Virtual machine management system and method based on graphics card configuration

By receiving and analyzing the user's shared instructions and historical usage information in the virtual machine management system, calculating the sharing stability of the virtual machine, optimizing the sharing time period of the virtual machine, solving the problem of resource mismatch in virtual machine sharing and improving users Experience and resource utilization efficiency.

CN118921283APending Publication Date: 2024-11-08CHONGQING BORA INTELLIGENT COMPUTING TECHNOLOGY CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410960037.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-17
Publication Date
2024-11-08

AI Technical Summary

Technical Problem

The existing virtual machine management platform lacks unified coordination in the virtual machine sharing mechanism, resulting in the problems of resource mismatch and poor user experience.

Method used

By receiving the user's sharing instructions and historical usage information on the server, counting the number of idle times and usage types of virtual machines, setting idle and sharing weight values, calculating sharing stability, optimizing the sharing time period of virtual machines, and avoiding resource mismatch.

Benefits of technology

It improves the efficiency and user experience of virtual machine sharing, reduces time costs, and realizes dynamic optimization and security management of resources.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118921283A_ABST
    Figure CN118921283A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of virtual machine management, in particular to a virtual machine management system and method based on graphics card configuration. The server side comprises a sharing instruction receiving module, a historical data calling module, an identification module, a first processing module, a second processing module, a calculation module and a sharing module, and the calculation module is used for calculating user sharing stability corresponding to each time period of a day of a corresponding user according to historical use information of the virtual machine; the user sharing stability is associated with an idle stability weight value and a sharing stability weight value; the sharing module is used for arranging according to the calculated user sharing stability corresponding to each time period in one day in a descending order to form a sharing stability arrangement table, and selecting virtual machine sharing time periods corresponding to the user sides from the sharing stability arrangement table in order according to the sharing quantity demand to obtain a sharing time period of the virtual machine; and transmitting the data to the virtual machine sharing platform.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of virtual machine management, and in particular to a virtual machine management system and method based on graphics card configuration. Background Art

[0002] In the context of the rapid development of information technology, cloud computing and virtualization technology have become important pillars for enterprise informatization construction and personal user computing needs. Among them, virtual machine technology has been widely used in data centers, cloud services, high-performance computing and other fields due to its advantages such as resource isolation and flexible expansion. However, with the large-scale deployment and use of virtual machines, resource utilization has gradually become the focus of the industry, especially in the management and utilization of virtual machine idle time resources, there are obvious challenges and shortcomings.

[0003] Existing virtual machine management platforms mostly rely on users to independently determine risk time periods in their virtual machine sharing mechanisms in order to complete the sharing of their respective virtual machines. However, this approach still has certain limitations, such as the lack of unified coordination, which causes users to spend a lot of energy when sharing virtual machines, and there may be resource mismatch problems, as well as poor user experience. Summary of the invention

[0004] One of the purposes of the present invention is to provide a virtual machine management system and method based on graphics card configuration, which can accurately determine the sharing time period of the user-side virtual machine, avoid the problem of resource mismatch, greatly improve the user experience, reduce the user's time cost, and improve sharing efficiency.

[0005] In order to achieve the above object, a virtual machine management system based on graphics card configuration is provided, including a server and a user;

[0006] The server includes:

[0007] A sharing instruction receiving module, used for receiving the corresponding sharing instruction information from the user end;

[0008] A historical data retrieval module is used to retrieve the historical usage information of the virtual machine corresponding to the corresponding user terminal after receiving the sharing instruction information of the user terminal; the historical usage information of the virtual machine includes the usage of the virtual machine corresponding to each historical time period of a day;

[0009] an identification module, for collecting statistics on the use of virtual machines by users in various time periods of a day according to the corresponding virtual machine history use information, determining the number of idle times of the users corresponding to the various time periods of a day, and judging whether the corresponding virtual machines of the users are more idle during the day or at night according to the corresponding number of idle times of the users, and determining the virtual machine use type of the corresponding user according to the judgment result, wherein the virtual machine use type includes a daytime use type and a nighttime use type;

[0010] The first processing module is used to retrieve the corresponding weight setting strategy according to the virtual machine usage type corresponding to the user, and set the idle stable weight value corresponding to the corresponding user in each time period of the day;

