Control method and control device of learning machine and learning machine

By obtaining the user's learning target data and comparing the preset learning plan model, a personalized learning plan is generated and the learning machine is controlled to perform display actions, the problem of single functions of the traditional learning machine is solved, and the personalization and efficiency of the learning process is achieved.

CN118967390AInactive Publication Date: 2024-11-15深圳倍爱思科技有限公司
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
CN202411140185.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-20
Publication Date
2024-11-15
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

Traditional learning machines have single functions and lack intelligent control methods, and cannot adaptively adjust according to users' learning habits and progress, resulting in low learning efficiency.

Method used

By obtaining the user's learning target data and comparing it with the preset learning plan model, a personalized learning plan is generated, and control instructions are generated based on the plan, the learning machine is controlled to perform display actions, and the learning progress is obtained in real time to generate a learning plan report.

Benefits of technology

It improves the intelligence level of the learning machine, accurately matches users' learning needs, and realizes personalization and efficiency of the learning process.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118967390A_ABST
    Figure CN118967390A_ABST
Patent Text Reader

Abstract

The invention provides a learning machine control method and device and a learning machine, and belongs to the technical field of education, and the learning machine control method comprises the steps: obtaining learning target data of a user; according to the learning target data and a preset learning plan model, generating a corresponding personalized learning plan; generating a control instruction corresponding to the learning machine according to the personalized learning plan; and according to the control instruction, controlling the learning machine to execute a display action according to the personalized learning plan, and obtaining the learning progress of the user in real time to generate a learning plan report of the user. The learning target data of the user is acquired and compared with the preset learning plan model to generate the corresponding personalized learning plan, then the control instruction corresponding to the learning machine is generated, the learning machine is controlled to execute the display action according to the personalized learning plan, and the learning progress of the user is acquired in real time to generate the learning plan report of the user. The intelligent level of the learning machine is improved, and individuation and high efficiency of the learning process are realized.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of educational technology, and in particular to a control method and a control device for a learning machine, and a learning machine. Background Art

[0002] Learning machines, as an important part of modern educational technology, have been widely used by learners of all ages. Traditional learning machines often only provide fixed learning content and mechanized learning methods, with single functions and lack of intelligent control methods. They cannot make adaptive adjustments based on users' learning habits and progress, resulting in low learning efficiency. Summary of the invention

[0003] The main purpose of the present invention is to provide a control method for a learning machine, aiming to improve the intelligence level of the learning machine and realize the personalization and efficiency of the learning process by accurately matching the user's learning needs and resources.

[0004] To achieve the above object, the present invention provides a control method for a learning machine, the method comprising: Obtain the user's learning goal data; Generate a corresponding personalized learning plan based on the learning goal data and the preset learning plan model; Generate control instructions corresponding to the learning machine according to the personalized learning plan; According to the control instruction, the learning machine is controlled to perform display actions according to the personalized learning plan, and the user's learning progress is obtained in real time to generate a learning plan report for the user.

[0005] Optionally, the step of generating a corresponding personalized learning plan according to the learning target data and a preset learning plan model includes: Determining the user's learning needs, learning time, and learning difficulty preferences based on the learning goal data; Input the learning needs, the learning time and the learning difficulty preference into the preset learning plan model, match and calculate through the model algorithm, and generate corresponding output results; Determine the corresponding learning content, learning sequence and learning time allocation according to the output results; The corresponding personalized learning plan is generated according to the learning content, the learning sequence and the learning time allocation.

[0006] Optionally, the step of inputting the learning needs, the learning time and the learning difficulty preference into the preset learning plan model, matching and calculating through a model algorithm, and generating a corresponding output result includes: Inputting the learning needs, the learning time and the learning difficulty preference into the preset learning plan model, and calculating the matching degree between each learning need and the preset learning resource; According to the matching degree, the weight of the learning time and the weight of the learning difficulty preference, a multi-objective optimization process is performed to screen out the optimal learning path and resource combination; Prioritize the selected optimal learning paths and resource combinations, and select the target learning resources that are most relevant to the user's current learning stage; The output result is generated according to the target learning resource.

[0007] Optionally, the step of performing multi-objective optimization processing according to the matching degree, the weight of the learning time, and the weight of the learning difficulty preference to screen out the optimal learning path and resource combination includes: Establishing a corresponding objective function according to the matching degree, the weight of the learning time, and the weight of the learning difficulty preference; According to the objective function, corresponding constraint conditions are determined, and the objective function is solved to determine a global optimal solution; Constructing a multi-objective optimization model according to the objective function and the global optimal solution; The weight of the learning time and the weight of the learning difficulty preference are input into the multi-objective optimization model to screen out the optimal learning path and resource combination.

