Loan data screening method and device, electronic equipment and storage medium

Abstract

The present disclosure provides a loan data screening method and device, electronic equipment and storage medium, which can be applied to the field of big data technology. The loan data screening method can be applied to a first system, which comprises: in response to receiving a screening instruction from a second system, analyzing the screening instruction to obtain a first screening condition, a total number of transactions and a total size of assets; screening M loan data from a database according to the first screening condition, wherein the loan data comprises attribute information of a user and information generated in a transaction process, and M≥2; screening N first loan data from the M loan data according to the total number of transactions and the total size of assets, wherein 2≤N≤M; generating a first loan list according to the N first loan data, wherein the first loan list comprises identification information of the first loan data; and sending the first loan list to the second system.

Description

Technical Field

[0001] This disclosure relates to the field of big data technology, specifically to a method, apparatus, electronic device, and storage medium for filtering borrowed data. Background Technology

[0002] Large banks typically have tens of millions of loan documents and total assets exceeding trillions. They regularly select eligible loan documents from these tens of millions and add them to a securitization asset pool, using the loan documents in the pool to generate transferable trading certificates.

[0003] In related technologies, the above screening operations are generally performed by branches of large banks. However, the screening process requires business personnel to manually determine screening indicators, screening conditions, and other information based on experience. The high return rate of the loan data aggregated to the head office necessitates frequent re-screening operations, resulting in low screening efficiency and high time and labor costs. Summary of the Invention

[0004] In view of the above problems, this disclosure provides a method, apparatus, electronic device and storage medium for filtering loan data.

[0005] According to a first aspect of this disclosure, a method for filtering loan receipt data is provided, applied to a first system, the method comprising:

[0006] In response to receiving a filtering instruction from the second system, the filtering instruction is parsed to obtain the first filtering condition, the total number of transactions, and the total asset size.

[0007] Based on the first screening condition, M loan receipt data are obtained from the database. The loan receipt data includes user attribute information and information generated during the transaction process, where M≥2.

[0008] Based on the total number of transactions and the total asset size, select N first loan records from M loan records, where 2≤N≤M;

[0009] A first loan agreement list is generated based on N first loan agreement data. The first loan agreement list includes the identification information of the first loan agreement data; and

[0010] Send the first list of promissory notes to the second system.

[0011] According to embodiments of this disclosure, the above method further includes:

[0012] In response to receiving a return instruction from the second system, the return instruction is parsed to obtain the number of returns and the scale of returned assets.

[0013] Based on the number of returned assets and the scale of returned assets, at least one second loan record is obtained by filtering from the M loan record data.

[0014] Generate a second list of promissory notes based on at least one second promissory note data; and

[0015] Send the second list of promissory notes to the second system.

[0016] According to an embodiment of this disclosure, the first screening condition includes P first indicators and a screening threshold for the first indicators, wherein the first indicators include attribute indicators, and P≥1;

[0017] Based on the first filtering criterion, M loan receipt data are obtained from the database, including:

[0018] Filter the database to find M loan records that include P primary indicators and meet P filtering thresholds.

[0019] According to embodiments of this disclosure, selecting N first loan receipt data from M loan receipt data based on the total number of transactions and the total asset size includes:

[0020] Obtain the allocation relationship between the first system and the second system, including the allocation ratio of the first system to the second system;

[0021] Based on the allocation relationships, the total number of transactions, and the total asset size, determine the transaction allocation amount and asset allocation size for the first system; and

[0022] Based on the asset allocation scale, select N first-level loan records from M loan records. The number of N first-level loan records corresponds to the number of transactions allocated.

[0023] According to embodiments of this disclosure, selecting N first loan receipt data from M loan receipt data based on the asset allocation scale includes:

[0024] After the first screening, T sets of preliminary screening datasets are randomly selected from M loan receipt data. Each set of preliminary screening datasets includes N preliminary screening loan receipt data, and T≥2.

[0025] Calculate the asset valuation and asset size of N initial screening loan receipts within each initial screening dataset;

[0026] If the t-th preliminary screening dataset meets the second screening condition, the t-th preliminary screening dataset is taken as the first optimal solution set. The second screening condition includes the highest asset valuation and the asset size being closest to the asset allocation size, 1≤t≤T.

[0027] After randomly deleting L initial screening loan data from the first optimal solution set, after a second screening, L second screening loan data are obtained from the loan data outside the first optimal solution set. The L second screening loan data and (NL) initial screening loan data are combined to form a second screening dataset, where 1≤L≤N.

[0028] Compare the asset valuations of the first optimal solution set and the second screening dataset to determine the second optimal solution set; and

[0029] After a preset number of screening and comparisons, the final optimal solution set is determined, which includes N first loan data.

[0030] According to embodiments of this disclosure, calculating the asset valuation and asset size of N initial screening loan receipts within each initial screening dataset includes:

[0031] For each of the Q secondary indicators, calculate the indicator mean and indicator variance of the N initial screening loan data to obtain the Q indicator mean and Q indicator variance corresponding to the Q secondary indicators. The secondary indicators include indicators that characterize user transaction behavior, and Q≥2.

[0032] Obtain the Q historical institutional means and Q historical institutional variances corresponding to the Q second indicators. The historical institutional means and historical institutional variances represent the historical asset status of the first system; and

[0033] The asset valuation is determined based on the mean of Q indicators, the variance of Q indicators, the mean of Q historical institutions, and the variance of Q historical institutions.

[0034] According to embodiments of this disclosure, determining the asset valuation based on the mean of Q indicators, the variance of Q indicators, the mean of Q historical institutions, and the variance of Q historical institutions includes:

[0035] For each second indicator, a first evaluation value is generated if the indicator's mean is lower than the historical average of the institutions.

[0036] A second assessment value is generated when the absolute value of the indicator variance is less than the absolute value of the historical institutional variance; and

[0037] The asset valuation is obtained by combining the first and second valuation values ​​of Q secondary indicators.

[0038] A second aspect of this disclosure provides a method for filtering loan data, applied to a second system, the second system interacting with at least one first system, the method comprising:

[0039] Receive a first list of promissory notes from at least one first system, the first system generates a first list of promissory notes, the first list of promissory notes includes identification information of at least one first promissory note data;

[0040] Based on the identification information, retrieve R first loan receipt data from the database, where R ≥ 2;

[0041] Calculate the asset valuation of R first-order loan records;

[0042] Based on the asset valuation, S third-party loan data are determined from R first-party loan data. The S third-party loan data are used to generate transaction vouchers, where 2≤S≤R.

[0043] According to embodiments of this disclosure, after determining S third loan receipts from R first loan receipts based on asset valuation, the process includes:

[0044] Based on the identification information of the (RS) first debit data that were not selected, at least one return instruction is generated, which is used to return the (RS) first debit data to the first system from which it originated;

[0045] Distribute at least one return instruction to at least one first system.

[0046] A third aspect of this disclosure provides a filtering device for loan data, applied to a first system, the filtering device comprising:

[0047] The first receiving module is used to respond to receiving a filtering instruction from the second system, parse the filtering instruction, and obtain the first filtering condition, the total number of transactions, and the total asset size;

[0048] The first filtering module is used to filter M loan data from the database according to the first filtering condition. The loan data includes user attribute information and information generated during the transaction process, where M≥2.

[0049] The second filtering module is used to filter N first loan data from M loan data based on the total number of transactions and the total asset size, where 2≤N≤M;

[0050] The generation module is used to generate a first loan agreement list based on N first loan agreement data. The first loan agreement list includes the identification information of the N first loan agreement data; and

[0051] The sending module is used to send the first list of promissory notes to the second system.

[0052] A fourth aspect of this disclosure provides a filtering device for loan data, applied to a second system, the second system interacting with at least one first system, the filtering device comprising:

[0053] The second receiving module is used to receive a first list of loan receipts from at least one first system. The first system generates a first list of loan receipts, which includes identification information of at least one first loan receipt data.

[0054] The acquisition module is used to retrieve R first loan receipt data from the database based on the identification information, where R≥2;

[0055] The calculation module is used to calculate the asset valuation of R first loan receipts;

[0056] The determination module is used to determine S third-party loan data from R first-party loan data based on the asset valuation. The S third-party loan data are used for asset securitization, where 2≤S≤R.

[0057] A fifth aspect of this disclosure provides an electronic device comprising: one or more processors; and a memory for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors perform the aforementioned method for filtering loan data.

[0058] A sixth aspect of this disclosure also provides a computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, cause the processor to perform the aforementioned method for filtering borrow data.

