Operation Optimization Method, Control Device and Learning Machine of Learning Machine

Abstract

The present invention provides an operation optimization method, a control device and a learning machine for a learning machine, belonging to the field of educational technology. The operation optimization method for the learning machine includes: obtaining the user's historical learning records and the type of learning objective currently input or selected by the user through the learning machine; determining the user's current learning progress, learning preferences and learning difficulties during the learning process according to the historical learning records; generating corresponding learning objective data according to the current learning progress, learning preferences, learning difficulties and the type of learning objective; determining the corresponding necessary application programs for the operation of the learning machine and the operation data of the application programs according to the learning objective data; and determining the operation optimization scheme of the learning machine according to the operation data and a preset operation model. The present invention can improve the operation efficiency and user experience of the learning machine, dynamically adjust the operation strategy of the learning machine, and ensure the reasonable allocation of learning resources and the efficient operation of the system.

Description

Technical Field

[0001] This application relates to the field of educational technology, and particularly to an operation optimization method, a control device, and a learning machine for a learning machine. Background Art

[0002] With the development of educational technology, learning machines have become important auxiliary tools for students to learn. However, in the actual use process, learning machines often have low operation efficiency due to problems such as software aging, system lag, cache accumulation, and memory shortage, which affect the user experience and learning efficiency. Existing technologies mostly try to solve the problem through simple cache cleaning or system upgrading, but the effect is limited, and it is difficult to fundamentally solve the deep-seated problems in the operation of learning machines. Summary of the Invention

[0003] The main purpose of the present invention is to provide an operation optimization method for a learning machine, aiming to improve the operation efficiency and user experience of the learning machine, dynamically adjust the operation strategy of the learning machine, and ensure the reasonable allocation of learning resources and the efficient operation of the system.

[0004] To achieve the above purpose, the present invention provides an operation optimization method for a learning machine, and the operation optimization method includes:

[0005] Obtain the user's historical learning records and the type of learning goals currently input or selected by the user through the learning machine;

[0006] According to the historical learning records, determine the user's current learning progress, learning preferences, and learning difficulties during the learning process;

[0007] Generate corresponding learning goal data according to the current learning progress, learning preferences, learning difficulties, and type of learning goals;

[0008] According to the learning goal data, determine the corresponding necessary application programs for the operation of the learning machine and the operation data of the application programs;

[0009] Determine the operation optimization plan of the learning machine according to the operation data and the preset operation model.

[0010] Optionally, the step of generating corresponding learning goal data according to the current learning progress, learning preferences, learning difficulties, and type of learning goals includes:

[0011] Analyze the user's mastery of knowledge points and interest directions according to the current learning progress and learning preferences;

[0012] According to the learning difficulties, determine the problem data of the user during the learning process, and evaluate the influence degree of these problem data on the current learning progress;

[0013] Construct a corresponding target learning framework according to the mastery level, the interest direction, the problem data, and the influence degree.

[0014] Generate a plurality of corresponding sub-goal tasks according to the learning goal type and the target learning framework.

[0015] Determine corresponding learning goal data according to the plurality of sub-goal tasks.

[0016] Optionally, the step of determining the problem data of the user during the learning process according to the learning difficulties and evaluating the influence degree of these problem data on the current learning progress includes:

[0017] Analyze a plurality of corresponding difficulty types currently existing in the user according to the learning difficulties and the preset difficulty types.

[0018] Determine the logical relationship between the learning difficulties according to the plurality of difficulty types to determine the problem data of the user during the learning process.

[0019] Construct a problem dependency network for each learning difficulty according to the logical relationship to determine the learning order of each learning difficulty in the problem dependency network.

[0020] Evaluate the influence degree of the problem data on the current learning progress according to the learning order.

[0021] Optionally, the step of constructing a corresponding target learning framework according to the mastery level, the interest direction, the problem data, and the influence degree includes:

[0022] Set the corresponding learning content priority according to the mastery level and the interest direction.

[0023] Determine the key area and the secondary area of the learning content according to the learning content priority, the problem data, and the influence degree.

[0024] Construct a corresponding target learning framework according to the key area and the secondary area.

[0025] Optionally, the step of determining the operation optimization scheme of the learning machine according to the operation data and the preset operation model includes:

[0026] Analyze the performance of each application program currently running on the learning machine according to the operation data of the application program.

[0027] Evaluate the contribution degree of each application program to the overall operation efficiency of the learning machine and the potential resource occupation conflict according to the performance and the preset operation model.

[0028] Determine the priorities of each application based on the sorting algorithm and the contribution degree;

[0029] Generate the operation optimization plan according to the priorities and the resource occupancy conflicts;

[0030] Optionally, the step of evaluating the contribution degree of each application to the overall operation efficiency of the learning machine and potential resource occupancy conflicts according to the performance and the preset operation model includes:

[0031] According to the performance, count the operation efficiency indexes of each application under preset conditions;

[0032] Calculate the weighted operation efficiency of each application according to the operation efficiency index and the corresponding operation weight factor;

[0033] Evaluate the contribution degree of each application to the overall operation efficiency of the learning machine according to the weighted operation efficiency and the preset operation model;

[0034] Determine potential resource occupancy conflicts according to the weighted operation efficiency, the preset operation model and the contribution degree;

[0035] Optionally, the step of determining the priorities of each application based on the sorting algorithm and the contribution degree includes:

[0036] Based on a multi-objective sorting algorithm, use the contribution degree and the potential resource occupancy conflicts as optimization objectives to comprehensively evaluate the applications;

[0037] Sort the applications according to the comprehensive evaluation results to determine the priorities of each application in the operation optimization plan.