[0008] Optionally, the preset learning plan model is generated by the following steps: Acquire the user's historical learning data and historical learning achievements, and pre-process the historical learning data and the historical learning achievements; Based on the machine learning algorithm, the preprocessed historical learning data, and the preprocessed historical learning results, identify key factors that affect the learning effect; Based on the key factors, a target learning plan model is constructed; Using the historical learning data and the historical learning results as a training set to train the target learning plan model; Generate evaluation indicators based on the trained target learning plan model to verify the model performance; The verified target learning plan model is determined as the preset learning plan model.

[0009] Optionally, the step of controlling the learning machine to perform a display action according to the personalized learning plan according to the control instruction includes: Obtaining display interface data and display preference data of the user's learning machine; Determining the user's current learning progress according to the control instruction, and generating learning resources corresponding to the learning progress; Generate a page layout corresponding to the display interface of the learning machine according to the display interface data, the display preference data and the learning resources; According to the page layout, the display interface of the learning machine is controlled to perform the display action.

[0010] Optionally, the step of generating a page layout corresponding to the display interface of the learning machine according to the display interface data, the display preference data and the learning resource includes: Acquire the width of the window of the display interface, the height of the window, and the resolution range, determine the optimal resolution information of the display interface, and generate screen display information corresponding to the optimal resolution information; Determining display elements of the display interface according to the learning resource; Analyze the user's visual habits and interface operation habits according to the screen display information and display preference data to determine the optimal size and optimal position of the display element; According to the optimal size and the optimal position, the page layout corresponding to the display interface is adjusted.

[0011] Optionally, the step of generating a control instruction corresponding to the learning machine according to the personalized learning plan includes: Determine the learning tasks corresponding to the current stage according to the personalized learning plan; According to the learning task, identify the required learning resource type and retrieve matching learning resources from a preset learning resource library; Sort and organize the retrieved learning resources according to the learning sequence and learning time allocation, and generate a detailed learning resource list; Generate corresponding control instructions based on the learning resource list.

[0012] In addition, to achieve the above-mentioned purpose, the present invention also provides a control device, which includes: a memory, a processor, and a control program of a learning machine stored in the memory and executable on the processor, wherein the control program of the learning machine is configured to implement the control method of the learning machine as described above.

[0013] In addition, to achieve the above-mentioned purpose, the present invention also provides a learning machine, comprising the control device as described above.

[0014] The embodiment of the present invention obtains the user's learning goal data and compares it with a preset learning plan model to generate a corresponding personalized learning plan, and then generates corresponding control instructions for the learning machine, thereby controlling the learning machine to perform display actions according to the personalized learning plan, and obtains the user's learning progress in real time to generate a learning plan report for the user, so as to improve the intelligence level of the learning machine, and realize personalization and efficiency of the learning process by accurately matching the user's learning needs and resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0016] Figure 1 is a flow chart of a control method for a learning machine according to an embodiment of the present invention; Figure 2 A flow chart of a control method for a learning machine according to another embodiment of the present invention; Figure 3 A flow chart of a control method for a learning machine according to another embodiment of the present invention; Figure 4 A flow chart of a control method for a learning machine according to another embodiment of the present invention; Figure 5 A flow chart of a control method for a learning machine according to another embodiment of the present invention; Figure 6 A flow chart of a control method for a learning machine according to another embodiment of the present invention; Figure 7 A flow chart of a control method for a learning machine according to another embodiment of the present invention; Figure 8 The present invention is a flow chart of a control method for a learning machine according to another embodiment of the present invention.

[0017] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments, and the well-known modules, units and their connections, links, communications or operations are not shown or described in detail. In addition, the described features, architectures or functions can be combined in any way in one or more embodiments. It should be understood by those skilled in the art that the various embodiments described below are only for illustration and not for limiting the scope of protection of the present invention. It can also be easily understood that the modules or units or processing methods in the various embodiments described herein and shown in the drawings can be combined and designed according to various different configurations. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0019] The limitations of various nouns or methods referred to in the following embodiments, except for those that are logically untenable, are generally based on the broad concepts that can be implemented under the premise of the disclosure in the embodiments. Under such understanding, the various specific subordinate specific limitations of the nouns or methods should be regarded as the inventive content of the present invention, and should not be understood narrowly or interpreted in a biased manner on the grounds that the specification does not disclose the specific limitations. Similarly, under the premise that it can be implemented logically, the order of the steps in the method is flexible and changeable, and the specific subordinate specific limitations in the broad concepts of various nouns or methods all fall within the scope of protection of the present invention.