[0059] The seventh aspect of this disclosure also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method for filtering loan data.

[0060] The embodiments of this disclosure, in response to receiving a filtering instruction from a second system, parse the filtering instruction to obtain a first filtering condition, the total number of transactions, and the total asset size; based on the first filtering condition, filter out M loan receipt data from the database; based on the total number of transactions and the total asset size, filter out N first loan receipt data from the M loan receipt data; generate a first loan receipt list based on the N first loan receipt data, the first loan receipt list including the identification information of the first loan receipt data; send the first loan receipt list to the second system, thus realizing automatic filtering of loan receipt data, eliminating the need for business personnel to manually select and adjust filtering conditions based on experience, and improving filtering efficiency. Since the first system performs standard filtering based on the total number of transactions and the total asset size from the second system, the filtering operations performed by multiple first systems are identical, eliminating the need to expend additional resources to eliminate filtering differences between multiple first systems, and improving business filtering efficiency. Attached Figure Description

[0061] The foregoing contents, as well as other objects, features, and advantages of this disclosure, will become clearer from the following description of embodiments with reference to the accompanying drawings, in which:

[0062] Figure 1 This illustration schematically depicts an application scenario of the method for filtering loan data according to embodiments of the present disclosure;

[0063] Figure 2 A flowchart illustrating a method for filtering loan data applied to a first system according to an embodiment of the present disclosure is shown schematically.

[0064] Figure 3 A flowchart illustrating a second promissory note list determination method according to an embodiment of the present disclosure is shown schematically.

[0065] Figure 4 This diagram illustrates an application scenario of the second loan data filtering method according to an embodiment of the present disclosure.

[0066] Figure 5 A flowchart illustrating the filtering of N first solution data according to an embodiment of the present disclosure is shown schematically;

[0067] Figure 6 A flowchart illustrating a method for filtering loan data according to a specific embodiment of the present disclosure is shown schematically;

[0068] Figure 7 A flowchart illustrating a method for filtering loan data applied to a second system according to an embodiment of the present disclosure is shown schematically.

[0069] Figure 8 This schematically illustrates a structural block diagram of a device for filtering loan data applied to a first system according to an embodiment of the present disclosure;

[0070] Figure 9 A schematic diagram illustrates a structural block diagram of a borrowing data filtering device applied to a second system according to an embodiment of the present disclosure; and

[0071] Figure 10 A block diagram of an electronic device suitable for a data filtering method according to an embodiment of the present disclosure is shown schematically. Detailed Implementation

[0072] The embodiments of the present disclosure will now be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the disclosure. In the following detailed description, numerous specific details are set forth to provide a thorough understanding of the embodiments of the present disclosure for ease of explanation. However, it will be apparent that one or more embodiments may be practiced without these specific details. Furthermore, descriptions of well-known structures and techniques are omitted in the following description to avoid unnecessarily obscuring the concepts of the present disclosure.

[0073] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit this disclosure. The terms “comprising,” “including,” etc., as used herein indicate the presence of the stated features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0074] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein are to be interpreted in a manner consistent with the context of this specification, and not in an idealized or overly rigid way.

[0075] When using expressions such as "at least one of A, B, and C", they should generally be interpreted in accordance with the meaning that is commonly understood by a person skilled in the art (e.g., "a system having at least one of A, B, and C" should include, but is not limited to, a system having A alone, a system having B alone, a system having C alone, a system having A and B, a system having A and C, a system having B and C, and / or a system having A, B, and C, etc.).

[0076] It should be noted that the methods and apparatus for screening publicly disclosed loan data can be used in the screening process of asset securitization in the financial field, and can also be used for data screening operations in any field other than the financial field. The application fields of the methods and apparatus for screening publicly disclosed loan data are not limited.

[0077] In the technical solutions disclosed herein, the collection, storage, use, processing, transmission, provision, disclosure, and application of data (including but not limited to user personal information) comply with the provisions of relevant laws and regulations, necessary confidentiality measures have been taken, and they do not violate public order and good morals.

[0078] During the asset securitization screening process, each branch office selects eligible loan data from within its organization according to the head office's requirements and then reports it to the head office. Currently, each branch office's system can only screen based on hard criteria, automatically selecting a set of results that meet the conditions. Branch office staff must manually select the loan documents that meet their requirements from the result set. This screening process relies heavily on the staff's experience.

[0079] After receiving the loan list submitted by each branch, the head office uses system functions to calculate the overall situation of the loan list. Based on the overall situation reflecting the differences in screening by each branch, the head office then adjusts, adds, or returns the loan data submitted by each branch. Through multiple adjustments, the final securitized asset pool is obtained.

[0080] Multiple screening operations not only waste a lot of database access and computing resources, but also occupy the human resources of various branches and the head office, resulting in low screening efficiency and high time and labor costs.

[0081] In addition, each adjustment operation requires information exchange between the branches and the head office. Due to various reasons, the branches and the head office may not be able to perform the screening operation in a timely manner, resulting in long screening time and low screening efficiency.

[0082] The embodiments of this disclosure provide a method for filtering loan receipt data, which can be applied to a first system, including: responding to receiving a filtering instruction from a second system, parsing the filtering instruction to obtain a first filtering condition, a total number of transactions, and a total asset size; filtering M loan receipt data from a database according to the first filtering condition, the loan receipt data including user attribute information and information generated during the transaction process, where M≥2; filtering N first loan receipt data from the M loan receipt data according to the total number of transactions and the total asset size, where 2≤N≤M; generating a first loan receipt list based on the N first loan receipt data, the first loan receipt list including identification information of the first loan receipt data; and sending the first loan receipt list to the second system.

[0083] Figure 1 The illustration depicts an application scenario of the method for filtering loan data according to embodiments of the present disclosure.

[0084] like Figure 1 As shown, application scenario 100 according to this embodiment may include a first server 101, a second server 102, and a third server 103. A network can provide a communication link between the first server 101, the second server 102, and the third server 103. The network may include various connection types, such as wired or wireless communication links, or fiber optic cables, etc.

[0085] The first server 101 may include multiple sub-servers, such as first sub-server 101-1…i-th sub-server 101-1…I-th sub-server 101-I. These multiple sub-servers can be deployed in multiple branches across multiple cities and regions to install the first system and perform data filtering operations on loan documents.

[0086] The second server 102 is deployed at the headquarters and is used to install the second system and perform the filtering operation of the loan data.

[0087] The third server 103 may include multiple sub-servers for storing loan data from multiple cities and regions.

[0088] The loan receipt data stored on the third server 103 can be collected from various types of mobile terminal devices used by the user, wherein the collection of loan receipt data is carried out with the user's permission. The terminal devices can be various electronic devices with displays and web browsing capabilities, including but not limited to smartphones, tablets, laptops, and desktop computers.

[0089] Various communication client applications can be installed on terminal devices, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social media platform software, banking clients, etc. (for example only).

[0090] It should be noted that the method for filtering loan data applied to the first system provided in this embodiment can generally be executed by the first server 101. Correspondingly, the device for filtering loan data applied to the first system provided in this embodiment can generally be located in the first server 101. The method for filtering loan data applied to the first system provided in this embodiment can also be executed by a server or server cluster that is different from the first server 101 and capable of communicating with the second server 102 and / or the third server 103. Correspondingly, the device for filtering loan data applied to the first system provided in this embodiment can also be located in a server or server cluster that is different from the first server 101 and capable of communicating with the second server 102 and / or the third server 103.

[0091] The method for filtering loan receipt data applied to the second system provided in this disclosure embodiment can generally be executed by the second server 102. Correspondingly, the device for filtering loan receipt data applied to the second system provided in this disclosure embodiment can generally be located in the second server 102. The method for filtering loan receipt data applied to the second system provided in this disclosure embodiment can also be executed by a server or server cluster that is different from the second server 102 and capable of communicating with the first server 101 and / or the third server 103. Correspondingly, the device for filtering loan receipt data applied to the second system provided in this disclosure embodiment can also be located in a server or server cluster that is different from the second server 102 and capable of communicating with the first server 101 and / or the third server 103.

[0092] It should be understood that Figure 1 The number of servers shown is merely illustrative. Depending on implementation needs, any number of servers can be used.

[0093] Figure 2 A flowchart illustrating a method for filtering loan data applied to a first system according to an embodiment of the present disclosure is shown.

[0094] like Figure 2 As shown, method 200 includes operations S210 to S250. This method is applied to the first system.

