Desktop and application intelligent management method and system based on AI desktop cloud

Abstract

The invention discloses a desktop and application intelligent management method and system based on AI desktop cloud, and belongs to the technical field of AI intelligent application, and the method comprises the following steps: data collection and preprocessing: collecting application use data of a user in a desktop cloud environment, and carrying out cleaning, conversion and integration; user grouping based on AI: analyzing the preprocessed application use data by using a machine learning algorithm, extracting user behavior characteristics, dividing users into different groups and generating group portraits; personalized recommendation and management: providing personalized application recommendation and desktop management strategies in combination with an AI recommendation algorithm based on the user group portrait and the historical use data of the individual user; and abnormal monitoring and early warning: setting various index thresholds of application management, monitoring application use data in real time, and giving out early warning when the indexes exceed the thresholds. According to the invention, user grouping, personalized recommendation management and abnormity early warning are realized, and the intelligent level of application management and the user experience are improved.

Description

Technical Field

[0001] This invention relates to the field of AI intelligent application technology, specifically a method and system for intelligent management of desktops and applications based on AI desktop cloud. Background Technology

[0002] With the continuous development of cloud computing technology, desktop cloud technology has been widely used in various institutions such as enterprises, governments, and educational institutions due to its advantages such as centralized management, resource sharing, flexible deployment, and data security. In a desktop cloud environment, users access the cloud desktop through terminal devices to use various applications, thereby generating massive amounts of application usage data.

[0003] These applications contain a wealth of information in their data, such as user behavior habits (e.g., common operation paths, operation frequency), usage preferences (e.g., preferences for specific functional modules, preferences for application interface styles), usage frequency (e.g., the number of times a certain application is used daily / weekly), usage duration (e.g., single usage duration, cumulative usage duration), usage time (e.g., concentrated use on weekday mornings or evenings), and relationships between applications (e.g., combinations of applications used simultaneously or sequentially).

[0004] However, current analyses of these application usage data mostly remain at a superficial level, such as only counting basic metrics like overall application usage frequency and total number of users. The analytical methods are fragmented and simplistic. This superficial analysis fails to fully uncover the deeper value hidden behind the data, and cannot reveal the differentiated needs of different user groups, the potential patterns in application usage, or any potential risks.

[0005] The lack of in-depth utilization of data has led to numerous problems in application management:

[0006] App recommendations lack precision and often adopt a "one-size-fits-all" approach, failing to meet the personalized needs of different user groups.

[0007] The lack of data support for management decisions such as application updates and maintenance makes it difficult to formulate reasonable strategies based on actual user usage.

[0008] When abnormal situations such as a sudden increase in user churn rate or an application failure rate exceeding the normal range occur, the inability to detect and intervene in a timely manner may affect user experience and system stability.

[0009] Therefore, how to conduct in-depth analysis of application usage data in the desktop cloud environment and leverage AI technology to achieve intelligent management of desktops and applications has become an urgent problem to be solved. Summary of the Invention

[0010] The technical objective of this invention is to address the above-mentioned shortcomings by providing a method and system for intelligent management of desktops and applications based on AI desktop cloud. This system can achieve user segmentation, personalized recommendation management, and anomaly warning by deeply analyzing application usage data and combining AI technology, thereby improving the intelligence level of application management and user experience.

[0011] The technical solution adopted by this invention to solve its technical problem is:

[0012] A method for intelligent management of desktops and applications based on AI desktop cloud, the implementation of which includes the following steps:

[0013] Data Acquisition and Preprocessing: Collect user application usage data in the desktop cloud environment, and clean, transform, and integrate it;

[0014] AI-based user segmentation: Utilizing machine learning algorithms to analyze preprocessed application usage data, extracting user behavior characteristics, dividing users into different groups, and generating group profiles;

[0015] Personalized Recommendations and Management: Based on user profiles and individual user historical usage data, combined with AI recommendation algorithms, we provide personalized application recommendations and desktop management strategies.

[0016] Anomaly monitoring and early warning: Set thresholds for various indicators of application management, monitor application usage data in real time, and issue an early warning when the indicators exceed the thresholds.

