Asset evaluation method and system

Abstract

The invention discloses an asset assessment method and system. The method comprises the steps of obtaining first asset data of a target customer in a first time period; determining a first rate evaluation value according to the first asset data; acquiring a plurality of second asset data of which the data type is the same as the data type included in the first asset data in the historical database; determining a second rate evaluation value according to the plurality of second asset data; determining a target rate of return evaluation value according to the first rate of return evaluation value and the second rate of return evaluation value; determining a target return amount evaluation value and a target cash flow evaluation value according to the target return rate evaluation value and the first asset data; determining a target evaluation result according to the target return rate evaluation value, the target return amount evaluation value and the target cash flow evaluation value; and generating and outputting an evaluation report according to the target evaluation result. According to the invention, the efficiency and accuracy of asset assessment can be improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to an asset evaluation method and system. Background Art

[0002] Personal loan non-performing assets refer to loans formed when the borrower is unable to repay the principal and interest of the loan on time as per the original loan agreement, or when there are signs that the borrower is unlikely to repay the principal and interest of the loan on time as per the original loan agreement. In order to reduce the economic losses caused by non-performing assets, it is necessary to value the non-performing assets, so as to reasonably estimate the borrower's repayment situation in the future, so that financial institutions can formulate effective asset management strategies in advance.

[0003] Traditional asset valuation methods usually rely on manual experience and subjective judgment, and have problems such as low efficiency, poor accuracy, and susceptibility to human factors. In addition, applicable valuation models are often limited to static valuations, and are unable to conduct accurate non-performing asset valuations based on the differences in individual loans of different target customers and market changes. It is difficult to meet the needs for accurate and efficient asset valuations for differentiated individual loan non-performing assets. Summary of the invention

[0004] The present application provides an asset evaluation method and system, wherein a server obtains the first asset data of a target customer in a first period; then, a first collection rate evaluation value is determined based on the first asset data; then, a plurality of second asset data in a historical database containing the same data type as the first asset data is obtained; secondly, a second collection rate evaluation value is determined based on the plurality of second asset data; thirdly, a target collection rate evaluation value is determined based on the first collection rate evaluation value and the second collection rate evaluation value; and, a target collection amount evaluation value and a target cash flow evaluation value are determined based on the target collection rate evaluation value and the first asset data; thirdly, a target evaluation result is determined based on the target collection rate evaluation value, the target collection amount evaluation value and the target cash flow evaluation value; finally, an evaluation report is generated and output based on the target evaluation result. The target collection rate evaluation value in a future period is determined comprehensively through the customer's asset data and the historical database, and then the target evaluation result is determined. The asset evaluation method is adjusted in combination with market changes, which is conducive to improving the accuracy and efficiency of asset evaluation.

[0005] In a first aspect, an embodiment of the present application provides an asset evaluation method, which is applied to a server of an asset evaluation system, and the method comprises the following steps:

[0006] Acquire first asset data of a target customer in a first period of time, wherein the first asset data includes loan information, repayment information, and property information;

[0007] Determine a first collection rate evaluation value based on the first asset data, where the first collection rate evaluation value refers to a prediction index value that independently evaluates the repayment ability of the target customer in the second period from the collection rate index dimension;

[0008] Acquire a plurality of second asset data in a historical database, the data type of which is the same as the data type included in the first asset data, the plurality of second asset data corresponding to a historical user set, the historical user set including at least one user;

[0009] Determine a second repayment rate evaluation value according to the plurality of second asset data, wherein the second repayment rate evaluation value refers to a quantitative index value for comprehensively evaluating the repayment ability of the at least one user in a historical period from the repayment rate index dimension;

[0010] Determine a target collection rate evaluation value according to the first collection rate evaluation value and the second collection rate evaluation value; and determine a target collection amount evaluation value and a target cash flow evaluation value according to the target collection rate evaluation value and the first asset data;

[0011] Determine a target evaluation result based on the target collection rate evaluation value, the target collection amount evaluation value and the target cash flow evaluation value;

[0012] An evaluation report is generated and outputted according to the target evaluation results.

[0013] In a second aspect, an embodiment of the present application provides an asset evaluation system, the system comprising:

[0014] A first acquisition module is used to acquire first asset data of a target customer within a first period of time, wherein the first asset data includes loan information, repayment information and property information;

[0015] A first evaluation module, configured to determine a first collection rate evaluation value according to the first asset data, wherein the first collection rate evaluation value refers to a prediction index value for independently evaluating the repayment ability of the target customer in the second period from the collection rate index dimension;

[0016] A second acquisition module is used to acquire a plurality of second asset data in a historical database, the data type of which is the same as the data type included in the first asset data, the plurality of second asset data corresponding to a historical user set, the historical user set including at least one user;

[0017] A second evaluation module, configured to determine a second repayment rate evaluation value based on the plurality of second asset data, wherein the second repayment rate evaluation value refers to a quantitative index value for comprehensively evaluating the repayment ability of the at least one user in a historical period from a repayment rate index dimension;

[0018] A first determination module is used to determine a target collection rate evaluation value according to the first collection rate evaluation value and the second collection rate evaluation value; and to determine a target collection amount evaluation value and a target cash flow evaluation value according to the target collection rate evaluation value and the first asset data;

[0019] A second determination module is used to determine a target evaluation result according to the target collection rate evaluation value, the target collection amount evaluation value and the target cash flow evaluation value;

[0020] The output module is used to generate and output an evaluation report based on the target evaluation results.

[0021] In a third aspect, an embodiment of the present application provides an electronic device, comprising a processor, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the program includes instructions for executing the steps in the first aspect of the embodiment of the present application.

[0022] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program / instruction stored thereon, which is executed by a processor to implement the steps of the method described in the first aspect above.

[0023] It can be seen that in the embodiment of the present application, the server first obtains the first asset data of the target customer within the first time period, and the first asset data includes loan information, repayment information and property information; then, a first collection rate assessment value is determined based on the first asset data; then, a plurality of second asset data containing the same data type as the first asset data in the historical database is obtained; secondly, a second collection rate assessment value is determined based on the plurality of second asset data; again, a target collection rate assessment value is determined based on the first collection rate assessment value and the second collection rate assessment value; and, a target collection amount assessment value and a target cash flow assessment value are determined based on the target collection rate assessment value and the first asset data; again, a target assessment result is determined based on the target collection rate assessment value, the target collection amount assessment value and the target cash flow assessment value; finally, an assessment report is generated and output based on the target assessment result. Compared with the existing personal loan non-performing asset assessment scheme that is affected by subjective factors and cannot adapt to individual differences and market changes, it can solve subjective influences and eliminate the influence of individual differences based on historical databases and adjustable asset assessment methods, thereby improving the accuracy and efficiency of asset assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0025] Figure 1 It is a flowchart of the steps of an asset evaluation method provided by an embodiment of the present application;

[0026] Figure 2 It is an overall flow chart of an asset data acquisition method provided by an embodiment of the present application;

[0027] Figure 3 It is a schematic diagram of a display interface of an asset evaluation system provided in an embodiment of the present application;

[0028] Figure 4 This is a schematic diagram of an output interface of a target evaluation result provided in an embodiment of the present application;

[0029] Figure 5 It is a system architecture diagram of an asset evaluation system provided in an embodiment of the present application;

[0030] Figure 6 It is a structural block diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0031] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0032] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0033] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0034] Currently, existing asset appraisal schemes mainly rely on limited appraisal models and manual experience. They are unable to conduct accurate and efficient asset appraisals on different types of asset packages of different customers based on the differences in individual loans of different customers and market changes. It is difficult to meet the needs of efficient and accurate asset appraisals for differentiated individual loan non-performing assets.