[0095] According to embodiments of this disclosure, the first system may be a system used by branch offices to filter loan receipt data. The second system may be a system used by the head office to filter loan receipt data. The head office's second system may interface with multiple first systems of multiple branch offices to obtain the filtering lists from the multiple first systems.

[0096] In operation S210, in response to receiving a filtering instruction from the second system, the filtering instruction is parsed to obtain the first filtering condition, the total number of transactions, and the total asset size.

[0097] According to an embodiment of this disclosure, the first system responds to receiving a filtering instruction from the second system and performs a filtering operation based on the filtering instruction. The first system can parse the received filtering instruction to obtain the first filtering condition, the total number of transactions, and the total asset size from the second system.

[0098] According to embodiments of this disclosure, the first filtering condition includes fixed filtering conditions for fixed indicators. The first system can implement filtering in the form of computer expressions. The filtering instruction includes the first indicator.

[0099] For example, the first indicator includes start time, remaining time, and balance range. The first screening criteria include: the balance range is between 500,000 and 1,000,000, and the remaining time is greater than 120 * number of periods.

[0100] According to embodiments of this disclosure, the total number of transactions and the total asset size represent the sum of the number of transactions and the asset size required by the head office from multiple first systems.

[0101] In operation S220, based on the first filtering condition, M loan data are obtained from the database. The loan data includes user attribute information and information generated during the transaction process, where M≥2.

[0102] According to embodiments of this disclosure, the database includes loan receipt data from multiple branches and regions. Both the first system and the second system can search, query, and retrieve loan receipt data from this database.

[0103] According to embodiments of this disclosure, the loan data includes user attribute information and information generated during the transaction process. For example, attribute information includes credit status, loan behavior, etc., the transaction process includes the loan implementation process, and the information generated during the transaction process includes loan balance, loan amount, remaining term, loan interest rate, etc.

[0104] According to embodiments of this disclosure, filtering based on the first filtering condition can eliminate a large amount of useless loan receipt data, reducing the number of loan receipts from tens of millions to 1,000 or 10,000, effectively reducing workload and filtering difficulty. Furthermore, using the first filtering condition can initially improve the accuracy of the filtered data and reduce the number of adjustments, thereby improving filtering efficiency.

[0105] In operation S230, based on the total number of transactions and the total asset size, select N first loan records from M loan records, where 2≤N≤M.

[0106] According to embodiments of this disclosure, the first system can calculate the total number of transactions and total asset size obtained from the parsing, as well as the historical data of the branch, to determine the actual loan data that the branch needs to report.

[0107] According to an embodiment of this disclosure, after obtaining M loan receipt data from the database using the first filtering criteria, the data is filtered again based on the determined actual loan receipt data to obtain N first loan receipt data.

[0108] According to embodiments of this disclosure, N first loan agreement data can be selected from M resolution data based on transaction characteristics included in the loan agreement data. For example, the transaction characteristics include loan balance, loan amount, remaining term, and loan interest rate.

[0109] In operation S240, a first loan list is generated based on N first loan data. The first loan list includes the identification information of the first loan data.

[0110] According to embodiments of this disclosure, the loan agreement data itself includes user attribute information and information generated during the transaction process, and the amount of loan agreement data is also very large. During the interaction between the first system and the second system, transmitting the filtered first loan agreement data will result in high transmission resource consumption and long transmission time.

[0111] According to embodiments of this disclosure, after filtering and obtaining N first loan receipt data, the first system generates a list of first loan receipts based on the N first loan receipt data. Since the first loan receipt list only includes the identification information of the first loan receipt data, and the size of the first loan receipt list can be at the kilobyte level, fast and delay-free transmission can be achieved when transmitting the first loan receipt list.

[0112] In operation S250, the first list of promissory notes is sent to the second system.

[0113] According to an embodiment of this disclosure, after the first system generates a first list of loan receipts, it sends the first list of loan receipts to the second system so that the second system can retrieve N filtered first loan receipt data from the database based on the identification information in the first list of loan receipts, and perform adjustments, filtering, and other processing on the N first loan receipt data.

[0114] The embodiments of this disclosure, in response to receiving a filtering instruction from a second system, parse the filtering instruction to obtain a first filtering condition, the total number of transactions, and the total asset size; based on the first filtering condition, filter out M loan receipt data from the database; based on the total number of transactions and the total asset size, filter out N first loan receipt data from the M loan receipt data; generate a first loan receipt list based on the N first loan receipt data, the first loan receipt list including the identification information of the first loan receipt data; send the first loan receipt list to the second system, thus realizing automatic filtering of loan receipt data, eliminating the need for business personnel to manually adjust the filtering conditions based on experience, and improving filtering efficiency. Since the first system performs standard filtering based on the total number of transactions and the total asset size from the second system, the filtering operations performed by multiple first systems are identical, eliminating the need to expend additional resources to eliminate filtering differences between multiple first systems, thereby improving business filtering efficiency.

[0115] Figure 3 A flowchart illustrating a second promissory note list determination method according to an embodiment of the present disclosure is shown schematically.

[0116] like Figure 3 As shown, the second promissory note list determination method 300 of this embodiment includes operations S310 to S340. Operations S310 to S340 can occur after operations S210 to S250.

[0117] In operation S310, in response to receiving a return instruction from the second system, the return instruction is parsed to obtain the number of returns and the scale of the returned assets.

[0118] In operation S320, at least one second loan record is obtained from M loan record data based on the number of returns and the scale of returned assets.

[0119] In operation S330, a second list of debit notes is generated based on at least one second debit note data.

[0120] In operation S340, the second list of promissory notes is sent to the second system.

[0121] According to embodiments of this disclosure, after the head office performs a screening operation through the second system, it needs to delete loan receipt data that does not meet the requirements. Since the loan receipt data comes from multiple first systems, after the second system deletes the loan receipt data that does not meet the requirements, it will send a return instruction to the first system that sourced the deleted loan receipt data so that the first system can replenish the loan receipt data that meets the requirements.

[0122] According to embodiments of this disclosure, the return instruction includes the number of returns and the scale of returned assets. The first system, by parsing the return instruction, can obtain the number of returned loan receipts and the scale of returned assets, so as to re-filter the M loan receipt data obtained using the first filtering conditions based on the number of returns and the scale of returned assets, and obtain at least one second loan receipt data. The number of second loan receipt data is the same as the number of returns.

[0123] For example, parsing the return instruction yields 100 return orders, with a total returned asset value of 1 million. Filtering the M loan receipt data obtained using the first filtering condition yields 100 second loan receipt data. These 100 second loan receipt data may include one with an asset value of 100,000, or another with an asset value of 1,000.

[0124] According to embodiments of this disclosure, the operation of filtering second loan data from M loan data based on the number of returns and the scale of returned assets is the same as or similar to the operation of filtering first resolution data, and will not be described again here.

[0125] According to an embodiment of this disclosure, after at least one second loan receipt data is obtained through screening, a second loan receipt list including identification information of the at least one second loan receipt data is generated, and the second loan receipt list is sent to a second system.

[0126] The embodiments of this disclosure automatically re-filter data by the first system in response to a return instruction from the second system, based on the number of returns and the scale of returned assets, without the need for manual processing.

[0127] Figure 4 The illustration shows an application scenario diagram of the second borrowing data filtering method according to an embodiment of the present disclosure.

[0128] like Figure 4 As shown, application scenario 400 includes a first system 401, a database 402, and a second system 403.

[0129] According to an embodiment of this disclosure, in response to receiving a return instruction from the second system 403, the first system 401 parses the return instruction to obtain the number of returns and the scale of returned assets. It then performs filtering based on the number of returns and the scale of returned assets. Specifically, based on the number of returns and the scale of returned assets, it filters the loan receipt data in the database 402 that has already been filtered using the first filtering criteria, obtaining at least one second loan receipt. The first system 401 generates a second loan receipt list based on the at least one loan receipt data returned by the database 102 and sends the generated second loan receipt list to the second system 403.

[0130] According to embodiments of this disclosure, the screening process based on the number of returned loans and the size of the returned assets can be performed through T loops. In each loop, loan receipt data with the same number of returned loans are randomly selected, and the asset valuation and asset size of the loan receipt data are calculated. From the T loops, the group of loan receipt data with the highest asset valuation and the asset size most similar to the returned asset size is selected as the second group of loan receipt data.

[0131] According to an embodiment of this disclosure, the first screening condition includes P first indicators and a screening threshold for the first indicators, wherein the first indicators include attribute indicators, and P≥1.

[0132] Based on the first filtering criterion, M loan receipt data are obtained from the database, including:

[0133] Filter the database to find M loan records that include P primary indicators and meet P filtering thresholds.

