Production safety cloud training service data intelligent management method and system
By dynamically managing the training content of cloud training services, dynamic production safety training forests are generated based on user differences, solving the problems of inefficiency and resource waste caused by fixed training content in existing cloud training services, and achieving more efficient training results and resource utilization.
Patent Information
- Application Number
- CN202510109249.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-01-23
- Publication Date
- 2025-05-27
AI Technical Summary
The training format and content of existing cloud training services are fixed, and cannot adapt to the differences between different users, resulting in low training efficiency, waste of resources and waste of communication resources.
The training content is dynamically managed through the dynamic production safety training forest, and the training content is adaptively generated based on the degree of mastery and understanding of each user, a dynamic production safety training sequence is generated, and the loading and provision of training content is optimized through the deep priority traversal and expansion mechanism.
It improves the efficiency of training and the utilization efficiency of software and hardware resources, optimizes the space use efficiency of cloud servers, and achieves more efficient training results.
Smart Images
Figure CN120047277A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of cloud computing, and particularly relates to a method and system for intelligent management of production safety cloud training service data.
Background Art
[0002] Cloud training service refers to an online training solution provided through cloud computing technology, aiming to help enterprises or individuals conduct efficient and convenient learning and training through the Internet. Such services usually include various functions and tools, such as online courses, examinations, knowledge bases, videos, live broadcasts, AI coaches, etc., to meet the learning needs of different users; the cloud training platform provides rich functions, including examinations, knowledge bases, videos, live broadcasts, AI coaches, organizational knowledge extraction, job ability models, learning communities, intelligent learning reports, online learning plans, teaching tools, etc.; cloud training services provide enterprises and individuals with an efficient, convenient, and personalized training solution through cloud computing technology. It not only has powerful functions, but also has a beautiful interface, perfect after-sales service, a wide range of customer groups, and diverse learning methods, which can meet the learning needs of different users and improve learning enthusiasm and effects; cloud training service is an enterprise training solution that can provide one-stop learning, mobile learning, combination of examinations and learning, and build a multi-terminal learning platform and a smart learning community; cloud computing technology provides powerful computing and storage resources, enabling enterprises to access and use these resources through the Internet without building their own data centers, thus greatly reducing the costs of enterprises and improving the flexibility and scalability of resources; big data analysis technology is used to process and analyze a large amount of production safety data to help enterprises identify potential safety risks and optimize production processes. Through data mining and machine learning algorithms, real-time monitoring and early warning of production data can be achieved.
[0003] Cloud training services usually use cloud training servers, which are server facilities dedicated to cloud computing training. They are usually deployed in a cloud computing environment and provide a hardware platform for trainees to receive cloud computing-related training. It has high-performance computing capabilities and needs to have sufficient processing power to meet the needs of multiple trainees for training simultaneously. It is usually equipped with multi-core processors, large-capacity memory, and high-speed hard disks to support complex computing tasks; at the same time, it also needs to have multi-user support capabilities, be able to be provided for multiple trainees to use simultaneously, and each trainee can independently use the resources of the server for experiments and learning, improving training efficiency and reducing resource waste; in addition, network connection performance is also very important and must have a high-speed and stable network connection to ensure that trainees can smoothly access the cloud computing platform and related resources and reduce waiting time.
[0004] In the prior art, it is often the enterprise that formulates training programs for trainees to choose and study, establishes examination tasks for trainees to take exams, and then constructs an effective evaluation and feedback system to evaluate the training effect, identify potential problems and provide improvement measures. However, the training form and content are often fixed, unable to adapt to different users, and the differences between users are not fully utilized, resulting in low training efficiency, waste of time, software and hardware resources. Whether the training content is effective or not, it will be generated and pushed in a package, wasting communication resources, storage resources, computing resources, and the training time of users. The present invention aims to solve the deficiencies of the prior art. Based on the above problems, the present invention dynamically manages the training content through a dynamic production safety training forest, adaptively generates training content according to the different mastery and understanding levels of each user, improves the training efficiency, and fully utilizes the software and hardware resources of the cloud training server.
Summary of the Invention
[0005] To solve the above problems in the prior art, the present invention proposes a method and system for intelligent management of production safety cloud training service data. The method includes:
[0006] Step S1: The training server receives a training request, determines the training content based on the training request, and arranges the training content in the order of occurrence in the production process according to the training topics involved in its corresponding key links and / or potential risks to form a production safety training sequence.
[0007] Step S2: Generate a dynamic production safety training forest based on the production safety training sequence, and conduct production safety training for users based on the production safety training forest. Specifically:
[0008] Step S21: Take each element in the production safety training sequence as a root node in turn to form the initial structure of the current production safety training forest.
