Loan credit audit optimization method and device, electronic equipment and readable storage medium

Abstract

The application discloses a loan credit audit optimization method and device, electronic equipment and a readable storage medium, which are applied to the technical field of financial technology. The loan credit audit optimization method comprises the following steps: collecting face data of a target user; performing credit level evaluation on the target user while performing face recognition on the target user according to the face data; if it is detected that the credit level of the target user does not meet a preset level and / or the face recognition of the target user fails, determining that the loan credit audit result of the target user is failed; and if it is detected that the credit level of the target user meets the preset level and the face recognition of the target user is passed, determining that the loan credit audit result of the target user is passed. The application solves the technical problem of low efficiency of loan credit audit.

Description

Technical Field

[0001] This application relates to the field of financial technology (Fintech), and in particular to a method, apparatus, electronic device, and readable storage medium for optimizing loan credit assessment. Background Technology

[0002] With the continuous development of fintech, especially internet-based fintech, more and more technologies are being applied in the financial sector. However, the financial industry is also placing higher demands on these technologies, such as on the creditworthiness of users. When a user takes out a loan, that is, when the user's credit data is relatively rich, there may be situations where the user is unable to repay the loan, or where someone impersonates another person. Therefore, it is necessary to verify the user's creditworthiness and identity information.

[0003] Currently, a sequential review mechanism is typically used. That is, when a user's identity information is detected to match their corresponding identity credentials, the user's credit level is assessed in order to review the user's loan credit. However, because the detection of user identity information and the assessment of credit level take a long time, the loan credit review process is lengthy, resulting in low efficiency. Summary of the Invention

[0004] The main objective of this application is to provide a method, apparatus, electronic device, and readable storage medium for optimizing loan credit review, aiming to solve the technical problem of low efficiency in loan credit review in the prior art.

[0005] To achieve the above objectives, this application provides a method for optimizing loan credit review, the method comprising:

[0006] Collect facial data of the target user;

[0007] While performing facial recognition on the target user based on the facial data, the credit level of the target user is also assessed.

[0008] If the credit level of the target user is found to be inconsistent with the preset level, and / or the facial recognition of the target user fails, then the loan credit review result of the target user is determined to be unsuccessful.

[0009] If the target user's credit level is detected to meet the preset level and the target user's facial recognition is successful, then the target user's loan credit review result is determined to be successful.

[0010] To achieve the above objectives, this application also provides a loan credit review optimization device, which includes:

[0011] The data acquisition module is used to collect facial data from the target user.

[0012] A parallel module is used to perform face recognition on the target user based on the face data and simultaneously assess the credit level of the target user.

[0013] The first determination module is used to determine that the loan credit review result of the target user is unsuccessful if it is detected that the credit level of the target user does not meet the preset level, and / or the face recognition of the target user fails.

[0014] The second determination module is used to determine that the loan credit review result of the target user is passed if the target user's credit level meets the preset level and the target user's face recognition is successful.

[0015] This application also provides an electronic device, the electronic device comprising: a memory, a processor, and a program of the loan credit review optimization method stored in the memory and executable on the processor, wherein when the program of the loan credit review optimization method is executed by the processor, it can implement the steps of the loan credit review optimization method as described above.

[0016] This application also provides a computer-readable storage medium storing a program for implementing a loan credit review optimization method, wherein when the program for the loan credit review optimization method is executed by a processor, it implements the steps of the loan credit review optimization method as described above.

[0017] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the loan credit review optimization method described above.

[0018] This application provides a method, apparatus, electronic device, and readable storage medium for optimizing loan credit review. Compared to a serial review mechanism, which assesses a user's creditworthiness upon detecting that their identity information matches their corresponding identity credential, this application collects the target user's facial data. Simultaneously, it performs facial recognition on the target user based on the facial data and assesses their creditworthiness. If the target user's creditworthiness does not meet a preset level, and / or the facial recognition fails, the loan credit review result is deemed unsuccessful. Conversely, if the target user's creditworthiness meets the preset level and the facial recognition passes, the loan credit review result is deemed successful. By simultaneously assessing the user's creditworthiness during the lengthy facial recognition process, the time required for loan credit review is reduced to some extent, thus improving the efficiency of loan credit review. Attached Figure Description

[0019] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0020] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a flowchart illustrating the first embodiment of the optimized loan credit review method for this application.

[0022] Figure 2 This is a sequence diagram of the credit level assessment process in one scenario involved in the optimized credit review method for this loan application.

[0023] Figure 3 This is a sequence diagram of the credit rating process in a scenario where there is an abnormal database in the parallel query database, which is involved in the credit review optimization method for this loan application.

