Loan application request processing method and device and electronic equipment

Abstract

The invention discloses a loan application request processing method and device and electronic equipment, and relates to the field of financial science and technology, and the method comprises the steps: detecting a network state between a financial institution and N data systems after a first loan application request of a target user is received; under the condition that the network state between the financial institution and each data system is a normal state, encrypting data related to the loan application request stored in each data system based on a first preset protocol to obtain N pieces of first encrypted data corresponding to the N data systems; performing feature extraction on the first encryption data corresponding to the data system through each data system to obtain N first encryption vectors corresponding to the N data systems; and processing a loan application request of the target user based on the N first encryption vectors. The technical problem of low user loan risk assessment accuracy caused by information isolation between different systems is solved.

Description

Technical Field

[0001] This application relates to the field of financial technology, and more specifically, to a method, apparatus, and electronic device for processing loan application requests. Background Technology

[0002] In the wave of digital transformation, to improve the accuracy of user loan risk assessment, financial institutions rely on data stored in different data systems to evaluate user loan risk. These systems collect and store user information, financial status, credit history, and other data. However, due to strict privacy policies and technological barriers, data between different systems cannot be completely transparent to protect user privacy, resulting in relative isolation and the formation of information silos. This fragmented and isolated data structure limits financial institutions' ability to conduct comprehensive user risk assessments, leading to the technical problem of low accuracy in user loan risk assessment.

[0003] There is currently no effective solution to the above problems. Summary of the Invention

[0004] This application provides a method, apparatus, and electronic device for processing loan application requests, in order to at least solve the technical problem of low accuracy in user loan risk assessment caused by information isolation between different systems.

[0005] According to one aspect of this application, a method for processing loan application requests is provided, comprising: upon receiving an initial loan application request from a target user, detecting the network status between a financial institution and N data systems, where N is a positive integer, and different data systems are used to store different types of data related to the loan application request; assuming the network status between the financial institution and each data system is normal, encrypting the data related to the loan application request stored in each data system based on a first preset protocol to obtain N first encrypted data corresponding to the N data systems, wherein the first preset protocol is an encryption protocol jointly negotiated and determined by the financial institution and the N data systems; extracting features from the first encrypted data corresponding to each data system to obtain N first encrypted vectors corresponding to the N data systems; and processing the target user's loan application request based on the N first encrypted vectors.

[0006] Optionally, after detecting the network status between the financial institution and the N data systems, the loan application request processing method further includes: if the network status between the financial institution and at least one of the N data systems is abnormal, selecting the data systems with normal network status among the N data systems as target data systems, resulting in P target data systems, where P is a positive integer less than or equal to N; encrypting the data related to the loan application request stored in the target data system based on a second preset protocol corresponding to each target data system, resulting in P second encrypted data corresponding to the P target data systems, where the second preset protocol is an encryption protocol negotiated and determined by both the financial institution and each target data system; extracting features from the second encrypted data corresponding to each target data system through each target data system, resulting in P second encrypted vectors corresponding to the P target data systems; and processing the target user's loan application request based on the P second encrypted vectors.

[0007] Optionally, the data related to the loan application request stored in each data system is encrypted based on a first preset protocol, including: filtering data in the i-th data system based on the user identifier of the target user to obtain the original data related to the loan application request stored in the i-th data system, where i is a positive integer less than or equal to N; cleaning the original data in the i-th data system to obtain first data, where data cleaning is used to remove redundant data in the original data; desensitizing the first data corresponding to the i-th data system to obtain second data, where desensitization is used to remove / update sensitive data in the original data; and encrypting the second data corresponding to the i-th data system based on the first preset protocol.

[0008] Optionally, encrypting the second data corresponding to the i-th data system based on the first preset protocol includes: encrypting the second data corresponding to the i-th data system based on the first key corresponding to the first preset protocol to obtain a first encryption result; and adding random noise data to the first encryption result corresponding to the i-th data system based on the differential privacy parameter corresponding to the first preset protocol to obtain the first encrypted data corresponding to the i-th data system.

[0009] Optionally, the step of processing a target user's loan application request based on N first encrypted vectors includes: aligning the N first encrypted vectors to obtain N third encrypted vectors, wherein the N third encrypted vectors have the same dimension; inputting the N third encrypted vectors into a target model, wherein the target model is a federated model trained on N-dimensional historical data of different types corresponding to N data systems; performing a weighted summation of the N third encrypted vectors through the target model to obtain a first target vector, wherein the first target vector is used to characterize the target user's credit rating; determining the target user's loan risk based on the first target vector and the target user's user type, and processing the target user's loan application request based on the target user's loan risk.

[0010] Optionally, after obtaining the first target vector by weighted summation of N third encrypted vectors through the target model, the loan application request processing method further includes: if the target user is not initiating a loan application request for the first time, obtaining the generation duration of the first target vector, wherein the generation duration is the duration between the generation time of the first target vector and the current time; if the generation duration of the first target vector is greater than a preset duration, generating a control signal, wherein the control signal is used to re-detect the network status between the financial institution and the N data systems.

[0011] Optionally, after obtaining the generation duration of the first target vector, the loan request processing method further includes: if the generation duration of the first target vector is less than or equal to a preset duration, determining X preset rules corresponding to the target user based on the user type, where X is a positive integer, and the X preset rules are risk assessment rules created by the financial institution based on historical loan applications with loan risks greater than a preset risk value within a historical time period; detecting the data related to the loan application request collected by the financial institution based on the X preset rules to obtain a first detection result; and processing the target user's loan application request based on the first detection result and the first target vector.

[0012] According to another aspect of this application, a loan application request processing apparatus is also provided, comprising: a first detection unit, configured to detect the network status between a financial institution and N data systems after receiving an initial loan application request from a target user, wherein N is a positive integer, and different data systems are used to store different types of data related to the loan application request; a first encryption unit, configured to encrypt the data related to the loan application request stored in each data system based on a first preset protocol, provided that the network status between the financial institution and each data system is normal, to obtain N first encrypted data corresponding to the N data systems, wherein the first preset protocol is an encryption protocol jointly negotiated and determined by the financial institution and the N data systems; a first extraction unit, configured to extract features from the first encrypted data corresponding to each data system to obtain N first encrypted vectors corresponding to the N data systems; and a first processing unit, configured to process the target user's loan application request based on the N first encrypted vectors.

[0013] According to another aspect of this application, a computer program product is also provided, which stores a computer program, wherein, when the computer program is running, it controls the computer program product to execute the processing method of any of the above-mentioned loan application requests.

[0014] According to another aspect of this application, an electronic device is also provided, wherein the electronic device includes 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 cause the one or more processors to implement the processing method of the loan application request of any of the above.