[0020] The main solution of the embodiment of the present application is: by obtaining the user's learning goal data and comparing it with the preset learning plan model to generate a corresponding personalized learning plan, and then generating corresponding control instructions for the learning machine, so as to control the learning machine to perform display actions according to the personalized learning plan, and obtain the user's learning progress in real time to generate a learning plan report for the user.

[0021] In this embodiment, for the convenience of description, the following description is made with the control device as the execution subject.

[0022] Because existing learning machines often only provide fixed learning content and mechanized learning methods, have single functions, lack intelligent control methods, and are unable to make adaptive adjustments based on users' learning habits and progress, resulting in low learning efficiency.

[0023] This application provides a solution to improve the intelligence level of the learning machine and realize the personalization and efficiency of the learning process by accurately matching the user's learning needs and resources.

[0024] To this end, the present invention proposes a control 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 MCU (Microcontroller Unit), DSP (Digital Signal Process), FPGA (Field Programmable Gate Array), SOC (System On Chip), etc.

[0025] Reference Figure 1 In one embodiment of the present invention, the control method of the learning machine includes steps S100-S400, wherein: S100, obtaining the user's learning goal data; S200, generating a corresponding personalized learning plan according to the learning goal data and the preset learning plan model; S300, generating control instructions corresponding to the learning machine according to the personalized learning plan; S400. According to the control instruction, the learning machine is controlled to execute display actions according to the personalized learning plan, and the user's learning progress is obtained in real time to generate a learning plan report for the user.

[0026] In this embodiment, the learning goal data may be the learning outcomes that the user expects to achieve, the expected learning time, the preferred learning method (such as video learning, reading materials, exercises, etc.), and possible learning difficulties or knowledge points that have been mastered. This information can be obtained through the user's input on the learning machine, the interactive dialogue with the user, or extracted from the user's historical learning data. The preset learning plan model can be an algorithm model trained based on a large amount of user learning behavior data. It can dynamically adjust and optimize the learning plan based on the user's learning goal data, taking into account the difficulty of the learning content, the relevance of the knowledge points, the allocation of learning time, and the user's personal learning habits. The personalized learning plan may include learning content, learning sequence, learning time, and recommended learning methods for different knowledge points. For example, if the user's learning goal is to improve English speaking ability and prefers to learn by watching videos, then the personalized learning plan may recommend a series of English speaking teaching videos suitable for their level, and arrange daily learning time and review plans.

[0027] In this embodiment, the control instructions are used to instruct the learning machine to perform specific display and operation actions to implement the personalized learning plan. The control instructions may include but are not limited to video playback instructions, document display instructions, exercise question generation instructions, progress tracking instructions, etc.

[0028] In this embodiment, after generating a personalized learning plan, the control device will analyze the specific content and requirements in the plan and generate corresponding control instructions accordingly. For the video learning part, the control instruction will specify that the learning machine plays a specific teaching video, and may include parameters such as the playback speed, whether to play in a loop, and whether to turn on subtitles. For the document reading part, the control instruction will specify that the learning machine display related electronic books, handouts or notes, and may include adjustments to reading settings such as font size and background color.

[0029] Then, the control device sends these control instructions to the interactive module of the learning machine, so that the learning machine can perform corresponding display actions according to the arrangement of the personalized learning plan. For example, play the teaching video at a specified time, automatically jump to the next section after the video ends, or display the answer and analysis after the user completes a certain exercise.

[0030] In order to obtain the user's learning progress in real time, the control device communicates with the interactive module of the learning machine to monitor the user's operation behavior and learning status. This includes the length of time the user watches the video, the number of exercises completed, the accuracy rate, and the user's interaction during the learning process (such as asking questions, marking key points, etc.). By collecting this data, the control device can dynamically evaluate the user's learning effect and adjust the learning plan as needed.

