Training resource allocation method and device, electronic equipment and storage medium

Abstract

The invention provides a training resource allocation method and device, electronic equipment and a storage medium, and the method comprises the steps: collecting training resources related to a training task, including a training task type, a training scale, training resource use condition data, a training task priority and individual training data, and extracting key features from the training resources; and therefore, the unique resource demand of each training task can be accurately identified. The analysis method based on data driving can effectively avoid the problem of resource idleness or shortage caused by neglecting demand difference in a traditional empirical static resource allocation mode. Moreover, training tasks with similar demand characteristics are classified into one class through clustering analysis, resource demand evaluation is carried out on each class, and the scheme can reflect changes of training task demands in real time and dynamically adjust a resource allocation strategy. Compared with a dynamic resource allocation method based on a simple rule, the method can deal with dynamic changes of demands more flexibly, and the maximum efficiency of training resources is brought into full play.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of training resource allocation, and in particular to a training resource allocation method and device, an electronic device and a storage medium. BACKGROUND

[0002] In the training process, the reasonable configuration of training resources directly affects the training effect and the improvement of combat effectiveness. Training resources cover training sites (such as shooting ranges, tactical training sites), training equipment (such as weapons and equipment, simulation training equipment), training personnel (including instructors and trainees), and training time.

[0003] Currently, training resource allocation mostly relies on traditional experience-based static allocation mode. For example, according to the annual training plan, a certain amount of training sites and equipment use time, and corresponding instructor resources are fixedly allocated to different types of personnel or training units. This allocation method has many drawbacks. On the one hand, it cannot fully consider the actual demand differences of different training tasks. For example, the professionalism and accuracy of simulation training equipment are extremely high for TZ combat training, while the area demand of the site is large for regular training. However, under the static allocation, the resource supply and demand may not match. On the other hand, it lacks consideration of dynamic changes in the training process, such as different training progress caused by individual ability differences, and urgent resource needs of sudden training tasks, which can easily cause resource idling or shortage, reduce training efficiency, and is difficult to meet the needs of modern and refined military training.

[0004] Some units have tried to allocate resources dynamically based on simple rules, such as adjusting resource allocation according to training progress. However, due to the lack of comprehensive and accurate analysis of training tasks, it is difficult to achieve scientific and efficient allocation of resources, and the maximum effectiveness of training resources cannot be fully utilized. SUMMARY

[0005] The present application provides a training resource allocation method, device, electronic device and storage medium to solve the defects in the prior art that the traditional experience-based static resource allocation mode is used, the demand differences and dynamic changes of training tasks are often ignored, resulting in resource idling or shortage, which is difficult to meet the requirements of modern training, and the dynamic resource allocation based on simple rules cannot fully utilize the maximum effectiveness of training resources.

[0006] The present application provides a training resource allocation method, comprising the following steps: obtaining training resources related to a training task; the training resources include training task type, training scale, historical training time, training resource use data, training task priority and individual training data; extracting key features in the training resources; the key features are used to reflect the resource demand characteristics of the training task; cluster the key features to obtain each clustering feature cluster, and perform resource demand evaluation on the each clustering feature cluster to obtain a resource demand evaluation result; perform training resource allocation based on the resource demand evaluation result.

[0007] According to the training resource allocation method provided by the application, the key features include training resource consumption rate of unit personnel or equipment, site usage intensity, equipment wear rate, training task type feature, training progress deviation and skill improvement rate; The extracting the key features from the training resources comprises: Based on the training scale and the historical training duration, the training resource consumption rate of the unit personnel or equipment is determined; The site usage intensity and the equipment wear rate in the training resource usage data are extracted; The training task type feature of the training task type is extracted; The training progress deviation and the skill improvement rate in the individual training data are extracted.

[0008] According to the training resource allocation method provided by the application, the training task type includes tactical training, shooting training, physical training and informationized combat training; The training resource usage data includes training site usage frequency, training site usage duration, equipment wear degree, instructor teaching duration and instructor teaching intensity; The individual training data includes physical test results, skill mastery degree and learning progress.

[0009] According to the training resource allocation method provided by the application, the resource demand evaluation on the each clustering feature cluster to obtain a resource demand evaluation result comprises: The average resource demand and resource demand fluctuation range of the training task in the each clustering feature cluster are determined; Based on the average resource demand, the resource demand fluctuation range, the training task priority and the individual training data, resource demand evaluation is performed to obtain the resource demand evaluation result.