[0015] In this application, after receiving the target user's initial loan application request, the network status between the financial institution and N data systems is first detected, where N is a positive integer. Different data systems are used to store different types of data related to the loan application request. Then, assuming that the network status between the financial institution and each data system is normal, this application encrypts the data related to the loan application request stored in each data system based on a first preset protocol, obtaining N first encrypted data corresponding to the N data systems. The first preset protocol is an encryption protocol jointly negotiated and determined by the financial institution and the N data systems. Then, this application extracts features from the first encrypted data corresponding to each data system, obtaining N first encrypted vectors corresponding to the N data systems. Finally, this application processes the target user's loan application request based on the N first encrypted vectors.

[0016] As can be seen from the above, this application adopts a collaborative encryption and feature vector integration approach. By monitoring the network status between financial institutions and multiple data systems and applying a preset encryption protocol, it achieves the goal of integrating user data from different data systems while protecting user privacy. This results in improving the accuracy of loan risk assessment and solves the technical problem of low accuracy in user loan risk assessment.

[0017] Specifically, upon receiving the initial loan application, this application monitors network connections with N data systems in real time to ensure the stability and security of data transmission. When all network conditions are detected as normal, this application encrypts the data in each system using a mutually agreed-upon encryption protocol, forming N encrypted data sets. Subsequently, this application controls each data system to extract features from the encrypted data internally, generating encrypted feature vectors. Finally, this application performs risk assessment based on the encrypted vectors from different data systems, thus avoiding access to the original data. While adhering to privacy protection requirements, this achieves the technical effect of improving the accuracy of user loan risk assessment, thereby solving the technical problem of low accuracy in user loan risk assessment caused by information isolation between different systems. Attached Figure Description

[0018] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0019] Figure 1 This is a hardware structure block diagram of a computer terminal (or mobile device) for implementing a loan application request processing method according to an embodiment of this application.

[0020] Figure 2 This is a flowchart of an optional loan application request processing method according to an embodiment of this application;

[0021] Figure 3 This is a flowchart of an optional method for identifying loan risk behaviors according to an embodiment of this application;

[0022] Figure 4 This is a flowchart of another optional method for identifying loan risk behaviors according to an embodiment of this application;

[0023] Figure 5 This is a schematic diagram of an optional loan application request processing apparatus according to an embodiment of this application;

[0024] Figure 6 This is a structural block diagram of an electronic device according to an embodiment of this application. Detailed Implementation

[0025] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0026] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0027] It should also be noted that all relevant information (including but not limited to information used for display and analysis) and data (including but not limited to user data from different data systems) involved in this application are information and data authorized by the user or fully authorized by all parties. For example, if there is an interface between this system and the relevant user or organization, before obtaining relevant information, it is necessary to send an acquisition request to the aforementioned user or organization through the interface, and obtain the relevant information after receiving consent from the aforementioned user or organization.

[0028] Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of relevant information and data involved in this application all comply with the relevant laws, regulations, and standards of the relevant regions, and necessary confidentiality measures have been taken. This application does not violate public order and good morals. In addition, this application provides a corresponding operation entry point for users to choose to agree to or refuse authorization. If the user chooses to refuse authorization, the corresponding expert decision-making process will be initiated.

[0029] According to an embodiment of this application, an embodiment of a method for processing a loan application request is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0030] The methods and embodiments provided in this application can be executed on mobile terminals, computer terminals, or similar computing devices. Figure 1 This is a hardware structure block diagram of a computer terminal (or mobile device) for implementing a loan application request processing method according to an embodiment of this application. Figure 1 As shown, the computer terminal 10 (or mobile device) may include one or more processors 102 (shown as 102a, 102b, ..., 102n in the figure) 102 (processor 102 may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of a BUS bus), a network interface, a power supply, and / or a camera. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, computer terminal 10 may also include... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0031] Optionally, it should be noted that the aforementioned one or more processors 102 and / or other data processing circuitry may generally be referred to herein as "data processing circuitry". This data processing circuitry may be embodied, in whole or in part, in software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuitry may be a single, independent processing module, or may be wholly or partially integrated into any other element within the computer terminal 10 (or mobile device). As involved in the embodiments of this application, the data processing circuitry serves as a processor control mechanism (e.g., selection of a variable resistor termination path connected to an interface).

[0032] Optionally, the memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the loan application request processing method in this embodiment. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, thereby implementing the aforementioned loan application request processing method. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the computer terminal 10 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0033] Optionally, the transmission device 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of the computer terminal 10. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 may be a Radio Frequency (RF) module, used for wireless communication with the Internet.

[0034] Alternatively, the display can be configured as a touchscreen liquid crystal display (LCD) that allows the user to interact with the user interface of the computer terminal 10 (or mobile device).

[0035] Optionally, under the above operating environment, this application provides a loan application request processing system (hereinafter referred to as the processing system) for executing the loan application request processing method in this application. Figure 2 This is a flowchart of an optional loan application request processing method according to an embodiment of this application, such as... Figure 2 As shown, the method includes the following steps:

[0036] Step S201: After receiving the target user's first loan application request, detect the network status between the financial institution and N data systems, where N is a positive integer and different data systems are used to store different types of data related to the loan application request.

[0037] Optionally, target users refer to individuals or businesses that apply for loans from financial institutions.

[0038] Optionally, network status refers to the connectivity and stability of the network between the business system and the financial institution, thereby ensuring the reliability of subsequent data transmission.

[0039] Optionally, the N data systems are business systems that store different types of data related to loan application requests, such as social security systems, tax systems, credit reporting systems, and telecommunications operator systems that have established cooperative relationships with financial institutions. It should be noted that the processing system will only conduct loan risk assessment based on user data in the N data systems after receiving the user's authorization information.

[0040] Optionally, the processing system ensures that the connection between the financial institution and all relevant data systems is secure and reliable by pre-detecting the network status between the financial institution and N data systems, thereby avoiding data leakage or delays caused by network failures and improving the security of the entire loan risk assessment process.

[0041] Step S202: Under the condition that the network status between the financial institution and each data system is normal, the data related to the loan application request stored in each data system is encrypted based on the first preset protocol to obtain N first encrypted data corresponding to N data systems. The first preset protocol is an encryption protocol jointly negotiated and determined by the financial institution and the N data systems.

[0042] Optionally, the processing system encrypts the data related to the loan application request stored in each data system based on a first preset protocol, ensuring the security of data transmission. Through encryption, even if the transmitted data is intercepted by a third party, it is difficult to parse its content, thereby improving data security. Furthermore, the use of encryption technology can protect the target user's personal information from being obtained by unauthorized third parties, thereby maintaining user privacy and security.

