Computer Resource Allocation Method and Device for Differentiated Teaching Scenarios

Abstract

The present invention provides a computer resource configuration method and device for differentiated teaching scenarios, which are specifically suitable for teaching management purposes. The method includes collecting resource requirements of multiple teaching scenarios; dividing the multiple teaching scenarios into at least two scenario groups based on the resource requirements; analyzing the priority levels of the resource requirements in the scenario groups, and calculating the resource weights of the resource requirements in the scenario groups based on the priority levels; analyzing the key resources of the scenario groups based on the resource weights; dividing the scenario groups into high-priority scenario groups or low-priority scenario groups based on the key resources; reserving a minimum resource amount for each high-priority scenario group; calculating the remaining resource amount based on the total resource amount and the minimum resource amount; configuring the resource allocation ratio for each low-priority scenario group; and allocating resources to each low-priority scenario group based on the remaining resource amount and the resource allocation ratio.

Description

Technical Field

[0001] The present invention relates to the field of computer technology specifically applicable to teaching management, and in particular to a computer resource configuration method and device for differentiated teaching scenarios. Background Art

[0002] In the context of educational informatization, high-computing applications like virtual simulation labs and multimedia teaching platforms coexist with lower-priority technical tasks like general computer rooms and online teaching platforms. Establishing computer resource allocation strategies for these diverse teaching scenarios, while effectively improving their capabilities and flexibility, remains a pressing technical challenge for those skilled in the art.

[0003] The resource allocation methods for different technical fields in the existing technology are becoming increasingly mature, but the resource allocation methods in various technical fields in the existing technology are not applicable to the teaching field.

[0004] Document 1, publication number CN116402318A, proposes a multi-level computing resource allocation method for distribution networks. This allocation method determines computing resources based on the task requirements of different end-side devices (computer terminals). Based on the computing resources, it determines whether any end-side device's resource quota remains, and then redistributes the remaining resource quota. While Document 1 avoids wasting computing resources on each end-side device, the resource quotas allocated to each end-side device are fixed and determined by their hardware, making it unsuitable for teaching. Computer devices in teaching provide different support for different teaching scenarios. For some teaching scenarios, computer devices are essential for completing teaching tasks, such as virtual simulation laboratories and multimedia teaching platforms. Inefficient computer device operation in these scenarios can hinder successful completion of teaching tasks. For other teaching scenarios, computer devices are not essential for completing teaching tasks, such as in standard computer rooms and online teaching platforms. In these scenarios, inefficient computer device operation only impacts the teaching experience but does not prevent the task from being completed. So for the commonly used cloud server deployment and local computer execution devices, how to allocate resources according to different teaching scenarios, on the one hand to ensure the minimum operating requirements of some teaching scenarios, and on the other hand to maximize the resource allocation efficiency for all teaching scenarios, will be the key difficulty in applying resource allocation technology to teaching scenarios.

[0005] Document 2, publication number CN116012067A, proposes a resource allocation method. This method, used in the advertising sector, efficiently allocates computing resources based on the value of different business outputs, improving resource allocation utilization. However, Document 2 focuses solely on allocating computing resources across multiple business outputs (equivalent to a teaching scenario), without considering minimum resource requirements for each business output. It also fails to consider how to more adaptively and efficiently allocate resources across all business outputs when there are too many. Summary of the Invention

[0006] In view of this, a first aspect of the present invention provides a computer resource configuration method for differentiated teaching scenarios.

[0007] The method comprises the following steps,

[0008] Collect resource requirements for multiple teaching scenarios;

[0009] Dividing the plurality of teaching scenarios into at least two scenario groups according to the resource requirements;

[0010] Analyzing the priority levels of the resource requirements in the scenario group, and calculating the resource weight of the resource requirements in the scenario group according to the priority levels;

[0011] Obtaining key resources of the scenario group according to the resource weight analysis;

[0012] Divide the scenario group into a high-priority scenario group or a low-priority scenario group according to the key resources;

[0013] Reserving a minimum amount of resources for each of the high-priority scenario groups;

[0014] Calculate the remaining resources based on the total resources and the stated minimum resources;

[0015] Configuring a resource allocation ratio for each of the low-priority scenario groups;

[0016] Resources are allocated to each of the low-priority scenario groups according to the remaining resource amount and the resource allocation ratio.