[0035] In view of the above problems, an embodiment of the present application provides an asset evaluation method and system, which will be described in detail below in conjunction with the accompanying drawings.

[0036] See also Figure 1 , Figure 1 is a flowchart of the steps of an asset evaluation method provided in an embodiment of the present application, which is applied to a server of an asset evaluation system, such as Figure 1 As shown, the method comprises the following steps:

[0037] Step S110, obtaining first asset data of a target customer in a first time period.

[0038] Among them, the first asset data includes loan information, repayment information and property information.

[0039] Among them, the loan information specifically includes the loan amount, loan type, such as personal loan, mortgage, car loan, etc., interest rate, loan term, loan issuance date, repayment method, such as equal installments of principal and interest, equal installments of principal, etc., loan status, such as normal, overdue, settled, etc., borrower information, including name, ID number, contact information, etc.

[0040] Among them, the repayment information includes the repayment plan, that is, the repayment amount and repayment date of each period, the actual repayment record, the overdue record, including the number of overdue times, the overdue amount and the overdue days, the early repayment information, including whether there is an early repayment, the amount and date of the early repayment, the remaining principal, that is, the current unpaid loan principal, etc.

[0041] Among them, property information includes property type, such as immovable property (real estate), movable property (vehicles, equipment, etc.), property valuation, property ownership certificate, such as real estate certificate, vehicle registration certificate, etc., mortgage information, including whether there is a mortgage, detailed information on the mortgaged property, insurance information, including whether the property is insured, the insurance company and policy number, etc.

[0042] In a possible embodiment, obtaining the first asset data of the target customer in the first period includes:

[0043] Acquiring data on the non-performing asset package of the target customer within the first period;

[0044] The non-performing asset package data is processed to obtain the first asset data.

[0045] Among them, the data of the non-performing asset package is processed, including parsing, comparing and batch importing the data of the non-performing asset package. Specifically, the parsing includes identifying the format of the asset package data (such as CSV, Excel, JSON, etc.), mapping the fields in the asset package with the fields in the system, ensuring that the data can be correctly imported, performing data cleaning, processing missing values, duplicate data and outliers, ensuring the accuracy and completeness of the data, and standardizing the data from different sources for subsequent comparison and analysis; and,

[0046] The comparison includes comparing the newly imported data with the historical data, identifying changes and trends, checking the consistency of the new data with the existing data in the system to ensure there are no conflicts or errors, and identifying possible abnormal data, such as unreasonable loan amounts, overdue records, etc.; and,

[0047] The batch import includes data verification before importing to ensure that all data meets system requirements, using the batch import tool provided by the system to import the parsed data into the database, recording logs during the import process, including successful import records and failed records, to facilitate subsequent troubleshooting, and backing up existing data before importing to prevent data loss or damage.

[0048] It can be seen that after obtaining the asset package data of the target customer, the asset appraisal system parses, compares and batch imports the asset package data to obtain the first asset data. The first asset data includes loan information, repayment information and property information, so that a preliminary asset appraisal can be performed based on the first asset data, which is conducive to an in-depth asset appraisal based on the first asset data and the historical database, so as to obtain the target evaluation results and improve the accuracy of the asset appraisal.

[0049] Step S120: determining a first collection rate assessment value based on the first asset data.

[0050] In a possible embodiment, the first collection rate evaluation value includes the collection rate evaluation value of the target customer in each period within the first collection period; and determining the first collection rate evaluation value according to the first asset data includes:

[0051] Obtaining an asset adjustment factor corresponding to the first asset data, wherein the asset adjustment factor refers to an input parameter used in a Monte Carlo simulation algorithm or a coefficient of certain assumptions in a simulation process; and,

[0052] Determine the number of simulations according to the first payment collection period;

[0053] Adjusting the Monte Carlo simulation algorithm according to the asset adjustment factor and the number of simulations;

[0054] The first asset data is subjected to feature prediction according to the Monte Carlo simulation algorithm to obtain the first collection rate evaluation value.

[0055] Among them, the first collection rate assessment value refers to the predictive index value that independently evaluates the repayment ability of the target customer in the second time period from the collection rate index dimension; and the first collection period refers to the expected collection period of the target customer in the second time period determined based on the first asset data.

[0056] It can be understood that the Monte Carlo algorithm evaluates non-performing assets based on the Monte Carlo model. The prominent points are random sampling and the establishment of a mathematical and statistical model for asset evaluation to describe the changing patterns and uncertainties of asset values. For different asset selling institutions, such as banks, consumer finance, small loans, etc., according to different asset forms, such as products, debt distribution, etc., different random ranges and preset repayment anchor points are innovatively adapted. After a specified number of random simulations, the target repayment amount assessment value and the repayment rate assessment value for each period within the first repayment period for the target customer in the second period in the future are obtained, thereby obtaining the first repayment rate assessment value, which includes the repayment rate assessment values ​​of multiple periods.

[0057] Among them, according to the Monte Carlo model, not only the first collection rate evaluation value can be determined, but also the total asset value can be preliminarily determined, that is, the total amount of collection expected from the target customers in the second period.

[0058] In a possible embodiment, determining the first payment assessment value and the total asset value according to the Monte Carlo model includes:

[0059] Obtain multiple asset types contained in the bad asset package data;

[0060] Layering the non-performing asset packages according to the multiple asset form types to obtain multiple sub-level data;

[0061] Determine the total number of simulations according to the first payment collection period;

[0062] In each round of total simulation, according to the number of random sub-simulations, a random collection rate is configured for each sub-level data through the Monte Carlo model in each round of sub-simulation, and the random collection rate is within a preset collection rate range;

[0063] Determine multiple simulated values ​​of the asset package after the number of sub-simulations according to the random repayment rate and the assets corresponding to each of the sub-level data;

[0064] Determine the target repayment amount corresponding to the current repayment period according to the multiple simulated values;

[0065] Determine multiple target repayment amounts after a total number of simulations; and obtain a target repayment amount corresponding to each period according to the multiple target repayment amounts;

[0066] The first repayment rate evaluation value is determined based on the target repayment amount and the total amount to be repaid corresponding to each period; and the total asset value is determined based on the multiple target repayment amounts.