[0134] According to embodiments of this disclosure, for different filtering tasks, the first indicator in the filtering instruction sent by the second system may be different, and the filtering threshold for the first indicator may also be different. For different filtering tasks, the first indicator in the filtering instruction may be the same, but the filtering threshold for the first indicator may be different.

[0135] For example, for the screening task of Project A, the first indicators are account opening time, loan date, and interest rate. The screening thresholds for these three first indicators are 2020, 2021, and 4%, respectively. The first screening condition is that the user's account opening time is before 2020, the loan date is before 2021, and the loan interest rate is below 4%.

[0136] For the screening task of Project B, the primary indicators are the execution interest rate, the balance range, and the remaining number of periods. The screening thresholds for these three primary indicators are 4% and 5%, 500,000 and 1,000,000, and 120, respectively. The primary screening criteria are: loan data with an execution interest rate between 4% and 5%, a balance range between 500,000 and 1,000,000, and more than 120 remaining periods.

[0137] According to embodiments of this disclosure, due to continuous upgrades to banking systems, older loan receipt data may be incomplete; or, due to different loan types, the focus of loan receipt data registration may differ. Therefore, the loan receipt data may not include the first indicator within the first screening criteria.

[0138] According to an embodiment of this disclosure, when searching in the database, the database is first filtered based on whether it simultaneously includes P first indicators, and then filtered based on whether the P first indicators meet the first filtering conditions, thereby determining M loan data from the database.

[0139] According to embodiments of this disclosure, by filtering M loan data from the database that include P first indicators and satisfy P screening thresholds, preliminary screening based on P first indicators is achieved, which greatly reduces the amount of data to be screened and improves screening efficiency.

[0140] Figure 5 A flowchart illustrating the filtering of N first loan receipt data according to an embodiment of the present disclosure is shown.

[0141] like Figure 5 As shown, the flowchart 500 for filtering N first loan data includes operations S531 to S533, which can be used as a specific embodiment of operation S230.

[0142] According to embodiments of this disclosure, loan interest rates, outstanding balances, and transaction frequencies vary across different cities and regions. For example, interest rates, outstanding balances, and transaction frequencies in economically developed regions are significantly higher than those in economically underdeveloped regions. If the asset size is evenly distributed among branches, it may result in insufficient asset size and transaction frequency.

[0143] In the above situation, branch offices or head offices need to apply for information from other regions, which generates new calling steps, increases the number of interactions between multiple systems, prolongs the screening time, and affects screening efficiency.

[0144] In operation S531, the allocation relationship between the first system and the second system is obtained, including the allocation ratio of the first system to the second system.

[0145] According to embodiments of this disclosure, the first system determines the allocation relationship between the first system and the second system by analyzing historical data of the current branch and historical data of the head office. The historical data includes loan receipt data for all historical projects of the branch where the first system is located.

[0146] According to embodiments of this disclosure, after obtaining the total number of transactions and the total asset size, a pre-determined allocation relationship between the first system and the second system is retrieved from the relationship address of the first system.

[0147] According to embodiments of this disclosure, the allocation relationship includes an allocation ratio. The allocation ratio can be determined by calculating the ratio between the historical asset size of the current branch and the historical asset size of the head office.

[0148] The historical asset size of a branch can be calculated using formula (1):

[0149]

[0150] Among them, z nt represents the historical asset size of branch n. i b represents the number of transactions or loans in the i-th phase of the project. i Let I represent the balance of the i-th period project, and let I represent the total number of periods for all historical projects.

[0151] The historical asset size of the head office can be calculated using formula (2):

[0152] IB231214

[0153]

[0154] Where Z represents the historical asset size of the head office, T represents the number of transactions or loans in the i-th phase of the project, and B i Let I represent the balance of the i-th period project, and let I represent the total number of periods for all historical projects.

[0155] According to embodiments of this disclosure, the allocation ratio can be z. n / Z.

[0156] In operation S532, the transaction number allocation and asset allocation scale of the first system are determined based on the allocation relationship, the total number of transactions, and the total asset size.

[0157] According to embodiments of this disclosure, after obtaining the allocation relationship, the total number of transactions, and the total asset size from the first system, the transaction allocation amount of the first system is determined based on the product of the allocation relationship and the total number of transactions; and the asset allocation size of the first system is determined based on the product of the allocation relationship and the total asset size.

[0158] In operation S533, based on the asset allocation scale, N first loan records are selected from M loan records, and the number of N first loan records matches the transaction allocation.

[0159] According to an embodiment of this disclosure, the transaction frequency allocation is the number of first loan data selected by the first system this time, that is, the transaction frequency allocation is N.

[0160] After obtaining the asset allocation scale, the asset valuation and asset size of the selected loan data are calculated based on the transaction characteristics of the loan data itself. Then, based on the asset valuation, asset size and asset allocation scale, N first loan data are determined.

[0161] The embodiments of this disclosure obtain the allocation relationship between the first system and the second system, and determine the transaction allocation amount and asset allocation scale of the first system based on the allocation relationship, the total number of transactions and the total asset scale; and select N first loan data from M loan data based on the asset allocation scale, thereby realizing the personalized determination of the number of loan data to be selected based on the asset situation of the first system itself, avoiding additional replenishment operations and improving execution efficiency.

[0162] According to embodiments of this disclosure, based on the asset allocation scale, N first loan receipt data are selected from M loan receipt data, including: after a first screening, T sets of preliminary screening datasets are randomly determined from the M loan receipt data, each set of preliminary screening datasets includes N preliminary screening loan receipt data, T≥2; the asset valuation and asset size of the N preliminary screening loan receipt data in each set of preliminary screening datasets are calculated; if the t-th set of preliminary screening datasets meets the second screening condition, the t-th set of preliminary screening datasets is taken as the first optimal solution set, the second screening condition includes the highest asset valuation and the asset size closest to the asset allocation scale, 1≤t≤T.

[0163] After randomly deleting L initial screening loan data from the first optimal solution set, a second screening is performed to re-screen the loan data outside the first optimal solution set to obtain L second screening loan data. The L second screening loan data and (NL) initial screening loan data form a second screening dataset, 1≤L≤N. The asset valuation values ​​of the first optimal solution set and the second screening dataset are compared to determine the second optimal solution set. After a preset number of screenings and comparisons, the final optimal solution set is determined, which includes N first screening loan data.

[0164] According to embodiments of this disclosure, after determining the number of transaction allocations, the number of loan receipt data required by the first system can be determined as N. During the first screening process, T sets of initial screening datasets are obtained through T loops, and the asset valuation and asset size of the T sets of initial screening datasets are determined. Each initial screening dataset includes N initial screening loan receipt data. In each loop, N initial screening loan receipt data are randomly selected from M loan receipt data. The T sets of initial screening datasets may include identical initial screening loan receipt data or different initial screening loan receipt data.

[0165] In each iteration, after randomly acquiring a preliminary screening dataset, the asset valuation and asset size of N preliminary screening loan receipts within that dataset are calculated. After T iterations, T preliminary screening datasets are obtained, along with their corresponding asset valuations and asset sizes.

[0166] According to the embodiments of this disclosure, after determining T asset valuations and T asset sizes, the T asset valuations are arranged in descending order. The t-th preliminary screening dataset, which has the highest asset valuation and the asset size closest to the asset allocation size, is selected and used as the optimal solution in the first iteration. The N preliminary screening loan data within the t-th preliminary screening dataset are used as the first optimal solution set.

[0167] According to embodiments of this disclosure, the degree of similarity between asset size and asset allocation size can be represented by the difference between asset size and asset allocation size.

[0168] According to embodiments of this disclosure, due to the large volume of loan receipt data, random screening would result in a large amount of data not being screened, leading to the omission of valid data. Therefore, after determining the first optimal solution set through the first screening process, L initially screened loan receipt data are randomly deleted from the first optimal solution set, and then random screening and addition are performed from the M loan receipt data.

[0169] According to embodiments of this disclosure, the number of initial screening loan data deleted from the first optimal solution set can be a fixed number; it can also be a fixed proportion of the number of transactions allocated, such as 70%, 50%, or 40%.

[0170] According to embodiments of this disclosure, the purpose of the second screening is to replenish the deleted L IOU data.

[0171] In the second screening process, T sets of datasets are obtained through T iterations, and the asset valuation and asset size of the T sets of datasets are determined. Each dataset includes L loan receipts and (NL) initial screening loan receipts. In each iteration, L loan receipts are randomly selected from M loan receipts. The T sets of datasets may contain the same loan receipts or different loan receipts.