[0017] Furthermore, a second aspect of the present invention provides a computer resource configuration method for differentiated teaching scenarios.

[0018] The method comprises the following steps,

[0019] Collect resource requirements for multiple teaching scenarios;

[0020] Dividing the plurality of teaching scenarios into at least two scenario groups according to the resource requirements;

[0021] Analyze the combination characteristics of the resource requirements in the scenario group, and configure at least two resource requirements as a combined resource requirement;

[0022] Analyzing the priority levels of the resource requirements and / or the combined resource requirements in the scenario group, and calculating the resource weights of the resource requirements and / or the combined resource requirements in the scenario group according to the priority levels;

[0023] Obtaining key resources and / or key combination resources of the scenario group according to the resource weight analysis;

[0024] Divide the scenario groups into high-priority scenario groups or low-priority scenario groups according to the key resources and / or key combination resources;

[0025] Reserving a minimum amount of resources for each of the high-priority scenario groups;

[0026] Calculate the remaining resources based on the total resources and the stated minimum resources;

[0027] Configuring a resource allocation ratio for each of the low-priority scenario groups;

[0028] Resources are allocated to each of the low-priority scenario groups according to the remaining resource amount and the resource allocation ratio.

[0029] And, a third aspect of the present invention provides a computer resource configuration device for differentiated teaching scenarios.

[0030] The device includes a demand collection module, a scene group configuration module, a scene group division module and a resource allocation module.

[0031] The demand collection module is used to collect resource requirements of multiple teaching scenarios;

[0032] The scene group configuration module is used to divide the multiple teaching scenes into at least two scene groups according to the resource requirements;

[0033] The scenario group division module is used to analyze the priority levels of resource requirements in the scenario group, calculate the resource weights of the resource requirements in the scenario group according to the priority levels; obtain the key resources of the scenario group according to the resource weights; and divide the scenario group into a high-priority scenario group or a low-priority scenario group according to the key resources;

[0034] The resource allocation module is used to reserve the minimum amount of resources for each high-priority scenario group; calculate the remaining amount of resources based on the total amount of resources and the minimum amount of resources; configure the resource allocation ratio of each low-priority scenario group; and allocate resources to each low-priority scenario group based on the remaining amount of resources and the resource allocation ratio.

[0035] Compared to existing technologies, this invention divides multiple teaching scenarios into different scenario groups based on their resource requirements. Within each scenario group, the resource requirements of each scenario are similar. Resource weights are then established based on the relative relationships between the different resource requirements within the scenario groups. Finally, the resource weights are used to determine the priority of the scenario groups and establish resource allocation rules for high- and low-priority scenario groups. This invention leverages the technical principle of "seeking common ground while reserving differences" to uniformly allocate resources for similar teaching scenarios while establishing priority-based resource allocation strategies for differentiated teaching scenarios. This improves the efficiency and robustness of computer resource allocation for differentiated teaching scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0037] Figure 1 Schematic diagram of the flow of the computer resource configuration method for differentiated teaching scenarios of the present invention;

[0038] Figure 2 A schematic diagram of the process of dividing scene groups according to the present invention;

[0039] Figure 3 This is a structural diagram of the computer resource configuration device for differentiated teaching scenarios of the present invention. DETAILED DESCRIPTION

[0040] The following will be combined with the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the embodiments described 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.

[0041] An embodiment of the present invention provides a computer resource configuration method for differentiated teaching scenarios.

[0042] Figure 1 This is a flow chart of the computer resource configuration method for differentiated teaching scenarios according to the present invention.

[0043] Figure 1 It is shown that the method of the present invention includes steps 10 to 90.

[0044] 10. Collect resource requirements for multiple teaching scenarios.

