Bank card self-service unfreezing method and device, electronic equipment and storage medium

Abstract

The invention discloses a bank card self-service unfreezing method and device, electronic equipment and a storage medium, and relates to the field of financial science and technology. The method comprises the following steps: receiving an unfreezing request sent by a user through terminal equipment; generating an unfreezing suggestion text according to the freezing reason of the target function module and appeal information submitted by the user in the unfreezing request; determining a remote authorization end corresponding to the unfreezing request and a processing sequence of the unfreezing request according to the data source of the unfreezing request, the service type of the target function module and the processing waiting duration of the unfreezing request; and according to the processing sequence of the unfreezing request, sending the unfreezing request to a corresponding remote authorization terminal, and according to reply information of the remote authorization terminal for the unfreezing suggestion text, determining a processing operation for the unfreezing request. The technical problem that in the prior art, the handling process of the bank card unfreezing service is tedious and low in efficiency due to the fact that the handling of the bank card unfreezing service mainly depends on a traditional counter manual auditing mode is solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of financial technology, in particular to a bank card self-unfreezing method and device, an electronic device and a storage medium. BACKGROUND

[0002] In the current financial industry, bank card unblocking business, as an important service, aims to lift the restrictions on bank card functions caused by various reasons (such as transaction abnormalities, account freezing, etc.), and to restore the normal use of bank cards by users. However, this process has long relied on the traditional manual audit mode at the counter, specifically, users need to go to the bank outlets to complete a series of operations such as identity verification and data submission through window services, and the bank staff manually audits and makes unblocking decisions.

[0003] This traditional mode faces significant technical problems, the core of which is the complexity of the process and the low efficiency. On the one hand, the process of manual audit is time-consuming, and users need to wait on site, which greatly affects the customer experience, especially during peak hours, long queues have almost become the norm, reducing service satisfaction. On the other hand, this mode relying on manpower is unreasonable in resource allocation, and banks need to allocate enough staff at each outlet to handle unblocking requests, which not only increases operating costs, but also limits processing capacity and scalability, making it difficult to meet the growing business needs.

[0004] In view of the above problems, no effective solutions have been proposed so far. SUMMARY

[0005] The embodiments of the present application provide a bank card self-unfreezing method, device, electronic device and storage medium to at least solve the technical problem that the bank card unblocking business is mainly dependent on the traditional manual audit mode at the counter, resulting in a complex and inefficient bank card unblocking business process.

[0006] According to an aspect of an embodiment of the present application, a bank card self-unfreezing method is provided, comprising: receiving an unfreezing request sent by a user through a terminal device, wherein the unfreezing request is used to request to unfreeze a target function module in a frozen state of a target bank card; in the case that the user identity verification is successful, generating an unfreezing suggestion text according to the frozen reason of the target function module and the appeal information submitted by the user in the unfreezing request; determining the remote authorization end corresponding to the unfreezing request and the processing order of the unfreezing request according to the data source of the unfreezing request, the business type of the target function module, and the processing waiting time of the unfreezing request; according to the processing order of the unfreezing request, sending the unfreezing request to the corresponding remote authorization end, and determining the processing operation for the unfreezing request according to the reply information of the remote authorization end to the unfreezing suggestion text.

[0007] Optionally, after receiving the unfreezing request sent by the user through the terminal device, the N kinds of identification information of the user are collected under the authorization of the user, wherein the N kinds of identification information include at least one of sound identification information, face identification information, iris identification information, fingerprint identification information, and certificate identification information; and the identity of the user is verified according to the N kinds of identification information of the user and the reserved user identification information corresponding to the target bank card.

[0008] Optionally, the unfreezing suggestion text is generated according to the freezing reason and the appeal information submitted by the user in the unfreezing request, including: determining the verification data source of the appeal information according to the freezing reason, wherein the verification data source is used to verify the authenticity of the appeal information; sending the appeal information to the verification data source for verification; and generating the unfreezing suggestion text according to the verification result returned by the verification data source for the appeal information, the freezing reason of the target function module, and the appeal information.

[0009] Optionally, the unfreezing suggestion text is generated according to the freezing reason and the appeal information submitted by the user in the unfreezing request, including: using the same semantic analysis strategy to respectively perform semantic analysis on the freezing reason and the appeal information; taking the semantic analysis result corresponding to the freezing reason as first semantic information; taking the semantic analysis result corresponding to the appeal information as second semantic information; detecting the semantic correlation degree of the first semantic information and the second semantic information, wherein the semantic correlation degree is used to represent the explanation accuracy of the second semantic information for the first semantic information; and generating the unfreezing suggestion text according to the semantic correlation degree of the first semantic information and the second semantic information, the freezing reason of the target function module, and the appeal information.

[0010] Optionally, the semantic correlation degree of the first semantic information and the second semantic information is detected, including: obtaining a knowledge graph, wherein the knowledge graph includes a plurality of first nodes and a plurality of second nodes, wherein each first node is used to describe a freezing reason of the bank card function module, and each second node is used to describe an unfreezing reason of the bank card function module; taking the first node with the highest semantic similarity to the first semantic information in the knowledge graph as a first target node, which describes the freezing reason; taking the second node with the highest semantic similarity to the second semantic information in the knowledge graph as a second target node, which describes the unfreezing reason; determining the shortest path from the first target node to the second target node in the knowledge graph; and determining the semantic correlation degree of the first semantic information and the second semantic information according to the length of the shortest path.