[0067] In each round of simulation, the Monte Carlo model is used to determine the estimated value of the repayment rate and the target repayment amount corresponding to the current repayment period. The specific formula is as follows:

[0068]

[0069] Among them, P refers to the target repayment amount of this round of simulation, γ refers to the adjustment factor, N refers to the number of sub-simulations, n = 1 refers to the first sub-simulation, T refers to the number of asset package layers, t = 1 refers to the first layer of assets, A t refers to the t-th layer of assets in the asset package hierarchy, R tn It refers to the random repayment rate corresponding to the t-th layer of assets in the asset package layering.

[0070] Exemplarily, the total amount to be repaid of the asset package is 1 million yuan, which is divided into 4 layers according to different asset types. The assets of the 1st to 4th layers are 100,000 yuan, 200,000 yuan, 300,000 yuan, and 400,000 yuan respectively. The first repayment period can be 5 periods, so the total number of simulations is 5 times, and the number of random sub-simulations N can be 2 times. In the first round of total simulation, the first sub-simulation can assign four random repayment rates to the 4 levels of asset packages, which can be 5%, 3%, 7%, and 10%, respectively. The repayment amount of the first sub-simulation of the asset package is 10×5%+20×3%+30×7%+40×10%=72,000 yuan; the random repayment rates assigned in the second sub-simulation can be 8%, 9%, 4%, and 6%, respectively. The repayment amount of the second sub-simulation is 62,000 yuan. The average value is calculated to obtain an assessed value of the repayment amount for the first period of 67,000 yuan, and then the assessed value of the repayment rate for the first period is 6.7%. Similarly, after the total number of simulations, the repayment amount and repayment rate for each period can be obtained, and then the first repayment rate valuation and total asset value can be determined.

[0071] Furthermore, the adjustment factor can be a pre-set value and stored in the server, which is automatically called when the first collection rate assessment value is determined, and supports users to modify it at any time; and, after obtaining the preliminary total asset value, considering the impact of risk factors such as market conditions, industry trends, and policy changes on the collection of asset packages in the second period in the future, the Monte Carlo simulation design supports the use of adjustment factors to adjust the final pricing based on the impact of macroeconomics and industry policies.

[0072] It can be seen that in this embodiment, the server adjusts the Monte Carlo model by adjusting the factor and the number of simulations, and processes the first asset data according to the adjusted Monte Carlo model, stratifies the asset data, and assigns a random collection rate to each layer of assets within a preset range. After the number of simulations, the first collection rate assessment value is obtained, and the preliminary total asset value can be obtained. In addition, since the Monte Carlo model supports adjusting the model by adjusting factors, it can conduct timely and accurate asset appraisal of individual loan non-performing asset packages in combination with market changes, which is conducive to reducing the market lag of asset appraisal and the impact of individual differences, and improving the accuracy of appraisal.

[0073] Step S130, obtaining a plurality of second asset data in a historical database, the data type of which is the same as the data type included in the first asset data, wherein the plurality of second asset data corresponds to a historical user set, and the historical user set includes at least one user.

[0074] In a possible embodiment, the similarity between each of the second asset data and the first asset data exceeds a preset threshold; the acquisition history database includes a plurality of second asset data of the same data type as the first asset data, including:

[0075] Acquire a first data type included in the first asset data;

[0076] Acquire a plurality of historical asset data in the historical database, the data type of which is the same as the first data type;

[0077] Combining the first asset data with the plurality of historical asset data to form an asset package measurement sample;

[0078] Using an adversarial verification algorithm to perform similarity evaluation on the asset package measurement samples, and obtain the similarity between each of the historical asset data and the first asset data;

[0079] The plurality of historical asset data whose similarity exceeds the preset threshold is used as the plurality of second asset data.

[0080] Among them, the data types include numerical types and field types. The numerical types include integers, floating point numbers, strings, date / times, Boolean values, binary data, etc.; the field types refer to multiple fields corresponding to the loan information, repayment information and property information included in the first asset data, such as name, age, amount of debt, etc.

[0081] It is understandable that the data of the non-performing asset package has been desensitized, and it is difficult to match the identity of the borrower in the asset package using methods such as ID card number and mobile phone number. However, the asset package will provide basic information of the customer such as age, place of origin, industry, position, education level, etc., as well as behavioral data such as the customer's borrowing behavior, repayment behavior, and poor situation. The historical database has abundant overdue customer asset data, as well as corresponding basic data and label variable features under dozens of subject categories. Using a machine learning-based adversarial verification model, the information of the asset package borrowers and historical asset data on the proposed variable features is used to output multiple customers similar to the asset package borrowers, so as to predict the target customers' repayment situation in a certain period of time in the future based on the historical repayment situation of these customers.

[0082] In a possible embodiment, the output is a plurality of customers similar to the borrowers of the asset package, including:

[0083] Acquire a plurality of historical asset data in a historical database, the data type of which is the same as the data type included in the first asset data;

[0084] Performing feature extraction on the first asset data;

[0085] training an adversarial verification model based on the historical database and the first asset data;

[0086] Inputting the first asset data into the trained adversarial verification model to obtain the similarity between the asset data of each historical user and the first asset data;

[0087] Output the multiple historical asset data whose similarity exceeds the preset similarity.

[0088] The similarity comparison can be determined by obtaining data features of multiple historical asset data, comparing them with the data features of the first asset data, and evaluating the similarity. Specifically, the similarity evaluation can be completed by calculating the similarity metric between the features (such as cosine similarity, Euclidean distance, etc.).

[0089] It can be seen that in this embodiment, by calling the historical database and using the adversarial verification model to compare the data features of the first asset data with the data features of multiple historical asset data of multiple users in the historical database; and performing data type comparison, a plurality of historical asset data with exactly the same data type as the first asset data and a high degree of data similarity are obtained, and then a plurality of second asset data are determined, so that the target customer's collection rate assessment value in the second time period can be predicted based on the historical collection situation of the plurality of second asset data, thereby realizing the evaluation of the asset package in combination with historical similar customer data, which is conducive to dealing with the problem of inaccurate evaluation caused by differences in personal loans and improving the accuracy and efficiency of asset evaluation.

[0090] Step S140, determining a second payment collection rate evaluation value based on the plurality of second asset data.

[0091] In a possible embodiment, determining the second payment collection rate evaluation value according to the plurality of second asset data includes:

[0092] Determine multiple historical repayment amounts and multiple historical total amounts to be repaid for each user within the historical period according to multiple repayment information in the multiple second asset data;

[0093] Determine the historical repayment rate of each user in each period during the historical period according to the multiple historical repayment amounts and the multiple historical total amounts to be repaid;

[0094] Determine the historical average repayment rate for each period according to the multiple historical repayment rates corresponding to the same period in the multiple second asset data;

[0095] Determine the first repayment period of the target customer within the second period according to the first asset data;

[0096] The multiple historical average collection rates corresponding to the collection period and the first collection period are determined as the second collection rate evaluation value.

[0097] The duration of the historical period includes the duration of the first period and the duration of the second period.