[0011] The second processing module is used to count the number of user shares corresponding to each time period in a day according to the idle sharing time period of the virtual machine shared by other user terminals in the virtual machine sharing platform, and determine the sharing stability weight value corresponding to each time period in a day on the virtual machine sharing platform according to the number of user shares;

[0012] A calculation module, for calculating the user sharing stability corresponding to the corresponding user in each time period of the day according to the historical usage information of the virtual machine corresponding to the user terminal and based on a preset user sharing stability calculation formula, wherein the user sharing stability is associated with an idle stability weight value and a sharing stability weight value;

[0013] The sharing module is used to arrange the user sharing stabilities corresponding to the calculated users in various time periods of the day in descending order to form a sharing stability ranking table, and select the virtual machine sharing time period of the corresponding user terminal from the sharing stability ranking table in order according to the sharing quantity requirements, and transmit it to the virtual machine sharing platform.

[0014] Technical principles and effects of this solution: In this solution, the first step is to receive the sharing instruction information sent by the user end. Through this step, the system can determine whether the user end shares the virtual machine, separate and identify users who can share virtual machines and those who cannot share virtual machines, and then retrieve the virtual machine historical usage information corresponding to the corresponding user end as soon as possible, where the virtual machine historical usage information includes the virtual machine usage corresponding to the corresponding user end in various time periods of the day.

[0015] Afterwards, according to the historical usage information of the virtual machine, the user's use of the virtual machine in each time period of the day is counted, so as to determine the number of idle times of the user corresponding to each time period of the day. For example, in the 20 days of history, the number of times the virtual machine was not used in time period A was 20 times, and the number of times the virtual machine was not used in time period B was 10 times. Or, the number of times used during the day was 200 times, and the number of times used during the night was 50 times. In this way, the user's virtual machine usage type can be determined, whether it is daytime use or nighttime use. Through this step of operation identification, the sharing ratio of the time period during the day and the time period during the night can be determined when the corresponding user's virtual machine is shared. For example, user A often uses the virtual machine during the day, but generally does not use it at night, while user B generally uses it at night and generally does not use it during the day. Then, when sharing, the proportion of the time period during the night in the time period shared by user A will be greater than the time period during the day.

[0016] Subsequently, according to the corresponding virtual machine usage type, the corresponding weight setting strategy is called to set the idle stable weight value corresponding to the user in each time period of the day, which greatly improves the stability and reliability of the subsequent sharing time period determination.

[0017] Of course, the sharing stability weight value of each time period on the sharing platform will be determined based on the idle sharing time period of the virtual machines shared by other users on the virtual machine sharing platform, and then the subsequent calculation of user sharing stability will be associated with the idle stability weight value and the sharing stability weight value, so as to further improve the sharing stability and reliability of the virtual machines on the user side when sharing, thereby achieving the effectiveness and feasibility of sharing the idle time period of the virtual machines on the user side. That is, it is able to accurately determine the sharing time period of the virtual machines on the user side, avoid the problem of resource mismatch, greatly improve the user experience, reduce the user's time cost, and improve the sharing efficiency.

[0018] Furthermore, the preset user sharing stability calculation formula is:

[0019]

[0020] Where F is the user sharing stability corresponding to the user terminal, W1 is the idle stability weight value, W2 is the sharing stability weight value, and K i is the number of idle times of the virtual machine corresponding to the user end in time period i, K Z is the total number of idle times of the virtual machine corresponding to the user end in one day, and m is the total time period corresponding to the user end.

[0021] Beneficial effects: Associating the user sharing stability in each time period of the day with the idle stability weight value and the sharing stability weight value can better identify the shortcomings of the user's best virtual machine sharing time period in each time period, optimize resource allocation, reduce resource photovoltaics, improve user satisfaction, and realize dynamic resource allocation.

[0022] Furthermore, it also includes a time period slicing module, which is used to count the usage time corresponding to the user corresponding to the user terminal each time the virtual machine is used according to the historical usage information of the virtual machine corresponding to the user terminal, set the corresponding usage weight value according to the number of times of each usage time, and calculate the basic time division segment corresponding to the user terminal, and divide a day into multiple basic time division segments to form each time period corresponding to the user in a day.

