CN111597023A - Intelligent cluster scheduling method and device based on learning state - Google Patents

Intelligent cluster scheduling method and device based on learning state Download PDF

Info

Publication number
CN111597023A
CN111597023A CN202010398398.4A CN202010398398A CN111597023A CN 111597023 A CN111597023 A CN 111597023A CN 202010398398 A CN202010398398 A CN 202010398398A CN 111597023 A CN111597023 A CN 111597023A
Authority
CN
China
Prior art keywords
student
cluster
scheduling table
class
cluster scheduling
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202010398398.4A
Other languages
Chinese (zh)
Other versions
CN111597023B (en
Inventor
海克洪
黄龙吟
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hubei Meihe Yisi Education Technology Co ltd
Original Assignee
Hubei Meihe Yisi Education Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Hubei Meihe Yisi Education Technology Co ltd filed Critical Hubei Meihe Yisi Education Technology Co ltd
Priority to CN202010398398.4A priority Critical patent/CN111597023B/en
Publication of CN111597023A publication Critical patent/CN111597023A/en
Application granted granted Critical
Publication of CN111597023B publication Critical patent/CN111597023B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G06F9/48—Program initiating; Program switching, e.g. by interrupt
    • G06F9/4806—Task transfer initiation or dispatching
    • G06F9/4843—Task transfer initiation or dispatching by program, e.g. task dispatcher, supervisor, operating system
    • G06F9/4881—Scheduling strategies for dispatcher, e.g. round robin, multi-level priority queues
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/44—Arrangements for executing specific programs
    • G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
    • G06F9/45533—Hypervisors; Virtual machine monitors
    • G06F9/45558—Hypervisor-specific management and integration aspects
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
    • G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
    • G06F9/5027—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
    • G06F9/5061—Partitioning or combining of resources
    • G06F9/5072—Grid computing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/44—Arrangements for executing specific programs
    • G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
    • G06F9/45533—Hypervisors; Virtual machine monitors
    • G06F9/45558—Hypervisor-specific management and integration aspects
    • G06F2009/4557—Distribution of virtual machine instances; Migration and load balancing
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management

Landscapes

  • Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Medical Informatics (AREA)
  • Computing Systems (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention provides a learning state-based cluster intelligent scheduling method and device. The method comprises the following steps: receiving a student cluster starting instruction, searching a student cluster scheduling table, and when the student cluster scheduling table is not searched, newly building a student cluster scheduling table to be added; the method comprises the steps of obtaining the class information of the current class students, establishing a learning state weight algorithm, calculating the class information according to the learning state weight algorithm, obtaining the weight value of each class student, associating the weight value with the corresponding class student, inserting the weight value into a to-be-added student cluster scheduling table, and obtaining the to-be-used student cluster scheduling table; according to the method and the device, the learning weight values of the students in the class are calculated by using the weight value algorithm, so that the virtual machines are reasonably distributed according to the learning weight values, the learning efficiency of the students is improved, meanwhile, the uncertainty of cluster scheduling is solved, and the cluster starting speed is also improved.