[0024] Figure 4 This is a sequence diagram of the credit rating process in another scenario involving the optimization method for credit review of this loan application, when there is an abnormal database in the parallel query database;

[0025] Figure 5 This is a schematic diagram of the device structure involved in the optimized loan credit review method for this application;

[0026] Figure 6 This is a schematic diagram of the hardware operating environment involved in the loan credit review optimization method in this application embodiment.

[0027] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0028] To make the above-mentioned objectives, features, and advantages of this application more apparent and understandable, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of this application, and not all embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0029] Example 1

[0030] This application provides a method for optimizing loan credit review. In the first embodiment of this loan credit review optimization method, refer to... Figure 1 The loan credit review optimization method includes:

[0031] Step S10: Collect facial data of the target user;

[0032] In this embodiment, it should be noted that the target user is a user who has applied for a loan from a bank and is waiting for a loan credit review.

[0033] In this embodiment, the target user is verified by SMS and / or password. After the SMS verification and / or password verification is detected to be successful, the target user's facial data is collected.

[0034] In one feasible embodiment, facial data of the target user is collected by a camera device.

[0035] Step S20: While performing facial recognition on the target user based on the facial data, assess the credit level of the target user.

[0036] In one feasible embodiment, the credit data corresponding to the target user is obtained, and the credit level of the target user is assessed based on the credit data and a pre-trained credit level prediction model to obtain a credit level result.

[0037] In another feasible embodiment, credit data corresponding to the target user is obtained, and transaction behavior detection is performed on the user based on the credit data.

[0038] In step S20, after the step of performing facial recognition on the target user based on the facial data and simultaneously assessing the target user's credit level, the method further includes:

[0039] Step D10: If the credit level of the target user is detected to be in line with the preset level and the face recognition process of the target user has not ended, then stop face recognition of the user and initiate call recognition for the target user.

[0040] Understandably, while both facial recognition and credit assessment processes take a long time, if the complexity of the target user's facial recognition is high, or if the camera that collects the target user's facial data has not been maintained for a long time, resulting in insufficient clarity of the collected facial data, the facial recognition process may take too long. In other words, the facial recognition process may take longer than the credit assessment process, leading to lower efficiency in loan credit review.

[0041] Step D20: If the call identification of the target user is detected as successful, the loan review result of the target user is determined to be successful.

[0042] In one feasible embodiment, if the call identification of the target user fails, the loan review result of the target user is determined to be unsuccessful.

[0043] In this embodiment, if the target user's credit level is detected to meet the preset level, and the target user's facial recognition process has not ended, then facial recognition of the user is stopped, and call recognition is initiated for the target user. If the facial recognition process is lengthy, call recognition is promptly initiated for the target user. This avoids the technical defects where the facial recognition process takes longer than the credit level assessment process because the complexity of the target user's facial recognition is high, or the camera that collects the target user's facial data has not been maintained for a long time, resulting in insufficient clarity of the collected facial data. Therefore, the efficiency of loan credit review is improved.

[0044] Step S30: If it is detected that the credit level of the target user does not meet the preset level, and / or the facial recognition of the target user fails, then the loan credit review result of the target user is determined to be unsuccessful.

[0045] In one feasible embodiment, if it is detected that the credit level of the target user does not meet the preset level, the loan credit review result of the target user is determined to be unsuccessful.

[0046] In another feasible embodiment, if the facial recognition of the target user fails, the loan credit review result of the target user is determined to be unsuccessful.

[0047] In another feasible embodiment, if it is detected that the credit level of the target user does not meet the preset level and the facial recognition of the target user fails, then the loan credit review result of the target user is determined to be unsuccessful.

[0048] Step S40: If the credit level of the target user is detected to meet the preset level and the facial recognition of the target user is passed, then the loan credit review result of the target user is determined to be passed.

[0049] This application provides an optimized method for loan credit review. Compared to a sequential review mechanism, which assesses a user's creditworthiness upon detecting that their identity information matches their corresponding identity credential, this application collects the target user's facial data. Simultaneously, it performs facial recognition on the target user based on the facial data and assesses their creditworthiness. If the target user's creditworthiness does not meet a preset level, and / or the facial recognition fails, the loan credit review result is deemed unsuccessful. Conversely, if the target user's creditworthiness meets the preset level and the facial recognition passes, the loan credit review result is deemed successful. By simultaneously assessing the user's creditworthiness during the lengthy facial recognition process, the loan credit review time is reduced to some extent, thus improving efficiency.

[0050] Example 2

[0051] Furthermore, based on the first embodiment of this application, in another embodiment of this application, the content that is the same as or similar to that in Embodiment 1 above can be referred to the above description and will not be repeated hereafter. Based on this, in step S20, the step of assessing the credit level of the target user includes:

[0052] Step S21: Obtain multiple credit databases of the target user, and divide the multiple credit databases into multiple parallel query databases and at least one serial query database;

[0053] In one feasible embodiment, multiple credit databases containing the credit data of the target user are acquired.

