Cloud data management method and system based on machine learning, electronic equipment and medium

Abstract

The invention discloses a cloud data management method and system based on machine learning, electronic equipment and a medium. The method comprises the following steps: acquiring application programming interfaces of various cloud storage platforms of an enterprise; then obtaining query request data and authority data of enterprise employees; according to the query request data and the authority data, performing data request on the application programming interface by adopting a leaky bucket algorithm and an intelligent frequency control mode to obtain first cloud data; and on the basis of a machine learning model, preprocessing the cloud data to obtain second cloud data, and sending the second cloud data to the enterprise employees. Compared with the prior art, the method and the device have the following effects that various cloud storage platforms are uniformly managed, so that the cloud data files on the various cloud storage platforms are effectively integrated, the complicated steps of acquiring the cloud data by a user are simplified, the use efficiency of the cloud data is improved, and the user experience is improved. And the user experience is improved.

Description

Technical Field

[0001] The present invention relates to the field of machine learning technology, and in particular to a cloud data management method, system, electronic device and medium based on machine learning. Background Art

[0002] With the in-depth development of cloud computing and digital transformation, enterprises are increasingly storing cloud data such as documents, data and other knowledge assets on various cloud platforms in order to improve collaboration efficiency and resource flexibility. These cloud platforms, such as Feishu, WeChat for Enterprise, Google Drive, OneDrive, etc., provide enterprises with convenient access and sharing functions.

[0003] However, since data between different cloud platforms is often difficult to transmit and share directly, enterprises are unable to effectively integrate data between different platforms, which makes it difficult for enterprises to manage and use these cloud data files. Summary of the invention

[0004] The purpose of the present invention is to provide a cloud data management method, system, electronic device and medium based on machine learning to solve the problems in related technologies such as difficulty in managing multiple storage cloud platforms, inconsistent security and low data utilization efficiency when enterprises use multiple storage cloud platforms.

[0005] In order to achieve the above object, the present invention provides the following technical solutions: A first aspect: The present invention provides a cloud data management method based on machine learning, comprising: Obtain application programming interfaces of various cloud storage platforms of the enterprise; obtain query request data and permission data of enterprise employees; based on the query request data and permission data, use a leaky bucket algorithm and intelligent frequency control method to request data from the application programming interface to obtain first cloud data; pre-process the cloud data based on a machine learning model to obtain second cloud data, and send the second cloud data to the enterprise employees.

[0006] Preferably, the method further includes: judging whether risk data exists in the second cloud data according to preset rules; if risk data exists, forming a risk data document and sending it to relevant personnel of the enterprise; if risk data does not exist, sending the second cloud data to the enterprise employees.

[0007] Preferably, the determining whether there is risk data in the second cloud data according to preset rules includes: determining whether the second cloud data includes: commercial confidential data, amount data, unmasked passwords and keys; if so, there is risk data in the second cloud data; if not, there is no risk data in the second cloud data.

[0008] Preferably, the obtaining of the query request data and authority data of the enterprise employee includes: An analysis model is used to analyze the query data of enterprise employees to determine whether there is abnormal request data in the query data of the enterprise employees. If not, the query request data of the enterprise employees is obtained; based on the user role and operation frequency of the enterprise employees, the permission data of the enterprise employees is obtained.

[0009] Preferably, the leaky bucket algorithm and intelligent frequency control are used to request data from the application programming interface to obtain corresponding cloud data, including: Acquire various application programming interface requests in real time, prioritize the various application programming interface requests according to preset rules, and control the request rate of various application programming interface requests based on the leaky bucket algorithm; monitor the response and load status of various application programming interfaces in real time, and dynamically adjust the request frequency of various application programming interface requests according to the response and load status; request data for the various application programming interfaces based on the request rate and the request frequency to obtain corresponding cloud data.

[0010] Preferably, the method further comprises: if a request failure occurs in the application programming interface, an error handling and retry mechanism is triggered.

