A resource intelligent scheduling system and method based on resource sharing cloud platform

Abstract

The present invention relates to the field of information sharing technology, and specifically to a resource intelligent scheduling system and method based on a resource sharing cloud platform. The system includes a cloud platform data processing module, an early warning condition generation module, an application processing optimization model construction module, and an emergency method generation module. The application processing optimization model construction module is used to obtain the status of the early warning device in real time based on the monitoring results of the system early warning device, and pre-process the operation behavior of the corresponding bound user in the cloud platform processing sequence in combination with the status of the early warning device. According to the pre-processing results and the CPU performance of the corresponding cloud host, an application processing optimization model is generated. The present invention monitors the application memory value required to be processed by the corresponding user in the cloud platform in real time, and rationally allocates it in combination with the CPU processing capacity of the corresponding cloud host, thereby not only improving the work efficiency of the corresponding cloud host, but also making full use of the processing capacity of the cloud host.

Description

Technical Field

[0001] The present invention relates to the field of information sharing technology, and specifically to a resource intelligent scheduling system and method based on a resource sharing cloud platform. Background Art

[0002] Compared to traditional desktop office methods, cloud desktops allow employees to access cloud desktops anytime, anywhere through any device (mobile phones, computers, tablets), easily realize document sharing and resource sharing, and save hardware costs through cloud desktop resource sharing. Cloud desktops can centrally manage applications. Administrators can centrally manage, deploy, and publish applications, and set permissions for applications without having to set up and update them on each device. This centralized management saves companies a lot of manpower and material costs. Compared with VDI solutions, virtual machines are created one by one. The user shared login method can maximize the efficiency of cloud host resources. The cloud host and cloud terminal are connected through remoteApp, achieving a stable connection from desktop to cloud terminal, no lag, and a good experience. Cloud hosts are intelligently allocated according to the cloud host resource situation. It has the characteristics of simple, flexible, and efficient deployment. However, the processing capacity of virtual machines is limited. Based on the different applications required by different users, the processing capacity of virtual machines cannot be fully utilized compared with traditional processing methods. Therefore, a resource intelligent scheduling system and method based on resource sharing cloud platform is needed. Summary of the Invention

[0003] The purpose of the present invention is to provide a resource intelligent scheduling system and method based on a resource sharing cloud platform to solve the problems raised in the above background technology. The present invention provides the following technical solutions:

[0004] A resource intelligent scheduling method based on a resource sharing cloud platform, the method comprising the following steps:

[0005] S1. Obtain the user information of the bound user and the corresponding user application data information through the cloud platform, and pre-process it in combination with the corresponding user data information;

[0006] S2. Based on the bound users of the current cloud platform, the corresponding user's operation behavior is obtained in combination with the cloud terminal request sequence, and the corresponding application processing condition value is analyzed in combination with the operation behavior and the corresponding cloud host CPU performance, and an early warning signal is generated according to the processing condition value of the corresponding application;

[0007] S3. Based on the monitoring results of the system early warning device, the status of the early warning device is obtained in real time. The operation behavior of the corresponding bound user in the cloud platform processing sequence is preprocessed in combination with the status of the early warning device. The application processing optimization model is generated based on the preprocessing results and the CPU performance of the corresponding cloud host;

[0008] S4. Adjust the corresponding cloud host application processing order in real time based on the application processing optimization model, and take emergency measures in real time based on the adjustment results based on the feedback results of the corresponding bound users.

[0009] Furthermore, the method in S1 includes the following steps:

[0010] Step 1001: Obtain user information of the bound user through the cloud platform, and obtain corresponding user application data information in combination with the corresponding user information, which is recorded as set A;

[0011] A=(A1,A2,A3,...,A n ),

[0012] Among them A n Indicates the application data information corresponding to the nth bound user, where n represents the number of users bound to the cloud platform. The application data information includes application type and application memory usage;

[0013] Step 1002: Based on the analysis results in step 1001, the elements with the same application type are divided and the corresponding applications are bundled with the corresponding application memory values. An application of any type is obtained and the memory values of the corresponding applications of type a are bundled as set B.

[0014]

[0015] in represents the mth application in the ath type, Indicates the memory usage corresponding to the mth application in the ath type, where m represents the number of applications of the same type;

[0016] Step 1003: Based on the analysis result in step 1002, obtain the first associated application of the corresponding application, and record the first associated application corresponding to the m-th application in the a-th type as a set

[0017]

[0018] in represents the i-th first associated application corresponding to the m-th application in the a-th type, where the first associated application is a preset value;

[0019] Step 1004: Based on the analysis results in step 1003, loop step 1002 to obtain the application memory usage value of each first associated application, and bundle the application memory usage value with the corresponding first associated application. Combine the corresponding application with the corresponding first associated application based on the bundling result, and combine the mth application in the ath type with the corresponding first associated application to generate a combination D, where

[0020] Step 1005: loop through steps 1002 to 1004 to obtain a combination of different types of corresponding applications and corresponding first associated applications, which is recorded as set E.

