Disk data management system and management method thereof

Abstract

The invention discloses a disk data management system and a management method thereof, and relates to the technical field of disk data management, and the method comprises the following steps: collecting operation behavior data of a user on disk data by using an operating system; constructing a deep learning model according to the operation behavior data, and analyzing and learning behavior characteristics of the user; dynamically adjusting a cache space strategy according to behavior characteristics and operation behavior data of the user; predicting user demands based on behavior characteristics of the user and formulating personalized cache space services; and establishing a feedback mechanism, and optimizing the deep learning model in real time according to user feedback and monitoring data. According to the method, personalized cache space services are formulated according to behavior characteristics of different users, and the experience of the users during use of the disk data management system can be greatly improved through rapid data access and personalized services according to actual requirements of the users and the running state of the system by dynamically adjusting a cache space strategy; therefore, the working efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of disk data management, in particular to a disk data management system and a management method thereof. Background Art

[0002] With the rapid development of information technology, disks, as a major data storage medium, have an increasing capacity and increasingly wide application scenarios. Traditional disk data management methods face many challenges. As users' demand for data access continues to increase, the read and write speed of disks has become a key factor affecting system performance. Traditional disk data management systems usually adopt fixed cache strategies and cannot dynamically adjust the cache space according to the actual needs of users, resulting in low data access efficiency when facing complex and changeable user operation behaviors. Different users have different operating habits and behavioral characteristics. Traditional disk data management systems are difficult to meet the personalized needs of users. Traditional disk data management systems cannot perform personalized cache space allocation and service formulation based on the behavioral characteristics of different users, thus affecting the user experience. At present, most disk data management systems still rely on traditional algorithms and rules, lacking in-depth analysis and learning capabilities of user behavior. In order to improve the management efficiency of disk data, meet the personalized needs of users, and give full play to the advantages of deep learning technology, it is necessary to develop a new type of disk data management system and its management method.

[0003] However, the common solutions currently available have many shortcomings, including: traditional cache space strategies usually rely on fixed rules and preset parameters, and cannot dynamically adjust the cache space according to the user's actual behavior and needs. The management of cache space is relatively extensive, which can easily lead to cache space waste and key data not being cached, thereby affecting data access efficiency; traditional systems lack the ability to accurately predict user needs and cannot prepare data that users may need in advance, resulting in users having to wait for a long time when accessing data. It is impossible to develop personalized cache space services based on users' personalized needs, and the service quality is relatively simple. Summary of the invention

[0004] The present invention is proposed in view of the fact that when managing cache space on the disk, the prior art cannot dynamically adjust the cache space according to the actual behavior and needs of the user, which easily leads to the waste of cache space and the failure of key data to be cached, thereby affecting the data access efficiency and other problems.

[0005] Therefore, the problem to be solved by the present invention is how to provide a method for dynamically adjusting the cache space strategy according to the user's behavior characteristics and operation behavior data, extending the service life of the disk, and improving data access efficiency.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In the first aspect, an embodiment of the present invention provides a disk data management method, which includes using an operating system to collect user operation behavior data on disk data; constructing a deep learning model based on the operation behavior data, and analyzing and learning the user's behavior characteristics; dynamically adjusting the cache space strategy based on the user's behavior characteristics and the operation behavior data; predicting user needs based on the user's behavior characteristics and formulating personalized cache space services; establishing a feedback mechanism to optimize the deep learning model in real time based on user feedback and monitoring data.

[0008] As a preferred solution of the disk data management method described in the present invention, the operation behavior data includes: opening, closing, reading, writing, copying and moving behaviors of files; the user's behavior characteristics include: file type preference, access frequency distribution, network access behavior and data storage location preference; the cache space strategy is to allocate resources for cache space.

[0009] As a preferred solution of the disk data management method of the present invention, the construction of the deep learning model includes the following steps: dividing the operation behavior data and generating user behavior labels; constructing a deep learning model based on a recurrent neural network RNN ​​and extracting user behavior features; further learning and analyzing the extracted user behavior features using an unsupervised learning method; evaluating the model and adjusting the model structure or parameters according to the evaluation results; the specific formula of the user behavior features is as follows:

[0010]

[0011] Among them, H t is the user behavior feature at time t; O(τ) is the user's operation data at time τ; D(τ) is the dynamic value of the data file feature; R(τ) is the user demand at time τ; e is the base of the natural logarithm.