[0017] This method utilizes in-depth analysis of application usage data and AI technology to segment users into different groups, enabling personalized recommendation management based on the usage characteristics of each group. Various indicator thresholds are set, and the system promptly issues alerts when application usage data anomalies occur, such as a sudden increase in user churn or an application failure rate exceeding normal range. This achieves intelligent management of the application management platform, improving application management efficiency and enhancing user experience.

[0018] Furthermore, the data acquisition and preprocessing involves collecting user application usage data in the desktop cloud environment in real time or at regular intervals through data acquisition modules deployed on the desktop cloud client and server; the types of data collected include:

[0019] Basic user information, including user ID, department, role, etc.;

[0020] Application usage details include the application name, version, start time, end time, duration, operation path, function module call records, and number of times the application was started / closed.

[0021] System interaction data: desktop configuration modification history, application installation / uninstallation history, resource usage (CPU, memory, network bandwidth), etc.

[0022] The collected raw data is cleaned, transformed, and integrated, specifically including:

[0023] Remove redundant data, fill in missing values, and detect and handle outliers;

[0024] Convert unstructured data (such as operation path text) into structured data;

[0025] Standardize or normalize the data to build a dataset with a unified format for application use.

[0026] Furthermore, the AI-based user segmentation includes user behavior characteristics such as usage frequency characteristics, duration distribution characteristics, preferred application characteristics, and operating habit characteristics.

[0027] Clustering algorithms, or a combination of clustering and classification algorithms, can be used to divide users into different groups based on their behavioral characteristics; for example, they can be divided into "high-frequency office application users", "design application preference users", and "lightweight application temporary users".

[0028] Summarize and analyze the usage characteristics of each user group to generate a group profile, including the group's typical application usage patterns, core needs, and usage time patterns.

[0029] Furthermore, the clustering algorithm includes the K-Means algorithm or the DBSCAN algorithm; the classification algorithm includes decision trees or support vector machines.

[0030] Furthermore, the personalized recommendation and management, the AI ​​recommendation algorithm includes collaborative filtering algorithm, content recommendation algorithm, and deep learning recommendation model;

[0031] Personalized application recommendations and desktop management strategies for different user groups or individual users include:

[0032] Application recommendations: Recommend applications that are frequently used by the user’s group and may be valuable to them, or recommend related applications based on the user’s usage habits (e.g., recommend a PDF reader after using PPT);

[0033] Desktop configuration recommendations: Based on the user group's desktop usage preferences, we recommend suitable desktop icon layouts, shortcut settings, default application configurations, etc.

[0034] Resource allocation optimization: Based on the resource needs of different groups, dynamically adjust the computing and storage resources allocated by the desktop cloud to these users to ensure smooth application operation;

[0035] It supports users in providing feedback on recommended content (such as accepting, rejecting, or adjusting), and incorporates the feedback data into model training to continuously optimize recommendation accuracy.

[0036] Furthermore, the anomaly monitoring and early warning system sets various indicator thresholds for application management based on historical data and business needs, including:

[0037] User-related metrics include user churn rate thresholds (such as a single-day churn rate exceeding 5%), active user ratio thresholds, and thresholds for the decline in user usage rate for specific applications.

[0038] Application performance metrics include application failure rate thresholds (e.g., an application experiencing more than 10 failures per day), average response time thresholds, and crash rate thresholds.

[0039] Resource usage metrics include average application CPU utilization threshold, peak memory usage threshold, and abnormal network bandwidth fluctuation threshold.

[0040] Furthermore, the aforementioned anomaly monitoring and early warning,

[0041] The AI ​​monitoring model performs real-time or near-real-time analysis of application usage data, comparing the current data with the set threshold.

[0042] When a certain indicator is detected to exceed the set threshold, the system will automatically issue an early warning. The early warning methods include platform alarm prompts, email notifications, and SMS notifications. At the same time, the system can provide preliminary handling suggestions based on the warning level. For example, for a warning of excessively high application failure rate, it is recommended to update the application version or troubleshoot the problem.