Description

Intelligent cluster scheduling method and device based on learning state
Technical Field
The invention relates to the technical field of computer software, in particular to a learning state-based intelligent cluster scheduling method and device.
Background
With the rapid development of big data and artificial intelligence, more and more industries begin to widely use big data and add elements of artificial intelligence. In the field of education, with the increasing national requirements for talents of higher education and the demand of times for development, more and more big data courses and related specialties appear in various colleges of higher education. However, due to the complexity of big data courses and the particularity of requirements on experimental environments, the traditional experimental environments cannot meet the current teaching requirements, and normal teaching activities such as teaching and experiments need to be completed by means of the experimental platform, so that various big data platforms for advanced teaching are produced by the way, and are generally shown in the sight of the public as bamboo shoots in spring.
The existing big data related platform carries out related work through a cluster, and in the working process, the cluster usually needs to virtualize a plurality of virtual machines simultaneously for meeting the experimental environment, but the use of a large number of virtual machines can have higher requirements on the cluster performance, but the cluster performance of the existing big data related platform can not meet the requirements, so that the cluster running speed is slow, for students, the attention and the enthusiasm of the students can be influenced by the time for carrying out experimental waiting, and the learning efficiency of the students is reduced.
The above is only for the purpose of assisting understanding of the technical aspects of the present invention, and does not represent an admission that the above is prior art.
Disclosure of Invention
In view of this, the present invention provides a method and an apparatus for intelligently scheduling a cluster based on a learning state, and aims to solve the technical problem that the prior art cannot realize intelligent scheduling of the cluster according to the learning state.
The technical scheme of the invention is realized as follows:
in one aspect, the invention provides a learning state-based intelligent cluster scheduling method, which comprises the following steps:
s1, receiving a student cluster starting instruction, searching a student cluster scheduling table, and when the student cluster scheduling table is not searched, newly building a student cluster scheduling table to be added;
s2, acquiring the class information of the current students, establishing a learning state weight algorithm, calculating the class information according to the learning state weight algorithm, acquiring the weight value of each student, associating the weight value with the corresponding student, inserting the weight value into a to-be-added student cluster scheduling table, and acquiring the to-be-used student cluster scheduling table;
and S3, creating a student cluster according to the student cluster scheduling table to be used, and allocating a virtual machine.
On the basis of the above technical solution, preferably, in step S1, receiving a student cluster start instruction, searching a student cluster scheduling table, and when the student cluster scheduling table is not found, newly creating a student cluster scheduling table to be added, further comprising the steps of receiving the student cluster start instruction, searching the student cluster scheduling table, and when the student cluster scheduling table is found, sequentially starting the student clusters according to the student cluster scheduling table; and when the student cluster scheduling table is not found, newly building a student cluster scheduling table to be added.
On the basis of the above technical solution, preferably, when the student cluster scheduling table is found, the student clusters are sequentially started according to the student cluster scheduling table, and the method further includes the following steps of, when the student cluster scheduling table is found, obtaining login information of a current student in class, where the login information includes: and the ID information and the MAC address information of the corresponding client machine are used for searching the login information of the current student in the local record, if the login information of the current student in class exists in the local record, the student cluster is started in sequence according to the student cluster scheduling table, and if the login information of the current student in class does not exist in the local record, the student cluster scheduling table to be added is newly built.
On the basis of the above technical solution, preferably, in step S2, the method for acquiring the lesson information of the current lesson student further includes the following steps: the basic information of the student and the corresponding learning state information, wherein the basic information comprises: student class information, ID information and MAC address information of a corresponding client machine; the learning state information includes: pre-class pre-study data, post-class work completion data, attendance data and class interaction data.
On the basis of the above technical solution, preferably, in step S2, a learning state weight algorithm is established, calculating the class information according to the learning state weight algorithm, obtaining the weight value of each class student, associating the weight value with the corresponding class student, and inserting the obtained result into the student cluster scheduling table to be added to obtain the student cluster scheduling table to be used, and also includes the following steps of establishing a learning state weight algorithm, calculating the class information according to the learning state weight algorithm, obtaining the weight value of each class student, associating the weight value with the basic information of the corresponding class student, and establishing a corresponding relationship, according to the numerical value, the weighted values of the students in class are sorted in the sequence from high to low, the weighted value with larger numerical value is ranked higher, the sorted weighted value sequence is obtained, and the corresponding students in class are inserted into the student cluster scheduling table according to the weighted value sequence.