[0045] Teaching scenarios, such as multimedia classrooms, online teaching platforms, programming labs, virtual simulation labs, and regular computer rooms, all have their own unique resource requirements. For example, multimedia classrooms require high GPU performance, large memory requirements, and real-time high-speed storage.

[0046] There are various ways to collect resource requirements for teaching scenarios. For example, monitoring systems (such as Prometheus) can be used to collect historical resource data for each teaching scenario. Alternatively, questionnaires can be used to interview the teaching staff responsible for each teaching scenario to determine and analyze the resource requirements for each teaching scenario.

[0047] 20 Divide the plurality of teaching scenarios into at least two scenario groups according to the resource requirements.

[0048] A scenario group is a collection of multiple teaching scenarios with similar resource requirements. This method assigns multiple teaching scenarios with similar resource requirements to the same scenario group and then uses the scenario group as a unit for resource allocation. This reduces the need for overly elaborate and unnecessary computer resource allocation for individual teaching scenarios, reduces the complexity of resource configuration across multiple teaching scenarios, and improves robustness.

[0049] In the present invention, K-means is used to divide multiple teaching scenes into different scene groups.

[0050] Figure 2 FIG. 2 is a flow chart of dividing scene groups in step 20 of the present invention.

[0051] Figure 2 It is shown that dividing the scene groups in step 20 includes steps 21 to 25.

[0052] 21 defines the resource requirements of the teaching scenario as an n-dimensional vector, , is the demand for resource k in teaching scenario i.

[0053] For example, the vector for the programming lab is [4 cores, 0.8GB (memory), 100GB (hard disk), 100Mbps].

[0054] 22 Randomly initialize K of the teaching scenes as group centers, ;

[0055] 23 Calculate the Euclidean distance from each teaching scene to the center of each group,

[0056] ,

[0057] is the Euclidean distance between the standardized resource demand of teaching scenario i and group center j, for go through The standardized value of is the resource demand of resource k of group center j, is the dimensional distance between teaching scene i and group center j only in the dimension of resource k.

[0058] In order to avoid the influence of dimensional differences on the cluster structure, the present invention adopts Z-score standardization. , is the mean value of k required for all scenarios, is the standard deviation of the demand for resource k.

[0059] 24 assigning each of the teaching scenes to the group center with the minimum Euclidean distance and forming the scene group with it,

[0060] ,

[0061] is the scene group belonging to group center j after the t-th iteration calculation, is the minimum distance from teaching scene i to all group centers (i.e., assigning teaching scene i to the group center with the minimum distance), and K is the number of initialized group centers.

[0062] 25 iteratively calculating the group center of each of the scene groups according to at least one stopping condition and returning to calculate the Euclidean distance;

[0063] ,

[0064] The stopping condition is Or the current number of iterations reaches an iteration threshold, is the number of teaching scenarios in scenario group j, is the vector sum of all teaching scenario resource requirements in scenario group j, The current group center of scene group j after group center j is calculated for the t+1th iteration, This means that the group center of scene group j is the same at iteration t and iteration t+1. If the stopping condition is not met after step 25, step 23 is repeated. If the stopping condition is met after step 25, the process ends and the current scene groups are saved.

[0065] Therefore, the present invention divides multiple teaching scenes into K scene groups, minimizing the sum of squares of distances (WCSS) from the teaching scenes within the group to the group center. Then all teaching scenarios can be clustered into several scenario groups according to their n-dimensional resource demand characteristics to facilitate resource allocation.

[0066] Preferably, each resource requirement in a scenario group is the mean or median of the corresponding resource requirements of the teaching scenarios in the group.

[0067] 30 Analyze the priority levels of the resource requirements in the scenario group, and calculate the resource weight of each resource requirement in the scenario group according to the priority levels.

[0068] The priority level can be established using a scaling rule, that is, a 1-9 scale is used to define the relative importance of each resource requirement.

