Data processing method, electronic device and computer program product

Abstract

The invention provides a data processing method, electronic equipment and a computer program product. The method comprises the following steps: in response to a credit objection processing request for a first object, determining a processing type corresponding to the credit objection processing request; based on a processing type corresponding to the credit objection processing request, first data of the first object is determined, and the first data comprises object data of the first object and statistical data of the credit investigation behavior implemented by the first object; determining a processing result for the credit objection processing request based on the first data; and sending the processing result to a request terminal corresponding to the credit objection processing request. According to the method and the device, the credit objection processing request can be processed in a targeted manner according to the processing type of the credit objection processing request, so that the data processing efficiency and accuracy and the data security are improved.

Description

Technical Field

[0001] The present application relates to computer technology, and in particular to a data processing method, electronic equipment, and computer program product. Background Art

[0002] With the continuous improvement of the social credit system, personal credit reports have become crucial information reflecting an individual's credit status and are widely used in various business scenarios. However, during the actual generation of credit information, inaccurate or incomplete content may occur due to errors in information collection or untimely updates. To address this issue, credit report objection handling mechanisms have emerged, providing individuals with a way to correct errors in their credit reports and ensuring the accuracy of their personal credit information. Summary of the Invention

[0003] The embodiments of the present application provide a data processing method, electronic device, and computer program product, which can perform targeted processing on credit objection processing requests based on the processing type of the credit objection processing requests, thereby improving the efficiency, accuracy, and security of data processing.

[0004] The technical solution of the embodiment of the present application is implemented as follows:

[0005] This embodiment of the present application provides a data processing method, the method comprising:

[0006] In response to a credit objection handling request for a first object, determining a processing type corresponding to the credit objection handling request;

[0007] determining, based on the processing type corresponding to the credit objection processing request, first data of the first object, the first data including object data of the first object and statistical data of credit investigation actions performed by the first object;

[0008] Determining a processing result for the credit objection processing request based on the first data;

[0009] The processing result is sent to the request terminal corresponding to the credit objection processing request.

[0010] An embodiment of the present application provides a data processing device, including:

[0011] a determination module, configured to, in response to a credit objection handling request for a first object, determine a processing type corresponding to the credit objection handling request;

[0012] The determining module is further configured to determine first data of the first object based on the processing type corresponding to the credit objection processing request, where the first data includes object data of the first object and statistical data of credit investigation behavior performed by the first object;

[0013] The determining module is further configured to determine a processing result for the credit objection processing request based on the first data;

[0014] The sending module is used to send the processing result to the request terminal corresponding to the credit objection processing request.

[0015] An embodiment of the present application provides an electronic device, comprising:

[0016] a memory for storing computer-executable instructions or computer programs;

[0017] The processor is used to implement the data processing method provided in the embodiment of the present application when executing the computer-executable instructions or computer programs stored in the memory.

[0018] An embodiment of the present application provides a computer-readable storage medium storing a computer program or computer-executable instructions for implementing the data processing method provided in the embodiment of the present application when executed by a processor.

[0019] An embodiment of the present application provides a computer program product, including a computer program or computer-executable instructions. When the computer program or computer-executable instructions are executed by a processor, the data processing method provided in the embodiment of the present application is implemented.

[0020] The embodiments of the present application have the following beneficial effects:

[0021] In an embodiment of the present application, in response to a credit objection processing request for a first object, the processing type corresponding to the credit objection processing request is determined, and then based on the processing type corresponding to the credit objection processing request, the first data of the first object is determined, wherein the first data includes the object data of the first object and the statistical data of the credit investigation behavior implemented by the first object. By sending the processing result to the request terminal corresponding to the credit objection processing request, the processing terminal can perform targeted processing on the first object according to the processing result, thereby ensuring the rationality and data security of the processing of the first object. Therefore, through the embodiment of the present application, the credit objection processing request can be targeted according to the processing type of the credit objection processing request, thereby improving the efficiency, accuracy and data security of the credit objection processing. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 is a structural diagram of a data processing system 100 provided in an embodiment of the present application;

[0023] Figure 2 2 is a schematic diagram of the structure of the server 200 provided in an embodiment of the present application;

[0024] Figure 3A Schematic diagram of the data processing method provided in the embodiment of the present application;

[0025] Figure 3B is a schematic diagram of a process for determining first data provided in an embodiment of the present application;

[0026] Figure 3C This is a flowchart of determining a processing result provided by an embodiment of the present application;

[0027] Figure 3D is another flowchart of determining a processing result provided by an embodiment of the present application;

[0028] Figure 4 This is a schematic diagram of the structure of the credit investigation objection handling system provided in an embodiment of the present application;

[0029] Figure 5 This is a flowchart of credit investigation objection processing provided by an embodiment of the present application;

[0030] Figure 6 This is another flowchart for determining processing results provided in an embodiment of the present application. DETAILED DESCRIPTION

[0031] In order to make the purpose, technical solutions and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as limiting this application. All other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0032] In the following description, reference is made to “some embodiments”, which describes a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0033] In the following description, the terms "first\second\third" involved are merely used to distinguish similar objects and do not represent a specific ordering of the objects. It can be understood that "first\second\third" can be interchanged with a specific order or sequence where permitted, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.

[0034] In the embodiments of the present application, the term "module" or "unit" refers to a computer program or a part of a computer program that has a predetermined function and works together with other related parts to achieve a predetermined goal, and can be implemented in whole or in part by using software, hardware (such as processing circuits or memories) or a combination thereof. Similarly, a processor (or multiple processors or memories) can be used to implement one or more modules or units. In addition, each module or unit can be part of an overall module or unit that includes the function of the module or unit.

[0035] Unless otherwise defined, all technical and scientific terms used in the embodiments of the present application have the same meanings as those commonly understood by those skilled in the art. The terms used in the embodiments of the present application are only for the purpose of describing the embodiments of the present application and are not intended to limit the present application.

[0036] The relevant data collection and processing in the embodiments of this application should be strictly in accordance with the requirements of relevant laws and regulations when applied in examples, and the informed consent or separate consent of the personal information subject should be obtained. Subsequent data use and processing should be carried out within the scope of authorization of laws and regulations and the personal information subject.

[0037] Before further describing the embodiments of the present application in detail, the nouns and terms involved in the embodiments of the present application are explained. The nouns and terms involved in the embodiments of the present application are subject to the following interpretations.

[0038] 1) Credit investigation business: the activities of collecting, organizing, storing, processing and providing credit information of enterprises and individuals to information users;

[0039] 2) Credit information: also known as credit investigation information, refers to basic information, loan information, and other relevant information collected in accordance with the law to provide services for financial activities and used to identify and judge the credit status of enterprises and individuals, as well as analytical and evaluation information based on the aforementioned information;

[0040] 3) Credit information objection: refers to the formal questioning and correction request made by the information subject to the credit reporting agency or information provider when the information subject disagrees with the credit information reflected in the credit report and believes that the information contains errors or omissions;

[0041] 4) Credit Repair: This refers to the process whereby individuals or businesses, when discovering inaccurate, incomplete, or outdated information in their credit reports, apply through legal channels to have this information corrected or deleted. The purpose is to ensure that the credit report truly reflects the credit status of the information subject, thereby safeguarding their legitimate rights and interests.