[0021] E=(E1,E2,E3,...,E j ),

[0022] Among them E j represents the jth combination, where j represents the number of combinations of corresponding applications of different types and corresponding first associated applications.

[0023] The present invention obtains user information of bound users through the cloud platform, and obtains corresponding application data information in combination with the corresponding user information, divides the obtained application data information into types, analyzes the first association relationship between the corresponding applications in turn, and combines the applications with the first association relationship, thereby providing data reference for subsequent optimization of cloud host CPU resource utilization.

[0024] Furthermore, the method in S2 includes the following steps:

[0025] Step 2001: Based on the bound user of the current cloud platform, the corresponding user's operation behavior is obtained in combination with the cloud terminal request sequence. The operation behavior represents the data that the corresponding user needs to transmit and the processing method of the corresponding data. The processing method is a preset value in the database.

[0026] Obtain the cloud platform processing sequence according to the cloud terminal request sequence, recorded as sequence F.

[0027] F=(F1,F2,F3,...,F k ), k=n,

[0028] Among them F k Indicates the kth bound user in the cloud platform processing sequence;

[0029] Step 2002: Based on the analysis results in step 2001, the operation behaviors of each bound user are obtained in sequence. Combined with the operation behaviors and the CPU performance of the corresponding cloud host, it is determined whether the conditions for the corresponding cloud host to process the corresponding application in the platform processing sequence meet the requirements.

[0030] If the memory usage of the corresponding application in the current bound user's operation behavior is within the processing capacity of the corresponding cloud host CPU, no warning signal will be issued.

[0031] If the memory usage of the corresponding application in the operation behavior of the currently bound user is not within the processing capacity range of the corresponding cloud host CPU, an early warning signal will be issued. The processing capacity range is the preset value of the database.

[0032] The present invention obtains the operation behavior of the corresponding user by combining the cloud terminal request sequence, and generates the corresponding processing sequence of the cloud host according to the data required to be transmitted in the corresponding user operation behavior and the processing method of the corresponding data, and judges whether it meets the CPU processing capacity of the corresponding cloud host in combination with the memory usage value of the application to be processed, and then generates an early warning signal in combination with the judgment result to provide data reference for subsequent adjustment of the processing sequence.

[0033] Furthermore, the method in S3 includes the following steps:

[0034] Step 3001: Based on the monitoring results of the system early warning device, the status of the early warning device is obtained in real time. In combination with the monitoring results, the corresponding applications in the operation behaviors of each bound user in the monitored area are obtained. Based on the analysis results in steps 1002 and 1005, the memory usage values of the combinations of different types of corresponding applications and the corresponding first associated applications are obtained.

[0035] Step 3002: Combined with the analysis results in step 3001, pre-process the operation behavior of the corresponding bound user in the cloud platform processing sequence.

[0036] If the system warning device does not receive the warning signal, it will perform corresponding application processing according to the current cloud platform processing sequence.

[0037] If the system early warning device receives an early warning signal, it pre-processes the corresponding application of the corresponding bound user in the current cloud platform processing sequence, obtains the task information of any cloud host, analyzes the resource utilization of the corresponding cloud host in combination with the task information, and records the memory usage of the corresponding application in the task information of the a-th cloud host as The resource utilization rate of the a-th cloud host is recorded as Utilize a ,

[0038]

[0039] Where α represents the proportional coefficient, which is a preset value in the database. Indicates the CPU processing capacity of the a-th cloud host, which is the default value of the database;

[0040] Step 3003: loop step 3002 to obtain the comprehensive resource utilization of the corresponding cloud host, which is recorded as comprehensive.

[0041]

[0042] Utilize b represents the resource utilization of the bth cloud host, and c represents the number of cloud hosts in the corresponding area of the cloud platform;

[0043] Step 3004: Based on the analysis results in step 3003, determine whether the current resource utilization rate meets the standard. If the comprehensive resource utilization rate of the current cloud host is within the preset range, it indicates that the resource utilization rate of the current cloud host meets the standard. If the comprehensive resource utilization rate of the current cloud host is not within the preset range, it indicates that the resource utilization rate of the current cloud host does not meet the standard.

[0044] Step 3005: Based on the analysis results in step 3004, further adjust the corresponding application processing mechanism in the cloud platform processing sequence where the resource utilization rate does not meet the standard.

[0045] Obtain the analysis results in step 1005, and combine the total value of the occupied value applied in each combination, sort the elements in the set E in descending order according to the total value of the occupied value, and record it as sequence E * ,

[0046]

[0047] in It represents the jth combination after sorting the total value from large to small.

[0048] According to the corresponding cloud host CPU processing capacity, the application is rationalized and an application processing optimization model is generated, which is recorded as Model.

[0049]

[0050] Where H() represents the judgment function. hour, represents the u-th combination, Represents the vth combination, where u≠v and both u and v are less than j, min() represents the minimum function, when hour, when and When , the Model output result is 1, otherwise the Mode output is 0;

[0051] Step 3006: Based on the analysis results in step 3005, analyze the sequence E in sequence based on the application processing optimization model. * The degree of fit between the elements in the sequence E * The relationship between the memory usage of any number of elements and the processing capacity of the corresponding cloud host is extracted, and the combination with the output result of 1 is extracted. Based on the sequence E * Sort the elements in the sequence and interpolate them. Insert the elements with output result 1 into the corresponding elements one by one, and then update the sequence E. * Get a new sequence, denoted as E ** ,

[0052]

[0053] in Represents the jth combination after the update sequence.

