Password resource scheduling method and system based on data access pattern prediction

Abstract

The application relates to the technical field of password resource scheduling, in particular to a password resource scheduling method and system based on data access mode prediction, which comprises the following steps: obtaining historical data access records and extracting data access mode features; constructing a prediction model based on the data access mode features, outputting a future data access demand prediction result through the prediction model; and scheduling password resources in a password resource pool and allocating adaptive password processing resources to a target data access request according to the future data access demand prediction result. Therefore, accurate allocation, dynamic scheduling and load balancing of password resources can be realized, and the security and efficiency of data access are guaranteed.

Description

Technical Field

[0001] This application relates to the field of cryptographic resource scheduling technology, and in particular to a cryptographic resource scheduling method and system based on data access pattern prediction. Background Technology

[0002] In the digital age, the frequency, concurrency, and security requirements of data access exhibit significant dynamic changes. Cryptographic resources, as the core support for ensuring data access security, are directly affected by the rationality of their scheduling, impacting response efficiency and security protection capabilities. Existing cryptographic resource scheduling technologies mostly employ static allocation or passive scheduling based on real-time load, resulting in the following technical shortcomings: Strongly arbitrary resource allocation: Existing technologies do not incorporate historical data access patterns for prediction, relying primarily on current load for resource allocation. This easily leads to insufficient cryptographic resource supply during peak periods and idle and wasted resources during off-peak periods, resulting in low resource utilization. Summary of the Invention

[0003] This application provides a cryptographic resource scheduling method and system based on data access pattern prediction, which can solve at least one of the technical problems in the background art to a certain extent.

[0004] To achieve the above objectives, this application adopts the following technical solution: Firstly, a cryptographic resource scheduling method based on data access pattern prediction is provided, including: Obtain historical data access records and extract data access pattern features; A prediction model is constructed based on the data access pattern characteristics, and the prediction model outputs the prediction results of future data access needs. Based on the predicted future data access demands, the cryptographic resources in the cryptographic resource pool are scheduled to allocate appropriate cryptographic processing resources for the target data access request.

[0005] Secondly, a cryptographic resource scheduling system based on data access pattern prediction is provided, comprising: The acquisition module is used to acquire historical data access records and extract data access pattern features; The output module is used to construct a prediction model based on the data access pattern characteristics, and output the prediction results of future data access needs through the prediction model; The scheduling module is used to schedule cryptographic resources in the cryptographic resource pool based on the predicted results of future data access needs, and allocate appropriate cryptographic processing resources to the target data access request.

[0006] Thirdly, embodiments of this application provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the cryptographic resource scheduling method based on data access pattern prediction as described in any one of the first aspects above.

[0007] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the cryptographic resource scheduling method based on data access pattern prediction as described in any one of the first aspects above.

[0008] Fifthly, embodiments of this application provide a computer program product that, when run on an electronic device, causes the electronic device to execute the cryptographic resource scheduling method based on data access pattern prediction as described in any of the first aspects.

[0009] It is understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant descriptions in the first aspect mentioned above, and will not be repeated here.

[0010] In this embodiment, historical data access records are first acquired, and data access pattern features are extracted. A prediction model is then constructed based on these features. The prediction model outputs a prediction result of future data access demands. Based on this prediction, cryptographic resources in the cryptographic resource pool are scheduled to allocate appropriate cryptographic processing resources to the target data access request. This achieves accurate prediction of future data access demands, provides a reliable basis for cryptographic resource scheduling, improves resource utilization, and constructs a scientific resource scheduling mechanism. Combined with load balancing strategies and differentiated priority rules, it ensures efficient response to high-priority, high-security-level data access requests.

[0011] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description

[0012] Various other advantages and benefits will become apparent to those skilled in the art upon reading the detailed description of the preferred embodiments below. The accompanying drawings are for illustrative purposes only and are not intended to limit the scope of this application. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings: Figure 1 This is a flowchart illustrating the cryptographic resource scheduling method based on data access pattern prediction provided in an embodiment of this application. Figure 2 This is a structural block diagram of the cryptographic resource scheduling system based on data access pattern prediction provided in the embodiments of this application; Figure 3 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0013] The embodiments of the technical solutions of this application will now be described in detail with reference to the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solutions of this application, and are therefore merely examples and should not be used to limit the scope of protection of this application. When the following description relates to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. Various changes, modifications, and equivalents of the methods, apparatus, and / or systems described herein will become apparent upon understanding this disclosure. For example, the order of operations described herein is merely illustrative and is not limited to those orders set forth herein, but can be changed as will become apparent upon understanding this disclosure, except for operations that must be performed in a specific order. Furthermore, for clarity and conciseness, descriptions of features known in the art may be omitted.