[0042] 5) Credit fraud: also known as credit fraud, credit falsification, etc., refers to the act of criminals using personal information to falsely change or delete real negative credit records in credit reports by fabricating facts, forging materials, abusing credit objection procedures, etc.

[0043] In related technologies, objection application information is collected and structured, and then related objection businesses are associated, and finally objection processing is carried out. However, this method of handling credit objections has the following problems:

[0044] 1. It is difficult to detect fraud risks in objection application information through text analysis, and data security is low;

[0045] 2. The information source is single, so the accuracy of the objection handling results is low;

[0046] 3. The generated objection handling information can only serve the information collection agency. When the same objection application is related to other businesses, it is necessary to collect evidence, analyze and make decisions again, which has low processing efficiency.

[0047] The embodiments of the present application provide a data processing method, apparatus, device, computer-readable storage medium, and computer program product, which can perform targeted processing on credit objection processing requests based on the processing type of the credit objection processing request, thereby improving processing efficiency, processing accuracy, and data security. The following describes exemplary applications of the electronic devices provided in the embodiments of the present application. The electronic devices provided in the embodiments of the present application can be implemented as various types of terminals, such as laptops, tablet computers, desktop computers, set-top boxes, smartphones, smart speakers, smart watches, smart TVs, and in-vehicle terminals, and can also be implemented as servers. Below, we will describe exemplary applications of the electronic device implemented as a server.

[0048] See also Figure 1 , Figure 1 is a structural diagram of a data processing system 100 provided in an embodiment of the present application, Figure 1 The server 200, the network 300 and the request terminal 400 are involved. The request terminal 400 is connected to the server 200 via the network 300, which can be a wide area network or a local area network, or a combination of the two. The request terminal 400 is used to generate a credit objection processing request according to the user's operation and send it to the server 200 via the network 300. The server 200 responds to the credit objection processing request for the first object and determines the processing type corresponding to the credit objection processing request; based on the processing type corresponding to the credit objection processing request, determines the first data of the first object, the first data including the object data of the first object and the statistical data of the credit investigation behavior implemented by the first object; based on the first data, determines the processing result for the credit objection processing request; then the server 200 sends the processing result to the request terminal 400 corresponding to the credit objection processing request via the network 300, so that the request terminal 400 processes the first object according to the processing result.

[0049] For example, the electronic device that processes data is the server mentioned above, see Figure 2 , Figure 2 is a schematic diagram of the structure of the server 200 provided in an embodiment of the present application, Figure 2 The server 200 shown includes: at least one processor 210, a memory 230 and at least one network interface 220. The various components in the server 200 are coupled together via a bus system 240. It is understood that the bus system 240 is used to achieve connection and communication between these components. In addition to including a data bus, the bus system 240 also includes a power bus, a control bus and a status signal bus. However, for the sake of clarity, the bus system 240 is not described in detail. Figure 2 Various buses are labeled as bus system 240 .

[0050] The processor 210 can be an integrated circuit chip with signal processing capabilities, such as a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc., where the general-purpose processor can be a microprocessor or any conventional processor, etc.

[0051] The memory 230 may be removable, non-removable, or a combination thereof. Exemplary hardware devices include solid-state memory, a hard drive, an optical drive, etc. The memory 230 may optionally include one or more storage devices that are physically remote from the processor 210.

[0052] The memory 230 includes volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory may be a read-only memory (ROM), and the volatile memory may be a random access memory (RAM). The memory 230 described in the embodiments of the present application is intended to include any suitable type of memory.

[0053] In some embodiments, memory 230 can store data to support various operations, examples of which include programs, modules, and data structures, or a subset or superset thereof, as exemplified below.

[0054] Operating system 231, including system programs for processing various basic system services and performing hardware-related tasks, such as the framework layer, core library layer, driver layer, etc., for implementing various basic services and processing hardware-based tasks;

[0055] The network communication module 232 is used to reach other electronic devices via one or more (wired or wireless) network interfaces 220 . Exemplary network interfaces 220 include Bluetooth, Wireless Authentication (WiFi), and Universal Serial Bus (USB).

[0056] In some embodiments, the apparatus provided in the embodiments of the present application may be implemented in software. Figure 2 The data processing device 233 stored in the memory 230 is shown. This device can be software in the form of a program or plug-in, and includes the following software modules: a determination module 2331 and a sending module 2332. These modules are logical and can be arbitrarily combined or further separated according to the functions they implement. The functions of each module will be described below.

[0057] In other embodiments, the apparatus provided in the embodiments of the present application may be implemented in hardware. As an example, the apparatus provided in the embodiments of the present application may be a processor in the form of a hardware decoding processor, which is programmed to execute the data processing method provided in the embodiments of the present application. For example, the processor in the form of a hardware decoding processor may be one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), or other electronic components.

[0058] The data processing method provided in the embodiment of the present application will be described in conjunction with the exemplary application and implementation of the terminal provided in the embodiment of the present application.

[0059] The following describes the data processing method provided by the embodiment of the present application. As mentioned above, the electronic device that implements the data processing method of the embodiment of the present application can be a terminal, a server, or a combination of the two. Therefore, the execution entity of each step will not be repeated below.

[0060] It should be noted that the data processing examples below are based on credit data in a credit investigation scenario. Based on their understanding of the following, those skilled in the art can apply the data processing method provided in the embodiments of this application to data processing including other types of data.

[0061] See also Figure 3A , Figure 3A This is a flow chart of the data processing method provided in the embodiment of the present application, which will be combined with Figure 3A The steps shown are explained.

[0062] In step 101 , in response to a credit objection handling request for a first object, a processing type corresponding to the credit objection handling request is determined.

[0063] Here, a credit objection handling request is used to request an update or acquisition of the credit data of the first subject. Therefore, the processing types corresponding to the credit objection handling request include a data update type and a data acquisition type. Taking the credit investigation scenario as an example, when a user objects to their own credit information, they can submit a data processing request to the credit investigation agency to modify the credit information. The purpose is to change their own credit information. In this case, the processing type of the data processing request is a data update type. If the credit investigation agency refuses to change the user's credit information, the user can continue to file a credit investigation review or lawsuit through the court. In this case, the court will send a credit objection handling request for administrative review and litigation evidence collection to the relevant credit investigation agency. The purpose is to obtain the user's relevant credit investigation data to determine whether the refusal to change the user's credit information is reasonable. In this case, the processing type of the credit objection handling request sent by the court to the relevant credit investigation agency for administrative review and litigation evidence collection is a data acquisition type. In some embodiments, the processing type of the credit objection handling request can be determined based on the source of the credit objection handling request. This is because data update-type credit objection processing requests are usually sent by individual users or by users entrusting relevant credit reporting agencies, while data acquisition-type credit objection processing requests are usually sent by banks or courts, etc. Therefore, the processing type of the credit objection processing request can be determined based on the source of the credit objection processing request. Alternatively, the processing type corresponding to the credit objection processing request can be determined by analyzing the purpose of the credit objection processing request. If the purpose of the credit objection processing request is to update data, the processing type is the data update type; if the purpose of the data acquisition request is to obtain data, the processing type is the data acquisition type.

[0064] In step 102, first data of a first object is determined based on a processing type corresponding to the credit objection processing request.