[0054] In one feasible embodiment, the plurality of credit databases are randomly divided into a plurality of parallel query databases and at least one serial query database.

[0055] In another feasible embodiment, the plurality of credit databases are divided into multiple batches of parallel query databases and at least one serial query database.

[0056] In step S21, the step of dividing the plurality of credit databases into a plurality of parallel query databases and at least one serial query database includes:

[0057] Step A10: Obtain the database correlation between each of the credit reporting databases;

[0058] In this embodiment, it should be noted that the database correlation refers to the correlation between the credit data corresponding to the target users in each pair of credit databases.

[0059] It is understandable that, since a single transaction by a target user may be linked to multiple sources—for example, if a target user places an order on a social media platform and pays through a payment platform—the database correlation between the credit database that sources credit information from the social media platform and the credit database that sources credit information from the payment platform is relatively high.

[0060] In one feasible embodiment, the credit data of the target user in each of the credit databases is obtained; and database associations between each of the credit databases are generated based on the source of formation of each of the credit data.

[0061] Step A20: Based on the correlation of each database, the multiple credit reporting databases are divided into multiple parallel query databases and at least one serial query database. The correlation between any two databases in each parallel query database is less than or equal to a preset correlation threshold, and the correlation between any database in each serial query database and any database in each parallel query database is greater than the preset correlation threshold.

[0062] In one feasible embodiment, if the correlation of each of the databases is less than or equal to the first correlation threshold, then each of the credit databases is directly used as the plurality of parallel query databases.

[0063] In another feasible embodiment, multiple parallel query databases are selected from the multiple credit reporting databases such that the corresponding database correlation is less than or equal to the preset correlation threshold, and the databases other than the multiple parallel query databases in the multiple credit reporting databases are used as at least one serial query database.

[0064] It is understandable that when there is a high correlation between two databases in the parallel query database, since the subsequent transaction behavior detection of the target user is performed simultaneously based on the credit data of the target user in each of the parallel query databases, resulting in multiple parallel transaction behavior detection results, there may be cases where the parallel transaction behavior detection results corresponding to the credit data of the target user in the parallel query database with high database correlation are inaccurate. This would lead to inaccurate credit level assessment and thus inaccurate loan credit review.

[0065] In this embodiment, by selecting multiple parallel query databases from the multiple credit databases such that the correlation between the corresponding databases is less than or equal to the preset correlation threshold, the risk of inaccurate parallel transaction behavior detection results corresponding to the credit data of the target user in parallel query databases with high database correlation is avoided. This is because the subsequent transaction behavior detection results are obtained by simultaneously detecting the target user's transaction behavior based on the credit data of the target user in each of the parallel query databases, resulting in multiple parallel transaction behavior detection results. Therefore, the accuracy of credit level assessment is improved, that is, the accuracy of loan credit review is improved.

[0066] In step S21, the step of dividing the plurality of credit databases into a plurality of parallel query databases and at least one serial query database includes:

[0067] Step B10: Determine the weight of each of the credit databases in judging the transaction behavior of the target user;

[0068] In this embodiment, it should be noted that the weight is used to characterize the contribution of the credit database to the determination of the target user's transaction behavior.

[0069] In one feasible embodiment, the number of transactions and / or transaction amount of the target user in each of the credit reporting databases are accumulated, and any database in each of the credit reporting databases is selected as the selected database. Based on the number of transactions and / or transaction amount of the target user in the selected database, the weight of the selected database for judging the transaction behavior of the target user is generated.

[0070] Understandably, the more transactions a target user makes in a credit database, the more frequently the target user is using the corresponding database source. Therefore, this method is more accurate in identifying the target user's transaction behavior. Similarly, the larger the transaction amount of a target user in a credit database, the more important the corresponding database source is. Therefore, this method is also more accurate in identifying the target user's transaction behavior.

[0071] Step B20: Divide the multiple credit databases into multiple parallel query databases with corresponding weights greater than the first preset weight threshold, and at least one serial query database with corresponding weights less than or equal to the first preset weight threshold.

[0072] It is understandable that if one or more credit databases with low weights are set in multiple parallel query databases, since their contribution to the determination of the target user's transaction behavior is low, even if the target user's transaction behavior is determined first based on them, there may be a waste of identification time, resulting in low efficiency of credit level assessment.

[0073] In this embodiment, by dividing the multiple credit databases into multiple parallel query databases with corresponding weights greater than a first preset weight threshold, and at least one serial query database with corresponding weights less than or equal to the first preset weight threshold, the credit databases with higher weights are assigned to the parallel query databases, thereby avoiding the potential waste of identification time and improving the efficiency of credit level assessment.

