Identity authentication process adjustment method and device based on self-service cash withdrawal equipment

Abstract

The application discloses an identity authentication process adjustment method and device based on a self-service cash deposit and withdrawal equipment, and relates to the field of financial technology, wherein the method comprises the following steps: determining a target interface region according to user historical operation data, generating simplified interface structure data based on element distribution characteristics of the interface region, adjusting an identity verification process structure to be presented, generating a reorganized verification process sequence, embedding operation instructions, generating identity verification process data with guide information, identifying individual difference characteristics through a preset clustering analysis strategy, generating user behavior classification model data, generating personalized verification step sequence data according to the user behavior classification model data, adjusting the execution order of the identity verification process data, analyzing the adaptability of different user groups, and generating multiple identity authentication scripts. The application solves the technical problem that the excessively complex user interface of the self-service cash deposit and withdrawal machine increases cognitive load and makes operation difficult in the prior art.

Description

Technical Field

[0001] This invention relates to the field of financial technology or other related fields, and more specifically, to a method and apparatus for adjusting the identity authentication process based on self-service deposit and withdrawal equipment. Background Technology

[0002] In the current field of fintech and smart banking services, ATMs serve as a crucial bridge connecting financial institutions and users, and their security and convenience have always been key considerations in design and innovation. While multi-factor authentication methods for ATMs offer a degree of transaction security, their inherent limitations—such as complex interface design, lengthy verification processes, and insufficient support for specific user groups like the elderly and those with special needs—still constrain user experience and system adoption. Specifically, overly complex user interfaces increase cognitive load, making operation difficult, especially for elderly users and those with special needs; a lack of intuitive and guided verification processes slows down operations and reduces efficiency; and insufficient intelligent adaptation to user behavior patterns, failing to optimize verification steps according to different user habits and needs, poses significant challenges to the security and usability of ATMs.

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

[0004] This invention provides a method and apparatus for adjusting the identity authentication process of self-service deposit and withdrawal machines, in order to at least solve the technical problem in the related art that the overly complex user interface of self-service deposit and withdrawal machines increases the cognitive load and makes operation difficult.

[0005] To achieve the above objectives, according to one aspect of this application, a method for adjusting the identity authentication process based on a self-service deposit and withdrawal device is provided, comprising: acquiring historical user operation data of the self-service deposit and withdrawal device; determining a target interface area based on the historical user operation data; and generating simplified interface structure data based on the element distribution characteristics of the target interface area, wherein the historical user operation data includes at least: the number of clicks and dwell time of each area of ​​the device interface; adjusting the identity verification process structure to be presented on the self-service deposit and withdrawal device based on the simplified interface structure data, generating a recombined verification process sequence, and embedding operation guidance in the recombined verification process sequence to generate identity verification process data with guidance information; extracting user behavior data from the identity verification process data, identifying individual difference characteristics through a preset clustering analysis strategy, generating user behavior classification model data, and generating personalized verification step sequence data based on the user behavior classification model data; adjusting the execution order of the identity verification process data based on the personalized verification step sequence data; and analyzing the adaptability of different user groups based on the adjusted identity verification process data to generate a multi-identity authentication script.

[0006] Optionally, the step of determining the target interface area based on the user's historical operation data and generating simplified interface structure data based on the element distribution characteristics of the target interface area includes: analyzing the number of clicks and dwell time of each area of ​​the device interface in the user's historical operation data, and outputting user operation behavior distribution data; processing the user operation behavior distribution data using statistical analysis tools to determine the correlation index between interface complexity and cognitive burden; confirming the location of the target interface area based on the number of clicks and dwell time when the correlation index exceeds a preset correlation threshold; obtaining the element distribution characteristics within the target interface area and generating a complexity metric; and dividing the area using a preset clustering algorithm based on the complexity metric to obtain simplified interface structure data.

[0007] Optionally, the step of adjusting the identity verification process structure presented on the self-service deposit and withdrawal device based on the simplified interface structure data to generate a recombined verification process sequence includes: extracting the original information of the verification process from the simplified interface structure data to obtain the process structure distribution; dividing the process structure distribution into multiple single-task units using a hierarchical decomposition strategy, and extracting independent unit features from the single-task unit division results to generate a single-task unit set; recombining and adjusting the single-task unit set using a preset sorting algorithm to obtain the recombined process structure; if the total execution time of the recombined process structure exceeds a preset time threshold, iteratively optimizing the recombined process structure, and dividing the iteratively optimized process sequence results using a preset clustering algorithm to generate a target verification process sequence; extracting key features from the target verification process sequence, and judging the process integrity based on the extracted key features; if the judgment result indicates that the target verification process sequence meets the integrity requirements, using the target verification process sequence as the recombined verification process sequence.

[0008] Optionally, the step of embedding operation guidance into the recombined verification process sequence to generate identity verification process data with guidance information includes: generating an initial data set based on the recombined verification process sequence, adjusting the sequence order using a preset embedding design strategy to obtain recombined sequence data; extracting operation instructions from the recombined sequence data to generate a preliminary guidance framework; generating real-time operation guidance using preset dynamic prompt generation rules based on the preliminary guidance framework, and determining the correspondence between the real-time operation guidance and the recombined sequence data; extracting key information from the verification process data when the correspondence between the real-time operation guidance and the recombined sequence data is detected to be incomplete, adjusting the verification process using the key information to obtain optimized verification process data; clustering the guidance information using a preset clustering algorithm for the optimized verification process data to generate segmented guidance data; extracting prompt generation rules from the segmented guidance data, generating target operation guidance using the prompt generation rules, and confirming target verification process data based on the target operation guidance; verifying the target verification process data using preset integrity judgment rules to generate the identity verification process data with guidance information.

[0009] Optionally, the step of extracting user behavior data from the identity verification process data, identifying individual differences through a preset clustering analysis strategy, and generating user behavior classification model data includes: extracting user behavior data from the identity verification process data; organizing the extracted user behavior data into a structured behavior data set according to preset field mapping rules; performing clustering analysis on the structured behavior data set using a preset clustering analysis strategy, grouping data with similar behavior patterns into the same group to obtain an individual difference feature set; and calculating the variance contribution rate of each feature in the set using principal component analysis, based on... The weights of the contribution rate feature are adjusted to obtain weighted feature data. If, during comparison, data points in the weighted feature data deviate from the mean by more than a predetermined standard deviation, the weighted feature data is filtered out, and the effective feature data is retained. The effective feature data is divided into multiple categories using a preset clustering algorithm to generate preliminary classification model data. The feature distribution patterns of the cluster centers are extracted from the preliminary classification model data to form dynamic generation rules, resulting in optimized user behavior classification data. The optimized user behavior classification data is then compared with the original structured behavior data set to verify the matching degree, generating the user behavior classification model data.

[0010] Optionally, the step of generating personalized verification step sequence data based on the user behavior classification model data includes: extracting user behavior data from the user behavior classification model data; using a decision tree algorithm to locate user habit preferences based on the extracted user behavior data to obtain personalized features; adjusting preset rules according to the personalized features to determine verification steps; generating a verification sequence according to the verification steps; analyzing the distribution characteristics of the verification sequence using data analysis tools to obtain preliminary sequence data; adjusting the judgment logic to generate adjusted sequence data when the preliminary sequence data matches the user behavior data; and generating the personalized verification step sequence data based on the adjusted sequence data.

[0011] Optionally, after generating personalized verification step sequence data based on the user behavior classification model data, the method further includes: using a timing tool to count the operation time to obtain a time consumption statistics result; if the time consumption statistics result exceeds a preset time consumption threshold, using a parallel processing algorithm to rearrange the execution order to obtain adjusted sequence data; generating time-optimized process data based on the adjusted sequence data; extracting personalized behavior features from the time-optimized process data; using a preset clustering algorithm to divide the behavior distribution to obtain user behavior classification data; and adjusting the verification step logic based on the user behavior classification data to generate time-optimized verification process data.

[0012] Optionally, after adjusting the verification step logic based on the user behavior classification data and generating time-optimized verification process data, the method further includes: using a threat modeling strategy to detect potential vulnerabilities in the time-optimized verification process data, generating suspected vulnerability stage distribution data based on the potential vulnerabilities; extracting key risk points from the suspected vulnerability stage distribution data, determining the priority order of the key risk points, and adjusting the execution order of the key risk points if the priority order exceeds a preset priority threshold, thereby generating optimized process data; detecting behavior distribution based on the optimized process data, obtaining dynamic change trend characteristics, adjusting the verification process hardening strategy based on the dynamic change trend characteristics, and generating security-hardened verification process data.

[0013] According to another aspect of the present invention, an identity authentication process adjustment device based on a self-service deposit and withdrawal device is also provided, comprising: an interface simplification unit, configured to acquire user historical operation data of the self-service deposit and withdrawal device, determine a target interface area based on the user historical operation data, and generate simplified interface structure data based on the element distribution characteristics of the target interface area, wherein the user historical operation data includes at least: the number of clicks and dwell time of each area of ​​the device interface; a verification process reorganization unit, configured to adjust the identity authentication process structure to be presented on the self-service deposit and withdrawal device based on the simplified interface structure data, generate a reorganized verification process sequence, and embed operation guidance in the reorganized verification process sequence to generate identity authentication process data with guidance information; a personalized verification step sequence generation unit, configured to extract user behavior data from the identity authentication process data, identify individual difference characteristics through a preset clustering analysis strategy, generate user behavior classification model data, and generate personalized verification step sequence data based on the user behavior classification model data; a verification process order adjustment unit, configured to adjust the execution order of the identity authentication process data based on the personalized verification step sequence data; and a multi-identity authentication script generation unit, configured to analyze the adaptability of different user groups based on the adjusted identity authentication process data and generate a multi-identity authentication script.