[0038] Optionally, the operation optimization method further includes:

[0039] Obtain the historical operation data of multiple users using the learning machine in different learning scenarios, and preprocess the historical operation data;

[0040] According to the preprocessed historical operation data, analyze the interaction relationship, resource occupancy situation among each application during the operation of the learning machine, and the influence of each application on the overall performance of the learning machine to generate corresponding analysis results;

[0041] According to the analysis results, construct a target mathematical model for the operation of the learning machine, and train the target mathematical model based on a machine learning algorithm;

[0042] Determine the trained target mathematical model as the preset operation model.

[0043] In addition, to achieve the above object, the present invention further provides a control device, which includes: a memory, a processor, and an operation optimization program of a learning machine stored on the memory and executable on the processor. The operation optimization program of the learning machine is configured to implement the operation optimization method of the learning machine as described above.

[0044] In addition, to achieve the above object, the present invention further provides a learning machine, including the control device as described above.

[0045] In an embodiment of the present invention, by obtaining the historical learning records of the user, the current learning progress of the user, as well as the learning preferences and learning difficulties during the learning process are determined. Then, the type of learning objective currently input or selected by the user through the learning machine is obtained, and combined with the current learning progress, learning preferences, and learning difficulties, corresponding learning objective data is generated. Then, the corresponding necessary application programs for the operation of the learning machine and the operation data of the application programs are determined. Finally, in combination with a preset operation model, an operation optimization scheme for the learning machine is determined, so as to improve the operation efficiency of the learning machine and the user experience, dynamically adjust the operation strategy of the learning machine, and ensure the reasonable allocation of learning resources and the efficient operation of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0047] Figure 1 It is a schematic flowchart of the operation optimization method of a learning machine according to an embodiment of the present invention;

[0048] Figure 2 It is a schematic flowchart of the operation optimization method of a learning machine according to another embodiment of the present invention;

[0049] Figure 3 It is a schematic flowchart of the operation optimization method of a learning machine according to still another embodiment of the present invention;

[0050] Figure 4 It is a schematic flowchart of the operation optimization method of a learning machine according to yet another embodiment of the present invention;

[0051] Figure 5 It is a schematic flowchart of the operation optimization method of a learning machine according to still another embodiment of the present invention;

[0052] Figure 6 It is a schematic flowchart of the operation optimization method of a learning machine according to another embodiment of the present invention;

[0053] Figure 7 Schematic flowchart of the operation optimization method of the learning machine according to another embodiment of the present invention;

[0054] Figure 8 Schematic flowchart of the operation optimization method of the learning machine according to still another embodiment of the present invention.

[0055] The realization of the object, functional features and advantages of the present invention will be further described with reference to the embodiments and the accompanying drawings. Specific embodiments

[0056] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Well-known modules, units and their connections, links, communications or operations therebetween are not shown or not described in detail. And the described features, architectures or functions can be combined in any way in one or more embodiments. Those skilled in the art should understand that the following various embodiments are only used for illustration, rather than for limiting the protection scope of the present invention. It can also be easily understood that the modules, units or processing methods in the various embodiments described herein and shown in the drawings can be combined and designed in various different configurations. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the protection scope of the present invention.

[0057] The limitations on various nouns or methods referred to in the following embodiments, except in cases where they cannot be logically established, generally refer to the broad concepts that can be implemented on the premise of the content disclosed in the embodiments. Under such an understanding, various specific lower-level specific limitations of the nouns or methods should be regarded as the content of the present invention, and should not be narrowly understood or prejudicially interpreted on the grounds that the specific limitations are not disclosed in the specification. Similarly, on the premise that it can be logically realized, the order of the steps in the method is flexible and changeable, and the specific lower-level specific limitations in the broad concepts of various nouns or methods all belong to the protection scope of the present invention.

[0058] The main solution of the embodiments of the present application is: by obtaining the user's historical learning records, determining the user's current learning progress, learning preferences and learning difficulties during the learning process, then obtaining the type of learning objective input or selected by the user through the learning machine currently, and combining the current learning progress, learning preferences and learning difficulties, generating corresponding learning objective data, then determining the corresponding necessary application programs for the operation of the learning machine and the operation data of the application programs, and finally combining the preset operation model to determine the operation optimization plan of the learning machine.

[0059] In this embodiment, for the convenience of description, the following will be described with the control device as the execution subject.

[0060] Since in the prior art, problems such as system lag, cache accumulation, and insufficient memory in learning machines are often attempted to be solved through simple cache cleaning or system upgrades, but the effects are limited and it is difficult to fundamentally solve the deep-seated problems in the operation of learning machines.

[0061] This application provides a solution to improve the operation efficiency and user experience of learning machines, dynamically adjust the operation strategy of learning machines, and ensure the reasonable allocation of learning resources and the efficient operation of the system.

[0062] For this reason, the present invention proposes an operation optimization method for a learning machine; it can be understood that a control device for storing and executing the following method is provided in the learning machine, and the control device can be implemented by a main controller, such as an MCU (Microcontroller Unit, micro control unit), DSP (Digital Signal Process, digital signal processing chip), FPGA (Field Programmable Gate Array, programmable logic gate array chip), SOC (System On Chip, system-level chip), etc.

[0063] Refer to Figure 1 , Figure 1 is a schematic flow chart of an operation optimization method for a learning machine according to an embodiment of the present invention. In an embodiment of the present invention, the operation optimization method includes steps S100 - S500, where:

[0064] S100. Obtain the user's historical learning records and the type of learning goal currently input or selected by the user through the learning machine;

[0065] S200. Determine the user's current learning progress, learning preferences, and learning difficulties during the learning process according to the historical learning records;

[0066] S300. Generate corresponding learning goal data according to the current learning progress, learning preferences, learning difficulties, and type of learning goal;

[0067] S400. Determine the corresponding necessary application programs for the operation of the learning machine and the operation data of the application programs according to the learning goal data;

[0068] S500. Determine the operation optimization plan of the learning machine according to the operation data and the preset operation model.