[0014] The embodiments described in the following examples of this disclosure are not representative of all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0015] It should be noted that this invention belongs to the field of hardware acceleration for array anti-interference algorithms and is applicable to scenarios such as satellite navigation and satellite communication. In this context, this invention first accumulates the signal autocorrelation matrix of the target frequency points using Fast Fourier Transform. It then significantly improves the real-time performance and parallelism of solving complex symmetric matrix equations by fine-grained parallelization of the Kolesky decomposition and equation iterative solution modules, and by using a resource-controllable pipeline to expand the core computational logic of both modules. Finally, the process of accumulating the autocorrelation matrix and solving the matrix equations is pipelined to reduce the algorithm latency caused by accumulating a large number of sampling points.

[0016] The executing entity of the cryptographic resource scheduling method based on data access pattern prediction in this embodiment can be a cryptographic resource scheduling system based on data access pattern prediction, but this application embodiment does not limit this.

[0017] See Figure 1 This is a flowchart illustrating the cryptographic resource scheduling method based on data access pattern prediction provided in the first embodiment of this application. Figure 1 As shown, the cryptographic resource scheduling method based on data access pattern prediction may include the following steps: Step 101: Obtain historical data access records and extract data access pattern features.

[0018] Optionally, historical data access records within a preset time period are obtained. These historical data access records include information such as access subject information, access time, access data type, access request strength, security level requirements, and response time. Data access pattern features are extracted from these historical data access records. These features include at least two of the following: data access frequency, access time distribution, access data type, access request strength, and access subject identifier. The feature dimensions can be expanded according to the actual business scenario to ensure that the features can comprehensively reflect the data access patterns.

[0019] Step 102: Construct a prediction model based on data access pattern characteristics, and output the prediction results of future data access needs through the prediction model.

[0020] Optionally, feature filtering and dimensionality reduction can be performed on the data access pattern features to obtain the target core features. The target core features are then divided into training sample sets, validation sample sets, and test sample sets according to time series. The time span of the sample sets covers peak and off-peak access periods. A hybrid model architecture that integrates time series prediction algorithms and attention mechanisms is adopted. The model is trained using the target core features as input and historical data access demands as labels to obtain an initial prediction model. The hyperparameters of the initial prediction model are adjusted using the validation sample set, and the prediction accuracy of the initial prediction model is verified using the test sample set. When the prediction error is lower than a preset threshold, the initial prediction model is determined as the prediction model. Based on the prediction model, the real-time features of the current data access pattern are input, and the prediction results of future data access demands within a preset time window are output. The prediction results of future data access demands include the number of access requests, peak concurrent access, proportion of high-security-level requests, and time series distribution.

[0021] Optionally, the data access pattern characteristics include at least two of the following: data access frequency, access time period distribution, access data type, access request intensity, and access subject identifier.

[0022] A prediction model is built based on the extracted data access pattern features. The prediction model outputs predictions of future data access needs, including: Specifically, feature selection and dimensionality reduction can be performed on data access pattern characteristics. Algorithms such as correlation analysis and principal component analysis (PCA) can be used to eliminate redundant and noisy features, retaining the core target features strongly correlated with data access needs. This reduces model training complexity and improves prediction efficiency. The core target features are divided into training, validation, and test sample sets according to time series. The time span of the sample sets must cover both peak access periods (such as weekday morning peaks and business promotion periods) and off-peak access periods (such as late nights and holidays) to ensure the completeness and representativeness of the sample sets. The training sample set should account for no less than 70%, while the proportions of the validation and test sample sets can be adjusted according to actual conditions. A hybrid model architecture integrating time series prediction algorithms and attention mechanisms is adopted. The core target features are used as input, and historical data access needs (such as the number of historical access requests and peak concurrency) are used as labels for model training to obtain the initial prediction model. The time series prediction algorithms include Long Short-Term Memory (LSTM) networks and Gated Recurrent Units (GRUs). Alternatively, a Temporal Convolutional Network (TCN) can be used to enhance the feature weights corresponding to key time periods and core access subjects through an attention mechanism, thereby improving the prediction model's ability to capture important access patterns. The hyperparameters of the initial prediction model (such as learning rate, number of iterations, number of hidden layer nodes, etc.) are adjusted through a validation sample set, and the prediction accuracy of the initial prediction model is verified using a test sample set. The prediction error is quantified and evaluated using mean absolute error (MAE) or root mean square error (RMSE). When the prediction error is lower than a preset threshold (such as preset MAE ≤ 5%), the initial prediction model is determined as the final prediction model used for prediction. Based on the prediction model, the real-time features of the current data access pattern (such as the current time period, real-time access frequency, etc.) are input, and the prediction results of future data access demand within a preset future time window are output. The prediction results of future data access demand include the number of access requests, peak concurrent access, proportion of high-security-level requests, and time series distribution. The preset future time window can be configured to 15 minutes, 30 minutes, 1 hour, or 2 hours, and the window granularity can be dynamically adjusted according to the business scenario.