[0014] According to another aspect of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to perform any of the above-described identity authentication process adjustment methods based on self-service deposit and withdrawal devices.

[0015] According to another aspect of the present invention, an electronic device is also provided, including one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to implement the identity authentication process adjustment method based on any one of the above-described self-service deposit and withdrawal devices.

[0016] According to another aspect of the present invention, a computer program product is also provided, including a computer program that, when executed by a processor, implements the steps of the identity authentication process adjustment method based on self-service deposit and withdrawal equipment as described above.

[0017] In this disclosure, historical user operation data of self-service deposit and withdrawal devices is obtained. Target interface areas are determined based on this data, and simplified interface structure data is generated based on the element distribution characteristics of these areas. The historical user operation data includes at least the number of clicks and dwell time in each area of ​​the device interface. The identity verification process structure presented on the self-service deposit and withdrawal device is adjusted based on the simplified interface structure data, generating a recombined verification process sequence. Operation guidance is embedded in the recombined verification process sequence, generating identity verification process data with guidance information. User behavior data is extracted from the identity verification process data. Individual differences are identified through a preset clustering analysis strategy, generating user behavior classification model data. Personalized verification step sequence data is generated based on the user behavior classification model data. The execution order of the identity verification process data is adjusted based on the personalized verification step sequence data. The adaptability of the adjusted identity verification process data to different user groups is analyzed, generating a multi-identity authentication script.

[0018] Based on the above-mentioned disclosures, by comprehensively considering factors such as interface complexity, user behavior, and operational efficiency, the identity authentication process is fully optimized, improving the system's usability and adaptability while ensuring security. This effectively enhances the overall performance and user experience of multi-identity authentication, thereby solving the technical problem in related technologies where overly complex user interfaces of self-service ATMs increase cognitive load and make operation difficult. Attached Figure Description

[0019] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0020] Figure 1 A hardware structure block diagram of a computer terminal (or mobile device) for implementing an identity authentication process adjustment method based on a self-service deposit and withdrawal device is shown.

[0021] Figure 2 This is a flowchart of an optional method for adjusting the identity authentication process based on a self-service deposit and withdrawal device according to an embodiment of the present invention;

[0022] Figure 3 This is a schematic diagram of an optional identity authentication process adjustment device based on a self-service deposit and withdrawal device according to an embodiment of the present invention;

[0023] Figure 4 This is a structural block diagram of an electronic device that performs an identity authentication process adjustment method based on a self-service deposit and withdrawal device, according to an embodiment of this application. Detailed Implementation

[0024] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0025] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0026] To facilitate understanding of the present invention by those skilled in the art, some terms or nouns involved in the various embodiments of the present invention are explained below:

[0027] K-means clustering algorithm, or K-means for short, is a commonly used unsupervised machine learning algorithm for cluster analysis of datasets. It determines the optimal clustering result by minimizing the sum of squared distances between each sample and its cluster center. In this invention, K-means is used to perform cluster analysis on user operation areas, verification steps, guidance information, and time-optimized user behavior to more effectively manage and optimize the user verification process, while also identifying the unique behavioral patterns of different user groups.

[0028] Density-Based Spatial Clustering of Applications with Noise (DBSCAN) is a clustering algorithm suitable for processing noisy data. It does not require pre-specifying the number of clusters; instead, it automatically discovers cluster boundaries based on the density distribution of data points. In this invention, DBSCAN is used to identify groups with similar operating patterns in user behavior data, thereby providing a basis for the design of subsequent personalized verification processes.

[0029] The Autoregressive Integrated Moving Average (ARIMA) model is a statistical model used for time series forecasting, suitable for stationary time series data. It combines three techniques: autoregression (AR), differencing (I), and moving average (MA), enabling it to analyze trends, seasonality, and random fluctuations in time series data, thereby predicting future data trends. In this invention, ARIMA is used to analyze and predict future trends of key indicators such as user authentication success rate, time consumption changes, and coverage, assisting decision-makers in making reasonable design adjustments.

[0030] It should be noted that the method and apparatus for adjusting the identity authentication process of self-service deposit and withdrawal devices disclosed herein can be used in the financial technology field to optimize the identity authentication process and implement multi-identity authentication of self-service deposit and withdrawal devices, and can also be used in any field other than the financial technology field to optimize the identity authentication process and implement multi-identity authentication of self-service deposit and withdrawal devices. This disclosure does not limit the application field of the method and apparatus for adjusting the identity authentication process of self-service deposit and withdrawal devices.

[0031] It should 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 used for analysis, stored data, and displayed data) collected in this public disclosure are information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of related data all comply with the relevant laws, regulations, and standards of the relevant regions, necessary confidentiality measures have been taken, and they do not violate public order and good morals. Corresponding operation entry points are provided for users to choose to authorize or refuse. For example, this system has interfaces with relevant users or organizations. Before obtaining relevant information, a request to obtain the information needs to be sent to the aforementioned user or organization through the interface, and the relevant information is obtained only after receiving consent from the aforementioned user or organization.

[0032] It should be noted that in this disclosure, customer information is collected and analyzed, and users are provided with corresponding operation entry points to choose whether to agree to or reject the automated decision results; if the user chooses to reject, the process will proceed to the expert decision-making process.

[0033] The following embodiments of the present invention can be applied to various systems / applications / devices based on adjustments to the identity authentication process of self-service deposit and withdrawal devices. The present invention is applicable to fintech scenarios, especially multi-factor authentication systems deploying self-service deposit and withdrawal machines (ATMs), and is particularly suitable for banks and financial institutions seeking to improve transaction security and user experience. It can be widely applied to various financial transaction scenarios such as deposit and withdrawal operations, account inquiries, and transfers at ATMs, enhancing higher-level security measures while maintaining operational convenience.

[0034] This invention effectively identifies and defends against potential security risks through user behavior pattern analysis and threat modeling, reducing the probability of identity theft and fraud. Interface complexity and cognitive burden analysis ensure the intuitiveness and simplicity of the user interface. Embedded operation guidance design, combined with personalized verification step sequencing, makes the operation process more user-friendly, especially for the elderly and special groups.

[0035] At the same time, the verification process is dynamically adjusted based on user behavior characteristics, achieving a highly personalized identity authentication experience that can cover a wider range of users, including but not limited to young users, middle-aged users and elderly users, adapting to different operating habits and needs.

[0036] The present invention will now be described in detail with reference to various embodiments.

[0037] Example 1

[0038] According to an embodiment of the present invention, an embodiment of an identity authentication process adjustment method based on a self-service deposit and withdrawal device is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0039] The method for adjusting the identity authentication process based on self-service deposit and withdrawal devices provided in Embodiment 1 of this application can be executed on a mobile terminal, computer terminal, or similar computing device. Figure 1 A hardware block diagram of a computer terminal (or mobile device) for implementing an identity authentication process adjustment method based on self-service deposit and withdrawal devices is shown. Figure 1 As shown, computer terminal 10 (or mobile device) may include one or more ( Figure 1(Illustrated as 102a, 102b, ..., 102n) Processor 102 (processor 102 may include, but is not limited to, a microprocessor MCU (Microcontroller Unit) or a programmable gate array (FPGA), etc.), memory 104 for storing data, and transmission device 106 for communication functions. In addition, it may include: a display, input / output interface (I / O interface), Universal Serial Bus (USB) port (which may be included as one of the ports of a BUS bus), network interface, power supply, and / or camera. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, computer terminal 10 may also include... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0040] It should be noted that the aforementioned one or more processors 102 and / or other data processing circuits are generally referred to herein as "data processing circuits". These data processing circuits may be embodied, in whole or in part, in software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuits may be a single, independent processing module, or may be integrated, in whole or in part, into any other element within the computer terminal 10 (or mobile device). As involved in the embodiments of this application, the data processing circuits serve as a processor control mechanism (e.g., selection of a variable resistor termination path connected to an interface).

[0041] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the self-service deposit and withdrawal device-based identity authentication process adjustment method in this embodiment of the application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, thereby realizing the aforementioned self-service deposit and withdrawal device-based identity authentication process adjustment method. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the computer terminal 10 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0042] The transmission device 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of the computer terminal 10. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 may be a Radio Frequency (RF) module, used for wireless communication with the Internet.

[0043] The display can be, for example, a touchscreen liquid crystal display (LCD), which allows the user to interact with the user interface of the computer terminal 10 (or mobile device).

[0044] Under the aforementioned operating environment, this application provides the following: Figure 2 The method for adjusting the identity authentication process based on self-service deposit and withdrawal devices is shown. Figure 2 This is a flowchart of an optional identity authentication process adjustment method based on a self-service deposit and withdrawal device according to an embodiment of the present invention, such as... Figure 2 As shown, the method includes the following steps:

[0045] Step S201: Obtain the user's historical operation data of the self-service deposit and withdrawal device, determine the target interface area based on the user's historical operation data, and generate simplified interface structure data based on the element distribution characteristics of the target interface area. The user's historical operation data includes at least the number of clicks and dwell time of each area of ​​the device interface.

[0046] In this embodiment, step S201 collects historical user operation data from the self-service deposit and withdrawal device and analyzes the relationship between the complexity of the interface and the user's cognitive burden. Based on this, the target interface area is simplified to generate optimized interface structure data. By obtaining detailed records of user interaction with the device interface, including but not limited to the number of clicks and dwell time in each area, a deeper understanding of user operation patterns and interface usage efficiency is achieved.