[0069] In this embodiment, the historical learning records may include detailed learning data such as the courses the user has studied, the exercises completed, the teaching videos watched, and the learning activities participated in during different time periods. These detailed learning data not only reflect the user's learning trajectory but also imply the user's learning habits, interest preferences, and possible difficulties and challenges encountered. By deeply analyzing these historical learning records, we can more accurately grasp the user's current learning status and needs. The learning objective types are clarified through the user's input or selection on the learning machine. For example, the user may hope to strengthen the mathematical foundation, improve oral English ability, or prepare for an upcoming exam, etc. These objective types provide a clear direction for the user's learning path, enabling the optimization strategy of the learning machine to be more targeted.

[0070] In this embodiment, the learning preference refers to the preference shown by the user during the learning process for specific knowledge areas, teaching methods, or learning materials. For example, some users may prefer to learn new knowledge by watching videos, while others may be more inclined to consolidate knowledge by reading and solving problems. The learning difficulties refer to the knowledge points or skills that are difficult for the user to understand and master during the learning process. These difficulties may stem from the user's weak basic knowledge, different thinking modes, or deviations in the understanding of specific concepts.

[0071] In this embodiment, by combining the current learning progress, learning preferences, learning difficulties, and learning objective types, a more personalized learning experience can be provided for the learning machine. This process is not limited to generating simple learning objective data but also involves the in-depth customization of learning content, learning paths, and learning methods. According to the learning objective data, the necessary application programs corresponding to this learning session and the priorities and execution strategies of these application programs can be determined. For example, if the user's learning objective is to improve English reading comprehension ability and the historical learning records show that the user has difficulties in vocabulary memory, then the learning machine can preferentially start and optimize the application programs related to vocabulary memory, such as vocabulary flashcards, vocabulary tests, etc., and may adjust the display interface, learning progress feedback method of these application programs, and add interactive elements that match the user's learning preferences, such as gamified learning, audio-assisted memory, etc., to improve learning efficiency and user experience. When determining the necessary application programs and their running data, the current system state of the learning machine, such as the remaining storage space, processor load, battery power, etc., can also be combined to ensure that the selected application programs can run under optimal hardware conditions. For example, if the learning machine has a low battery power currently, the system may preferentially close or limit those application programs that consume a large amount of power, or optimize the power consumption strategies of these application programs, such as reducing the screen brightness, reducing unnecessary data transmission, etc., to extend the usage time of the learning machine.

[0072] In addition, a preset operation model can be combined. The preset operation model is trained based on a large amount of user learning data, operation status data, and application performance data, and can predict and evaluate the impact of different operation strategies on the performance and learning effect of the learning machine in real time. After determining the necessary applications and their operation data, the control device will formulate an optimal operation optimization plan according to the preset operation model, comprehensively considering various factors such as the urgency of the learning goal, the difficulty of the learning content, and the user's attention concentration. These operation optimization plans may include adjusting the startup order of applications, optimizing memory allocation, improving the processor scheduling strategy, enhancing network communication efficiency, etc., to ensure that the learning machine can efficiently and stably support the user's learning activities.

[0073] In actual application, if user A logs in to the account he uses on the learning machine, and the historical learning records of user A are recorded in this account, and then the learning goal type input or selected by user A through the learning machine is obtained. There is an operation panel on the learning machine, or it is wirelessly connected to an intelligent terminal to input or select the learning goal type; at this time, the control device will also automatically determine the current learning progress of user A, as well as the learning preferences and learning difficulties during the learning process. Furthermore, according to the current learning progress, for example, if 100 words need to be recited and 45 have been recited so far, the learning progress is 45%, and the learning preference, for example, user A prefers to deepen understanding by watching teaching videos and conducting online interactive exercises, while the learning difficulties are concentrated on complex grammar structures and reading comprehension. The control device will intelligently analyze this information and generate personalized learning goal data for user A.

[0074] After generating the learning objective data, the learning opportunity determines a series of necessary applications to be launched based on this data, such as an English grammar teaching video application, a reading comprehension training application, and a comprehensive learning platform that integrates vocabulary memorization and online testing. After determining the applications to be launched, in combination with the preset operation model, it judges which application takes up a large amount of space and has low operating efficiency, and may take a series of optimization measures to ensure the efficient operation of these applications. For example, for the English grammar teaching video application that takes up a large amount of space, the learning opportunity checks its cached content and automatically deletes the cached videos that have been watched to free up storage space for other applications. At the same time, if there are multiple versions of this video application, the learning opportunity selects the video clarity most suitable for the user's current environment for playback according to the current network condition and processor capacity, so as to reduce the data transmission volume and the processor burden. For the reading comprehension training application, the learning opportunity preferentially displays those exercises that contain complex grammar structures and in-depth reading comprehension questions according to user A's learning preferences. To enhance the user experience, the learning machine will also dynamically adjust the presentation method of these exercises according to the preset operation model, such as highlighting key sentences, providing an instant translation tool or adding interactive analysis to help users better understand and master the difficulties. For the comprehensive learning platform, as one of the core applications, it will integrate all relevant learning resources and functions, such as vocabulary memorization, online testing, learning progress tracking, etc. The learning opportunity automatically recommends a learning path according to user A's learning progress and learning objectives, such as completing the vocabulary memorization task first, then conducting reading comprehension training, and finally testing the learning results through an online test. At the same time, this platform will also use big data analysis technology to regularly evaluate the learning effect of users, automatically adjust the learning plan and difficulty, and ensure the pertinence and effectiveness of the learning content.