[0098] It can be understood that if the data features of the multiple second asset data are highly similar to those of the first asset data and the data types are exactly the same, then the multiple historical total amounts to be repaid in the multiple second asset data are similar to or the same as the total amounts to be repaid of the target customers, and the multiple historical repayment periods are similar to or the same as the total repayment periods of the target customers.

[0099] Exemplarily, the total amount of the target customer's outstanding repayments may be RMB 1 million, the total number of repayment periods may be 36, and the repayments are expected to be paid in 6 periods each year. The target customer has already paid back 3 periods in the first period of 2 years, totaling RMB 200,000. The second period may be a preset value of 3 years. Then, the multiple second asset data may include the second asset data of two users, and the total amount of outstanding repayments may be RMB 1 million and RMB 1 million respectively. The total number of repayment periods is also 36, and the repayments are also expected to be paid in 6 periods each year. Therefore, the repayment amount of each user in each period within 36 periods is determined according to the repayment information of each user, and the repayment rate of each period is obtained. The repayment rates of the corresponding periods of the two users are averaged to obtain the historical average repayment rate of each period; and, excluding the 3 periods of arrears that the target customer has already paid, starting from the historical average repayment rate of the 4th to the 12th period, the second repayment rate evaluation value is formed, and the second repayment rate evaluation value is used as the repayment rate evaluation value of each period of the target customer starting from the second period.

[0100] It can be seen that in this embodiment, the server obtains the historical asset data of multiple users in the historical database that are highly similar to the first asset data of the target customer, obtains multiple second asset data, and determines the user's repayment amount in each period of the historical repayment period based on the multiple historical repayment information in the multiple second asset data, and then obtains the average repayment rate for each period, and then determines the number of periods to be repaid for the target customer in the future second period based on the repayment information of the target customer in the first period, so as to use the multiple historical average repayment rates corresponding to the number of periods to be repaid in the second period as the target customer's repayment rate evaluation value in the second period. It is realized that the repayment situation of the target customer in the future period is simulated based on similar historical user asset data, which is conducive to asset evaluation based on the differences of different personal loans and improves the accuracy of asset evaluation.

[0101] Step S150, determining a target collection rate evaluation value based on the first collection rate evaluation value and the second collection rate evaluation value; and determining a target collection amount evaluation value and a target cash flow evaluation value based on the target collection rate evaluation value and the first asset data.

[0102] In a possible embodiment, determining a target collection rate evaluation value according to the first collection rate evaluation value and the second collection rate evaluation value includes:

[0103] Obtaining an evaluation difference between the first payment collection rate evaluation value and the second payment collection rate evaluation value;

[0104] Detecting whether the evaluation difference is within a preset difference range;

[0105] If it is detected that the evaluation difference is within the preset difference range, then obtaining a first weight value corresponding to the first collection rate evaluation value; and obtaining a second weight value corresponding to the second collection rate evaluation value; and,

[0106] The target collection rate evaluation value is obtained by weightedly summing the first collection rate evaluation value and the second collection rate evaluation value according to the first weight value and the second weight value.

[0107] In a possible embodiment, the method further includes:

[0108] If it is detected that the evaluation difference is not within the preset difference range, updating the first collection rate evaluation value according to the first asset data; and,

[0109] The target collection rate evaluation value is obtained by weightedly summing the updated first collection rate evaluation value and the second collection rate evaluation value according to the first weight value and the second weight value.

[0110] Among them, the first collection rate evaluation value and the second collection rate evaluation value both include the collection rate evaluation value of each period within the expected collection period of the target customer in the second time period, except that the second collection rate evaluation value selects the historical average collection rate of multiple users, but the periods are corresponding; and the evaluation difference includes the collection rate evaluation difference for each period.

[0111] Among them, the target collection rate evaluation value is obtained by weightedly adding the first collection rate evaluation value and the second collection rate evaluation value according to the first weight value and the second weight value, including: for the first collection rate evaluation value and the second collection rate evaluation value of the corresponding period, the first collection rate evaluation value and the second collection rate evaluation value are weightedly added according to the first weight value and the second weight value to obtain the collection rate evaluation value of the corresponding period; the target collection rate evaluation value is obtained according to the collection rate evaluation values ​​of multiple periods.

[0112] It is understandable that when the evaluation difference is not within the preset difference range, it means that the first repayment rate evaluation value and / or the second repayment rate evaluation value are abnormal. Since the second repayment rate evaluation value is selected from the historical repayment data of multiple users in the historical database, the probability of abnormality is very small, and the first repayment rate evaluation value is obtained by randomly adapting the repayment rate according to the Monte Carlo model, which is prone to large deviations. Therefore, it is necessary to continue to update the first repayment rate evaluation value according to the Monte Carlo model until the evaluation difference falls within the preset difference range.

[0113] In a possible embodiment, the target collection rate evaluation value includes the collection rate evaluation value of each period within the first collection period, the target collection amount evaluation value includes the collection amount evaluation value of each period within the first collection period, and the target cash flow evaluation value includes the cash flow evaluation value of each period within the first collection period; determining the target collection amount evaluation value and the target cash flow evaluation value according to the target collection rate evaluation value and the first asset data includes:

[0114] Determine the total amount of the target customer's outstanding debt according to the first asset data;

[0115] Determine the estimated value of the repayment amount for each period according to the estimated value of the repayment rate for each period and the total amount to be repaid, and obtain the estimated value of the target repayment amount; and

[0116] The cash flow evaluation value of each period is determined according to the collection amount evaluation value of each period and the collection cost of each period to obtain the target cash flow evaluation value. The collection cost refers to the cost incurred in order to recover the collection amount evaluation value.

[0117] The cash flow valuation for each period = the repayment amount for each period - the recovery cost for each period - the default amount for each period. The recovery cost for each period and the default amount for each period are calculated and evaluated by the asset package evaluator, i.e. the financial institution.

[0118] Exemplarily, the first number of repayment periods can be 3 periods, and the target repayment rate assessment value includes the first period repayment rate assessment value of 2%, the second period repayment rate assessment value of 1.8%, and the third period repayment rate assessment value of 2.2%. The total amount to be repaid can be 1 million yuan, and the repayment amount assessment values ​​for each period can be 20,000 yuan, 18,000 yuan and 22,000 yuan respectively, so the target repayment amount is obtained. According to the estimated recovery costs of the three periods, they can be 0 yuan, 1,000 yuan and 2,000 yuan respectively, and the default amount for each period can be 4,000 yuan, 8,000 yuan and 12,000 yuan respectively. The cash flow assessment values ​​for each period are 19,600 yuan, 16,200 yuan and 18,800 yuan respectively, so the target cash flow assessment value is obtained.