On the basis of the above technical solution, preferably, the learning state weight algorithm is:
Figure BDA0002488526890000031
wherein w is the total weight value, n is the category number of the statistical parameter, si(i ∈ {1, 2.. eta., n }) is the score of a single category, tiIs a weight value of a single statistical class, and
Figure BDA0002488526890000032
on the basis of the above technical solution, preferably, after creating a student cluster according to the to-be-used student cluster scheduling table and allocating a virtual machine in step S3, the method further includes the following steps of extracting student data in the to-be-used student cluster scheduling table after receiving a student cluster stopping instruction, storing the student data in a local record, and clearing all information in the to-be-used student cluster scheduling table.
Still further preferably, the intelligent cluster scheduling device based on learning state includes:
the new building module is used for receiving a student cluster starting instruction, searching a student cluster scheduling table, and building a student cluster scheduling table to be added when the student cluster scheduling table is not searched;
the calculation module is used for acquiring the class information of the current class students, establishing a learning state weight algorithm, calculating the class information according to the learning state weight algorithm, acquiring the weight value of each class student, associating the weight value with the corresponding class student, inserting the weight value into a to-be-added student cluster scheduling table, and acquiring the to-be-used student cluster scheduling table;
and the cluster creating module is used for creating the student cluster according to the student cluster scheduling table to be used and distributing the virtual machine.
In a second aspect, the method for intelligent cluster scheduling based on learning status further includes a device, where the device includes: the intelligent dispatching method comprises a memory, a processor and a learning state-based cluster intelligent dispatching method program which is stored on the memory and can run on the processor, wherein the learning state-based cluster intelligent dispatching method program is configured to realize the steps of the learning state-based cluster intelligent dispatching method.
In a third aspect, the intelligent dispatching method for clusters based on learning status further includes a medium, where the medium is a computer medium, and the computer medium stores a program of the intelligent dispatching method for clusters based on learning status, and the program of the intelligent dispatching method for clusters based on learning status implements the steps of the intelligent dispatching method for clusters based on learning status as described above when executed by a processor.
Compared with the prior art, the intelligent cluster scheduling method based on the learning state has the following beneficial effects:
(1) by introducing the weight value algorithm and realizing the dispatching of the student clusters through the weight value algorithm, the uncertainty of the dispatching of the clusters can be solved, and meanwhile, the starting speed of the clusters can also be improved.
(2) Through getting in touch student's learning state information and trunking dispatch, increased trunking dispatch's fairness, the student that the learning attitude is good can obtain longer virtual machine operating time, has avoided the condition of student's latency overlength to appear, has also improved student's enthusiasm simultaneously, makes the student can better accomplish the teaching activity.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic diagram of an apparatus in a hardware operating environment according to an embodiment of the present invention;
FIG. 2 is a schematic flowchart of a first embodiment of a learning state-based intelligent cluster scheduling method according to the present invention;
fig. 3 is a functional module diagram of a first embodiment of the intelligent cluster scheduling method based on learning state according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention.
As shown in fig. 1, the apparatus may include: a processor 1001, such as a Central Processing Unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may include a Display screen (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a WIreless interface (e.g., a WIreless-FIdelity (WI-FI) interface). The Memory 1005 may be a Random Access Memory (RAM) Memory, or may be a Non-Volatile Memory (NVM), such as a disk Memory. The memory 1005 may alternatively be a storage device separate from the processor 1001.
Those skilled in the art will appreciate that the configuration shown in fig. 1 does not constitute a limitation of the device, and that in actual implementations the device may include more or less components than those shown, or some components may be combined, or a different arrangement of components.
As shown in fig. 1, a storage 1005 as a medium may include an operating system, a network communication module, a user interface module, and a learning state-based cluster intelligent scheduling method program.
In the device shown in fig. 1, the network interface 1004 is mainly used for establishing a communication connection between the device and a server storing all data required in the system of the cluster intelligent scheduling method based on the learning state; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 of the intelligent dispatching method device of cluster based on learning state of the present invention can be arranged in the intelligent dispatching method device of cluster based on learning state, and the intelligent dispatching method device of cluster based on learning state calls the intelligent dispatching method program of cluster based on learning state stored in the memory 1005 through the processor 1001, and executes the intelligent dispatching method of cluster based on learning state provided by the present invention.