[0172] In each iteration, after randomly acquiring L datasets, the asset valuation and asset size of each dataset are calculated, i.e., the asset valuation and asset size of the L datasets and (NL) initial screening loan receipts. After T iterations, T datasets are obtained, along with their corresponding asset valuations and asset sizes. The optimal dataset, with the highest asset valuation and asset size closest to the asset allocation size, is selected from the T datasets. This optimal dataset is used as the second screening dataset, and the L loan receipts within it are used as the second screening loan receipts.

[0173] Compare the asset valuation values ​​of the first optimal solution set and the second screening dataset, and use the set or dataset with the higher asset valuation value as the second optimal solution set obtained in the second screening process.

[0174] According to the embodiments of this disclosure, the above screening and comparison are repeated. After a preset number of screenings and comparisons, the optimal solution set obtained in the last screening process is taken as the final optimal solution set, and the N final loan data in the final optimal solution set are taken as the N first loan data obtained by the branch office.

[0175] According to embodiments of this disclosure, the number of loan receipts deleted in each filtering process can be the same or different, or they can decrease in an arithmetic progression or decrease in a preset ratio.

[0176] For example, after three screening processes, 50% of the loan receipt data is deleted after the first screening process, 25% of the loan receipt data is deleted after the second screening process, and the third screening process is the final screening process.

[0177] The embodiments of this disclosure effectively reduce the adverse effects of randomness in the screening process by performing a preset number of screenings, randomly deleting a preset number of loan data after each screening process, and then adding the data again.

[0178] According to embodiments of this disclosure, the asset valuation and asset size of N initial screening loan receipts within each initial screening dataset are calculated, including:

[0179] For each of the Q secondary indicators, calculate the indicator mean and indicator variance of the N initial screening loan data to obtain the Q indicator mean and Q indicator variance corresponding to the Q secondary indicators. The secondary indicators include indicators that characterize user transaction behavior, and Q≥2.

[0180] Obtain the Q historical institutional means and Q historical institutional variances corresponding to the Q second indicators. The historical institutional means and historical institutional variances represent the historical asset status of the first system; and

[0181] The asset valuation is determined based on the mean of Q indicators, the variance of Q indicators, the mean of Q historical institutions, and the variance of Q historical institutions.

[0182] According to embodiments of this disclosure, the second indicator includes the total loan amount, loan balance, remaining loan term, and loan interest rate.

[0183] For example, in the screening of this project, the second indicator is the total loan amount. The average total loan amount of the N initially screened loan receipts is calculated and used as the indicator mean for the total loan amount. Based on the indicator mean for the total loan amount and the total loan amount of the N initially screened loan receipts, the indicator variance for the total loan amount is determined.

[0184] According to embodiments of this disclosure, the process of calculating the mean of the index satisfies:

[0185]

[0186] in, I represents the mean of the m-th second indicator for the n-th project. n m represents the number of transactions in the nth phase of the project. i This represents the value of the m-th second indicator of the i-th loan data.

[0187] The process of calculating the variance of the index satisfies:

[0188]

[0189] in, I represents the variance of the second indicator for the nth project and the mth indicator. n m represents the number of transactions in the nth phase of the project. i This represents the value of the m-th second indicator of the i-th loan data.

[0190] According to embodiments of this disclosure, the historical institutional mean and historical institutional variance respectively characterize the mean and variance of each second indicator of all historical items in the branch.

[0191] According to embodiments of this disclosure, the process of calculating the historical institutional average satisfies:

[0192]

[0193] Among them, E m Let I represent the historical institutional average of the m-th second indicator across all historical projects, and let m represent the number of transactions across all historical projects. i This represents the value of the m-th second indicator of the i-th loan data.

[0194] The process of calculating the variance of the index satisfies:

[0195]

[0196] Among them, S m Let m represent the historical institutional variance of all historical projects and the m-th second indicator, where I represents the number of transactions for all historical projects. i This represents the value of the m-th second indicator of the i-th loan data.

[0197] The mean and variance of the Q historical institutions corresponding to the Q second indicators are pre-calculated according to formulas (5) and (6). The first system can retrieve the mean and variance of the Q historical institutions corresponding to the Q second indicators from the target address.

[0198] According to embodiments of this disclosure, determining the asset valuation based on the mean of Q indicators, the variance of Q indicators, the mean of Q historical institutions, and the variance of Q historical institutions includes: determining the asset valuation based on the difference between the mean of each indicator and the mean of each historical institution, and the difference between the variance of each indicator and the variance of each historical institution.

[0199] In the embodiments of this disclosure, Q second indicators are used to jointly screen loan data to ensure that the screened loan data meets the requirements, thereby reducing the number of returned loan data, reducing return operations, and improving screening efficiency.

[0200] According to embodiments of this disclosure, the asset valuation is determined based on the mean of Q indicators, the variance of Q indicators, the mean of Q historical institutions, and the variance of Q historical institutions, including:

[0201] For each second indicator, a first evaluation value is generated if the indicator's mean is lower than the historical average of the institutions.

[0202] A second assessment value is generated when the absolute value of the indicator variance is less than the absolute value of the historical institutional variance; and

[0203] The asset valuation is obtained by combining the first and second valuation values ​​of Q secondary indicators.

[0204] According to embodiments of this disclosure, for a new project, for each second indicator, a first assessment value is generated if the indicator mean is less than the historical institutional mean; a second assessment value is generated if the indicator variance is less than the absolute value of the historical institutional variance. If the indicator variance is greater than or equal to the absolute value of the historical institutional variance and the indicator mean is greater than or equal to the historical institutional mean, no assessment value is calculated. All the obtained first and second assessment values ​​are then added together to obtain the asset assessment value.

[0205] According to embodiments of this disclosure, for an already opened loan project, the mean and variance of the loan project for a certain second indicator are calculated according to formulas (3) and (4). Then, based on the difference between the mean of each second indicator and the historical institutional mean, a set of mean offsets for Q second indicators is generated. Based on the difference between the variance of each secondary indicator and the historical institutional variance, a set of variance offsets for Q secondary indicators is generated.

[0206] Calculate the set of mean offsets The process satisfies:

[0207]

[0208] Among them, E m e represents the historical institutional mean of the m-th second indicator for all historical projects. Nm This represents the mean of the second indicator for the m-th indicator in this project.

[0209] Calculate the set of variance offsets The process satisfies:

[0210]

[0211] Among them, S m This represents the historical institutional variance of all historical items and the m-th second indicator. This represents the variance of the second indicator for the m-th indicator of the project.

[0212] According to embodiments of this disclosure, the mean value of the q-th second indicator is less than the set of mean offsets. Given the q-th mean offset, a first evaluation value is generated, where 1 ≤ q ≤ Q; the absolute value of the variance of the q-th second indicator is less than the variance offset set. Given the absolute value of the q-th mean offset, a second valuation value is generated. The asset valuation value is obtained by combining the first and second valuation values ​​of the Q second indicators.

[0213] According to the embodiments of this disclosure, the asset valuation of the loan receipt data can be calculated in accordance with the above embodiments, and the specific operations for calculating the asset valuation in each screening process will not be repeated again.

[0214] According to embodiments of this disclosure, the asset size of the loan data can be calculated according to formula (1) or (2).

[0215] Figure 6 A flowchart illustrating a method for filtering loan data according to a specific embodiment of the present disclosure is shown.

[0216] like Figure 6 As shown, the flowchart 600 of the borrowing data filtering method in a specific embodiment includes operations S601 to S614.

[0217] In operation S601, filtering is performed based on the first criterion. Specifically, filtering can be performed based on P first criteria within the first filtering conditions.

[0218] In operation S602, the allocation amount of transaction frequency and the asset allocation scale of the first system are determined. Specifically, based on the total number of transactions, the total asset size, and the allocation relationship, the allocation amount of transaction frequency and the asset allocation scale of the first system are calculated.

[0219] In operation S603, randomly extract loan receipt data. Specifically, randomly select N initial screening loan receipt data from M loan receipt data.

[0220] In operation S604, the mean, variance, and asset size of the indicators are calculated based on the second indicators. Specifically, the mean, variance, and asset size of the indicators can be calculated for N initial screening loan data based on Q second indicators.

[0221] In operation S605, the first optimal solution set in the initial screening dataset of group T in this cycle is selected. Specifically, the asset valuation is calculated based on the indicator mean and indicator variance, and the first optimal solution set is selected based on the asset valuation and asset size.

[0222] In operation S606, 50% of the first optimal solution set is randomly replaced.