[0010] According to the training resource allocation method provided by the application, the obtaining of the training resource related to the training task comprises: Obtaining original training resources related to the training task; Performing preprocessing operation on the original training resources to obtain the training resources; the preprocessing operation includes data cleaning, denoising processing, normalization processing and missing value processing; The missing value processing includes mean filling, median filling, and predicted value filling based on a prediction model constructed based on the original training resource; The mean filling and the median filling are respectively based on the mean and the median of the same type of training task of the training task.

[0011] According to the training resource allocation method provided by the application, the key features are clustered to obtain each clustering feature cluster, including: The key features are clustered to obtain each clustering feature cluster by using a K-means clustering algorithm or a density-based spatial clustering application algorithm with noise.

[0012] According to the training resource allocation method provided by the application, the resource demand evaluation result is used to allocate training resources, including: In the case that the resource demand evaluation result is that the training resources meet the first type, the resource demand proportion of each clustering feature cluster is used to allocate training resources; In the case that the resource demand evaluation result is that the training resources meet the second type, the priority of each clustering feature cluster is used to allocate training resources.

[0013] According to the training resource allocation method provided by the application, the resource demand evaluation result is used to allocate training resources, and then further includes: Monitoring running data and resource usage data; the running data and the resource usage data are obtained from each training task after the training resources are allocated to each training task; Based on the running data and the resource usage data, the resource demand evaluation result is updated.

[0014] The application also provides a training resource allocation device, including the following units: An acquisition unit is configured to acquire training resources related to a training task; the training resources include training task types, training scales, historical training durations, training resource usage data, training task priorities, and individual training data; An extraction unit is configured to extract key features in the training resources; the key features are used to reflect resource demand characteristics of the training task; A resource demand evaluation unit is configured to cluster the key features to obtain each clustering feature cluster, and to evaluate resource demands of each clustering feature cluster to obtain a resource demand evaluation result; A training resource allocation unit is configured to allocate training resources based on the resource demand evaluation result.

[0015] The application further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the training resource allocation method according to any one of the above when executing the program.

[0016] The application further provides a non-transitory computer-readable storage medium, which stores a computer program, wherein the computer program is executed by a processor to implement the training resource allocation method according to any one of the above.

[0017] The application further provides a computer program product, comprising a computer program, wherein the computer program is executed by a processor to implement the training resource allocation method according to any one of the above.

[0018] The training resource allocation method, device, electronic device and storage medium provided by the application can accurately identify the unique resource requirements of each training task by comprehensively collecting various data related to the training task, including training task type, training scale, historical training duration, training resource usage data, training task priority and individual training data, and extracting key features therefrom. This data-driven analysis method can effectively avoid the problems of resource idling or shortage caused by neglecting demand differences in traditional experience-based static resource allocation mode. Moreover, by clustering analysis, training tasks with similar demand characteristics are classified into a category, and resource demand evaluation is performed on each category. This scheme can reflect the changes in training task demand in real time and dynamically adjust the resource allocation strategy. Compared with the dynamic resource allocation method based on simple rules, this method can more flexibly cope with the dynamic changes in demand and fully utilize the maximum efficiency of training resources. The training resource allocation based on the resource demand evaluation result not only improves the utilization rate of resources, but also ensures that the training task can be completed efficiently, thereby meeting the high requirements of modern training on resource allocation. BRIEF DESCRIPTION OF DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the application or prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are some embodiments of the application, and for those skilled in the art, other drawings can also be obtained without creative labor.

[0020] Figure 1 is a flowchart of the training resource allocation method provided by the application.

[0021] Figure 2 is a structural schematic diagram of the training resource allocation device provided by the application.

[0022] Figure 3 is a structural schematic diagram of the electronic device provided by the application. DETAILED DESCRIPTION

[0023] In order to make the objects, technical solutions and advantages of the present application clearer, the technical solutions in the present application will be described clearly and completely below with reference to the drawings in the present application. Obviously, the described embodiments are only some but not all of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall into the protection scope of the present application.

[0024] Figure 1 is a flowchart of the training resource allocation method provided by the present application, as shown in Figure 1 The method comprises steps 110, 120, 130 and 140.