[0011] Optionally, the semantic correlation degree of the first semantic information and the second semantic information is determined according to the length of the shortest path, including: converting the first semantic information into a first vector and converting the second semantic information into a second vector; detecting the vector similarity of the first vector and the second vector; and determining the semantic correlation degree of the first semantic information and the second semantic information according to the vector similarity and the length of the shortest path.

[0012] Optionally, the shortest path length and the semantic relevance are negatively correlated, and the vector similarity and the semantic relevance are positively correlated.

[0013] According to another aspect of the present application, a bank card self-unfreezing device is also provided, wherein the device comprises: a receiving unit configured to receive an unfreezing request sent by a user through a terminal device, wherein the unfreezing request is used to request to unfreeze a target function module of a target bank card in a frozen state; a text generation unit configured to generate an unfreezing suggestion text according to a freezing reason of the target function module and appeal information submitted by the user in the unfreezing request in a case where user identity verification is successful; a first determination unit configured to determine a remote authorization end corresponding to the unfreezing request and a processing order of the unfreezing request according to a data source of the unfreezing request, a business type of the target function module, and a processing waiting time length of the unfreezing request; and a second determination unit configured to send the unfreezing request to the corresponding remote authorization end according to the processing order of the unfreezing request, and determine a processing operation for the unfreezing request according to reply information of the remote authorization end to the unfreezing suggestion text.

[0014] According to another aspect of the present application, a computer readable storage medium is also provided, wherein the computer readable storage medium stores a computer program, wherein when the computer program is running, the computer readable storage medium makes a device where the computer readable storage medium is located execute the bank card self-unfreezing method.

[0015] According to another aspect of the present application, an electronic device is also provided, wherein the electronic device comprises one or more processors and a memory, and the memory is configured 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 execute the bank card self-unfreezing method.

[0016] According to another aspect of the present application, a computer program product is also provided, wherein the computer program product comprises a computer program or instructions, and the computer program or instructions realize the bank card self-unfreezing method when executed by a processor.

[0017] In the present application, first, a user sends a defrosting request through a terminal device, wherein the defrosting request is used to request to defrost a target function module of a target bank card in a frozen state. Then, in the case that the user identity verification is successful, a defrosting suggestion text is generated according to the frozen reason of the target function module and the appeal information submitted by the user in the defrosting request. Subsequently, according to the data source of the defrosting request, the business type of the target function module, the processing waiting time of the defrosting request, a remote authorization end corresponding to the defrosting request and the processing order of the defrosting request are determined. Finally, according to the processing order of the defrosting request, the defrosting request is sent to the corresponding remote authorization end, and the processing operation for the defrosting request is determined according to the reply information of the remote authorization end to the defrosting suggestion text.

[0018] From the above, according to the technical solution of the present application, through seamless docking of the integrated terminal device and the background system, the user can complete online identity verification and defrosting request submission without queuing at the counter, which greatly simplifies the business process, shortens the user waiting time, and effectively avoids the long waiting caused by manual review. Secondly, the present application can automatically generate a defrosting suggestion text in combination with the frozen reason of the target function module and the user's appeal information, which eliminates the subjectivity and inconsistency of manual analysis, ensures the objectivity and accuracy of the defrosting decision, and greatly improves the processing speed and reduces the error rate caused by human error. Moreover, according to the data source of the defrosting request, the business type and the waiting time, etc. Parameters, the system can intelligently determine the remote authorization end and the processing order of the defrosting request, realize the reasonable allocation and optimization of resources, effectively avoid the processing bottleneck in peak period, and improve the flexibility and efficiency of business processing.

[0019] By sending the defrosting request to the corresponding remote authorization end according to the priority, the decision cycle is greatly reduced, the authorized personnel can quickly review the defrosting suggestion text without geographical restrictions, and the decision information is replied through the system, the whole process is automated and standardized, which significantly improves the decision speed and operation standardization.

[0020] In summary, the present technical solution solves the problem of complicated process and low efficiency caused by the dependence of bank card defrosting business on traditional manual review in the prior art, and achieves the technical effect of improving the defrosting business processing efficiency. BRIEF DESCRIPTION OF DRAWINGS

[0021] The drawings described herein are used to provide further understanding of the present application, and form a part of the present application. The schematic embodiments of the present application and their descriptions are used to explain the present application, and do not constitute an improper limitation on the present application. In the drawings:

[0022] Figure 1is a flowchart of an optional bank card self-unfreezing method according to an embodiment of the present application;

[0023] Figure 2 is a flowchart of an optional generation of unfreezing suggestion text according to an embodiment of the present application;

[0024] Figure 3 is a schematic diagram of an optional bank card self-unfreezing device according to an embodiment of the present application. DETAILED DESCRIPTION

[0025] In order to enable persons skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by persons skilled in the art without creative labor should fall within the scope of protection of the present application.

[0026] It should be noted that the terms "first", "second", and the like in the specification and claims of the present application and the above-described drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or a chronological sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product, or device that includes a series of steps or units does not necessarily have to be limited to only those steps or units clearly listed, but can include other steps or units that are not clearly listed or inherent to the process, method, product, or device.

[0027] It should also be noted that the information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) collected by the present application are information and data authorized by the user or authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure, and application of related data comply with relevant laws, regulations, and standards in relevant regions, necessary security measures are taken, do not violate public order and good customs, and provide corresponding operation portals for users to choose authorization or refusal. For example, interfaces are provided between the system and related users or agencies, and before obtaining relevant information, the interface needs to send an acquisition request to the aforementioned user or agency, and after receiving the consent information fed back by the aforementioned user or agency, the relevant information is acquired.