[0031] After obtaining enough learning progress data, the control device will further analyze the data and generate a learning plan report for the user. The report can show the user's performance at each learning stage in detail, including learning progress, learning results, existing problems, and improvement suggestions. The user can view this report through the display interface of the learning machine to understand his or her learning situation and adjust his or her learning strategy according to the suggestions in the report, so as to provide users with comprehensive learning feedback and suggestions, which not only improves the efficiency of the learning machine and the user experience, but also provides users with a more scientific and efficient way of learning.

[0032] In actual application, for example, the user enters his own learning goals on the interactive module of the learning machine, such as preparing to pass the English Level 4 exam within three months, and clearly expresses his preference for improvement through mock exams and real questions practice. According to this learning goal data, the control device will use the preset learning plan model, which has been optimized based on the data of tens of thousands of learners with similar goals, and can accurately match the user's learning needs. Personalized learning plans are carefully formulated. The personalized learning plan not only includes the daily English learning schedule, such as listening training in the morning, reading comprehension exercises in the afternoon, and focusing on writing and translation in the evening, but also plans in detail the difficulty gradient of the learning content, from basic vocabulary to advanced grammar, and then to mock exams of real questions in previous years, to ensure that the learning process is both targeted and systematic. In addition, the plan also incorporates the user's learning preferences, such as specially arranging multiple sets of real simulation questions, so that users can test their learning results in an environment close to the real exam. The control device generates a series of control instructions that are refined to the minute based on this personalized learning plan. These control instructions cover all functional modules of the learning machine, from automatically downloading and pushing the latest English learning materials, to setting alarms to remind users to start learning, to intelligently adjusting the difficulty of practice questions according to the user's answering situation, to ensure that each step closely fits the user's actual learning needs. For example, when a user answers several difficult questions in a mock exam, the control device will instantly generate new and more challenging questions for the user to practice; and if the user frequently makes mistakes on a certain type of question, the review frequency of this type of question will be increased. Driven by the control instructions, the learning machine performs various learning tasks in an orderly manner. Users only need to follow the guidance of the learning machine to easily complete their daily learning plan. At the same time, the built-in sensors and interactive modules of the learning machine capture the user's learning status in real time, such as concentration, answering speed, emotional changes, etc., and feed back these data to the control device in real time. The control device uses these data to continuously optimize the execution strategy of the learning plan to ensure the efficiency and smoothness of the learning process. As the learning progress continues to advance, users can clearly see their own progress trajectory, which knowledge points are more firmly mastered, and which areas need to be strengthened. This detailed report not only provides users with valuable learning feedback, but also points out the direction for their future learning. In this way, users can gradually achieve their learning goals with the help of the intelligent learning machine.

[0033] This embodiment obtains the user's learning goal data and compares it with a preset learning plan model to generate a corresponding personalized learning plan, and then generates corresponding control instructions for the learning machine, thereby controlling the learning machine to perform display actions according to the personalized learning plan, and obtaining the user's learning progress in real time to generate a learning plan report for the user, so as to improve the intelligence level of the learning machine, and realize personalization and efficiency of the learning process by accurately matching the user's learning needs and resources.

[0034] Further, see Figure 2 Another embodiment of the present invention provides a control method for a learning machine, based on the above Figure 1 In the embodiment shown, the steps of generating a corresponding personalized learning plan according to the learning target data and the preset learning plan model include S210-S240, wherein: S210, determining the user's learning needs, learning time, and learning difficulty preference according to the learning goal data; S220, inputting learning needs, learning time and learning difficulty preference into a preset learning plan model, matching and calculating through a model algorithm, and generating corresponding output results; S230, determining corresponding learning content, learning sequence and learning time allocation according to the output results; S240: Generate a corresponding personalized learning plan based on the learning content, learning sequence, and learning time allocation.

[0035] In this embodiment, the learning goal data can be obtained through a user's learning preference questionnaire, historical learning records, or direct communication with the user. These data not only cover the specific goals that the user hopes to achieve (such as passing a certain exam, mastering a certain skill, etc.), but also go deep into the user's personal learning habits, preferred areas, and difficulties. By carefully analyzing these data, the control device can more accurately determine the user's learning needs, learning time, and learning difficulty preferences, so as to grasp the user's learning needs and lay a solid foundation for the subsequent learning plan formulation.