[0065] Here, the first data includes the object data of the first object and the statistical data of the credit investigation behavior implemented by the first object. Object data refers to personal information related to the user, such as basic information such as user identifier (ID), age, telephone number, occupation, address, etc. Credit investigation behavior refers to behavior related to credit investigation, such as borrowing, use of credit cards, tax payment, etc. Correspondingly, statistical data can be loan and credit card repayment records (whether repayments are made on time, including loans, credit cards, consumer installments, etc.); whether there are overdue repayments, and the number and severity of overdue payments; records of providing guarantees for others or acting as a guarantor; court judgments, arbitration awards, administrative penalty records and other credit investigation behaviors, which can reflect the credit status of individuals or enterprises and are used to assess credit risks.

[0066] In step 103 , a processing result for the credit objection processing request is determined based on the first data.

[0067] Here, the processing result includes the data update policy or data acquisition result for the credit objection handling request. Specifically, if the credit objection handling request is of the data update type, the corresponding processing result is the data update policy; if the credit objection handling request is of the data acquisition type, the corresponding processing result is the data acquisition result. The data update policy indicates whether the relevant data of the first object is updated.

[0068] The following describes the processing type of a credit objection processing request as a data update type.

[0069] In some embodiments, see Figure 3B In the case where the processing type is a data update type, step 102 may be implemented through steps 1021 to 1023, including:

[0070] In step 1021, based on the object identifier of the first object, object data of the first object and first behavior data of the first object performing the credit investigation behavior are determined from a first data source.

[0071] Here, an object identifier is an identifier assigned to an object to uniquely identify it within the system. It can be a user ID, mobile phone number, location information, or other fields that identify the user. First behavioral data refers to behavioral data related to the first object's credit reporting behavior, stored in the first data source. The first data source belongs to the first entity providing services for the first object and refers to the entity that receives the credit objection handling request. For example, the first data source is the credit reporting agency that receives the credit objection handling request, referred to as this agency. Using the first object's object identifier, this agency retrieves information related to the first object from its stored data. For example, basic information such as the user's ID, phone number, occupation, and address, which the user proactively provides during the pre-loan application phase, is used as object data. The first behavioral data also includes the user's credit usage and overdue payments during the loan phase; audio and video materials of the user's communication with the agency's consumer protection, customer service, and other customer service departments during the post-loan phase, as evidence that the overdue payment was not intentional but due to force majeure and should be waived; and information such as the user's voiceprint, audio and video recordings, profile pictures, location, network access method, and personal credit report, which are stored by the user.

[0072] In step 1022, based on the object identifier, second behavior data of the first object performing the credit investigation behavior is determined from the second data source.

[0073] Here, the second data source belongs to a second entity that is different from the first entity, and refers to a related institution that has not received a credit objection handling request, called a peer institution, which may include a credit reporting center, a bank, a financial regulatory authority, other regulatory departments, a court, other credit reporting institutions, etc. Through the object identifier of the first object, information related to the first object is read from the data stored by the peer institution, including personal information and other financial evidence submitted by the user when applying for a credit limit; information related to the objection applicant that is disclosed by the peer institution and is helpful in making objection handling; information on the credit objection-related activities of the objection applicant that can be obtained by the information collection agency from the peer institution through technical means; derivative information generated after processing user information, such as anti-fraud processing information in the form of text, image, or audio and video, such as user voice, voiceprint, image and other information.

[0074] In step 1023, based on the first behavior data and the second behavior data, statistical data of the credit investigation behavior performed by the first subject is determined.

[0075] Here, the first behavior data and the second behavior data are combined to determine statistical data of the credit investigation behavior performed by the first object.

[0076] In step 1024 , the object data and the statistical data are combined into first data.

[0077] Here, the object data and the statistical data are combined and determined as first data of the first object.

[0078] In an embodiment of the present application, when the processing type is a data update type, first information of the first object is determined from a first data source based on the object identifier of the first object. The first information includes the object data of the first object and second data related to the first object's credit investigation behavior. Based on the object identifier, third data related to the first object's credit investigation behavior is determined from a second data source. The second data and the third data are determined as statistical data related to the first object's credit investigation behavior. In this way, collecting relevant data of the first object through different data sources can improve the comprehensiveness and efficiency of determining the first data of the first object, facilitate accurate analysis of the first object through the first data, and thus improve the accuracy of data processing.

[0079] In some embodiments, see Figure 3C In the case where the processing type is a data update type, step 103 may be implemented through steps 1031A to 1033A, including:

[0080] In step 1031A, credit prediction processing is performed on the first data using at least one pre-trained prediction model to obtain at least one prediction result.

[0081] Here, multiple prediction models can be pre-trained. Then, at least one of the pre-trained prediction models can be used to perform credit prediction processing on the first data, generating at least one prediction result. The prediction result represents the probability that the first subject is subject to credit risk, suspected of fraud, or suspected of illegal behavior. For example, the first data can be input into a pre-trained intelligent recognition model, an anti-fraud recognition model, and an intelligent question-and-answer model to generate at least one prediction result. The at least one prediction result represents the probability that the user is suspected of illegal fraud. The intelligent recognition model is used to identify the probability that the first subject is subject to credit risk based on the first data. The anti-fraud recognition model is used to identify the probability that the first subject is subject to fraud based on the first data. The intelligent question-and-answer model is a pre-trained knowledge-based language model based on relevant laws and regulations such as credit reporting services and credit reporting industry management measures, relevant laws and regulations on credit reporting objections, administrative reconsideration cases for credit reporting objections, litigation cases involving credit reporting objections, and typical fraud cases involving credit reporting objections. It can perform intelligent question-and-answer based on the application materials and supporting documents provided by the user filing a credit reporting objection. It then uses relevant laws and regulations to determine whether the user is suspected of illegal credit reporting, the probability of suspected illegal credit reporting, and the analysis process and basis.

[0082] In step 1032A, matching processing is performed on at least one prediction result based on preset rules to obtain a first update strategy.

[0083] Here, the first update strategy is to approve or reject the update. The first update strategy can be obtained by matching at least one prediction result with a pre-trained expert model based on preset rules. The expert model contains a series of preset rules that determine whether a credit objection request should be approved by determining whether the first subject is suspected of fraud and whether it is legal and compliant. The preset rules include a first rule and a second rule. If at least one prediction result successfully matches the first rule, the first update strategy is to reject the update. If every prediction result successfully matches the second rule, the first update strategy is to approve the update.

[0084] In some embodiments, step 1032A may be implemented by the following process, including:

[0085] When at least one prediction result matches any first rule in the preset rules, the first update strategy is determined to be to reject the update; when each prediction result matches N second rules in the preset rules, the first update strategy is determined to be to agree to the update, where N is an integer greater than 1.