[0025] In step 110, training resources related to a training task are acquired; the training resources comprise a training task type, a training scale, a historical training duration, training resource usage data, a training task priority and individual training data.

[0026] In step 120, key features in the training resources are extracted; the key features are used to reflect resource demand features of the training task.

[0027] In step 130, the key features are clustered to obtain various clustering feature clusters, and resource demand evaluation is performed on the various clustering feature clusters to obtain a resource demand evaluation result.

[0028] In step 140, training resource allocation is performed based on the resource demand evaluation result.

[0029] Specifically, first, training resources related to a training task are acquired, wherein the training resources comprise a training task type, a training scale, a historical training duration, training resource usage data, a training task priority and individual training data. Here, the training task type comprises a tactical training, a shooting training, a physical training and an informationized combat training, etc., which are not limited by the embodiments of the present application.

[0030] The training resource usage data comprises a training site usage frequency, a training site usage duration, an equipment wear degree, a trainer teaching duration and a trainer teaching intensity, etc., which are not limited by the embodiments of the present application.

[0031] The individual training data comprises a physical test result, a skill mastery degree and a learning progress, etc., which are not limited by the embodiments of the present application.

[0032] Here, the training scale can include the number of participants and the number of equipment, and the historical training duration refers to the cumulative duration of the training task that has been performed. The training task priority is the task level set based on strategic requirements and training objectives.

[0033] It should be noted that data collection can be performed through training management system records, training site sensor collection, training file updates, etc., to ensure the authenticity and integrity of the data.

[0034] Here, the training resources refer to the pre-processing of the original training resources. The pre-processing can include data cleaning, denoising, normalization, and missing value processing, which are not specifically limited by the embodiments of the present application. Data cleaning refers to removing duplicate data and correcting incorrect information to ensure data consistency; denoising is based on filtering algorithms (such as mean filtering and median filtering) to remove abnormal peaks and noise interference and improve data quality; normalization is to standardize each dimension of data to the interval [0, 1] to avoid the influence of inconsistent dimensions on analysis.

[0035] Among them, the missing value processing includes mean filling, median filling and predicted value filling based on a prediction model constructed from the original training resources. The mean filling and median filling are based on the mean and median of the same type of training task of the training task.

[0036] For example, in the data set of the training site usage duration, if a record is missing, the average usage duration is calculated based on a large number of sample data of the same type of physical training for mean filling, or a reasonable filling value is predicted using a regression model.

[0037] Then, the key features in the obtained training resources are extracted, and the key features are used to reflect the resource demand characteristics of the training task for subsequent cluster analysis.

[0038] Further, the extracted key features are subjected to big data clustering processing, and a clustering algorithm is used to obtain each clustering feature cluster. The training tasks are divided into different categories according to the similarity of resource demand, and each clustering cluster represents a typical resource demand mode.

[0039] It can be understood that the key features are clustered to obtain each clustering feature cluster, and the resource demand of each clustering feature cluster is evaluated to obtain the resource demand evaluation result, so as to deeply analyze the resource demand characteristics of the training task, and to realize the precise matching of the training resources and the training task, and to avoid resource waste and uneven distribution.

[0040] Here, the K-means clustering (K-Means) algorithm or the density-based spatial clustering of applications with noise (Density-Based Spatial Clustering of Applications with Noise, DBSCAN) algorithm can be used to cluster the key features to obtain the clustering feature clusters, and the embodiments of the present application are not limited thereto.

[0041] Taking infantry tactics, new soldier shooting, armored soldier driving, and information warfare simulation training as examples, after collecting relevant data, preprocessing, and feature extraction, the K-Means clustering algorithm is used to divide them into three clusters. The high-resource-demand and high-skill-required armored soldier driving and information warfare simulation training form one cluster, the medium-resource-demand new soldier shooting training forms one cluster, and the low-resource-demand infantry tactics training focusing on team cooperation forms one cluster. According to the characteristics and priorities of each cluster, different proportions of training sites, equipment, and instructor resources are allocated, and the actual situation is dynamically adjusted during training. For example, if some soldiers in the new soldier shooting training part improve their performance quickly and need to increase training time, resources can be allocated from other tasks or idle resources in a timely manner.