[0075] In addition, the learning machine will also conduct overall optimization of system resources according to the preset operation model. In terms of processor scheduling, the learning opportunity will give priority to ensuring that the currently used learning applications obtain sufficient computing resources, while reducing the occupancy of irrelevant background processes to improve the system response speed and fluency. In terms of memory management, the learning opportunity will reduce unnecessary data occupancy through intelligent compression technology and optimize the memory allocation strategy to ensure that the learning applications can run stably without freezing. In terms of network communication, the learning opportunity will automatically adjust the data transmission strategy according to the current network environment. When the network condition is poor, the learning opportunity will give priority to transmitting necessary learning data, such as learning progress updates, emergency notifications, etc., while reducing the transmission of unnecessary online video streams to avoid the impact of network latency on the learning effect. When the network environment is good, the learning opportunity will accelerate the data transmission speed to ensure that users can smoothly watch teaching videos and conduct online interactions.

[0076] In this embodiment, by obtaining the user's historical learning records, the current learning progress, learning preferences, and learning difficulties during the learning process of the user are determined. Then, the type of learning objective input or selected by the user through the learning machine currently is obtained, and combined with the current learning progress, learning preferences, and learning difficulties, corresponding learning objective data is generated. Next, the corresponding necessary application programs and the running data of the application programs running on the learning machine are determined. Finally, combined with the preset running model, the running optimization scheme of the learning machine is determined, so as to improve the running efficiency of the learning machine and the user experience, dynamically adjust the running strategy of the learning machine, and ensure the reasonable allocation of learning resources and the efficient operation of the system.

[0077] Further, referring to Figure 2 , another embodiment of the present invention provides a method for optimizing the operation of a learning machine. Based on the above Figure 1 shown embodiment, the step of generating corresponding learning objective data according to the current learning progress, learning preferences, learning difficulties, and learning objective type includes S310 - S350, where:

[0078] S310. Analyze the user's mastery degree and interest direction of knowledge points according to the current learning progress and learning preferences;

[0079] S320. Determine the problem data of the user during the learning process according to the learning difficulties, and evaluate the influence degree of these problem data on the current learning progress;

[0080] S330. Construct a corresponding target learning framework according to the mastery degree, the interest direction, the problem data, and the influence degree;

[0081] S340. Generate a plurality of corresponding sub - target tasks according to the learning objective type and the target learning framework;

[0082] S350. Determine the corresponding learning objective data according to the plurality of sub - target tasks.

[0083] In this embodiment, the user's mastery degree of knowledge points is quantified by learning progress data, and the interest direction is inferred through the behavior pattern in the learning preferences. Knowledge points with a high mastery degree may mean that the user is already relatively familiar, while the interest direction can reveal the areas where the user is more willing to invest energy. Such analysis not only helps to identify the user's strengths but also locates the aspects that the user may overlook or be confused about.

[0084] Conduct a deep analysis of learning difficulties, which are often obstacles encountered by users during the learning process and directly affect the learning progress. By analyzing the data of these difficulties, the control device can evaluate their specific impact on the user's current learning progress, such as minor delays or serious obstacles. This detailed evaluation provides an important basis for formulating targeted learning strategies in the follow-up.

[0085] Based on the mastery level, interest direction, problem data and their impact degree, the system begins to construct a target learning framework. This framework is a dynamically adjustable learning blueprint that reasonably plans the future learning path according to the user's personalized needs and learning status. The framework includes the knowledge points that need to be focused on, the learning methods suitable for the user, and the expected learning effects. By determining the content of the above target learning framework, the user's needs can be better determined, and thus the operation of the learning machine can be optimized according to different needs.

[0086] Subsequently, according to the learning target type (such as improving reading speed, mastering new language skills, etc.) and the target learning framework, the control device breaks down the large target into multiple specific sub-goal tasks. These sub-goal tasks are more specific and operable, facilitating the user to achieve them step by step. For example, if the learning target is to improve reading speed, the sub-goal tasks may include reading a certain number of articles every day, conducting speed reading training, learning and applying reading skills, etc. Each sub-goal task sets clear goals and completion criteria so that the user can clearly understand what they need to do and how to measure the learning results. After determining multiple sub-goal tasks, the control device will synthesize this information to generate corresponding learning target data. These data not only include specific learning tasks but also associate the required learning resources, recommended learning paths, and expected learning effect evaluation criteria. In a data-driven way, the learning target becomes clearer and more traceable, providing strong support for optimizing the operation of the learning machine.

[0087] In addition, this embodiment also introduces a dynamic adjustment mechanism. During the learning process, the control device will monitor the user's learning progress, mastery level, learning experience and other feedback information in real time, and dynamically adjust the learning target data according to this information. For example, if it is found that the user encounters great difficulties in a certain sub-goal task, the control device may increase relevant learning resources or adjust the learning path to help the user better overcome the difficulties. This dynamic adjustment ensures the pertinence and effectiveness of the learning target, improves the learning efficiency and user experience, and at the same time can better optimize the operation efficiency of the learning machine.