[0086] Here, the first rule represents the rules that are satisfied when refusing to update the data of the first object. For example, the first rule may include: at least one prediction result given by multiple models tends to determine that the consumer is suspected of fraud; at least one prediction result given by multiple models indicates that the probability of the consumer being suspected of fraud is higher than a threshold probability; the first data indicates that the user is suspected of illegal behavior at at least one peer institution; the first data has a high risk; the first data is highly similar to the supporting materials of other consumers; the supporting materials in the first data are determined by the image recognition model to be forged (such as photocopied certificates, tampered certificates, tampered hospital diagnosis certificates, forged official seals, etc.). The first rule can be manually determined or generated through analysis and screening using a large prediction model, and can be adjusted based on actual operating conditions. When at least one prediction result matches any first rule in the preset rules, the first update strategy is determined to be to refuse the update. In addition to the first rule automatically determining that a credit objection processing request has failed, the preset rules also include a second rule automatically determining that an objection has succeeded. The second rule represents the rules that are satisfied when approving the data update of the first object. For example, the second rule may include: the user's objection content is that the overdue record is incorrect, and the user's overdue information and repayment information conflict after business determination; the user has settled within the specified time limit but is incorrectly marked as overdue; the supporting materials provided by the user are identified as having a low probability of being forged, or are manually verified to be authentic; no automatic rules that can determine that the objection has failed are triggered; the prediction results given by multiple models all reflect an extremely low probability of the user being a fraud or an intermediary; other scenarios that the People's Bank of China or regulatory authorities determine should be supported, etc. When some or all of the above second rules are met, that is, the number of second rules that are met is greater than N, then the credit objection processing request can be determined to have been approved, and the first update strategy is determined to be approving the update.

[0087] In an embodiment of the present application, if at least one prediction result matches any first rule in the preset rules, the first update policy is determined to be to reject the update; if each prediction result matches N second rules in the preset rules, the first update policy is determined to be to approve the update. In this way, the preset rules can be flexibly set according to actual needs, and by matching at least one prediction result with both the first rule and the second rule simultaneously, the accuracy and efficiency of determining the first update policy can be improved.

[0088] In step 1033A, if the first update strategy meets the preset output condition, the first update strategy is determined as the processing result.

[0089] Here, the preset output conditions include the first update strategy being approved for the update and not selected for manual determination, or the first update strategy being rejected for the update. This is because, after matching at least one prediction result using the expert model, a portion of credit objection handling requests for which the first update strategy is approved for the update is randomly selected according to a preset selection probability for manual verification to ensure the accuracy of the first update strategy. If the first update strategy is approved for the update but not selected, or if the first update strategy is rejected for the update, the first update strategy can be directly determined as the processing result.

[0090] In an embodiment of the present application, credit prediction processing is performed on first data using at least one pre-trained prediction model to obtain at least one prediction result; matching processing is performed on the at least one prediction result based on preset rules to obtain a first update strategy; and if the first update strategy meets preset output conditions, the first update strategy is determined as the processing result. In this way, determining the first update strategy based on at least one prediction result and preset rules can improve the accuracy of determining the first update strategy. Moreover, if the first update strategy meets the preset output conditions, the first update strategy is determined as the processing result, further improving the efficiency and accuracy of determining the processing result.

[0091] In some embodiments, when the first update strategy does not meet the preset output condition, the processing result can be determined by the following process, including:

[0092] Determine first data, at least one prediction result and a first update strategy as data to be processed; determine a processing level corresponding to the data to be processed, and send the data to be processed to a processing terminal pre-associated with the processing level; receive a second update strategy sent by the processing terminal based on the data to be processed, and determine the second update strategy as a processing result.

[0093] Here, the processing level is used to characterize the processing difficulty of the data to be processed. It can be determined based on the amount of data to be processed. The larger the amount of data, the higher the processing difficulty of the data to be processed. The processing terminal is pre-associated with the processing level. Different processing terminals correspond to different staff members. The staff member's work experience and data processing capabilities correspond to the processing level. When the first update strategy does not meet the preset output conditions, it means that the first update strategy is agreed to update and is randomly selected for manual judgment. At this time, the first data, at least one prediction result, and the first update strategy are determined as the data to be processed, and the data to be processed are sent to the processing terminal corresponding to the processing level corresponding to the data to be processed. The data to be processed is manually analyzed and the second update strategy is determined. The second update strategy obtained by manual judgment is then determined as the processing result.

[0094] In an embodiment of the present application, if the first update strategy does not meet the preset output conditions, the first data, at least one prediction result, and the first update strategy are determined as pending data; the processing level corresponding to the pending data is determined, and the pending data is sent to the processing terminal corresponding to the processing level; the second update strategy sent by the processing terminal based on the pending data is received, and the second update strategy is determined as the processing result. In this way, for a credit objection processing request where the first update strategy is to approve the update, manual determination can be made to further determine whether the data of the first object can be updated, thereby improving the accuracy of determining the processing result corresponding to the credit objection processing request and ensuring the data security of the first object.

[0095] In some embodiments, when the processing type is a data update type, after determining the processing result of the credit objection processing request, the processing process of the credit objection processing request may be recorded through the following process, including:

[0096] A first decision record is generated, the first data and the first decision record are combined into first evidential data, and the first evidential data is stored.

[0097] Here, the first decision record includes the processing result and the corresponding first decision basis. The first decision basis includes the processing result, all decision basis used in determining the processing result, and the source of the decision basis. When storing the first evidential data, the evidence can be stored in a blockchain or by invoking an external evidence storage service. This first evidential data can record and preserve the relevant data of the credit objection processing request, providing an effective basis for subsequent verification of the authenticity, integrity, and reliability of the processing process, thereby improving the security and credibility of data processing.

[0098] The following describes the data acquisition type using the credit objection handling request processing type as the data acquisition type.

[0099] In some embodiments, when the processing type is a data acquisition type, step 102 may be implemented by the following process, including:

[0100] The object identifier of the first object is determined based on the credit objection processing request; when the first data source includes second evidence data corresponding to the object identifier, the second evidence data is determined as the first data of the first object.

[0101] Here, the credit objection processing request usually carries the object identifier of the first object. The object identifier is an identifier assigned to an object in order to uniquely identify an object in the system. It can be a user ID, user mobile phone number, user location information, or other fields that have the function of identifying the user's identity. When the processing type is data acquisition type, it means that the user has previously objected to his or her own credit information and submitted a credit objection request to the credit reporting agency, but the credit reporting agency refused to change the user's credit information. Therefore, the credit reporting agency should have a processing record of the user's previous credit objection request, that is, the second evidence data. If the first data source includes the second evidence data corresponding to the object identifier, the second evidence data can be directly determined as the first data of the first object.

[0102] In some embodiments, if the first data source does not include the second evidentiary data corresponding to the object identifier, this indicates that the entity that previously accepted the user's credit investigation objection request is not the entity corresponding to the first data source, or that data loss has occurred, resulting in the first data source not including the second evidentiary data. In this case, it is necessary to determine the object data of the first object and the first behavior data of the first object's credit investigation behavior from the first data source based on the object identifier of the first object. Then, based on the object identifier, determine the second behavior data of the first object's credit investigation behavior from the second data source. The first behavior data and the second behavior data are then combined to determine the statistical data of the first object's credit investigation behavior, thereby obtaining the first data of the first object.

[0103] In this embodiment of the present application, when the processing type is data acquisition, the object identifier of the first object is determined based on the credit objection processing request; if the first data source includes second stored evidence data corresponding to the object identifier, the second stored evidence data is determined as the first data of the first object. By directly determining the second stored evidence data as the first data of the first object, the utilization rate of data from different processing stages of the same object can be improved, and the efficiency and accuracy of determining the first data can be improved.

[0104] In some embodiments, see Figure 3D In the case where the processing type is a data acquisition type, step 103 may be implemented through steps 1031B to 1033B, including:

[0105] In step 1031B, a third update strategy for the first object is determined from the second evidence data.