[0054] The present invention determines whether the efficiency of the corresponding cloud host in processing applications meets the standards by calculating the resource utilization rate of the corresponding cloud host, and generates an application processing optimization model based on the judgment result. The order of applications to be processed is adjusted according to the application processing optimization model, thereby ensuring that the processing capacity of the cloud host is fully utilized.

[0055] Furthermore, the method in S4 includes the following steps:

[0056] Step 4001: Obtain the analysis result in step 3006, and obtain feedback results of each bound user in the current cloud platform, wherein the feedback results represent the expected application time value of the corresponding bound user for the required processing;

[0057] Step 4002: Based on the analysis results in step 4001, obtain the feedback results of any bound user and record the feedback results of the hth user as F h , and combined with the application corresponding to the h-th bound user in the new sequence E ** The sequence number in the h-1th bound user is combined with the bound user feedback result corresponding to the application to be processed by the bound user to take emergency measures in real time.

[0058] If the expected application time for the processing required in the feedback result of the h-1th bound user is greater than the expected application time for the processing required in the feedback result of the hth bound user, then the application corresponding to the hth bound user is placed in the new sequence E ** The sequence number in the new sequence E corresponds to the application of the h-1th bound user. ** The sequence numbers in the exchange processing order,

[0059] If the expected application time for the required processing in the feedback result of the h-1th bound user is less than or equal to the expected application time for the required processing in the feedback result of the hth bound user, the order of the sequence elements remains unchanged.

[0060] A resource intelligent scheduling system based on a resource sharing cloud platform, the system includes the following modules:

[0061] Cloud platform data processing module: The cloud platform data processing module is used to obtain user information of bound users and corresponding user application data information through the cloud platform, and perform preprocessing based on the corresponding user data information;

[0062] Warning condition generation module: The warning condition generation module is used to obtain the corresponding user's operation behavior based on the current cloud platform's bound users and the cloud terminal request sequence, and analyze the corresponding application processing condition value based on the operation behavior and the corresponding cloud host CPU performance, and generate a warning signal according to the processing condition value of the corresponding application;

[0063] Application processing optimization model construction module: The application processing optimization model construction module is used to obtain the status of the early warning device in real time based on the monitoring results of the system early warning device, and pre-process the operation behavior of the corresponding bound user in the cloud platform processing sequence based on the status of the early warning device. Based on the pre-processing results and the corresponding cloud host CPU performance, an application processing optimization model is generated;

[0064] Emergency method generation module: The emergency method generation module is used to adjust the corresponding cloud host application processing sequence in real time in combination with the application processing optimization model, and take emergency measures in real time based on the adjustment results in combination with the feedback results of the corresponding bound users.

[0065] Furthermore, the cloud platform data processing module includes a data acquisition unit and a first correlation analysis unit:

[0066] The data acquisition unit is used to obtain user information of the bound user through the cloud platform, and obtain corresponding user application data information in combination with the corresponding user information;

[0067] The first association analysis unit is used to classify user application types based on the analysis result of the data collection unit, and match first associated applications with corresponding users.

[0068] Furthermore, the warning condition generation module includes a cloud platform processing sequence generation unit and a condition compliance judgment unit:

[0069] The cloud platform processing sequence generating unit is used to generate a cloud platform processing sequence in combination with the ordering method of the cloud terminal request sequence;

[0070] The condition compliance judgment unit is used to judge the compliance of the corresponding application memory usage value and the corresponding cloud host CPU processing capacity in the corresponding bound user's operation behavior in combination with the analysis results of the cloud platform processing sequence generation unit.

[0071] Furthermore, the application processing optimization model construction module includes a resource utilization analysis unit, an application processing optimization model construction unit, and a preprocessing priority sequence generation unit:

[0072] The resource utilization analysis unit is used to calculate the resource utilization rate of the corresponding cloud host in combination with the task information of the corresponding cloud host;

[0073] The application processing optimization model building unit is used to combine the analysis results of the resource utilization analysis unit with the corresponding cloud host CPU processing capacity to perform application rationalization processing, and generate an application processing optimization model based on the processing results;

[0074] The preprocessing priority sequence generating unit is used to generate a preprocessing priority sequence in combination with the analysis result of the application processing optimization model building unit.

[0075] Furthermore, the emergency method generation module includes a feedback result acquisition unit and an emergency plan implementation unit:

[0076] The feedback result acquisition unit is used to obtain the feedback results of each bound user in the current cloud platform;

[0077] The emergency plan implementation unit is used to determine whether the processing order of the corresponding applications can be adjusted based on the analysis result of the feedback result acquisition unit.