With reference to fig. 2, fig. 2 is a schematic flowchart of a first embodiment of the intelligent cluster scheduling method based on learning status according to the present invention.
In this embodiment, the intelligent cluster scheduling method based on the learning state includes the following steps:
s10: and receiving a student cluster starting instruction, searching a student cluster scheduling table, and newly building a student cluster scheduling table to be added when the student cluster scheduling table is not searched.
It should be understood that a cluster is a computer system that cooperates to perform computing work with a high degree of closeness through a set of loosely integrated computer software and/or hardware connections. In a sense, they may be considered a computer. The individual computers in a clustered system, often referred to as nodes, are typically connected by a local area network, but there are other possible connections. In this embodiment, the cluster typically uses Kubernets virtualization technology. Due to the particularity of the big data environment, in order to meet teaching activities, a virtual environment often needs to be created in a virtual machine, and the more advanced Docker container technology cannot meet the requirement and only can select a Kubernets virtualization technology. The student cluster scheduling table is a calling form which is generated according to the existing cluster and can call a virtual machine generated by the cluster, the student cluster scheduling table is a calling form which is generated according to the learning state of a student and can call the virtual machine when the student carries out a network course and needs to use the virtual machine to carry out course activities, and the student cluster scheduling table is generated according to the learning state of the student, so that the enthusiasm and the concentration degree of the student learning can be increased.
It should be understood that the system searches whether a student cluster scheduling table exists before receiving the student cluster starting instruction, and if the student cluster scheduling table can be found, the system judges the identity of the current student in class, and specifically, obtains login information of the current student in class, where the login information includes: ID information and MAC address information of a corresponding client machine are searched in a local record, login information of a current student is searched, if the login information can be found, judgment is passed, and a system can start student clusters in sequence according to a student cluster scheduling table; if the student cluster scheduling table is not found, the judgment is failed, and the system creates a new student cluster scheduling table to be added.
It should be understood that if the system does not find a student cluster scheduling table, the system creates a student cluster scheduling table to be added, and supplements the student cluster scheduling table to be added according to the information of the students who are currently in class.
S20: the method comprises the steps of obtaining the class information of the current class students, establishing a learning state weight algorithm, calculating the class information according to the learning state weight algorithm, obtaining the weight value of each class student, associating the weight value with the corresponding class student, inserting the weight value into a to-be-added student cluster scheduling table, and obtaining the to-be-used student cluster scheduling table.
It should be appreciated that to supplement the student cluster schedule to be added, the system will acquire the class information of the current class students, including: the basic information of the student and the corresponding learning state information, wherein the basic information comprises: student class information, ID information and MAC address information of a corresponding client machine; the learning state information includes: the data include pre-class pre-study data, post-class work completion data, attendance data and classroom interaction data, on one hand, the data are used for archiving and storing student identity information so as to be directly verified when a cluster is started next time, on the other hand, the cluster is reasonably distributed according to the learning state information, the student in a good learning state can be preferentially distributed to the cluster, and the cluster can be operated for a longer time, so that the enthusiasm and the learning efficiency of the student can be improved.
It should be understood that, the learning weight values of the students need to be calculated later, a learning state weight algorithm is established, the class information is calculated according to the learning state weight algorithm, the weight value of each class student is obtained, the weight value is associated with the basic information of the corresponding class student, a corresponding relation is established, the weight value of each class student is sequenced according to the numerical value in the sequence from high to low, the higher the numerical value is, the higher the ranking is, the ordered weight value sequence is obtained, the corresponding class students are inserted into the added student cluster scheduling table according to the weight value sequence, and the students with the same weight are inserted according to the student number sequence.
It should be understood that the learning state weight algorithm is:
Figure BDA0002488526890000071
wherein w is the total weight value, n is the category number of the statistical parameter, si(i ∈ {1, 2.. eta., n }) is the score of a single category, tiIs a weight value of a single statistical class, and
Figure BDA0002488526890000072
it should be understood that assuming the number of categories of the statistical parameter is n, the score of a single category is si(i ∈ {1, 2.. n }), the weight of a single statistical class
Figure BDA0002488526890000073
Then there is a certain student's current total weight
Figure BDA0002488526890000074
After the current total weight values of all students are calculated, the current total weight values can be sequentially inserted into the weight sequence list according to the respective weight values.