[0028] According to the embodiment of the present application, an embodiment of a bank card self-unfreezing method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that here.

[0029] According to the embodiment of the present application, a self-unfreezing system can be used as the execution subject of the bank card self-unfreezing method of the embodiment of the present application, wherein the system can be a software system or a combination of software and hardware embedded system. Of course, the method execution subject in the embodiment of the present application can also be other forms of execution subject, such as device, equipment, etc. Those skilled in the art should know that the specific form of the present application is not particularly limited.

[0030] Figure 1 is a flowchart of an optional bank card self-unfreezing method according to the embodiment of the present application, as shown in Figure 1 , the method comprises the following steps:

[0031] Step S101, receiving an unfreezing request sent by a user through a terminal device, wherein the unfreezing request is used to request to unfreeze a target function module of a target bank card in a frozen state.

[0032] Optionally, in the modern financial service system, the bank card can be frozen due to various reasons, such as abnormal transaction activity, reaching a preset security threshold, or bank internal risk control measures. When the bank card of the cardholder is in a frozen state and wants to restore the normal use of one or more function modules (such as transfer, payment, cash withdrawal, etc.), the present application provides a mechanism for sending an unfreezing request through a terminal device, aiming to simplify the unfreezing process and improve user experience and business processing efficiency.

[0033] Optionally, the user can access the application program or website of the bank through a smart phone, a computer or other networked devices, find and activate the unfreezing request function. This process does not require the user to go to the bank, greatly improving the accessibility and convenience of the service. After activating the unfreezing request function, the user needs to fill in the necessary information according to the instructions on the interface, including but not limited to bank card number, cardholder identification information, unfreezing reason, and any related complaint materials or proof documents. The user can also choose to request to unfreeze specific function modules, such as unfreezing the payment function without involving the cash withdrawal permission.

[0034] Optionally, the transmission of the unfreezing request should be through a secure communication method, such as HTTPS protocol, to ensure that the data is not intercepted or tampered with by third parties during transmission. The system also needs to encrypt sensitive information to protect user privacy. In order to ensure the effective processing of the unfreezing request, the system can limit the information submitted by the user to follow certain formats and standards. For example, the bank card number should use the internationally recognized format, the unfreezing reason needs to be clear and explicit, and the complaint materials should include all necessary evidence and attachments.

[0035] Step S102, in the case of successful user identity verification, generate an unfreezing suggestion text according to the freezing reason of the target function module and the complaint information submitted by the user in the unfreezing request.

[0036] Optionally, when receiving the unfreezing request from the user and after successful strict user identity verification, the self-service unfreezing system can evaluate the rationality of the unfreezing request and generate an unfreezing suggestion text. For example, when the user submits an unfreezing request through a terminal device, the self-service unfreezing system can require the user to provide proof information, including but not limited to bank card information, facial recognition, mobile phone verification code, etc., to ensure that the request initiator is indeed the legal holder of the bank card. This verification process is carried out before or at the same time as the user submits the unfreezing request, and once the verification is successful, the system continues to process the unfreezing request, avoiding the risk of illegal operation and identity fraud.

[0037] Optionally, the self-service unfreezing system can automatically query the status of all function modules of the target bank card, especially the target function module in the frozen state. The freezing reason may be contained in the bank's system records, such as freezing triggered by suspected abnormal transactions, reaching the preset security threshold, or bank internal risk control measures.

[0038] Optionally, using AI algorithms, the self-service unfreezing system can analyze the freezing reason, identify the specific rules and background that triggered the freezing. For example, if the freezing is due to abnormal transactions, the algorithm will further judge the nature of the abnormal transactions, whether it is frequent small amount transactions, large amount transactions, or transactions at irregular times or places. The complaint information submitted by the user in the unfreezing request is an important basis for request processing. The self-service unfreezing system can use natural language processing technology to understand the semantics and extract key information from the complaint information, including the reason for the complaint, the evidence provided, and the urgency of the request for unfreezing.

[0039] According to the freezing reason and the user's complaint content, the self-service unfreezing system can evaluate the rationality of the unfreezing request. This process may involve comparing the user's historical transaction records, credit scores, and bank regulations information to comprehensively judge whether the unfreezing is safe and feasible.

[0040] Step S103 , determining the remote authorization terminal corresponding to the thawing request and the processing order of the thawing request according to the data source of the thawing request, the business type of the target functional module, and the processing waiting time of the thawing request.

[0041] Alternatively, the unfreeze request may originate online (e.g., from the bank's mobile app or official website) or offline (e.g., from a self-service terminal at a bank branch). The system must identify and record the source of the request to determine whether it requires additional on-site identity verification or follows a specific offline processing procedure. Different data source channels may carry different amounts of information. For example, online channels often include user behavior data and transaction history, while offline channels may focus on face-to-face communication and direct document review. Identifying these characteristics helps to more accurately assess risks and priorities.

[0042] Optionally, the reasons why the functional modules of a bank card are frozen vary, and the types of business involved are also different, which may include payment, transfer, cash withdrawal, credit limit, etc. The different business types will directly affect the urgency of unfreezing and the complexity of the operation. Based on the business type, the self-service unfreezing system can evaluate the risk level of the unfreezing request. For example, an unfreezing request involving a large-value transfer function may require higher security verification, while the unfreezing of the payment function may be lower risk. Based on the risk level and business type, the self-service unfreezing system can intelligently match the remote authorization terminal that is most suitable for handling the unfreezing request, including determining different levels of risk control personnel, experts in specific business fields, or automated review systems.