[0074] Step S22: Simultaneously, based on the credit data of the target user in each of the parallel query databases, transaction behavior detection is performed on the target user to obtain multiple parallel transaction behavior detection results;

[0075] In one feasible embodiment, reference is made to Figure 2 , Figure 2 This is a sequence diagram of the credit level assessment process in a scenario involved in the optimized loan credit review method of this application. The business system calls the credit level assessment engine to simultaneously initiate credit data queries for the target user to each of the parallel query databases. The credit data of the target user obtained from the queries is sent to the credit level assessment engine through each of the parallel query databases. The credit level assessment engine then performs transaction behavior detection on the target user based on the credit data of the target user in each of the parallel query databases, and obtains multiple parallel transaction behavior detection results.

[0076] Step S23: If all the parallel transaction behavior detection results are detected as normal transaction behavior results, then select any database that is not used as the basis for the transaction behavior detection of the target user in each of the serial query databases as the target database, and perform transaction behavior detection on the target user according to the credit data of the target user in the target database to obtain the serial transaction behavior detection result;

[0077] In one feasible embodiment, if abnormal transaction behavior results are detected in each of the parallel transaction behavior detection results, it is determined that the credit level of the target user does not meet the preset level.

[0078] In one feasible embodiment, the database that is not used as the basis for detecting the transaction behavior of the target user and has the largest corresponding weight is selected from each of the serial query databases as the target database.

[0079] In another feasible embodiment, if it is detected that all the parallel transaction behavior detection results of the previous batch are normal transaction behavior results, then at the same time, according to the credit data of the target user in each parallel query database of the current batch, transaction behavior detection is performed on the target user respectively to obtain multiple parallel transaction behavior detection results of the current batch.

[0080] In another feasible embodiment, if the detection results of each batch of parallel transaction behavior are all normal transaction results, then the step of selecting any database that is not used as the basis for the detection of the target user's transaction behavior in each of the serial query databases is executed.

[0081] In one feasible embodiment, reference is made to Figure 2 If all the parallel transaction detection results are detected as normal transaction results, the credit level assessment engine initiates a credit data query for the target user to the serial query database A. The credit data of the target user obtained from the query is sent to the credit level assessment engine through the serial query database A. The credit level assessment engine then performs transaction behavior detection on the target user based on the credit data of the target user in the serial query database A to obtain the serial transaction behavior detection result.

[0082] In this embodiment, the target user's transaction behavior is first detected based on the database with the highest corresponding weight, thereby avoiding the waste of time that may be wasted on unnecessary identification and thus improving the efficiency of credit level assessment.

[0083] Step S24: If the serial transaction behavior detection result is detected as a normal transaction behavior result, then return to the step of selecting any database that is not used as the basis for the transaction behavior detection of the target user as the target database in each of the serial query databases, until the serial transaction behavior detection result is detected as an abnormal transaction behavior result or all of the serial query databases have been selected.

[0084] In one feasible embodiment, reference is made to Figure 2If the serial transaction behavior detection result corresponding to the serial query database A is detected as a normal transaction behavior result, then the credit level assessment engine initiates a credit data query for the target user to the serial query database B. The credit data of the target user obtained from the query is sent to the credit level assessment engine through the serial query database B. The credit level assessment engine then performs transaction behavior detection on the target user based on the credit data of the target user in the serial query database B to obtain the serial transaction behavior detection result.

[0085] Step S25: If the serial transaction behavior detection result is detected as an abnormal transaction behavior result, then it is determined that the credit level of the target user does not meet the preset level.

[0086] Step S26: If it is detected that all the serial query databases have been selected and the serial transaction detection result is a normal transaction result, then it is determined that the credit level of the target user meets the preset level.

[0087] This application embodiment obtains multiple credit databases of the target user, divides these databases into multiple parallel query databases and at least one serial query database; simultaneously, based on the target user's credit data in each of the parallel query databases, it performs transaction behavior detection on the target user, obtaining multiple parallel transaction behavior detection results; if all the parallel transaction behavior detection results are detected as normal transaction behavior results, then any database in the serial query database that was not used as the basis for the target user's transaction behavior detection is selected as the target database, and based on the target user's credit data in the target database, transaction behavior detection is performed on the target user, obtaining serial transaction behavior detection results; if the serial transaction behavior detection results are detected as normal transaction behavior results... If the result is not found, the process returns to the step of selecting any database that was not used as the basis for detecting the target user's transaction behavior in each of the serial query databases, until the serial transaction behavior detection result is detected as an abnormal transaction behavior result or all of the serial query databases have been selected. If the serial transaction behavior detection result is detected as an abnormal transaction behavior result, it is determined that the target user's credit level does not meet the preset level. If it is detected that all of the serial query databases have been selected and the serial transaction detection result is a normal transaction behavior result, it is determined that the target user's credit level meets the preset level. Parallel transaction behavior detection is performed on some databases in multiple credit databases, thereby reducing the time for credit level assessment to a certain extent and thus improving loan approval efficiency.