Taking 4 common statistical parameters of pre-class pre-study, post-class job completion, attendance checking and classroom interaction as an example, the current value of n is 4.
Suppose that by the time of the current lesson, the teacher has arranged x in totaltPre-lesson task, ytWork after class, ztRecord of attendance, ptAnd (5) secondary classroom interaction.
Take student a as an example, he has completed xaThe second preview submits yaWork after class, sign in zaChecking the work attendance once, participate in paAnd (5) secondary classroom interaction. The score of the pre-school lesson pre-study of student a
Figure BDA0002488526890000081
Score of post-lesson work
Figure BDA0002488526890000082
Check-in score
Figure BDA0002488526890000083
Classroom interaction scoring
Figure BDA0002488526890000084
After obtaining the statistical scores of each category, the weights of each category can be obtained respectively
Figure BDA0002488526890000085
Then the total weight w of student a at this timea＝t1+t2+t3+t4Wherein w isa∈[0,1]。
S30: and creating a student cluster according to the student cluster scheduling table to be used, and allocating a virtual machine.
It should be understood that when the teacher stops lecturing, that is, the system receives the instruction to stop the student cluster, the system will extract the student data in the to-be-used student cluster scheduling table, store the student data in the local record for recording, so as to perform identity verification and call subsequently, and then clear all the information in the to-be-used student cluster scheduling table, in this way, the cached data of the cluster is reduced, and the running speed of the cluster is increased.
It should be understood that, in this embodiment, the cluster intelligent scheduling flowchart based on the learning state specifically operates as follows:
first, the system will sequentially start student clusters according to the cluster schedule.
After the students log in the platform, the platform records the ID of the students and the MAC address of the current client machine, the students can apply for the virtual machine to the server by using the two types of information as the unique certificate of the application cluster through the client, the virtual machine is returned to the client after the server prepares the required cluster environment, and the client enters the cluster environment through the return address.
Before the system does not generate the student cluster scheduling table, the system randomly starts the clusters corresponding to different clients. After the system generates a student cluster scheduling table, the mode of starting the clusters by the system is changed from the original random sequence starting into the mode of starting according to the cluster scheduling table sequence, in the cluster scheduling sequence table, the clusters with high priority are arranged at the front position, and as a result, the records with the front positions are started preferentially.
When the teacher chooses to attend a class, the system starts to calculate the weight information of the current students according to the cluster scheduling table. The method comprises the steps of obtaining basic information of all students in a current class, associating the information with various information of the learning states of the students, calculating a weight value of each student according to a learning state weight algorithm, inserting the weight values into a cluster scheduling table from high to low according to the weight values of the students, and inserting the students with the same weight according to the student numbers. After the teaching activities are completed, the teacher can choose to leave the class, and the information in the cluster scheduling table is cleared.
It should be noted that, when all students log on the platform for the first time, since all the student weight values are 0, the order in the cluster scheduling table is arranged from low to high according to the student number.
After the weight value of each student is obtained, the students are sequentially inserted into the cluster scheduling table from high to low according to the total weight, so that the generation of the cluster scheduling table is completed, the fairness of the operation of the students is increased, the students with good learning attitude can obtain longer operation time, the increase enthusiasm of the learning of the students is also increased, in order to obtain longer operation time, the students need to actively complete all teaching activities arranged by a teacher on time, meanwhile, the uncertainty of the cluster scheduling is solved by adding a learning state weight algorithm, and the starting speed of the cluster can be improved.
The above description is only for illustrative purposes and does not limit the technical solutions of the present application in any way.
Through the above description, it is easy to find that, in the present embodiment, the student cluster scheduling table is searched by receiving a student cluster starting instruction, and when the student cluster scheduling table is not searched, a student cluster scheduling table to be added is newly created; the method comprises the steps of obtaining the class information of the current class students, establishing a learning state weight algorithm, calculating the class information according to the learning state weight algorithm, obtaining the weight value of each class student, associating the weight value with the corresponding class student, inserting the weight value into a to-be-added student cluster scheduling table, and obtaining the to-be-used student cluster scheduling table; according to the method, the student clusters are created according to the student cluster scheduling table to be used, the virtual machines are distributed, the learning weight values of the students in the class are calculated through the weight value algorithm, the virtual machines are reasonably distributed according to the learning weight values, the learning efficiency of the students is improved, meanwhile, the uncertainty of cluster scheduling is solved, and the cluster starting speed is also improved.
In addition, the embodiment of the invention also provides a cluster intelligent scheduling device based on the learning state. As shown in fig. 3, the intelligent cluster scheduling device based on learning state includes: the system comprises a new building module 10, a calculation module 20 and a cluster creating module 30.