[0078] The present invention monitors the memory usage of applications that need to be processed by corresponding users in the cloud platform in real time, and rationally allocates them in combination with the CPU processing capacity of the corresponding cloud host, thereby not only improving the work efficiency of the corresponding cloud host, but also making full use of the processing capacity of the cloud host, and can personalize the order of application processing according to user feedback, further improving user satisfaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0079] Figure 1 This is a flow chart of a resource intelligent scheduling method based on a resource sharing cloud platform of the present invention;

[0080] Figure 2 This is a module diagram of a resource intelligent scheduling system based on a resource sharing cloud platform of the present invention. DETAILED DESCRIPTION

[0081] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only 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 making creative efforts are within the scope of protection of the present invention.

[0082] Example 1: Please refer to Figure 1 , in this embodiment:

[0083] A resource intelligent scheduling method based on a resource sharing cloud platform, the method comprising the following steps:

[0084] S1. Obtain the user information of the bound user and the corresponding user application data information through the cloud platform, and pre-process it in combination with the corresponding user data information;

[0085] The method in S1 comprises the following steps:

[0086] Step 1001: Obtain user information of the bound user through the cloud platform, and obtain corresponding user application data information in combination with the corresponding user information, which is recorded as set A;

[0087] A=(A1,A2,A3,...,A n ),

[0088] Among them A n Indicates the application data information corresponding to the nth bound user, where n represents the number of users bound to the cloud platform. The application data information includes application type and application memory usage;

[0089] Step 1002: Based on the analysis results in step 1001, the elements with the same application type are divided and the corresponding applications are bundled with the corresponding application memory values. An application of any type is obtained and the memory values of the corresponding applications of type a are bundled as set B.

[0090]

[0091] in represents the mth application in the ath type, Indicates the memory usage corresponding to the mth application in the ath type, where m represents the number of applications of the same type;

[0092] Step 1003: Based on the analysis result in step 1002, obtain the first associated application of the corresponding application, and record the first associated application corresponding to the m-th application in the a-th type as a set

[0093]

[0094] in represents the i-th first associated application corresponding to the m-th application in the a-th type, where the first associated application is a preset value;

[0095] Step 1004: Based on the analysis results in step 1003, loop step 1002 to obtain the application memory usage value of each first associated application, and bundle the application memory usage value with the corresponding first associated application. Combine the corresponding application with the corresponding first associated application based on the bundling result, and combine the mth application in the ath type with the corresponding first associated application to generate a combination D, where

[0096] Step 1005: loop through steps 1002 to 1004 to obtain a combination of different types of corresponding applications and corresponding first associated applications, which is recorded as set E.

[0097] E=(E1,E2,E3,...,E j ),

[0098] Among them E j represents the jth combination, where j represents the number of combinations of corresponding applications of different types and corresponding first associated applications.

[0099] S2. Based on the bound users of the current cloud platform, the corresponding user's operation behavior is obtained in combination with the cloud terminal request sequence, and the corresponding application processing condition value is analyzed in combination with the operation behavior and the corresponding cloud host CPU performance, and an early warning signal is generated according to the processing condition value of the corresponding application;

[0100] The method in S2 comprises the following steps:

[0101] Step 2001: Based on the bound user of the current cloud platform, the corresponding user's operation behavior is obtained in combination with the cloud terminal request sequence. The operation behavior represents the data that the corresponding user needs to transmit and the processing method of the corresponding data. The processing method is a preset value in the database.

[0102] Obtain the cloud platform processing sequence according to the cloud terminal request sequence, recorded as sequence F.

[0103] F=(F1,F2,F3,...,F k ), k=n,

[0104] Among them F k Indicates the kth bound user in the cloud platform processing sequence;

[0105] Step 2002: Based on the analysis results in step 2001, the operation behaviors of each bound user are obtained in sequence. Combined with the operation behaviors and the CPU performance of the corresponding cloud host, it is determined whether the conditions for the corresponding cloud host to process the corresponding application in the platform processing sequence meet the requirements.

[0106] If the memory usage of the corresponding application in the current bound user's operation behavior is within the processing capacity of the corresponding cloud host CPU, no warning signal will be issued.

[0107] If the memory usage of the corresponding application in the operation behavior of the currently bound user is not within the processing capacity range of the corresponding cloud host CPU, an early warning signal will be issued. The processing capacity range is the preset value of the database.

[0108] S3. Based on the monitoring results of the system early warning device, the status of the early warning device is obtained in real time. The operation behavior of the corresponding bound user in the cloud platform processing sequence is preprocessed in combination with the status of the early warning device. The application processing optimization model is generated based on the preprocessing results and the CPU performance of the corresponding cloud host;

[0109] The method in S3 comprises the following steps:

[0110] Step 3001: Based on the monitoring results of the system early warning device, the status of the early warning device is obtained in real time. In combination with the monitoring results, the corresponding applications in the operation behaviors of each bound user in the monitored area are obtained. Based on the analysis results in steps 1002 and 1005, the memory usage values of the combinations of different types of corresponding applications and the corresponding first associated applications are obtained.

[0111] Step 3002: Combined with the analysis results in step 3001, pre-process the operation behavior of the corresponding bound user in the cloud platform processing sequence.