[0088] Example 3

[0089] Furthermore, based on the first and / or second embodiments of this application, in another embodiment of this application, the content that is the same as or similar to the above-described embodiments one and / or two can be referred to the above description and will not be repeated hereafter. Based on this, in step S22, the step of simultaneously performing transaction behavior detection on the target user according to the credit data of the target user in each of the parallel query databases to obtain multiple parallel transaction behavior detection results includes:

[0090] Step C10: If an abnormal query database is detected in each of the parallel query databases, then the target user's transaction behavior is detected in the databases other than the abnormal query database in each of the parallel query databases, and multiple parallel transaction behavior detection results are obtained.

[0091] In step C10, after the step of simultaneously performing transaction behavior detection on the target user based on the target user's credit data in each of the parallel query databases (excluding the query anomaly database) to obtain multiple parallel transaction behavior detection results, the method further includes:

[0092] Step C20: If the detection results of each of the parallel transaction behaviors are all normal transaction behaviors, then obtain the weight corresponding to the query abnormal database.

[0093] Optionally, the specific implementation steps for obtaining the weight corresponding to the query anomaly database can refer to the specific implementation content of step B10 above, and will not be repeated here.

[0094] Step C30: If the weight is greater than or equal to the second preset weight threshold, then it is determined that the credit level of the target user does not meet the preset level.

[0095] In one feasible embodiment, reference is made to Figure 3 , Figure 3 This is a sequence diagram of the credit level assessment process in a scenario where there is an abnormal database in the parallel query database involved in the credit review optimization method of this application. If the weight is greater than or equal to the second preset weight threshold, the credit level assessment engine outputs a credit assessment conclusion that the credit level of the target user does not meet the preset level.

[0096] Step C40: If the weight is less than the second preset weight threshold, then the step of selecting any database that is not used as the basis for detecting the transaction behavior of the target user in each of the serial query databases is executed.

[0097] In one feasible embodiment, reference is made to Figure 4 , Figure 4This is a sequence diagram of the credit level assessment process in another scenario involving the loan credit review optimization method of this application, when there is an abnormal database in the parallel query database. If the weight is less than the second preset weight threshold, the credit level assessment engine initiates a credit data query for the target user to the serial query database A. The credit data of the target user obtained by the query is sent to the credit level assessment engine through the serial query database A. The credit level assessment engine then performs transaction behavior detection on the target user based on the credit data of the target user in the serial query database A to obtain the serial transaction behavior detection result.

[0098] In this embodiment, if all parallel transaction detection results are detected as normal transaction results, the weight corresponding to the query abnormal database is obtained; if the weight is greater than or equal to a second preset weight threshold, the credit level of the target user is determined to be inconsistent with the preset level; if the weight is less than the second preset weight threshold, the step of selecting any database that is not used as the basis for the transaction behavior detection of the target user as the target database is executed. Thus, when the weight corresponding to the abnormal database is small, that is, when its contribution to the credit level assessment of the target user is small, the situation where it cannot be queried due to its abnormality is ignored, and the next step of serial query is directly entered, so as to reduce the query interruption caused by the query of the abnormal database and the unnecessary postponement of the credit level assessment task. When the weight corresponding to the abnormal database is large, that is, when its contribution to the credit level assessment of the target user is large, the assessment result that the credit level of the target user does not meet the preset level is directly output, so as to avoid the risk of inaccurate credit level assessment of the target user due to its inability to be queried. Therefore, to a certain extent, the efficiency of credit level assessment is improved.

[0099] Example 4

[0100] This application also provides a loan credit review optimization device, referring to... Figure 5 The loan credit review optimization device includes:

[0101] The data acquisition module is used to collect facial data from the target user.

[0102] A parallel module is used to perform face recognition on the target user based on the face data and simultaneously assess the credit level of the target user.

[0103] The first determination module is used to determine that the loan credit review result of the target user is unsuccessful if it is detected that the credit level of the target user does not meet the preset level, and / or the face recognition of the target user fails.

[0104] The second determination module is used to determine that the loan credit review result of the target user is passed if the target user's credit level meets the preset level and the target user's face recognition is successful.