The newly building module 10 is used for receiving a student cluster starting instruction, searching a student cluster scheduling table, and building a student cluster scheduling table to be added when the student cluster scheduling table is not searched;
the calculation module 20 is configured to obtain the class information of the current class student, establish a learning state weight algorithm, calculate the class information according to the learning state weight algorithm, obtain a weight value of each class student, associate the weight value with the corresponding class student, insert the class student into a to-be-added student cluster scheduling table, and obtain a to-be-used student cluster scheduling table;
and the cluster creating module 30 is used for creating the student cluster according to the student cluster scheduling table to be used and allocating the virtual machine.
In addition, it should be noted that the above-described embodiments of the apparatus are merely illustrative, and do not limit the scope of the present invention, and in practical applications, a person skilled in the art may select some or all of the modules to implement the purpose of the embodiments according to actual needs, and the present invention is not limited herein.
In addition, the technical details that are not described in detail in this embodiment may refer to the intelligent cluster scheduling method based on the learning state provided in any embodiment of the present invention, and are not described herein again.
In addition, an embodiment of the present invention further provides a medium, where the medium is a computer medium, and a learning state-based cluster intelligent scheduling method program is stored on the computer medium, and when executed by a processor, the learning state-based cluster intelligent scheduling method program implements the following operations:
s1, receiving a student cluster starting instruction, searching a student cluster scheduling table, and when the student cluster scheduling table is not searched, newly building a student cluster scheduling table to be added;
s2, acquiring the class information of the current students, establishing a learning state weight algorithm, calculating the class information according to the learning state weight algorithm, acquiring the weight value of each student, associating the weight value with the corresponding student, inserting the weight value into a to-be-added student cluster scheduling table, and acquiring the to-be-used student cluster scheduling table;
and S3, creating a student cluster according to the student cluster scheduling table to be used, and allocating a virtual machine.
Further, when executed by a processor, the learning state-based cluster intelligent scheduling method further implements the following operations:
receiving a student cluster starting instruction, searching a student cluster scheduling table, and starting student clusters sequentially according to the student cluster scheduling table when the student cluster scheduling table is searched; and when the student cluster scheduling table is not found, newly building a student cluster scheduling table to be added.
Further, when executed by a processor, the learning state-based cluster intelligent scheduling method further implements the following operations:
when the student cluster scheduling table is found, login information of the current students in class is obtained, wherein the login information comprises: and the ID information and the MAC address information of the corresponding client machine are used for searching the login information of the current student in the local record, if the login information of the current student in class exists in the local record, the student cluster is started in sequence according to the student cluster scheduling table, and if the login information of the current student in class does not exist in the local record, the student cluster scheduling table to be added is newly built.
Further, when executed by a processor, the learning state-based cluster intelligent scheduling method further implements the following operations:
the lesson information comprises: the basic information of the student and the corresponding learning state information, wherein the basic information comprises: student class information, ID information and MAC address information of a corresponding client machine; the learning state information includes: pre-class pre-study data, post-class work completion data, attendance data and class interaction data.
Further, when executed by a processor, the learning state-based cluster intelligent scheduling method further implements the following operations:
establishing a learning state weight algorithm, calculating the class information according to the learning state weight algorithm, acquiring the weight value of each class student, associating the weight value with the basic information of the corresponding class student, establishing a corresponding relation, sequencing the weight values of each class student according to the numerical value in a sequence from high to low, acquiring a sequencing finished weight value sequence when the ranking of the weight values is higher when the numerical value is larger, and inserting the corresponding class students into a student cluster scheduling table according to the weight value sequence.
Further, when executed by a processor, the learning state-based cluster intelligent scheduling method further implements the following operations:
the learning state weight algorithm is as follows:
Figure BDA0002488526890000111
wherein w is the total weight value, n is the category number of the statistical parameter, si(i ∈ {1, 2.. eta., n }) is the score of a single category, tiIs a weight value of a single statistical class, and
Figure BDA0002488526890000112
further, when executed by a processor, the learning state-based cluster intelligent scheduling method further implements the following operations:
and after receiving an instruction of stopping the student clustering, extracting the student data in the student clustering scheduling table to be used, storing the student data in a local record, and clearing all information in the student clustering scheduling table to be used.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.