[0012] As a preferred solution of the disk data management method of the present invention, the specific formula of the storage capacity is as follows:

[0013]

[0014] Among them, S is the storage capacity; B t is the operation behavior data at time t; F t is the data file feature at time t; U t is the user demand at time t; β is the minimum cache capacity of the system; α is the dynamic adjustment parameter; γ is the parameter of the control feedback mechanism; S t is the feedback value.

[0015] As a preferred solution of the disk data management method of the present invention, the dynamic adjustment of the cache space strategy includes the following steps: combining user behavior characteristics and operation behavior data to establish a comprehensive data set; formulating a machine learning algorithm based on the comprehensive data set to dynamically adjust the cache space strategy; determining the resource allocation of the cache space; formulating a real-time update mechanism for the cache space strategy and updating the cache space strategy in real time; the specific formula of the machine learning algorithm is as follows:

[0016]

[0017] Among them, S adaptive is the probability of dynamically adjusting the cache space strategy; α is the baseline adjustment probability; β is the influence coefficient of user behavior characteristics; N is the number of samples in the comprehensive data set; u i is the user behavior characteristics; i Operation behavior data.

[0018] As a preferred solution of the disk data management method of the present invention, the specific situation of the dynamic adjustment of the cache space strategy is as follows: if the probability S of the dynamic adjustment of the cache space strategy is adaptive If the probability S of dynamically adjusting the cache space strategy is greater than the first threshold, the system enters the active mode and frequently adjusts the cache space strategy according to the real-time data, increases the resource allocation of the cache space, and improves the processing speed and storage capacity. adaptive If the change in the operation behavior data is not greater than the first threshold, the system enters a stable mode, maintains a static strategy for the cache space, and does not make frequent adjustments. If the change in the operation behavior data is greater than the second threshold, the system enters an active mode, and flexibly adjusts the cache space strategy according to the new operation behavior data. If the change in the operation behavior data is not greater than the second threshold, the system enters a stable mode and remains relatively stable.

[0019] As a preferred solution of the disk data management method of the present invention, the specific formula of the real-time update cache space strategy is as follows:

[0020]

[0021] Among them, P is the probability of real-time update of cache space strategy; T is the running time of the system; λ is the exponential decay factor; if the probability P of real-time update of cache space strategy is greater than the third threshold, the system updates the cache space strategy in real time; if the probability P of real-time update of cache space strategy is not greater than the third threshold, the system adopts non-real-time update method.

[0022] In the second aspect, in order to further solve the above-mentioned technical problems, the embodiments of the present invention provide a disk data management system, which includes: a data acquisition module, which is used to collect user operation behavior data on disk data; a model building module, which is used to build a deep learning model based on the operation behavior data and analyze and learn the user's behavior characteristics; a strategy adjustment module, which is used to dynamically adjust the cache space strategy according to the user's behavior characteristics and operation behavior data; a service formulation module, which is used to predict user needs according to user behavior characteristics and formulate personalized cache space services; a feedback optimization module, which is used to optimize the deep learning model in real time according to user feedback and monitoring data.

[0023] In a third aspect, an embodiment of the present invention provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of a disk data management method as described in the first aspect of the present invention is implemented.

[0024] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of a disk data management method as described in the first aspect of the present invention is implemented.

[0025] The beneficial effects of the present invention are as follows: the present invention formulates personalized cache space services according to the behavioral characteristics of different users to meet the specific needs of users. By dynamically adjusting the cache space strategy, cache resources can be reasonably allocated according to the actual needs of users and the operating status of the system to avoid waste of resources. Through fast data access and personalized services, the user experience when using the disk data management system can be greatly improved, waiting time can be reduced, and work efficiency can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0027] Figure 1 This is a flow chart for implementing the present invention in Example 1. DETAILED DESCRIPTION

[0028] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0029] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0030] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0031] Example 1

[0032] Reference Figure 1 , which is the first embodiment of the present invention, provides a disk data management method, comprising the following steps:

[0033] S1: Use the operating system to collect user operation behavior data on disk data.

