a transfer channel.
The asset processing device includes a processor and a memory, the above-described acquisition unit 10, determination unit 20, input unit 30, transfer unit 40, and the like are stored in the memory as program units, and the above-described program units stored in the memory are executed by the processor to realize the corresponding functions.
The processor includes a kernel, and the kernel fetches the corresponding program unit from the memory. The kernel may be provided with one or more kernel parameters to improve the accuracy of the risk assessment value.
The memory may include volatile memory, random Access Memory (RAM), and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM), among other forms in computer readable media, the memory including at least one memory chip.
Embodiments of the present invention provide a computer-readable storage medium having stored thereon a program that, when executed by a processor, implements an asset processing method.
The embodiment of the invention provides a processor, which is used for running a program, wherein the asset processing method is executed when the program runs.
Fig. 4 is a schematic diagram of an electronic device provided according to an embodiment of the present application. As shown in fig. 4, the electronic device 401 includes a processor, a memory, and a program stored on the memory and executable on the processor, and the processor implements the following steps when executing the program: acquiring a plurality of assets of a target enterprise, determining a life cycle of each asset, and judging whether the life cycle is greater than or equal to a life cycle threshold value; determining an asset with a life cycle greater than or equal to a life cycle threshold as an asset to be processed, and acquiring a risk assessment factor of the asset to be processed; inputting a risk assessment factor into a target model to obtain a risk assessment value of an asset to be processed, wherein the target model is trained by a plurality of groups of training samples, and each group of training samples comprises a historical risk assessment value and a historical risk assessment value; and determining a risk assessment value threshold, and transferring the assets to be processed with the risk assessment value greater than or equal to the risk assessment value threshold to a target customer group. The device herein may be a server, PC, PAD, cell phone, etc.
The present application also provides a computer program product adapted to perform, when executed on a data processing device, a program initialized with the method steps of: acquiring a plurality of assets of a target enterprise, determining a life cycle of each asset, and judging whether the life cycle is greater than or equal to a life cycle threshold value; determining an asset with a life cycle greater than or equal to a life cycle threshold as an asset to be processed, and acquiring a risk assessment factor of the asset to be processed; inputting a risk assessment factor into a target model to obtain a risk assessment value of an asset to be processed, wherein the target model is trained by a plurality of groups of training samples, and each group of training samples comprises a historical risk assessment value and a historical risk assessment value; and determining a risk assessment value threshold, and transferring the assets to be processed with the risk assessment value greater than or equal to the risk assessment value threshold to a target customer group.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, etc., such as Read Only Memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.
Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises an element.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and changes may be made to the present application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc. which are within the spirit and principles of the present application are intended to be included within the scope of the claims of the present application.
Claims (10)
1. A method of asset processing, comprising:
acquiring a plurality of assets of a target enterprise, determining a life cycle of each asset, and judging whether the life cycle is greater than or equal to a life cycle threshold value;
determining an asset with a life cycle greater than or equal to the life cycle threshold as an asset to be processed, and acquiring a risk assessment factor of the asset to be processed;
inputting the risk assessment factors into a target model to obtain a risk assessment value of the asset to be processed, wherein the target model is trained by a plurality of groups of training samples, and each group of training samples comprises a historical risk assessment value and a historical risk assessment value;
and determining a risk evaluation value threshold, and transferring the assets to be processed, of which the risk evaluation value is greater than or equal to the risk evaluation value threshold, to a target customer group.
2. The method of claim 1, wherein obtaining a risk assessment factor for the asset to be processed comprises:
extracting a plurality of asset correlation factors from the assets to be processed, and calculating pearson correlation coefficients of each asset correlation factor and the risk assessment value;
for each asset correlation factor, determining whether the pearson correlation coefficient is greater than or equal to a correlation coefficient threshold;
Calculating a significance evaluation value of the asset correlation factor based on the pearson correlation coefficient if the pearson correlation coefficient is greater than or equal to the correlation coefficient threshold;
and determining an asset correlation factor with the saliency assessment value being greater than or equal to a saliency assessment value threshold as a risk assessment factor of the asset to be processed.
3. The method of claim 2, wherein extracting a plurality of asset-related factors from the asset to be processed comprises:
determining a type of the asset to be processed, wherein the type includes at least one of: overtime loans, debt property resisting, account sales;
and extracting a plurality of asset-related factors corresponding to the type from the assets to be processed based on the type.
4. The method of claim 2, wherein calculating a significance evaluation value for the asset-correlation factor based on the pearson correlation coefficient comprises:
determining a sample number of the asset correlation factors;
calculating a difference value between the number of samples and a first preset value, calculating a first open square value of the difference value, and calculating a product of the pearson correlation coefficient and the first open square value to obtain a target product value;
Calculating the square value of the pearson correlation coefficient, calculating the difference value between a second preset value and the square value, and calculating a second open square value of the difference value;
and calculating the ratio of the target product value to the second square value to obtain the saliency assessment value of the asset correlation factor.
5. The method of claim 1, wherein the target model is derived by:
acquiring a history asset processing record, and extracting a history risk evaluation value and a history risk evaluation value of each history asset from the history asset processing record;
determining a historical risk assessment value and a historical risk assessment value of each historical asset as a group of training samples to obtain a plurality of groups of training samples;
and training a neural network model through the plurality of groups of training samples to obtain the target model.