Claims (10)

1. A cluster intelligent scheduling method based on learning state is characterized in that: comprises the following steps;
s1, receiving a student cluster starting instruction, searching a student cluster scheduling table, and when the student cluster scheduling table is not searched, newly building a student cluster scheduling table to be added;
s2, acquiring the class information of the current students, establishing a learning state weight algorithm, calculating the class information according to the learning state weight algorithm, acquiring the weight value of each student, associating the weight value with the corresponding student, inserting the weight value into a to-be-added student cluster scheduling table, and acquiring the to-be-used student cluster scheduling table;
and S3, creating a student cluster according to the student cluster scheduling table to be used, and allocating a virtual machine.
2. The intelligent dispatching method of cluster based on learning status as claimed in claim 1, characterized in that: step S1, receiving a student cluster starting instruction, searching a student cluster scheduling table, and creating a new student cluster scheduling table to be added when the student cluster scheduling table is not searched, and the method also comprises the following steps of receiving the student cluster starting instruction, searching the student cluster scheduling table, and when the student cluster scheduling table is searched, sequentially starting the student clusters according to the student cluster scheduling table; and when the student cluster scheduling table is not found, newly building a student cluster scheduling table to be added.
3. The intelligent dispatching method of cluster based on learning status as claimed in claim 2, characterized in that: when the student cluster scheduling table is found, sequentially starting the student clusters according to the student cluster scheduling table, and the method further comprises the following steps of obtaining login information of the current students in class when the student cluster scheduling table is found, wherein the login information comprises the following steps: and the ID information and the MAC address information of the corresponding client machine are used for searching the login information of the current student in the local record, if the login information of the current student in class exists in the local record, the student cluster is started in sequence according to the student cluster scheduling table, and if the login information of the current student in class does not exist in the local record, the student cluster scheduling table to be added is newly built.
4. The intelligent dispatching method of cluster based on learning status as claimed in claim 1, characterized in that: in step S2, the method for acquiring the information of the current student in class further includes the following steps: the basic information of the student and the corresponding learning state information, wherein the basic information comprises: student class information, ID information and MAC address information of a corresponding client machine; the learning state information includes: pre-class pre-study data, post-class work completion data, attendance data and class interaction data.
5. The intelligent dispatching method of cluster based on learning status as claimed in claim 4, characterized in that: in step S2, a learning state weight algorithm is established, the class information is calculated according to the learning state weight algorithm, a weight value of each class student is obtained, the weight value is associated with the corresponding class student, and inserting the obtained result into the student cluster scheduling table to be added to obtain the student cluster scheduling table to be used, and also includes the following steps of establishing a learning state weight algorithm, calculating the class information according to the learning state weight algorithm, obtaining the weight value of each class student, associating the weight value with the basic information of the corresponding class student, and establishing a corresponding relationship, according to the numerical value, the weighted values of the students in class are sorted in the sequence from high to low, the weighted value with larger numerical value is ranked higher, the sorted weighted value sequence is obtained, and the corresponding students in class are inserted into the student cluster scheduling table according to the weighted value sequence.
6. The intelligent dispatching method of cluster based on learning status as claimed in claim 5, characterized in that: the method further comprises the following steps that:
Figure FDA0002488526880000021
wherein w is the total weight value, n is the category number of the statistical parameter, si(i ∈ {1, 2.. eta., n }) is the score of a single category, tiIs a weight value of a single statistical class, and
Figure FDA0002488526880000022
7. the intelligent dispatching method of cluster based on learning status as claimed in claim 5, characterized in that: in step S3, after creating a student cluster according to the to-be-used student cluster scheduling table and allocating a virtual machine, the method further includes the steps of, after receiving an instruction to stop the student cluster, extracting student data in the to-be-used student cluster scheduling table, storing the extracted student data in a local record, and removing all information in the to-be-used student cluster scheduling table.
8. The intelligent cluster dispatching device based on the learning state is characterized by comprising:
the new building module is used for receiving a student cluster starting instruction, searching a student cluster scheduling table, and building a student cluster scheduling table to be added when the student cluster scheduling table is not searched;
the calculation module is used for acquiring the class information of the current class students, establishing a learning state weight algorithm, calculating the class information according to the learning state weight algorithm, acquiring the weight value of each class student, associating the weight value with the corresponding class student, inserting the weight value into a to-be-added student cluster scheduling table, and acquiring the to-be-used student cluster scheduling table;
and the cluster creating module is used for creating the student cluster according to the student cluster scheduling table to be used and distributing the virtual machine.
9. An apparatus, characterized in that the apparatus comprises: a memory, a processor and a learning state based intelligent cluster scheduling method program stored on the memory and executable on the processor, the learning state based intelligent cluster scheduling method program being configured to implement the steps of the learning state based intelligent cluster scheduling method according to any one of claims 1 to 7.
10. A medium, characterized in that the medium is a computer medium, on which a learning state-based cluster intelligent scheduling method program is stored, which when executed by a processor implements the steps of the learning state-based cluster intelligent scheduling method according to any one of claims 1 to 7.
CN202010398398.4A 2020-05-12 2020-05-12 Cluster intelligent scheduling method and device based on learning state Active CN111597023B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010398398.4A CN111597023B (en) 2020-05-12 2020-05-12 Cluster intelligent scheduling method and device based on learning state