[0043] Optionally, the automatic thawing system can also monitor the progress of thawing requests in real time, recording the waiting time from request submission to completion. This is crucial for evaluating system efficiency and user satisfaction. The longer the waiting time for thawing requests, the greater the user's anxiety. Therefore, the system should dynamically adjust the processing order based on waiting time, prioritizing those requests with longer wait times to reduce user dissatisfaction.

[0044] Taking the above factors into consideration, the system uses intelligent algorithms (such as machine learning models) to automatically dispatch unfreeze requests to the appropriate remote authorization end and determine the optimal processing order to ensure efficient resource utilization and fair processing.

[0045] Step S104: sending the unfreeze request to the corresponding remote authorization end according to the processing order of the unfreeze request, and determining the processing operation for the unfreeze request according to the reply information of the remote authorization end to the unfreeze suggestion text.

[0046] Optionally, in the unfreeze request processing flow, once the processing order of unfreeze requests is determined, the self-service unfreeze system can efficiently route these requests to the correct remote authorization end and perform corresponding unfreeze operations based on the response of the authorization end.

[0047] Optionally, based on the previously analyzed sources of unfreezing requests, the type of business of the target function module, and the processing waiting time of the unfreezing request, the self-unfreezing system can use intelligent algorithms to determine the processing order of the request and the selection of the authorized end. This means that each unfreezing request will be automatically assigned to the most suitable remote authorized end, whether it is a branch office in a specific region, a team of experts in a specific business field, or an automated processing system with the corresponding authority. The intelligent routing algorithm can also consider the processing capacity and current workload of the remote authorized end to ensure that the request can be processed in a timely manner without affecting the overall system performance. For high-load authorized ends, the system may temporarily delay the distribution of certain non-urgent requests or reassign them to other low-load authorized ends.

[0048] Optionally, the remote authorized end is responsible for reviewing the unfreezing proposal text, evaluating the risk and legality of the unfreezing request, including re-verification of user identity, in-depth analysis of the appeal information, and prediction and consideration of the consequences of the unfreezing operation. When reviewing the unfreezing proposal text, the authorized end will refer to the bank's risk control policies and internal guidelines to ensure that each unfreezing operation is carried out within the framework of safety and compliance. Whether to agree to unfreeze or maintain the frozen state, the remote authorized end will generate detailed reply information, including the unfreezing decision, the reason for the decision, and any additional operation guidance or restriction conditions. These information is crucial for subsequent operation execution.

[0049] Optionally, according to the reply information of the remote authorized end, the self-unfreezing system will automatically or semi-automatically execute the unfreezing operation to restore the normal operation of the target function module. For unfreezing requests that require manual operation, the system will generate operation guidelines to guide on-site or remote operators to process.

[0050] In an optional embodiment, with the authorization of the user, the self-unfreezing system can collect N kinds of identification information of the user, wherein the N kinds of identification information include at least one of voice identification information, face identification information, iris identification information, fingerprint identification information, and certificate identification information. Then, the self-unfreezing system can perform identity verification on the user according to the N kinds of identification information of the user and the pre-reserved user identification information corresponding to the target bank card.

[0051] Optionally, the self-unfreezing system takes into account the balance between user privacy and security when designing, requiring explicit authorization from the user before starting the identity verification process. This step ensures that only the legitimate cardholder can perform the unfreezing operation, while avoiding unnecessary invasion of the user's privacy.

[0052] The self-unfreezing system can collect the user's biometric information through terminal devices such as mobile phone cameras, fingerprint scanners, and voiceprint recognizers, including but not limited to the following biometric information:

[0053] Voice identification information: By recording a user's voice sample, such as speaking or a specific voice command, the system can match the voice characteristics associated with the user's account.

[0054] Face identification information: Using a camera to capture the user's face image, the system uses face recognition technology to compare with the pre-registered face database.

[0055] Iris identification information: Through iris scanning technology, the system can accurately identify the user's eye iris characteristics.

[0056] Fingerprint identification information: Using a fingerprint recognition module, the system can read the user's fingerprint and match it with the fingerprint data bound to the account.

[0057] Certificate identification information: The user uploads images of identity cards, passports, and other certificate images, and the system uses OCR (Optical Character Recognition) technology to extract key information for verification.

[0058] The user provides at least one of the above N kinds of identification information on the terminal device. For example, the user may need to submit face identification information through the phone camera, or provide fingerprint identification information through the device's fingerprint recognition module. The self-unfreezing system compares the user identification information collected with the user identification information pre-registered in the target bank card account. These pre-registered information is updated at the time of user account opening or through formal procedures to ensure its accuracy and security. The system can determine whether the user's identity matches according to the comparison result. In order to improve security, the system may require at least two different identification information to match successfully before considering the identity verification successful. For example, in addition to fingerprint matching, the system may also require face or voice recognition verification.

[0059] In addition, considering the reliability differences of different biometric characteristics, the self-unfreezing system can dynamically adjust the verification standard according to the actual situation. For example, in a high-risk environment, the system may require more identification information matching to increase the difficulty and security of verification.