[0009] Step S22: Perform a depth-first traversal of the current production safety training forest. For each current node during the traversal, obtain a test file based on its training topic. The user conducts a test based on the test file and obtains a test score. When the test score is greater than or equal to the first preset score, obtain the sibling node of the current node as the new current node, and continue the depth-first traversal of the current production safety training forest. Otherwise, expand the current node. Take the expanded safety training forest as the updated current production safety training forest and continue the depth-first traversal. Repeat this step until the traversal ends.
[0010] The expansion of the current node is specifically: obtain the sub-training topics included in the training topic corresponding to the current node, and arrange each sub-training topic in the order of training time as the child nodes of the current node.
[0011] Further, the training server is a cloud server.
[0012] Further, after receiving a training request, the training server creates an application space corresponding to the training request in the training application space.
[0013] Further, the application space includes a program space and a storage space.
[0014] Further, training requests from different users share the training application space.
[0015] Further, the created application space corresponding to each training request is dynamically scalable.
[0016] A production safety cloud training service data intelligent management system, which is used to implement the above-mentioned production safety cloud training service data intelligent management method.
[0017] A production safety cloud training service data intelligent management device, which is used to implement the above-mentioned production safety cloud training service data intelligent management method.
[0018] A production safety cloud training service data intelligent management cloud server, which is used to implement the above-mentioned production safety cloud training service data intelligent management method.
[0019] A production safety cloud training service data intelligent management server, characterized in that the production safety cloud training service data intelligent management server is used to implement the above-mentioned production safety cloud training service data intelligent management method.
[0020] The beneficial effects of the present invention include:
[0021] (1) Dynamically manage training content through a dynamic production safety training forest, adaptively generate training content according to the different mastery and understanding levels of each user, reduce unnecessary training content loading and training, and improve the training efficiency and the utilization efficiency of software and hardware resources;
[0022] (2) Preload training content while expanding to improve the providing efficiency and pertinence of training content, optimize the use of program space among multiple users, improve the space utilization efficiency of the cloud server, and ultimately achieve the effect of improving training efficiency;
[0023] (3) Through forward pruning and backward pruning, fine-grained training content can be advanced at an early stage, making the training arrangement more compact and coupled; it is also possible to change the splitting method according to the test scores, flexibly change the training method, and find a training method suitable for users during the dynamic expansion process, further improving the training effect.
BRIEF DESCRIPTION OF THE DRAWINGS
[0024] The drawings described herein are used to provide a further understanding of the present invention, form a part of this application, but do not constitute an improper limitation to the present invention. In the drawings:
[0025] Figure 1 It is a schematic diagram of the intelligent management method for production safety cloud training service data provided by the present invention.
DETAILED DESCRIPTION OF THE EMBODIMENTS
[0026] The present invention will be described in detail below in conjunction with the drawings and specific embodiments, in which the illustrative embodiments and descriptions are only used to explain the present invention, but do not constitute a limitation to the present invention.
[0027] The present invention proposes an intelligent management method and system for production safety cloud training service data. As shown in the attached Figure 1 figure, the method includes the following steps:
[0028] Step S1: Generate a production safety training sequence based on the production process; specifically: the training server receives a training request, determines the training content based on the training request; arranges the training content in the order of occurrence in the production process according to the corresponding key links and / or training topics related to potential risks to form a production safety training sequence; then each training topic corresponds to an element in the production safety training sequence;
[0029] Preferably: The training server is a cloud server;
[0030] Preferably: After receiving the training request, the training server creates an application space corresponding to the training request in the training application program space; wherein: the application space includes a program space and a storage space;
[0031] Preferably: Training requests from different users share the training application program space; the created application space corresponding to each training request is dynamically expandable, and when preloading data is loaded, it is dynamically expanded according to the created application space associated with the training request to adapt to the dynamically changing preloaded data size;
[0032] Preferably: Identify the key links and / or potential risk points in the production process, determine the training topics corresponding to each key link and potential risk point, and arrange the training topics in the order of occurrence of their corresponding key links and / or potential risks in the production process to form a production safety training sequence; these main training topics may include safety operation procedures, equipment use and maintenance, and / or emergency handling, etc.;
[0033] The identification of the key links and / or potential risk points in the production process is specifically as follows: Analyze the production process in detail, and identify the safety risks and operation key points in each link through flowcharts, operation manuals, and on-site observations, so as to determine the key links and / or potential risk points related to the safety training of the production process;
[0034] Alternatively: Generate a production safety training sequence based on the production process; specifically: According to the determined training topics and the production process analysis results, formulate a training plan, and the training plan should include training time, training content, and training methods; Arrange the training content in the order of time to form a production safety training sequence;