[0023] Beneficial effect: In this scheme, the virtual machine usage requests corresponding to different user terminals are different. Therefore, when slicing the time period, the basic time division segments corresponding to different user terminals are different, that is, the dynamic change of the time period division of the virtual machine usage of the user terminal in a day is realized, which can meet the usage needs of the users of the user terminal, and at the same time, it can also better and more targetedly divide the time period of the virtual machine usage of the user terminal, thereby improving the reliability and scientificity of the division.

[0024] Furthermore, the weight setting strategy is:

[0025] According to the corresponding virtual machine usage type, a corresponding first basic weight value is set for each time period corresponding to the daytime, and a corresponding second basic weight value is set for each time period corresponding to the nighttime; when the corresponding virtual machine usage type is daytime usage, the first basic weight value is less than the second basic weight value; when the corresponding virtual machine usage type is nighttime usage, the first basic weight value is greater than the second basic weight value;

[0026] According to the number of idle times of the user corresponding to each historical time period of the user in a day, a first stable influence coefficient is set for the first basic weight value, and a second stable influence coefficient is set for the second basic weight value, and the idle stable weight values ​​corresponding to each time period of the user in a day are integrated to form the corresponding idle times of the user; the first stable influence coefficient and the second stable idle coefficient are both associated with the number of idle times of the user.

[0027] Beneficial effects: In this solution, according to the corresponding virtual machine usage type, the corresponding first basic weight value is set for each time period during the day, and the corresponding second basic weight value is set for each time period during the night; different virtual machine usage types have different corresponding first basic weight values ​​and second basic weight values, that is, they are dynamically adjusted, which greatly improves the rationality of the weight value setting. Secondly, the first stable influence coefficient and the second stable idle coefficient are both related to the number of user idle times, which further improves the rationality and reliability of the corresponding idle stable weight value setting, and provides reliable data support for subsequent data processing.

[0028] Furthermore, the user terminal includes:

[0029] A signal receiving feedback module is used to obtain the virtual machine sharing period corresponding to the user terminal on the virtual machine sharing platform, and send feedback information to the virtual machine sharing platform based on the virtual machine sharing period; the virtual machine sharing platform determines whether the virtual machine sharing period corresponding to the user terminal is a valid period according to the received feedback information, and if so, generates virtual machine sharing information corresponding to the user terminal based on the corresponding virtual machine sharing period;

[0030] An access module is used to obtain virtual machine sharing information corresponding to each other user terminal on the virtual machine sharing platform, and select the corresponding virtual machine sharing information to form a corresponding sharing use order;

[0031] The usage module is used to make corresponding order payments according to the shared usage order. After the payment is completed, the virtual machine of the user end corresponding to the virtual machine sharing information is installed to the user end corresponding to the payment completion, and the usage data corresponding to the virtual machine of the user end corresponding to the virtual machine sharing information is deleted synchronously.

[0032] Beneficial effects: In this solution, users on the user side can not only share the idle space of virtual machines, but also use the virtual machines of other user sides on the virtual machine sharing platform. Before using the virtual machines of other user sides, the usage data corresponding to the virtual machines will be deleted in time, so as to ensure the user data security of the user side sharing the virtual machine and improve the data security and reliability in the virtual machine sharing process.

[0033] The present invention also provides a virtual machine management method based on graphics card configuration, using the above-mentioned virtual machine management system based on graphics card configuration, comprising the following steps:

[0034] S1. Receive the corresponding sharing instruction information from the user end;

[0035] S2. After receiving the sharing instruction information from the user terminal, retrieve the historical usage information of the virtual machine corresponding to the corresponding user terminal; the historical usage information of the virtual machine includes the usage of the virtual machine corresponding to each time period in the history of the day;

[0036] S3. According to the corresponding virtual machine historical usage information, statistics are collected on the use of the virtual machine by the user in each historical time period of the day, and the number of idle times of the user corresponding to each historical time period of the day is determined. According to the corresponding number of idle times of the user, it is determined whether the corresponding virtual machine of the corresponding user is more idle during the day or during the night, and the virtual machine usage type of the corresponding user is determined according to the judgment result, and the virtual machine usage type includes daytime usage type and nighttime usage type.