[0088] Furthermore, referring to Figure 3 , another embodiment of the present invention provides an operation optimization method for a learning machine, based on the above Figure 2In the illustrated embodiment, the step of determining the problem data of the user during the learning process according to the learning difficulties and evaluating the degree of influence of these problem data on the current learning progress includes S321 - S324, where:

[0089] S321. Analyze multiple corresponding difficulty types currently existing for the user according to the learning difficulties and preset difficulty types;

[0090] S322. Determine the logical relationship between each learning difficulty according to the multiple difficulty types to determine the problem data of the user during the learning process;

[0091] S323. Construct a problem dependency network for each learning difficulty according to the logical relationship to determine the learning order of each learning difficulty in the problem dependency network;

[0092] S324. Evaluate the degree of influence of the problem data on the current learning progress according to the learning order.

[0093] In this embodiment, the preset difficulty types can be based on extensive educational and psychological research, and common learning disabilities and challenges are summarized into different categories, such as difficulties in concept understanding, insufficient memory ability, lack of problem-solving skills, etc. By comparing these preset difficulty types with the learning difficulties actually encountered by the user, the control device can quickly identify the difficulty types currently faced by the user, determine the specific learning plan for the user, and optimize the operation of the learning machine according to the learning plan.

[0094] In this embodiment, by deeply analyzing the logical relationship between these difficulty types. This logical relationship may be manifested as sequential dependence, parallel relationship, or mutual influence, etc. For example, in some disciplines, understanding basic theories is a prerequisite for mastering advanced concepts, so there is an obvious hierarchical dependence relationship between these difficulties. By determining this logical relationship between each learning difficulty, the system can more accurately depict the panoramic view of the problem data of the user during the learning process, revealing which difficulties are isolated, which difficulties are closely connected, and the way they interact with each other.

[0095] After mastering the difficulty types and their logical relationships, it is possible to better construct a problem dependency network. This problem dependency network takes learning difficulties as nodes and their logical relationships as edges, forming a graph that intuitively shows the user's learning obstacles. Through the problem dependency network, not only can the position and role of each difficulty be clearly seen, but also the best path and order to solve these difficulties can be inferred. This analysis method based on the network structure helps the system to more scientifically formulate a learning plan and ensure the orderliness and efficiency of learning activities.

[0096] Finally, the system evaluates the impact of these problem data on the current learning progress according to the learning order of each learning difficulty in the problem dependency network. This evaluation not only considers the difficulty and importance of the difficulty itself, but also combines the user's current learning status and progress, as well as the logical relationship between difficulties. Once it is found that the user has made significant progress or encountered new obstacles in a certain difficulty, the control device will make timely adjustments to ensure that the learning plan always keeps pace with the user's actual needs. This dynamic feedback and adjustment mechanism makes the operation optimization of the learning machine more flexible and efficient.

[0097] Further, referring to Figure 4 , another embodiment of the present invention provides an operation optimization method for a learning machine. Based on the above Figure 3 shown embodiment, the step of constructing a corresponding target learning framework according to the mastery level, the interest direction, the problem data, and the influence degree includes S331 - S333, where:

[0098] S331. Set the corresponding learning content priority according to the mastery level and the interest direction;

[0099] S332. Determine the key area and the secondary area of the learning content according to the learning content priority, the problem data, and the influence degree;

[0100] S333. Construct a corresponding target learning framework according to the key area and the secondary area.

[0101] In this embodiment, the learning content priority can be set according to the user's mastery level and interest direction to ensure that the learning content not only conforms to the user's current ability level but also can stimulate their learning enthusiasm. Areas with a high mastery level can be set as review or in - depth understanding links, while areas with a low mastery level require more time and resources for basic knowledge consolidation and improvement. At the same time, the user's interest direction is also an important reference factor for setting the learning content priority. Placing the content that the user is interested in in the priority position can increase the motivation and persistence of learning. After determining the learning content priority, the next step is to determine the key area and the secondary area of the learning content according to this priority, the problem data, and the influence degree of the problem data on the learning progress. The key area usually refers to the difficulties and key knowledge points encountered by the user during the learning process. These areas need special attention because they directly relate to whether the user can successfully achieve the learning goal. The secondary area may be relatively easy to understand or have a low correlation with the user's current learning goal, and less attention can be given in terms of resource allocation.

[0102] After identifying the key areas and secondary areas, the corresponding target learning framework can be constructed. The target learning framework is a systematic learning blueprint that divides the learning content into different modules or stages based on the importance, difficulty of the learning content, and the user's learning habits, and sets corresponding learning goals and time plans. By constructing such a framework, the learning machine can provide a more personalized and efficient learning experience for users, helping users to advance the learning process in an orderly manner and gradually achieve the learning goals.

[0103] In addition, this embodiment also emphasizes the flexibility and dynamics in the process of constructing the target learning framework. As the user's learning progress advances and feedback information accumulates, the learning machine can continuously adjust and optimize the learning framework to adapt to the user's learning needs and changes. For example, when the user makes a breakthrough in a certain difficult point, the system can automatically adjust the relevant content from the key area to the secondary area; when the user encounters new learning obstacles, the system can quickly identify and increase the corresponding learning resources and learning support.

[0104] By comprehensively considering the user's mastery level, interest direction, problem data, and the impact degree of these factors on the learning progress, and optimizing the operation process of the learning machine accordingly, it can ensure that the learning experience is both personalized and efficient. This optimization is not limited to the arrangement of learning content, but also involves multiple dimensions such as the diversification of learning methods, the control of learning rhythm, and the instant feedback of learning effects.

[0105] Furthermore, referring to Figure 5 , another embodiment of the present invention provides an operation optimization method for a learning machine. Based on any of the embodiments shown above Figures 1 to 4 , the step of determining the operation optimization plan of the learning machine according to the operation data and the preset operation model includes S510 - S540, where:

[0106] S510. Analyze the performance of each application program currently running on the learning machine according to the operation data of the application program;

[0107] S520. Evaluate the contribution degree of each application program to the overall operation efficiency of the learning machine and the potential resource occupation conflicts according to the performance and the preset operation model;

[0108] S530. Determine the priority of each application program based on the sorting algorithm and the contribution degree;

[0109] S540. Generate the operation optimization plan according to the priority and the resource occupation conflicts.