[0112] If the system warning device does not receive the warning signal, it will perform corresponding application processing according to the current cloud platform processing sequence.

[0113] If the system early warning device receives an early warning signal, it pre-processes the corresponding application of the corresponding bound user in the current cloud platform processing sequence, obtains the task information of any cloud host, analyzes the resource utilization of the corresponding cloud host in combination with the task information, and records the memory usage of the corresponding application in the task information of the a-th cloud host as The resource utilization rate of the ath cloud host is recorded as Utileize a ,

[0114]

[0115] Where α represents the proportional coefficient, which is a preset value in the database. Indicates the CPU processing capacity of the a-th cloud host, which is the default value of the database;

[0116] Step 3003: loop step 3002 to obtain the comprehensive resource utilization of the corresponding cloud host, which is recorded as comprehensive.

[0117]

[0118] Utilize b represents the resource utilization of the bth cloud host, and c represents the number of cloud hosts in the corresponding area of the cloud platform;

[0119] Step 3004: Based on the analysis results in step 3003, determine whether the current resource utilization rate meets the standard. If the comprehensive resource utilization rate of the current cloud host is within the preset range, it indicates that the resource utilization rate of the current cloud host meets the standard. If the comprehensive resource utilization rate of the current cloud host is not within the preset range, it indicates that the resource utilization rate of the current cloud host does not meet the standard.

[0120] Step 3005: Based on the analysis results in step 3004, further adjust the corresponding application processing mechanism in the cloud platform processing sequence where the resource utilization rate does not meet the standard.

[0121] Obtain the analysis results in step 1005, and combine the total value of the occupied value applied in each combination, sort the elements in the set E in descending order according to the total value of the occupied value, and record it as sequence E * ,

[0122]

[0123] in It represents the jth combination after sorting the total value from large to small.

[0124] According to the corresponding cloud host CPU processing capacity, the application is rationalized and an application processing optimization model is generated, which is recorded as Model.

[0125]

[0126] Where H() represents the judgment function. hour, represents the u-th combination, Represents the vth combination, where u≠v and both u and v are less than j, min() represents the minimum function, when hour, when and When , the Model output result is 1, otherwise the Mode output is 0;

[0127] Step 3006: Based on the analysis results in step 3005, analyze the sequence E in sequence based on the application processing optimization model. * The degree of fit between the elements in the sequence E * The relationship between the memory usage of any number of elements and the processing capacity of the corresponding cloud host is extracted, and the combination with the output result of 1 is extracted. Based on the sequence E * Sort the elements in the sequence and interpolate them. Insert the elements with output result 1 into the corresponding elements one by one, and then update the sequence E. * Get a new sequence, denoted as E ** ,

[0128]

[0129] in Represents the jth combination after the updated sequence.

[0130] S4. Adjust the corresponding cloud host application processing order in real time based on the application processing optimization model, and take emergency measures in real time based on the adjustment results based on the feedback results of the corresponding bound users.

[0131] The method in S4 comprises the following steps:

[0132] Step 4001: Obtain the analysis result in step 3006, and obtain feedback results of each bound user in the current cloud platform, wherein the feedback results represent the expected application time value of the corresponding bound user for the required processing;

[0133] Step 4002: Based on the analysis results in step 4001, obtain the feedback results of any bound user and record the feedback results of the hth user as F h , and combined with the application corresponding to the h-th bound user in the new sequence E ** The sequence number in the h-1th bound user is combined with the bound user feedback result corresponding to the application to be processed by the bound user to take emergency measures in real time.

[0134] If the expected application time for the processing required in the feedback result of the h-1th bound user is greater than the expected application time for the processing required in the feedback result of the hth bound user, then the application corresponding to the hth bound user is placed in the new sequence E ** The sequence number in the new sequence E corresponds to the application of the h-1th bound user. ** The sequence numbers in the exchange processing order,

[0135] If the expected application time for the required processing in the feedback result of the h-1th bound user is less than or equal to the expected application time for the required processing in the feedback result of the hth bound user, the order of the sequence elements remains unchanged.

[0136] In this embodiment: a resource intelligent scheduling system based on a resource sharing cloud platform is disclosed (such as Figure 2 As shown), the system is used to implement the specific solution content of the method, and the system includes the following modules:

[0137] Cloud platform data processing module: The cloud platform data processing module is used to obtain user information of bound users and corresponding user application data information through the cloud platform, and perform preprocessing based on the corresponding user data information;

[0138] Warning condition generation module: The warning condition generation module is used to obtain the corresponding user's operation behavior based on the current cloud platform's bound users and the cloud terminal request sequence, and analyze the corresponding application processing condition value based on the operation behavior and the corresponding cloud host CPU performance, and generate a warning signal according to the processing condition value of the corresponding application;

[0139] Application processing optimization model construction module: The application processing optimization model construction module is used to obtain the status of the early warning device in real time based on the monitoring results of the system early warning device, and pre-process the operation behavior of the corresponding bound user in the cloud platform processing sequence based on the status of the early warning device. Based on the pre-processing results and the corresponding cloud host CPU performance, an application processing optimization model is generated;

[0140] Emergency method generation module: The emergency method generation module is used to adjust the corresponding cloud host application processing sequence in real time in combination with the application processing optimization model, and take emergency measures in real time based on the adjustment results in combination with the feedback results of the corresponding bound users.