[0023] Step 103: Based on the prediction results of future data access needs, schedule the cryptographic resources in the cryptographic resource pool and allocate suitable cryptographic processing resources for the target data access request.

[0024] Specifically, based on the predicted future data access demands, cryptographic resources in the cryptographic resource pool are scheduled to allocate appropriate cryptographic processing resources for the target data access request. This includes: Specifically, based on the predicted number of access requests, peak concurrent access, proportion of high-security requests, and time-series distribution from future data access demand forecasts, the required types of cryptographic resources (such as encryption / decryption computing resources, key management resources, access authentication resources, etc.), the required quantities, and their time-series distribution can be determined. This clarifies resource scheduling priorities for different time periods, obtains the current resource occupancy status of the cryptographic resource pool (including utilization rates of various types of cryptographic resources and idle resource quantities), resource performance parameters (including computing speed, concurrent processing capabilities, security encryption levels, response latency, etc.), and redundant resource reserves, ensuring a comprehensive understanding of the resource pool's status. Based on the cryptographic resource demand analysis results and the cryptographic resource pool's status assessment results, combined with load balancing strategies, a resource scheduling scheme is generated. This scheme includes resource allocation ratios, allocation sequences, dynamic expansion thresholds, idle resource release conditions, and differentiated allocation rules. Following the resource scheduling scheme, cryptographic resources in the cryptographic resource pool are scheduled, allocating suitable cryptographic processing resources to target data access requests. Pre-allocation, real-time allocation, dynamic migration, or elastic release operations of cryptographic resources are executed to ensure precise matching between resource supply and access demand.

[0025] Optionally, based on the prediction results of future data access needs, the demand type, demand quantity and time series distribution of cryptographic resources can be determined. According to the current resource occupancy status, resource performance parameters and load balancing strategy of the cryptographic resource pool, a resource scheduling scheme can be generated. According to the resource scheduling scheme, the cryptographic resources in the cryptographic resource pool can be scheduled to allocate suitable cryptographic processing resources for the target data access request.

[0026] Optionally, high-performance cryptographic resources can be allocated to high-priority data access requests first. When the cryptographic resource pool load exceeds a preset upper limit threshold, redundant cryptographic resources can be expanded or a low-priority request queuing mechanism can be initiated. When the cryptographic resource pool load falls below a preset lower limit threshold, idle cryptographic resources can be released.

[0027] Optionally, the actual execution status of data access requests and the running status of cryptographic resources can be monitored in real time, and the prediction results of future data access needs can be corrected based on the actual execution status and the running status of cryptographic resources.

[0028] Optionally, it can also monitor in real time the actual execution status of data access requests (including the number of actual access requests, peak concurrent access, proportion of high-security level requests, actual response time, etc.) and the operating status of cryptographic resources (including resource utilization, response latency, fault alarms, resource consumption, etc.). Based on the actual execution status and the operating status of cryptographic resources, it calculates the deviation between the actual access status and the prediction results. When the deviation exceeds a preset deviation threshold (e.g., deviation ≥ 10%), it analyzes the causes of the deviation (e.g., sudden changes in access patterns, aging of model parameters, etc.), corrects the feature weights of data access patterns based on the causes of the deviation, performs online iterative optimization of the prediction model, improves the model prediction accuracy, and dynamically adjusts the resource scheduling scheme according to the optimized prediction results and resource operating status to ensure that the supply of cryptographic resources matches the actual access demand in real time, and ensures the rationality and efficiency of resource scheduling.