[0060] From the above, multi-factor identity verification combines multiple biometric characteristics that are difficult to forge, significantly enhancing the security of identity verification and reducing the risk of identity fraud and fraud.

[0061] In an optional embodiment, a thawing suggestion text is generated based on the freezing reason and the complaint information submitted by the user in the thawing request. This includes: the self-service thawing system may determine a verification data source for the complaint information based on the freezing reason, where the verification data source is used to verify the authenticity of the complaint information. The self-service thawing system may also send the complaint information to the verification data source for verification. Finally, the self-service thawing system may also generate a thawing suggestion text based on the verification result returned by the verification data source regarding the complaint information, the freezing reason of the target functional module, and the complaint information.

[0062] Optionally, the self-service thawing system determines the verification data source based on the reason for the freeze. For example, if the freeze is due to an unusual transaction, the system can access data sources such as transaction records, user spending habits, and geographic location information to verify the transaction details provided in the user's complaint. If the freeze is due to legal proceedings, the self-service thawing system can connect to relevant databases to query relevant records and verify the case status or judgment results mentioned in the complaint. If the freeze is due to an outstanding debt, financial records, repayment plans, or credit reports will become key data sources to verify the authenticity of the complaint information.

[0063] Optionally, the self-service unfreeze system can send the complaint information submitted by the user in the unfreeze request to the corresponding verification data source for real-time or near-real-time data comparison and query to verify the accuracy of the complaint content. This step involves cross-system data calls, API interface calls, or in-depth searches of internal databases.

[0064] After receiving a response from the verification data source, the self-service unfreezing system will evaluate the authenticity of the complaint information based on the response. For example, if the complaint information matches the data source records, the complaint is considered to be highly credible. Conversely, if the information is significantly different, further investigation or manual intervention may be required.

[0065] Finally, the self-service unfreeze system combines the verification results, the reason for the freeze, and the user's appeal information to produce a detailed unfreeze recommendation. This recommendation not only includes an overview of the user's request, but also details how the system verified the appeal information, the data sources used, and detailed reasons for recommending unfreezing or maintaining the freeze.

[0066] From the above content, we can see that the self-service unfreezing system intelligently analyzes the reasons for freezing, effectively verifies the authenticity and completeness of the complaint information, and finally generates a detailed unfreezing suggestion text, providing users with an efficient, safe and transparent unfreezing request processing experience.

[0067] In an optional embodiment, Figure 2 This is a flow chart of generating an optional unfreeze suggestion text according to an embodiment of the present application, such as Figure 2 As shown, the following steps are included:

[0068] Step S201, using the same semantic analysis strategy, the freezing reason and the complaint information are respectively subjected to semantic analysis;

[0069] Step S202, the semantic analysis result corresponding to the freezing reason is taken as the first semantic information;

[0070] Step S203, the semantic analysis result corresponding to the complaint information is taken as the second semantic information;

[0071] Step S204, the semantic correlation degree of the first semantic information and the second semantic information is detected, wherein the semantic correlation degree is used to represent the explanation accuracy of the second semantic information to the first semantic information;

[0072] Step S205, according to the semantic correlation degree of the first semantic information and the second semantic information, the freezing reason of the target function module and the complaint information, a thawing suggestion text is generated.

[0073] Optionally, according to the technical solution of the present application, the self-help thawing system can create a knowledge graph, wherein the knowledge graph contains two main types of nodes: first nodes and second nodes. The first nodes are used to represent various possible bank card function module freezing reasons, such as “abnormal transaction”, “overdue payment” or “judicial requirement” and the like; the second nodes correspond to possible thawing reasons, such as “transaction has been verified”, “payment has been completed” or “judicial thawing” and the like.

[0074] Optionally, in the knowledge graph, the first nodes of the freezing reasons and the second nodes of the corresponding thawing reasons are connected by edges (connecting lines) to form a network structure. These edges represent the potential association between the freezing reasons and the thawing reasons, for example, “abnormal transaction” can be connected to multiple thawing reason nodes such as “transaction has been verified”, “transaction confirmation is correct” and the like.

[0075] Optionally, when the self-help thawing system receives a thawing request, the self-help thawing system can convert the freezing reason described in the thawing request into the first semantic information. Then, the self-help thawing system finds the first node with the most similar semantics to the first semantic information in the knowledge graph, which is the first target node. The similarity can be realized by semantic analysis techniques such as natural language processing, word embedding and semantic vector comparison.

[0076] Similarly, the self-help thawing system can convert the thawing reason mentioned in the thawing request into the second semantic information, and find the second node with the most similar semantics to it in the knowledge graph as the second target node.

[0077] In the knowledge graph, the self-unfreezing system can calculate the shortest path from the first target node to the second target node. For example, the self-unfreezing system can use a graph algorithm to find the most direct route connecting the two target nodes. The length of the shortest path reflects the degree of direct association between the freezing reason and the unfreezing reason. The length of the shortest path is used as an indicator to measure the semantic relevance between the first semantic information (freezing reason) and the second semantic information (unfreezing reason). Generally speaking, the shorter the path, the higher the direct association between the two concepts, and the greater the rationality of the unfreezing request; on the contrary, the longer the path, the more indirect association between the concepts, and the higher the possibility of requiring additional evidence or prudent evaluation.