[0037] S4. According to the virtual machine usage type corresponding to the user, the corresponding weight setting strategy is retrieved to set the idle stable weight value corresponding to the corresponding user in each time period of the day;

[0038] S5. According to the idle sharing time periods of virtual machines shared by other users in the virtual machine sharing platform, the number of user shares corresponding to each time period in a day is counted, and according to the number of user shares, the stable sharing weight value corresponding to each time period in a day on the virtual machine sharing platform is determined;

[0039] S6. According to the historical usage information of the virtual machine corresponding to the user terminal, based on the preset user sharing stability calculation formula, the user sharing stability corresponding to the corresponding user in each time period of the day is calculated, and the user sharing stability is associated with the idle stability weight value and the sharing stability weight value;

[0040] S7. Arrange the calculated user sharing stabilities corresponding to the users in various time periods of the day in descending order to form a sharing stability ranking table. Select the virtual machine sharing time period of the corresponding user terminal from the sharing stability ranking table in order according to the sharing quantity requirement, and transmit it to the virtual machine sharing platform. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 This is a logic block diagram of a virtual machine management system based on graphics card configuration in Embodiment 1 of the present invention;

[0042] Figure 2 This is a flowchart of a virtual machine management method based on graphics card configuration in Embodiment 1 of the present invention. DETAILED DESCRIPTION

[0043] The following is further described in detail through specific implementation methods:

[0044] Embodiment 1

[0045] A virtual machine management system based on graphics card configuration, basically like Figure 1 As shown, it includes a server and a user;

[0046] The server includes:

[0047] A sharing instruction receiving module, used for receiving the corresponding sharing instruction information from the user end;

[0048] A historical data retrieval module is used to retrieve the historical usage information of the virtual machine corresponding to the corresponding user terminal after receiving the sharing instruction information of the user terminal; the historical usage information of the virtual machine includes the usage of the virtual machine corresponding to each historical time period of a day;

[0049] It also includes a time period slicing module, which is used to count the usage time corresponding to each time the user corresponding to the user terminal uses the virtual machine according to the historical usage information of the virtual machine corresponding to the user terminal, set the corresponding usage weight value according to the number of times of each usage time, and calculate the time division basic segment corresponding to the user terminal, and divide a day into multiple time division basic segments to form the time periods corresponding to the user in a day. In this embodiment, for example, the usage time corresponding to each time a user uses the virtual machine is a hour, b hour, and c hour respectively, where the number of times corresponding to each usage time is x, y, and z respectively, and the usage weight value is set according to the corresponding number of times, for example, respectively. Then the calculation formula for dividing the basic time segment is:

[0050]

[0051] Then the 24 hours will be divided into multiple time periods according to each time period S. For example, when S=2, the 24 hours in a day will be divided into 12 time periods, each of which is 2 hours. When S=2, the 24 hours in a day will be divided into 8 time periods, each of which is 3 hours.

[0052] The identification module is used to collect statistics on the use of virtual machines by users in various historical time periods of a day according to the corresponding virtual machine historical use information, determine the number of user idle times corresponding to the user in various historical time periods of a day, and judge whether the corresponding virtual machine of the corresponding user is more idle during daytime or nighttime according to the corresponding user idle times, and determine the virtual machine use type of the corresponding user according to the judgment result, the virtual machine use type including daytime use type and nighttime use type; in this embodiment, the daytime period is from 9 am to 9 pm, and the night period is from 9 pm to 9 am.