[0011] Preferably, the model based on the machine learning pre-processes the first cloud data to obtain the second cloud data, including: using natural language processing technology to perform semantic analysis and content extraction on the first cloud data to obtain the first cloud data with content tags; using a machine learning classification algorithm to classify the first cloud data with content tags to obtain the second cloud data.

[0012] Second aspect: The present invention also provides a cloud data management system based on machine learning, comprising: The first acquisition module is used to obtain the application programming interface of various cloud storage platforms of the enterprise; the second acquisition module is used to obtain the query request data and permission data of the enterprise employees; the data query module is used to request data from the application programming interface based on the query request data and permission data, using a leaky bucket algorithm and intelligent frequency control method to obtain first cloud data; the data processing module is used to pre-process the cloud data based on a machine learning model to obtain second cloud data, and send the second cloud data to the enterprise employees.

[0013] A third aspect: The present invention also provides a computer electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any one of the above-mentioned cloud data management methods based on machine learning when executing the computer program.

[0014] Aspect 4: The present invention also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps of any one of the above-mentioned cloud data management methods based on machine learning are implemented.

[0015] The present invention provides a cloud data management method, system, electronic device and medium based on machine learning. The management method obtains the application programming interface of various cloud storage platforms of the enterprise; obtains the query request data and permission data of the enterprise employees; according to the query request data and permission data, uses the leaky bucket algorithm and intelligent frequency control method to request data from the application programming interface to obtain first cloud data; based on the machine learning model, pre-processes the cloud data to obtain second cloud data, and sends the second cloud data to the enterprise employees. Compared with the related art, the present invention has the following effects: the present invention manages various cloud storage platforms in a unified manner, thereby achieving effective integration of cloud data files on various cloud storage platforms, while simplifying the complicated steps for users to obtain cloud data, it also improves the efficiency of using cloud data and enhances the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a flowchart of a cloud data management method based on machine learning according to an embodiment of the present invention; Figure 2 It is a structural diagram of a cloud data management system based on machine learning according to an embodiment of the present invention; Figure 3 It is a structural schematic diagram of a computer electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0018] It should be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be a central element. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be a central element at the same time. In contrast, when an element is referred to as being "directly on" another element, there is no intermediate element. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are for illustrative purposes only.

[0019] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0020] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0021] The terms used in one or more embodiments of the present invention are only for the purpose of describing specific embodiments, and are not intended to limit one or more embodiments of the present invention. The singular forms "a", "said" and "the" used in one or more embodiments of the present invention are also intended to include plural forms, unless the context clearly indicates other meanings.

[0022] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein in the specification of the template are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more of the associated listed items.

[0023] It should be understood that, although the terms first, second, etc. may be used to describe various types of information in one or more embodiments of the present invention, such information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of one or more embodiments of the present invention, the first may also be referred to as the second, and similarly, the second may also be referred to as the first. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when the time of".

[0024] At present, when enterprises use multiple storage cloud platforms to store data, they usually face the following problems because data between different cloud storage platforms cannot be directly transmitted and shared: 1. Documents are scattered and difficult to manage: Enterprise cloud documents are distributed on multiple platforms. Due to the lack of unified management tools, data between different platforms cannot be effectively integrated. This dispersion makes document retrieval difficult and increases the time cost for employees to find and use documents. In addition, the complexity of permission management, data redundancy, and security risks also increase, making it difficult for enterprises to conduct efficient document management.

[0025] 2. Lack of unified security and permission management: The security policies and permission management of each cloud platform are independent of each other, lacking standardization and interoperability, and enterprises cannot achieve overall protection of all intellectual assets. This decentralized security architecture not only increases the risk of data leakage, but also easily leads to permission abuse, which may cause major security incidents in serious cases, causing immeasurable losses to enterprises.

[0026] 3. Low data utilization efficiency: Existing cloud platforms mainly focus on storage and sharing functions, and lack the ability to deeply analyze stored document data. Enterprises are usually unable to quickly and effectively extract valuable information from a large number of cloud documents for decision support, resulting in low data utilization efficiency. In addition, existing management tools generally lack intelligent and automated analysis capabilities and cannot help enterprises obtain higher value in knowledge asset management.