[0047] This embodiment begins with a comprehensive analysis of historical user operation data, which covers click frequency and user attention dwell time across all areas of the device interface. By recording and analyzing this data, user preferences and pain points during operation can be captured, providing empirical evidence for interface optimization. Optionally, the steps of determining the target interface area based on historical user operation data and generating simplified interface structure data based on the element distribution characteristics of the target interface area include: analyzing the click count and dwell time of each area of ​​the device interface in the historical user operation data to output user operation behavior distribution data; processing the user operation behavior distribution data using statistical analysis tools to determine the correlation index between interface complexity and cognitive burden; confirming the location of the target interface area based on the click count and dwell time when the correlation index exceeds a preset correlation threshold; obtaining the element distribution characteristics within the target interface area to generate a complexity quantification value; and dividing the area using a preset clustering algorithm based on the complexity quantification value to obtain simplified interface structure data.

[0048] Specifically, when acquiring user historical operation data, front-end tracking technology can be used to record the number of clicks and dwell time of users on the interface of self-service deposit and withdrawal devices. For example, on a product details page of an e-commerce platform, suppose a user clicks the "Add to Cart" button 3 times, with a total dwell time of 15 seconds, while dwelling on the "Product Description" area for 40 seconds without clicking. Such data reflects the distribution characteristics of user operation behavior. The number of clicks may indicate the clarity of the operation intent, while the dwell time may suggest the difficulty of understanding the content or the degree of interest of the user.

[0049] After analyzing historical user operation data, the system generates a detailed user operation behavior distribution report. This report records the number of clicks and average dwell time for each interface area, helping to accurately identify which areas pose additional challenges to users. For example, the report might indicate that the "Account Information Modification" page receives more clicks and has a longer dwell time than the "Balance Inquiry" page, suggesting that this area may need simplification. Next, this embodiment uses professional statistical analysis tools to process the operation behavior distribution data and calculate the correlation index between interface complexity and user cognitive burden. By setting a preset correlation threshold, when the calculated correlation index exceeds this threshold, the system can identify that a specific area of ​​the interface design may be causing excessive cognitive pressure on users. For example, on the "Account Information Modification" page, if the correlation index is found to be as high as 0.85, far exceeding the standard threshold of 0.6, it indicates that the area is highly complex and significantly correlated with user cognitive burden, and this page needs to be adjusted to reduce user cognitive burden. Once the correlation index exceeds the threshold, this embodiment will accurately locate the target interface area (i.e., the high-complexity area) that needs optimization based on the number of clicks and dwell time of users in specific areas. For example, if the "Personal Information Editing" section on the "Account Information Modification" page is frequently clicked and has the longest dwell time, then this section becomes the primary target for optimization to reduce the user's operational burden. For instance, in the "Product Description" area, a dwell time of up to 40 seconds without a click might indicate that the content is lengthy or poorly formatted, making it difficult for users to quickly extract information. After identifying the problem area in this way, the distribution characteristics of elements within that area are obtained, such as 5 text paragraphs, 3 images, and 1 button. A complex quantification is then generated; for example, a quantification value of 8, higher than the average of 5.

[0050] To further analyze the complexity of the target interface area, the system extracts element distribution features from this area, such as text length, number of buttons, and image resolution. Each feature is assigned a corresponding numerical value using a specific quantification method, ultimately summing them into a complexity quantification value. This value quantifies the cognitive challenges users may encounter when facing this area. For example, if the "Personal Information Editing" section includes multiple required fields, multiple optional buttons, and complex validation logic, its complexity quantification value may be very high. Based on the complexity quantification value, this embodiment uses a preset clustering algorithm, such as K-means, to subdivide the target interface area, grouping similar interface elements together. Through clustering, it becomes clear which elements combine to form the greatest operational obstacles, allowing for targeted simplification. For example, the clustering results may show that adjustments to "Name," "Address," and "Contact Information" fall into the same high-complexity group, indicating that inputting and editing this information is a difficult point for users. As another example, assuming the "Product Description" area is divided into three categories: text-dense areas, image display areas, and interactive areas, clustering yields simplified interface structure data. Dense text areas may be merged into a single collapsible text box to reduce visual clutter. This data can be used to generate optimized interface presentation data, such as displaying images and text in separate columns and placing interactive buttons in prominent positions.

[0051] It's worth noting that when extracting key features from the optimized interface presentation data, one can focus on factors such as the uniformity of element spacing and the clarity of information hierarchy. For example, if the optimized text spacing is adjusted to 10 pixels and the button response time is shortened to 0.5 seconds, the completeness of the final output data can be assessed. If all key features are present and user test feedback indicates a decrease in dwell time to 25 seconds, resulting in a 20% improvement in click efficiency, then the optimization effect is significant.

[0052] Through the above steps, this embodiment can accurately identify and simplify the target interface areas in self-service deposit and withdrawal machines that cause cognitive pressure to users, and generate simplified interface structure data. This not only improves the smoothness and efficiency of user operation, but also significantly reduces user confusion and operational errors caused by improper interface design. At the same time, it enhances the user experience of self-service deposit and withdrawal machines, especially for elderly users and special groups who may be confused by the complexity of the interface, providing a more friendly and intuitive operating interface, and promoting the popularization and inclusiveness of financial services.

[0053] Step S202: Based on the simplified interface structure data, adjust the identity verification process structure to be presented on the self-service deposit and withdrawal device, generate a reorganized verification process sequence, embed operation guidance in the reorganized verification process sequence, and generate identity verification process data with guidance information.

[0054] In this embodiment, step S202 can adjust the identity verification process structure presented on the self-service deposit and withdrawal device based on the analysis results of user operation data, i.e., the simplified interface structure data, so as to generate a reorganized verification process sequence.

[0055] Optionally, the steps of adjusting the identity verification process structure presented on the self-service deposit and withdrawal device based on the simplified interface structure data to generate a recombined verification process sequence include: extracting the original information of the verification process from the simplified interface structure data to obtain the process structure distribution; dividing the process structure distribution into multiple single-task units using a hierarchical decomposition strategy, and extracting independent unit features from the single-task unit division results to generate a single-task unit set; recombining and adjusting the single-task unit set using a preset sorting algorithm to obtain the recombined process structure; iteratively optimizing the recombined process structure when the total execution time of the recombined process structure exceeds a preset time threshold, and dividing the iteratively optimized process sequence results using a preset clustering algorithm to generate a target verification process sequence; extracting key features from the target verification process sequence, and judging the process integrity based on the extracted key features; and using the judgment result indicating that the target verification process sequence meets the integrity requirements as the recombined verification process sequence.

[0056] First, the original information of the verification process needs to be extracted from the simplified interface structure data to understand the composition and structure of the current verification process and obtain its structure distribution. This includes, but is not limited to, each authentication step the user needs to perform, the logical relationships between steps, and the order of operations. Based on the extracted structure distribution, a hierarchical decomposition strategy is used to break down the complex process into smaller, more manageable units based on function or operation type. This divides the verification process into multiple single-task units, each representing an independent verification action or function, such as password input or biometric identification. For example, in a payment verification process on an e-commerce platform, the original information might include steps such as user password input, verification code recognition, and fingerprint confirmation, with timestamps and operation status recorded for each step. For instance, suppose the logs show that the user spends an average of 20 seconds on verification code recognition and only 5 seconds on password input, reflecting the initial structure of each step in the process. Based on the structure distribution, a hierarchical decomposition method is used to divide it into multiple single-task units. In one possible implementation, payment verification can be decomposed into three units: "password input," "verification code recognition," and "fingerprint confirmation." The decomposition result can be determined based on operational independence and goal clarity. Specifically, "CAPTCHA recognition," as a single task unit, may be divided separately due to the long time required for image loading and user identification. When extracting independent unit features from the division of single task units, we can focus on the operation duration and interaction frequency of each unit. For example, the unit features of "CAPTCHA recognition" might be an operation duration of 20 seconds and an interaction frequency of 1 time, while "fingerprint confirmation" might have an operation duration of 2 seconds and an interaction frequency of 1 time.

[0057] Next, independent unit features are extracted from the partitioning results of the hierarchical decomposition strategy. These features may include the execution time of a single task unit, the number of times a user attempts to complete the task, and the acceptance of the unit by a specific user group (such as the elderly or visually impaired). Based on these features, a set of single task units is generated to provide a basis for subsequent process reengineering.

[0058] Furthermore, this embodiment reorganizes and adjusts the set of single-task units using a preset sorting algorithm, aiming to optimize the user verification experience and shorten the total operation time. The sorting algorithm can be based on user preferences, task execution efficiency, or dependencies between units. For example, the unit with the shortest execution time or the highest user completion rate can be placed at the beginning of the process to quickly filter unauthorized users or quickly confirm authorized users, reducing waiting time and improving verification smoothness. In one embodiment, if efficiency is prioritized, "fingerprint confirmation" can be placed first because it has the shortest time consumption. The reorganized process becomes "fingerprint confirmation - password input - verification code recognition." It should be noted that if the total time of the reorganized process exceeds a preset threshold, such as 15 seconds, iterative optimization is required.

[0059] If the total execution time of the reorganized process structure exceeds a preset time threshold—for example, if the overall process time exceeds the system-defined average acceptable user time—then this stage requires iterative optimization of the reorganized process structure. Iterative optimization involves re-evaluating the sorting logic of the unit set, adjusting the connection method between single-task units, or improving efficiency through parallel processing strategies. After optimization, a preset clustering algorithm, such as K-means clustering, is used to divide the iteratively optimized process sequence results. The aim is to identify the most efficient and intuitive verification process pattern and generate a target verification process sequence. Key features, such as unit execution order, user completion time distribution, and error rate, are extracted from the target verification process sequence. Based on these extracted key features, the integrity of the process is judged to ensure that all necessary verification steps are reasonably included and that the process logic is coherent, without omissions or redundancy. For example, the CAPTCHA loading time can be reduced to 10 seconds to generate the optimized sequence result. Based on the optimized sequence result, when using the K-means clustering algorithm to divide the sequence, the steps can be divided into two categories: "fast verification" and "complex verification." For example, "fingerprint confirmation" and "password input" are classified as quick verification, while "CAPTCHA recognition" is classified as complex verification, ultimately generating a verification process sequence.