[0043] Optionally, if the network status between the financial institution and at least one of the N data systems is detected to be abnormal, the processing system selects the data systems with normal network status among the N data systems as target data systems, resulting in P target data systems, where P is a positive integer less than or equal to N. Then, the processing system encrypts the data related to the loan application request stored in each target data system based on the second preset protocol corresponding to each target data system.

[0044] Step S203: Extract features from the first encrypted data corresponding to each data system to obtain N first encrypted vectors corresponding to N data systems.

[0045] Optionally, a first encryption vector is obtained by extracting features from the encrypted user data of each data system. Through feature extraction, even if the data system is attacked, it is difficult for the attacker to recover the complete original data from the encryption vector, thereby further ensuring the integrity and security of the user data in the data system.

[0046] Step S204: Process the target user's loan application request based on N first encryption vectors.

[0047] Optionally, by using encrypted data, the processing system can review loan applications while protecting user privacy and data security, ensuring the security and compliance of the entire process. Furthermore, based on encrypted feature vectors from multiple data systems, the processing system can build more complex risk control models, thereby improving the ability to identify loan risks.

[0048] In summary, the steps of the above embodiments, from network status detection to data encryption, and then to the extraction and processing of encryption vectors, constitute a complete and secure loan application processing flow. This flow not only significantly improves data security and transmission efficiency, but also strengthens risk control capabilities through the use of encryption vectors, thereby protecting user privacy. At the same time, through the above steps, the problem of low accuracy in identifying abnormal transactions in existing technologies can be effectively solved. Especially in loan application scenarios, it can more accurately identify potential risks, reduce false alarms and false negatives, and thus optimize the financial service experience.

[0049] As can be seen from the above, this application adopts a collaborative encryption and feature vector integration approach. By monitoring the network status between financial institutions and multiple data systems and applying a preset encryption protocol, it achieves the goal of integrating user data from different data systems while protecting user privacy. This results in improving the accuracy of loan risk assessment and solves the technical problem of low accuracy in user loan risk assessment.

[0050] Specifically, upon receiving the initial loan application, this application monitors network connections with N data systems in real time to ensure the stability and security of data transmission. When all network conditions are detected as normal, this application encrypts the data in each system using a mutually agreed-upon encryption protocol, forming N encrypted data sets. Subsequently, this application controls each data system to extract features from the encrypted data internally, generating encrypted feature vectors. Finally, this application performs risk assessment based on the encrypted vectors from different data systems, thus avoiding access to the original data. While adhering to privacy protection requirements, this achieves the technical effect of improving the accuracy of user loan risk assessment, thereby solving the technical problem of low accuracy in user loan risk assessment caused by information isolation between different systems.

[0051] In one optional embodiment, after detecting the network status between the financial institution and N data systems, if the processing system detects that the network status between the financial institution and at least one of the N data systems is abnormal, the data systems with normal network status among the N data systems are selected as target data systems, resulting in P target data systems, where P is a positive integer less than or equal to N. Then, based on a second preset protocol corresponding to each target data system, the processing system encrypts the data related to the loan application request stored in that target data system, resulting in P second encrypted data corresponding to the P target data systems. The second preset protocol is an encryption protocol negotiated and determined by both the financial institution and each target data system. Next, the processing system extracts features from the second encrypted data corresponding to each target data system, obtaining P second encrypted vectors corresponding to the P target data systems. Finally, the processing system processes the target user's loan application request based on the P second encrypted vectors.

[0052] Optionally, the aforementioned target data system refers to those data systems that show a normal network status during detection.

[0053] Optionally, in the event of network failures in N data systems, the processing system can make federated decisions based on the data systems whose current network status is normal, and process the loan application requests of the target users, that is, assess the loan risk of the users, thereby ensuring the continuity and reliability of loan application processing and improving the disaster recovery capability of the processing system.

[0054] Optionally, the processing system avoids wasting computing and storage resources in abnormal network environments by processing only data systems with normal network conditions, thereby improving the overall system operating efficiency. At the same time, it encrypts user data in each target data system based on a second preset protocol. This personalized encryption scheme can better adapt to the security requirements of different systems, thereby improving the overall security protection level of the processing system.

[0055] In summary, in the above embodiments, even if some data sources are restricted, financial institutions can still conduct loan risk assessments based on P second encryption vectors corresponding to P target data systems. That is, when facing uncertainties such as abnormal network conditions, the above embodiments provide a flexible solution. By selecting target data systems with good network conditions, a customized second encryption protocol can be used to encrypt and extract features from user data in the target data systems, thereby ensuring that loan applications can continue to be processed. This not only improves the robustness of the processing system, but also enhances the system's ability to respond to abnormal network conditions.

[0056] In one optional embodiment, the processing system first filters data in the i-th data system based on the user identifier of the target user to obtain the original data related to the loan application request stored in the i-th data system, where i is a positive integer less than or equal to N. Then, the processing system cleans the original data in the i-th data system to obtain first data, where data cleaning is used to remove redundant data in the original data. Next, the processing system performs desensitization processing on the first data corresponding to the i-th data system to obtain second data, where desensitization processing is used to remove / update sensitive data in the original data. Finally, the processing system encrypts the second data corresponding to the i-th data system based on a first preset protocol.

[0057] Optionally, the i-th data system can be any one of the N data systems.

[0058] Optionally, a user identifier refers to a unique identification code for a target user within a financial institution, used to accurately locate data records related to that user in the data system. Retrieving user data in the data system based on the user identifier has the following functions:

[0059] (1) Improve data retrieval efficiency: By using user identification to locate, data related to loan application requests can be found quickly, thereby improving the efficiency of data processing.

[0060] (2) Improve the accuracy of loan risk assessment: By using user identification for location, erroneous analysis and decision-making caused by user data confusion are avoided, thereby enhancing the accuracy of loan application processing.

[0061] Optionally, data cleaning of the raw data has the following benefits:

[0062] (1) Ensure data quality: Data cleaning removes unnecessary data interference, reduces data noise, and improves the reliability of subsequent data analysis.

[0063] (2) Simplify data processing: The first data after cleaning is more concise and standardized, which reduces the complexity of data processing and helps to improve the speed and efficiency of the overall process.

[0064] Optionally, by de-identifying the first data obtained from data cleaning, sensitive information is not exposed even if user data is accessed by unauthorized parties, thereby improving the security of user information.

[0065] Optionally, encrypting the second data obtained after de-identification processing based on a first preset protocol has the following effects:

[0066] (1) Enhanced data security: Encrypted data is not easily stolen or tampered with by third parties during transmission, effectively protecting data from network attacks and improving the overall security of data.