[0078] Optionally, in practical applications, the construction of the knowledge graph is often based on a large amount of historical data and expert knowledge. The definition of nodes and edges, the calculation of semantic similarity, and other processes may require the use of machine learning models and rule engines to achieve automation and intelligence. By quantifying semantic relevance, the self-unfreezing system can more objectively assess the rationality and risk level of the unfreezing request, assisting the system or remote authorization end in making more accurate unfreezing decisions.

[0079] The above technical means help the self-unfreezing system to deeply understand the user's complaint content, even if the expression method is different, the essential association between the freezing reason and the unfreezing reason can be captured, thereby providing personalized and more targeted services. The application of the knowledge graph helps to identify high-risk unfreezing requests, for example, if the freezing reason is "judicial requirements", but only a slight "password reset" is provided in the unfreezing reason, then the longer length of the shortest path will prompt the system to conduct more stringent review or reject the unfreezing request to comply with regulations and banking policies.

[0080] It should be noted that using the knowledge graph to evaluate the semantic relevance between the freezing reason and the unfreezing reason in the unfreezing request not only improves the understanding and decision-making ability of the self-unfreezing system, but also provides users with a more accurate and transparent service experience. By quantifying semantic distance, the self-unfreezing system can better assess risks and build an efficient and secure unfreezing mechanism.

[0081] In an optional embodiment, determining the semantic relevance of the first semantic information and the second semantic information according to the length of the shortest path includes: the self-unfreezing system can convert the first semantic information into a first vector and the second semantic information into a second vector, and then the self-unfreezing system detects the vector similarity of the first vector and the second vector. Finally, the self-unfreezing system determines the semantic relevance of the first semantic information and the second semantic information according to the vector similarity and the length of the shortest path.

[0082] Optionally, the self-unfreeze system first converts the first semantic information (frozen reason) and the second semantic information (unfreeze reason) into vector representations. These vectors are usually in a high-dimensional semantic space, capable of capturing the intrinsic meaning and contextual information of the text. The construction of vectors can rely on pre-trained language models, which can convert text into vectors that reflect its semantic features through deep learning techniques.

[0083] Optionally, the vector representation can achieve the quantification of semantics, so that the system can use mathematical methods to compare the similarity between different texts, which is difficult for traditional text comparison methods. In addition, high-dimensional vectors can preserve the subtle differences in semantics, helping the system make more accurate matching and judgment in complex language environments.

[0084] When calculating the similarity between the first vector (frozen reason vector) and the second vector (unfreeze reason vector), the self-unfreeze system uses similarity calculation methods including but not limited to cosine similarity, Euclidean distance, etc. Cosine similarity is an indicator to measure the similarity of the direction of two vectors, and its value range is usually between -1 and 1. The closer the value is to 1, the more similar the two vectors are.

[0085] A high vector similarity means that the frozen reason and the unfreeze reason have a close relationship in semantics, which provides preliminary evidence for the reasonableness of the unfreeze request. Conversely, if the similarity is low, the system may need to conduct more in-depth analysis or manual intervention to ensure the safety of the unfreeze operation.

[0086] In the knowledge graph, the shortest path length from the first target node describing the frozen reason to the second target node describing the unfreeze reason is calculated, aiming to measure the "logical distance" between the two concepts. The shorter the path, the more direct the frozen reason can be explained or refuted by the unfreeze reason at the conceptual level, increasing the reasonableness of the unfreeze request.

[0087] The self-unfreeze system finally combines the vector similarity and the shortest path length to determine the semantic relevance between the first semantic information and the second semantic information. Specifically, the self-unfreeze system can set a set of scoring rules to convert the similarity and path length into corresponding scores, and then combine these two scores to obtain the final semantic relevance score. For example, high vector similarity and short path length will get high scores, indicating that the unfreeze request is reasonable both logically and semantically.

[0088] It should be noted that by converting semantic information into vectors and combining the shortest path length in the knowledge graph, the self-unfreeze system can accurately evaluate the semantic relevance between the frozen reason and the unfreeze reason. This process not only enhances the decision-making ability of the system, but also provides users with a safe and efficient self-service solution by quantifying risks and reasonableness.

[0089] Optionally, the length of the shortest path is negatively correlated with the semantic relevance, and the vector similarity is positively correlated with the semantic relevance.

[0090] Optionally, the length of the shortest path represents the number of most direct association steps between the freezing reason and the unfreezing reason. For example, if “abnormal transaction” is a freezing reason and “transaction verification is correct” is an unfreezing reason, the shortest path between them in the knowledge graph may be directly connected through a “transaction verification” node, with a shorter path length. The length of the shortest path is negatively correlated with the semantic relevance, meaning that the shorter the path, the higher the semantic relevance between the freezing reason and the unfreezing reason, and vice versa. This is because the shortest path usually reflects the most direct logical reasoning path, and a short path indicates that the unfreezing reason directly targets the freezing reason, which is logically more coherent and closely related, and thus has a higher semantic relevance.

[0091] Optionally, the vector similarity is calculated by natural language processing techniques, such as word embedding models, to convert the freezing reason and the unfreezing reason into vectors in a high-dimensional vector space, and then calculate the similarity (e.g., cosine similarity) between these vectors. A high vector similarity means that the freezing reason and the unfreezing reason are very similar in semantics, such as they may use similar vocabulary or express similar concepts. This similarity is based on semantic features rather than literal matching, so it can capture deeper semantic relationships. The vector similarity is positively correlated with the semantic relevance, i.e., the higher the similarity, the higher the semantic relevance. This is because the vector similarity directly reflects the closeness of the freezing reason and the unfreezing reason in the semantic space, and a high similarity means that they have a close connection in meaning, which usually corresponds to a stronger semantic relevance.