[0043] This invention also claims a system for intelligent management of desktops and applications based on AI desktop cloud, comprising:

[0044] The data acquisition and preprocessing module is used to collect user application usage data in the desktop cloud environment and to clean, transform, and integrate it.

[0045] The AI-based user segmentation module is used to analyze preprocessed application usage data, extract user behavior characteristics, divide users into different groups, and generate group profiles.

[0046] The personalized recommendation and management module is used to provide personalized application recommendations and desktop management strategies based on user group profiles and individual user historical usage data, combined with AI recommendation algorithms.

[0047] The anomaly monitoring and early warning module is used to set various thresholds for application management metrics, monitor application usage data in real time, and issue an early warning when the metrics exceed the thresholds.

[0048] The system achieves intelligent management of desktops and applications through the methods described above.

[0049] The present invention also claims a device for intelligent management of desktops and applications based on AI desktop cloud, comprising: at least one memory and at least one processor;

[0050] The at least one memory is used to store a machine-readable program;

[0051] The at least one processor is used to call the machine-readable program to implement the above method.

[0052] The present invention also claims a computer-readable medium storing computer instructions that, when executed by a processor, enable the implementation of the above-described method.

[0053] Compared with existing technologies, the method and system for intelligent management of desktops and applications based on AI desktop cloud of the present invention have the following advantages:

[0054] 1. Deeply mine the value of data: By comprehensively collecting and deeply analyzing application usage data, we break through the limitations of traditional superficial analysis, fully explore the user behavior patterns and application usage characteristics contained in the data, and provide data-driven decision-making basis for application management.

[0055] 2. Achieve precise user segmentation: By leveraging AI algorithms to scientifically segment users and build group profiles, application management can shift from "unified management" to "differentiated management by segmentation," thereby improving the targeting of management.

[0056] 3. Personalized services enhance the experience: Personalized recommendations based on user groups and individual characteristics enable users to more easily obtain the applications and desktop configurations they need, reduce operating costs, and significantly improve the user experience.

[0057] 4. Anomaly warning ensures stability: By setting indicator thresholds and monitoring in real time, abnormal situations during application use (such as increased user churn or frequent application failures) can be detected in a timely manner, facilitating rapid response and handling by administrators and ensuring the stable operation and service quality of the desktop cloud system.

[0058] 5. Improve management efficiency: Intelligent recommendation management and anomaly early warning mechanisms reduce the workload of manual intervention, lower management costs, and improve the overall operational efficiency of the application management platform. Attached Figure Description

[0059] Figure 1 This is a flowchart illustrating the method for intelligent management of desktops and applications based on AI desktop cloud, as provided in an embodiment of the present invention. Detailed Implementation

[0060] The present invention will be further described below with reference to specific embodiments.

[0061] This invention provides a method for intelligent management of desktops and applications based on AI desktop cloud. The implementation of this method includes the following steps:

[0062] Data Acquisition and Preprocessing: Collect user application usage data in the desktop cloud environment, and clean, transform, and integrate it.

[0063] AI-based user segmentation: Utilizing machine learning algorithms to analyze preprocessed application usage data, extracting user behavior characteristics, dividing users into different groups, and generating group profiles.

[0064] Personalized Recommendations and Management: Based on user profiles and individual user historical usage data, combined with AI recommendation algorithms, we provide personalized application recommendations and desktop management strategies.

[0065] Anomaly monitoring and early warning: Set thresholds for various indicators of application management, monitor application usage data in real time, and issue an early warning when the indicators exceed the thresholds.

[0066] The specific implementation method is as follows:

[0067] 1. Data Acquisition and Preprocessing:

[0068] Data collection modules deployed on desktop cloud clients and servers collect user application usage data in the desktop cloud environment in real time or at regular intervals. The types of data collected include:

[0069] Basic user information: User ID, department, role, etc.;

[0070] Application usage details: application name, version, start time, end time, duration, operation path, function module call records, number of times the application was started / closed, etc.