[0223] In operation S607, the indicator mean, indicator variance, and asset size are calculated based on the second indicator.

[0224] In operation S608, the optimal group is selected from the T groups of loan receipt data in this cycle. The T groups of loan receipt data in this cycle include 50% of the initial screening loan receipt data and 50% of the rescreened data. The optimal group includes 50% of the initial screening loan receipt data and 50% of the second screening loan receipt data.

[0225] In operation S609, the first optimal solution set and the optimal group are compared to determine the second optimal solution set.

[0226] In operation S610, 25% of the second optimal solution set is randomly replaced.

[0227] In operation S611, the indicator mean, indicator variance, and asset size are calculated based on the second indicator.

[0228] In operation S612, select the optimal solution from N calculations.

[0229] In operation S613, select the optimal group from the borrow data of group T in this cycle.

[0230] In operation S614, the second optimal solution set and the optimal group are compared to determine the final optimal solution set.

[0231] Figure 7 A flowchart illustrating a method for filtering loan data applied to a second system according to an embodiment of the present disclosure is shown.

[0232] like Figure 7 As shown, the method 700 for filtering loan data applied to the second system in this embodiment includes operations S710 to S740.

[0233] In operation S710, a first list of promissory notes is received from at least one first system. The first system generates a first list of promissory notes, which includes identification information of at least one first promissory note data.

[0234] In operation S720, based on the identification information, R first loan data are retrieved from the database, where R ≥ 2.

[0235] In operation S730, calculate the asset valuation of R first promissory note data.

[0236] In operation S740, based on the asset valuation, S third-party loan data are determined from R first-party loan data. The S third-party loan data are used to generate transaction vouchers, where 2≤S≤R.

[0237] According to embodiments of this disclosure, the second system interacts with at least one first system, and the second system may be deployed in the head office system.

[0238] According to embodiments of this disclosure, after the second system sends a filtering instruction to at least one first system, the first system performs a filtering operation according to the filtering instruction to generate a first list of promissory notes. The second system receives the first list of promissory notes from at least one first system. The first system generates a first list of promissory notes.

[0239] According to embodiments of this disclosure, the second system needs to filter the first loan receipt data sent by the branch offices. The second system can retrieve R first loan receipt data from the database based on the identification information in the first loan receipt list. After calculating the asset appraisal value of the R first loan receipt data, based on the asset appraisal value, S third loan receipt data are determined from the R first loan receipt data, and the S third loan receipt data are used to generate transaction vouchers.

[0240] According to embodiments of this disclosure, calculating the asset valuation of R first loan receipts includes: for each of Q second indicators, calculating the overall mean and overall variance of the R first loan receipts to obtain Q overall means and Q overall variances corresponding to the Q second indicators; calling the Q historical overall means and Q historical overall variances corresponding to the Q second indicators in the second system; and calculating the asset valuation of the R first loan receipts based on the Q overall means, Q overall variances, Q historical overall means, and Q historical overall variances.

[0241] According to embodiments of this disclosure, when the asset valuation is greater than or equal to a valuation threshold, S third-party loan agreement data are determined from R first-party loan agreement data. After obtaining the S third-party loan agreement data, the second system can directly use the S third-party loan agreement data to generate transaction vouchers.

[0242] According to embodiments of this disclosure, since the data included in the first loan receipt list received by the second system from at least one first system has undergone multiple screenings, and the screening operations performed by multiple first systems are identical, the second system does not need to expend additional resources to eliminate screening differences between multiple first systems, thus improving business screening efficiency. Furthermore, the second system also achieves automatic screening of loan receipt data, eliminating the need for business personnel to manually adjust screening conditions based on experience, further improving screening efficiency.

[0243] According to embodiments of this disclosure, after determining S third loan agreement data from R first loan agreement data based on asset appraisal values, the process includes:

[0244] Based on the identification information of the (RS) first debit data that were not selected, at least one return instruction is generated, which is used to return the (RS) first debit data to the first system from which it originated;

[0245] Distribute at least one return instruction to at least one first system.

[0246] According to embodiments of this disclosure, the identification information of the first loan receipt data in the first loan receipt list includes not only the serial number of the first loan receipt data in the database, but also the identification of the first system that filters the first loan receipt data.

[0247] For example, the identification information of the first loan receipt data is XXXX-100001, where XXXX represents the identifier of the first system and 100001 represents the sequence number of the first loan receipt data in the database.

[0248] According to embodiments of this disclosure, for (RS) first loan receipt data that do not meet the requirements, at least one return instruction is generated based on the identification information of the (RS) first loan receipt data that were not selected, and the at least one return instruction is distributed to at least one first system.

[0249] According to embodiments of this disclosure, the process of the first system determining the optimal solution set and the process of the second system performing the screening can both be improved by introducing artificial intelligence algorithms such as genetic algorithms, ant colony algorithms, and simulated annealing algorithms to enhance the screening efficiency.

[0250] Figure 8 A schematic block diagram of a device for filtering loan data applied to a first system according to an embodiment of the present disclosure is shown.

[0251] like Figure 8 As shown, the filtering device 800 for loan data applied to the first system in this embodiment includes a first receiving module 810, a first filtering module 820, a second filtering module 830, a generating module 840, and a sending module 850.

[0252] The first receiving module 810 is configured to, in response to receiving a filtering instruction from the second system, parse the filtering instruction to obtain the first filtering condition, the total number of transactions, and the total asset size. In one embodiment, the first receiving module 810 may be used to execute the operation S210 described above, which will not be repeated here.

[0253] The first filtering module 820 is used to filter M loan receipt data from the database according to a first filtering condition. The loan receipt data includes user attribute information and information generated during the transaction process, where M ≥ 2. In one embodiment, the first filtering module 820 can be used to perform the operation S220 described above, which will not be repeated here.

[0254] The second filtering module 830 is used to filter N first loan receipt data from M loan receipt data based on the total number of transactions and the total asset size, where 2≤N≤M. In one embodiment, the second filtering module 830 can be used to perform the operation S230 described above, which will not be repeated here.

[0255] The generation module 840 is used to generate a first loan receipt list based on N first loan receipt data. The first loan receipt list includes identification information of the N first loan receipt data. In one embodiment, the generation module 840 can be used to perform the operation S240 described above, which will not be repeated here.

[0256] The sending module 850 is used to send the first IOU list to the second system. In one embodiment, the sending module 850 can be used to perform the operation S250 described above, which will not be repeated here.

[0257] According to embodiments of this disclosure, the filtering device 800 for the loan data applied to the first system further includes: a third receiving module, a third filtering module, a return list generation module, and a return list sending module.

[0258] The third receiving module is used to respond to a return instruction received from the second system, parse the return instruction, and obtain the number of returns and the scale of returned assets. In one embodiment, the third receiving module can be used to perform the operation S310 described above, which will not be repeated here.

[0259] The third filtering module is used to filter at least one second loan receipt from M loan receipt data based on the number of returns and the scale of returned assets. In one embodiment, the third filtering module can be used to perform the operation S320 described above, which will not be repeated here.

[0260] The return list generation module is used to generate a second promissory note list based on at least one second promissory note data. In one embodiment, the return list generation module can be used to perform the operation S330 described above, which will not be repeated here.

[0261] The return list sending module is used to send the second IOU list to the second system. In one embodiment, the return list sending module can be used to perform the operation S340 described above, which will not be repeated here.

[0262] According to an embodiment of this disclosure, the first screening module 820 includes a first screening submodule, used to screen M loan data from the database that include P first indicators and satisfy P screening thresholds.

[0263] According to embodiments of this disclosure, the second screening module 830 includes a second screening submodule, a third screening submodule, and a fourth screening submodule.

[0264] The second filtering submodule is used to obtain the allocation relationship between the first system and the second system, including the allocation ratio of the first system to the second system. In one embodiment, the return list sending module can be used to perform the operation S531 described above, which will not be repeated here.

[0265] The third filtering submodule is used to determine the transaction allocation amount and asset allocation scale of the first system based on the allocation relationship, the total number of transactions, and the total asset size. In one embodiment, the return list sending module can be used to perform the operation S532 described above, which will not be repeated here.

[0266] The fourth filtering submodule is used to filter N first loan records from M loan records based on the asset allocation scale, where the number of N first loan records corresponds to the transaction allocation. In one embodiment, the return list sending module can be used to execute the operation S533 described above, which will not be repeated here.

[0267] According to embodiments of this disclosure, the fourth screening submodule includes a first screening unit, a second screening unit, a third screening unit, a fourth screening unit, a fifth screening unit, and a sixth screening unit.