[0053] The first processing module is used to retrieve the corresponding weight setting strategy according to the virtual machine usage type corresponding to the user, and set the idle stable weight value corresponding to the corresponding user in each time period of the day;

[0054] The weight setting strategy is:

[0055] According to the corresponding virtual machine usage type, a corresponding first basic weight value is set for each time period corresponding to the daytime, and a corresponding second basic weight value is set for each time period corresponding to the nighttime; when the corresponding virtual machine usage type is daytime usage, the first basic weight value is less than the second basic weight value; when the corresponding virtual machine usage type is nighttime usage, the first basic weight value is greater than the second basic weight value;

[0056] According to the number of idle times of the user corresponding to each time period in the history of the user in a day, a first stable influence coefficient is set for the first basic weight value, and a second stable influence coefficient is set for the second basic weight value, and the corresponding idle stable weight values ​​corresponding to each time period in a day are integrated; the first stable influence coefficient and the second stable idle coefficient are both associated with the number of idle times of the user. In this embodiment, the size of the corresponding first stable influence coefficient and the second stable influence coefficient is positively correlated with the number of idle times of the user corresponding to the corresponding time period. The greater the number of idle times of the user, the greater the corresponding stable influence coefficient, and the greater the calculated weight value, and the greater the probability of the time period being selected for sharing.

[0057] The second processing module is used to count the number of user shares corresponding to each time period in a day according to the idle sharing time period of the virtual machine shared by other user terminals in the virtual machine sharing platform, and determine the sharing stability weight value corresponding to each time period in a day on the virtual machine sharing platform according to the number of user shares;

[0058] The calculation module is used to calculate the user sharing stability corresponding to the corresponding user in each time period of the day based on the historical usage information of the virtual machine corresponding to the user terminal and the preset user sharing stability calculation formula, and the user sharing stability is associated with the idle stability weight value and the sharing stability weight value.

[0059] The preset user sharing stability calculation formula is:

[0060]

[0061] Where F is the user sharing stability corresponding to the user terminal, W1 is the idle stability weight value, W2 is the sharing stability weight value, and K i is the number of idle times of the virtual machine corresponding to the user end in time period i, K Zis the total number of idle times of the virtual machine corresponding to the user end in one day, and m is the total time period corresponding to the user end.

[0062] The sharing module is used to arrange the user sharing stabilities corresponding to the calculated users in various time periods of the day in descending order to form a sharing stability ranking table, and select the virtual machine sharing time period of the corresponding user terminal from the sharing stability ranking table in order according to the sharing quantity requirements, and transmit it to the virtual machine sharing platform.

[0063] The user terminal comprises:

[0064] A signal receiving feedback module is used to obtain the virtual machine sharing period corresponding to the user terminal on the virtual machine sharing platform, and send feedback information to the virtual machine sharing platform based on the virtual machine sharing period; the virtual machine sharing platform determines whether the virtual machine sharing period corresponding to the user terminal is a valid period according to the received feedback information, and if so, generates virtual machine sharing information corresponding to the user terminal based on the corresponding virtual machine sharing period;

[0065] An access module is used to obtain virtual machine sharing information corresponding to each other user terminal on the virtual machine sharing platform, and select the corresponding virtual machine sharing information to form a corresponding sharing use order;

[0066] The usage module is used to make corresponding order payments according to the shared usage order. After the payment is completed, the virtual machine of the user end corresponding to the virtual machine sharing information is installed to the user end corresponding to the payment completion, and the usage data corresponding to the virtual machine of the user end corresponding to the virtual machine sharing information is deleted synchronously.

[0067] like Figure 2 As shown, this embodiment also discloses a virtual machine management method based on graphics card configuration, using the above-mentioned virtual machine management system based on graphics card configuration, including the following steps:

[0068] S1. Receive the corresponding sharing instruction information from the user end;

[0069] S2. After receiving the sharing instruction information from the user terminal, retrieve the historical usage information of the virtual machine corresponding to the corresponding user terminal; the historical usage information of the virtual machine includes the usage of the virtual machine corresponding to each time period in the history of the day;

[0070] S3. According to the corresponding virtual machine historical usage information, statistics are collected on the use of the virtual machine by the user in each historical time period of the day, and the number of idle times of the user corresponding to each historical time period of the day is determined. According to the corresponding number of idle times of the user, it is determined whether the corresponding virtual machine of the corresponding user is more idle during the day or during the night, and the virtual machine usage type of the corresponding user is determined according to the judgment result, and the virtual machine usage type includes daytime usage type and nighttime usage type.