[0035] Step S2: Generate a dynamic production safety training forest based on the production safety training sequence; Conduct production safety training for users based on the production safety training forest; specifically:
[0036] Step S21: Take each element in the production safety training sequence as a root node in turn to form the initial structure of the current production safety training forest;
[0037] Preferably: This step further includes: Pre-load the training content involved in the training topics corresponding to all training nodes in the current production safety training forest; The training content is loaded into the created application program space associated with the training request;
[0038] Step S22: Perform a depth-first traversal of the current production safety training forest; For each current node during the traversal process, obtain a test file based on its training topic; The user conducts a test based on the test file and obtains a test score; Expand the current production safety training forest based on the test score or continue the traversal of the current production safety training forest; Repeat this step until the traversal ends; At the end of the traversal, the current node is empty;
[0039] Preferably: The test file is a test file adapted to the training topic; When conducting tests for the same training topic multiple times, the test file is variable or fixed;
[0040] Preferably: Use an artificial intelligence model to generate test files. Specifically: Determine the type and content of the exam files to be generated, such as single-choice questions, multiple-choice questions, true or false questions, etc.; Collect and train documents related to the theme, such as PPT, Word, PDF, etc.; Select an artificial intelligence model and perform the function of intelligent question generation to generate test files; Set test parameters to determine the time limit of the test, test criteria, etc.; After the test, the system automatically grades and generates test scores;
[0041] Expand the current production safety training forest based on the test score or continue the traversal of the current production safety training forest; Specifically: When the test score is greater than or equal to the first preset score, obtain the sibling node (or the next node) of the current node as the new current node, and continue the depth-first traversal of the current production safety training forest; Otherwise (when the test score is less than the first preset score), expand the current node; Use the expanded safety training forest as the updated current production safety training forest and continue the depth-first traversal;
[0042] Expand the current node; Specifically: Obtain the sub-training themes included in the training theme corresponding to the current node, and arrange each sub-training theme in the order of training time and use them as the child nodes of the current node in turn; It can be seen that the expansion here is one-layer expansion;
[0043] Preferably: Set the initial value of the current node to the first root node, that is, the first element in the production safety training sequence;
[0044] Preferably: When the test score is greater than or equal to the second preset score, delete the training content of the training theme corresponding to the current node from the application space created for the training request; Wherein: The second preset score is greater than the first preset score;
[0045] Preferably, during the depth-first traversal, if there are no unvisited sibling nodes for the current node, then the sibling node (or the next node) of the parent node of the current node is used as the new current node; when the current node is empty, that is, there are no unvisited new current nodes, the traversal of the current production safety training forest ends, marking the end of the production safety training; for example, during the traversal, when passing through the current node A for the first time, if the test score for node A is less than the first preset score, it is expanded. If the test scores of all child nodes after expansion are greater than or equal to the first preset score, the traversal will return to node A again; at this time, there are two processing methods; Method 1: Do not test node A anymore; set the current node to the sibling node of node A, or the sibling node of the parent node (or the next node), and perform the traversal of the subsequent nodes; Method 2: Test node A again. If the score for node A is still less than the first preset score at this time, then node A needs to be expanded again. Here, the expansion method needs to change the splitting method of the training topic for node A. The training topic is split into sub-training topics using the replacement splitting method and then expanded again; all child nodes of node A formed in the previous expansion need to be deleted before expansion; of course, after re-splitting, the subtree with node A as the root needs to be traversed again until the test score for node A is greater than or equal to the first preset score when passing through node A again; it can also be selected to change the splitting method after the number of re-traversals reaches the preset number of times;
[0046] The obtaining of the sub-training topics included in the training topic corresponding to the current node is specifically as follows: obtain the splitting method of the training topic, and split the training topic into one or more sub-training topics based on the obtained splitting method; during multiple expansions of the same training topic, the splitting method can be changed according to the test score, flexibly changing the training method, and finding a training method suitable for users during the dynamic expansion process to improve the training effect;
[0047] Preferably, the sub-training topics after expansion do not intersect or intersect with each other;
[0048] Preferably, after the expansion, pruning is performed on the expanded safety training forest; specifically: perform forward pruning on the expanded safety training forest; obtain each child node of the current node, and sequentially judge the repetition degree (or semantic similarity) between each child node and the training topic (or the training content involved) of the subsequent nodes of the production safety training forest (subsequent nodes in the depth-first traversal relationship); when the repetition degree (or semantic similarity) is greater than or equal to the repetition degree threshold (or similarity threshold), delete the child node; it can be seen that forward pruning is a coarse-grained pruning. When the repetition degree between the coarse-grained training content and the subsequent training content is relatively high, then from the perspective of training time, it is a more appropriate training arrangement to postpone the training content;
[0049] Preferably, the repetition threshold and the similarity threshold are preset values; for example, 50%.