[0029] Furthermore, load balancing strategies include: Prioritize the allocation of high-performance cryptographic resources (such as hardware cryptographic modules, HSM) to high-priority data access requests (such as financial transaction data access and government core data access). Low-priority requests can be allocated software cryptographic services or virtual cryptographic node resources. When the cryptographic resource pool load exceeds the preset upper limit threshold (such as load rate ≥ 80%), the redundant cryptographic resource expansion or elastic cloud cryptographic node access mechanism is activated to quickly improve resource processing capacity and avoid resource shortages during peak periods. When the cryptographic resource pool load is lower than the preset lower limit threshold (such as load rate ≤ 30%), cryptographic resources that have been idle for more than the preset time (such as idle for more than 30 minutes) are released to reduce energy consumption and resource loss and improve the overall resource utilization rate.

[0030] In this embodiment, historical data access records are first acquired, and data access pattern features are extracted. A prediction model is then constructed based on these features. The prediction model outputs a prediction result of future data access demands. Based on this prediction, cryptographic resources in the cryptographic resource pool are scheduled to allocate appropriate cryptographic processing resources to the target data access request. This achieves accurate prediction of future data access demands, provides a reliable basis for cryptographic resource scheduling, improves resource utilization, and constructs a scientific resource scheduling mechanism. Combined with load balancing strategies and differentiated priority rules, it ensures efficient response to high-priority, high-security-level data access requests.

[0031] This invention extracts multi-dimensional data access pattern features and constructs a high-precision prediction model that integrates time-series prediction algorithms and attention mechanisms to accurately predict future data access needs. By combining load balancing strategies and differentiated scheduling rules, it achieves dynamic and efficient scheduling of cryptographic resources, effectively improving resource utilization and data access response efficiency. Through real-time monitoring and adaptive optimization mechanisms, it can quickly adapt to changes in data access patterns, ensuring that resource scheduling matches actual needs in real time.

[0032] This invention addresses the shortcomings of existing cryptographic resource scheduling technologies, such as low resource utilization, insufficient prediction accuracy, poor load balancing, and lack of adaptive capabilities. It is suitable for data access needs in multiple scenarios, including finance, government affairs, and cloud computing. It can provide reliable cryptographic resource support for high-priority and high-security data access requests, ensuring the security and efficiency of data access. It has significant technical, application, and commercial value.

[0033] Corresponding to the cryptographic resource scheduling method based on data access pattern prediction in the above embodiments, Figure 2 This is a structural block diagram of a cryptographic resource scheduling system based on data access pattern prediction provided in an embodiment of this application.

[0034] Reference Figure 2 The cryptographic resource scheduling system 200 based on data access pattern prediction includes: The acquisition module 210 is used to acquire historical data access records and extract data access pattern features; Output module 220 is used to construct a prediction model based on the data access pattern characteristics, and output the prediction result of future data access demand through the prediction model; The scheduling module 230 is used to schedule cryptographic resources in the cryptographic resource pool according to the prediction results of future data access needs, and allocate appropriate cryptographic processing resources for the target data access request.

[0035] Optionally, the output module is specifically used for: The data access pattern features are subjected to feature filtering and dimensionality reduction processing to obtain the target core features; The target core features are divided into training sample sets, validation sample sets, and test sample sets according to time series, and the time span of the sample sets covers peak access periods and off-peak access periods; A hybrid model architecture that integrates temporal prediction algorithms and attention mechanisms is adopted. The model is trained with the core features of the target as input and historical data access requirements as labels to obtain an initial prediction model. The hyperparameters of the initial prediction model are adjusted using the validation sample set, and the prediction accuracy of the initial prediction model is verified using the test sample set. When the prediction error is lower than a preset threshold, the initial prediction model is determined to be the prediction model. Based on the prediction model, the real-time characteristics of the current data access mode are input, and the prediction results of future data access demand within a preset time window are output. The prediction results of future data access demand include the number of access requests, peak concurrent access, proportion of high security level requests, and time series distribution.

[0036] Optionally, the data access pattern features include at least two of the following: data access frequency, access time period distribution, access data type, access request intensity, and access subject identifier.