[0141] The cloud platform data processing module includes a data acquisition unit and a first correlation analysis unit:

[0142] The data acquisition unit is used to obtain user information of the bound user through the cloud platform, and obtain corresponding user application data information in combination with the corresponding user information;

[0143] The first association analysis unit is used to classify user application types based on the analysis result of the data collection unit, and match first associated applications with corresponding users.

[0144] The warning condition generation module includes a cloud platform processing sequence generation unit and a condition compliance judgment unit:

[0145] The cloud platform processing sequence generating unit is used to generate a cloud platform processing sequence in combination with the ordering method of the cloud terminal request sequence;

[0146] The condition compliance judgment unit is used to judge the compliance of the corresponding application memory usage value and the corresponding cloud host CPU processing capacity in the corresponding bound user's operation behavior in combination with the analysis results of the cloud platform processing sequence generation unit.

[0147] The application processing optimization model construction module includes a resource utilization analysis unit, an application processing optimization model construction unit, and a preprocessing priority sequence generation unit:

[0148] The resource utilization analysis unit is used to calculate the resource utilization rate of the corresponding cloud host in combination with the task information of the corresponding cloud host;

[0149] The application processing optimization model building unit is used to combine the analysis results of the resource utilization analysis unit with the corresponding cloud host CPU processing capacity to perform application rationalization processing, and generate an application processing optimization model based on the processing results;

[0150] The preprocessing priority sequence generating unit is used to generate a preprocessing priority sequence in combination with the analysis result of the application processing optimization model building unit.

[0151] The emergency method generation module includes a feedback result acquisition unit and an emergency plan implementation unit:

[0152] The feedback result acquisition unit is used to obtain the feedback results of each bound user in the current cloud platform;

[0153] The emergency plan implementation unit is used to determine whether the processing order of the corresponding applications can be adjusted based on the analysis result of the feedback result acquisition unit.

[0154] Example 2: Obtain application data information that needs to be processed by the Ath bound user in the current cloud platform, where the applications to be processed include application a, application b, application c, and application d, where application a occupies Z memory. a , application b occupies Z b , application c occupies Z c , application d occupies Z d , application a and application d are the first associated application relationship. Based on the current system processing order of application a, application b, application c and application d, it is calculated that the comprehensive resource utilization rate of the current cloud host is comprehensive.

[0155]

[0156] Based on the calculation results, it is known that the comprehensive resource utilization of the current cloud host does not meet the requirements. Therefore, the current system processing order is adjusted to application a, application d, application b, and application c.

[0157] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above and that the invention can be embodied in other specific forms without departing from the spirit or essential characteristics of the invention. Therefore, the embodiments should be considered in all respects as illustrative and non-restrictive, and the scope of the invention is defined by the appended claims, not the foregoing description, and all variations within the meaning and range of equivalents of the claims are intended to be included therein. Any reference sign in a claim should not be construed as limiting the claim to which it relates.

[0158] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0159] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art will be able to modify the technical solutions described in the aforementioned embodiments or substitute equivalents for some of the technical features. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

Claims

1. A resource intelligent scheduling method based on a resource sharing cloud platform, characterized in that: The method comprises the following steps: S1. Obtain the user information of the bound user and the corresponding user application data information through the cloud platform, and pre-process it in combination with the corresponding user data information; S2. Based on the bound users of the current cloud platform, the corresponding user's operation behavior is obtained in combination with the cloud terminal request sequence, and the corresponding application processing condition value is analyzed in combination with the operation behavior and the corresponding cloud host CPU performance, and an early warning signal is generated according to the processing condition value of the corresponding application; S3. Based on the monitoring results of the system early warning device, the status of the early warning device is obtained in real time. The operation behavior of the corresponding bound user in the cloud platform processing sequence is preprocessed in combination with the status of the early warning device. The application processing optimization model is generated based on the preprocessing results and the CPU performance of the corresponding cloud host; According to the corresponding cloud host CPU processing capacity, the application is rationalized and an application processing optimization model is generated, which is recorded as Model. Where H() represents the judgment function, Indicates the CPU processing capacity of the a-th cloud host. The processing capacity is the default value of the database. hour, represents the u-th combination, Represents the vth combination, where u≠v and both u and v are less than j, min() represents the minimum function, when hour, when and When , the Model output is 1, otherwise the Model output is 0; S4. Adjust the corresponding cloud host application processing order in real time based on the application processing optimization model, and take emergency measures in real time based on the adjustment results based on the feedback results of the corresponding bound users.