6. The method of claim 5, wherein after transferring the pending asset having the risk assessment value greater than or equal to the risk assessment value threshold to a target customer group, the method further comprises:
determining a target risk assessment value of the target customer group for assessing the asset to be processed, and calculating an assessment value difference value between the target risk assessment value and the risk assessment value;
Judging whether the difference value of the evaluation values is larger than or equal to a difference value threshold value or not;
storing the transfer scheme of the asset to be processed in a sample database under the condition that the evaluation value difference is smaller than the difference threshold;
determining a risk evaluation factor and the target risk evaluation value of the asset to be processed as a new training sample under the condition that the evaluation value difference value is greater than or equal to the difference value threshold;
and adding the newly added training samples to the multiple groups of training samples to obtain updated multiple groups of training samples, and training a neural network model based on the updated multiple groups of training samples to obtain an updated target model.
7. The method of claim 1, wherein transferring the asset to be processed having the risk assessment value greater than or equal to the risk assessment value threshold to a target customer group comprises:
determining an evaluation value range to which the risk evaluation value belongs, and determining a target customer group and a transfer channel based on the evaluation value range;
and publishing asset transfer information to the target client group, and transferring the to-be-processed asset to the target client group through the transfer channel.
8. An asset processing device, comprising:
The system comprises an acquisition unit, a storage unit and a control unit, wherein the acquisition unit is used for acquiring a plurality of assets of a target enterprise, determining the life cycle of each asset and judging whether the life cycle is greater than or equal to a life cycle threshold value or not;
the determining unit is used for determining the asset with the life cycle being more than or equal to the life cycle threshold as an asset to be processed and acquiring a risk assessment factor of the asset to be processed;
the input unit is used for inputting the risk assessment factors into a target model to obtain a risk assessment value of the asset to be processed, wherein the target model is trained by a plurality of groups of training samples, and each group of training samples comprises a historical risk assessment value risk assessment factor and a historical risk assessment value;
and the transfer unit is used for determining a risk evaluation value threshold and transferring the assets to be processed with the risk evaluation value greater than or equal to the risk evaluation value threshold to a target customer group.
9. A non-volatile storage medium, characterized in that the non-volatile storage medium comprises a stored program, wherein the program, when run, controls a device in which the non-volatile storage medium is located to perform the asset processing method of any one of claims 1 to 7.
10. An electronic device comprising one or more processors and a memory for storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the asset processing method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311119130.2A CN117273945A (en) | 2023-08-31 | 2023-08-31 | Asset processing method and device, storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311119130.2A CN117273945A (en) | 2023-08-31 | 2023-08-31 | Asset processing method and device, storage medium and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117273945A true CN117273945A (en) | 2023-12-22 |
Family
ID=89209577
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311119130.2A Pending CN117273945A (en) | 2023-08-31 | 2023-08-31 | Asset processing method and device, storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117273945A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118037046A (en) * | 2024-02-21 | 2024-05-14 | 广州番禺职业技术学院 | Asset data processing method and system based on history record |
-
2023
- 2023-08-31 CN CN202311119130.2A patent/CN117273945A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118037046A (en) * | 2024-02-21 | 2024-05-14 | 广州番禺职业技术学院 | Asset data processing method and system based on history record |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Di Maggio et al. | Invisible primes: Fintech lending with alternative data | |
| Li et al. | The impact of FinTech start-ups on incumbent retail banks’ share prices | |
| Altamuro et al. | The financial reporting of fair value based on managerial inputs versus market inputs: evidence from mortgage servicing rights | |
| Harford et al. | Refinancing risk and cash holdings | |
| Doblas-Madrid et al. | Sharing information in the credit market: Contract-level evidence from US firms | |
| García‐Teruel et al. | Supplier financing and earnings quality | |
| Crouzet | Credit disintermediation and monetary policy | |
| US20080021813A1 (en) | Method for scoring accounts for retention and marketing accounts based on retention and profitability | |
| Gupta | Financial determinants of corporate credit ratings: An Indian evidence | |
| Lu et al. | Fintech and the future of financial service: A literature review and research agenda | |
| Rey et al. | Earnings management and debt maturity: Evidence from Italy | |
| Biswas et al. | Automated credit assessment framework using ETL process and machine learning | |
| CN116450951A (en) | Service recommendation method and device, storage medium and electronic equipment | |
| Duarte et al. | Credit risk, owner liability, and bank loan maturities during the global financial crisis | |
| CN116739750A (en) | Lender default prediction method, lender default prediction device, lender default prediction equipment and lender default prediction medium | |
| Tercero‐Lucas | Nonstandard monetary policies and bank profitability: The case of Spain | |
| KR102139938B1 (en) | System for selection of companies subject to credit guarantees based on credit guarantees propensity analysis | |
| CN117273945A (en) | Asset processing method and device, storage medium and electronic equipment | |
| Bertola et al. | Dealer pricing of consumer credit | |
| Klimowicz et al. | Concept of peer-to-peer lending and application of machine learning in credit scoring | |
| Lara‐Rubio et al. | Promoting entrepreneurship at the base of the social pyramid via pricing systems: A case study | |
| US10699335B2 (en) | Apparatus and method for total loss prediction | |
| Chong et al. | Bank loans, trade credits, and borrower characteristics: Theory and empirical analysis | |
| Smith et al. | Countercyclical capital regime revisited: Tests of robustness | |
| Ahlawat | Evaluation of mortgage default characteristics using Fannie Mae’s loan performance data |
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 |