[0027] Please refer to Figure 1 , a cloud data management method based on machine learning provided by an embodiment of the present invention is applied to a cloud data management system and comprises at least the following steps: S10. Obtain the application programming interfaces of various cloud storage platforms of the enterprise.

[0028] It is understandable that, generally speaking, enterprises will store various file data on multiple cloud storage platforms. These data are collectively referred to as cloud data. In this embodiment, it is first necessary to obtain the application programming interfaces corresponding to all cloud storage platforms in the enterprise, and then information can be exchanged with the corresponding cloud storage platforms through these application programming interfaces.

[0029] It should be noted that application programming interface (API) is a set of predefined functions in software development, which aims to provide applications and developers with the ability to access a set of routines based on certain software or hardware without accessing the source code or understanding the details of the internal working mechanism.

[0030] S20. Obtain query request data and authority data of enterprise employees.

[0031] Specifically, enterprises can log in to the cloud data management system through their own accounts. In the cloud data management system, they can enter the data that needs to be queried. The backend of the cloud data management system will receive the user's query request data and permission data.

[0032] It should be noted that in order to solve the problem that it is inconvenient for enterprise users to log in to various cloud storage platforms across platforms through the cloud data management system, a unified identity authentication function module can be built in the cloud data management system to improve the security of the system and user experience, as follows: SSO integration: Integrate the single sign-on system of multiple platforms to simplify the user login process through a unified authentication mechanism, thereby improving security and management efficiency.

[0033] OAuth and SAML support: Supports OAuth 2.0 and SAML protocols to achieve unified management of identity authentication and authorization on different platforms.

[0034] S30. According to the query request data and the authority data, a leaky bucket algorithm and an intelligent frequency control method are used to request data from the application programming interface to obtain first cloud data.

[0035] Specifically, when the cloud data management system receives the query request data and permission data from the enterprise employees, it will request data from various cloud storage platforms through the application programming interface based on these contents. Since the restrictions of the cloud storage platform may be triggered when data is quickly requested across platforms through the application programming interface, in this embodiment, in order to solve the problem of excessive frequency of cross-platform document pulling, this embodiment combines the leaky bucket algorithm with the intelligent frequency control mechanism to achieve dynamic optimization of cross-platform document pulling requests to avoid triggering platform restrictions due to excessive request frequency.

[0036] In some optional embodiments, the leaky bucket algorithm can also be changed to an enhanced leaky bucket algorithm, that is, based on the existing leaky bucket algorithm, an adaptive adjustment mechanism can be introduced, combined with machine learning technology, to dynamically optimize the leaky bucket parameters according to the actual load and access restrictions of different cloud platforms. Specifically: Adaptive leaky bucket: Design an adaptive leaky bucket model to dynamically adjust the leaky bucket capacity and water release rate according to real-time traffic and platform restrictions. Intelligent prediction: Combine historical data and trend prediction algorithms to adjust the request frequency in advance to avoid request conflicts during peak periods.

[0037] It should be noted that in order to prevent the leakage of document data information, cloud data can be encrypted by encryption algorithm during cloud data transmission, and data privacy protection and compliance management are handled as follows: Data encryption: Advanced encryption technologies (such as AES-256 and RSA) are used to encrypt and protect data. Encryption algorithms are used during data storage and transmission to ensure data security and privacy.

[0038] Compliance audit: Integrate compliance audit tools (such as AWS CloudTrail, Azure SecurityCenter), automate the audit data processing process, and generate compliance reports that comply with local laws and regulations. The system provides compliance checking and reporting functions to ensure that data management complies with relevant legal requirements.

[0039] Privacy protection: Implement privacy protection measures (such as Data Masking, Access Controls) and use strict access control policies to protect sensitive data. The system sets data access rights and privacy protection measures according to privacy protection regulations to ensure data security and compliance.

[0040] In a specific embodiment, the privacy protection of cloud data can be further enhanced according to the data protection regulations of different regions, for example, by using blockchain technology and dynamic privacy settings, as follows: blockchain technology is used to record and audit data transactions to ensure that data operations cannot be tampered with and are transparent. Dynamic privacy setting options are provided to adjust the data privacy level according to user needs and regulatory requirements.