[0060] If the judgment result indicates that the target verification process sequence meets the integrity requirements, for example, all necessary verification steps are covered and there are no major logical errors or execution times exceeding the threshold in the process, the target verification process sequence is used as the reorganized verification process sequence. It is then prepared to further embed operation guidance to generate identity verification process data with guidance information, ensuring that each identity verification step is reasonably arranged, and that the process structure is stable, efficient and user-friendly, making the identity verification process both secure and convenient.

[0061] Finally, operational guidance is embedded into the restructured verification process sequence. This process includes identifying potential user confusion or operational difficulties during verification and providing clear and timely guidance to enhance the interactivity and usability of the user interface. For example, before the fingerprint recognition step, the system can display prompts such as "Please place your finger flat, avoiding tilting or moving it" to improve the success rate of recognition. In this way, generating identity verification process data with guidance information not only helps reduce user errors but also improves the user experience, especially for users less familiar with technical operations, enabling them to easily complete the identity verification process and enhancing the accessibility and ease of use of self-service deposit and withdrawal devices.

[0062] In this embodiment, in order to further improve the intuitiveness and user-friendliness of the identity verification process, a step is also provided to embed operation guidance in the reorganized verification process sequence, which includes multiple detailed and orderly steps, aiming to ensure that each user can clearly understand and successfully complete the verification process. Optionally, the step of embedding operation guidance into the recombined verification process sequence to generate identity verification process data with guidance information includes: generating an initial data set based on the recombined verification process sequence, adjusting the sequence order using a preset embedding design strategy to obtain recombined sequence data; extracting operation instructions from the recombined sequence data to generate a preliminary guidance framework; generating real-time operation guidance using preset dynamic prompt generation rules based on the preliminary guidance framework, and determining the correspondence between the real-time operation guidance and the recombined sequence data; extracting key information from the verification process data when an incomplete correspondence is detected between the real-time operation guidance and the recombined sequence data, adjusting the verification process using the key information to obtain optimized verification process data; clustering the guidance information using a preset clustering algorithm for the optimized verification process data to generate segmented guidance data; extracting prompt generation rules from the segmented guidance data, generating target operation guidance using the prompt generation rules, and confirming the target verification process data based on the target operation guidance; and verifying the target verification process data using preset integrity judgment rules to generate identity verification process data with guidance information.

[0063] This embodiment first constructs an initial dataset containing all verification steps and their related attributes, starting from the optimized and recombined verification process sequence. These attributes can cover step identifiers, execution times, required user input types, etc. Specifically, this embodiment uses a predefined embedding design strategy to adjust the presentation and order of verification steps, ensuring that guidance is naturally integrated into the process and that the order in which each step appears is reasonable. For example, in an e-commerce payment scenario, the initial dataset may include three steps: "password input," "verification code verification," and "fingerprint recognition," each with a timestamp and operation status. When adjusting the sequence order for this initial dataset, the embedding design method can embed weights based on user operating habits. For instance, assuming a user prefers to complete fingerprint recognition quickly, this step can be moved forward, and the adjusted sequence becomes "fingerprint recognition - password input - verification code verification," generating recombined sequence data. This adjustment makes the process more aligned with user habits.

[0064] For example, if it is found that "fingerprint recognition" is the most familiar and fastest verification method for users, the strategy may place it at the beginning of the process to guide users to quickly enter the verification state and generate recombined sequence data.

[0065] This embodiment will next identify the user operation instructions required for each verification step from the reconstructed sequence data. These instructions may include specific operation guidelines such as "touch the screen," "enter password," and "scan fingerprint." At this stage, based on the preliminary guidance framework and preset dynamic prompt generation rules, this embodiment will generate more detailed real-time operation guidelines for each verification step. For example, for the "fingerprint recognition" step, in addition to the basic instruction of "scan fingerprint," specific prompts such as "Please place your finger flat on the sensor and keep it stable until confirmation" may be provided. At the same time, each real-time operation guide will establish a precise one-to-one mapping relationship with the corresponding verification step, ensuring that the user receives timely and effective guidance during the operation. When the system detects that the generated real-time operation guide fails to fully cover or match the verification steps in the reconstructed sequence data, this embodiment will immediately initiate a correction process. At this time, in a certain key verification step, the user's guidance information is missing or insufficient. By deeply mining the verification process data, key information such as common user errors and operational difficulties is extracted. Then, based on this information, the verification process is adjusted, necessary operation guidelines are added or modified, and new optimized verification process data is generated to ensure that each step has clear guidance information, eliminating blind spots and obstacles in user operation.

[0066] This embodiment uses a pre-defined clustering algorithm to group the guidance information in the optimized process. The aim is to identify verification steps with similar guidance requirements for unified management. For example, all steps involving touchscreen operations may be grouped into one category, and all password input-related operations into another, generating segmented guidance data. From this segmented guidance data, this embodiment further extracts general prompt generation rules. For touchscreen operation steps, the rule might require "ensuring guidance includes finger placement and pressure requirements"; for password input steps, it might emphasize "providing clear prompts that distinguish between uppercase and lowercase letters, numbers, and characters." These rules will be used to generate more personalized and refined target operation guidance, ensuring that each prompt helps users operate smoothly to the greatest extent possible. Based on this, the entire process data is reconfirmed to ensure it covers all necessary steps, generating target verification process data.

[0067] Finally, this embodiment conducts a comprehensive review of the target verification process data to ensure that all steps are not only logically continuous and complete, but also that there are no omissions or conflicts in user guidance information. Preset integrity judgment rules may include checking whether each step has corresponding guidance information, whether all guidance information follows consistency principles, and whether there are redundant or invalid guidance items. Only when the target verification process data passes all integrity verification conditions can the identity verification process data with guidance information be formally generated, ensuring that users receive the most direct and effective operation guidance at each verification step.

[0068] Step S203: Extract user behavior data from the identity verification process data, identify individual differences through a preset clustering analysis strategy, generate user behavior classification model data, and generate personalized verification step sequence data based on the user behavior classification model data.

[0069] Optionally, the steps of extracting user behavior data from identity verification process data, identifying individual differences through a preset clustering analysis strategy, and generating user behavior classification model data include: extracting user behavior data from identity verification process data; organizing the extracted user behavior data into a structured behavior data set according to preset field mapping rules; performing clustering analysis on the structured behavior data set using a preset clustering analysis strategy to group data with similar behavior patterns into the same group, thus obtaining an individual difference feature set; calculating the variance contribution rate of each feature in the set using principal component analysis, adjusting the feature weights according to the contribution rate, and obtaining weighted feature data; filtering out data points in the weighted feature data that deviate from the mean by more than a predetermined standard deviation, and retaining valid feature data; dividing the valid feature data into multiple categories using a preset clustering algorithm to generate preliminary classification model data; extracting the feature distribution patterns of each cluster center point from the preliminary classification model data to form dynamic generation rules, thus obtaining optimized user behavior classification data; and verifying the matching degree between the optimized user behavior classification data and the original structured behavior data set to generate user behavior classification model data.

[0070] First, this embodiment extracts user behavior data from the identity verification process data. This user behavior data includes, but is not limited to, operation time, operation frequency, input error rate, and the verification method selected by the user. Then, according to preset field mapping rules, the extracted user behavior data is organized into a structured behavior data set to ensure data consistency and analyzability. The field mapping rules typically define how to map the raw behavior data to specific data fields, such as mapping operation time to a "timestamp" field and input error rate to an "error count" field. Next, the structured behavior data set is processed using a preset clustering analysis strategy to group data with similar behavior patterns into the same group, resulting in a set of individual difference characteristics, i.e., the behavioral characteristics of different user groups.

[0071] In one optional embodiment, when extracting user behavior data from verification process data with guidance information, it can be viewed as capturing the user's operational habits and preferences during the verification process. For example, in e-commerce payment scenarios, user behavior data may include "fingerprint recognition completion time," "password input count," and "pause duration during verification code verification." For instance, assuming a user spends an average of 1 second on fingerprint recognition, attempts 2 times on password input, and pauses for 5 seconds during verification code verification, this data is organized into a structured behavioral data set using preset field mapping rules. Specifically, the field mapping rules can be defined as mapping "time consumption" to a time field and "number of attempts" to a count field, forming a set containing multi-dimensional information. When using the DBSCAN algorithm for cluster analysis, similar patterns can be grouped together based on the density of the user behavior data.

[0072] In one possible implementation, assuming that the variance contribution rate of "fingerprint recognition time" is 40% and "password input count" is 30%, after adjusting the weights according to the contribution rates, the weighted feature data will better highlight the impact of key behaviors.

[0073] It should be noted that if a user's data deviates from the mean by more than three standard deviations, such as fingerprint recognition taking 10 seconds, these outliers will be filtered out, retaining only the valid feature data to ensure the accuracy of the analysis. When using the K-means algorithm for classification based on the valid feature data, users can be divided into multiple categories.

[0074] For example, data might be categorized into three types: "quick completion," "repeated attempts," and "intermittent pauses," generating preliminary classification model data. Specifically, the cluster centroids of "quick completion" might be characterized by short processing time and few attempts; "repeated attempts" would show multiple input behaviors. Extracting feature distribution patterns from these cluster centroids can form dynamically generated rules, such as "prioritizing users with short processing times to simplify processes," thus obtaining optimized user behavior classification data. When validating the matching between the optimized user behavior classification data and the original dataset, the aim is to ensure that the classification results are consistent with actual behavior.