[0050] Considering that different users have different degrees of understanding of the training content, the amount of training content that needs to be participated in also needs to be dynamically adapted, so as to improve the training efficiency. Therefore, the following replacement method is proposed to expand and preload the training content at the same time, so as to improve the provision efficiency and pertinence of the training content. At the same time, since the training application space is often shared among multiple users, through the preloading of the training content, the program space can be optimized and utilized among multiple users, improving the space utilization efficiency of the cloud server, and finally achieving the effect of improving the training efficiency.
[0051] Preferably, when the test score is less than the first preset score, pre-expand the current node and preload the corresponding training content based on the amount of the test score; specifically, it includes the following steps:
[0052] Step S2A1: Obtain the pre-expansion level and the preloading data size; specifically: determine the score range in which the test score falls; obtain the pre-expansion level and the preloading data size corresponding to the score range; when the value of the score range that falls is lower, the deeper the pre-expansion level of the current node, and the more the corresponding training content preloaded; conversely, when the value of the score range that falls is higher, the shallower the pre-expansion level of the current node, and the less the corresponding training content preloaded.
[0053] Preferably, the values between the score ranges do not overlap.
[0054] Preferably, set the numerical space of the score to 0-100; divide it into 2-10 score ranges. When the score range is 10, the divided score ranges are: [0, 10), [10, 20),..., [90, 100]; of course, in some score ranges, the pre-expansion level can be set to 0, and the preloading data size is also correspondingly 0.
[0055] Preferably, pre-set and save the correspondence between the score range and the pre-expansion level and the preloading data size.
[0056] Step S2A2: Set the initial values of the level count value and the size count value to 0; set the expansion root node as the current node; set the pointer node as the expansion root node.
[0057] Step S2A3: Expand the training topics involved in the pointer node to obtain one or more sub-training topics; arrange each sub-training topic in chronological order of training and use them as the child nodes of the pointer node in sequence; set the size count value to be equal to the sum of the size count value and the sum of the training content data sizes of all sub-training topics; set the level count value to be equal to the level count value plus one;
[0058] Preferably: If the sum of the data sizes of all sub-training topics is greater than the difference between the pre-loaded data size and the size count value, then select some sub-training topics whose sum of data sizes is closest to this difference, arrange them in chronological order of training, and use them as the child nodes of the current node in sequence;
[0059] Alternatively: If the sum of the data sizes of all sub-training topics is greater than the difference between the pre-loaded data size and the size count value, then select some sub-training topics whose sum of data sizes is closest to this difference according to the importance level, arrange them in chronological order of training, and use them as the child nodes of the current node in sequence;
[0060] Step S2A4: If the level count value is less than the pre-expanded level or the size count value is less than the pre-loaded data size, then proceed to the next step; otherwise, proceed to Step S2A6;
[0061] Step S2A5: Set the pointer node as traversed, and update and set the pointer node as the first untraversed child node when performing a breadth-first traversal of the subtree with the expanded root node as the root node; return to Step S2A3;
[0062] Step S2A6: Load the training content data involved in the training topics of all nodes in the subtree with the expanded root node as the root node into the application space corresponding to the training request;
[0063] Preferably: Before performing data loading, prune the subtree with the expanded root node as the root node; specifically: perform backward pruning on the subtree with the expanded root node as the root node; traverse the subtree with the expanded root node as the root node in a depth-first traversal manner; for each current node during the traversal process, judge the duplication degree (or semantic similarity degree) between it and the subsequent nodes. If there is a subsequent node whose duplication degree (or semantic similarity degree) with this node is greater than or equal to the duplication threshold (or similarity threshold), then delete this subsequent node; after multi-level expansion, the granularity of the training content involved in the training topics is relatively small. At this time, using the backward pruning method can advance the fine-grained training content earlier, making the training arrangement more compact and coupled;
[0064] Based on the same inventive concept, the present invention also provides an intelligent management system for production safety cloud training service data. The system is used to execute the above-mentioned intelligent management method for production safety cloud training service data. The system includes a cloud training server and user terminals. The user terminals are used to send training requests to the cloud training server, and the cloud training server is used to generate a current production safety training forest corresponding to the training request and create an application program space corresponding to the training request.