[0042] The resource demand of each clustering feature cluster is evaluated, the resource consumption characteristics and fluctuation range of the training tasks in the clustering cluster are analyzed in depth, and the resource demand is dynamically adjusted according to the training task priority and individual training data to finally form a scientific and reasonable resource demand evaluation result.

[0043] Finally, based on the resource demand evaluation result, a training resource allocation scheme is developed, and training resources are reasonably allocated to each clustering cluster to achieve a high degree of matching between resources and demand.

[0044] It can be understood that dynamically allocating resources according to individual training conditions and actual training task requirements can help meet the individualized needs of different training tasks and individuals, improve individual training enthusiasm and training effectiveness, and thus improve overall combat effectiveness. Moreover, by monitoring training resources in real time and dynamically adjusting resource allocation, the potential of training resources can be fully tapped, the use efficiency of training sites, equipment, and other resources can be improved, the service life of equipment can be extended, and the training cost can be reduced.

[0045] It should be noted that the method provided by the embodiments of the present application can adapt to the diversified and dynamic training needs of units, whether it is daily training, exercises, or responding to sudden training tasks, and can quickly and reasonably allocate resources to ensure the smooth development of training work.

[0046] It can be understood that this systematic resource allocation method can comprehensively improve training effectiveness and resource utilization efficiency, reduce resource waste, improve the completion rate and quality of training tasks, shorten the training cycle, and improve overall training efficiency.

[0047] The method provided by the embodiment of the present application can accurately identify the unique resource requirements of each training task by comprehensively collecting various data related to the training task, including training task type, training scale, historical training duration, training resource usage data, training task priority and individual training data, and extracting key features therefrom. This data-driven analysis method can effectively avoid the problems of resource idling or shortage caused by neglecting demand differences in the traditional experience-based static resource allocation mode. Moreover, by clustering analysis, training tasks with similar demand characteristics are classified into a category, and resource demand evaluation is performed on each category. This scheme can reflect the changes in training task demand in real time and dynamically adjust the resource allocation strategy. Compared with the dynamic resource allocation method based on simple rules, this method can more flexibly cope with the dynamic changes in demand and fully utilize the maximum efficiency of training resources. The training resource allocation based on the resource demand evaluation results not only improves the utilization rate of resources, but also ensures that the training task can be completed efficiently, thereby meeting the high requirements of modern training on resource allocation.

[0048] Based on the above embodiment, the key features include training resource consumption rate of unit personnel or equipment, site usage intensity, equipment wear rate, training task type feature, training progress deviation and skill improvement rate; The step 120 comprises: Step 121, determining the training resource consumption rate of unit personnel or equipment based on the training scale and the historical training duration; Step 122, extracting the site usage intensity and the equipment wear rate in the training resource usage data; Step 123, extracting the training task type feature of the training task type; Step 124, extracting the training progress deviation and the skill improvement rate in the individual training data.

[0049] Specifically, the key features include training resource consumption rate of unit personnel or equipment, site usage intensity, equipment wear rate, training task type feature, training progress deviation and skill improvement rate.

[0050] Correspondingly, the training resource consumption rate of unit personnel or equipment can be determined based on the training scale and the historical training duration. Here, the training resource consumption rate of unit personnel or equipment = total resource consumption amount / (training scale x historical training duration). For example, in a certain military training task, the total resource consumption amount is 1000 units, the training scale is 100 people, and the historical training duration is 10 days, then the training resource consumption rate of unit personnel is 1000 / (100 x 10) = 1 unit / (person-day).

[0051] Then, the intensity of field usage and the rate of equipment wear and tear in the training resource usage data can be extracted. Here, the intensity of field usage refers to the load degree of the field per unit time, which is obtained by counting the frequency and duration of training field usage in the training resource usage data. The rate of equipment wear and tear refers to the proportion of equipment wear and tear in training, which is calculated based on the equipment wear and tear data.

[0052] Further, the training task type feature is to encode different training task types (tactics, shooting, physical fitness, information-based operations, etc.) into quantifiable numerical values, such as One-Hot Encoding or embedding vectors, etc.

[0053] The training progress deviation is calculated by analyzing the difference between the actual training progress and the planned progress in the individual training data, which can reflect the difference between the individual training effect and the expected goal. The skill improvement rate is calculated based on the change rate of skill mastery degree in the individual training data, which is used to evaluate the speed of skill growth of the trainee.