[0069] For example, a scale value of 1 indicates that resource demand i is equally important as resource demand j; a scale value of 3 indicates that resource demand i is slightly more important than resource demand j; a scale value of 5 indicates that resource demand i is significantly more important than resource demand j; a scale value of 7 indicates that resource demand i is strongly more important than resource demand j; a scale value of 9 indicates that resource demand i is absolutely more important than resource demand j, and so on.

[0070] 40. Analyze the resource weights to obtain the key resources of the scenario group.

[0071] In step 40, a judgment matrix is established for each of the scene groups according to the priority level.

[0072] , is the scale value between the nth resource requirement and the nth resource requirement in the scenario group.

[0073] Normalize the judgment matrix and obtain the resource weight of each resource.

[0074] , is the resource weight of scenario group i to resource k.

[0075] 50. Divide the scenario group into a high-priority scenario group or a low-priority scenario group according to the key resources.

[0076] In step 50, the key resources of the scenario group are obtained according to the resource weight analysis. . The scenario group whose resource value is not less than a resource threshold is the high-priority scenario group; The scenario group with a resource value smaller than a resource threshold is the low-priority scenario group.

[0077] Preferably, a high-priority scene group in all scene groups can be configured as one group, and by adjusting the resource threshold of a certain resource weight, only one high-priority scene group is divided out of the scene groups.

[0078] 60 Reserve the minimum amount of resources for each high-priority scenario group.

[0079] Preferably, the step 60 of reserving the minimum amount of resources includes reserving the minimum amount of key resources.

[0080] , is the minimum amount of resources reserved for the key resource k in the high-priority scenario group,

[0081] is the total resource amount of key resource k, is the resource threshold, is the resource requirement of the teaching scenario i on the key resource k, It is the sum of the resource requirements of each teaching scenario in the high-priority scenario group for the key resource k.

[0082] Preferably, considering that the minimum resource requirements of some scenario groups are extremely high, while the overall resource amount corresponding to the resources is limited, when reserving the minimum resource amount of each key resource, it is necessary to configure the upper limit of the reserved minimum resource amount.

[0083] For example, , is the maximum reserved resource amount for key resource k, is the global upper limit coefficient.

[0084] 70 Calculate the remaining resource amount based on the total resource amount and the minimum resource amount.

[0085] Preferably, the remaining resource amount calculated in step 70 includes the remaining resource amount of the reserved key resources,

[0086] , is the remaining resource amount of the key resource k, and m1 is the number of the teaching scenarios in the high-priority scenario group.

[0087] 80 configures the resource allocation ratio of each low-priority scenario group.

[0088] The configuration of resource allocation ratio in step 80 includes: , is the resource allocation ratio of resource i in the j-th low-priority scenario group, is the resource demand weight of resource i in the low-priority scenario group; is the sum of the resource demand weights of resource i in all the low-priority scenario groups.

[0089] Preferably, the resource allocation ratio in step 80 is configurable. , K is the resource allocation ratio of a certain resource, The resource demand of a resource in the low-priority scenario group; It is the sum of the resource requirements of a certain resource in all the low-priority scenario groups.

[0090] 90 Allocate resources to each of the low-priority scenario groups according to the remaining resource amount and the resource allocation ratio.

[0091] Preferably, allocating resources to the low-priority scenario group in step 90 includes: , is the allocation amount of key resources of the teaching scenes in the low-priority scene group, and m2 is the number of the teaching scenes in the low-priority scene group.

[0092] Preferably, after step 90, the resource utilization rates of all the teaching scenarios are monitored. When the utilization rate of key resources of one or more teaching scenarios in the high-priority scenario group is lower than a utilization rate threshold, it is assumed that the teaching scenario is in a low-activity state, and these low-activity teaching scenarios are separated from the high-priority scenario group in which they are located, and temporarily grouped into a low-priority scenario group, and the process returns to step 60 to execute the reservation of the minimum amount of resources in the high-priority scenario group and the subsequent allocation of the remaining amount of resources in the low-priority scenario group.