[0034] Preferably, Figure 1 The figure shows the implementation process of the present invention. First, the user's operation behavior data on disk data is collected through the operating system, a deep learning model is constructed based on the operation behavior data, and the user's behavior characteristics are analyzed and learned. The cache space strategy is dynamically adjusted according to the user's behavior characteristics and operation behavior data. Based on the user's behavior characteristics, user needs are predicted and personalized cache space services are formulated. A feedback mechanism is established to optimize the deep learning model in real time according to user feedback and monitoring data.

[0035] Furthermore, the operation behavior data includes: file opening, closing, reading, writing, copying and moving behaviors.

[0036] Specifically, the preprocessing process ensures the quality and consistency of the data by preprocessing the disk driving data and environmental data in real time on the edge node, including data cleaning, noise reduction, and standardization.

[0037] S2: Build a deep learning model based on disk driving data and analyze and learn user behavior characteristics.

[0038] Preferably, the user's behavioral characteristics include: file type preference, access frequency distribution, network access behavior, and data storage location preference.

[0039] Specifically, building a deep learning model includes the following steps:

[0040] Divide the operation behavior data and generate user behavior tags;

[0041] Build a deep learning model based on recurrent neural network (RNN) and extract user behavior features;

[0042] Use unsupervised learning methods to further learn and analyze the extracted user behavior features;

[0043] Evaluate the model and adjust the model structure or parameters based on the evaluation results;

[0044] Furthermore, the specific formula of user behavior characteristics is as follows:

[0045]

[0046] Among them, H t is the user behavior feature at time t; O(τ) is the user's operation data at time τ; D(τ) is the dynamic value of the data file feature; R(τ) is the user demand at time τ; e is the base of the natural logarithm.

[0047] S3: Dynamically adjust the cache space strategy based on user behavior characteristics and operation behavior data.

[0048] Preferably, the cache space strategy is to perform resource allocation of the cache space.

[0049] Specifically, the specific formula for storage capacity is as follows:

[0050]

[0051] Among them, S is the storage capacity; B t is the operation behavior data at time t; F t is the data file feature at time t; U t is the user demand at time t; β is the minimum cache capacity of the system; α is the dynamic adjustment parameter; γ is the parameter of the control feedback mechanism; S i is the feedback value.

[0052] Furthermore, dynamically adjusting the cache space strategy includes the following steps:

[0053] Combine user behavior characteristics and operational behavior data to create a comprehensive data set;

[0054] Develop machine learning algorithms based on comprehensive data sets and dynamically adjust cache space strategies;

[0055] Determine resource allocation for cache space;

[0056] Develop a real-time update mechanism for cache space strategy and update the cache space strategy in real time;

[0057] The specific formula of the machine learning algorithm is as follows:

[0058]

[0059] Among them, S adaptive is the probability of dynamically adjusting the cache space strategy; α is the baseline adjustment probability; β is the influence coefficient of user behavior characteristics; N is the number of samples in the comprehensive data set; u i is the user behavior characteristics; i Operation behavior data.

[0060] Furthermore, the specific situation of dynamically adjusting the cache space strategy is as follows:

[0061] If the probability S of dynamically adjusting the cache space strategy adaptive If the value is greater than the first threshold, the system enters the active mode, frequently adjusting the cache space strategy according to the real-time data, increasing the resource allocation of the cache space, and improving the processing speed and storage capacity;

[0062] If the probability S of dynamically adjusting the cache space strategy adaptive If the value is not greater than the first threshold, the system enters a stable mode, maintains a static strategy for the cache space, and does not make frequent adjustments;

[0063] If the change in the operation behavior data is greater than the second threshold, the system enters the active mode and flexibly adjusts the cache space strategy according to the new operation behavior data;

[0064] If the change in the operation behavior data is not greater than the second threshold, the system enters a stable mode and remains relatively stable.