[0036] Next, these learning needs, learning time, and learning difficulty preferences are used as inputs and fed into the preset learning plan model. Based on big data analysis and machine learning technology, this preset learning plan model has deeply studied and optimized the behaviors of tens of thousands of learners, and can efficiently match the personalized needs of users. Within the model, complex algorithms will intelligently match and calculate according to the parameters entered by the user, comprehensively considering the difficulty of the learning content, the correlation between knowledge points, and the reasonable allocation of learning time, and finally generate a set of scientific and efficient personalized learning plans.

[0037] The generated personalized learning plan not only includes specific learning content (such as which chapters and which exercises), but also clarifies the learning order (i.e. what to learn first and what to learn later) and the allocation of learning time (how long to study every day and the learning focus of each stage). This design is intended to ensure the coherence and systematicness of the learning process and help users advance their learning progress in an orderly manner.

[0038] In order to improve user experience and learning effect, during the execution of the learning plan, the control device will conduct real-time evaluation based on the user's actual learning progress and effect. If the user masters certain knowledge points faster or slower, the control device will automatically adjust the learning plan based on the evaluation results, increase or decrease the learning time and difficulty of the relevant content, and ensure that learning always stays in the user's "zone of proximal development", neither too easy nor too difficult.

[0039] Further, see Figure 3 Another embodiment of the present invention provides a control method for a learning machine, based on the above Figure 2 In the embodiment shown, the steps of inputting learning needs, learning time and learning difficulty preference into a preset learning plan model, matching and calculating through a model algorithm, and generating corresponding output results include S221-S224, wherein: S221, inputting learning needs, learning time and learning difficulty preference into a preset learning plan model, and calculating the matching degree between each learning need and the preset learning resources; S222, performing multi-objective optimization processing according to the matching degree, the weight of the learning time, and the weight of the learning difficulty preference to screen out the optimal learning path and resource combination; S223, prioritizing the selected optimal learning paths and resource combinations, and selecting the target learning resources that are most relevant to the user's current learning stage; S224. Generate output results based on target learning resources.

[0040] In this embodiment, after inputting learning needs, learning time and learning difficulty preferences into the preset learning plan model, the preset learning plan model will start its powerful calculation engine, firstly conduct an in-depth analysis of each learning need, and calculate the matching degree with the preset rich learning resource library. This process not only takes into account the direct relevance of knowledge points, but also integrates the diversity, interest and practical application scenarios of learning resources, and strives to recommend the most suitable learning materials for users.

[0041] Next, a complex multi-objective optimization process is performed based on the weight of learning time and the weight of learning difficulty preference. The learning time weight reflects the user's expectations for learning efficiency, while the learning difficulty preference reflects the user's acceptance of learning content of different difficulty levels. Through careful weighing, the model can find a balance point to ensure that the learning plan is neither too compact to cause user fatigue nor too loose to affect learning progress. At the same time, the difficulty just meets the user's expectations, avoiding a "one-size-fits-all" learning experience.

[0042] After completing the multi-objective optimization process, the model will further prioritize the selected learning paths and resource combinations. Based on the in-depth understanding of the user's current learning stage, as well as the logical relationship and dependency between learning paths, the control device can ensure that the user can proceed step by step in the learning process, starting with the easy and then the difficult, and gradually build a complete knowledge system. At the same time, it will also give priority to recommending the learning resources that are most closely related to the user's current learning stage to improve the pertinence and effectiveness of learning.

[0043] Finally, the model will select the target learning resources that best meet the user's current needs based on the results of the priority sorting, and generate corresponding output results. These output results include not only specific learning resource links or paths, but may also include learning suggestions, learning tips, and learning progress tracking information to help users better understand and master the learning content and ensure a smooth and efficient learning process.

[0044] Further, see Figure 4 Another embodiment of the present invention provides a control method for a learning machine, based on the above Figure 3 In the embodiment shown, multi-objective optimization processing is performed according to the matching degree, the weight of the learning time, and the weight of the learning difficulty preference to screen out the steps of the optimal learning path and resource combination, including S2221-S2224, wherein: S2221. Establish a corresponding objective function according to the matching degree, the weight of the learning time, and the weight of the learning difficulty preference; S2222. Determine corresponding constraint conditions according to the objective function, and solve the objective function to determine a global optimal solution; S2223. Construct a multi-objective optimization model according to the objective function and the global optimal solution; S2224. Input the weight of learning time and the weight of learning difficulty preference into the multi-objective optimization model to screen out the optimal learning path and resource combination.