[0092] According to another aspect of the embodiments of the present application, a bank card self-help unfreezing device is also provided, wherein, Figure 3 is a schematic diagram of an optional bank card self-help unfreezing device according to an embodiment of the present application, as Figure 3 shown, the device comprises a receiving unit 301, a text generation unit 302, a first determination unit 303, and a second determination unit 304.

[0093] Optionally, the receiving unit 301 is configured to receive a thaw request sent by a user through a terminal device, where the thaw request is used to request to thaw a target function module of a target bank card in a frozen state; the text generation unit 302 is configured to generate a thaw suggestion text according to a freezing reason of the target function module and appeal information submitted by the user in the thaw request in a case where the user identity verification is successful; the first determining unit 303 is configured to determine a remote authorization end corresponding to the thaw request and a processing order of the thaw request according to a data source of the thaw request, a business type of the target function module, and a processing waiting time length of the thaw request; and the second determining unit 304 is configured to send the thaw request to the corresponding remote authorization end according to the processing order of the thaw request, and determine a processing operation for the thaw request according to reply information of the remote authorization end to the thaw suggestion text.

[0094] Optionally, the bank card self-service thawing device further comprises: an acquisition unit configured to acquire N kinds of identification information of the user in a case where the user is authorized, where the N kinds of identification information include at least one of voice identification information, face identification information, iris identification information, fingerprint identification information, and certificate identification information; and a verification unit configured to perform identity verification on the user according to the N kinds of identification information of the user and the reserved user identification information corresponding to the target bank card.

[0095] Optionally, the text generation unit 302 comprises: a first determining subunit, a sending subunit, and a generating subunit. The first determining subunit is configured to determine a verification data source of the appeal information according to the freezing reason, where the verification data source is used to verify the authenticity of the appeal information; the sending subunit is configured to send the appeal information to the verification data source for verification; and the generating subunit is configured to generate the thaw suggestion text according to a verification result returned by the verification data source for the appeal information, the freezing reason of the target function module, and the appeal information.

[0096] Optionally, the text generation unit 302 comprises: a semantic division subunit configured to use the same semantic analysis strategy to perform semantic analysis on the freezing reason and the appeal information respectively; a first processing subunit configured to take the semantic analysis result corresponding to the freezing reason as first semantic information; a second processing subunit configured to take the semantic analysis result corresponding to the appeal information as second semantic information; a detection subunit configured to detect semantic correlation degrees of the first semantic information and the second semantic information, where the semantic correlation degrees are used to represent the explanation accuracy of the second semantic information to the first semantic information; and a text generation subunit configured to generate the thaw suggestion text according to the semantic correlation degrees of the first semantic information and the second semantic information, the freezing reason of the target function module, and the appeal information.

[0097] Optionally, the detection subunit includes: an acquisition module for acquiring a knowledge graph, wherein the knowledge graph includes multiple first nodes and multiple second nodes, wherein each first node is used to describe a freezing reason of a bank card function module, and each second node is used to describe a thawing reason of the bank card function module; a first processing module for taking the first node in the knowledge graph, in which the semantic similarity between the freezing reason described and the first semantic information is the highest, as the first target node; a second processing module for taking the second node in the knowledge graph, in which the semantic similarity between the thawing reason described and the second semantic information is the highest, as the second target node; a first determination module for determining the shortest path from the first target node to the second target node in the knowledge graph; and a second determination module for determining the semantic relevance between the first semantic information and the second semantic information based on the length of the shortest path.

[0098] Optionally, the second determination module includes: a first processing sub-module, used to convert the first semantic information into a first vector, and convert the second semantic information into a second vector; a second processing sub-module, used to detect the vector similarity between the first vector and the second vector; and a third processing sub-module, used to determine the semantic relevance between the first semantic information and the second semantic information based on the vector similarity and the length of the shortest path.

[0099] Optionally, the length of the shortest path is negatively correlated with the semantic relevance; and the vector similarity is positively correlated with the semantic relevance.

[0100] According to another aspect of the present application, a computer-readable storage medium is also provided, wherein a computer program is stored in the computer-readable storage medium, wherein when the computer program is run, the device where the computer-readable storage medium is located executes the above-mentioned bank card self-service unfreezing method.

[0101] According to another aspect of the present application, an electronic device is also provided, wherein the electronic device 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 one or more processors, the one or more processors execute the above-mentioned bank card self-service unfreezing method.

[0102] According to another aspect of the present application, a computer program product is also provided, wherein the computer program product includes a computer program or instructions, and when the computer program or instructions are executed by a processor, the computer program or instructions implements the above-mentioned bank card self-service unfreezing method.

[0103] The serial numbers of the above embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0104] In the above-described embodiments of the present application, the description of each embodiment focuses on different aspects, and the parts not described in detail in a certain embodiment can be referred to the relevant description of other embodiments.

[0105] In several embodiments provided in the present application, it should be understood that the disclosed technical content can be implemented by other manners. Among them, the above-described device embodiments are only schematic, for example, the division of the units can be a logical function division, and in actual implementation, there can be another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units or modules shown or discussed can be indirect coupling or communication connection through some interfaces, units or modules, which can be electrical or other forms.

[0106] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed to a plurality of units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0107] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The above integrated unit can be realized in the form of hardware or in the form of software functional unit.