[0054] Based on the above embodiments, the resource demand evaluation of each cluster feature cluster in step 130 obtains a resource demand evaluation result, which includes: Step 131, determining the average resource demand and resource demand fluctuation range of the training tasks in each cluster feature cluster; Step 132, based on the average resource demand, the resource demand fluctuation range, the training task priority and the individual training data, performing resource demand evaluation to obtain the resource demand evaluation result.

[0055] Specifically, the average resource demand and resource demand fluctuation range of the training tasks in each cluster feature cluster can be determined, wherein the average resource demand includes the average field usage area, the average equipment usage duration, and the average number of instructors.

[0056] The average resource demand refers to the average consumption of all training tasks in a certain cluster feature cluster on a specific resource type. For example, the average field usage area refers to the average value of the field area used by all training tasks in the cluster; the average equipment usage duration refers to the average duration of equipment used by all training tasks; and the average number of instructors refers to the average number of instructors allocated to each training task. These average values are calculated by collecting and analyzing the relevant data of all training tasks in the cluster, which can provide a benchmark reference for resource allocation.

[0057] The resource demand fluctuation range reflects the degree of change in resource demand between different training tasks. It is determined by calculating the difference between the resource demand of each training task within a cluster and the average resource demand, usually in the form of standard deviation or range. The greater the fluctuation range, the greater the difference in resource demand between different tasks, and the higher the flexibility that needs to be considered in resource allocation.

[0058] Based on the average resource demand and resource demand fluctuation range calculated above, combined with training task priority and individual training data, a comprehensive resource demand assessment is made. Training task priority refers to the different priorities given according to the importance and urgency of the training task. High-priority tasks will be given priority in resource allocation. Individual training data includes specific information about each individual participating in training, such as training progress and skill level. These data help to more accurately assess the actual resource needs of each individual.

[0059] By integrating these factors, a resource demand assessment result can be obtained, which can provide a scientific basis for resource allocation and ensure that resource allocation meets the basic needs of training tasks while taking into account task priorities and individual differences, thereby achieving rational and efficient allocation of resources.

[0060] Based on any of the above embodiments, step 140 includes: Step 141, in the case where the resource demand assessment result is that the training resources meet the first type, based on the resource demand proportion of each clustering feature cluster, training resource allocation is performed; Step 142, in the case where the resource demand assessment result is that the training resources meet the second type, based on the priority of each clustering feature cluster, training resource allocation is performed.

[0061] Specifically, in the case where the resource demand assessment result is that the training resources meet the first type, based on the resource demand proportion of each clustering feature cluster, training resource allocation is performed. In the case where the resource demand assessment result is that the training resources meet the second type, based on the priority of each clustering feature cluster, training resource allocation is performed.

[0062] Here, the training resources meet the first type, i.e., the training resources are sufficient, and the training resources meet the second type, i.e., the training resources are insufficient. If the resources are insufficient, the resource demand of high-priority clustering clusters is prioritized, and for low-priority clustering clusters, resource rotation, shared use, etc. are used for allocation, and a resource dynamic adjustment mechanism is established to optimize the resource allocation scheme in a timely manner according to new situations that arise during training.

[0063] The method provided by the embodiment of the present application adopts different allocation strategies according to whether the resources are sufficient, so that the resource allocation is more flexible and can adapt to different resource conditions. When the resources are sufficient, the demand proportion allocation can fully utilize the resources; and when the resources are insufficient, the priority allocation can ensure that the key tasks are met, which embodies the adaptability of the resource allocation strategy.

[0064] Based on the above embodiment, step 140 further includes: Step 140-1, monitoring running data and resource usage data; the running data and the resource usage data are obtained from the training tasks after the training resources are allocated to the training tasks; Step 140-2, updating the resource demand evaluation result based on the running data and the resource usage data.

[0065] Specifically, the training resources are allocated to the training tasks according to the formulated resource allocation strategy, and the running data and the resource usage data of the training tasks are collected in real time through the training monitoring system in the training process.

[0066] Then, the resource demand evaluation result is updated based on the running data and the resource usage data. Based on the updated resource demand evaluation result, the resource allocation is performed. That is, based on the new situation (such as the individual training progress speeding up or slowing down, the temporary adjustment of the training task, etc.) in the training process in the running data and the resource usage data, the resource allocation scheme is optimized in time.