[0105] Optionally, the parallel module is further configured to:

[0106] Obtain multiple credit databases for the target user, and divide the multiple credit databases into multiple parallel query databases and at least one serial query database;

[0107] Simultaneously, based on the credit data of the target user in each of the parallel query databases, transaction behavior detection is performed on the target user to obtain multiple parallel transaction behavior detection results;

[0108] If all the parallel transaction behavior detection results are detected as normal transaction behavior results, then any database that is not used as the basis for the transaction behavior detection of the target user is selected from each of the serial query databases as the target database, and the transaction behavior of the target user is detected based on the credit data of the target user in the target database to obtain the serial transaction behavior detection result;

[0109] If the serial transaction behavior detection result is detected as a normal transaction behavior result, then return to the step of selecting any database that is not used as the basis for the transaction behavior detection of the target user as the target database in each of the serial query databases, until the serial transaction behavior detection result is detected as an abnormal transaction behavior result or all of the serial query databases have been selected;

[0110] If the serial transaction behavior detection result is detected as an abnormal transaction behavior result, it is determined that the target user's credit level does not meet the preset level;

[0111] If it is detected that all the serial query databases have been selected and the serial transaction detection result is a normal transaction result, then it is determined that the credit level of the target user meets the preset level.

[0112] Optionally, the parallel module is further configured to:

[0113] Obtain the pairwise database relationships between each of the aforementioned credit reporting databases;

[0114] Based on the correlation of each database, the multiple credit reporting databases are divided into multiple parallel query databases and at least one serial query database. The correlation between any two databases in each parallel query database is less than or equal to a preset correlation threshold, and the correlation between any database in each serial query database and any database in each parallel query database is greater than the preset correlation threshold.

[0115] Optionally, the parallel module is further configured to:

[0116] Determine the weight of each of the aforementioned credit databases in judging the transaction behavior of the target user;

[0117] The multiple credit reporting databases are divided into multiple parallel query databases with corresponding weights greater than a first preset weight threshold, and at least one serial query database with corresponding weights less than or equal to the first preset weight threshold.

[0118] Optionally, the parallel module is further configured to:

[0119] If an abnormal query database is detected in any of the parallel query databases, then the target user's transaction behavior is detected in the databases other than the abnormal query database, and multiple parallel transaction behavior detection results are obtained.

[0120] Optionally, after the step of simultaneously performing transaction behavior detection on the target user based on the target user's credit data in each of the parallel query databases (excluding the query anomaly database) to obtain multiple parallel transaction behavior detection results, the loan credit review optimization device is further configured to:

[0121] If the detection results of each of the parallel transaction behaviors are all normal transaction behaviors, then the weight corresponding to the query abnormal database is obtained;

[0122] If the weight is greater than or equal to the second preset weight threshold, then it is determined that the credit level of the target user does not meet the preset level;

[0123] If the weight is less than the second preset weight threshold, then the step of selecting any database that is not used as the basis for detecting the transaction behavior of the target user in each of the serial query databases is executed.

[0124] Optionally, after the step of simultaneously performing facial recognition on the target user based on the facial data and assessing the target user's creditworthiness, the loan credit review optimization device is further configured to:

[0125] If the target user's credit level is detected to be in line with the preset level, and the target user's facial recognition process has not ended, then facial recognition of the user is stopped, and call recognition is initiated for the target user.

[0126] If the call identification of the target user is detected as successful, the loan review result of the target user is determined to be approved.

[0127] The loan credit review optimization device provided in this application adopts the loan credit review optimization method in the above embodiments, solving the technical problem of low efficiency in loan credit review. Compared with the prior art, the beneficial effects of the loan credit review optimization device provided in this application are the same as the beneficial effects of the loan credit review optimization method provided in the above embodiments, and other technical features in the loan credit review optimization device are the same as the features disclosed in the methods of the above embodiments, and will not be repeated here.

[0128] Example 5

[0129] This application provides an electronic device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, which are executed by the at least one processor to enable the at least one processor to perform the loan credit review optimization method in the above embodiments.

[0130] The following is for reference. Figure 6 The diagram illustrates a structural schematic of an electronic device suitable for implementing embodiments of the present disclosure. The electronic devices in the embodiments of the present disclosure may include, but are not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Tablet PCs), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 6 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.

[0131] like Figure 6 As shown, an electronic device may include a processing unit (such as a central processing unit, graphics processing unit, etc.), which can perform various appropriate actions and processes based on programs stored in ROM (Read-Only Memory) or programs loaded from storage devices into RAM (Random Access Memory). RAM also stores various programs and data required for the operation of the electronic device. The processing unit, ROM, and RAM are interconnected via a bus. Input / output (I / O) interfaces are also connected to the bus.

[0132] Typically, the following systems can be connected to the I / O interface: input devices including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices including, for example, magnetic tapes, hard disks, etc.; and communication devices. Communication devices allow electronic devices to communicate wirelessly or wiredly with other devices to exchange data. Although electronic devices with various systems are shown in the figures, it should be understood that it is not required to implement or possess all the systems shown. More or fewer systems may be implemented alternatively.