[0065] Specifically, the specific formula for real-time update cache space strategy is as follows:

[0066]

[0067] Where P is the probability of real-time update of cache space strategy; T is the running time of the system; λ is the exponential decay factor;

[0068] If the probability P of real-time updating of the cache space strategy is greater than the third threshold, the system performs real-time updating of the cache space strategy;

[0069] If the probability P of real-time updating of the cache space strategy is not greater than the third threshold, the system adopts a non-real-time updating method.

[0070] S4: Predict user needs based on user behavior characteristics and develop personalized cache space services.

[0071] Preferably, the personalized cache space service includes: customized cache allocation, intelligent cache preloading and cache priority adjustment.

[0072] Specifically, by analyzing the user's behavioral characteristics, the user's future needs are predicted, and then personalized cache space services are customized. The services are updated in real time during the user's operation based on monitoring data to ensure the real-time and accuracy of the services.

[0073] S5: Establish a feedback mechanism to optimize the deep learning model in real time based on user feedback and monitoring data.

[0074] Specifically, optimizing the deep learning model includes the following steps: collecting user feedback data, including user satisfaction and demand change information.

[0075] Based on monitoring data and user feedback data, a real-time optimization mechanism for deep learning models is constructed using incremental learning algorithms.

[0076] Regularly review model performance and adjust the model's weights, structure, or hyperparameters based on user feedback and monitoring data to improve the model's accuracy and adaptability.

[0077] This embodiment also provides a disk data management system, including: a model building module, which is used to collect disk driving data and environmental data and build a deep learning model to analyze and learn user behavior characteristics; a strategy adjustment module, which is used to dynamically adjust the cache space strategy according to the user's behavior characteristics and environmental data and update the cache space strategy in real time; a service formulation module, which is used to predict user needs and formulate personalized services according to the user's behavior characteristics; a feedback optimization module, which is used to collect user feedback and real-time monitoring data and optimize the deep learning model.

[0078] This embodiment also provides a computer device, which is applicable to a disk data management method, including: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement a disk data management method as proposed in the above embodiment.

[0079] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0080] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, a disk data management method as proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0081] In summary, the present invention formulates personalized cache space services according to the behavioral characteristics of different users to meet the specific needs of users. By dynamically adjusting the cache space strategy, cache resources can be reasonably allocated according to the actual needs of users and the operating status of the system to avoid waste of resources. Through fast data access and personalized services, the user experience when using the disk data management system can be greatly enhanced, waiting time can be reduced, and work efficiency can be improved.

[0082] Example 2

[0083] Referring to Tables 1 to 3, the second embodiment of the present invention is shown. This embodiment is different from the first embodiment in that, in order to verify its beneficial effects, operating data and related instructions of the present invention in an actual environment are provided.

[0084] Table 1 shows a comparison of data access performance between the technology of the present invention and the prior art in this example.

[0085] Table 1 Data access performance comparison table

[0086]

[0087] Table 2 shows a comparison of the satisfaction of personalized services between the technology of the present invention and the prior art in this example.

[0088] Table 2 Comparison of personalized service satisfaction

[0089] Compare Projects Prior art The technology of the present invention Personalized service satisfaction (1-10 points) 5 8 Specific needs satisfaction (%) 60 90 Employees' recognition of personalized cache allocation (%) 65 95 Employee satisfaction with smart preloading service (%) 70 92

[0090] Table 3 shows a comparison of employee work efficiency and system performance between the technology of the present invention and the prior art in this example.

[0091] Table 3 Comparison of employee work efficiency and system performance

[0092] Compare Projects Prior art The technology of the present invention Improvement in employee work efficiency (%) 10 30 Reduction in system resource usage (%) 15 40 Data processing speed improvement (%) 20 50

[0093] It can be seen from the above table that the present invention demonstrates the creativity and novelty of de-emphasis in the embodiments, effectively solving the problems existing in the prior art such as high data access latency, low cache hit rate, insufficient personalized services, high system resource usage, etc., and greatly improving the efficiency of disk management and user experience.

[0094] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A disk data management method, characterized in that: include: Use the operating system to collect user operation behavior data on disk data; Building a deep learning model based on the operation behavior data, and analyzing and learning the user's behavior characteristics; Dynamically adjust the cache space strategy according to the user's behavior characteristics and the operation behavior data; Predict user needs based on the user's behavioral characteristics and develop personalized cache space services; A feedback mechanism is established to optimize the deep learning model in real time based on user feedback and monitoring data.