[0075] In one embodiment, if the matching degree reaches 90% or higher, the final classification model data is generated. For example, a user's behavioral data is "fingerprint recognition 1 second, password input 1 time, verification code verification 3 seconds," which is classified as "quick completion type," consistent with the trend of the original data. Preferably, this classification model data can provide a basis for subsequent process optimization, improving the relevance of the user experience. It can be understood that the entire process from extracting behavioral data to generating the final classification model forms a complete analytical chain.

[0076] For example, by identifying "repeated attempt" users, the design of the CAPTCHA input interface can be adjusted to increase the clarity of prompts and reduce operation interruptions. In one embodiment, the waiting time for "interrupted" users is extended to reduce the timeout exit rate. These adjustments are data-driven and can effectively improve the smoothness of the verification process.

[0077] The feature distribution patterns of cluster centroids are extracted from the initial classification model data to form dynamic generation rules. These rules guide the system in dynamically adjusting the verification process based on the behavioral characteristics of different users, thus achieving personalized authentication. Subsequently, the optimized user behavior classification data is compared with the original structured behavior data set to verify the matching degree, ensuring that the classification results are highly consistent with actual user behavior, thereby generating user behavior classification model data.

[0078] Optionally, the step of generating personalized verification step sequence data based on user behavior classification model data includes: extracting user behavior data from user behavior classification model data; using a decision tree algorithm to locate user habit preferences based on the extracted user behavior data to obtain personalized features; adjusting preset rules according to personalized features to determine verification steps; generating a verification sequence according to the verification steps; analyzing the distribution characteristics of the verification sequence using data analysis tools to obtain preliminary sequence data; adjusting the judgment logic when the preliminary sequence data matches the user behavior data to generate adjusted sequence data; and generating personalized verification step sequence data based on the adjusted sequence data.

[0079] During the process of multi-factor authentication when using a self-service ATM, the user's choice of authentication method, operation speed, authentication frequency, and specific interaction methods and time consumption in each authentication process are included, but are not limited to. Based on the extracted user behavior data, this embodiment uses a decision tree algorithm to analyze and determine the user's habit preferences, thereby obtaining personalized features. The decision tree mentioned in this embodiment is a supervised learning method that can generate a series of rules by learning the relationship between features and labels in a dataset, used to classify or predict unknown data. In this scenario, the construction of the decision tree aims to identify whether the user prefers a fast and convenient authentication process or a more secure and detailed verification process. Based on the user's historical operation records, such as the frequency and time consumption of fingerprint recognition and password input, and whether the user has chosen additional security measures in specific situations, the user's preference is determined and this information is transformed into personalized features. For example, users who frequently and quickly complete fingerprint recognition may be labeled as "efficiency-oriented," while those who prefer dual password and fingerprint authentication may be classified as "security-oriented." Based on the obtained individual characteristics, this embodiment dynamically adjusts the preset verification rules to more closely match personal habits. For users who prefer efficient operation, the system will automatically optimize the verification process, reducing steps or optimizing the process order to shorten authentication time. For users who prefer higher security, additional verification layers may be added, such as SMS verification codes or facial recognition. Next, the verification steps are determined according to the adjusted rules, and the system will generate a corresponding verification sequence. It should be noted that this verification sequence may include a series of identity authentication operations customized based on user behavior and preferences, such as "fingerprint recognition - confirmation" or "password input - SMS verification - confirmation".

[0080] Furthermore, given that the initial sequence data matches user behavior data—meaning the verification sequence design effectively reflects user habits—this embodiment will further adjust the judgment logic to generate more refined sequence data. For example, if data analysis reveals that the success rate and speed of fingerprint scanning immediately after entering the password are higher than scanning the fingerprint first and then entering the password, the system will adjust the order, prioritizing password input. This adjustment ensures the verification process is more aligned with individual habits, reducing user waiting time and errors during authentication, thus generating adjusted sequence data. Subsequently, personalized verification step sequence data is generated based on the adjusted sequence data. This data will be directly applied to the user's next identity authentication, providing a customized user experience.

[0081] Optionally, after generating personalized verification step sequence data based on user behavior classification model data, the method further includes: using a timing tool to count the operation time to obtain time statistics; if the time statistics exceed a preset time threshold, using a parallel processing algorithm to rearrange the execution order to obtain adjusted sequence data; generating time-optimized process data based on the adjusted sequence data; extracting personalized behavior features from the time-optimized process data; using a preset clustering algorithm to divide the behavior distribution to obtain user behavior classification data; and adjusting the verification step logic based on the user behavior classification data to generate time-optimized verification process data.

[0082] In this embodiment, a timing tool is used to monitor and record the time spent on each key step of the user's identity verification process, aiming to quantify the efficiency of the verification process. This timing tool can be integrated into the software interface of the self-service ATM, automatically starting and stopping the timer. Once the identity verification process begins, it immediately records the start and end times of each verification activity, including but not limited to password input, biometric matching, and verification code confirmation. The introduction of the timing tool provides objective and quantitative data support for subsequent process optimization and performance evaluation. The time consumption statistics reflect the average time, standard deviation, and potential operational bottlenecks for users to complete verification. This embodiment accurately identifies which steps take the longest, thereby making targeted optimization adjustments.

[0083] In this embodiment, if the operation time exceeds a preset threshold, it indicates that the current verification process may cause unnecessary time pressure on the user and affect the overall user experience. Therefore, this embodiment employs a parallel processing algorithm to adjust the execution order of verification steps, executing independent and concurrent verification steps in parallel to shorten the total verification time. For example, this embodiment may allow loading the verification code image while fingerprint recognition is being performed, or preprocessing biometric data during password input. This way, while the user waits for one step to complete, other verification steps are simultaneously performed in the background, achieving time overlap and significantly reducing the user's waiting time during verification. The adjusted sequence not only optimizes the process execution efficiency but also improves the user experience, especially in time-sensitive scenarios such as peak hours or emergency withdrawals. This optimization effectively alleviates user anxiety and improves the overall smoothness of the system's operation.

[0084] Furthermore, based on the parallel processing algorithm optimization, this embodiment transforms the adjusted step execution sequence into a complete, time-optimized verification process data, ensuring that the process maintains logical coherence while achieving the shortest total operation time. After implementing the time-optimized process, this embodiment further analyzes the personalized behavioral characteristics of user operations using data mining techniques. This focuses not only on average time consumption and overall efficiency but also on identifying differentiated behaviors of different users when executing the verification process. For example, some users may prefer quick fingerprint verification, while others may prefer redundant security steps, such as dual authentication like password confirmation and facial recognition. By employing a pre-defined clustering algorithm, such as K-means clustering, users can be classified according to their operating habits and preferences. These classification results form the basis of user behavior distribution.

[0085] Optionally, after adjusting the verification step logic based on user behavior classification data and generating time-optimized verification process data, the method further includes: using a threat modeling strategy to detect potential vulnerabilities in the time-optimized verification process data, generating suspected vulnerability stage distribution data based on the potential vulnerabilities; extracting key risk points from the suspected vulnerability stage distribution data, determining the priority order of the key risk points, and adjusting the execution order of the key risk points if the priority order exceeds a preset priority threshold, thereby generating optimized process data; detecting behavior distribution based on the optimized process data, obtaining dynamic trend characteristics, adjusting the verification process hardening strategy based on the dynamic trend characteristics, and generating security-hardened verification process data.

[0086] In this embodiment, a threat modeling strategy is introduced to assess the security weaknesses of the time-optimized verification process data, comprehensively examining potential security risks from dimensions such as tampering, repudiation, information leakage, denial of service, and privilege escalation. By analyzing the data flow and control flow in the verification process, threat modeling can identify vulnerabilities that attackers may exploit. The obtained distribution data of suspected vulnerability points includes not only the specific vulnerability location but also the vulnerability type and potential impact range, providing precise targets for subsequent hardening strategies. Based on the vulnerability distribution obtained through threat modeling, this embodiment further filters out key points with higher risk, i.e., critical risk points, to determine the priority order of each risk point. The priority judgment criteria may be based on preset thresholds, such as affecting more than a certain percentage of users or the probability of a successful attack exceeding a preset probability.

[0087] For identified critical risk points, if their priority exceeds a preset threshold, it indicates a high level of security threat, requiring immediate action for reinforcement. In this embodiment, the system can adjust the execution order of these critical risk points in the verification process to reduce risk exposure time or facilitate earlier identification of potential attacks. For example, assuming the facial recognition step is identified as high-risk, perhaps due to its susceptibility to ambient light, the system may move this step forward to perform more stringent identity verification at an earlier stage, or perform it in parallel with other verification steps (such as fingerprint recognition) to improve overall verification security. The generated optimized process data will focus more on security and the effectiveness of protective measures, ensuring that while improving process efficiency, the overall security level of the system is not reduced.

[0088] The monitoring and optimization of the verification process impacts user behavior during actual execution, and continuous data analysis is used to obtain dynamic trends in behavioral patterns. When detecting behavioral distribution, it may involve statistically analyzing metrics such as the average time users take to complete verification, success rate, and the acceptance of the new process by different user groups. The obtained dynamic trend characteristics reflect the actual performance of the system after the verification process adjustment, such as the smoothness of user operations, response speed, and changes in potential security threats.

[0089] In one alternative implementation, when extracting behavioral data from user behavior, it can be viewed as capturing the user's operational habits during the verification process. For example, in e-commerce payment verification scenarios, behavioral data may include the frequency with which the user selects a verification method, the input speed, and the interval between clicking confirm.