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010398398.4A CN111597023B (en) 2020-05-12 2020-05-12 Cluster intelligent scheduling method and device based on learning state

Publications (2)

Publication Number Publication Date
CN111597023A true CN111597023A (en) 2020-08-28
CN111597023B CN111597023B (en) 2023-07-07

Family

ID=72182284

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010398398.4A Active CN111597023B (en) 2020-05-12 2020-05-12 Cluster intelligent scheduling method and device based on learning state

Country Status (1)

Country Link
CN (1) CN111597023B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112100187A (en) * 2020-08-31 2020-12-18 湖北美和易思教育科技有限公司 Student learning data storage method and device based on VueJS
CN113487456A (en) * 2021-05-26 2021-10-08 杭州米络星科技(集团)有限公司 Online classroom fidelity analysis method and device, server and storage medium

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20040115596A1 (en) * 2001-04-23 2004-06-17 Jonathan Scott Snyder System for scheduling classes and managing educational resources
CN105022670A (en) * 2015-07-17 2015-11-04 中国海洋大学 Heterogeneous distributed task processing system and processing method in cloud computing platform
CN107370783A (en) * 2016-05-13 2017-11-21 北京金山云网络技术有限公司 A kind of dispatching method and device of cloud computing cluster resource
CN108519911A (en) * 2018-03-23 2018-09-11 上饶市中科院云计算中心大数据研究院 The dispatching method and device of resource in a kind of cluster management system based on container
CN109032801A (en) * 2018-07-26 2018-12-18 郑州云海信息技术有限公司 A kind of request scheduling method, system and electronic equipment and storage medium

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20040115596A1 (en) * 2001-04-23 2004-06-17 Jonathan Scott Snyder System for scheduling classes and managing educational resources
CN105022670A (en) * 2015-07-17 2015-11-04 中国海洋大学 Heterogeneous distributed task processing system and processing method in cloud computing platform
CN107370783A (en) * 2016-05-13 2017-11-21 北京金山云网络技术有限公司 A kind of dispatching method and device of cloud computing cluster resource
CN108519911A (en) * 2018-03-23 2018-09-11 上饶市中科院云计算中心大数据研究院 The dispatching method and device of resource in a kind of cluster management system based on container
CN109032801A (en) * 2018-07-26 2018-12-18 郑州云海信息技术有限公司 A kind of request scheduling method, system and electronic equipment and storage medium

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112100187A (en) * 2020-08-31 2020-12-18 湖北美和易思教育科技有限公司 Student learning data storage method and device based on VueJS
CN112100187B (en) * 2020-08-31 2024-01-26 武汉美和易思数字科技有限公司 Student learning data storage method and device based on VueJS
CN113487456A (en) * 2021-05-26 2021-10-08 杭州米络星科技(集团)有限公司 Online classroom fidelity analysis method and device, server and storage medium

Also Published As

Publication number Publication date
CN111597023B (en) 2023-07-07

Similar Documents

Publication Publication Date Title
US8214375B2 (en) Manual and automatic techniques for finding similar users
CN103873321B (en) Distributed file system-based simulation distributed parallel computing platform and method
CN102737536B (en) Operating method of language experience teaching system
CN111597023B (en) Cluster intelligent scheduling method and device based on learning state
CN111736990B (en) Teaching and scientific research platform resource allocation method and device based on load balancing
CN110322931A (en) A kind of base recognition methods, device, equipment and storage medium
Li The use of artificial intelligence combined with cloud computing in the design of education information management platform
CN117294727A (en) Cloud edge end collaborative management method based on cloud primordia and container technology
CN113934839A (en) Method, equipment and storage medium for volume grouping according to knowledge points
CN110837549A (en) Information processing method, device and storage medium
CN115688495B (en) Distributed LVC simulation system collaborative planning method, server and storage medium
CN112214602A (en) Text classification method and device based on humor, electronic equipment and storage medium
CN108769233B (en) Resource optimization allocation method based on desktop cloud
JP2003280505A (en) Learning support method and learning support program
CN106250407A (en) A kind of social communication method and apparatus
CN110084519A (en) A kind of many wound space enterprise hatching method for running, device, equipment and medium
Kong et al. Application Research of Personalized Recommendation Technology in College English Teaching Reform under The Background of Big Data
CN115293275A (en) Data identification method and device, electronic equipment and storage medium
CN114372699A (en) Employee management method and device, electronic equipment and storage medium
CN113205434A (en) Online experimental teaching system and method based on container technology
CN114418120A (en) Data processing method, device, equipment and storage medium of federal tree model
CN113704608A (en) Personalized item recommendation method and device, electronic equipment and storage medium
US20200342411A1 (en) Platform for training and testing users in reality-based simulated environment
KR101245824B1 (en) Method, system and computer-readable recording medium for providing study information
Maimaiti Design of cloud computing-based foreign language teaching management system based on parallel computing

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
CB02 Change of applicant information
CB02 Change of applicant information

Address after: Room 01, 2 / F, building A14, phase 1.1, Wuhan National Geospatial Information Industrialization Base (New Area), no.6, Beidou Road, Donghu New Technology Development Zone, Wuhan City, Hubei Province, 430000

Applicant after: Wuhan Meihe Yisi Digital Technology Co.,Ltd.

Address before: No.01-6, 1st floor, building 6, international enterprise center, special 1, Guanggu Avenue, Donghu New Technology Development Zone, Wuhan City, Hubei Province, 430000

Applicant before: HUBEI MEIHE YISI EDUCATION TECHNOLOGY Co.,Ltd.

GR01 Patent grant
GR01 Patent grant