[0067] (2) Promote data sharing: Encryption not only protects data security, but also promotes data sharing between financial institutions and data systems under the premise of complying with security standards, thereby providing data support for loan application processing.

[0068] In summary, the steps in the above embodiments provide financial institutions with a comprehensive data preprocessing framework aimed at improving the efficiency and accuracy of data processing while ensuring user privacy and data security. Through precise screening, rigorous cleaning, meticulous desensitization, and secure encryption, the above embodiments construct a loan application processing flow that is both efficient and secure, effectively addressing the growing data processing needs of the financial industry.

[0069] In one optional embodiment, the processing system first encrypts the second data corresponding to the i-th data system based on the first key corresponding to the first preset protocol to obtain a first encryption result. Then, the processing system adds random noise data to the first encryption result corresponding to the i-th data system based on the differential privacy parameter corresponding to the first preset protocol to obtain the first encrypted data corresponding to the i-th data system.

[0070] Optionally, the processing system can also encrypt the de-identified user data in the j-th target data system based on the second key corresponding to the second preset protocol to obtain a second encryption result. Then, based on the differential privacy parameter corresponding to the second preset protocol, the processing system adds random noise data to the second encryption result corresponding to the j-th target data system to obtain the second encrypted data corresponding to the j-th target data system.

[0071] Optionally, the first key is an encryption key that corresponds to the first preset protocol. It is used to convert plaintext data into ciphertext data and is a key component of the encryption process. The use of the first key has the following functions:

[0072] (1) Enhance data security: Through encryption, even if the encrypted user data is intercepted during transmission over the network, third parties will not be able to read the true content of the data, thus effectively protecting the security of user information.

[0073] (2) Ensure data integrity: Encryption using a specific key ensures that the data maintains a consistent structure and content before and after encryption, facilitating subsequent decryption and data use.

[0074] Optionally, differential privacy parameters refer to a parameter introduced based on differential privacy technology to protect user data. Differential privacy parameters define the degree to which random noise is added to the data in order to achieve anonymization of personal data.

[0075] Optionally, random noise data refers to a random data element added under a differential privacy protection strategy to ensure that the information of any single individual in the dataset is not easily leaked.

[0076] Alternatively, the use of differential privacy parameters has the following effects:

[0077] (1) Enhanced privacy protection: By adding random noise to encrypted data, it is difficult for attackers to infer information about any specific individual from the dataset even if they obtain the encrypted data, thus providing an extra layer of privacy protection.

[0078] (2) Balancing analysis accuracy and privacy: Differential privacy technology ensures the security of personal privacy without significantly sacrificing the effectiveness of dataset analysis, which is crucial for handling sensitive data in the financial field.

[0079] In summary, the two steps in the above embodiments provide financial institutions with a high level of data protection when processing loan applications. By combining data encryption and differential privacy technologies, the processing system not only achieves secure data transmission and storage, but also further enhances the protection of user privacy. Even in the event of improper access to data, it can effectively prevent the leakage of sensitive information.

[0080] In one optional embodiment, the processing system first aligns N first encrypted vectors to obtain N third encrypted vectors, wherein the N third encrypted vectors have the same dimension. Then, the processing system inputs the N third encrypted vectors into a target model, wherein the target model is a federated model trained on N different types of historical data corresponding to N data systems. Then, the processing system performs a weighted summation of the N third encrypted vectors through the target model to obtain a first target vector, wherein the first target vector is used to characterize the credit rating of the target user. Finally, the processing system determines the loan risk of the target user based on the first target vector and the user type of the target user, and processes the loan application request of the target user based on the loan risk of the target user.

[0081] Optionally, aligning the N first encryption vectors will adjust each vector to the same dimension. This step has the following effect:

[0082] (1) Compatibility and consistency: Ensure that vectors from different data sources are consistent in dimension, which facilitates comprehensive analysis and processing in subsequent federated models and avoids calculation errors caused by dimensional differences.

[0083] (2) Data fusion preparation: This prepares the data for inputting the encryption vectors of different systems into a unified model for processing, thereby enhancing the coordination and comparability between the data.

[0084] Optionally, the target model is a pre-built model based on federated learning technology, which is trained using N-dimensional historical data jointly provided by N data systems.

[0085] Optionally, processing the N third encryption vectors through the target model has the following effects:

[0086] (1) Model generalization ability: Federated models can handle a wider range of more complex data combinations, thereby improving the model's adaptability and prediction accuracy.

[0087] (2) Privacy protection: Federated learning allows each participant to train the model locally without directly sharing sensitive data, thus protecting the privacy of user data.

[0088] Alternatively, in the federated model, weighted summation of the N third-party encryption vectors has the following effect:

[0089] (1) Refined credit assessment: The first target vector includes a comprehensive consideration of information from various data systems, which can more comprehensively and precisely assess the user's credit rating, thereby improving the accuracy of loan approval.

[0090] (2) Risk identification capability: It combines the weighted summation of multiple data, which helps to identify risk patterns hidden in multi-layer transaction data and improve the ability to identify abnormal loan applications.

[0091] Optionally, the processing system can determine the loan risk of a target user based on a first target vector, and then process the user's loan application based on the loan risk. Based on the quantification of loan risk, financial institutions can automatically process loan application requests, thereby speeding up the approval process and reducing the bias and risk caused by human decision-making.

[0092] In summary, financial institutions can leverage federated learning technology and encrypted data processing to automate and intelligently assess the risk of user loan applications. Alignment processing ensures data consistency and comparability, while the use of federated models enhances the model's generalization ability and predictive accuracy, and strengthens privacy protection. The weighted summation and loan risk determination steps provide financial institutions with refined credit assessment and efficient automated decision-making support. These embodiments not only optimize the loan approval process and improve approval efficiency but also enhance the accuracy of user loan risk assessment.

[0093] In an optional embodiment, after obtaining the first target vector by weighted summation of N third encrypted vectors through the target model, if the processing system detects that the target user is not initiating a loan application request for the first time, the processing system obtains the generation duration of the first target vector, wherein the generation duration is the duration between the generation time of the first target vector and the current time, and compares the generation duration with the preset duration.

[0094] Optionally, the generation time refers to the time difference from the generation time of the first target vector to the current time, which is used to measure the timeliness of the target vector data.

[0095] Optionally, the processing system checks the generation time of the first target vector, which has the following functions:

[0096] (1) Data timeliness monitoring: By calculating the generation time, it is possible to determine whether the first target vector is valid.

[0097] (2) Dynamic assessment of user credit: Considering that the user's credit status will change over time, the processing system checks the generation time of the first target vector, thereby ensuring that financial institutions use timely credit assessment data when processing users' non-first loan applications, thus improving the accuracy of decision-making.