[0106] Here, the third update strategy refers to the update strategy recorded in the second evidence data, which is determined when the user previously submitted a credit objection request to the credit reporting agency. The third update strategy is usually to refuse to update.

[0107] In step 1032B, a fourth update strategy for the first object is determined based on the fourth data carried in the credit objection handling request.

[0108] Here, the fourth data refers to the latest proof data carried in the credit objection processing request. This is because, after a user has previously submitted a credit objection request and was rejected, when filing a review or lawsuit again, new proof materials are usually added to prove that their credit data should be updated. In this case, it is necessary to perform prediction processing on the fourth data to obtain at least one prediction result, and match the at least one prediction result based on preset rules to obtain a candidate fourth update strategy; when the candidate fourth update strategy meets the preset output conditions, the candidate fourth update strategy is determined as the fourth update strategy; when the candidate fourth update strategy does not meet the preset output conditions, the first data, at least one prediction result and the candidate fourth update strategy are determined as the data to be processed; the processing level corresponding to the data to be processed is determined, and the data to be processed is sent to the processing terminal corresponding to the processing level; the new update strategy sent by the processing terminal based on the data to be processed is received and determined as the fourth update strategy.

[0109] In step 1033B, when the third update strategy and the fourth update strategy are the same, the second evidence data is determined as the processing result.

[0110] Here, if the third and fourth update strategies are identical, this indicates that the new update strategy is identical to the previous one. In this case, the second stored evidence data is determined as the processing result and returned to the requesting terminal that submitted the credit objection processing request to verify the rationality and accuracy of the previous decision-making process. Thus, when the third and fourth update strategies are identical, determining the second stored evidence data as the processing result verifies the rationality and accuracy of the previous decision-making process, thereby improving the credibility and reliability of the data processing.

[0111] In some embodiments, when the third update strategy and the fourth update strategy are different, a second decision record is generated; and the second decision record and the second evidence data are determined as the processing result.

[0112] Here, if the third and fourth update policies differ, this indicates that the previous third update policy was inaccurate, or that the fourth data provided by the user significantly differs from the previous user-related data. In this case, the decision-making process for the fourth update policy and the previous second stored evidence data must be returned to the requesting terminal for review and verification. The second decision record includes the fourth update policy and the second decision basis corresponding to the fourth update policy. The second decision basis includes all decision basis used in determining the fourth update policy, as well as the source of the decision basis. Thus, if the third and fourth update policies differ, the second decision record corresponding to the fourth update policy and the second stored evidence data are collectively determined as the processing result. This facilitates accuracy analysis of the first object based on the processing result, thereby improving the reliability and security of data processing for the first object.

[0113] In some embodiments, when the processing type is data acquisition type, after the second decision record is generated, the processing process of the credit objection handling request may be recorded through the following process, including:

[0114] The second stored evidence data is updated based on the second decision record to obtain updated second stored evidence data; or the second decision record is added to the second stored evidence data to obtain updated second stored evidence data; and the updated second stored evidence data is stored.

[0115] Here, the corresponding data in the second evidence data can be replaced based on the second decision record to obtain updated second evidence data. Alternatively, the second decision record can be added to the second evidence data to obtain updated second evidence data. The updated second evidence data is then stored again. In this way, the relevant data of the credit objection processing request can be recorded and saved through the second evidence data, which is convenient for providing an effective basis for the authenticity, integrity and reliability of the subsequent proof processing process, thereby improving the security and credibility of data processing. In addition, during the storage process, the interface of a qualified electronic evidence notarization agency can be called to notarize the updated second evidence data and generate an electronic notarial certificate to ensure the validity of the second evidence data.

[0116] In step 104, the processing result is sent to the request terminal corresponding to the credit objection processing request.

[0117] Here, the request terminal refers to the terminal device that sends the credit objection processing request. After obtaining the processing result corresponding to the credit objection processing request, the processing result needs to be sent to the request terminal corresponding to the credit objection processing request, so that the request terminal can take corresponding measures based on the processing result.

[0118] In an embodiment of the present application, in response to a credit objection handling request for a first object, a processing type corresponding to the credit objection handling request is determined, and then, based on the processing type corresponding to the credit objection handling request, first data of the first object is determined. In this way, the method for determining the first data can be flexibly selected based on the processing type corresponding to the credit objection handling request, thereby improving the efficiency and accuracy of determining the first data. The first data includes the object data of the first object and statistical data on the credit investigation behavior performed by the first object. Therefore, the first data can comprehensively and accurately reflect the object characteristics and behavioral characteristics related to credit investigation of the first object, thereby improving the accuracy of determining the processing result for the credit objection handling request based on the first data. By sending the processing result to the requesting terminal corresponding to the credit objection handling request, the processing terminal can perform targeted processing on the first object based on the processing result, thereby ensuring the rationality and data security of the processing of the first object. Therefore, through this embodiment of the present application, credit objection handling requests can be processed in a targeted manner based on the processing type of the credit objection handling request, improving the efficiency, accuracy, and data security of data processing.

[0119] In some embodiments, data sharing of credit objection handling requests may also be achieved through the following process, including:

[0120] Determine third stored evidence data for the credit objection processing request; send an information synchronization request to the second data source; or, in response to a data query request sent by the second data source, send the credit objection processing request and the third stored evidence data to the second data source.

[0121] Here, the information synchronization request carries a credit objection handling request and third-stored evidence data, actively requesting the second data source to store the credit objection handling request and third-stored evidence data. Alternatively, the information synchronization request can passively await a data query request from the second data source and, upon receipt of the data query request, send the credit objection handling request and third-stored evidence data to the second data source. The third-stored evidence data includes the first data, processing results, first decision records, or second decision records, and other data related to the credit objection handling request. The first or second-stored evidence data can be directly identified as the third-stored evidence data. By sending the credit objection handling request and third-stored evidence data to the second data source, data sharing between different data sources can be achieved, improving data liquidity and data utilization.

[0122] The following describes an exemplary application of the embodiments of the present application in a practical application scenario.

[0123] See also Figure 4 , Figure 4 This is a structural diagram of the credit investigation objection handling system provided in the embodiment of the present application. Figure 4As shown, the credit investigation objection handling system provided in the embodiment of the present application includes five modules:

[0124] Credit objection processing request receiving module 41: is used to receive credit objection processing requests, including: credit objection applications 411 initiated by credit objection applicants, credit objection applications 412 forwarded by credit reporting centers entrusted by credit objection applicants, credit objection applications 413 forwarded by banks, financial regulatory authorities, or other institutions that accept credit complaints, and credit objection evidence inquiry applications 414 filed by courts when accepting administrative or civil lawsuits. At the same time, it can also receive objection application forms and related supporting materials submitted by objection applicants. The objection application form contains the applicant's relevant information (name, ID number, address, and other personal information). The related supporting materials include supporting materials submitted by the applicant proving that their overdue or outstanding debts meet the requirements for elimination, which can be in the form of text, images, audio, or video.