[0041] S40. Preprocess the first cloud data based on a machine learning model to obtain second cloud data, and send the second cloud data to the enterprise employees.

[0042] In some optional embodiments, step S40, preprocessing the first cloud data based on the machine learning model to obtain the second cloud data, includes: S41, using natural language processing technology to perform semantic analysis and content extraction on the first cloud data to obtain first cloud data with content tags; S42: Use a machine learning classification algorithm to classify the first cloud data with the content tag to obtain second cloud data, and send the second cloud data to the enterprise employees.

[0043] Specifically, after obtaining the first cloud data, the cloud data management system will perform some preprocessing operations on the data, such as classifying and labeling the first cloud data to obtain the second cloud data, so that the second cloud data is more readable than the first cloud data and is more conducive to user reading.

[0044] In a specific embodiment, the first cloud data is pre-processed as follows: 1. NLP processing: Use natural language processing technology (such as BERT, GPT-4) to perform semantic analysis and content extraction on multi-platform documents. The system can identify key information in documents, extract features and generate structured data.

[0045] 2. Machine learning classification: Use machine learning classification algorithms (such as Support Vector Machine, SVM; Decision Trees; Neural Networks) to classify and annotate documents and build a knowledge graph. The system generates intelligent indexes and related information of documents through classification and annotation.

[0046] 3. Content recommendation: Use recommendation algorithms (such as Collaborative Filtering and Content-Based Filtering) to provide intelligent recommendations based on user needs and document content. The system can generate personalized content summaries and recommendation lists based on user historical behavior and document features, improving information retrieval efficiency and decision support capabilities.

[0047] The present application provides a cloud data management method based on machine learning. The management method obtains the application programming interface of various cloud storage platforms of the enterprise; then obtains the query request data and permission data of the enterprise employees; based on the query request data and permission data, the leaky bucket algorithm and intelligent frequency control method are used to request data from the application programming interface to obtain the first cloud data; based on the machine learning model, the cloud data is preprocessed to obtain the second cloud data, and the second cloud data is sent to the enterprise employees. Compared with the related art, the present invention has the following effects: the present invention realizes the effective integration of cloud data files on various cloud storage platforms by unifying the management of various cloud storage platforms, which simplifies the complicated steps for users to obtain cloud data, improves the efficiency of using cloud data, and enhances the user experience.

[0048] In some optional embodiments, the method further comprises: S50: According to a preset rule, determine whether there is risk data in the second cloud data.

[0049] It is understandable that in order to prevent some risky data from being leaked, a risk check can be performed on the second cloud data when the cloud data is transmitted to the company's employees. The risk check rules can be set according to the company's own situation. For example, the company's financial data, personnel data, and related non-masked passwords and other data in the second cloud data can be screened.

[0050] S60. If there is risk data, a risk data document is generated and sent to relevant personnel of the enterprise.

[0051] S70: If there is no risk data, the second cloud data is sent to the enterprise employee.

[0052] Specifically, if it is determined that risk data exists in the second cloud data, the cloud data management background will automatically generate a risk report and send the risk report to relevant management personnel of the enterprise for processing to prevent the risk data from being leaked.

[0053] In some optional embodiments, judging whether risk data exists in the second cloud data according to a preset rule includes: S51. Determine whether the second cloud data includes: commercial confidential data, amount data, unmasked passwords, and keys.

[0054] S52: If yes, there is risk data in the second cloud data; if no, there is no risk data in the second cloud data.

[0055] In some optional embodiments, step S20, obtaining the query request data and authority data of the enterprise employee, includes: S21. Analyze the query data of the enterprise employees using an analysis model to determine whether the query data of the enterprise employees contains abnormal request data. If not, obtain the query request data of the enterprise employees.

[0056] Specifically, behavioral analysis models (such as Random Forest and Isolation Forest) can be used to analyze user operation patterns and identify abnormal behaviors, for example, whether there is abnormal request data. If there is abnormal request data, the use rights of the enterprise employees can be restricted or disabled.