[0133] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device, or installed from a ROM. When the computer program is executed by a processing device, it performs the functions defined above in the methods of embodiments of this disclosure.

[0134] The electronic device provided in this application employs the loan credit review optimization method in the above embodiments, solving the technical problem of low efficiency in loan credit review. Compared with the prior art, the beneficial effects of the electronic device provided in this application are the same as those of the loan credit review optimization method provided in the above embodiments, and other technical features of the electronic device are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0135] It should be understood that various parts of this disclosure can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics may be combined in any suitable manner in one or more embodiments or examples.

[0136] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0137] Example 6

[0138] This embodiment provides a computer-readable storage medium having computer-readable program instructions stored thereon, which are used to execute the loan credit review optimization method in the above embodiment.

[0139] The computer-readable storage medium provided in this application embodiment may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, RAM, ROM, EPROM (Erasable Programmable Read Only Memory) or flash memory, optical fiber, CD-ROM (compact disc read-only memory), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0140] The aforementioned computer-readable storage medium may be included in an electronic device or may exist independently without being assembled into an electronic device.

[0141] The aforementioned computer-readable storage medium carries one or more programs that, when executed by an electronic device, cause the electronic device to: collect facial data of a target user; simultaneously perform facial recognition on the target user based on the facial data and assess the target user's creditworthiness; if the target user's creditworthiness does not meet a preset level, and / or the target user's facial recognition fails, then the target user's loan credit review result is determined to be unsuccessful; if the target user's creditworthiness meets the preset level and the target user's facial recognition passes, then the target user's loan credit review result is determined to be successful.

[0142] Computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a LAN (Local Area Network) or a WAN (Wide Area Network)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0143] 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 application. 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 the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can 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.

[0144] The modules described in the embodiments of this disclosure can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0145] The computer-readable storage medium provided in this application stores computer-readable program instructions for executing the above-described loan credit review optimization method, thus solving the technical problem of low efficiency in loan credit review. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as the beneficial effects of the loan credit review optimization method provided in the above-described implementation, and will not be repeated here.

[0146] Example 7

[0147] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the loan credit review optimization method described above.

[0148] The computer program product provided in this application solves the technical problem of low efficiency in loan credit review. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as the beneficial effects of the loan credit review optimization method provided in the above embodiments, and will not be repeated here.

[0149] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent scope of this application.

Claims

1. A method for optimizing loan credit review, characterized in that, The loan credit review optimization method includes: Collect facial data of the target user; While performing facial recognition on the target user based on the facial data, the credit level of the target user is also assessed. If the credit level of the target user is found to be inconsistent with the preset level, and / or the facial recognition of the target user fails, then the loan credit review result of the target user is determined to be unsuccessful. If the target user's credit level is detected to meet the preset level and the target user's facial recognition is successful, then the target user's loan credit review result is determined to be successful. The steps for assessing the creditworthiness of the target user include: Obtain multiple credit databases for the target user, and divide the multiple credit databases into multiple parallel query databases and at least one serial query database; Simultaneously, based on the credit data of the target user in each of the parallel query databases, transaction behavior detection is performed on the target user to obtain multiple parallel transaction behavior detection results; If all the parallel transaction behavior detection results are detected as normal transaction behavior results, then any database that is not used as the basis for the transaction behavior detection of the target user is selected from each of the serial query databases as the target database, and the transaction behavior of the target user is detected based on the credit data of the target user in the target database to obtain the serial transaction behavior detection result; If the serial transaction behavior detection result is detected as a normal transaction behavior result, then return to the step of selecting any database that is not used as the basis for the transaction behavior detection of the target user as the target database in each of the serial query databases, until the serial transaction behavior detection result is detected as an abnormal transaction behavior result or all of the serial query databases have been selected; If the serial transaction behavior detection result is detected as an abnormal transaction behavior result, it is determined that the target user's credit level does not meet the preset level; If it is detected that all of the serial query databases have been selected and the serial transaction behavior detection result is a normal transaction behavior result, then it is determined that the credit level of the target user meets the preset level; The step of simultaneously performing transaction behavior detection on the target user based on the credit data of the target user in each of the parallel query databases to obtain multiple parallel transaction behavior detection results includes: If an abnormal query database is detected in any of the parallel query databases, then the target user's transaction behavior is detected in the databases other than the abnormal query databases in each of the parallel query databases, and multiple parallel transaction behavior detection results are obtained. After the step of simultaneously performing transaction behavior detection on the target user based on the target user's credit data in each of the parallel query databases (excluding the query anomaly database) to obtain multiple parallel transaction behavior detection results, the method further includes: If the detection results of each of the parallel transaction behaviors are all normal transaction behaviors, then the weight corresponding to the query abnormal database is obtained; If the weight is greater than or equal to the second preset weight threshold, then it is determined that the credit level of the target user does not meet the preset level; If the weight is less than the second preset weight threshold, then the step of selecting any database that is not used as the basis for detecting the transaction behavior of the target user in each of the serial query databases is executed.