[0125] Information collection module 42: located downstream of the objection application acceptance module, it can determine the source of the objection application (user individual, credit reporting center, bank, financial supervision and administration bureau, other regulatory departments, court, other institutions, etc.), determine the processing type of the credit objection application according to the source of the objection application, and collect some or all of the following information (corresponding to the first data in other embodiments): applicant information already mastered by the information collector, including personal information and other financial proof materials submitted when applying for the credit limit; information related to the objection applicant disclosed by peer institutions that is helpful for making objection handling; information that the information collection agency can obtain from peer institutions through technical means on the objection applicant's activities related to credit objection; all laws, regulations and industry management methods issued by banks, courts and other institutions on the handling of credit objections; relevant information on changes in credit objection complaints that can be collected on the Internet and has been refuted by the bank credit reporting center and is a rumor; derivative information generated after processing information from the above three sources, such as anti-fraud processing information in the form of text, image or audio and video, such as sound, voiceprint, image, etc.

[0126] Disposal decision module 43: used to make a processing decision for the credit objection processing request based on the processing type of the credit objection processing request and the information collected by the information collection module 42 (corresponding to the processing results in other embodiments).

[0127] Evidence storage module 44: used to store on the blockchain the credit investigation objection-related business information stored by this institution (corresponding to the first data source in other embodiments), including the loan business applied for by the applicant and the repayment record, and the objection handling decision information, including the decision conclusion, decision basis, the source of the decision basis, etc.; the evidence storage method can use the alliance chain joined by this institution or the external evidence storage service called. When it is identified that the source of the objection application is not administrative reconsideration and litigation, it means that the processing type is a data update type. At this time, only general blockchain evidence storage is performed for the original information and electronic evidence. When it is identified that the objection application request comes from the court, it means that the processing type is a data acquisition type. At this time, you can also apply for notarization from an institution with electronic evidence notarization qualifications to ensure the effectiveness of the stored electronic evidence.

[0128] Information feedback module 45: used to provide an interface for querying or pushing the objection application processing conclusion, and push the relevant processing conclusion to the applicant 451, the credit reporting agency 452 (credit reporting center, bank, etc.), the court 453 and other relevant institutions and departments.

[0129] like Figure 5 As shown, Figure 5 : This is a flow chart of the credit investigation objection handling process provided by the embodiment of the present application. The credit investigation objection handling process provided by the embodiment of the present application includes:

[0130] In step 501, a credit objection handling request is received, and a handling type of the credit objection handling request is determined.

[0131] Here, a credit objection handling request refers to a credit objection request forwarded by an objection applicant, a credit reporting center, or the People's Bank of China. Upon receiving a credit objection handling request, the handling type of the credit objection request is determined based on the source of the credit objection handling request. If the credit objection request is for complaint handling, the handling type is determined to be data update. If the credit objection request is for credit objection review or litigation, the handling type is determined to be data acquisition. For example, if the handling type of the credit objection handling request is data update, then steps 502 to 504 will continue.

[0132] In step 502, first data corresponding to the credit objection handling request is collected.

[0133] Here, relevant evidence information is collected for making credit objection decision-making, including: reading the business information related to the applicant stored by this organization (corresponding to the first information in other embodiments), including: basic information such as user identifier ID, telephone number, occupation, address, etc. actively provided by the user in the pre-loan application stage; user credit usage and overdue situation in the mid-loan stage; audio and video materials communicated by the user service department in the post-loan stage, and supporting materials submitted to prove that the overdue was not intentional but due to force majeure and should be exempted; voiceprints, audio and video, avatars and background images retained by the user, user location (such as Global Positioning System (GPS), Beidou positioning, mobile communication base station identity for cellular communication, etc.), access network method (wireless network (wifi) identity identifier (Service Set Identifier, SSID), etc.); personal credit report and other information. The Private Set Intersection (PSI) algorithm is used to obtain information shared by financial peers (corresponding to the second information in other embodiments), including: first, using the PSI algorithm, fuzzy collision is performed on the user ID, user mobile phone number, user location, or other fields that can identify the user's identity with financial peers; if a collision hits, it is determined that information can be obtained from the financial peers in a secure manner; if there is no hit, the financial peer information cannot be obtained. Among them, financial peers use blockchain infrastructure such as consortium chains or public chains to publicly disclose the information they collect on suspected illegal credit reporting services and configure access rights. When a PSI intersection hit is found, a query portal is provided to provide relevant information, including: information shared by peers regarding suspected illegal credit reporting objections by users, user voiceprint summary data, desensitized user communication addresses, desensitized user complaint mobile phone numbers, information related to credit reporting objections filed by users with other institutions, the content of user complaint materials and data similar to other user complaint materials, information about users using false materials, records of user complaint numbers being complained about by other users, information related to users' links to intermediaries, and other black and gray market behavior data. Among them, peer-shared information is obtained through intersection through a multi-party secure computing system, and the above information can be obtained using privacy computing or blockchain query methods.

[0134] In step 503 , a processing result for the credit objection processing request is determined based on the first data.

[0135] Here, anti-fraud identification is performed on the first data collected in step 502 through anti-fraud identification models, anti-financial black and gray industry identification models, illegal agent intermediary identification models, etc., to obtain at least one prediction result, and then the processing result of the credit objection processing request is determined based on the prediction result.

[0136] In some embodiments, see Figure 6, Figure 6 This is a flow chart of determining the processing results provided by an embodiment of the present application, including: inputting the first data 61 into the intelligent recognition model 621, the anti-fraud recognition model 622 and the intelligent question-answering model 623 respectively, and obtaining at least one prediction result, wherein the at least one prediction result is used to represent the probability that the user is suspected of illegality or fraud. Among them, the intelligent question-answering model 623 is a large language model of knowledge pre-trained based on relevant laws and regulations such as credit reporting business and credit reporting industry management methods, relevant laws and regulations on credit reporting objections, administrative reconsideration cases of credit reporting objections, litigation cases of credit reporting objections, typical cases of fraud involving credit reporting reconsideration, etc. It can conduct intelligent question-answering based on the application materials and supporting materials provided by the user who raised the credit reporting objection, determine whether the user is suspected of illegal credit reporting reconsideration, the probability of suspected illegal credit reporting reconsideration, and the process and basis of the analysis. Afterwards, a credit reporting objection handling decision is made based on the at least one prediction result, and the at least one prediction result is processed based on the intelligent judgment model 631 and the expert model 632 to obtain the first update strategy. If the automated decision fails, meaning the first update strategy is not successfully determined, the decision will be transferred to manual processing 641 for manual processing. At this point, the decision can be graded and classified based on the amount of information obtained, and handled by personnel with different levels of experience. Furthermore, if the first update strategy is to approve the update, a random selection is made to transfer to manual processing 641 for manual processing, and the result is compared with the automated decision. If the first update strategy is to reject the update, or if the first update strategy is to approve the update but is not randomly selected, the first update strategy is determined as the processing result through automated decision 642. Finally, the relevant evidence is stored through evidence retention 65.