[0110] In this embodiment, the operation data may include key metrics such as the startup time, response time, CPU occupancy rate, memory occupancy rate, and network bandwidth usage of various applications in the learning machine. These key metric data reflect the operation status and performance of the learning machine under different tasks. By analyzing this data, the system can deeply understand the current operation status of the learning machine and provide strong support for subsequent optimization.

[0111] The control device will first preprocess the collected operation data, including data cleaning, denoising, and normalization, to ensure the accuracy and reliability of the analysis results. Subsequently, methods such as statistical analysis, machine learning, or data mining are used to deeply analyze the performance of each application in the learning machine. These analyses not only focus on the operation efficiency of a single application but also examine the interactions and influences among them.

[0112] After understanding the performance of each application, the control device will evaluate their contribution to the overall operation efficiency of the learning machine according to the preset operation model. This evaluation process comprehensively considers multiple factors such as the importance, usage frequency, resource consumption of the application, and its compatibility with other applications. At the same time, the control device will also identify potential resource occupancy conflicts, which may cause problems such as lag and crashes during the operation of the learning machine, seriously affecting the user experience.

[0113] To effectively solve these problems, the control device uses a sorting algorithm to sort the applications by priority. This sorting process considers both the contribution of the applications and their resource occupancy. By preferentially ensuring the operation of applications with high contribution and reasonable resource occupancy, the control device can ensure that the learning machine can maintain an efficient and stable operation state in most cases.

[0114] Finally, based on the sorting results and the analysis of resource occupancy conflicts, the system generates a specific operation optimization plan. This operation optimization plan may include measures such as adjusting the startup order of applications, optimizing the resource allocation strategy, and restricting the resource usage permissions of some applications. By implementing these optimization plans, the learning machine can significantly improve its overall operation efficiency and provide a smoother and more comfortable learning experience for users.

[0115] Furthermore, referring to Figure 6 , another embodiment of the present invention provides an operation optimization method for a learning machine. Based on the above Figure 5 shown embodiment, the step of evaluating the contribution of each application to the overall operation efficiency of the learning machine and potential resource occupancy conflicts according to the performance and the preset operation model includes S521 - S524, where:

[0116] S521. According to the performance, count the running efficiency indicators of each application under preset conditions;

[0117] S522. Calculate the weighted running efficiency of each application according to the running efficiency indicator and the corresponding running weight factor;

[0118] S523. Evaluate the contribution degree of each application to the overall running efficiency of the learning machine according to the weighted running efficiency and the preset running model;

[0119] S524. Determine potential resource occupancy conflicts according to the weighted running efficiency, the preset running model and the contribution degree.

[0120] In this embodiment, the running efficiency indicators may include the startup speed of the application, the completion time of the executed task, the memory occupancy rate, the CPU usage rate, and the network transmission efficiency, etc. These indicators directly reflect the performance of the application during operation and are an important part of the overall running efficiency of the learning machine.

[0121] First, the control device will count the running efficiency indicators of each application under preset conditions. These preset conditions may include different learning tasks, learning scenarios, or user-defined usage habits, etc. By simulating these conditions, the performance data of each application in the actual usage scenario can be obtained, providing a basis for subsequent analysis and optimization.

[0122] Next, calculate the weighted running efficiency of each application according to the running efficiency indicator and the corresponding running weight factor. The running weight factor is comprehensively set according to factors such as the importance of the application, the usage frequency, and the impact on the overall performance of the learning machine. By introducing the weight factor, the control device can more accurately evaluate the actual contribution degree of each application in terms of running efficiency and avoid the one-sidedness brought by a single indicator.

[0123] Then, evaluate the contribution degree of each application to the overall running efficiency of the learning machine according to the weighted running efficiency and the preset running model. This step combines the performance of each application with the overall running goal of the learning machine, and comprehensively considers their roles and values in the running process of the learning machine. Through this evaluation process, the control device can identify the key applications that have a greater impact on the overall running efficiency, providing a key direction for subsequent optimization.

[0124] Finally, based on the weighted running efficiency, the preset running model, and the contribution degree, potential resource occupancy conflicts are determined. During the operation of the learning machine, different applications may conflict due to resource requirements, resulting in a decrease in the overall running efficiency. By comprehensively considering the weighted running efficiency, contribution degree of each application, and their resource usage situations, the control device can predict and identify potential resource occupancy conflicts. These conflicts may include CPU resource contention, memory leakage, network bandwidth bottlenecks, etc., posing a threat to the stable operation of the learning machine.

[0125] For these potential resource occupancy conflicts, the control device can take a series of optimization measures, such as adjusting the priorities of applications, optimizing resource allocation strategies, increasing resource monitoring and warning mechanisms, etc. Through these measures, the system can effectively alleviate or eliminate resource occupancy conflicts, improve the overall running efficiency of the learning machine, and provide users with a more stable and efficient learning experience.

[0126] Furthermore, referring to Figure 7 , another embodiment of the present invention provides an operation optimization method for a learning machine. Based on the above Figure 6 shown embodiment, the step of determining the priorities of each application based on the sorting algorithm and the contribution degree includes S531 - S532, where:

[0127] S531. Based on the multi - objective sorting algorithm, taking the contribution degree and the potential resource occupancy conflicts as optimization objectives, comprehensively evaluate the applications;

[0128] S532. According to the comprehensive evaluation results, sort the applications to determine the priorities of each application in the operation optimization plan.