[0057] S22. Obtaining permission data of the enterprise employee based on the user role and operation frequency of the enterprise employee.

[0058] Specifically, based on user roles and operation frequency, dynamic permission control technology (such as Attribute-Based Access Control, ABAC) is used to automatically adjust access rights.

[0059] In some optional embodiments, step S30, using a leaky bucket algorithm and intelligent frequency control to request data from the application programming interface to obtain corresponding cloud data, includes: S31. Obtain various application programming interface requests in real time, prioritize the various application programming interface requests according to preset rules, and control the request rates of the various application programming interface requests based on a leaky bucket algorithm.

[0060] S32. Monitor the response status and load status of various application programming interfaces in real time, and dynamically adjust the request frequency of various application programming interface requests according to the response status and load status.

[0061] S33. Based on the request rate and the request frequency, request data from the various application programming interfaces to obtain corresponding cloud data.

[0062] It is understandable that in order to solve the problem of excessive frequency of cross-platform document pulling, this application combines the leaky bucket algorithm with the intelligent frequency control mechanism. The leaky bucket algorithm is used to manage the request frequency to ensure that the requests are not too concentrated and avoid triggering the platform's access restrictions. The intelligent frequency control mechanism dynamically adjusts the request frequency by monitoring the platform's API response and load status in real time. The details are as follows: Request queue management: Classify cross-platform requests into different priorities and use the leaky bucket algorithm to control the request rate to ensure that the frequency is within the limit.

[0063] Dynamic adjustment: Based on the real-time feedback from each platform (such as API limit response, error rate, etc.), intelligently adjust the request frequency and optimize the data synchronization effect.

[0064] In some optional embodiments, the method further comprises: S34. If a request failure occurs in the application programming interface, an error handling and retry mechanism is triggered.

[0065] It is understandable that since request failures may occur when requesting data through an application programming interface, an error handling and retry mechanism is set in this embodiment. For example, when accessing a cloud platform, if access is not possible for the first time, an interval time can be set to re-access the platform. This ensures that the stability of data synchronization can be maintained when encountering restrictions or failures.

[0066] See also Figure 2 The present invention also provides a cloud data management system 200 based on machine learning, comprising: The first acquisition module 201 is used to acquire the application programming interfaces of various cloud storage platforms of the enterprise; The second acquisition module 202 is used to acquire the query request data and authority data of the enterprise employees; The data query module 203 is used to request data from the application programming interface according to the query request data and the permission data by using a leaky bucket algorithm and an intelligent frequency control method to obtain first cloud data; The data processing module 204 is used to pre-process the cloud data based on a machine learning model to obtain second cloud data, and send the second cloud data to the enterprise employees.

[0067] See also Figure 3 An embodiment of the present invention further provides a computer electronic device 400, including a memory 403 and a processor 402, wherein the memory 403 stores a computer program, and when the processor executes the computer program, the steps of the cloud data management method based on machine learning are implemented in any one of the above.

[0068] Specifically, the electronic device 400 includes: a transceiver 401, a bus interface and a processor 402, wherein the processor 402 is used to obtain application programming interfaces of various cloud storage platforms of the enterprise; then obtain query request data and permission data of enterprise employees; then, based on the query request data and permission data, a leaky bucket algorithm and an intelligent frequency control method are used to request data from the application programming interface to obtain first cloud data; finally, based on a machine learning model, the cloud data is pre-processed to obtain second cloud data, and the second cloud data is sent to the enterprise employees.

[0069] In the embodiment of the present invention, the electronic device 400 further includes a memory 403. Figure 3 In the embodiment, the bus architecture may include any number of interconnected buses and bridges, specifically linking together various circuits of one or more processors represented by processor 402 and memory represented by memory 403. The bus architecture may also link together various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. The bus interface provides an interface. The transceiver 401 may be a plurality of components, i.e., including a transmitter and a receiver, providing a unit for communicating with various other devices on a transmission medium. The processor 402 is responsible for managing the bus architecture and general processing, and the memory 403 may store data used by the processor 402 when performing operations.