[0119] It can be seen that in this embodiment, after detecting that the evaluation difference between the first collection rate evaluation value and the second collection rate evaluation value is within the preset interval, the first collection rate evaluation value and the second collection rate evaluation value are further weighted and summed according to the first weight value and the second weight value to obtain the target collection rate evaluation value, and, when detecting that the evaluation difference is not within the preset interval, the first collection rate evaluation value is updated, the target collection rate evaluation value is recalculated, and then the target collection amount evaluation value and the target cash flow evaluation value are obtained according to the target collection rate evaluation value. The collection rate evaluation value within a certain period of time in the future is determined according to the adjustable Monte Carlo model and the historical database, the evaluation model can be adjusted according to the change in time, and the asset package data of multiple historical users with high similarity are selected according to the historical database, which is conducive to more accurate and efficient asset evaluation for individual loan differences.

[0120] Step S160, determining a target evaluation result according to the target collection rate evaluation value, the target collection amount evaluation value and the target cash flow evaluation value.

[0121] Among them, the target evaluation results include the target collection rate evaluation value, the target collection amount evaluation value and the target cash flow evaluation value for each period in the first collection period of the target customer in the second period in the future.

[0122] It is understandable that since most owners of the non-performing asset packages are overdue customers with poor asset quality, as the collection period increases, the collection period and the target collection amount assessment value are generally negatively correlated; and, the collection period and the target collection rate assessment value are generally negatively correlated; and, the collection period and the target cash flow assessment value are generally negatively correlated; thus, it can be determined that the collection period and the cumulative collection amount are positively correlated; and, the collection period and the cumulative collection rate are positively correlated; and, the collection period and the cumulative target cash flow are positively correlated, and the correlation between the various quantitative indicators of the above target assessment results and the input asset data conforms to the laws of nature.

[0123] Step S170: Generate and output an evaluation report based on the target evaluation result.

[0124] Among them, the evaluation report mainly includes the target collection rate evaluation value, the target collection amount evaluation value and the target cash flow evaluation value; and the evaluation report may also include an asset pool evaluation overview, asset pool characteristics, risk description, bond or borrower granular collection details appendix and other contents.

[0125] The specific presentation content of the evaluation report can be customized according to customer requirements, and the results of one or more asset evaluation indicators mentioned above can be selected as the main content of the evaluation report, and users are supported to view and download it.

[0126] It can be seen that in this embodiment, the server determines the first collection rate evaluation value based on the first asset data, and determines the second collection rate evaluation value based on multiple second asset data, and then determines the target collection rate evaluation value based on the first collection rate evaluation value and the second collection rate evaluation value, and determines the target collection amount evaluation value and the target cash flow evaluation value based on the target collection rate evaluation value, so as to obtain the target evaluation result, and generate and output the evaluation report, to obtain the prediction result of the collection situation of the target customer in a certain period of time in the future, which is conducive to improving the accuracy of asset evaluation, improving evaluation efficiency and convenience.

[0127] See also Figure 2 , Figure 2 is an overall flow chart of an asset data acquisition method provided in an embodiment of the present application, which is applied to a server of an asset evaluation system, such as Figure 2 As shown, the method comprises the following steps:

[0128] Step S210, data type comparison.

[0129] The data type comparison refers to comparing the data type of the first asset data with the data types of multiple asset data in the historical database to obtain multiple historical asset data in the historical database having the same data type as the first asset data.

[0130] Among them, the data types include numerical types and field types. The numerical types include integers, floating point numbers, strings, date / times, Boolean values, binary data, etc.; the field types refer to multiple fields corresponding to the loan information, repayment information and property information included in the first asset data, such as name, age, amount of debt, etc.

[0131] Step S220: data cleaning and parameter setting.

[0132] Among them, the data cleaning includes checking missing values, which can be handled by deleting records containing missing values, or using reasonable filling methods (such as mean, median, mode, etc.) to fill them; and, including processing duplicate values, which requires deduplication processing to avoid affecting the analysis results; and, including outlier detection, that is, identifying and processing possible outliers, processing methods include deletion, replacement (such as replacement with mean, median), or correction based on business understanding; and, including format unification; and, including data type conversion, converting data into a type suitable for analysis; and, including data standardization, for data of different scales, normalization or standardization may be required for comparison and analysis; and, including data verification, checking whether the data conforms to business logic, such as age cannot be negative, income cannot be less than zero, etc.

[0133] Among them, data cleaning of the multiple historical asset data may also include desensitization processing, and hash function encryption or anonymization technology may be used to protect personal privacy.

[0134] The parameter setting refers to setting multiple parameters in multiple historical asset data as comparison parameters, so as to perform similarity comparison based on multiple comparison parameters. The comparison parameters may be the expected period, the total amount to be repaid, etc.

[0135] It can be understood that after data cleaning and parameter setting of multiple historical asset data, a measurement sample set can be obtained, and the measurement sample set can be input into the adversarial verification model to prepare for similarity comparison, thereby obtaining multiple second asset data that are highly similar to the first asset data.

[0136] Step S230, input first asset data.

[0137] It can be seen that in this embodiment, after the first asset data is input into the adversarial verification model, the first asset data and the measurement sample set composed of multiple historical asset data together constitute an asset package measurement sample. The adversarial verification model processes the asset package measurement sample, and performs comparative measurement using multiple comparison parameters to analyze the similarity between each historical asset data in the asset package measurement sample and the first asset data, so as to obtain multiple second asset data.

[0138] Step S240, calculating the similarity.

[0139] Among them, the adversarial verification model calculates the similarity between each historical asset data and the first asset data, specifically evaluates the similarity of each identical comparison parameter, and finally calculates the similarity of each historical asset data according to the similarity values ​​of multiple comparison parameters; and after obtaining multiple similarities, performs a similarity comparison with a preset similarity, and uses multiple historical asset data exceeding the preset similarity as the second asset data.

[0140] Specifically, calculating the similarity can be by obtaining data features of multiple historical asset data, comparing them with the data features of the first asset data, and evaluating the similarity. Specifically, evaluating the similarity can be completed by calculating a similarity metric between the features (such as cosine similarity, Euclidean distance, etc.).

[0141] It can be seen that in this embodiment, by obtaining multiple historical asset data with the same data type as the first asset data of the target customer in the historical database, and then calculating the similarity between the multiple historical asset data and the first asset data, the multiple historical asset data with higher similarity are used as the second asset data, so as to evaluate the target customer's repayment situation based on the repayment situation of multiple users corresponding to the multiple second asset data, thereby realizing the evaluation of the target customer's repayment situation based on similar customer asset data in the historical database, which is conducive to obtaining accurate asset valuation results for different individual differences and solving the problem of the broadness of existing valuation methods.

[0142] See also Figure 3 , Figure 3 is a schematic diagram of a display interface of an asset evaluation system provided in an embodiment of the present application, such as Figure 3 As shown, the display interface of the asset evaluation system is the asset package management interface in the intelligent management platform for personal loan non-performing assets.

[0143] Among them, the display interface is divided into two parts, the left part is the menu bar, and from top to bottom are the system names, namely, personal loan non-performing assets intelligent management platform, business system, search menu, personal loan operation and system management. Among them, the drop-down menu of personal loan operation includes personal loan strategy management, collection business management, collection workbench, personal loan business management, quality inspection management, interactive analysis, organizational management, credit management, and asset evaluation. Among them, asset evaluation also includes asset package management.