[0071] System interaction data: desktop configuration modification records, application installation / uninstallation records, resource usage (CPU, memory, network bandwidth), etc.

[0072] The collected raw data is cleaned, transformed, and integrated, specifically including:

[0073] Remove redundant data, fill in missing values, and detect and handle outliers;

[0074] Convert unstructured data (such as operation path text) into structured data;

[0075] Standardize or normalize the data to build a dataset with a unified format for application use.

[0076] 2. AI-based user segmentation:

[0077] Machine learning algorithms are used to analyze the preprocessed application dataset to extract user behavioral characteristics, including usage frequency characteristics, duration distribution characteristics, preferred application characteristics, and operating habit characteristics.

[0078] Clustering algorithms (such as K-Means and DBSCAN) or a combination of clustering and classification algorithms (such as decision trees and support vector machines) can be used to divide users into different groups based on their behavioral characteristics. For example, they can be divided into "high-frequency office application users," "design application preference users," and "lightweight application temporary users."

[0079] Summarize and analyze the usage characteristics of each user group to generate a group profile, including the group's typical application usage patterns, core needs, and usage time patterns.

[0080] 3. Personalized recommendations and management:

[0081] Based on user profiles and historical usage data of individual users, and combined with AI recommendation algorithms (such as collaborative filtering, content recommendation, and deep learning recommendation models), personalized application recommendations and desktop management strategies are provided for different user groups or individual users.

[0082] (1) Application recommendation: Recommend applications that are frequently used by the user’s group and may be valuable to them, or recommend related applications based on the user’s usage habits (e.g., recommend a PDF reader after using PPT);

[0083] (2) Desktop configuration recommendations: Based on the user group's desktop usage preferences, recommend suitable desktop icon layouts, shortcut settings, default application configurations, etc.

[0084] (3) Resource allocation optimization: Based on the resource needs of different groups, dynamically adjust the computing and storage resources allocated by the desktop cloud to the users of that group to ensure smooth application operation.

[0085] It supports users in providing feedback on recommended content (such as accepting, rejecting, or adjusting), and incorporates the feedback data into model training to continuously optimize recommendation accuracy.

[0086] 4. Anomaly monitoring and early warning:

[0087] (1) Setting indicator thresholds: Based on historical data and business needs, set various indicator thresholds for application management, including:

[0088] User-related metrics: user churn rate threshold (e.g., daily churn rate exceeding 5%), active user ratio threshold, threshold for the decline in user usage rate of a specific application, etc.

[0089] Application performance metrics: application failure rate threshold (e.g., an application fails more than 10 times in a single day), average response time threshold, crash rate threshold, etc.

[0090] Resource usage metrics: application average CPU utilization threshold, peak memory usage threshold, abnormal network bandwidth fluctuation threshold, etc.

[0091] (2) Real-time monitoring and analysis: The AI ​​monitoring model is used to analyze the application usage data in real time or near real time and compare the current data with the set threshold.

[0092] (3) Warning Triggering and Handling: When a certain indicator is detected to exceed the set threshold, the system will automatically issue a warning message. The warning methods include, but are not limited to, platform alarm prompts, email notifications, and SMS notifications. At the same time, the system can provide preliminary handling suggestions based on the warning level. For example, for a warning of excessively high application failure rate, it is recommended to update the application version or troubleshoot the problem.

[0093] Figure 1 The flowchart shown is a process for intelligent management of desktops and applications based on AI desktop cloud in this embodiment. It sequentially illustrates the relationship between the four steps: data collection and preprocessing, AI-based user segmentation, personalized recommendation and management, and anomaly monitoring and early warning.

[0094] This method addresses the shortcomings of existing technologies that merely analyze desktop cloud application usage data superficially, failing to fully unlock the data's value and provide in-depth, accurate decision support. This results in inefficient application management and poor user experience. By deeply analyzing application usage data and combining it with AI technology, this method enables user segmentation, personalized recommendation management, and anomaly alerts, thereby improving the intelligence level of application management and user experience.