[0090] For example, a user prefers fingerprint verification and has an average input time of 2 seconds, with a confirmation interval of 3 seconds. This data can be extracted into a structured set through field extraction. Specifically, "verification method selection" and "input time" can be used as feature inputs to train a model to identify whether the user prefers a fast or cautious operating style.

[0091] In one possible implementation, the model output shows that a user has an 85% probability of preferring fingerprint verification, reflecting a preference for efficiency in their personality traits. After obtaining habitual preferences from these traits, adjusting preset rules is key to personalized design. For example, if a user prefers fast verification, fingerprint verification can be set as the default option, reducing unnecessary steps.

[0092] Preferably, this adjustment can shorten the verification time and generate a verification sequence after determining the intelligent steps. It is understood that the verification sequence may be "fingerprint verification - confirmation" or "password input - verification code verification." When analyzing the sequence distribution using the `describe` function in Pandas, specifically, the mean and distribution range of the time taken for each step in the sequence can be obtained. For example, the average time taken for the fingerprint verification step is 1.5 seconds, with a standard deviation of 0.5 seconds, which provides data support for subsequent optimization. If the initial sequence data matches the behavioral data, the `DecisionTreeClassifier` is used to optimize the judgment logic.

[0093] In one embodiment, by adding "user abort frequency" as a new feature, the model can more accurately predict whether a user is likely to abandon verification midway. The adjusted sequence data may shorten the time window for certain steps. When obtaining the correlation between individual characteristics and preset rules for the adjusted sequence data, for example, if efficient users are highly correlated with simplified rules, an optimized verification sequence, such as "single-step fingerprint verification," can be generated. After extracting the sequence distribution from the optimized verification sequence, user behavior is segmented using KMeans from Scikit-learn.

[0094] Specifically, the data is assumed to be divided into a "high-efficiency group" and a "multi-step trial group," the former characterized by short processing time and few steps, and the latter by the opposite. After obtaining the final categorized data, comparing it with habit preferences can reveal dynamic changes in user behavior.

[0095] For example, a user who previously belonged to the "high-efficiency group" may have recently experienced longer input times, indicating a change in their habits. One possible implementation is to add helpful prompts to the user when generating personalized sequence data, reducing the difficulty of operation.

[0096] In one embodiment, if users in the "multi-step attempt group" frequently abort, the sequence can be optimized to "step-by-step guided verification" to reduce the interruption rate. Based on dynamic trend characteristics, this embodiment dynamically adjusts the verification process hardening strategy to generate more secure and user-friendly process data. It should be noted that this adjustment may include enhancing the security verification mechanisms of certain key steps, such as by adding additional authentication factors or strengthening data encryption, to ensure that the verification process can effectively resist attacks even in high-risk environments. Simultaneously, considering user experience, the hardening strategy should avoid excessively increasing verification complexity, striving to find a balance between security and ease of use. The security-hardened verification process data will not only include the original verification steps but may also embed intelligent alarm systems, real-time threat perception mechanisms, and more detailed user behavior monitoring functions to ensure that the self-service ATM's identity verification system can continue to provide efficient and secure services in future use.

[0097] The system acquires personalized verification step sequence data and uses a timing tool to track operation time, generating a time statistics result. If the time statistics result exceeds a preset threshold, the execution order is rearranged. For example, in an e-commerce payment verification scenario, the timing tool records the time for each step from when the user selects a verification method to when they click confirm. For instance, a user selects fingerprint verification, which takes 1 second, and enters their password, which takes 3 seconds, for a total process time of 5 seconds, generating a time statistics result. If the preset threshold is 4 seconds, this result exceeds the threshold.

[0098] Step S204: Adjust the execution order of the identity verification process data based on the personalized verification step sequence data.

[0099] The personalized verification step sequence can include the user's most frequently selected verification methods and their order. For example, for a user who frequently uses fingerprint recognition and quickly completes password input, the personalized verification step sequence might be "fingerprint recognition" followed by "password input." This embodiment not only generates a personalized verification step sequence but also adjusts the execution order of the entire identity verification process data based on the time consumption, ease of operation, and security level of each step in the sequence. Based on a "user-centric" design philosophy, it ensures a balance between efficiency and security in the process. For example, for users who demonstrate high proficiency in the personalized verification step sequence, the system can place short-duration, low-error-rate verification steps such as fingerprint recognition at the beginning of the process, while placing longer-duration, higher-security verification steps such as facial recognition or signature confirmation at the end or as backup steps.

[0100] In adjusting the execution order, this embodiment combines parallel processing technology and serial processing logic. For verification steps that are time-consuming but can be performed simultaneously (such as sending and receiving SMS verification codes), the system adopts parallel processing to save overall verification time. For critical verification steps that must be completed in sequence (such as dynamic password verification after password input), the serial processing principle is followed to ensure the continuity and security of the process.

[0101] Step S205: Analyze the adaptability of the adjusted identity verification process data to different user groups and generate a multi-identity authentication script.

[0102] In step S205, this embodiment conducts in-depth analysis of the adjusted identity verification process data to evaluate the adaptability of different user groups (such as young people, the elderly, and people with disabilities) to the new execution order. Analysis metrics may include, but are not limited to, operation success rate, average completion time, and user satisfaction rating, to comprehensively understand the effectiveness of process optimization. For example, for the elderly, the analysis may show that they are slower to respond to touchscreens; therefore, when generating the multi-factor authentication script, the system will appropriately delay the touch response time to ensure that each elderly user has sufficient time to operate.

[0103] Based on the results of adaptive analysis, this embodiment generates a multi-identity authentication script. The script includes an identity verification process optimized for different user groups. The generation of the script not only considers the security and efficiency of identity verification, but also incorporates human-centered design ideas. For example, it provides larger fonts and high-contrast interfaces for users with poor eyesight, and provides vibration feedback instead of sound prompts for users with hearing impairments, ensuring that every user can feel convenient and respected when verifying their identity.

[0104] By generating multi-factor authentication scripts, this embodiment significantly improves the coverage and inclusivity of the authentication process. Compared to traditional authentication methods that ignore individual differences among users, causing some users to abandon ATMs due to operational inconvenience, this embodiment, through meticulous adaptability assessment combined with advanced clustering algorithms and statistical analysis tools, provides the most suitable authentication scheme for each user group. This not only enhances the user experience but also expands the service recipients of ATMs, making financial services more accessible and equitable.

[0105] Through the above steps, historical user operation data of the self-service deposit and withdrawal device can be obtained. Based on this data, the target interface area is determined, and simplified interface structure data is generated based on the element distribution characteristics of that area. The historical user operation data includes at least the number of clicks and dwell time in each area of ​​the device interface. Based on the simplified interface structure data, the identity verification process structure presented on the self-service deposit and withdrawal device is adjusted, generating a recombined verification process sequence. Operation guidance is embedded into this sequence, generating identity verification process data with guidance information. User behavior data is extracted from the identity verification process data, and individual differences are identified using a preset clustering analysis strategy to generate user behavior classification model data. Personalized verification step sequence data is generated based on this data. The execution order of the identity verification process data is adjusted based on this personalized verification step sequence data. The adaptability of the adjusted identity verification process data to different user groups is analyzed, and a multi-identity authentication script is generated. In this embodiment, by comprehensively considering factors such as interface complexity, user behavior, and operational efficiency, the identity authentication process is fully optimized, improving the system's usability and adaptability while ensuring security. This effectively enhances the overall performance and user experience of multi-identity authentication, thereby solving the technical problem in related technologies where overly complex user interfaces of self-service ATMs increase cognitive load and make operation difficult.

[0106] The following is a detailed description with reference to another embodiment.

[0107] Example 2

[0108] The identity authentication process adjustment device based on self-service deposit and withdrawal equipment provided in this embodiment includes multiple implementation units, each of which corresponds to the implementation steps in the above embodiment one. Its specific implementation method and beneficial effects can be referred to the foregoing method embodiment, and will not be repeated here.

[0109] Figure 3 This is a schematic diagram of an optional identity authentication process adjustment device based on a self-service deposit and withdrawal device according to an embodiment of the present invention, such as... Figure 3 As shown, the identity authentication process adjustment device based on self-service deposit and withdrawal equipment may include: an interface simplification unit 31, a verification process reorganization unit 32, a personalized verification step sequence generation unit 33, a verification process order adjustment unit 34, and a multi-identity authentication script generation unit 35.

[0110] The interface simplification unit 31 is used to acquire the user's historical operation data of the self-service deposit and withdrawal device, determine the target interface area based on the user's historical operation data, and generate simplified interface structure data based on the element distribution characteristics of the target interface area. The user's historical operation data includes at least the number of clicks and dwell time of each area of ​​the device interface.

[0111] The verification process reorganization unit 32 is used to adjust the identity verification process structure to be presented on the self-service deposit and withdrawal device based on the simplified interface structure data, generate a reorganized verification process sequence, embed operation guidance in the reorganized verification process sequence, and generate identity verification process data with guidance information.

[0112] The personalized verification step sequence generation unit 33 is used to extract user behavior data from the identity verification process data, identify individual differences through a preset clustering analysis strategy, generate user behavior classification model data, and generate personalized verification step sequence data based on the user behavior classification model data.

[0113] The verification process sequence adjustment unit 34 is used to adjust the execution order of the identity verification process data based on the personalized verification step sequence data.

[0114] The multi-identity authentication script generation unit 35 is used to generate multi-identity authentication scripts based on the adaptability analysis of different user groups according to the adjusted identity verification process data.