[0268] The first screening unit is used to randomly select T sets of initial screening datasets from M loan receipt data after the first screening. Each set of initial screening datasets includes N initial screening loan receipt data, and T≥2.

[0269] The second screening unit is used to calculate the asset valuation and asset size of N initial screening loan data in each initial screening dataset.

[0270] The third screening unit is used to select the t-th preliminary screening dataset as the first optimal solution set if the t-th preliminary screening dataset meets the second screening condition. The second screening condition includes the highest asset valuation and the asset size being closest to the asset allocation size, 1≤t≤T.

[0271] The fourth screening unit is used to randomly delete L initial screening loan data from the first optimal solution set, and then, after a second screening, re-screen the loan data outside the first optimal solution set to obtain L second screening loan data. The L second screening loan data and (NL) initial screening loan data are then combined to form a second screening dataset, where 1≤L≤N.

[0272] The fifth screening unit is used to compare the asset valuation values ​​of the first optimal solution set and the second screening dataset to determine the second optimal solution set.

[0273] The sixth filtering unit is used to determine the final optimal solution set after a preset number of filtering and comparisons. The final optimal solution set includes N first loan data.

[0274] According to embodiments of this disclosure, the second screening unit includes a first screening subunit, a second screening subunit, and a calculation subunit.

[0275] The first screening subunit is used to calculate the mean and variance of the N initial screening loan data for each of the Q second indicators, so as to obtain the mean and variance of the Q indicators corresponding to the Q second indicators. The second indicators include indicators that characterize user transaction behavior, and Q≥2.

[0276] The second screening subunit is used to obtain the mean and variance of Q historical institutions corresponding to the Q second indicators. The mean and variance of historical institutions represent the historical asset status of the first system.

[0277] The calculation subunit is used to determine the asset valuation based on the mean of Q indicators, the variance of Q indicators, the mean of Q historical institutions, and the variance of Q historical institutions.

[0278] According to embodiments of this disclosure, the calculation subunit is further configured to generate a first evaluation value for each second indicator when the indicator mean is less than the historical institutional mean.

[0279] A second assessment value is generated when the absolute value of the indicator variance is less than the absolute value of the historical institutional variance; and

[0280] The asset valuation is obtained by combining the first and second valuation values ​​of Q secondary indicators.

[0281] According to embodiments of this disclosure, any multiple modules among the first receiving module 810, the first filtering module 820, the second filtering module 830, the generating module 840, and the sending module 850 can be combined into one module, or any one of these modules can be split into multiple modules. Alternatively, at least some of the functions of one or more of these modules can be combined with at least some of the functions of other modules and implemented in one module.

[0282] According to embodiments of this disclosure, at least one of the first receiving module 810, the first filtering module 820, the second filtering module 830, the generating module 840, and the transmitting module 850 can be at least partially implemented as hardware circuitry, such as a field-programmable gate array (FPGA), a programmable logic array (PLA), a system-on-a-chip, a system-on-a-substrate, a system-on-package, an application-specific integrated circuit (ASIC), or any other reasonable method of integrating or packaging the circuitry, or implemented in software, hardware, or firmware, or in any suitable combination of any of these three methods. Alternatively, at least one of the first receiving module 810, the first filtering module 820, the second filtering module 830, the generating module 840, and the transmitting module 850 can be at least partially implemented as a computer program module, which, when run, can perform corresponding functions.

[0283] Figure 9 A schematic block diagram of a device for filtering loan data applied to a second system according to an embodiment of the present disclosure is shown.

[0284] like Figure 9 As shown, the filtering device 900 for loan data applied to the second system in this embodiment includes a second receiving module 910, an acquisition module 920, a calculation module 930, and a determination module 940.

[0285] The second receiving module 910 is configured to receive a first loan receipt list from at least one first system. The first system generates a first loan receipt list, which includes identification information for at least one first loan receipt. In one embodiment, the second receiving module 910 may be used to perform the operation S710 described above, which will not be repeated here.

[0286] The acquisition module 920 is used to retrieve R first loan receipt data from the database based on the identification information, where R ≥ 2. In one embodiment, the acquisition module 920 can be used to perform the operation S720 described above, which will not be repeated here.

[0287] The calculation module 930 is used to calculate the asset valuation of R first loan receipts. In one embodiment, the calculation module 930 can be used to perform the operation S730 described above, which will not be repeated here.

[0288] The determining module 940 is used to determine S third-party loan data from R first-party loan data based on the asset appraisal value. These S third-party loan data are used for asset securitization, where 2 ≤ S ≤ R. In one embodiment, the determining module 940 can be used to perform the operation S740 described above, which will not be repeated here.

[0289] According to embodiments of this disclosure, the filtering device 900 for loan data applied to the second system further includes: a return instruction generation module and a return module.

[0290] The return instruction generation module is used to generate at least one return instruction based on the identification information of the (RS) first loan data that were not selected. The return instruction is used to return the (RS) first loan data to the source first system.

[0291] The rollback module is used to distribute at least one rollback instruction to at least one first system.

[0292] According to embodiments of this disclosure, any multiple modules among the second receiving module 910, the acquiring module 920, the calculating module 930, and the determining module 940 can be combined into one module, or any one of these modules can be split into multiple modules. Alternatively, at least some of the functions of one or more of these modules can be combined with at least some of the functions of other modules and implemented in one module.

[0293] According to embodiments of this disclosure, at least one of the second receiving module 910, acquiring module 920, calculating module 930, and determining module 940 can be at least partially implemented as hardware circuitry, such as a field-programmable gate array (FPGA), a programmable logic array (PLA), a system-on-a-chip, a system-on-a-substrate, a system-on-package, an application-specific integrated circuit (ASIC), or any other reasonable method of integrating or packaging circuitry, or implemented in software, hardware, or firmware, or in any suitable combination of any of these three methods. Alternatively, at least one of the second receiving module 910, acquiring module 920, calculating module 930, and determining module 940 can be at least partially implemented as a computer program module, which, when run, can perform corresponding functions.

[0294] Figure 10 A block diagram of an electronic device suitable for a data filtering method according to an embodiment of the present disclosure is shown schematically.

[0295] like Figure 10As shown, an electronic device 1000 according to an embodiment of the present disclosure includes a processor 1001, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage portion 1008 into a random access memory (RAM) 1003. The processor 1001 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or an associated chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 1001 may also include onboard memory for caching purposes. The processor 1001 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.

[0296] RAM 1003 stores various programs and data required for the operation of electronic device 1000. Processor 1001, ROM 1002, and RAM 1003 are interconnected via bus 1004. Processor 1001 performs various operations of the method flow according to embodiments of the present disclosure by executing programs in ROM 1002 and / or RAM 1003. It should be noted that the programs may also be stored in one or more memories other than ROM 1002 and RAM 1003. Processor 1001 may also perform various operations of the method flow according to embodiments of the present disclosure by executing programs stored in said one or more memories.

[0297] According to embodiments of this disclosure, the electronic device 1000 may further include an input / output (I / O) interface 1005, which is also connected to a bus 1004. The electronic device 1000 may also include one or more of the following components connected to the I / O interface 1005: an input section 1006 including a keyboard, mouse, etc.; an output section 1007 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 1008 including a hard disk, etc.; and a communication section 1009 including a network interface card such as a LAN card, modem, etc. The communication section 1009 performs communication processing via a network such as the Internet. A drive 1010 is also connected to the I / O interface 1005 as needed. A removable medium 1011, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on the drive 1010 as needed so that computer programs read from it can be installed into the storage section 1008 as needed.

[0298] This disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or it may exist independently and not assembled into the device / apparatus / system. The computer-readable storage medium carries one or more programs that, when executed, implement the method according to the embodiments of this disclosure.

[0299] According to embodiments of this disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, such as including, but not limited to: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this disclosure, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, according to embodiments of this disclosure, the computer-readable storage medium may include ROM 1002 and / or RAM 1003 and / or one or more memories other than ROM 1002 and RAM 1003 described above.

[0300] Embodiments of this disclosure also include a computer program product comprising a computer program containing program code for performing the methods shown in the flowchart. When the computer program product is run on a computer system, the program code enables the computer system to implement the loan data filtering method provided in embodiments of this disclosure.