[0144] Among them, in the right part of the display interface, the top is the query bar, and from left to right are the setting icons, which are used to set multiple parameters and functions, and the sign-in bar. The left side of the sign-in bar prompts you to enter "your landline number", and the right side is the search icon. Further to the right is the voice call icon, as well as the current call duration record, total call duration record, busy duration record, online duration record and number of calls record, message prompt icon and user icon. The user name is displayed on the right side of the user icon, such as Zhang San.

[0145] Among them, in the right part of the display interface, the middle part is the asset package management page, and the middle part can present different interfaces. When one interface is displayed, other interfaces exist in the form of page labels, such as the page labels such as "My Workspace" and "My Frequently Used Menu" displayed on the middle part. The asset package management page is presented in the form of a table. The top of the table supports users to enter asset package number, asset package name, import status, creator and other information for query or reset, and supports asset package import and template download. Among them, the asset package management table includes information such as asset package number, asset package name, simulation type, asset package type, import status, creation time, creator, update time and operation. Each asset package corresponds to multiple of the above information, and a total of 10 data are displayed in the lower right corner of the table. The current page is the first page of table data, and 20 asset package information is presented on each page.

[0146] It can be seen that in this embodiment, in the intelligent management platform for personal loan non-performing assets, the asset package management interface supports uploading and querying asset packages, and can obtain the number, name, simulation type, type, import status, creation time, creator, update time and other information corresponding to the asset package, which is used to manage and evaluate the asset package; and it also supports operations on asset packages, including variable statistics, model prediction and coefficient adjustment, which are used to count the variable characteristics of asset package data, perform Monte Carlo model asset evaluation and modify adjustment factors, so as to obtain asset evaluation results, which is conducive to improving the convenience and efficiency of asset evaluation.

[0147] See also Figure 4 , Figure 4 is a schematic diagram of an output interface of a target evaluation result provided in an embodiment of the present application, such as Figure 4 As shown, the output interface of the target evaluation result is the asset evaluation interface in the intelligent management platform for personal loan non-performing assets.

[0148] Among them, the asset appraisal interface is the same as the left part of the above-mentioned asset package management interface, which is the menu bar part, and the upper right part is the same, which is the query bar. The page labels are also the same, including "My Workspace", "My Common Menu", "Asset Package Management", and the current page is "Asset Appraisal".

[0149] Among them, the middle area on the right side of the asset appraisal interface is the target appraisal result output area. The target appraisal result is presented in the form of statistical charts, including two statistical charts on the left and right. The statistical chart on the left is the curve of the amount of repayment and the repayment rate for each period, and the statistical chart on the right is the curve of the cumulative amount of repayment and the repayment rate. The number of periods for each statistical chart is 20, and there are five icons in the upper right corner of each statistical chart, from left to right, they are the data query icon, the statistical chart setting icon, the data analysis icon, the refresh icon and the download icon.

[0150] Among them, the statistical chart on the left includes a bar chart consisting of the amount of collection in each period and a line chart consisting of the collection rate in each period. The number of collection periods and the amount of collection in each period are generally negatively correlated; and, the number of collection periods and the collection rate in each period are generally negatively correlated; and, the statistical chart on the right is the cumulative collection amount and collection rate curve, the number of collection periods and the cumulative collection amount are positively correlated, and, the number of collection periods and the cumulative collection rate are positively correlated.

[0151] Among them, above the two statistical charts is the future cash flow forecast, and the specific value of the discount rate is calculated based on the statistical chart data, which can be 7% at present; and, below the two statistical charts is the acquisition cost forecast, and the user can enter the initial collection cost rate, which can be 20% at present, and the right part prompts "Custom Collection Cost Rate"; further down are the target yield and valuation period number, which can be 8% and 36 at present; and, it also includes the acquisition cost calculation based on the established target yield and the acquisition cost calculation based on the established number of periods; and, in the lower right corner are the historical data icon, reset icon and download report icon.

[0152] It is understandable that after the user imports the asset package data into the intelligent management platform for personal loan non-performing assets, the prediction model can be selected to value the asset package data. The user can select the Monte Carlo model alone to obtain the first collection rate assessment value, or select the adversarial verification model and combine the historical database to obtain the second collection rate assessment value. When two models are selected at the same time, the target collection rate assessment value based on the weighted sum of the first collection rate assessment value and the second collection rate assessment value can be determined, and then the target collection amount assessment value and the target cash flow assessment value can be determined, so that the target assessment results are presented in the form of statistical charts on the asset assessment page, and an assessment report is generated at the same time, which supports users to view and download. It realizes asset assessment in various ways for the asset package data of target customers, and improves the accuracy and speed of asset package assessment.

[0153] See also Figure 5 , Figure 5 is a system architecture diagram of an asset evaluation system provided in an embodiment of the present application, such as Figure 5 As shown, the asset evaluation system includes the following modules:

[0154] A first acquisition module 510 is used to acquire first asset data of a target customer in a first period of time, wherein the first asset data includes loan information, repayment information and property information;

[0155] A first evaluation module 520 is used to determine a first collection rate evaluation value based on the first asset data, where the first collection rate evaluation value refers to a prediction index value for independently evaluating the repayment ability of the target customer in the second period from the collection rate index dimension;

[0156] A second acquisition module 530 is used to acquire a plurality of second asset data in a historical database, the data type of which is the same as the data type included in the first asset data, the plurality of second asset data corresponding to a historical user set, the historical user set including at least one user;

[0157] A second evaluation module 540 is used to determine a second repayment rate evaluation value according to the plurality of second asset data, wherein the second repayment rate evaluation value refers to a quantitative index value for comprehensively evaluating the repayment ability of the at least one user in a historical period from the repayment rate index dimension;

[0158] A first determination module 550 is used to determine a target collection rate evaluation value according to the first collection rate evaluation value and the second collection rate evaluation value; and to determine a target collection amount evaluation value and a target cash flow evaluation value according to the target collection rate evaluation value and the first asset data;

[0159] A second determination module 560 is used to determine a target evaluation result according to the target collection rate evaluation value, the target collection amount evaluation value and the target cash flow evaluation value;

[0160] The output module 570 is used to generate and output an evaluation report according to the target evaluation result.

[0161] In one embodiment, the first collection rate evaluation value includes the collection rate evaluation value of the target customer in each period within the first collection period; and determining the first collection rate evaluation value based on the first asset data includes:

[0162] Obtaining an asset adjustment factor corresponding to the first asset data, wherein the asset adjustment factor refers to an input parameter used in a Monte Carlo simulation algorithm or a coefficient of certain assumptions in a simulation process; and,

[0163] Determine the number of simulations according to the first payment collection period;

[0164] Adjusting the Monte Carlo simulation algorithm according to the asset adjustment factor and the number of simulations;

[0165] The first asset data is subjected to feature prediction according to the Monte Carlo simulation algorithm to obtain the first collection rate evaluation value.