[0115] The aforementioned identity authentication process adjustment device based on self-service deposit and withdrawal equipment can obtain historical user operation data of the self-service deposit and withdrawal equipment through the interface simplification unit 31, determine the target interface area based on the historical user operation data, and generate simplified interface structure data based on the element distribution characteristics of the target interface area. The verification process reorganization unit 32 adjusts the identity authentication process structure to be presented on the self-service deposit and withdrawal equipment based on the simplified interface structure data, generates a reorganized verification process sequence, embeds operation guidance in the reorganized verification process sequence, and generates identity authentication process data with guidance information. The personalized verification step sequence generation unit 33 extracts user behavior data from the identity authentication process data, identifies individual differences through a preset clustering analysis strategy, generates user behavior classification model data, generates personalized verification step sequence data based on the user behavior classification model data, adjusts the execution order of the identity authentication process data based on the personalized verification step sequence data through the verification process order adjustment unit 34, and generates a multi-identity authentication script based on the multi-identity authentication script generation unit 35 based on the adjusted identity authentication process data and the adaptability of different user groups. In this embodiment, by comprehensively considering factors such as interface complexity, user behavior, and operational efficiency, the identity authentication process is fully optimized, improving the system's usability and adaptability while ensuring security. This effectively enhances the overall performance and user experience of multi-identity authentication, thereby solving the technical problem in related technologies where overly complex user interfaces of self-service ATMs increase cognitive load and make operation difficult.

[0116] Optionally, the interface simplification unit includes: an interface analysis module, used to analyze the number of clicks and dwell time of each area of ​​the device interface in the user's historical operation data, and output user operation behavior distribution data; a first processing module, used to process the user operation behavior distribution data using statistical analysis tools, and determine the correlation index between interface complexity and cognitive burden; an interface area location confirmation module, used to confirm the location of the target interface area based on the number of clicks and dwell time when the correlation index exceeds a preset correlation threshold; an interface element feature acquisition module, used to acquire the element distribution features in the target interface area and generate a complex quantification value; and a clustering partitioning module, used to partition the area using a preset clustering algorithm based on the complex quantification value, and obtain simplified interface structure data.

[0117] Optionally, the verification process reorganization unit includes: a verification process extraction module, used to extract the original information of the verification process from the simplified interface structure data to obtain the process structure distribution; a process structure decomposition module, used to divide the process structure distribution into multiple single-task units using a hierarchical decomposition strategy, and extract independent unit features from the single-task unit division results to generate a single-task unit set; a unit reorganization module, used to reorganize and adjust the single-task unit set using a preset sorting algorithm to obtain the reorganized process structure; a process structure optimization module, used to iteratively optimize the reorganized process structure when the total execution time of the reorganized process structure exceeds a preset time threshold, and use a preset clustering algorithm to divide the iteratively optimized process sequence results to generate a target verification process sequence; a process sequence feature extraction module, used to extract key features from the target verification process sequence and judge the process integrity based on the extracted key features; and a verification process sequence confirmation module, used to use the target verification process sequence as the reorganized verification process sequence when the judgment result indicates that the target verification process sequence meets the integrity requirements.

[0118] Optionally, the verification process reorganization unit further includes: a sequence order adjustment module, used to generate an initial data set based on the reorganized verification process sequence, adjust the sequence order using a preset embedding design strategy, and obtain reorganized sequence data; an operation instruction extraction module, used to extract operation instructions from the reorganized sequence data and generate a preliminary guidance framework; an operation instruction generation module, used to generate real-time operation guidance according to the preliminary guidance framework using preset dynamic prompt generation rules, and determine the correspondence between the real-time operation guidance and the reorganized sequence data; a verification process key information extraction module, used to extract key information from the verification process data when an incomplete correspondence is detected between the real-time operation guidance and the reorganized sequence data, and use the key information to adjust the verification process to obtain optimized verification process data; a guidance information clustering module, used to cluster the guidance information in the optimized verification process data using a preset clustering algorithm to generate segmented guidance data; a prompt generation rule extraction module, used to extract prompt generation rules from the segmented guidance data, use the prompt generation rules to generate target operation guidance, and confirm the target verification process data based on the target operation guidance; and a verification process integrity judgment module, used to verify the target verification process data through preset integrity judgment rules and generate identity verification process data with guidance information.

[0119] Optionally, the personalized verification step sequence generation unit includes: a user behavior data extraction module, used to extract user behavior data from the identity verification process data, and organize the extracted user behavior data into a structured behavior data set according to preset field mapping rules; a structured clustering module, used to perform cluster analysis on the structured behavior data set through preset clustering analysis strategies, dividing data with similar behavior patterns into the same group to obtain an individual difference feature set; and a principal component analysis module, used to calculate the variance contribution rate of each feature in the set using principal component analysis, and adjust the feature weights according to the contribution rate to obtain weighted feature data; The filtering module filters out data points in the weighted feature data that deviate from the mean by more than a predetermined standard deviation, retaining only valid feature data. The feature clustering module uses a preset clustering algorithm to divide the valid feature data into multiple categories, generating preliminary classification model data. The feature distribution pattern extraction module extracts the feature distribution patterns of each cluster center point from the preliminary classification model data, forming dynamic generation rules to obtain optimized user behavior classification data. The data matching and verification module verifies the matching degree between the optimized user behavior classification data and the original structured behavior data set, generating user behavior classification model data.

[0120] Optionally, the personalized verification step sequence generation unit further includes: a user habit preference judgment module, used to extract user behavior data from user behavior classification model data, and based on the extracted user behavior data, use a decision tree algorithm to locate user habit preferences and obtain personalized features; a verification step determination module, used to adjust preset rules according to personalized features, determine verification steps, generate a verification sequence according to the verification steps, and use data analysis tools to analyze the distribution characteristics of the verification sequence to obtain preliminary sequence data; and a judgment logic adjustment module, used to adjust the judgment logic when the preliminary sequence data matches the user behavior data, generate adjusted sequence data, and generate personalized verification step sequence data based on the adjusted sequence data.

[0121] Optionally, the identity authentication process adjustment device based on the self-service deposit and withdrawal device further includes: an operation time statistics unit, used to generate personalized verification step sequence data based on user behavior classification model data, and then use a timing tool to count the operation time to obtain the time statistics result. If the time statistics result exceeds a preset time threshold, a parallel processing algorithm is used to rearrange the execution order to obtain the adjusted sequence data; a personalized behavior feature extraction unit, used to generate time-optimized process data based on the adjusted sequence data, extract personalized behavior features from the time-optimized process data, and use a preset clustering algorithm to divide the behavior distribution to obtain user behavior classification data; and a time adjustment unit, used to adjust the verification step logic based on the user behavior classification data to generate time-optimized verification process data.

[0122] Optionally, the identity authentication process adjustment device based on self-service deposit and withdrawal equipment further includes: a potential vulnerability detection unit, used to detect potential vulnerabilities in the time-optimized verification process data after adjusting the verification step logic according to user behavior classification data and generating time-optimized verification process data, using a threat modeling strategy, and generating suspected vulnerability step distribution data; a risk point priority determination unit, used to extract key risk points from the suspected vulnerability step distribution data based on the potential vulnerabilities, determine the priority order of the key risk points, and adjust the execution order of the key risk points if the priority order exceeds a preset priority threshold, generating optimized process data; and a verification process hardening unit, used to detect behavior distribution based on the optimized process data, obtain dynamic change trend characteristics, adjust the verification process hardening strategy through the dynamic change trend characteristics, and generate security-hardened verification process data.

[0123] The aforementioned identity authentication process adjustment device based on self-service deposit and withdrawal equipment may also include a processor and a memory. The aforementioned interface simplification unit 31, verification process reorganization unit 32, personalized verification step sequence generation unit 33, verification process order adjustment unit 34, and multi-identity authentication script generation unit 35 are all stored in the memory as program units, and the processor executes the aforementioned program units stored in the memory to realize the corresponding functions.

[0124] The aforementioned processor contains a kernel, which retrieves the corresponding program units from memory. One or more kernels can be configured, and the authentication process for ATMs can be optimized by adjusting kernel parameters.

[0125] The aforementioned memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0126] Example 3

[0127] Embodiments of this application may provide an electronic device. Figure 4 This is a structural block diagram of an electronic device that executes an identity authentication process adjustment method based on a self-service deposit and withdrawal device, according to an embodiment of this application. Figure 4 As shown, the electronic device may include: one or more ( Figure 4 (Only one is shown) processor 402, memory 404, memory controller, and peripheral interface, wherein the peripheral interface is connected to the radio frequency module, audio module and display.

[0128] The memory can be used to store software programs and modules, such as the program instructions / modules corresponding to the identity authentication process adjustment method and device based on self-service deposit and withdrawal equipment in this application embodiment. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, thereby realizing the aforementioned identity authentication process adjustment method based on self-service deposit and withdrawal equipment. The memory may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include memory remotely located relative to the processor, and these remote memories can be connected to the terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0129] The processor can access information and applications stored in the memory via a transmission device to perform the following steps: acquire historical user operation data of the self-service deposit and withdrawal device; determine the target interface area based on the historical user operation data; generate simplified interface structure data based on the element distribution characteristics of the target interface area; the historical user operation data includes at least the number of clicks and dwell time in each area of ​​the device interface; adjust the identity verification process structure to be presented on the self-service deposit and withdrawal device based on the simplified interface structure data; generate a recombined verification process sequence; embed operation guidance in the recombined verification process sequence; generate identity verification process data with guidance information; extract user behavior data from the identity verification process data; identify individual differences through a preset clustering analysis strategy; generate user behavior classification model data; generate personalized verification step sequence data based on the user behavior classification model data; adjust the execution order of the identity verification process data based on the personalized verification step sequence data; analyze the adaptability of different user groups based on the adjusted identity verification process data; and generate a multi-identity authentication script.