2. A resource intelligent scheduling method based on a resource sharing cloud platform according to claim 1, characterized in that: The method in S1 comprises the following steps: Step 1001: Obtain user information of the bound user through the cloud platform, and obtain corresponding user application data information in combination with the corresponding user information, which is recorded as set A; <h2 style=";text-align:left;direction:ltr">A=(A1, A2, A3,..., A<h2 style=";text-align:left;direction:ltr"> n <h2 style=";text-align:left;direction:ltr"> ), Among them A n Indicates the application data information corresponding to the nth bound user, where n represents the number of users bound to the cloud platform. The application data information includes application type and application memory usage; Step 1002: Based on the analysis results in step 1001, the elements with the same application type are divided and the corresponding applications are bundled with the corresponding application memory values. An application of any type is obtained and the memory values of the corresponding applications of type a are bundled as set B. in represents the mth application in the ath type, Indicates the memory usage corresponding to the mth application in the ath type, where m represents the number of applications of the same type; Step 1003: Based on the analysis result in step 1002, obtain the first associated application of the corresponding application, and record the first associated application corresponding to the m-th application in the a-th type as a set in represents the i-th first associated application corresponding to the m-th application in the a-th type, where the first associated application is a preset value; Step 1004: Based on the analysis results in step 1003, loop step 1002 to obtain the application memory usage value of each first associated application, and bundle the application memory usage value with the corresponding first associated application. Combine the corresponding application with the corresponding first associated application based on the bundling result, and combine the mth application in the ath type with the corresponding first associated application to generate a combination D, where Step 1005: loop through steps 1002 to 1004 to obtain a combination of different types of corresponding applications and corresponding first associated applications, which is recorded as set E. E=(E1,E2,E3,...,E j ), Among them E j represents the jth combination, where j represents the number of combinations of corresponding applications of different types and corresponding first associated applications.

3. The resource intelligent scheduling method based on the resource sharing cloud platform according to claim 2 is characterized in that: The method in S2 comprises the following steps: Step 2001: Based on the bound user of the current cloud platform, the corresponding user's operation behavior is obtained in combination with the cloud terminal request sequence. The operation behavior represents the data that the corresponding user needs to transmit and the processing method of the corresponding data. The processing method is a preset value in the database. Obtain the cloud platform processing sequence according to the cloud terminal request sequence, recorded as sequence F. <h2 style=";text-align:left;direction:ltr">F=(F1, F2, F3,..., F<h2 style=";text-align:left;direction:ltr"> k <h2 style=";text-align:left;direction:ltr"> ),k=n, Among them F k Indicates the kth bound user in the cloud platform processing sequence; Step 2002: Based on the analysis results in step 2001, the operation behaviors of each bound user are obtained in sequence. Combined with the operation behaviors and the CPU performance of the corresponding cloud host, it is determined whether the conditions for the corresponding cloud host to process the corresponding application in the platform processing sequence meet the requirements. If the memory usage of the corresponding application in the current bound user's operation behavior is within the processing capacity of the corresponding cloud host CPU, no warning signal will be issued. If the memory usage of the corresponding application in the operation behavior of the currently bound user is not within the processing capacity range of the corresponding cloud host CPU, an early warning signal will be issued. The processing capacity range is the preset value of the database.

4. The resource intelligent scheduling method based on the resource sharing cloud platform according to claim 3 is characterized in that: The method in S3 comprises the following steps: Step 3001: Based on the monitoring results of the system early warning device, the status of the early warning device is obtained in real time. In combination with the monitoring results, the corresponding applications in the operation behaviors of each bound user in the monitored area are obtained. Based on the analysis results in steps 1002 and 1005, the memory usage values of the combinations of different types of corresponding applications and the corresponding first associated applications are obtained. Step 3002: Combined with the analysis results in step 3001, pre-process the operation behavior of the corresponding bound user in the cloud platform processing sequence. If the system warning device does not receive the warning signal, it will perform corresponding application processing according to the current cloud platform processing sequence. If the system early warning device receives an early warning signal, it pre-processes the corresponding application of the corresponding bound user in the current cloud platform processing sequence, obtains the task information of any cloud host, analyzes the resource utilization of the corresponding cloud host in combination with the task information, and records the memory usage of the corresponding application in the task information of the a-th cloud host as The resource utilization rate of the a-th cloud host is recorded as Utilize a , Wherein ɑ represents the proportional coefficient, which is a preset value in the database; Step 3003: loop step 3002 to obtain the comprehensive resource utilization of the corresponding cloud host, which is recorded as comprehensive. Utilize b represents the resource utilization of the bth cloud host, and c represents the number of cloud hosts in the corresponding area of the cloud platform; Step 3004: Based on the analysis results in step 3003, determine whether the current resource utilization rate meets the standard. If the comprehensive resource utilization rate of the current cloud host is within the preset range, it indicates that the resource utilization rate of the current cloud host meets the standard. If the comprehensive resource utilization rate of the current cloud host is not within the preset range, it indicates that the resource utilization rate of the current cloud host does not meet the standard. Step 3005: Based on the analysis results in step 3004, further adjust the corresponding application processing mechanism in the cloud platform processing sequence where the resource utilization rate does not meet the standard. Obtain the analysis results in step 1005, and combine the total value of the occupied value applied in each combination, sort the elements in the set E in descending order according to the total value of the occupied value, and record it as sequence E * , in It represents the jth combination after sorting the total value from large to small. Step 3006: Based on the analysis results in step 3005, analyze the sequence E in sequence based on the application processing optimization model. * The degree of fit between the elements in the sequence E * The relationship between the memory usage of any number of elements and the processing capacity of the corresponding cloud host is extracted, and the combination with the output result of 1 is extracted. Based on the sequence E * Sort the elements in the sequence and interpolate them. Insert the elements with output result 1 into the corresponding elements one by one, and then update the sequence E. * Get a new sequence, denoted as E ** , in Represents the jth combination after the updated sequence.