[0067] The present application aims to provide a method for optimizing training resource allocation by using big data clustering algorithm, which can accurately grasp the resource demand characteristics of different training tasks through clustering analysis of big data related to training tasks, realize dynamic, reasonable and efficient allocation of training resources, improve training quality and resource utilization efficiency, and enhance combat effectiveness. The specific implementation steps of the method are as follows: first, data collection, through training management system, field sensors and other channels, collect multi-dimensional information such as training task type, scale, historical duration, resource usage, task priority and individual training data, lay a foundation for subsequent analysis; then, data preprocessing, cleaning, denoising and normalizing the collected data, such as correcting error data, filling missing values, mapping data to the range of [0, 1], to ensure data quality; then, feature extraction, calculate the training resource consumption rate of unit personnel or equipment, site usage intensity and other key features, encode task type, and mine individual training progress and other features to provide basis for clustering analysis; then, use K-Means, DBSCAN and other big data clustering algorithms to divide training tasks into different clustering clusters according to feature data, and each cluster has similar resource demand mode; for each clustering cluster, build a resource demand evaluation model, calculate the average resource demand, fluctuation range and other indicators, dynamically adjust the resource demand combined with the task priority and individual situation; according to the evaluation results, develop resource allocation strategies, allocate resources in proportion to demand when resources are sufficient, prioritize high-priority tasks when resources are insufficient, allocate low-priority tasks using resource rotation, sharing and other methods, and establish a dynamic adjustment mechanism; finally, execute resource allocation, use the training monitoring system to collect training data in real time, and feed back to the evaluation module for continuous optimization of resource allocation.

[0068] The training resource allocation device provided by the present application is described below. The training resource allocation device described below can be referred to in conjunction with the training resource allocation method described above.

[0069] Based on any of the above embodiments, the present application provides a training resource allocation device, Figure 2 is a structural schematic diagram of the training resource allocation device provided by the present application, as Figure 2 shown, the device comprises: An acquisition unit 210 is configured to acquire training resources related to training tasks. The training resources include training task type, training scale, historical training duration, training resource usage data, training task priority and individual training data. An extraction unit 220 is configured to extract key features from the training resources. The key features are used to reflect the resource demand characteristics of the training tasks. A resource demand evaluation unit 230 is configured to cluster the key features to obtain each clustering feature cluster, and evaluate the resource demand of each clustering feature cluster to obtain a resource demand evaluation result. The training resource allocation unit 240 is configured to allocate training resources based on the resource demand evaluation result.

[0070] The device provided by the embodiment of the present application can accurately identify the unique resource demand of each training task by comprehensively collecting various data related to the training task, including the training task type, the training scale, the historical training duration, the training resource usage data, the training task priority and the individual training data, and extracting key features therefrom. This data-driven analysis method can effectively avoid the problems of resource idling or shortage caused by neglecting demand differences in the traditional experience-based static resource allocation mode. Moreover, by cluster analysis, the training tasks with similar demand characteristics are classified into a category, and resource demand evaluation is performed on each category. This scheme can reflect the changes in training task demand in real time and dynamically adjust the resource allocation strategy. Compared with the dynamic resource allocation method based on simple rules, this method can more flexibly cope with the dynamic changes in demand and fully exert the maximum efficiency of the training resources. The training resource allocation based on the resource demand evaluation result not only improves the utilization rate of resources, but also ensures that the training task can be completed efficiently, thereby meeting the high requirements of modern training on resource allocation.

[0071] According to any one of the above embodiments, the key features include the training resource consumption rate of unit personnel or equipment, the site usage intensity, the equipment wear rate, the training task type feature, the training progress deviation and the skill improvement rate; The extraction unit 220 is specifically configured to: determine the training resource consumption rate of unit personnel or equipment based on the training scale and the historical training duration; extract the site usage intensity and the equipment wear rate from the training resource usage data; extract the training task type feature of the training task type; extract the training progress deviation and the skill improvement rate from the individual training data.

[0072] According to any one of the above embodiments, the training task type includes tactical training, shooting training, physical training and informationized combat training; The training resource usage data includes training site usage frequency, training site usage duration, equipment wear degree, instructor teaching duration and instructor teaching intensity; The individual training data includes physical test results, skill mastery degree and learning progress.