[0095] This invention also provides a system for intelligent management of desktops and applications based on an AI desktop cloud, comprising a data acquisition system that provides functions such as data acquisition, processing, and storage of application and desktop data; a data analysis service that provides AI analysis of the acquired data and offers target user suggestions for distribution strategies based on user profiles; and a strategy management module that provides strategy distribution and monitoring for desktops and applications. This system achieves intelligent management of desktops and applications through the method for intelligent management of desktops and applications based on an AI desktop cloud described in the above embodiments.

[0096] The system specifically includes:

[0097] 1. Data Acquisition and Preprocessing Module: This module collects user application usage data from the desktop cloud environment and performs cleaning, transformation, and integration. The specific implementation is as follows:

[0098] Data collection modules deployed on desktop cloud clients and servers collect user application usage data in the desktop cloud environment in real time or at regular intervals. The types of data collected include:

[0099] Basic user information: User ID, department, role, etc.;

[0100] Application usage details: application name, version, start time, end time, duration, operation path, function module call records, number of times the application was started / closed, etc.

[0101] System interaction data: desktop configuration modification records, application installation / uninstallation records, resource usage (CPU, memory, network bandwidth), etc.

[0102] The collected raw data is cleaned, transformed, and integrated, specifically including:

[0103] Remove redundant data, fill in missing values, and detect and handle outliers;

[0104] Convert unstructured data (such as operation path text) into structured data;

[0105] Standardize or normalize the data to build a dataset with a unified format for application use.

[0106] 2. An AI-based user segmentation module is used to analyze preprocessed application usage data, extract user behavior features, divide users into different groups, and generate group profiles. The specific implementation is as follows:

[0107] Machine learning algorithms are used to analyze the preprocessed application dataset to extract user behavioral characteristics, including usage frequency characteristics, duration distribution characteristics, preferred application characteristics, and operating habit characteristics.

[0108] Clustering algorithms (such as K-Means and DBSCAN) or a combination of clustering and classification algorithms (such as decision trees and support vector machines) can be used to divide users into different groups based on their behavioral characteristics. For example, they can be divided into "high-frequency office application users," "design application preference users," and "lightweight application temporary users."

[0109] Summarize and analyze the usage characteristics of each user group to generate a group profile, including the group's typical application usage patterns, core needs, and usage time patterns.

[0110] 3. Personalized Recommendation and Management Module: This module uses user profiles and individual user historical usage data, combined with AI recommendation algorithms, to provide personalized application recommendations and desktop management strategies. The specific implementation is as follows:

[0111] Based on user profiles and historical usage data of individual users, and combined with AI recommendation algorithms (such as collaborative filtering, content recommendation, and deep learning recommendation models), personalized application recommendations and desktop management strategies are provided for different user groups or individual users.

[0112] (1) Application recommendation: Recommend applications that are frequently used by the user’s group and may be valuable to them, or recommend related applications based on the user’s usage habits (e.g., recommend a PDF reader after using PPT);

[0113] (2) Desktop configuration recommendations: Based on the user group's desktop usage preferences, recommend suitable desktop icon layouts, shortcut settings, default application configurations, etc.

[0114] (3) Resource allocation optimization: Based on the resource needs of different groups, dynamically adjust the computing and storage resources allocated by the desktop cloud to the users of that group to ensure smooth application operation.

[0115] It supports users in providing feedback on recommended content (such as accepting, rejecting, or adjusting), and incorporates the feedback data into model training to continuously optimize recommendation accuracy.

[0116] 4. Anomaly monitoring and early warning module: This module is used to set thresholds for various application management metrics, monitor application usage data in real time, and issue early warnings when metrics exceed the thresholds. The specific implementation is as follows:

[0117] (1) Setting indicator thresholds: Based on historical data and business needs, set various indicator thresholds for application management, including:

[0118] User-related metrics: user churn rate threshold (e.g., daily churn rate exceeding 5%), active user ratio threshold, threshold for the decline in user usage rate of a specific application, etc.

[0119] Application performance metrics: application failure rate threshold (e.g., an application fails more than 10 times in a single day), average response time threshold, crash rate threshold, etc.