[0108] The integrated unit, if realized in the form of software functional unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the part of the prior art that makes a contribution or the whole or part of the technical solutions can be embodied in the form of software product, which is stored in a storage medium and includes a plurality of instructions for making a computer device (which can be a personal computer, a server or a network device, etc.) execute all or part of the steps of the method described in each embodiment of the present application. The foregoing storage medium includes various media that can store program codes, such as U disk, read-only memory (ROM), random access memory (RAM), mobile hard disk, magnetic disk or optical disk, etc.

[0109] The above is only the preferred embodiment of the present application, and it should be pointed out that for ordinary skilled in the art, without departing from the principles of the present application, a number of improvements and refinements can be made, and these improvements and refinements should be regarded as the protection scope of the present application.

Claims

1. A bank card self-service unfreezing method, characterized in that: include: Receiving a thawing request sent by a user through a terminal device, wherein the thawing request is used to request thawing of a target functional module of a target bank card that is in a frozen state; If the user identity verification is successful, generating an unfreezing suggestion text according to the freezing reason of the target functional module and the appeal information submitted by the user in the unfreezing request; Determining the remote authorization terminal corresponding to the thawing request and the processing order of the thawing request according to the data source of the thawing request, the business type of the target functional module, and the processing waiting time of the thawing request; According to the processing order of the unfreeze request, the unfreeze request is sent to the corresponding remote authorization end, and the processing operation for the unfreeze request is determined according to the reply information of the remote authorization end to the unfreeze suggestion text.

2. The method according to claim 1, characterized in that After receiving a thawing request sent by the user via the terminal device, the method further includes: With the user's authorization, collecting N types of identification information of the user, wherein the N types of identification information include at least one of voice identification information, face identification information, iris identification information, fingerprint identification information, and ID identification information; The user's identity is authenticated based on the N types of identification information of the user and the reserved user identification information corresponding to the target bank card.

3. The method according to claim 1, characterized in that Generate an unfreezing suggestion text based on the freezing reason and the appeal information submitted by the user in the unfreezing request, including: Determining a verification data source for the complaint information based on the freezing reason, wherein the verification data source is used to verify the authenticity of the complaint information; Sending the complaint information to the verification data source for verification; The unfreezing suggestion text is generated according to the verification result returned by the verification data source for the appeal information, the freezing reason of the target functional module and the appeal information.

4. The method according to claim 1, wherein Generate an unfreezing suggestion text based on the freezing reason and the appeal information submitted by the user in the unfreezing request, including: Using the same semantic analysis strategy, semantic analysis is performed on the freezing reason and the appeal information respectively; Using the semantic parsing result corresponding to the freezing reason as the first semantic information; Using the semantic parsing result corresponding to the complaint information as the second semantic information; detecting a semantic relevance between the first semantic information and the second semantic information, wherein the semantic relevance is used to represent an accuracy of interpretation of the first semantic information by the second semantic information; The unfreezing suggestion text is generated according to the semantic relevance between the first semantic information and the second semantic information, the freezing reason of the target functional module, and the appeal information.

5. The method according to claim 4, characterized in that Detecting the semantic relevance between the first semantic information and the second semantic information includes: Obtaining a knowledge graph, wherein the knowledge graph includes a plurality of first nodes and a plurality of second nodes, wherein each first node is used to describe a freezing reason of a bank card function module, and each second node is used to describe a thawing reason of the bank card function module; The first node in the knowledge graph that has the highest semantic similarity between the freezing reason described and the first semantic information is used as the first target node; The second node in the knowledge graph, which has the highest semantic similarity between the reason for unfreezing described and the second semantic information, is used as the second target node; In the knowledge graph, determining the shortest path from the first target node to the second target node; The semantic relevance between the first semantic information and the second semantic information is determined according to the length of the shortest path.

6. The method according to claim 5, characterized in that Determining the semantic relevance between the first semantic information and the second semantic information according to the length of the shortest path includes: Converting the first semantic information into a first vector and converting the second semantic information into a second vector; detecting vector similarity between the first vector and the second vector; The semantic relevance between the first semantic information and the second semantic information is determined according to the vector similarity and the length of the shortest path.

7. The method according to claim 6, characterized in that There is a negative correlation between the length of the shortest path and the semantic relevance; there is a positive correlation between the vector similarity and the semantic relevance.

8. A bank card self-service unfreezing device, characterized in that: include: a receiving unit, configured to receive a thawing request sent by a user via a terminal device, wherein the thawing request is used to request thawing of a target functional module of a target bank card that is in a frozen state; a text generating unit, configured to generate an unfreezing suggestion text according to the freezing reason of the target functional module and the appeal information submitted by the user in the unfreezing request, if the user identity authentication is successful; a first determining unit, configured to determine a remote authorization terminal corresponding to the thawing request and a processing order of the thawing request based on a data source of the thawing request, a service type of the target functional module, and a processing waiting time of the thawing request; The second determining unit is configured to send the unfreeze request to a corresponding remote authorization terminal according to a processing order of the unfreeze request, and determine a processing operation for the unfreeze request according to a reply message of the remote authorization terminal to the unfreeze suggestion text.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located executes the bank card self-service unfreezing 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, wherein the memory is 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 execute the bank card self-service unfreezing method as described in any one of claims 1 to 7.

11. A computer program product, characterized in that The method comprises a computer program or an instruction, which, when executed by a processor, implements the bank card self-service unfreezing method according to any one of claims 1 to 7.

Images