[0093] Based on this, the computer resource configuration method for differentiated teaching scenarios of the present invention divides multiple teaching scenarios into different scenario groups based on their resource requirements, and the resource requirements of each teaching scenario in the scenario group are similar. The present invention then establishes resource weights based on the relative relationship between different resource requirements in the scenario group, determines the priority of the scenario group using the resource weights, and establishes resource (preferably key resources) allocation rules for high- and low-priority scenario groups. The present invention utilizes the technical idea of "seeking common ground while reserving differences". On the one hand, it performs unified resource configuration for similar teaching scenarios, and on the other hand, it establishes resource (preferably key resources) allocation strategies based on priority levels for differentiated teaching scenarios, thereby improving the efficiency and robustness of computer resource configuration for differentiated teaching scenarios.

[0094] Furthermore, the present invention provides a computer resource configuration method for differentiated teaching scenarios, which includes the following steps 10 to 100.

[0095] 10. Collect resource requirements for multiple teaching scenarios.

[0096] 20. Dividing the plurality of teaching scenarios into at least two scenario groups according to the resource requirements;

[0097] 30 Analyze the combination characteristics of the resource requirements in the scenario group and configure at least two resource requirements as a combined resource requirement.

[0098] 40 Analyze the priority levels of the resource requirements and / or combined resource requirements in the scenario group, and calculate the resource weights of the resource requirements and / or combined resource requirements in the scenario group according to the priority levels.

[0099] 50. Analyze the resource weights to obtain the key resources and / or key combination resources of the scenario group.

[0100] 60. Divide the scenario groups into high-priority scenario groups or low-priority scenario groups according to the key resources and / or key combination resources.

[0101] 70 Reserve the minimum amount of resources for each high-priority scenario group.

[0102] 80 Calculate the remaining resource amount based on the total resource amount and the minimum resource amount.

[0103] 90 configures the resource allocation ratio of each low-priority scenario group.

[0104] 100 Allocate resources to each of the low-priority scenario groups according to the remaining resource amount and the resource allocation ratio.

[0105] Therefore, the present invention integrates related resource requirements to obtain combined resource requirements, and applies the combined resource requirements to the computer resource configuration for differentiated teaching scenarios of the present invention.

[0106] Furthermore, the present invention provides a computer resource configuration device for differentiated teaching scenarios.

[0107] Figure 3 This is a structural diagram of the computer resource configuration device for differentiated teaching scenarios of the present invention. Figure 3 It is shown that the device includes a demand collection module, a scene group configuration module, a scene group division module and a resource allocation module.

[0108] Among them, the demand collection module is used to collect resource requirements of multiple teaching scenarios.

[0109] The scenario group configuration module is used to divide the multiple teaching scenarios into at least two scenario groups according to the resource requirements.

[0110] Among them, the scenario group division module is used to analyze the priority levels among the resource requirements in the scenario group, and calculate the resource weights of the resource requirements in the scenario group according to the priority levels; obtain the key resources of the scenario group according to the resource weight analysis; and divide the scenario group into a high-priority scenario group or a low-priority scenario group according to the key resources.

[0111] Among them, the resource allocation module is used to reserve the minimum amount of resources for each high-priority scenario group; calculate the remaining resource amount based on the total resource amount and the minimum resource amount; configure the resource allocation ratio of each low-priority scenario group; and allocate resources to each low-priority scenario group based on the remaining resource amount and the resource allocation ratio.

[0112] Therefore, the computer resource configuration device for differentiated teaching scenarios of the present invention can execute the process steps of the computer resource configuration method for differentiated teaching scenarios, and realize the computer resource configuration of the teaching scenario in an embodied manner.

[0113] Furthermore, the present invention provides a computer device.

[0114] The computer device includes at least one processor, at least one memory, a power supply, a communication interface, an input / output interface, and a communication bus. The memory is used to store a computer program, which is loaded and executed by the processor to implement the relevant steps of any of the aforementioned methods.