[0070] An embodiment of the present invention also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps of any one of the above-mentioned cloud data management methods based on machine learning are implemented.

[0071] In this embodiment, the computer readable storage medium may be a non-volatile storage medium or a volatile storage medium. For example, the computer storage medium may include, but is not limited to, a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0072] In all examples shown and described herein, any specific values ​​should be interpreted as merely exemplary and not as limiting, and thus other examples of the exemplary embodiments may have different values.

[0073] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0074] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and structure diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in an alternative implementation, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the structure diagram and / or the flow diagram, and the combination of boxes in the structure diagram and / or the flow diagram, can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0075] In addition, the functional modules or units in the various embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

[0076] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling a terminal device (which can be a smart phone, a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application.

[0077] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A cloud data management method based on machine learning, characterized in that: include: Obtain the application programming interfaces of various cloud storage platforms for the enterprise; Obtain the query request data and permission data of enterprise employees; According to the query request data and the permission data, a leaky bucket algorithm and an intelligent frequency control method are used to request data from the application programming interface to obtain first cloud data; Based on a machine learning model, the cloud data is preprocessed to obtain second cloud data, and the second cloud data is sent to the enterprise employee.

2. The cloud data management method according to claim 1, characterized in that: After obtaining the second cloud data, the method further includes: According to preset rules, determining whether there is risk data in the second cloud data; If there is risk data, a risk data document will be generated and sent to relevant personnel of the enterprise; If there is no risk data, the second cloud data is sent to the enterprise employee.

3. The cloud data management method according to claim 2, characterized in that: The determining, according to a preset rule, whether risk data exists in the second cloud data includes: Determining whether the second cloud data includes: commercial confidential data, amount data, unmasked passwords, and keys; If so, there is risk data in the second cloud data; if not, there is no risk data in the second cloud data.

4. The cloud data management method according to claim 1, characterized in that: The obtaining of the query request data and authority data of the enterprise employee includes: Analyze the query data of the enterprise employees by using the analysis model to determine whether the query data of the enterprise employees contains abnormal request data, and if not, obtain the query request data of the enterprise employees; Based on the user role and operation frequency of the enterprise employee, the permission data of the enterprise employee is obtained.

5. The cloud data management method according to claim 1, characterized in that: The leaky bucket algorithm and intelligent frequency control are used to request data from the application programming interface to obtain corresponding cloud data, including: Acquire various application programming interface requests in real time, prioritize the various application programming interface requests according to preset rules, and control the request rates of various application programming interface requests based on the leaky bucket algorithm; Monitor the response and load status of various application programming interfaces in real time, and dynamically adjust the request frequency of various application programming interface requests according to the response and load status; Based on the request rate and the request frequency, data is requested from the various application programming interfaces to obtain corresponding cloud data.

6. The cloud data management method according to claim 5, characterized in that: The method further comprises: If a request fails in the application programming interface, an error handling and retry mechanism is triggered.

7. The cloud data management method according to claim 1, characterized in that: The preprocessing of the first cloud data based on the machine learning model to obtain the second cloud data includes: Using natural language processing technology, perform semantic analysis and content extraction on the first cloud data to obtain the first cloud data with content tags; A machine learning classification algorithm is used to classify the first cloud data with content tags to obtain second cloud data.

8. A cloud data management system based on machine learning, characterized in that: include: The first acquisition module is used to obtain the application programming interfaces of various cloud storage platforms of the enterprise; The second acquisition module is used to obtain the query request data and permission data of enterprise employees; A data query module, configured to request data from the application programming interface according to the query request data and the authority data by using a leaky bucket algorithm and an intelligent frequency control method, so as to obtain first cloud data; The data processing module is used to pre-process the cloud data based on a machine learning model to obtain second cloud data, and send the second cloud data to the enterprise employees.

9. A computer electronic device, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the cloud data management method based on machine learning described in any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the cloud data management method based on machine learning described in any one of claims 1 to 7 are implemented.

Images