[0073] According to any one of the above embodiments, the resource demand evaluation unit 230 is specifically configured to: determine the average resource demand and the resource demand fluctuation range of the training tasks in each cluster feature cluster. perform resource demand evaluation based on the average resource demand, the resource demand fluctuation range, the training task priority and the individual training data, to obtain the resource demand evaluation result.

[0074] In any of the above embodiments, the obtaining unit 210 is specifically configured to: obtain original training resources related to the training task; perform preprocessing operations on the original training resources to obtain the training resources; the preprocessing operations include data cleaning, denoising processing, normalization processing and missing value processing; The missing value processing includes mean filling, median filling and predicted value filling based on a prediction model constructed based on the original training resources. The mean filling and the median filling are based on the mean and the median of similar training tasks of the training task, respectively.

[0075] In any of the above embodiments, the resource demand evaluation unit 230 is specifically configured to: use a K-means clustering algorithm or a density-based spatial clustering application with noise algorithm to cluster the key features to obtain the feature clusters.

[0076] In any of the above embodiments, the training resource allocation unit 240 is specifically configured to: In the case that the resource demand evaluation result is that the training resources meet the first type, perform training resource allocation based on the resource demand proportion of each clustering feature cluster; In the case that the resource demand evaluation result is that the training resources meet the second type, perform training resource allocation based on the priority of each clustering feature cluster.

[0077] In any of the above embodiments, further comprising an updating unit, which is specifically configured to: monitor running data and resource usage data; the running data and the resource usage data are obtained from the training tasks after the training resources are allocated to the training tasks; update the resource demand evaluation result based on the running data and the resource usage data.

[0078] Figure 3 is a structural schematic diagram of an electronic device provided by the present application, as shown in Figure 3As shown, the electronic device can include a processor 310, a communications interface 320, a memory 330, and a communications bus 340, wherein the processor 310, the communications interface 320, and the memory 330 complete mutual communication through the communications bus 340. The processor 310 can invoke a logical instruction in the memory 330 to execute a training resource allocation method, which includes: obtaining training resources related to a training task; the training resources include a training task type, a training scale, a historical training duration, training resource usage data, a training task priority, and individual training data; extracting key features in the training resources; the key features are used to reflect resource demand characteristics of the training task; clustering the key features to obtain each clustering feature cluster, and performing resource demand evaluation on the each clustering feature cluster to obtain a resource demand evaluation result; and performing training resource allocation based on the resource demand evaluation result.

[0079] In addition, the logical instruction in the memory 330 described above can be implemented in the form of a software functional unit and sold or used as an independent product, and can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0080] On the other hand, the present application also provides a computer program product, which includes a computer program, the computer program can be stored on a non-transitory computer readable storage medium, and the computer program is executed by a processor, so that the computer can execute the training resource allocation method provided by the above-mentioned methods, which includes: obtaining training resources related to a training task; the training resources include a training task type, a training scale, a historical training duration, training resource usage data, a training task priority, and individual training data; extracting key features in the training resources; the key features are used to reflect resource demand characteristics of the training task; clustering the key features to obtain each clustering feature cluster, and performing resource demand evaluation on the each clustering feature cluster to obtain a resource demand evaluation result; and performing training resource allocation based on the resource demand evaluation result.

[0081] In yet another aspect, the present application also provides a non-transitory computer readable storage medium having stored thereon a computer program, which, when executed by a processor, implements the training resource allocation method provided by any of the above methods, the method comprising: obtaining training resources related to a training task; the training resources comprising training task type, training scale, historical training duration, training resource usage data, training task priority and individual training data; extracting key features in the training resources; the key features being used to reflect resource requirement characteristics of the training task; clustering the key features to obtain each clustering feature cluster, and performing resource requirement evaluation on each clustering feature cluster to obtain a resource requirement evaluation result; and performing training resource allocation based on the resource requirement evaluation result.

[0082] The device embodiments described above are merely illustrative, wherein the units described as separate components can or can not be physically separated, and the components displayed as units can or can not be physical units, i.e., they can be located in one place, or distributed on multiple network units. Part or all of the modules can be selected to achieve the purpose of the present embodiment scheme according to actual needs. Those skilled in the art can understand and implement it without creative labor.