2. The loan credit review optimization method as described in claim 1, characterized in that, The step of dividing the multiple credit reporting databases into multiple parallel query databases and at least one serial query database includes: Obtain the pairwise database relationships between each of the aforementioned credit reporting databases; Based on the correlation of each database, the multiple credit reporting databases are divided into multiple parallel query databases and at least one serial query database. The correlation between any two databases in each parallel query database is less than or equal to a preset correlation threshold, and the correlation between any database in each serial query database and any database in each parallel query database is greater than the preset correlation threshold.

3. The loan credit review optimization method as described in claim 1, characterized in that, The step of dividing the multiple credit reporting databases into multiple parallel query databases and at least one serial query database includes: Determine the weight of each of the aforementioned credit databases in judging the transaction behavior of the target user; The multiple credit reporting databases are divided into multiple parallel query databases with corresponding weights greater than a first preset weight threshold, and at least one serial query database with corresponding weights less than or equal to the first preset weight threshold.

4. The loan credit review optimization method as described in any one of claims 1 to 3, characterized in that, After the step of performing facial recognition on the target user based on the facial data and simultaneously assessing the target user's credit level, the method further includes: If the target user's credit level is detected to be in line with the preset level, and the target user's facial recognition process has not ended, then facial recognition of the user is stopped, and call recognition is initiated for the target user. If the call identification of the target user is detected as successful, the loan review result of the target user is determined to be approved.

5. A loan credit review optimization device, characterized in that, The loan credit review optimization device includes: The data acquisition module is used to collect facial data from the target user. A parallel module is used to perform face recognition on the target user based on the face data and simultaneously assess the credit level of the target user. The first determination module is used to determine that the loan credit review result of the target user is unsuccessful if it is detected that the credit level of the target user does not meet the preset level, and / or the face recognition of the target user fails. The second determination module is used to determine that the loan credit review result of the target user is passed if the target user's credit level meets the preset level and the target user's face recognition is passed. The steps for assessing the creditworthiness of the target user include: Obtain multiple credit databases for the target user, and divide the multiple credit databases into multiple parallel query databases and at least one serial query database; Simultaneously, based on the credit data of the target user in each of the parallel query databases, transaction behavior detection is performed on the target user to obtain multiple parallel transaction behavior detection results; If all the parallel transaction behavior detection results are detected as normal transaction behavior results, then any database that is not used as the basis for the transaction behavior detection of the target user is selected from each of the serial query databases as the target database, and the transaction behavior of the target user is detected based on the credit data of the target user in the target database to obtain the serial transaction behavior detection result; If the serial transaction behavior detection result is detected as a normal transaction behavior result, then return to the step of selecting any database that is not used as the basis for the transaction behavior detection of the target user as the target database in each of the serial query databases, until the serial transaction behavior detection result is detected as an abnormal transaction behavior result or all of the serial query databases have been selected; If the serial transaction behavior detection result is detected as an abnormal transaction behavior result, it is determined that the target user's credit level does not meet the preset level; If it is detected that all of the serial query databases have been selected and the serial transaction behavior detection result is a normal transaction behavior result, then it is determined that the credit level of the target user meets the preset level; The step of simultaneously performing transaction behavior detection on the target user based on the credit data of the target user in each of the parallel query databases to obtain multiple parallel transaction behavior detection results includes: If an abnormal query database is detected in any of the parallel query databases, then the target user's transaction behavior is detected in the databases other than the abnormal query databases in each of the parallel query databases, and multiple parallel transaction behavior detection results are obtained. After the step of simultaneously performing transaction behavior detection on the target user based on the target user's credit data in each of the parallel query databases (excluding the query anomaly database) to obtain multiple parallel transaction behavior detection results, the method further includes: If the detection results of each of the parallel transaction behaviors are all normal transaction behaviors, then the weight corresponding to the query abnormal database is obtained; If the weight is greater than or equal to the second preset weight threshold, then it is determined that the credit level of the target user does not meet the preset level; If the weight is less than the second preset weight threshold, then the step of selecting any database that is not used as the basis for detecting the transaction behavior of the target user in each of the serial query databases is executed.

6. An electronic device, characterized in that, The electronic device includes: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the steps of the loan credit review optimization method according to any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a program for implementing a loan credit review optimization method, which is executed by a processor to implement the steps of the loan credit review optimization method as described in any one of claims 1 to 4.

Images