[0130] Those skilled in the art will understand that Figure 4 The structure shown is for illustrative purposes only. Electronic devices can also be smartphones, tablets, handheld computers, mobile internet devices (MIDs), PADs, and other terminal devices. Figure 4 This does not limit the structure of the aforementioned electronic device. For example, electronic devices may also include components that are more... Figure 4 The more or fewer components shown (such as network interfaces, display devices, etc.), or having the same Figure 4 The different configurations shown.

[0131] Those skilled in the art will understand that all or part of the steps in the various identity authentication process adjustment methods based on self-service deposit and withdrawal devices in the above embodiments can be implemented by a program instructing the hardware related to the terminal device. The program can be stored in a computer-readable storage medium, which may include: flash drive, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0132] Example 4

[0133] Embodiments of this application also provide a storage medium. Optionally, in this embodiment, the storage medium can be used to store the program code executed by the identity authentication process adjustment method based on self-service deposit and withdrawal equipment provided in Embodiment 1.

[0134] According to another aspect of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored computer program, wherein, when the computer program is running, it controls the device where the computer-readable storage medium is located to execute the identity authentication process adjustment method based on any one of the above embodiments in the first embodiment.

[0135] Optionally, in this embodiment, the storage medium may be located in any computer terminal in a group of computer terminals in a computer network, or in any mobile terminal in a group of mobile terminals.

[0136] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the identity authentication process adjustment method based on self-service deposit and withdrawal equipment described in various embodiments of this application.

[0137] This application also provides a computer program product, including a non-volatile computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the identity authentication process adjustment method based on self-service deposit and withdrawal equipment described in various embodiments of this application.

[0138] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0139] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0140] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0141] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0142] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0143] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0144] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for adjusting the identity authentication process based on self-service deposit and withdrawal equipment, characterized in that, include: The system acquires historical user operation data of the self-service deposit and withdrawal device, determines the target interface area based on the historical user operation data, and generates simplified interface structure data based on the element distribution characteristics of the target interface area. The historical user operation data includes at least the number of clicks and dwell time of each area of ​​the device interface. Based on the simplified interface structure data, the identity verification process structure presented on the self-service deposit and withdrawal device is adjusted to generate a reorganized verification process sequence, and operation guidance is embedded in the reorganized verification process sequence to generate identity verification process data with guidance information. User behavior data is extracted from the identity verification process data, individual differences are identified through a preset clustering analysis strategy, user behavior classification model data is generated, and personalized verification step sequence data is generated based on the user behavior classification model data. Adjust the execution order of the identity verification process data based on the personalized verification step sequence data; Based on the data analysis of the adjusted identity verification process, adaptability to different user groups is analyzed to generate multi-identity authentication scripts.

2. The method according to claim 1, characterized in that, The steps of determining the target interface area based on the user's historical operation data and generating simplified interface structure data based on the element distribution characteristics of the target interface area include: Analyze the number of clicks and dwell time in each area of ​​the device interface from the user's historical operation data, and output user operation behavior distribution data; The user operation behavior distribution data was processed using statistical analysis tools to determine the correlation index between interface complexity and cognitive burden; If the correlation index exceeds a preset correlation threshold, the location of the target interface area is determined based on the number of clicks and the dwell time. Obtain the element distribution characteristics within the target interface area and generate complex quantification values; Based on the complex quantification value, a preset clustering algorithm is used to divide the region to obtain simplified interface structure data.

3. The method according to claim 1, characterized in that, Based on the simplified interface structure data, the steps for adjusting the identity verification process structure presented on the self-service deposit and withdrawal device and generating a reorganized verification process sequence include: The original information of the verification process is extracted from the simplified interface structure data to obtain the process structure distribution; The process structure is divided into multiple single-task units using a hierarchical decomposition strategy, and independent unit features are extracted from the single-task unit division results to generate a set of single-task units. The set of single task units is reorganized and adjusted using a preset sorting algorithm to obtain the reorganized process structure; If the total execution time of the reorganized process structure exceeds a preset time threshold, the reorganized process structure is iteratively optimized, and a preset clustering algorithm is used to divide the iteratively optimized process sequence results to generate a target verification process sequence. Key features are extracted from the target verification process sequence, and the integrity of the process is judged based on the extracted key features; If the judgment result indicates that the target verification process sequence meets the integrity requirements, the target verification process sequence shall be used as the recombined verification process sequence.

4. The method according to claim 1, characterized in that, The step of embedding operation instructions into the reorganized verification process sequence to generate authentication process data with guidance information includes: An initial data set is generated based on the recombined verification process sequence, and the sequence order is adjusted using a preset embedding design strategy to obtain the recombined sequence data; Operation instructions are extracted from the recombined sequence data to generate a preliminary bootstrapping framework; Based on the preliminary guidance framework, a real-time operation guide is generated using preset dynamic prompt generation rules, and the correspondence between the real-time operation guide and the recombinant sequence data is determined. If the correspondence between the real-time operation guidance and the recombinant sequence data is found to be incomplete, key information is extracted from the verification process data, and the verification process is adjusted using the key information to obtain optimized verification process data. For the optimized verification process data, a preset clustering algorithm is used to cluster the guidance information to generate segmented guidance data; Extract prompt generation rules from the segmented guidance data, use the prompt generation rules to generate target operation guidance, and confirm target verification process data based on the target operation guidance; The target verification process data is verified using preset integrity judgment rules to generate the identity verification process data with guidance information.

5. The method according to claim 1, characterized in that, The steps of extracting user behavior data from the identity verification process data, identifying individual differences through a preset clustering analysis strategy, and generating user behavior classification model data include: User behavior data is extracted from the authentication process data, and the extracted user behavior data is organized into a structured behavior data set according to the preset field mapping rules. By performing cluster analysis on the structured behavioral data set using a preset cluster analysis strategy, data with similar behavioral patterns are grouped into the same group to obtain a set of individual difference characteristics. For the set of individual differences in characteristics, principal component analysis is used to calculate the variance contribution rate of each characteristic in the set, and the weights of the characteristics are adjusted according to the contribution rate to obtain weighted feature data. If, during comparison, there are data points in the weighted feature data that deviate from the mean by more than a predetermined standard deviation multiple, the weighted feature data is filtered out, and the valid feature data is retained. The effective feature data is divided into multiple categories using a preset clustering algorithm to generate preliminary classification model data. The feature distribution patterns of each cluster center point are extracted from the preliminary classification model data to form dynamic generation rules, thereby obtaining optimized user behavior classification data. The optimized user behavior classification data is matched with the original structured behavior data set to verify the degree of matching, thereby generating the user behavior classification model data.

6. The method according to claim 1, characterized in that, The steps for generating personalized verification step sequence data based on the user behavior classification model data include: User behavior data is extracted from the user behavior classification model data. Based on the extracted user behavior data, a decision tree algorithm is used to locate user habit preferences and obtain personality characteristics. The preset rules are adjusted according to the individual characteristics to determine the verification steps, and a verification sequence is generated according to the verification steps. The distribution characteristics of the verification sequence are analyzed using data analysis tools to obtain preliminary sequence data. If the initial sequence data matches the user behavior data, the judgment logic is adjusted to generate adjusted sequence data, and the personalized verification step sequence data is generated based on the adjusted sequence data.

7. The method according to claim 1, characterized in that, After generating personalized verification step sequence data based on the user behavior classification model data, the method further includes: The operation time is counted by a timing tool to obtain the time consumption statistics. If the time consumption statistics exceed the preset time consumption threshold, the execution order is rearranged by a parallel processing algorithm to obtain the adjusted order data. Based on the adjusted sequence data, time-optimized process data is generated. Personalized behavioral features are extracted from the time-optimized process data, and a preset clustering algorithm is used to divide the behavioral distribution to obtain user behavior classification data. The verification step logic is adjusted based on the user behavior classification data to generate time-optimized verification process data.

8. The method according to claim 7, characterized in that, After adjusting the verification step logic based on the user behavior classification data and generating time-optimized verification process data, the process also includes: Threat modeling strategies are used to detect potential vulnerabilities in the time-optimized verification process data, and data on the distribution of suspected vulnerability stages are generated. Key risk points are extracted from the distribution data of the suspected vulnerability links, the priority order of the key risk points is determined, and if the priority order exceeds the preset priority threshold, the execution order of the key risk points is adjusted to generate optimized process data. Based on the optimized process data detection behavior distribution, dynamic change trend characteristics are obtained, and the verification process hardening strategy is adjusted according to the dynamic change trend characteristics to generate security-hardened verification process data.

9. A device for adjusting the identity authentication process based on a self-service deposit and withdrawal device, characterized in that, include: The interface simplification unit is used to acquire the user's historical operation data of the self-service deposit and withdrawal device, determine the target interface area based on the user's historical operation data, and generate simplified interface structure data based on the element distribution characteristics of the target interface area. The user's historical operation data includes at least the number of clicks and dwell time of each area of ​​the device interface. The verification process reorganization unit is used to adjust the identity verification process structure to be presented on the self-service deposit and withdrawal device based on the simplified interface structure data, generate a reorganized verification process sequence, embed operation guidance in the reorganized verification process sequence, and generate identity verification process data with guidance information. A personalized verification step sequence generation unit is used to extract user behavior data from the identity verification process data, identify individual differences through a preset clustering analysis strategy, generate user behavior classification model data, and generate personalized verification step sequence data based on the user behavior classification model data. A verification process sequence adjustment unit is used to adjust the execution order of the identity verification process data based on the personalized verification step sequence data. The multi-identity authentication script generation unit is used to generate multi-identity authentication scripts based on the data analysis of the adjusted identity verification process for different user groups.

10. An electronic device, characterized in that, It includes one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to implement the identity authentication process adjustment method based on any one of claims 1 to 8.

11. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the identity authentication process adjustment method based on any one of claims 1 to 8.

Images