[0115] In the present invention, the power supply is used to provide operating voltage for each hardware device on the electronic device; the communication interface can create a data transmission channel between the electronic device and the external device, and the communication protocol it follows is any communication protocol that can be applied to the present invention and is not specifically limited here; the input and output interface is used to obtain external input data or output data to the outside world, and its specific interface type can be selected according to the specific application needs and is not specifically limited here. The memory, as a carrier for resource storage, can be a read-only memory, random access memory, magnetic disk or optical disk, etc. The resources stored thereon can include an operating system, computer programs, etc., and the storage method can be temporary storage or permanent storage. The operating system is used to manage and control the various hardware devices and computer programs on the electronic device, and can be Windows Server, Netware, Unix, Linux, etc. In addition to including a computer program that can be used to complete the method executed by the electronic device provided in any of the aforementioned embodiments, the computer program can further include a computer program that can be used to complete other specific tasks.

[0116] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A computer resource configuration method for differentiated teaching scenarios, It is characterized in that The method comprises the following steps, Collect resource requirements for multiple teaching scenarios; Dividing the plurality of teaching scenarios into at least two scenario groups according to the resource requirements; Analyzing the priority levels of the resource requirements in the scenario group, and calculating the resource weight of the resource requirements in the scenario group according to the priority levels; Obtaining key resources of the scenario group according to the resource weight analysis; Divide the scenario group into a high-priority scenario group or a low-priority scenario group according to the key resources; Reserving a minimum amount of resources for each of the high-priority scenario groups; Calculate the remaining resources based on the total resources and the minimum resources; Configuring a resource allocation ratio for each of the low-priority scenario groups; Allocate resources to each of the low-priority scenario groups according to the remaining resource amount and the resource allocation ratio; Wherein, dividing the scene groups includes: K-means is used to divide the multiple teaching scenarios into at least two scenario groups, namely The resource requirements of the teaching scenario are defined as an n-dimensional vector, R i =[r i1 , r i2 , r i3 ,...,r in ],r ik is the demand for resource k in teaching scenario i; Initialize K of the teaching scenes as group centers, Calculate the Euclidean distance from each teaching scene to the center of each group, d ji is the Euclidean distance between the standardized resource demand of teaching scenario i and group center j, For r ik After the standardized value of Z-score, μ jk is the resource demand of resource k of group center j, is the dimensional distance between teaching scene i and group center j in resource k; Allocate each of the teaching scenes to the group center with the minimum Euclidean distance and form the scene group, is the scene group belonging to group center j after the t-th iteration calculation, MIN 1≤l≤K d li is the minimum distance from teaching scene i to all group centers, K is the number of initialized group centers; Iteratively calculating the group center of each of the scene groups according to at least one stopping condition and returning to recalculate the Euclidean distance; The stopping condition is Or the current number of iterations reaches an iteration threshold, is the number of teaching scenarios in scenario group j, is the vector sum of all teaching scenario resource requirements in scenario group j, Calculate the vector of the current group center of scene group j for the t+1th iteration, It means that the group center in scene group j is the same in the t-th iteration calculation and the t+1-th iteration calculation.

2. The computer resource configuration method for differentiated teaching scenarios according to claim 1, characterized in that: Calculating the resource weight includes: Analyzing the priority levels among the resource requirements in the scenario group, wherein the priority levels are relative importance values among the resource requirements; Establish a judgment matrix for each of the scene groups according to the priority level, x an→an is the relative importance value of the nth resource requirement to the nth resource requirement in the scenario group; Normalize the judgment matrix and obtain resource weights, W i =[w i1 , w i2 , w i3 ,...,w in ],w ik is the resource weight of scenario group i to resource k.

3. The computer resource configuration method for differentiated teaching scenarios according to claim 2, characterized in that: The key resources of the scenario group are obtained by analyzing the resource weights, MAX(w) ik ; Filter out MAX(w) ik The scenario group whose resource value is not less than a resource threshold is the high-priority scenario group; Filter out MAX(w) ik The scenario group with a resource value smaller than a resource threshold is the low-priority scenario group.