[0098] Optionally, if the generation time of the first target vector is longer than a preset time, the processing system generates a control signal, wherein the control signal is used to re-detect the network status between the financial institution and N data systems.

[0099] Optionally, if the generation time exceeds the preset time, it indicates that the current first target vector is not within its validity period. The processing system can then use control signals to drive the federated model to regenerate a valid first target vector based on encrypted user data from N data systems. This mechanism has the following functions:

[0100] (1) Automatic feedback mechanism: When the generation time of the first target vector exceeds the preset value, the system automatically generates a control signal to trigger subsequent operations, thereby improving the system's automation and response speed.

[0101] (2) Ensure data synchronization: By re-detecting the network status, it can be ensured that even after a long period of time, financial institutions can still obtain the latest user data from N data systems in a timely manner, thereby updating the first target vector and ensuring the timeliness of the assessment results of user loan risk.

[0102] In one optional embodiment, after obtaining the generation time of the first target vector, if the processing system detects that the generation time of the first target vector is less than or equal to a preset time, the processing system determines X preset rules corresponding to the target user based on the user type, where X is a positive integer, and the X preset rules are risk assessment rules created by financial institutions based on historical loan applications with loan risks greater than preset risk values ​​within a historical time period. Then, the processing system detects the data related to the loan application request collected by the financial institution based on the X preset rules to obtain a first detection result. Finally, the processing system processes the target user's loan application request based on the first detection result and the first target vector.

[0103] Optionally, the user type can be either an individual user or an enterprise user.

[0104] Optionally, X preset rules are a set of risk assessment rules extracted by financial institutions based on historical data of cases where loan risk exceeds a set threshold, used to identify potential risk points in loan applications of corresponding types of users.

[0105] Optionally, the data related to the loan application request can be detected based on X preset rules corresponding to the user type. By distinguishing user types, the processing system can more accurately apply different risk assessment rules, thereby improving the pertinence and accuracy of risk identification.

[0106] Optionally, the processing system determines the loan risk of the target user based on the first detection result and the first target vector, and has the following functions:

[0107] (1) Comprehensive risk assessment: The first target vector combines information from multiple data sources, while the first detection result is based on specific preset rules. The integration of the two can provide a comprehensive loan risk assessment.

[0108] (2) Decision support: The determination of loan risk provides a key basis for financial institutions to make loan approval decisions, which helps to balance risk and return and make more reasonable loan decisions.

[0109] In summary, through the steps described in the above embodiments, financial institutions can determine targeted risk assessment rules based on user types, conduct timely and accurate detection of loan application-related data, and accurately assess loan risks by combining comprehensive user information vectors. This method not only improves the efficiency and accuracy of risk detection but also reduces the credit risk of financial institutions and optimizes the loan approval process.

[0110] In one alternative embodiment, Figure 3 This is a flowchart of an optional method for identifying loan risk behaviors according to an embodiment of this application, such as... Figure 3As shown, after receiving a loan application request from a target user, the financial institution parses the application address and device, and based on the parsing results, checks whether the target user is real-name authenticated. Then, it checks whether the target user is a new user (i.e., whether it is the first time to initiate a loan application request). If the target user is a new user, the financial institution performs loan risk detection on the target user based on a pre-trained federated model.

[0111] If the target user is not a new user, the financial institution checks whether the detection result of the loan risk detection of the target user by the federated model is valid. If the detection result is valid, the financial institution collects business data related to the loan request based on the user type of the target user, and inputs the business data and the detection result output by the federated model into the risk control model for risk decision-making. The financial institution processes the user's loan application request based on the output result of the risk control model.

[0112] Optionally, in Figure 3 In this process, financial institutions connect to N data systems, namely the credit reporting system, tax system, social security system, and telecom operator system. They use federated learning technology to perform five-element modeling to obtain a federated model. The specific model construction is shown in the following formula (1):

[0113] Y = X1 + X2 + X3 + X4 (1)

[0114] In the above formula (1), if Y is greater than 0, it indicates that the target user has transaction risk, and the processing system will issue a risk warning. After that, it will enter the preset review process for further verification / the processing system will automatically reject the loan application of the target user. If the value of Y is 0, it indicates that the target user has no transaction risk or the transaction risk is low, and the processing system will proceed to the next automatic approval stage. The following is an explanation of the risk feature values ​​used in this model and an introduction to the application rules:

[0115] X1 = X 11 +X 12 +X 13 +X 14 (2)

[0116] In the above formulas (1) and (2), X1 is the risk feature value extracted from the operator's system when the target user authorizes and the operator to conduct joint modeling.

[0117] X 11 This is used to characterize the latest activation date of the encrypted number of the target user. If the time length from the latest activation date to the application date is less than 30 calendar days, the feature value is set to 1; otherwise, if it is greater than or equal to 30 calendar days, it is set to 0.

[0118] X 12: Used to characterize the encrypted daily average traffic information of the target user. If the daily average traffic usage is 0M, the feature value is set to 1; if it is greater than 0M, the feature value is set to 0.

[0119] X 13 : Used to characterize the encrypted communication record information of the target user, including communication records with preset risk areas, the feature value is set to 1; otherwise, the feature value is set to 1.

[0120] X 14 : Used to represent the encrypted communication payment information of the target user. The feature value is set to 1 if the user has no outstanding fees, and 0 if there are outstanding fees.

[0121] X2 = X 21 +X 22 (3)

[0122] In the above formulas (1) and (3), X2 is the risk characteristic value obtained in the tax system when the target user authorizes joint modeling with the tax system.

[0123] X 21 : Used to represent the encrypted individual income tax declaration information of the target user. The value is set to 1 if there is an abnormal declaration in the individual income tax declaration record; and set to 0 if there is no abnormal declaration.

[0124] X 22 This is used to represent the encrypted tax credit information of the target user. If the tax credit value is less than the preset credit value, the feature value is set to 1; if the tax credit value is greater than or equal to the preset credit value, the feature value is set to 0.

[0125] X3 = X 31 +X 32 +X 33 +X 34 +X 35 (4)

[0126] In formulas (1) and (4) above, X3 is the risk characteristic value obtained from the credit reporting system with the authorization of the target user. If any field extracted by the processing system from the credit report is greater than 0, it is considered that there is a bad credit record; if the field is 0, it is considered that there is no bad credit record. 31 X 32 X 33 X 34 and X 35 All of these are credit data fields obtained from the credit reporting system with the authorization of the target user.

[0127] X4=Max{X 41 X 42} (5)

[0128] In formulas (1) and (5) above, X4 is the risk characteristic value obtained from the social security system with the authorization of the target user, X 41 Used to represent social security / medical insurance payment information (1 indicates that the target user is paying social security / medical insurance normally, 0 indicates that the target user has not paid social security / medical insurance on time), X 42 Used to characterize medical insurance usage information (1 indicates that the target user can use medical insurance normally, 0 indicates that the target user's medical insurance is abnormal and cannot be used normally).