[0065] A program space corresponding to the training application program is set in the cloud training server. This program space includes an application program space corresponding to each training request and a shared program space shared among each training request.
[0066] Preferably, after the cloud training service is completed, all the training contents related to the training topics of the nodes are obtained from the production safety training forest in the order of depth-first traversal, and are pushed to the user terminals after being arranged in the traversal order.
[0067] A computer program (also known as a program, software, software application, script, or code) can be written in any form of programming language, including assembly or interpreted languages, declarative or procedural languages, and can be deployed in any form, including as a stand-alone program or as a module, component, subroutine, object, or other unit suitable for use in a computing environment. A computer program may or may not correspond to a file in a file system. The program can be stored as part of a file that holds other programs or data (such as one or more scripts stored in a markup language document), in a single file dedicated to the program, or in multiple cooperating files (such as files that store one or more modules, subroutines, or code portions). A computer program can be deployed to execute on one computer or on multiple computers located at one site or distributed across multiple sites and interconnected by a communication network.
[0068] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) containing computer-usable program code.
[0069] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing device produce a means for implementing the functions specified in one or more of the flows Figure 1 one or more of the flows and / or blocks Figure 1 or a means for implementing the functions specified in one or more of the blocks.
[0070] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory produce a manufactured article including an instruction means that implements the functions specified in one or more of the flows Figure 1 one or more of the flows and / or blocks Figure 1 or a means for implementing the functions specified in one or more of the blocks.
[0071] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more of the flows Figure 1 one or more of the flows and / or blocks Figure 1 or a means for implementing the functions specified in one or more of the blocks.
[0072] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: modifications or equivalent replacements can still be made to the specific embodiments of the present invention, and any modifications or equivalent replacements that do not depart from the spirit and scope of the present invention should be covered by the protection scope of the claims of the present invention.
Claims
1. A production safety cloud training service data intelligent management method, characterized in that: The method comprises: Step S1: The training server receives a training request and determines the training content based on the training request; the training content is arranged in the order of occurrence of the training topics corresponding to the key links and / or potential risks in the production process to form a production safety training sequence; Step S2: generating a dynamic production safety training forest based on the production safety training sequence; and performing production safety training on users based on the production safety training forest; Specifically: Step S21: taking each element in the production safety training sequence as a root node in turn to form the initial structure of the current production safety training forest; Step S22: Perform a depth-first traversal of the current production safety training forest; For each current node in the traversal process, obtain the test file based on its training topic; Users take tests based on test files and get test scores; When the test score is greater than or equal to the first preset score, the sibling node of the current node is obtained as the new current node, and the depth-first traversal of the current production safety training forest is continued; otherwise, the current node is expanded; Continue to perform depth-first traversal on the expanded safety training forest as the updated current production safety training forest; repeat this step until the traversal is completed; The expansion of the current node is specifically as follows: obtaining the sub-training topics contained in the training topic corresponding to the current node, and arranging each sub-training topic in the order of training time as the sub-nodes of the current node.
2. The method for intelligent management of production safety cloud training service data according to claim 1 is characterized in that: The training server is a cloud server.
3. The method for intelligent management of production safety cloud training service data according to claim 2 is characterized in that: After receiving the training request, the training server creates an application space corresponding to the training request in the training application space.
4. The method for intelligent management of production safety cloud training service data according to claim 3 is characterized in that: The application program space includes a program space and a storage space.
5. The method for intelligent management of production safety cloud training service data according to claim 4 is characterized in that: Training requests from different users share the training application space.
6. The method for intelligent management of production safety cloud training service data according to claim 5 is characterized in that: The application space created for each training request is dynamically scalable.
7. A production safety cloud training service data intelligent management system, characterized in that: The production safety cloud training service data intelligent management system is used to implement the production safety cloud training service data intelligent management method described in any one of claims 1-6 above.
8. A production safety cloud training service data intelligent management device, characterized in that: The production safety cloud training service data intelligent management device is used to implement the production safety cloud training service data intelligent management method described in any one of claims 1 to 6.
9. A production safety cloud training service data intelligent management cloud server, characterized in that: The production safety cloud training service data intelligent management cloud server is used to implement the production safety cloud training service data intelligent management method described in any one of claims 1-6 above.
10. A production safety cloud training service data intelligent management server, characterized in that: The production safety cloud training service data intelligent management server is used to implement the production safety cloud training service data intelligent management method described in any one of claims 1-6 above.