5. The resource intelligent scheduling method based on the resource sharing cloud platform according to claim 4 is characterized in that: The method in S4 comprises the following steps: Step 4001: Obtain the analysis result in step 3006, and obtain feedback results of each bound user in the current cloud platform, wherein the feedback results represent the expected application time value of the corresponding bound user for the required processing; Step 4002: Based on the analysis results in step 4001, obtain the feedback results of any bound user and record the feedback results of the hth user as F h , and combined with the application corresponding to the h-th bound user in the new sequence E ** The sequence number in the h-1th bound user is combined with the bound user feedback result corresponding to the application to be processed by the bound user to take emergency measures in real time. If the expected application time for the processing required in the feedback result of the h-1th bound user is greater than the expected application time for the processing required in the feedback result of the hth bound user, then the application corresponding to the hth bound user is placed in the new sequence E ** The sequence number in the new sequence E corresponds to the application of the h-1th bound user. ** The sequence numbers in the exchange processing order, If the expected application time for the required processing in the feedback result of the h-1th bound user is less than or equal to the expected application time for the required processing in the feedback result of the hth bound user, the order of the sequence elements remains unchanged.

6. A resource intelligent scheduling system based on a resource sharing cloud platform, which is applied to a resource intelligent scheduling method based on a resource sharing cloud platform according to any one of claims 1 to 5, characterized in that: The system includes the following modules: Cloud platform data processing module: The cloud platform data processing module is used to obtain user information of bound users and corresponding user application data information through the cloud platform, and perform preprocessing based on the corresponding user data information; Warning condition generation module: The warning condition generation module is used to obtain the corresponding user's operation behavior based on the current cloud platform's bound users and the cloud terminal request sequence, and analyze the corresponding application processing condition value based on the operation behavior and the corresponding cloud host CPU performance, and generate a warning signal according to the processing condition value of the corresponding application; Application processing optimization model construction module: The application processing optimization model construction module is used to obtain the status of the early warning device in real time based on the monitoring results of the system early warning device, and pre-process the operation behavior of the corresponding bound user in the cloud platform processing sequence based on the status of the early warning device. Based on the pre-processing results and the corresponding cloud host CPU performance, an application processing optimization model is generated; Emergency method generation module: The emergency method generation module is used to adjust the corresponding cloud host application processing sequence in real time in combination with the application processing optimization model, and take emergency measures in real time based on the adjustment results in combination with the feedback results of the corresponding bound users.

7. The resource intelligent scheduling system based on the resource sharing cloud platform according to claim 6 is characterized in that: The cloud platform data processing module includes a data acquisition unit and a first correlation analysis unit: The data acquisition unit is used to obtain user information of the bound user through the cloud platform, and obtain corresponding user application data information in combination with the corresponding user information; The first association analysis unit is used to classify user application types based on the analysis result of the data collection unit, and match first associated applications with corresponding users.

8. The resource intelligent scheduling system based on the resource sharing cloud platform according to claim 7 is characterized in that: The warning condition generation module includes a cloud platform processing sequence generation unit and a condition compliance judgment unit: The cloud platform processing sequence generating unit is used to generate a cloud platform processing sequence in combination with the ordering method of the cloud terminal request sequence; The condition compliance judgment unit is used to judge the compliance of the corresponding application memory usage value and the corresponding cloud host CPU processing capacity in the corresponding bound user's operation behavior in combination with the analysis results of the cloud platform processing sequence generation unit.

9. The resource intelligent scheduling system based on the resource sharing cloud platform according to claim 8, characterized in that: The application processing optimization model construction module includes a resource utilization analysis unit, an application processing optimization model construction unit, and a preprocessing priority sequence generation unit: The resource utilization analysis unit is used to calculate the resource utilization rate of the corresponding cloud host in combination with the task information of the corresponding cloud host; The application processing optimization model building unit is used to combine the analysis results of the resource utilization analysis unit with the corresponding cloud host CPU processing capacity to perform application rationalization processing, and generate an application processing optimization model based on the processing results; The preprocessing priority sequence generating unit is used to generate a preprocessing priority sequence in combination with the analysis result of the application processing optimization model building unit.

10. The resource intelligent scheduling system based on the resource sharing cloud platform according to claim 9, characterized in that: The emergency method generation module includes a feedback result acquisition unit and an emergency plan implementation unit: The feedback result acquisition unit is used to obtain the feedback results of each bound user in the current cloud platform; The emergency plan implementation unit is used to determine whether the processing order of the corresponding applications can be adjusted based on the analysis result of the feedback result acquisition unit.

Images