[0137] It should be noted that the expert model includes a series of preset rules that help the system automatically determine whether a credit objection request is suspected of fraud, whether it is legal and compliant, or whether there is insufficient evidence and manual processing is required. The preset rules include a negation rule (corresponding to the first rule in other embodiments), which is used to determine that the credit objection request fails and the user is suspected of fraud. For example, negation rules may include: at least one prediction result from multiple models tends to identify the consumer as suspected of fraud; at least one prediction result from multiple models indicates that the probability of the consumer being suspected of fraud is higher than a threshold probability; first data indicates that the user has a suspected illegal credit investigation dispute with at least one peer institution; the address the user reserved or used in a complaint is a high-risk address; the mobile phone number the user reserved or used in a complaint matches a database of phone numbers associated with fraud or illegal activities in the same industry; the mobile phone number the user reserved or used in a complaint has been complained about by other consumers at the same institution or other institutions; the supporting documents submitted by the user are highly similar to supporting documents obtained from other consumers at the same institution; the supporting documents used by the user are identified as forged by an image recognition model (such as photocopied or tampered documents, altered hospital diagnosis certificates, or forged official seals); the user's voiceprint matches a voiceprint from illegal activities through privacy calculations; the user files complaints simultaneously through multiple channels or against multiple peer institutions on multiple platforms; the user is associated with other intermediary activities or illegal activities, etc. Negation rules can be determined manually or generated through analysis and screening using large prediction models, and can be adjusted based on actual operational conditions. In addition to the above-mentioned negative rules for automatically determining that an objection has failed, the preset rules also include positive rules for automatically determining that an objection has succeeded (corresponding to the second rule in other embodiments). For example: the user's objection content is that the overdue record is incorrect, and the user's overdue information and repayment information are conflicting after business determination; the user has settled the loan within the specified time limit but was mistakenly marked as overdue; the supporting documents provided by the user are identified as having a low probability of being forged, or are manually verified to be authentic; no automatic rules that can determine that an objection has failed are triggered; the prediction results given by multiple models all reflect that the probability of the user being a fraud or intermediary is extremely low; and other scenarios that the People's Bank of China or regulatory authorities determine should be supported. When some or all of the above positive rules are met, the objection application can be determined to be approved.

[0138] In step 504, the first evidence data of the credit objection processing request is determined and stored.

[0139] Here, the relevant evidence data for the credit objection handling request is secured. This includes summarizing and uploading to the blockchain the original information related to the objection's business information retained by the institution; summarizing and uploading to the blockchain the rules triggered during the decision-making process, along with the institution's associated evidence identifiers and the evidence identifiers provided by peer institutions. Furthermore, a request can be sent to the peer institutions involved in the triggered rules and received a response, requesting them to deposit the original information of the relevant evidence. Alternatively, a credit objection handling report can be generated and a query interface provided, containing the identifiers of the evidence stored by the institution and those of peer institutions for easy query. Access conditions for evidence storage must be configured, including: granting access to the stored information to the institution and the peer institutions that provided the evidence; and granting access to the stored information to the credit reporting center, banks, financial supervision and administration agencies, and other regulatory agencies. Furthermore, the credit objection handling report can be pushed to the credit reporting center, banks, or other complaint handling agencies, which automatically verify the report, execute the regulatory complaint handling logic, and cancel the relevant complaint.

[0140] In some embodiments, when the objection request originates from a bank or court, the purpose of the credit objection handling request is determined to be evidence collection, i.e., the processing type of the credit objection handling request is data acquisition. In this case, the institution needs to query whether a credit objection handling report (corresponding to the second stored evidence data in other embodiments) has been generated based on the objection applicant identification information provided in the credit objection handling request. If the institution has not generated a report, the processing process for the credit objection handling request of data update type is executed, incorporating the information provided by the bank or court into the information collection module, executing the information collection and disposal decision-making process, generating a report, and returning it to the requesting terminal of the credit objection handling request. If a report has been generated, a new update policy (corresponding to the fourth update policy in other embodiments) is determined based on the information provided by the bank or court, and a determination is made as to whether the new update policy is consistent with the update policy in the report (corresponding to the third update policy in other embodiments). If they are consistent, the report generated by the institution is returned; if not, the new update policy and the report generated by the institution are returned together. The stored evidence data is then updated, and an interface of a qualified electronic evidence notarization agency is invoked to notarize the stored electronic evidence and generate an electronic notarial certificate.

[0141] In the embodiment of the present application, internal information, industry information, and administrative agency information are used to simultaneously conduct anti-fraud processing on credit objections, identify fraudsters or applicants seeking support from illegal agents, identify illegal and non-compliant credit objectors, and make correct objection handling. In this way, industry information sharing is achieved and the risk of damage from illegal credit review is reduced. Moreover, through information sharing among different institutions, the pressure of complaint handling is reduced and processing efficiency is improved. In addition, the embodiment of the present application reduces the processing workload of the same case at different processing stages (objection, complaint, review, prosecution), and improves processing efficiency and data security.

[0142] The following continues to describe the exemplary structure of the data processing device 233 provided in the embodiment of the present application implemented as a software module. In some embodiments, such as Figure 2 As shown, the software modules stored in the data processing device 233 of the memory 230 may include:

[0143] a determination module 2331 configured to, in response to a credit objection handling request for a first object, determine a processing type corresponding to the credit objection handling request;

[0144] The determining module 2331 is further configured to determine first data of the first object based on the processing type corresponding to the credit objection processing request, where the first data includes object data of the first object and statistical data of credit investigation activities performed by the first object;

[0145] The determining module 2331 is further configured to determine a processing result for the credit objection processing request based on the first data;

[0146] The sending module 2332 is used to send the processing result to the request terminal corresponding to the credit objection processing request.

[0147] In some embodiments, the determination module 2331 is further used to determine, from a first data source, based on the object identification of the first object, the object data of the first object and the first behavior data of the first object implementing the credit investigation behavior, wherein the first data source belongs to a first entity providing services for the first object; based on the object identification, determine, from a second data source, the second behavior data of the first object implementing the credit investigation behavior, wherein the second data source belongs to a second entity different from the first entity; based on the first behavior data and the second behavior data, determine the statistical data of the first object implementing the credit investigation behavior; and combine the object data and the statistical data into the first data.

[0148] In some embodiments, the determination module 2331 is further used to perform credit prediction processing on the first data through at least one pre-trained prediction model to obtain at least one prediction result; match the at least one prediction result based on preset rules to obtain a first update strategy; and when the first update strategy meets the preset output conditions, determine the first update strategy as the processing result.

[0149] In some embodiments, the determination module 2331 is also used to determine that the first update strategy is to refuse update when at least one of the prediction results matches any first rule in the preset data processing rules, and the first rule represents the rule that is satisfied when refusing to update data for the first object; and to determine that the first update strategy is to agree to update when each of the prediction results matches N second rules in the preset rules, where N is an integer greater than 1, and the second rule represents the rule that is satisfied when agreeing to update data for the first object.

[0150] In some embodiments, the determination module 2331 is also used to determine the first data, the at least one prediction result and the first update strategy as data to be processed when the first update strategy does not meet the preset output condition; determine the processing level corresponding to the data to be processed, and send the data to be processed to a processing terminal pre-associated with the processing level, and the processing level is used to characterize the processing difficulty of the data to be processed; receive a second update strategy sent by the processing terminal based on the data to be processed, and determine the second update strategy as the processing result.

[0151] In some embodiments, the determination module 2331 is further used to generate a first decision record, which includes the processing result and the first decision basis corresponding to the processing result; and combine the first data and the first decision record into first evidence data.

[0152] In some embodiments, the determination module 2331 is further used to determine the object identifier of the first object based on the credit objection processing request; when the first data source includes second evidence data corresponding to the object identifier, the second evidence data is determined as the first data of the first object.

[0153] In some embodiments, the determination module 2331 is further used to determine the third update strategy of the first object from the second evidence data; determine the fourth update strategy of the first object based on the fourth data carried in the credit objection processing request; and when the third update strategy and the fourth update strategy are the same, determine the second evidence data as the processing result.