4. The computer resource configuration method for differentiated teaching scenarios according to claim 3 is characterized in that: Reserving the minimum amount of resources includes reserving the minimum amount of key resources, R reserved is the minimum amount of resources reserved for the key resource k1 in the high-priority scenario group, C k is the total resource amount of key resource k1, w 阈值 is the resource threshold, R ik is the resource requirement of the teaching scenario i on the key resource k1, is the sum of resource requirements of the teaching scenarios in the high-priority scenario group for the key resource k1; The remaining resource amount obtained by calculation includes the remaining resource amount of the reserved key resources, R free =C k -m1×R reserved , R free is the remaining resource amount of the key resource k1, and m1 is the number of the teaching scenarios in each of the high-priority scenario groups; Configuring the resource allocation ratio of each low-priority scenario group includes: K j is the resource allocation ratio of resource i in the jth low-priority scenario group, w i is the resource demand weight of resource i in the low priority scenario group j, ∑w i is the sum of the resource demand weights of resource i in all the low-priority scenario groups; Configuring the resources of the low priority scenario group includes: is the allocation amount of key resources for each teaching scene in the low-priority scene group, and m2 is the number of the teaching scenes in the low-priority scene group.

5. The computer resource configuration method for differentiated teaching scenarios according to claim 4 is characterized in that: Reserving the minimum amount of resources includes: Configure the upper limit of the minimum resource amount for reserving key resources, is the maximum reserved resource amount of key resource k1, and β is the global upper limit coefficient.

6. The computer resource configuration method for differentiated teaching scenarios according to claim 5, characterized in that: Configuring the resources of the low priority scenario group includes: Monitor resource usage of each current teaching scenario; When the usage rate of key resources of one or more teaching scenes in the high-priority scene group is lower than a usage rate threshold, the one or more teaching scenes are temporarily grouped into a low-priority scene group and the reservation of the minimum amount of resources is re-executed.

7. A computer resource configuration device for differentiated teaching scenarios, characterized in that: The device includes a demand collection module, a scene group configuration module, a scene group division module and a resource allocation module; The demand collection module is used to collect resource requirements of multiple teaching scenarios; The scene group configuration module is used to divide the multiple teaching scenes into at least two scene groups according to the resource requirements; The scenario group division module is used to analyze the priority levels of the resource requirements in the scenario group and calculate the resource weight of each resource requirement in the scenario group according to the priority levels; Obtaining key resources of the scenario group according to the resource weight analysis; and dividing the scenario group into a high-priority scenario group or a low-priority scenario group according to the key resources; The resource allocation module is configured to reserve a minimum amount of resources for each of the high-priority scenario groups; calculate a remaining amount of resources based on the total amount of resources and the minimum amount of resources; configure a resource allocation ratio for each of the low-priority scenario groups; and allocate resources to each of the low-priority scenario groups based on the remaining amount of resources and the resource allocation ratio; Wherein, the scene group configuration module includes: K-means is used to divide the multiple teaching scenarios into at least two scenario groups, namely The resource requirements of the teaching scenario are defined as an n-dimensional vector, R i =[r i1 , r i2 , r i3 ,...,r in ],r ik is the demand for resource k in teaching scenario i; Initialize K of the teaching scenes as group centers, Calculate the Euclidean distance from each teaching scene to the center of each group, d ji is the Euclidean distance between the standardized resource demand of teaching scenario i and group center j, For r ik After the standardized value of Z-score, μ jk is the resource demand of resource k of group center j, is the dimensional distance between teaching scene i and group center j in resource k; Allocate each of the teaching scenes to the group center with the minimum Euclidean distance and form the scene group, is the scene group belonging to group center j after the t-th iteration calculation, MIN 1≤l≤K d li is the minimum distance from teaching scene i to all group centers, K is the number of initialized group centers; Iteratively calculating the group center of each of the scene groups according to at least one stopping condition and returning to recalculate the Euclidean distance; The stopping condition is Or the current number of iterations reaches an iteration threshold, is the number of teaching scenarios in scenario group j, is the vector sum of all teaching scenario resource requirements in scenario group j, Calculate the vector of the current group center of scene group j for the t+1th iteration, It means that the group center in scene group j is the same in the t-th iteration calculation and the t+1-th iteration calculation.

Images