[0129] In an optional embodiment, when a financial institution cannot simultaneously connect to N data systems, the model algorithm is adjusted from "Y = X1 + X2 + X3 + X4" to "Y = Y1 / Y2 / Y3 / Y4 + X1 / X2 / X3 / X4". That is, the strong correlation verification of risk feature values ​​provided by multiple data systems in the processing system is changed to weak correlation verification. In this solution, Y1, Y2, Y3, and Y4 refer to the rule hit results of risk verification of user data pre-stored in the financial institution.

[0130] Optionally, Figure 4 This is a flowchart of another optional method for identifying loan risk behaviors according to an embodiment of this application, such as... Figure 4 As shown, if the user is detected to be not a new user, and if the financial institution can successfully connect to at least one of the data systems in the credit reporting system, tax system, social security system, and operator system, the processing system controls the corresponding data system to encrypt and verify the user data stored in the data system. Based on the rules pre-stored in the financial institution, the processing system performs risk filtering on the user data stored in the data system, thereby obtaining the verification result under the decision of both the financial institution and the data system. If the verification result under the decision of both parties fails, the processing system rejects the loan application request of the target user. If the verification result under the decision of both parties passes, the processing system further makes risk decisions based on the risk control module.

[0131] As can be seen from the above, this application adopts a collaborative encryption and feature vector integration approach. By monitoring the network status between financial institutions and multiple data systems and applying a preset encryption protocol, it achieves the goal of integrating user data from different data systems while protecting user privacy. This results in improving the accuracy of loan risk assessment and solves the technical problem of low accuracy in user loan risk assessment.

[0132] Specifically, upon receiving the initial loan application, this application monitors network connections with N data systems in real time to ensure the stability and security of data transmission. When all network conditions are detected as normal, this application encrypts the data in each system using a mutually agreed-upon encryption protocol, forming N encrypted data sets. Subsequently, this application controls each data system to extract features from the encrypted data internally, generating encrypted feature vectors. Finally, this application performs risk assessment based on the encrypted vectors from different data systems, thus avoiding access to the original data. While adhering to privacy protection requirements, this achieves the technical effect of improving the accuracy of user loan risk assessment, thereby solving the technical problem of low accuracy in user loan risk assessment caused by information isolation between different systems.

[0133] This application embodiment can also provide a loan application request processing device. It should be noted that the loan application request processing device of this application embodiment can be used to execute the loan application request processing method provided in this application embodiment. The loan application request processing device provided in this application embodiment will be described below.

[0134] According to an embodiment of this application, an apparatus for implementing the above-described loan application request processing method is also provided. Figure 5 This is a schematic diagram of an optional loan application request processing apparatus according to an embodiment of this application, as shown below. Figure 5 As shown, the device includes: a first detection unit 501, a first encryption unit 502, a first extraction unit 503, and a first processing unit 504.

[0135] Optionally, the first detection unit 501 is used to detect the network status between the financial institution and N data systems after receiving the first loan application request from the target user, where N is a positive integer, and different data systems are used to store different types of data related to the loan application request; the first encryption unit 502 is used to encrypt the data related to the loan application request stored in each data system based on a first preset protocol when the network status between the financial institution and each data system is normal, to obtain N first encrypted data corresponding to the N data systems, where the first preset protocol is an encryption protocol jointly negotiated and determined by the financial institution and the N data systems; the first extraction unit 503 is used to extract features from the first encrypted data corresponding to each data system to obtain N first encrypted vectors corresponding to the N data systems; and the first processing unit 504 is used to process the target user's loan application request based on the N first encrypted vectors.

[0136] In one optional embodiment, the loan application request processing apparatus further includes: a first determining unit, a second encryption unit, a second extraction unit, and a second processing unit.

[0137] Optionally, the first determining unit is used to determine, when the network status between the financial institution and at least one of the N data systems is abnormal, the data systems with normal network status among the N data systems are taken as target data systems, resulting in P target data systems, where P is a positive integer less than or equal to N; the second encryption unit is used to encrypt the data related to the loan application request stored in the target data system based on a second preset protocol corresponding to each target data system, resulting in P second encrypted data corresponding to the P target data systems, where the second preset protocol is an encryption protocol negotiated and determined by both the financial institution and each target data system; the second extraction unit is used to extract features from the second encrypted data corresponding to each target data system through each target data system, resulting in P second encrypted vectors corresponding to the P target data systems; and the second processing unit is used to process the loan application request of the target user based on the P second encrypted vectors.

[0138] In one optional embodiment, the first encryption unit 502 includes: a filtering subunit, a cleaning subunit, a desensitizing subunit, and an encryption subunit.

[0139] Optionally, a filtering subunit is used to filter data in the i-th data system based on the user identifier of the target user to obtain the original data related to the loan application request stored in the i-th data system, where i is a positive integer less than or equal to N; a cleaning subunit is used to clean the original data in the i-th data system to obtain first data, where data cleaning is used to remove redundant data in the original data; a desensitization subunit is used to desensitize the first data corresponding to the i-th data system to obtain second data, where desensitization is used to remove / update sensitive data in the original data; and an encryption subunit is used to encrypt the second data corresponding to the i-th data system based on a first preset protocol.

[0140] In one optional embodiment, the encryption subunit includes: a first encryption module and a second encryption module.

[0141] Optionally, the first encryption module is used to encrypt the second data corresponding to the i-th data system based on the first key corresponding to the first preset protocol to obtain the first encryption result; the second encryption module is used to add random noise data to the first encryption result corresponding to the i-th data system based on the differential privacy parameter corresponding to the first preset protocol to obtain the first encrypted data corresponding to the i-th data system.

[0142] In one alternative embodiment, the first processing unit 504 includes: an alignment subunit, an input subunit, a summation subunit, and a determination subunit.

[0143] Optionally, an alignment subunit is used to align N first encrypted vectors to obtain N third encrypted vectors, wherein the N third encrypted vectors have the same dimension; an input subunit is used to input the N third encrypted vectors into a target model, wherein the target model is a federated model trained based on N+1-dimensional historical data of different types from financial institutions and N data systems; a summation subunit is used to perform a weighted summation of the N third encrypted vectors through the target model to obtain a first target vector, wherein the first target vector is used to characterize the credit rating of the target user; and a determination subunit is used to determine the loan risk of the target user based on the first target vector and the user type of the target user, and to process the loan application request of the target user based on the loan risk of the target user.

[0144] In an optional embodiment, the loan application request processing apparatus further includes an acquisition unit and a generation unit.