[0071] S4. According to the virtual machine usage type corresponding to the user, the corresponding weight setting strategy is retrieved to set the idle stable weight value corresponding to the corresponding user in each time period of the day;

[0072] S5. According to the idle sharing time periods of virtual machines shared by other users in the virtual machine sharing platform, the number of user shares corresponding to each time period in a day is counted, and according to the number of user shares, the stable sharing weight value corresponding to each time period in a day on the virtual machine sharing platform is determined;

[0073] S6. According to the historical usage information of the virtual machine corresponding to the user terminal, based on the preset user sharing stability calculation formula, the user sharing stability corresponding to the corresponding user in each time period of the day is calculated, and the user sharing stability is associated with the idle stability weight value and the sharing stability weight value.

[0074] S7. Arrange the calculated user sharing stabilities corresponding to the users in various time periods of the day in descending order to form a sharing stability ranking table. Select the virtual machine sharing time period of the corresponding user terminal from the sharing stability ranking table in order according to the sharing quantity requirement, and transmit it to the virtual machine sharing platform.

[0075] The above is only an embodiment of the present invention. The common sense such as the known specific structure and characteristics in the scheme is described too much here. The ordinary technicians in the relevant field know all the common technical knowledge in the technical field of the invention before the application date or priority date, can know all the existing technologies in the field, and have the ability to apply the conventional experimental means before that date. The ordinary technicians in the relevant field can improve and implement this scheme in combination with their own abilities under the enlightenment given by this application. Some typical known structures or known methods should not become obstacles for ordinary technicians in the relevant field to implement this application. It should be pointed out that for those skilled in the art, without departing from the structure of the present invention, several deformations and improvements can be made, which should also be regarded as the protection scope of the present invention, which will not affect the effect of the implementation of the present invention and the practicality of the patent. The protection scope required by this application shall be based on the content of its claims, and the specific implementation methods and other records in the specification can be used to interpret the content of the claims.

Claims

1. A virtual machine management system based on graphics card configuration, characterized in that: Including server and user side; The server includes: A sharing instruction receiving module, used for receiving the corresponding sharing instruction information from the user end; A historical data retrieval module is used to retrieve the historical usage information of the virtual machine corresponding to the corresponding user terminal after receiving the sharing instruction information of the user terminal; the historical usage information of the virtual machine includes the usage of the virtual machine corresponding to each historical time period of a day; an identification module, for collecting statistics on the use of virtual machines by users in various time periods of a day according to the corresponding virtual machine history use information, determining the number of idle times of the users corresponding to the various time periods of a day, and judging whether the corresponding virtual machines of the users are more idle during the day or at night according to the corresponding number of idle times of the users, and determining the virtual machine use type of the corresponding user according to the judgment result, wherein the virtual machine use type includes a daytime use type and a nighttime use type; The first processing module is used to retrieve the corresponding weight setting strategy according to the virtual machine usage type corresponding to the user, and set the idle stable weight value corresponding to the corresponding user in each time period of the day; The second processing module is used to count the number of user shares corresponding to each time period in a day according to the idle sharing time period of the virtual machine shared by other user terminals in the virtual machine sharing platform, and determine the sharing stability weight value corresponding to each time period in a day on the virtual machine sharing platform according to the number of user shares; A calculation module, for calculating the user sharing stability corresponding to the corresponding user in each time period of the day according to the historical usage information of the virtual machine corresponding to the user terminal and based on a preset user sharing stability calculation formula, wherein the user sharing stability is associated with an idle stability weight value and a sharing stability weight value; The sharing module is used to arrange the user sharing stabilities corresponding to the calculated users in various time periods of the day in descending order to form a sharing stability ranking table, and select the virtual machine sharing time period of the corresponding user terminal from the sharing stability ranking table in order according to the sharing quantity requirements, and transmit it to the virtual machine sharing platform.

2. The virtual machine management system based on graphics card configuration according to claim 1, characterized in that: The preset user sharing stability calculation formula is: Where F is the user sharing stability corresponding to the user terminal, W1 is the idle stability weight value, W2 is the sharing stability weight value, and K i is the number of idle times of the virtual machine corresponding to the user end in time period i, K Z is the total number of idle times of the virtual machine corresponding to the user end in one day, and m is the total time period corresponding to the user end.