[0129] In this embodiment, the multi - objective sorting algorithm may include genetic algorithms, particle swarm optimization algorithms, or simulated annealing algorithms, etc. These algorithms demonstrate powerful capabilities in solving multi - objective optimization problems. They can find a solution that balances multiple optimization objectives (such as contribution degree and potential resource occupancy conflicts) while considering them.

[0130] First, using a multi-objective sorting algorithm, the contribution degree and potential resource occupation conflicts are taken as two main optimization objectives to comprehensively evaluate the application programs. In this process, the multi-objective sorting algorithm will consider the performance of each application program on these two objectives and try to find a balance point that can both maximize the contribution degree of the application program to the overall operation efficiency of the learning machine and minimize potential resource occupation conflicts. This comprehensive evaluation not only depends on the individual indicators of the application programs but also synthesizes their interactions and overall impacts. Then, according to the comprehensive evaluation results, the application programs are sorted. The sorting process is a dynamically adjusted process, and the multi-objective sorting algorithm will determine their priorities based on the comprehensive scores of each application program (i.e., their performance on the optimization objectives). The application programs with higher priorities will enjoy higher priorities in the system resource allocation, thus ensuring that they can obtain sufficient resource support during operation to maintain an efficient and stable operation state.

[0131] In addition, it is worth noting that this embodiment also provides flexible configuration and customization options, allowing users to personalize the operation optimization scheme of the learning machine according to their usage habits and needs. For example, users can adjust the startup order of application programs, resource allocation strategies, etc. according to their learning tasks and learning scenarios to meet specific performance requirements. This function of personalized configuration makes the embodiments of the present invention more flexible and practical, and can meet the diverse needs of different users.

[0132] Further, referring to Figure 8 , another embodiment of the present invention provides an operation optimization method for a learning machine. Based on the above Figure 7 shown embodiment, the operation optimization method further includes S600 - S900, where:

[0133] S600: Obtain the historical operation data of multiple users using the learning machine in different learning scenarios, and preprocess the historical operation data;

[0134] S700: According to the preprocessed historical operation data, analyze the interaction relationships, resource occupation situations, and the impacts of each application program on the overall performance of the learning machine during operation to generate corresponding analysis results;

[0135] S800: According to the analysis results, construct a target mathematical model for the operation of the learning machine, and train the target mathematical model based on a machine learning algorithm;

[0136] S900: Determine the trained target mathematical model as the preset operation model.

[0137] In this embodiment, the historical operation data of the learning machine used in different learning scenarios may include key performance indicators such as CPU usage rate, memory occupancy, disk read / write frequency, and network bandwidth consumption in various learning tasks (such as reading, programming, video playback, etc.). These key performance indicator data are collected through the built-in monitoring system of the learning machine or external data collection tools and stored in a database for subsequent analysis. First, the collected historical operation data is preprocessed to eliminate noise, fill in missing values, standardize the data format, etc., to ensure the consistency and accuracy of the data. The preprocessing step is crucial for subsequent analysis and directly affects the reliability and effectiveness of the analysis results.

[0138] Then, using the preprocessed historical operation data, in-depth data mining and correlation analysis are carried out. By analyzing the interaction relationships between various application programs during the operation of the learning machine, their dependence, competition, or cooperation patterns can be revealed. At the same time, combined with the resource occupancy situation (such as CPU time slice allocation, memory allocation, I / O operations, etc.), the specific impact of each application program on the overall performance of the learning machine can be evaluated. These analysis results help us understand the operation status and performance bottlenecks of the learning machine more deeply.

[0139] Based on the above analysis results, a target mathematical model for the operation of the learning machine can be constructed. The target mathematical model aims to describe the performance of the learning machine in a specific learning scenario and predict the overall operation efficiency of the learning machine under different application program configurations. The target mathematical model may contain multiple variables and parameters to represent the impacts of factors such as the hardware configuration, software environment, and user behavior of the learning machine on its performance. To train the target mathematical model, machine learning algorithms can be used. Machine learning algorithms can automatically learn and extract features from historical operation data and continuously adjust the model parameters through an iterative optimization process to improve the prediction accuracy of the model for unknown data. During the training process, techniques such as cross-validation can also be used to evaluate the performance of the model and select the optimal combination of model parameters.

[0140] Finally, the trained target mathematical model is determined as the preset operation model. This model will serve as the basis and basis for subsequent operation optimization schemes, used to evaluate the priorities of various application programs, predict potential resource occupancy conflicts, optimize resource allocation strategies, etc. By continuously iterating and optimizing the preset operation model, the overall operation efficiency of the learning machine can be improved well, providing a better learning experience for users.

[0141] The present invention also proposes a control device, which includes: a memory, a processor, and a running optimization program of the learning machine stored on the memory and executable on the processor. The running optimization program of the learning machine is configured to implement the running optimization method of the learning machine as described above.

[0142] It should be noted that since the control device of the present invention is based on the above-mentioned operation optimization method of the learning machine, the embodiments of the control device of the present invention include all the technical solutions of all the embodiments of the above-mentioned operation optimization method of the learning machine, and the achieved technical effects are also exactly the same, and will not be elaborated here.

[0143] The present invention also provides a learning machine, which includes the control device as described in the above embodiments.

[0144] It should be noted that since the learning machine of the present invention is based on the above-mentioned control device, the embodiments of the learning machine of the present invention include all the technical solutions of all the embodiments of the above-mentioned control device, and the achieved technical effects are also exactly the same, and will not be elaborated here.

[0145] It should be noted that in this article, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or system. Without further limitation, an element defined by the statement "including a..." does not exclude the existence of additional identical elements in the process, method, article or system including that element.