[0037] Optionally, the scheduling module is specifically used for: Based on the predicted future data access needs, the demand types, demand quantities, and time-series distribution of cryptographic resources are determined. Based on the current resource occupancy status, resource performance parameters, and load balancing strategy of the cryptographic resource pool, a resource scheduling scheme is generated; According to the resource scheduling scheme, the cryptographic resources in the cryptographic resource pool are scheduled to allocate appropriate cryptographic processing resources for the target data access request.

[0038] In this embodiment, historical data access records are first acquired, and data access pattern features are extracted. A prediction model is then constructed based on these features. The prediction model outputs a prediction result of future data access demands. Based on this prediction, cryptographic resources in the cryptographic resource pool are scheduled to allocate appropriate cryptographic processing resources to the target data access request. This achieves accurate prediction of future data access demands, provides a reliable basis for cryptographic resource scheduling, improves resource utilization, and constructs a scientific resource scheduling mechanism. Combined with load balancing strategies and differentiated priority rules, it ensures efficient response to high-priority, high-security-level data access requests.

[0039] in addition, Figure 2 The cryptographic resource scheduling system based on data access pattern prediction shown can be a software unit, a hardware unit, or a combination of software and hardware built into an existing electronic device. It can also be integrated into the electronic device as an independent component, or exist as an independent electronic device.

[0040] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments 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. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0041] Figure 3 This is a schematic diagram of the structure of the electronic device provided in an embodiment of this application. For example... Figure 3 As shown, the electronic device 5 of this embodiment includes: at least one processor 50 ( Figure 3 (Only one is shown in the diagram) a processor, a memory 51, and a computer program 52 stored in the memory 51 and executable on the at least one processor 50, wherein the processor 50 executes the computer program 52 to implement the steps in any of the above embodiments of the cryptographic resource scheduling method based on data access pattern prediction.

[0042] The electronic device may be a desktop computer, laptop, handheld computer, or cloud server, etc. This electronic device may include, but is not limited to, a processor and memory. Those skilled in the art will understand that... Figure 3 This is merely an example of electronic device 5 and does not constitute a limitation on electronic device 5. It may include more or fewer components than shown in the figure, or combine certain components, or different components. For example, it may also include input / output devices, network access devices, etc.

[0043] The processor 50 may be a central processing unit, or it may be other general-purpose processors, digital signal processors, application-specific integrated circuits, off-the-shelf programmable gate arrays or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0044] In some embodiments, the memory 51 may be an internal storage unit of the electronic device 5, such as a hard disk or memory of the electronic device 5. In other embodiments, the memory 51 may be an external storage device of the electronic device 5, such as a plug-in hard disk, smart memory card, secure digital card, flash memory card, etc., equipped on the electronic device 5. Further, the memory 51 may include both internal storage units and external storage devices of the electronic device 5. The memory 51 is used to store operating systems, applications, boot loaders, data, and other programs, such as the program code of the computer program. The memory 51 can also be used to temporarily store data that has been output or will be output.

[0045] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, can implement the steps in the above-described method embodiments.

[0046] This application provides a computer program product that, when run on an electronic device, enables the electronic device to implement the steps described in the various method embodiments above.

[0047] If the integrated unit is implemented as a software functional unit and used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include at least: any entity or device capable of carrying computer program code to a device / electronic device, a recording medium, a computer memory, a read-only memory, a random access memory, an electrical carrier signal, a telecommunication signal, and a software distribution medium. Examples include USB flash drives, portable hard drives, magnetic disks, or optical disks.

[0048] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0049] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0050] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the application; the terms “comprising” and “having”, and any variations thereof, in the specification, claims, and foregoing description of the drawings are intended to cover non-exclusive inclusion.

[0051] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0052] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A cryptographic resource scheduling method based on data access pattern prediction, characterized in that, include: Obtain historical data access records and extract data access pattern features; A prediction model is constructed based on the data access pattern characteristics, and the prediction model outputs the prediction results of future data access needs. Based on the predicted future data access demands, the cryptographic resources in the cryptographic resource pool are scheduled to allocate appropriate cryptographic processing resources for the target data access request.