3. The virtual machine management system based on graphics card configuration according to claim 2, characterized in that: It also includes a time period slicing module, which is used to count the usage time corresponding to the user corresponding to the user terminal each time the virtual machine is used according to the historical usage information of the virtual machine corresponding to the user terminal, set the corresponding usage weight value according to the number of times of each usage time, and calculate the basic time division segment corresponding to the user terminal, and divide a day into multiple basic time division segments to form each time period corresponding to the user in a day.

4. The virtual machine management system based on graphics card configuration according to claim 3, characterized in that: The weight setting strategy is: According to the corresponding virtual machine usage type, a corresponding first basic weight value is set for each time period corresponding to the daytime, and a corresponding second basic weight value is set for each time period corresponding to the nighttime; when the corresponding virtual machine usage type is daytime usage, the first basic weight value is less than the second basic weight value; when the corresponding virtual machine usage type is nighttime usage, the first basic weight value is greater than the second basic weight value; According to the number of idle times of the user corresponding to each historical time period of the user in a day, a first stable influence coefficient is set for the first basic weight value, and a second stable influence coefficient is set for the second basic weight value, and the idle stable weight values ​​corresponding to each time period of the user in a day are integrated to form the corresponding idle times of the user; the first stable influence coefficient and the second stable idle coefficient are both associated with the number of idle times of the user.

5. The virtual machine management system based on graphics card configuration according to claim 4, characterized in that: The user terminal comprises: A signal receiving feedback module is used to obtain the virtual machine sharing period corresponding to the user terminal on the virtual machine sharing platform, and send feedback information to the virtual machine sharing platform based on the virtual machine sharing period; the virtual machine sharing platform determines whether the virtual machine sharing period corresponding to the user terminal is a valid period according to the received feedback information, and if so, generates virtual machine sharing information corresponding to the user terminal based on the corresponding virtual machine sharing period; An access module is used to obtain virtual machine sharing information corresponding to each other user terminal on the virtual machine sharing platform, and select the corresponding virtual machine sharing information to form a corresponding sharing use order; The usage module is used to make corresponding order payments according to the shared usage order. After the payment is completed, the virtual machine of the user end corresponding to the virtual machine sharing information is installed to the user end corresponding to the payment completion, and the usage data corresponding to the virtual machine of the user end corresponding to the virtual machine sharing information is deleted synchronously.

6. A virtual machine management method based on graphics card configuration, using a virtual machine management system based on graphics card configuration according to any one of claims 1 to 3, characterized in that: The following steps are involved: S1. Receive the corresponding sharing instruction information from the user end; S2. After receiving the sharing instruction information from the user terminal, retrieve the historical usage information of the virtual machine corresponding to the corresponding user terminal; the historical usage information of the virtual machine includes the usage of the virtual machine corresponding to each time period in the history of the day; S3. According to the corresponding virtual machine historical usage information, statistics are collected on the use of the virtual machine by the user in each historical time period of the day, and the number of idle times of the user corresponding to each historical time period of the day is determined. According to the corresponding number of idle times of the user, it is determined whether the corresponding virtual machine of the corresponding user is more idle during the day or during the night, and the virtual machine usage type of the corresponding user is determined according to the judgment result, and the virtual machine usage type includes daytime usage type and nighttime usage type. S4. According to the virtual machine usage type corresponding to the user, the corresponding weight setting strategy is retrieved to set the idle stable weight value corresponding to the corresponding user in each time period of the day; S5. According to the idle sharing time periods of virtual machines shared by other users in the virtual machine sharing platform, the number of user shares corresponding to each time period in a day is counted, and according to the number of user shares, the stable sharing weight value corresponding to each time period in a day on the virtual machine sharing platform is determined; S6. According to the historical usage information of the virtual machine corresponding to the user terminal, based on the preset user sharing stability calculation formula, the user sharing stability corresponding to the corresponding user in each time period of the day is calculated, and the user sharing stability is associated with the idle stability weight value and the sharing stability weight value; S7. Arrange the calculated user sharing stabilities corresponding to the users in various time periods of the day in descending order to form a sharing stability ranking table. Select the virtual machine sharing time period of the corresponding user terminal from the sharing stability ranking table in order according to the sharing quantity requirement, and transmit it to the virtual machine sharing platform.