[0166] In one embodiment, the similarity between each of the second asset data and the first asset data exceeds a preset threshold; the acquisition history database includes a plurality of second asset data of the same data type as the first asset data, including:

[0167] Acquire a first data type included in the first asset data;

[0168] Acquire a plurality of historical asset data in the historical database, the data type of which is the same as the first data type;

[0169] Combining the first asset data with the plurality of historical asset data to form an asset package measurement sample;

[0170] Using an adversarial verification algorithm to perform similarity evaluation on the asset package measurement samples, and obtain the similarity between each of the historical asset data and the first asset data;

[0171] The plurality of historical asset data whose similarity exceeds the preset threshold is used as the plurality of second asset data.

[0172] In one embodiment, determining the second payment collection rate evaluation value according to the plurality of second asset data includes:

[0173] Determine multiple historical repayment amounts and multiple historical total amounts to be repaid for each user within the historical period according to multiple repayment information in the multiple second asset data;

[0174] Determine the historical repayment rate of each user in each period during the historical period according to the multiple historical repayment amounts and the multiple historical total amounts to be repaid;

[0175] Determine the historical average repayment rate for each period according to the multiple historical repayment rates corresponding to the same period in the multiple second asset data;

[0176] The first repayment period of the target customer within the second time period is determined based on the first asset data.

[0177] In one embodiment, determining a target collection rate evaluation value according to the first collection rate evaluation value and the second collection rate evaluation value includes:

[0178] Obtaining an evaluation difference between the first payment collection rate evaluation value and the second payment collection rate evaluation value;

[0179] Detecting whether the evaluation difference is within a preset difference range;

[0180] If it is detected that the evaluation difference is within the preset difference range, then obtaining a first weight value corresponding to the first collection rate evaluation value; and obtaining a second weight value corresponding to the second collection rate evaluation value; and,

[0181] The target collection rate evaluation value is obtained by weightedly summing the first collection rate evaluation value and the second collection rate evaluation value according to the first weight value and the second weight value.

[0182] In one embodiment, the method further comprises:

[0183] If it is detected that the evaluation difference is not within the preset difference range, updating the first collection rate evaluation value according to the first asset data; and,

[0184] The target collection rate evaluation value is obtained by weightedly summing the updated first collection rate evaluation value and the second collection rate evaluation value according to the first weight value and the second weight value.

[0185] In one embodiment, the target collection rate evaluation value includes the collection rate evaluation value of each period within the first collection period, the target collection amount evaluation value includes the collection amount evaluation value of each period within the first collection period, and the target cash flow evaluation value includes the cash flow evaluation value of each period within the first collection period; the step of determining the target collection amount evaluation value and the target cash flow evaluation value based on the target collection rate evaluation value and the first asset data includes:

[0186] Determine the total amount of the target customer's outstanding debt according to the first asset data;

[0187] Determine the estimated value of the repayment amount for each period according to the estimated value of the repayment rate for each period and the total amount to be repaid, and obtain the estimated value of the target repayment amount; and

[0188] The cash flow evaluation value of each period is determined according to the collection amount evaluation value of each period and the collection cost of each period to obtain the target cash flow evaluation value. The collection cost refers to the cost incurred in order to recover the collection amount evaluation value.

[0189] It can be seen that in this embodiment, the asset management system first obtains the first asset data of the target customer in the first period through the first acquisition module 510; then, the first collection rate evaluation value is determined according to the first asset data through the first evaluation module 520; then, a plurality of second asset data in the historical database containing the same data type as the first asset data is obtained through the second acquisition module 530; secondly, the second collection rate evaluation value is determined according to the plurality of second asset data through the second evaluation module 540; thirdly, the target collection rate evaluation value is determined according to the first collection rate evaluation value and the second collection rate evaluation value through the first determination module 550; and the target collection amount evaluation value and the target cash flow evaluation value are determined according to the target collection rate evaluation value and the first asset data; thirdly, the target evaluation result is determined through the second determination module 560; finally, the evaluation report is generated and output through the output module 570. The asset package is evaluated based on the Monte Carlo model and the historical database, the evaluation method can be adjusted according to market changes, and the evaluation impact caused by the differentiation of individual loans is reduced, which is conducive to improving the evaluation accuracy.

[0190] See also Figure 6 , Figure 6 is a structural block diagram of an electronic device provided in an embodiment of the present application, such as Figure 6 As shown, the electronic device 600 may include one or more of the following components: a processor 610, and a memory 620 coupled to the processor 610, wherein the memory 620 may store one or more computer programs, and the one or more computer programs may be configured to implement the methods described in the above embodiments when executed by one or more processors 610.

[0191] The processor 610 may include one or more processing cores. The processor 610 uses various interfaces and lines to connect various parts of the entire electronic device 600, and executes various functions and processes data of the electronic device 600 by running or executing instructions, programs, code sets or instruction sets stored in the memory 620, and calling data stored in the memory 620. Optionally, the processor 610 can be implemented in at least one hardware form of digital signal processing (DSP), field-programmable gate array (FPGA), and programmable logic array (PLA). The processor 610 can integrate one or a combination of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. Among them, the CPU mainly processes the operating system, user interface, and application programs; the GPU is responsible for rendering and drawing display content; and the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 610, but may be implemented separately through a communication chip.

[0192] The memory 620 may include a random access memory (RAM) or a read-only memory (ROM). The memory 620 may be used to store instructions, programs, codes, code sets or instruction sets. The memory 620 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for implementing at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc. The data storage area may also store data created by the electronic device 600 during use, etc.

[0193] It is understandable that the electronic device 600 may include more or fewer structural elements than those in the above structural block diagram, for example, including a power module, physical buttons, a Wi-Fi module, a speaker, a Bluetooth module, a sensor, etc., which are not limited here.

[0194] In addition, an embodiment of the present application also provides a computer storage medium, which stores a computer program that can be loaded by a processor and execute the above-mentioned asset valuation method. The computer-readable storage medium includes, for example: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0195] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described action sequence, because according to the present application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and units involved are not necessarily required by the present application.

[0196] This is only a logical function division, and there may be other divisions in actual implementation; for example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, which may be electrical, mechanical or other forms.

[0197] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0198] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may be physically included separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0199] The above-mentioned integrated unit implemented in the form of a software functional unit can be stored in a computer-readable storage medium. The above-mentioned software functional unit is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform some steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a volatile memory or a non-volatile memory. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM) or a flash memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (double data rate SDRAM, DDR SDRAM), enhanced synchronous dynamic random access memory (enhanced SDRAM, ESDRAM), synchronous link dynamic random access memory (synchlink DRAM, SLDRAM) and direct memory bus random access memory (directrambus RAM, DR RAM) and other media that can store program code.