[0145] Optionally, the acquisition unit is used to acquire the generation duration of the first target vector when the target user is not initiating a loan application request for the first time, wherein the generation duration is the duration between the generation time of the first target vector and the current time; the generation unit is used to generate a control signal when the generation duration of the first target vector is greater than a preset duration, wherein the control signal is used to re-detect the network status between the financial institution and N data systems.

[0146] In one optional embodiment, the loan application request processing apparatus further includes: a second determining unit, a second detecting unit, and a second processing unit.

[0147] Optionally, the second determining unit is used to determine X preset rules corresponding to the target user based on the user type when the generation time of the first target vector is less than or equal to a preset time. Here, X is a positive integer, and the X preset rules are risk assessment rules created by financial institutions based on historical loan applications with loan risks greater than preset risk values ​​within a historical time period. The second detection unit is used to detect the data related to the loan application request collected by the financial institution based on the X preset rules to obtain a first detection result. The second processing unit is used to process the loan application request of the target user based on the first detection result and the first target vector.

[0148] It should be noted that the first detection unit 501, the first encryption unit 502, the first extraction unit 503, and the first processing unit 504 mentioned above correspond to steps S201 to S204 in the method embodiment. The four units and the corresponding steps implement the same instances and application scenarios, but are not limited to the content disclosed in the above embodiments. It should be noted that the above modules or units can be hardware or software components stored in memory (e.g., memory 104) and processed by one or more processors (e.g., processors 102a, 102b, ..., 102n). The above modules can also be part of the device and run in the computer terminal 10 provided in the embodiment.

[0149] Embodiments of this application can also provide an electronic device. Figure 6 This is a structural block diagram of an electronic device according to an embodiment of this application, such as... Figure 6 As shown, the electronic device includes: one or more ( Figure 6 (Only one is shown) processor 602, memory 604, memory controller, and peripheral interface, wherein the peripheral interface is connected to the radio frequency module, audio module and display.

[0150] The memory can be used to store software programs and modules, such as the program instructions / modules corresponding to the methods and apparatus in the embodiments of this application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, thereby implementing the above-described methods. The memory may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include memory remotely located relative to the processor, and these remote memories can be connected to the terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0151] A processor can invoke information and application programs stored in memory via a transmission device to perform the following steps: According to one aspect of this application, a method for processing a loan application request is provided, comprising: after receiving an initial loan application request from a target user, detecting the network status between a financial institution and N data systems, where N is a positive integer, and different data systems are used to store different types of data related to the loan application request; assuming the network status between the financial institution and each data system is normal, encrypting the data related to the loan application request stored in each data system based on a first preset protocol to obtain N first encrypted data corresponding to the N data systems, wherein the first preset protocol is an encryption protocol jointly negotiated and determined by the financial institution and the N data systems; extracting features from the first encrypted data corresponding to each data system to obtain N first encrypted vectors corresponding to the N data systems; and processing the target user's loan application request based on the N first encrypted vectors.

[0152] The processor can invoke information and application programs stored in memory via a transmission device to execute the following steps: When the network status between the financial institution and at least one of the N data systems is abnormal, the data systems with normal network status among the N data systems are selected as target data systems, resulting in P target data systems, where P is a positive integer less than or equal to N; based on a second preset protocol corresponding to each target data system, the data related to the loan application request stored in that target data system is encrypted to obtain P second encrypted data corresponding to the P target data systems, where the second preset protocol is an encryption protocol negotiated and determined by both the financial institution and each target data system; feature extraction is performed on the second encrypted data corresponding to each target data system through each target data system to obtain P second encrypted vectors corresponding to the P target data systems; the loan application request of the target user is processed based on the P second encrypted vectors.

[0153] The processor can invoke information and applications stored in the memory via a transmission device to perform the following steps: filtering data in the i-th data system based on the user identifier of the target user to obtain the original data related to the loan application request stored in the i-th data system, where i is a positive integer less than or equal to N; cleaning the original data in the i-th data system to obtain first data, where data cleaning is used to remove redundant data in the original data; desensitizing the first data corresponding to the i-th data system to obtain second data, where desensitization is used to remove / update sensitive data in the original data; and encrypting the second data corresponding to the i-th data system based on a first preset protocol.

[0154] The processor can call the information and application stored in the memory through the transmission device to perform the following steps: encrypting the second data corresponding to the i-th data system based on the first key corresponding to the first preset protocol to obtain the first encryption result; adding random noise data to the first encryption result corresponding to the i-th data system based on the differential privacy parameter corresponding to the first preset protocol to obtain the first encrypted data corresponding to the i-th data system.

[0155] The processor can access information and applications stored in memory via a transmission device to perform the following steps: aligning N first encrypted vectors to obtain N third encrypted vectors, wherein the N third encrypted vectors have the same dimension; inputting the N third encrypted vectors into a target model, wherein the target model is a federated model trained on N+1-dimensional historical data of different types from financial institutions and N data systems; performing a weighted summation of the N third encrypted vectors through the target model to obtain a first target vector, wherein the first target vector is used to characterize the credit rating of the target user; determining the loan risk of the target user based on the first target vector and the user type of the target user, and processing the loan application request of the target user based on the loan risk of the target user.

[0156] The processor can call the information and application stored in the memory through the transmission device to perform the following steps: if the target user is not initiating a loan application request for the first time, obtain the generation duration of the first target vector, wherein the generation duration is the duration between the generation time of the first target vector and the current time; if the generation duration of the first target vector is longer than a preset duration, generate a control signal, wherein the control signal is used to re-detect the network status between the financial institution and N data systems.

[0157] The processor can invoke information and applications stored in the memory via a transmission device to perform the following steps: If the generation time of the first target vector is less than or equal to a preset time, determine X preset rules corresponding to the target user based on the user type, where X is a positive integer, and the X preset rules are risk assessment rules created by financial institutions based on historical loan applications with loan risks greater than preset risk values ​​within a historical time period; detect the data related to the loan application request collected by the financial institution based on the X preset rules to obtain a first detection result; process the target user's loan application request based on the first detection result and the first target vector.

[0158] This application provides a loan application request processing scheme. It employs collaborative encryption and feature vector integration, monitoring the network status between financial institutions and multiple data systems and applying preset encryption protocols. This achieves the goal of integrating user data from different data systems while protecting user privacy, thereby improving the accuracy of loan risk assessment and solving the technical problem of low accuracy in user loan risk assessment.