[0301] When the computer program is executed by the processor 1001, it performs the functions defined in the system / apparatus of this disclosure embodiments. According to embodiments of this disclosure, the systems, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0302] In one embodiment, the computer program may rely on a tangible storage medium such as an optical storage device or a magnetic storage device. In another embodiment, the computer program may also be transmitted and distributed in the form of signals over a network medium, and may be downloaded and installed via the communication section 1009, and / or installed from a removable medium 1011. The program code contained in the computer program can be transmitted using any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination thereof.

[0303] In such an embodiment, the computer program can be downloaded and installed from a network via communication section 1009, and / or installed from removable medium 1011. When the computer program is executed by processor 1001, it performs the functions defined in the system of this disclosure embodiment. According to embodiments of this disclosure, the systems, devices, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0304] According to embodiments of this disclosure, program code for executing the computer programs provided in embodiments of this disclosure can be written in any combination of one or more programming languages. Specifically, these computational programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, languages ​​such as Java, C++, Python, "C", or similar programming languages. The program code can execute entirely on the user's computing device, partially on the user's device, partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0305] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0306] Those skilled in the art will understand that the features described in the various embodiments and / or claims of this disclosure can be combined or combined in various ways, even if such combinations or combinations are not explicitly described in this disclosure. In particular, the features described in the various embodiments and / or claims of this disclosure can be combined or combined in various ways without departing from the spirit and teachings of this disclosure. All such combinations and / or combinations fall within the scope of this disclosure.

[0307] The specific embodiments described above further illustrate the purpose, technical solutions, and beneficial effects of this disclosure. It should be understood that the above descriptions are merely specific embodiments of this disclosure and are not intended to limit this disclosure. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this disclosure should be included within the protection scope of this disclosure.

Claims

1. A method for filtering loan receipt data, applied to a first system, the method comprising: In response to receiving a filtering instruction from the second system, the filtering instruction is parsed to obtain the first filtering condition, the total number of transactions, and the total asset size; Based on the first filtering condition, M loan data are obtained from the database. The loan data includes user attribute information and information generated during the transaction process, where M≥2. Based on the total number of transactions and the total asset size, select N first loan records from the M loan records, where 2≤N≤M; A first loan receipt list is generated based on the N first loan receipt data, and the first loan receipt list includes the identification information of the first loan receipt data; as well as Send the first list of promissory notes to the second system; The step of selecting N first loan records from the M loan records based on the total number of transactions and the total asset size includes: Obtain the allocation relationship between the first system and the second system, wherein the allocation relationship includes the allocation ratio of the first system to the second system; The transaction number allocation of the first system is determined by multiplying the allocation relationship and the total number of transactions; the asset allocation scale of the first system is determined by multiplying the allocation relationship and the total asset size. Based on the asset allocation scale, N first loan records are selected from the M loan records, and the number of the N first loan records corresponds to the transaction number allocation.

2. The method according to claim 1, further comprising: In response to receiving a return instruction from the second system, the return instruction is parsed to obtain the number of returns and the scale of the returned assets; Based on the number of returned assets and the scale of returned assets, at least one second loan record is obtained by filtering from the M loan record data; A second list of promissory notes is generated based on the at least one second promissory note data; as well as Send the second list of promissory notes to the second system.

3. The method according to claim 1, wherein, The first screening condition includes P first indicators and a screening threshold for the first indicators. The first indicators include attribute indicators, and P≥1. The step of filtering M loan receipts from the database according to the first filtering condition includes: Select M loan data from the database that include the P first indicators and satisfy the P selection thresholds.

4. The method according to claim 1, wherein, The step of selecting the N first loan receipts from the M loan receipts based on the asset allocation scale includes: After the first screening, T sets of preliminary screening datasets are randomly selected from the M loan receipt data. Each set of preliminary screening datasets includes N preliminary screening loan receipt data, and T≥2. Calculate the asset valuation and asset size of N initial screening loan receipts within each initial screening dataset; If the t-th preliminary screening dataset meets the second screening condition, the t-th preliminary screening dataset is taken as the first optimal solution set. The second screening condition includes the highest asset valuation and the asset size being closest to the asset allocation size, 1≤t≤T. After randomly deleting L initial screening loan data from the first optimal solution set, after a second screening, L second screening loan data are obtained from the loan data outside the first optimal solution set. The L second screening loan data and (NL) initial screening loan data are combined to form a second screening dataset, where 1≤L≤N. By comparing the asset valuations of the first optimal solution set and the second screening dataset, a second optimal solution set is determined; and After a preset number of screening and comparisons, the final optimal solution set is determined, which includes the N first loan data.

5. The method according to claim 4, wherein, The calculation of the asset valuation and asset size of N preliminary screening loan receipts within each preliminary screening dataset includes: For each of the Q second indicators, calculate the indicator mean and indicator variance of the N initial screening loan data to obtain the Q indicator mean and Q indicator variance corresponding to the Q second indicators. The second indicators include indicators characterizing user transaction behavior, and Q≥2. Obtain the Q historical institutional means and Q historical institutional variances corresponding to the Q second indicators, wherein the historical institutional means and the historical institutional variances characterize the historical asset status of the first system; and The asset valuation is determined based on the mean of the Q indicators, the variance of the Q indicators, the mean of the Q historical institutions, and the variance of the Q historical institutions.

6. The method according to claim 5, wherein, The step of determining the asset valuation based on the mean of the Q indicators, the variance of the Q indicators, the mean of the Q historical institutions, and the variance of the Q historical institutions includes: For each second indicator, if the mean of the indicator is less than the historical average of the institution, a first evaluation value is generated; If the absolute value of the variance of the stated indicator is less than the absolute value of the variance of the historical institutions, a second evaluation value is generated; and The asset valuation is obtained by combining the first and second valuation values ​​of the Q second indicators.

7. A method for filtering loan data, applied to a second system, wherein the second system performs interactive operations with at least one first system as described in any one of claims 1 to 6, the method comprising: Receive a first list of promissory notes from at least one first system, wherein the first system generates a first list of promissory notes, and the first list of promissory notes includes identification information of at least one first promissory note data; Based on the identification information, retrieve R first loan receipt data from the database, where R ≥ 2; Calculate the asset valuation of the R first loan receipts; Based on the asset valuation, S third loan receipts are determined from the R first loan receipts. The S third loan receipts are used to generate transaction vouchers, where 2 ≤ S ≤ R.

8. The method according to claim 7, wherein, After determining S third loan receipts from the R first loan receipts based on the asset valuation, the process includes: Based on the identification information of the (RS) first loan data that were not selected, at least one return instruction is generated, the return instruction being used to return the (RS) first loan data to the first system from which they originated; Distribute the at least one return instruction to the at least one first system.

9. A data filtering device for loan receipts, applied in a first system, the filtering device comprising: The first receiving module is configured to respond to receiving a filtering instruction from the second system, parse the filtering instruction, and obtain the first filtering condition, the total number of transactions, and the total asset size; The first filtering module is used to filter M loan data from the database according to the first filtering condition. The loan data includes user attribute information and information generated during the transaction process, where M≥2. The second filtering module is used to filter N first loan data from the M loan data based on the total number of transactions and the total asset size, where 2≤N≤M; The generation module is used to generate a first loan list based on the N first loan data, wherein the first loan list includes the identification information of the N first loan data; as well as The sending module is used to send the first list of promissory notes to the second system; The second filtering module is also used for: Obtain the allocation relationship between the first system and the second system, wherein the allocation relationship includes the allocation ratio of the first system to the second system; The transaction number allocation of the first system is determined by multiplying the allocation relationship and the total number of transactions; the asset allocation scale of the first system is determined by multiplying the allocation relationship and the total asset size. Based on the asset allocation scale, N first loan records are selected from the M loan records, and the number of the N first loan records corresponds to the transaction number allocation.

10. A data filtering device for loan documents, applied to a second system, the second system performing interactive operations with at least one first system as described in any one of claims 1 to 6, the filtering device comprising: The second receiving module is used to receive a first loan list from the at least one first system, wherein the first system generates a first loan list, and the first loan list includes identification information of at least one first loan data. The acquisition module is used to acquire R first loan receipt data from the database based on the identification information, where R≥2; The calculation module is used to calculate the asset valuation of the R first loan receipts; The determination module is used to determine S third loan data from the R first loan data based on the asset valuation, and the S third loan data are used for asset securitization, where 2≤S≤R.

11. An electronic device, comprising: One or more processors; Storage device for storing one or more programs. Wherein, when the one or more programs are executed by the one or more processors, the one or more processors perform the method according to any one of claims 1 to 8.

12. A computer-readable storage medium having stored thereon executable instructions that, when executed by a processor, cause the processor to perform the method according to any one of claims 1 to 8.

13. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1 to 8.

Images