[0083] From the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be realized by means of software plus a necessary general hardware platform, and of course, it can also be realized by hardware. Based on such understanding, the above technical solutions, essentially or in other words, the part that contributes to the prior art, can be embodied in the form of a software product, which can be stored in a computer readable storage medium, such as a ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the methods described in each embodiment or some parts of the embodiments.

[0084] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement to some technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for allocating training resources, characterized in that, include: Acquire training resources relevant to the training task; The training resources include training task types, training scale, historical training duration, training resource usage data, training task priority, and individual training data. Extract key features from the training resources; these key features are used to reflect the resource requirements of the training task. The key features are clustered to obtain each cluster feature cluster, and the resource demand of each cluster feature cluster is assessed to obtain the resource demand assessment results. Based on the resource demand assessment results, training resources are allocated.

2. The training resource allocation method according to claim 1, characterized in that, The key features include the training resource consumption rate of a unit of personnel or equipment, the intensity of site use, the equipment wear rate, the characteristics of training task types, the deviation of training progress, and the skill improvement rate. The extraction of key features from the training resources includes: Based on the training scale and the historical training duration, determine the training resource consumption rate of the unit personnel or equipment; Extract the site usage intensity and equipment wear rate from the training resource usage data; Extract the training task type features of the training task type; Extract the training progress deviation and the skill improvement rate from the individual training data.

3. The training resource allocation method according to claim 1, characterized in that, The training mission types include tactical training, shooting training, physical training, and information warfare training; The data on the use of training resources includes the frequency of use of training venues, the duration of use of training venues, the degree of equipment wear and tear, the duration of instructor teaching, and the intensity of instructor teaching. The individual training data includes physical fitness test scores, skill mastery levels, and learning progress.

4. The training resource allocation method according to any one of claims 1 to 3, characterized in that, The process of assessing resource requirements for each cluster feature cluster to obtain resource requirement assessment results includes: Determine the average resource requirement and the range of resource requirement fluctuation for the training task within each cluster feature cluster; Resource demand is assessed based on the average resource demand, the range of resource demand fluctuation, the priority of the training task, and the individual training data, resulting in the resource demand assessment.

5. The training resource allocation method according to any one of claims 1 to 3, characterized in that, The acquisition of training resources related to the training task includes: Obtain the original training resources related to the training task; The original training resources are preprocessed to obtain the training resources; the preprocessing operations include data cleaning, noise reduction, normalization, and missing value handling. The missing value processing includes mean imputation, median imputation, and prediction value imputation based on the prediction model constructed from the original training resources; The mean padding and median padding are performed based on the mean and median of similar training tasks of the training task.

6. The training resource allocation method according to any one of claims 1 to 3, characterized in that, The clustering of the key features to obtain each cluster feature cluster includes: The key features are clustered using the K-means clustering algorithm or a density-based spatial clustering algorithm with noise to obtain the feature clusters.

7. The training resource allocation method according to any one of claims 1 to 3, characterized in that, The allocation of training resources based on the resource demand assessment results includes: If the resource requirement assessment result indicates that the training resources meet the first type, the training resources are allocated based on the resource requirement ratio of each cluster feature cluster. If the resource requirement assessment result indicates that the training resources meet the second type, the training resources are allocated based on the priority of each cluster feature cluster.

8. The training resource allocation method according to any one of claims 1 to 3, characterized in that, The process of allocating training resources based on the resource demand assessment results further includes: Monitor operational data and resource usage data; the operational data and resource usage data are obtained from each training task after the training resources are allocated to each training task; Based on the operational data and the resource usage data, update the resource demand assessment results.

9. A training resource allocation device, characterized in that, include: The acquisition unit is used to acquire training resources related to the training task; The training resources include training task types, training scale, historical training duration, training resource usage data, training task priority, and individual training data. An extraction unit is used to extract key features from the training resources; the key features are used to reflect the resource requirement features of the training task. The resource demand assessment unit is used to cluster the key features to obtain each cluster feature cluster, and to assess the resource demand of each cluster feature cluster to obtain the resource demand assessment result. The training resource allocation unit is used to allocate training resources based on the resource demand assessment results.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the training resource allocation method as described in any one of claims 1 to 8.

11. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the training resource allocation method as described in any one of claims 1 to 8.

Images