2. The method according to claim 1, characterized in that, The step of constructing a prediction model based on the data access pattern characteristics, and outputting a prediction result of future data access needs through the prediction model, includes: The data access pattern features are subjected to feature filtering and dimensionality reduction processing to obtain the target core features; The target core features are divided into training sample sets, validation sample sets, and test sample sets according to time series, and the time span of the sample sets covers peak access periods and off-peak access periods; A hybrid model architecture that integrates temporal prediction algorithms and attention mechanisms is adopted. The model is trained with the core features of the target as input and historical data access requirements as labels to obtain an initial prediction model. The hyperparameters of the initial prediction model are adjusted using the validation sample set, and the prediction accuracy of the initial prediction model is verified using the test sample set. When the prediction error is lower than a preset threshold, the initial prediction model is determined to be the prediction model. Based on the prediction model, the real-time characteristics of the current data access mode are input, and the prediction results of future data access demand within a preset time window are output. The prediction results of future data access demand include the number of access requests, peak concurrent access, proportion of high security level requests, and time series distribution.

3. The method according to claim 2, characterized in that, The data access pattern features include at least two of the following: data access frequency, access time period distribution, access data type, access request intensity, and access subject identifier.

4. The method according to claim 1, characterized in that, The step of scheduling cryptographic resources in the cryptographic resource pool based on the predicted future data access demands, and allocating suitable cryptographic processing resources for the target data access request, includes: Based on the predicted future data access needs, the demand types, demand quantities, and time-series distribution of cryptographic resources are determined. Based on the current resource occupancy status, resource performance parameters, and load balancing strategy of the cryptographic resource pool, a resource scheduling scheme is generated; According to the resource scheduling scheme, the cryptographic resources in the cryptographic resource pool are scheduled to allocate appropriate cryptographic processing resources for the target data access request.

5. The method according to claim 4, characterized in that, The load balancing strategy includes: Prioritize allocating high-performance cryptographic resources to high-priority data access requests; When the load of the cryptographic resource pool exceeds the preset upper limit threshold, a redundant cryptographic resource expansion or low-priority request queuing mechanism is activated. When the load of the cryptographic resource pool is lower than a preset lower threshold, idle cryptographic resources are released.

6. The method according to claim 1, characterized in that, The method further includes: Real-time monitoring of the actual execution status of data access requests and the operational status of cryptographic resources; Based on the actual execution status and the operating status of the cryptographic resources, the prediction results of future data access needs are revised.

7. A cryptographic resource scheduling system based on data access pattern prediction, characterized in that, include: The acquisition module is used to acquire historical data access records and extract data access pattern features; The output module is used to construct a prediction model based on the data access pattern characteristics, and output the prediction results of future data access needs through the prediction model; The scheduling module is used to schedule cryptographic resources in the cryptographic resource pool based on the predicted results of future data access needs, and allocate appropriate cryptographic processing resources to the target data access request.

8. The system according to claim 7, characterized in that, The output module is specifically used for: The data access pattern features are subjected to feature filtering and dimensionality reduction processing to obtain the target core features; The target core features are divided into training sample sets, validation sample sets, and test sample sets according to time series, and the time span of the sample sets covers peak access periods and off-peak access periods; A hybrid model architecture that integrates temporal prediction algorithms and attention mechanisms is adopted. The model is trained with the core features of the target as input and historical data access requirements as labels to obtain an initial prediction model. The hyperparameters of the initial prediction model are adjusted using the validation sample set, and the prediction accuracy of the initial prediction model is verified using the test sample set. When the prediction error is lower than a preset threshold, the initial prediction model is determined to be the prediction model. Based on the prediction model, the real-time characteristics of the current data access mode are input, and the prediction results of future data access demand within a preset time window are output. The prediction results of future data access demand include the number of access requests, peak concurrent access, proportion of high security level requests, and time series distribution.

9. The method according to claim 8, characterized in that, The data access pattern features include at least two of the following: data access frequency, access time period distribution, access data type, access request intensity, and access subject identifier.

10. The method according to claim 7, characterized in that, The scheduling module is specifically used for: Based on the predicted future data access needs, the demand types, demand quantities, and time-series distribution of cryptographic resources are determined. Based on the current resource occupancy status, resource performance parameters, and load balancing strategy of the cryptographic resource pool, a resource scheduling scheme is generated; According to the resource scheduling scheme, the cryptographic resources in the cryptographic resource pool are scheduled to allocate appropriate cryptographic processing resources for the target data access request.

Images