[0120] Resource usage metrics: application average CPU utilization threshold, peak memory usage threshold, abnormal network bandwidth fluctuation threshold, etc.

[0121] (2) Real-time monitoring and analysis: The AI ​​monitoring model is used to analyze the application usage data in real time or near real time and compare the current data with the set threshold.

[0122] (3) Warning Triggering and Handling: When a certain indicator is detected to exceed the set threshold, the system will automatically issue a warning message. The warning methods include, but are not limited to, platform alarm prompts, email notifications, and SMS notifications. At the same time, the system can provide preliminary handling suggestions based on the warning level. For example, for a warning of excessively high application failure rate, it is recommended to update the application version or troubleshoot the problem.

[0123] This invention also provides a device for intelligent management of desktops and applications based on AI desktop cloud, comprising: at least one memory and at least one processor;

[0124] The at least one memory is used to store a machine-readable program;

[0125] The at least one processor is used to call the machine-readable program to implement the method for intelligent management of desktops and applications based on AI desktop cloud described in the above embodiments.

[0126] This invention also provides a computer-readable medium storing computer instructions. When executed by a processor, these computer instructions implement the method for intelligent management of desktops and applications based on AI desktop cloud described in the above embodiments. Specifically, a system or device equipped with a storage medium storing software program code that implements the functions of any of the embodiments described above can be provided, enabling the computer (or CPU or MPU) of the system or device to read and execute the program code stored in the storage medium.

[0127] In this case, the program code read from the storage medium can itself implement the function of any of the above embodiments, and therefore the program code and the storage medium storing the program code constitute part of the present invention.

[0128] Examples of storage media used to provide program code include floppy disks, hard disks, magneto-optical disks, optical disks (such as CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD+RW), magnetic tapes, non-volatile memory cards, and ROMs. Alternatively, program code can be downloaded from a server computer via a communication network.

[0129] Furthermore, it should be clear that not only can the program code read by the computer be executed, but also the operating system or other components operating on the computer can be instructed based on the program code to perform some or all of the actual operations, thereby realizing the function of any of the embodiments described above.

[0130] Furthermore, it is understood that the program code read from the storage medium is written to the memory set in the expansion board inserted into the computer or to the memory set in the expansion unit connected to the computer. Then, based on the instructions of the program code, the CPU or other components installed on the expansion board or expansion unit execute some and all of the actual operations, thereby realizing the function of any of the embodiments described above.

[0131] The present invention has been shown and described in detail above with reference to the accompanying drawings and preferred embodiments. However, the present invention is not limited to these disclosed embodiments. Based on the above embodiments, those skilled in the art will know that more embodiments of the present invention can be obtained by combining the code review methods in the different embodiments. These embodiments are also within the protection scope of the present invention.

Claims

1. A method for intelligent management of desktops and applications based on AI desktop cloud, characterized in that, The implementation of this method includes the following steps: Data Acquisition and Preprocessing: Collect user application usage data in the desktop cloud environment, and clean, transform, and integrate it; AI-based user segmentation: Utilizing machine learning algorithms to analyze preprocessed application usage data, extracting user behavior characteristics, dividing users into different groups, and generating group profiles; Personalized Recommendations and Management: Based on user profiles and individual user historical usage data, combined with AI recommendation algorithms, we provide personalized application recommendations and desktop management strategies. Anomaly monitoring and early warning: Set thresholds for various indicators of application management, monitor application usage data in real time, and issue an early warning when the indicators exceed the thresholds.

2. The method for intelligent management of desktops and applications based on AI desktop cloud according to claim 1, characterized in that, The data acquisition and preprocessing involves collecting user application usage data in the desktop cloud environment in real time or at regular intervals through data acquisition modules deployed on the desktop cloud client and server. The types of data collected include: Basic user information, including user ID, department, and role; Application usage details include the application name, version, start time, end time, duration, operation path, function module call records, and number of times the application was started / stopped. System interaction data: desktop configuration modification history, application installation / uninstallation history, resource usage; The collected raw data is cleaned, transformed, and integrated, specifically including: Remove redundant data, fill in missing values, and detect and handle outliers; Convert unstructured data into structured data; Standardize or normalize the data to build a dataset with a unified format for application use.