2. The disk data management method according to claim 1, characterized in that: The operation behavior data includes: opening, closing, reading, writing, copying and moving of files; The user's behavioral characteristics include: file type preference, access frequency distribution, network access behavior, and data storage location preference; The cache space strategy is to allocate resources of the cache space; The personalized cache space service includes: customized cache allocation, intelligent cache preloading and cache priority adjustment.

3. The disk data management method according to claim 2, characterized in that: The construction of the deep learning model includes the following steps: Dividing the operation behavior data and generating user behavior tags; Build a deep learning model based on recurrent neural network (RNN) and extract user behavior features; Use unsupervised learning methods to further learn and analyze the extracted user behavior features; Evaluate the model and adjust the model structure or parameters based on the evaluation results; The specific formula of the user behavior characteristics is as follows: Among them, H t is the user behavior feature at time t; O(τ) is the user's operation data at time τ; D(τ) is the dynamic value of the data file feature; R(τ) is the user demand at time τ; e is the base of the natural logarithm.

4. The disk data management method according to claim 3, characterized in that: The specific formula for the storage capacity is as follows: Among them, S is the storage capacity; B t is the operation behavior data at time t; F t is the data file feature at time t; U t is the user demand at time t; β is the minimum cache capacity of the system; α is the dynamic adjustment parameter; γ is the parameter of the control feedback mechanism; S t is the feedback value.

5. The disk data management method according to claim 4, characterized in that: The dynamic adjustment of the cache space strategy includes the following steps: Combine user behavior characteristics and operational behavior data to create a comprehensive data set; Formulate a machine learning algorithm based on the comprehensive data set to dynamically adjust the cache space strategy; Determine resource allocation for cache space; Develop a real-time update mechanism for cache space strategy and update the cache space strategy in real time; The specific formula of the machine learning algorithm is as follows: Among them, S adaptive is the probability of dynamically adjusting the cache space strategy; α is the baseline adjustment probability; β is the influence coefficient of user behavior characteristics; N is the number of samples in the comprehensive data set; u i is the user behavior characteristics; i Operation behavior data.

6. The disk data management method according to claim 5, characterized in that: The specific situation of dynamically adjusting the cache space strategy is as follows: If the probability S of dynamically adjusting the cache space strategy adaptive If the value is greater than the first threshold, the system enters the active mode, frequently adjusting the cache space strategy according to the real-time data, increasing the resource allocation of the cache space, and improving the processing speed and storage capacity; If the probability S of dynamically adjusting the cache space strategy adaptive If the value is not greater than the first threshold, the system enters a stable mode, maintains a static strategy for the cache space, and does not make frequent adjustments; If the change in the operation behavior data is greater than the second threshold, the system enters the active mode and flexibly adjusts the cache space strategy according to the new operation behavior data; If the change in the operation behavior data is not greater than the second threshold, the system enters a stable mode and remains relatively stable.

7. The disk data management method according to claim 6, characterized in that: The specific formula of the real-time update cache space strategy is as follows: Where P is the probability of real-time update of cache space strategy; T is the running time of the system; λ is the exponential decay factor; If the probability P of real-time updating of the cache space strategy is greater than the third threshold, the system performs real-time updating of the cache space strategy; If the probability P of real-time updating of the cache space strategy is not greater than the third threshold, the system adopts a non-real-time updating method.

8. A disk data management system, based on a disk data management method according to any one of claims 1 to 7, characterized in that: include, The data collection module is used to collect the user's operation behavior data on the disk data; Model building module, used to build deep learning models based on operation behavior data and analyze and learn user behavior characteristics; A policy adjustment module is used to dynamically adjust the cache space policy according to the user's behavior characteristics and operation behavior data; The service formulation module is used to predict user needs and formulate personalized cache space services based on user behavior characteristics; Feedback optimization module, used to optimize deep learning models in real time based on user feedback and monitoring data.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of a disk data management method described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of a disk data management method described in any one of claims 1 to 7 are implemented.

Images