[0159] Specifically, upon receiving the initial loan application, this application monitors network connections with N data systems in real time to ensure the stability and security of data transmission. When all network conditions are detected as normal, this application encrypts the data in each system using a mutually agreed-upon encryption protocol, forming N encrypted data sets. Subsequently, this application controls each data system to extract features from the encrypted data internally, generating encrypted feature vectors. Finally, this application performs risk assessment based on the encrypted vectors from different data systems, thus avoiding access to the original data. While adhering to privacy protection requirements, this achieves the technical effect of improving the accuracy of user loan risk assessment, thereby solving the technical problem of low accuracy in user loan risk assessment caused by information isolation between different systems.

[0160] Those skilled in the art will understand that Figure 6 The structure shown is for illustrative purposes only. Electronic devices can also be smartphones, tablets, PDAs, mobile internet devices, PADs, and other terminal devices. Figure 6 This does not limit the structure of the aforementioned electronic device. For example, electronic devices may also include components that are more... Figure 6 The more or fewer components shown (such as network interfaces, display devices, etc.), or having the same Figure 6 The different configurations shown.

[0161] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing the hardware related to the terminal device. The program can be stored in a computer-readable storage medium, which may include: flash drive, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0162] Embodiments of this application may also provide a storage medium.

[0163] Optionally, in this embodiment of the application, the storage medium can be used to store the program code executed by the loan application request processing method provided in the above method embodiment.

[0164] Optionally, in this embodiment, the storage medium may be located in any computer terminal in a group of computer terminals in a computer network, or in any mobile terminal in a group of mobile terminals.

[0165] This application also provides a computer program product, which, when executed on a data processing device, is adapted to perform the processing method steps of a loan application request.

[0166] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0167] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0168] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0169] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0170] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0171] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0172] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method for processing loan application requests, characterized in that, include: After receiving the first loan application request from the target user, the network status between the financial institution and N data systems is detected, where N is a positive integer and the different data systems are used to store different types of data related to the loan application request; When the network status between the financial institution and each data system is normal, the data related to the loan application request stored in each data system is encrypted based on a first preset protocol to obtain N first encrypted data corresponding to the N data systems. The first preset protocol is an encryption protocol jointly negotiated and determined by the financial institution and the N data systems. By extracting features from the first encrypted data corresponding to each data system, N first encrypted vectors corresponding to the N data systems are obtained. The loan application request of the target user is processed based on the N first encryption vectors.

2. The method for processing loan application requests according to claim 1, characterized in that, After detecting the network status between the financial institution and N data systems, the method for processing the loan application request further includes: If the network status between the financial institution and at least one of the N data systems is abnormal, the data systems with normal network status among the N data systems are taken as target data systems, resulting in P target data systems, where P is a positive integer less than or equal to N. Based on the second preset protocol corresponding to each target data system, the data related to the loan application request stored in the target data system is encrypted to obtain P second encrypted data corresponding to the P target data systems, wherein the second preset protocol is an encryption protocol negotiated and determined by the financial institution and each target data system. By extracting features from the second encrypted data corresponding to each target data system, P second encrypted vectors corresponding to the P target data systems are obtained. The loan application request of the target user is processed based on the P second encryption vectors.

3. The method for processing loan application requests according to claim 1, characterized in that, Encrypting data related to the loan application request stored in each of the data systems based on a first preset protocol, including: Based on the user identifier of the target user, data is filtered in the i-th data system to obtain the original data related to the loan application request stored in the i-th data system, where i is a positive integer less than or equal to N; Data cleaning is performed on the original data in the i-th data system to obtain the first data, wherein the data cleaning is used to remove redundant data from the original data; The first data corresponding to the i-th data system is subjected to desensitization processing to obtain the second data, wherein the desensitization processing is used to remove / update sensitive data in the original data; The second data corresponding to the i-th data system is encrypted based on the first preset protocol.

4. The method for processing loan application requests according to claim 3, characterized in that, Encrypting the second data corresponding to the i-th data system based on the first preset protocol includes: Based on the first key corresponding to the first preset protocol, the second data corresponding to the i-th data system is encrypted to obtain the first encryption result; Based on the differential privacy parameters corresponding to the first preset protocol, random noise data is added to the first encryption result corresponding to the i-th data system to obtain the first encrypted data corresponding to the i-th data system.

5. The method for processing loan application requests according to claim 1, characterized in that, Processing the target user's loan application request based on the N first encryption vectors includes: The N first encryption vectors are aligned to obtain N third encryption vectors, wherein the N third encryption vectors have the same dimension; The N third encryption vectors are input into the target model, wherein the target model is a federated model trained based on N-dimensional historical data of different types corresponding to the N data systems; The target model is used to perform a weighted summation of the N third encryption vectors to obtain a first target vector, wherein the first target vector is used to characterize the credit rating of the target user. The loan application request of the target user is processed based on the first target vector.

6. The method for processing loan application requests according to claim 5, characterized in that, After obtaining the first target vector by weighted summation of the N third encrypted vectors using the target model, the processing method for the loan application request further includes: If the target user is not initiating a loan application for the first time, the generation duration of the first target vector is obtained, wherein the generation duration is the time between the generation time of the first target vector and the current time; If the generation time of the first target vector is longer than a preset time, a control signal is generated, wherein the control signal is used to re-detect the network status between the financial institution and the N data systems.

7. The method for processing loan application requests according to claim 6, characterized in that, After obtaining the generation time of the first target vector, the method for processing the loan application request further includes: If the generation time of the first target vector is less than or equal to the preset time, X preset rules corresponding to the target user are determined based on the user type, where X is a positive integer, and the X preset rules are risk assessment rules created by the financial institution based on historical loan applications with loan risk greater than a preset risk value within a historical time period. Based on the X preset rules, the data related to the loan application request collected by the financial institution is detected to obtain a first detection result; The loan application request of the target user is processed based on the first detection result and the first target vector.

8. A processing device for loan application requests, characterized in that, include: The first detection unit is used to detect the network status between the financial institution and N data systems after receiving the first loan application request from the target user, where N is a positive integer and the different data systems are used to store different types of data related to the loan application request. The first encryption unit is used to encrypt the data related to the loan application request stored in each data system based on a first preset protocol when the network status between the financial institution and each data system is normal, so as to obtain N first encrypted data corresponding to the N data systems. The first preset protocol is an encryption protocol jointly negotiated and determined by the financial institution and the N data systems. The first extraction unit is used to extract features from the first encrypted data corresponding to each data system to obtain N first encrypted vectors corresponding to the N data systems. The first processing unit is used to process the loan application request of the target user based on the N first encryption vectors.

9. A computer program product, characterized in that, The computer program product includes a computer program, wherein, when the computer program is executed, it controls the computer program product to perform the loan application request processing method according to any one of claims 1 to 7.

10. An electronic device, characterized in that, It includes one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to implement the loan application request processing method according to any one of claims 1 to 7.

Images