3. The method for intelligent management of desktops and applications based on AI desktop cloud according to claim 1, characterized in that, The AI-based user segmentation includes user behavior characteristics such as usage frequency characteristics, duration distribution characteristics, preferred application characteristics, and operating habit characteristics. Using clustering algorithms or a combination of classification algorithms, users are divided into different groups based on their behavioral characteristics; Summarize and analyze the usage characteristics of each user group to generate a group profile, including the group's typical application usage patterns, core needs, and usage time patterns.

4. The method for intelligent management of desktops and applications based on AI desktop cloud according to claim 3, characterized in that, The clustering algorithm includes the K-Means algorithm or the DBSCAN algorithm; the classification algorithm includes the decision tree or the support vector machine.

5. The method for intelligent management of desktops and applications based on AI desktop cloud according to claim 1, characterized in that, The personalized recommendation and management system uses AI recommendation algorithms, including collaborative filtering algorithms, content recommendation algorithms, and deep learning recommendation models. Personalized application recommendations and desktop management strategies for different user groups or individual users include: Application recommendation: Recommending applications that are frequently used and valuable to users within their group, or recommending related applications based on individual users' usage habits; Desktop configuration recommendations: Based on the user group's desktop usage preferences, we recommend desktop icon layouts, shortcut settings, and default application configurations; Resource allocation optimization: Based on the resource needs of different groups, dynamically adjust the computing and storage resources allocated by the desktop cloud to these users to ensure smooth application operation; It allows users to provide feedback on recommended content, and incorporates this feedback data into model training to continuously optimize recommendation accuracy.

6. The method for intelligent management of desktops and applications based on AI desktop cloud according to claim 1, characterized in that, The anomaly monitoring and early warning system sets various indicator thresholds for application management based on historical data and business needs, including: User-related metrics include user churn rate threshold, active user ratio threshold, and threshold for the decline in user usage rate of a specific application. Application performance metrics include application failure rate threshold, average response time threshold, and crash rate threshold. Resource usage metrics include average application CPU utilization threshold, peak memory usage threshold, and abnormal network bandwidth fluctuation threshold.

7. A method for intelligent management of desktops and applications based on AI desktop cloud according to claim 1 or 6, characterized in that, The aforementioned anomaly monitoring and early warning The AI ​​monitoring model performs real-time or near-real-time analysis of application usage data, comparing the current data with the set threshold. When a certain indicator is detected to exceed a set threshold, the system will automatically issue an early warning. The early warning methods include platform alarm prompts, email notifications, and SMS notifications. At the same time, the system can provide preliminary handling suggestions based on the early warning level.

8. A system for intelligent management of desktops and applications based on AI desktop cloud, characterized in that, include: The data acquisition and preprocessing module is used to collect user application usage data in the desktop cloud environment and to clean, transform, and integrate it. The AI-based user segmentation module is used to analyze preprocessed application usage data, extract user behavior characteristics, divide users into different groups, and generate group profiles. The personalized recommendation and management module is used to provide personalized application recommendations and desktop management strategies based on user group profiles and individual user historical usage data, combined with AI recommendation algorithms. The anomaly monitoring and early warning module is used to set various thresholds for application management metrics, monitor application usage data in real time, and issue an early warning when the metrics exceed the thresholds. The system achieves intelligent management of desktops and applications through the method described in any one of claims 1 to 7.

9. A device for intelligent management of desktops and applications based on AI desktop cloud, characterized in that, include: At least one memory and at least one processor; The at least one memory is used to store a machine-readable program; The at least one processor is configured to invoke the machine-readable program to implement the method according to any one of claims 1 to 7.

10. A computer-readable medium, characterized in that, The computer-readable medium stores computer instructions that, when executed by a processor, enable the implementation of the method described in any one of claims 1 to 7.

Images