[0200] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0201] The embodiments of the present application are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

[0202] Although the present application is disclosed as above, the present application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions without departing from the spirit and scope of the present application, and can make various changes and modifications, including the combination of the above-mentioned different functions and implementation steps, including software and hardware implementation methods, all of which are within the scope of protection of the present application.

Claims

1. An asset evaluation method, characterized in that: Applied to a server of an asset evaluation system, the method comprises: Acquire first asset data of a target customer in a first period of time, wherein the first asset data includes loan information, repayment information, and property information; Determine a first collection rate evaluation value based on the first asset data, where the first collection rate evaluation value refers to a prediction index value that independently evaluates the repayment ability of the target customer in the second period from the collection rate index dimension; Acquire a plurality of second asset data in a historical database, the data type of which is the same as the data type included in the first asset data, the plurality of second asset data corresponding to a historical user set, the historical user set including at least one user; Determine a second repayment rate evaluation value according to the plurality of second asset data, wherein the second repayment rate evaluation value refers to a quantitative index value for comprehensively evaluating the repayment ability of the at least one user in a historical period from the repayment rate index dimension; Determine a target collection rate evaluation value according to the first collection rate evaluation value and the second collection rate evaluation value; and determine a target collection amount evaluation value and a target cash flow evaluation value according to the target collection rate evaluation value and the first asset data; Determine a target evaluation result based on the target collection rate evaluation value, the target collection amount evaluation value and the target cash flow evaluation value; An evaluation report is generated and outputted according to the target evaluation results.

2. The method according to claim 1, characterized in that The determining a target payment collection rate evaluation value according to the first payment collection rate evaluation value and the second payment collection rate evaluation value comprises: Obtaining an evaluation difference between the first payment collection rate evaluation value and the second payment collection rate evaluation value; Detecting whether the evaluation difference is within a preset difference range; If it is detected that the evaluation difference is within the preset difference range, then obtaining a first weight value corresponding to the first collection rate evaluation value; and obtaining a second weight value corresponding to the second collection rate evaluation value; and, The target collection rate evaluation value is obtained by weightedly summing the first collection rate evaluation value and the second collection rate evaluation value according to the first weight value and the second weight value.

3. The method according to claim 2, characterized in that The method further comprises: If it is detected that the evaluation difference is not within the preset difference range, updating the first collection rate evaluation value according to the first asset data; and, The target collection rate evaluation value is obtained by weightedly summing the updated first collection rate evaluation value and the second collection rate evaluation value according to the first weight value and the second weight value.

4. The method according to claim 3, characterized in that The determining the second payment collection rate evaluation value according to the plurality of second asset data comprises: Determine multiple historical repayment amounts and multiple historical total amounts to be repaid for each user within the historical period according to multiple repayment information in the multiple second asset data; Determine the historical repayment rate of each user in each period during the historical period according to the multiple historical repayment amounts and the multiple historical total amounts to be repaid; Determine the historical average repayment rate for each period according to the multiple historical repayment rates corresponding to the same period in the multiple second asset data; Determine the first repayment period of the target customer within the second period according to the first asset data; The multiple historical average collection rates corresponding to the collection period and the first collection period are determined as the second collection rate evaluation value.

5. The method according to claim 4, characterized in that The similarity between each of the second asset data and the first asset data exceeds a preset threshold; The acquisition history database includes a plurality of second asset data of the same data type as the data type included in the first asset data, including: Acquire a first data type included in the first asset data; Acquire a plurality of historical asset data in the historical database, the data type of which is the same as the first data type; Combining the first asset data with the plurality of historical asset data to form an asset package measurement sample; Using an adversarial verification algorithm to perform similarity evaluation on the asset package measurement samples, and obtain the similarity between each of the historical asset data and the first asset data; The plurality of historical asset data whose similarity exceeds the preset threshold is used as the plurality of second asset data.

6. The method according to any one of claims 1 to 5, characterized in that: The first collection rate evaluation value includes the collection rate evaluation value of the target customer in each period within the first collection period; the first collection rate evaluation value is determined according to the first asset data, including: Obtaining an asset adjustment factor corresponding to the first asset data, wherein the asset adjustment factor refers to an input parameter used in a Monte Carlo simulation algorithm or a coefficient of certain assumptions in a simulation process; and, Determine the number of simulations according to the first payment collection period; Adjusting the Monte Carlo simulation algorithm according to the asset adjustment factor and the number of simulations; The first asset data is subjected to feature prediction according to the Monte Carlo simulation algorithm to obtain the first collection rate evaluation value.

7. The method according to claim 6, characterized in that The target collection rate evaluation value includes the collection rate evaluation value of each period within the first collection period, the target collection amount evaluation value includes the collection amount evaluation value of each period within the first collection period, and the target cash flow evaluation value includes the cash flow evaluation value of each period within the first collection period; The step of determining a target payment amount assessment value and a target cash flow assessment value according to the target payment rate assessment value and the first asset data includes: Determine the total amount of the target customer's outstanding debt according to the first asset data; Determine the estimated value of the repayment amount for each period according to the estimated value of the repayment rate for each period and the total amount to be repaid, and obtain the estimated value of the target repayment amount; and The cash flow evaluation value of each period is determined according to the collection amount evaluation value of each period and the collection cost of each period to obtain the target cash flow evaluation value. The collection cost refers to the cost incurred in order to recover the collection amount evaluation value.

8. An asset evaluation system, applied to the asset evaluation method according to any one of claims 1 to 7, characterized in that: include: A first acquisition module is used to acquire first asset data of a target customer within a first period of time, wherein the first asset data includes loan information, repayment information and property information; A first evaluation module, configured to determine a first collection rate evaluation value according to the first asset data, wherein the first collection rate evaluation value refers to a prediction index value for independently evaluating the repayment ability of the target customer in the second period from the collection rate index dimension; A second acquisition module is used to acquire a plurality of second asset data in a historical database, the data type of which is the same as the data type included in the first asset data, the plurality of second asset data corresponding to a historical user set, the historical user set including at least one user; A second evaluation module, configured to determine a second repayment rate evaluation value based on the plurality of second asset data, wherein the second repayment rate evaluation value refers to a quantitative index value for comprehensively evaluating the repayment ability of the at least one user in a historical period from a repayment rate index dimension; A first determining module, configured to determine a target collection rate evaluation value according to the first collection rate evaluation value and the second collection rate evaluation value; And, determining a target collection amount evaluation value and a target cash flow evaluation value according to the target collection rate evaluation value and the first asset data; A second determination module is used to determine a target evaluation result according to the target collection rate evaluation value, the target collection amount evaluation value and the target cash flow evaluation value; The output module is used to generate and output an evaluation report based on the target evaluation results.

9. An electronic device, characterized in that: The method comprises a processor, a memory, a communication interface and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the programs include instructions for executing the steps in any one of the methods of claims 1 to 7.

10. A computer-readable storage medium having a computer program / instruction stored thereon, characterized in that: The computer program / instructions are executed by a processor to implement the steps of the method according to any one of claims 1 to 7.

Images