[0146] The serial numbers of the above embodiments of the present invention are only for description and do not represent the superiority or inferiority of the embodiments.

[0147] Through the description of the above embodiments, those skilled in the art can clearly understand that the above embodiment methods can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium as described above (such as ROM / RAM, magnetic disk, optical disk), and includes several instructions for causing a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in various embodiments of the present invention.

[0148] The above are only the preferred embodiments of the present invention, and do not limit the patent scope of the present invention accordingly. Any equivalent structure or equivalent process transformation made by using the specification and drawings of the present invention, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present invention.

Claims

1. A method for optimizing the operation of a learning machine, characterized in that: The operation optimization method comprises: Obtain the user's historical learning records and the type of learning goal currently input or selected by the user through the learning machine; Determine the user's current learning progress and learning preferences and learning difficulties during the learning process based on the historical learning records; Generate corresponding learning goal data according to the current learning progress, learning preferences, learning difficulties and learning goal type; Determine, according to the learning target data, the corresponding necessary application programs and the operation data of the application programs to be run by the learning machine; Determine an operation optimization plan for the learning machine according to the operation data and the preset operation model; The step of generating corresponding learning target data according to the current learning progress, learning preferences, learning difficulties and learning target type includes: Analyze the user's mastery of knowledge points and interests based on the current learning progress and learning preferences; According to the learning difficulties, determine the problem data of the user in the learning process, and evaluate the degree of influence of these problem data on the current learning progress; Constructing a corresponding target learning framework according to the mastery level, the interest direction, the problem data, and the impact level; Generate a plurality of corresponding sub-goal tasks according to the learning goal type and the goal learning framework; Determine corresponding learning target data according to the plurality of sub-target tasks; The step of determining the problem data of the user in the learning process according to the learning difficulty and evaluating the influence of these problem data on the current learning progress includes: Analyze multiple corresponding difficulty types currently existing in the user according to the learning difficulties and the preset difficulty types; According to the plurality of difficulty types, determining the logical relationship between the learning difficulties, so as to determine the problem data of the user in the learning process; According to the logical relationship, construct a problem dependency network for each learning difficulty to determine the learning order of each learning difficulty in the problem dependency network; According to the learning sequence, evaluating the impact of the problem data on the current learning progress; The operation data includes key indicators of the startup time, response time, CPU occupancy, memory occupancy, and network bandwidth usage of various applications in the learning machine, which are used to analyze the performance of various applications currently running on the learning machine; The performance refers to the evaluation of the contribution of each application to the overall operating efficiency of the learning machine and the potential resource occupation conflict through the operating efficiency index. The operating efficiency index includes the startup speed of the application, the completion time of the execution task, the memory usage rate, the CPU usage rate and the network transmission efficiency. The operating efficiency index is used to directly reflect the performance of the application during operation; The step of determining the operation optimization scheme of the learning machine according to the operation data and the preset operation model includes: Analyze the performance of various applications currently running on the learning machine based on the running data of the application; According to the performance and the preset operation model, evaluate the contribution of each application to the overall operation efficiency of the learning machine and the potential resource occupation conflict; Determine the priority of each application based on the ranking algorithm and the contribution; The operation optimization plan is generated according to the priority and the resource occupation conflict.

2. The operation optimization method of a learning machine as claimed in claim 1, characterized in that: The step of constructing a corresponding target learning framework according to the mastery level, the interest direction, the problem data and the impact level includes: According to the mastery level and the interest direction, set the corresponding learning content priority; Determine the key areas and secondary areas of the learning content according to the learning content priority, the problem data, and the impact degree; A corresponding target learning framework is constructed according to the key area and the secondary area.

3. The operation optimization method of a learning machine as claimed in claim 1, characterized in that: The step of evaluating the contribution of each application to the overall operating efficiency of the learning machine and the potential resource occupation conflict according to the performance and the preset operating model includes: Based on the performance, the operating efficiency index of each application under the preset conditions is counted; Calculating the weighted operating efficiency of each application program according to the operating efficiency index and the corresponding operating weight factor; According to the weighted operating efficiency and the preset operating model, evaluating the contribution of each application to the overall operating efficiency of the learning machine; Potential resource occupation conflicts are determined according to the weighted operation efficiency, the preset operation model, and the contribution degree.

4. The operation optimization method of a learning machine as claimed in claim 3, characterized in that: The step of determining the priority of each application based on the ranking algorithm and the contribution includes: Based on a multi-objective sorting algorithm, the contribution and the potential resource occupation conflict are used as optimization targets to comprehensively evaluate the application; According to the comprehensive evaluation results, the applications are sorted and the priority of each application in the operation optimization plan is determined.

5. The operation optimization method of a learning machine as claimed in claim 4, characterized in that: The operation optimization method also includes: Acquire historical operation data of multiple users using the learning machine in different learning scenarios, and preprocess the historical operation data; Analyze the interaction relationship between the various application programs, resource usage, and the impact of each application program on the overall performance of the learning machine during operation of the learning machine according to the preprocessed historical operation data, so as to generate corresponding analysis results; According to the analysis results, a target mathematical model for the learning machine to run is constructed, and the target mathematical model is trained based on a machine learning algorithm; The trained target mathematical model is determined to be a preset operating model.

6. A control device, characterized in that: The control device includes: a memory, a processor, and an operation optimization program of the learning machine stored in the memory and executable on the processor, wherein the operation optimization program of the learning machine is configured to implement the operation optimization method of the learning machine as described in any one of claims 1 to 5.

7. A learning machine, characterized in that: Comprising a control device as claimed in claim 6.

Images