[0154] In some embodiments, the determination module 2331 is also used to generate a second decision record when the third update strategy and the fourth update strategy are different, and the second decision record includes the fourth update strategy and the second decision basis corresponding to the fourth update strategy; and the second decision record and the second evidence data are determined as the processing result.

[0155] In some embodiments, the determination module 2331 is further used to update the second evidence data based on the second decision record to obtain updated second evidence data; or, to add the second decision record to the second evidence data to obtain updated second evidence data.

[0156] In some embodiments, the determination module 2331 is further used to determine the third evidence data for the credit objection handling request; send an information synchronization request to a second data source, wherein the information synchronization request carries the credit objection handling request and the third evidence data; or, in response to a data query request sent by the second data source, send the credit objection handling request and the third evidence data to the second data source.

[0157] An embodiment of the present application provides a computer program product, which includes a computer program or computer-executable instructions stored in a computer-readable storage medium. A processor of an electronic device reads the computer-executable instructions from the computer-readable storage medium and executes the computer-executable instructions, causing the electronic device to perform the data processing method described in the embodiment of the present application.

[0158] The embodiment of the present application provides a computer-readable storage medium in which computer-executable instructions or computer programs are stored. When the computer-executable instructions or computer programs are executed by a processor, the processor will execute the data processing method provided in the embodiment of the present application, for example, Figure 3A The data processing method is shown.

[0159] In some embodiments, the computer-readable storage medium may be a memory such as RAM, ROM, flash memory, magnetic surface memory, optical disk, or CD-ROM; or may be various devices including one or any combination of the above memories.

[0160] In some embodiments, computer-executable instructions may be in the form of a program, software, software module, script, or code, written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and may be deployed in any form, including as a stand-alone program or as a module, component, subroutine, or other unit suitable for use in a computing environment.

[0161] As an example, computer-executable instructions may, but need not, correspond to a file in a file system, may be stored in part of a file that stores other programs or data, e.g., in one or more scripts in a HyperText Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple coordinating files (e.g., files storing one or more modules, subroutines, or code portions).

[0162] By way of example, computer-executable instructions may be deployed to be executed on one electronic device, or on multiple electronic devices located at one site, or on multiple electronic devices distributed across multiple sites and interconnected by a communication network.

[0163] In summary, in an embodiment of the present application, in response to a credit objection handling request for a first object, the processing type corresponding to the credit objection handling request is determined, and then, based on the processing type corresponding to the credit objection handling request, first data of the first object is determined. In this way, the method for determining the first data can be flexibly selected based on the processing type corresponding to the credit objection handling request, thereby improving the efficiency and accuracy of determining the first data. The first data includes the object data of the first object and statistical data on the credit investigation behavior performed by the first object. Therefore, the first data can comprehensively and accurately reflect the object characteristics and behavioral characteristics related to credit investigation of the first object, thereby improving the accuracy of determining the processing result for the credit objection handling request based on the first data. By sending the processing result to the requesting terminal corresponding to the credit objection handling request, the processing terminal can perform targeted processing on the first object based on the processing result, thereby ensuring the rationality and data security of the processing of the first object. Therefore, through this embodiment of the present application, the credit objection handling request can be processed in a targeted manner based on the processing type of the credit objection handling request, improving the efficiency, accuracy, and data security of data processing.

[0164] The above description is merely an embodiment of the present application and is not intended to limit the scope of protection of the present application. Any modifications, equivalent replacements, and improvements made within the spirit and scope of the present application are included in the scope of protection of the present application.

Claims

1. A data processing method, characterized in that: The method comprises: In response to a credit objection handling request for a first object, determining a processing type corresponding to the credit objection handling request; determining, based on the processing type corresponding to the credit objection processing request, first data of the first object, the first data including object data of the first object and statistical data of credit investigation actions performed by the first object; Determining a processing result for the credit objection processing request based on the first data; The processing result is sent to the request terminal corresponding to the credit objection processing request.

2. The method according to claim 1, characterized in that In a case where the processing type is a data update type, determining the first data of the first object based on the processing type corresponding to the credit objection processing request includes: Based on the object identifier of the first object, determining object data of the first object and first behavior data of the first object performing the credit investigation behavior from a first data source, where the first data source belongs to a first entity providing services for the first object; Based on the object identifier, determining second behavior data of the first object performing the credit investigation behavior from a second data source, where the second data source belongs to a second entity different from the first entity; Determining statistical data of the credit investigation behavior performed by the first subject based on the first behavior data and the second behavior data; The object data and the statistical data are combined into the first data.

3. The method according to claim 2, characterized in that The determining, based on the first data, a processing result for the credit objection processing request includes: Performing credit prediction processing on the first data using at least one pre-trained prediction model to obtain at least one prediction result; Performing matching processing on the at least one prediction result based on a preset rule to obtain a first update strategy; In a case where the first update strategy meets a preset output condition, the first update strategy is determined as the processing result.

4. The method according to claim 3, characterized in that The performing matching processing on the at least one prediction result based on the preset rule to obtain a first update strategy includes: In a case where at least one of the prediction results matches any one of the preset first rules, determining that the first update strategy is to reject the update, where the first rule represents a rule that is satisfied when rejecting data update of the first object; When each of the prediction results matches the preset N second rules, the first update strategy is determined to be agreeing to update, N is an integer greater than 1, and the second rules represent the rules that are satisfied when agreeing to update the data of the first object.

5. The method according to claim 3, characterized in that The method further comprises: If the first update strategy does not meet the preset output condition, determining the first data, the at least one prediction result, and the first update strategy as data to be processed; Determining a processing level corresponding to the data to be processed, and sending the data to be processed to a processing terminal pre-associated with the processing level, wherein the processing level is used to represent the processing difficulty of the data to be processed; A second update strategy is received from the processing terminal based on the data to be processed, and the second update strategy is determined as the processing result.

6. The method according to claim 1, characterized in that In a case where the processing type is a data acquisition type, determining the first data of the first object based on the processing type corresponding to the credit objection processing request includes: determining an object identifier of the first object based on the credit objection handling request; In a case where the first data source includes second stored evidence data corresponding to the object identifier, the second stored evidence data is determined as the first data of the first object.

7. The method according to claim 6, characterized in that The determining, based on the first data, a processing result for the credit objection processing request includes: Determining a third update strategy for the first object from the second stored evidence data; determining a fourth update strategy for the first object based on fourth data carried in the credit objection handling request; In a case where the third update strategy and the fourth update strategy are the same, determining the second stored evidence data as the processing result; In a case where the third update strategy and the fourth update strategy are different, generating a second decision record, the second decision record including the fourth update strategy and a second decision basis corresponding to the fourth update strategy; The second decision record and the second evidence data are determined as the processing result.

8. The method according to claim 7, characterized in that After generating the second decision record, the method further includes: updating the second stored evidence data based on the second decision record to obtain updated second stored evidence data; or The second decision record is added to the second stored evidence data to obtain updated second stored evidence data.

9. An electronic device, characterized in that: The electronic device comprises: a memory for storing computer-executable instructions or computer programs; A processor, configured to implement the method according to any one of claims 1 to 8 when executing computer-executable instructions or computer programs stored in the memory.

10. A computer program product comprising computer executable instructions or a computer program, characterized in that When the computer executable instructions or computer program are executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images