[0045] In this embodiment, the objective function may include three main dimensions: maximizing learning effectiveness, minimizing learning time, and adapting learning difficulty. These dimensions are interrelated and together constitute the core goal of optimizing learning paths and resource combinations. The objective function can be designed in the form of a weighted sum, and each dimension is assigned a different weight coefficient according to its importance, thereby reflecting the user's comprehensive consideration of learning efficiency, time management, and difficulty preference. Next, the corresponding constraints need to be determined. These constraints may include the availability of learning resources, the continuity of the learning path, the rationality of the learning time, and the adaptability of the learning difficulty. For example, the availability of learning resources requires that the selected resources must exist and be accessible; the continuity of the learning path emphasizes the connection and logical relationship between knowledge points to avoid jumping or repeating the learning content; the rationality of the learning time is based on the user's schedule and learning habits to ensure that the learning plan is not too tight or loose; the adaptability of the learning difficulty is based on the user's difficulty preference to ensure that the learning content is both challenging and not too difficult.

[0046] In this embodiment, after determining the objective function and constraints, we can use mathematical optimization methods (such as linear programming, nonlinear programming, genetic algorithms, etc.) to solve the objective function. In the solution process, heuristic algorithms or meta-heuristic algorithms, such as genetic algorithms, particle swarm optimization algorithms, or simulated annealing algorithms, are used to improve the solution efficiency and find results closer to the optimal solution, so as to find the global optimal solution that satisfies all constraints. This process may require the use of professional mathematical software or algorithm libraries to ensure the accuracy and efficiency of the calculation.

[0047] Once the global optimal solution is obtained, the control device can construct a multi-objective optimization model based on this result. The multi-objective optimization model can comprehensively consider multiple objectives such as learning effectiveness, learning time and learning difficulty, and provide users with a set of optimized learning paths and resource combinations. Through this multi-objective optimization model, the user's learning needs can be matched more accurately, improving the pertinence and effectiveness of learning.

[0048] Finally, the weight of learning time and the weight of learning difficulty preference are input into the multi-objective optimization model, which will perform intelligent calculation and screening based on these input parameters, and finally output the optimal learning path and resource combination. These output results will directly guide the user's learning process and help the user achieve learning goals in a more efficient and comfortable way. At the same time, as the user's learning progress progresses and feedback is collected, the control device can also continuously adjust and optimize the learning plan to ensure the continuity and effectiveness of the learning process.

[0049] Further, see Figure 5 Another embodiment of the present invention provides a control method for a learning machine, based on the above Figure 4In the embodiment shown, the control method further includes S500-S1000, wherein: S500, obtaining the user's historical learning data and historical learning results, and preprocessing the historical learning data and historical learning results; S600, based on machine learning algorithms, preprocessed historical learning data and preprocessed historical learning results, identify key factors affecting learning results; S700. Construct a target learning plan model based on key factors; S800, using historical learning data and historical learning results as training sets to train a target learning plan model; S900, generating evaluation indicators based on the trained target learning plan model to verify the model performance; S1000. Determine the verified qualified target learning plan model as the preset learning plan model.

[0050] In this embodiment, historical learning data may include various learning tasks completed by the user on the learning machine, learning time, selection of learning resources, tracking records of learning progress, etc. These data fully reflect the user's learning behavior and learning habits. Historical learning results refer to the specific results achieved by the user in the learning process, such as test scores, homework completion, project completion quality, etc., which directly reflect the user's learning effect and mastery.

[0051] First, these historical learning data and learning outcomes need to be preprocessed. Preprocessing steps may include data cleaning (removing duplicate, erroneous or irrelevant data), data conversion (unifying data in different formats or units), data reduction (reducing data complexity through dimensionality reduction or feature selection), etc., to ensure the accuracy and consistency of the data and provide a reliable basis for subsequent analysis.

[0052] Next, based on the machine learning algorithm, the key factors that affect the learning effect are identified using the preprocessed historical learning data and learning outcomes. These key factors may include the user's learning preferences, learning habits, learning ability, the quality and applicability of learning resources, the rationality of the learning path, etc. Through the machine learning algorithm, the potential relationship between these factors and the learning effect can be excavated, providing strong support for building a target learning plan model.

[0053] After identifying the key factors, a target learning plan model is constructed based on these factors. The target learning plan model aims to generate an optimal learning plan for users by comprehensively considering the learning characteristics and needs of users, as well as the characteristics and effects of learning resources. In the process of constructing the target learning plan model, it is necessary to determine the input (such as user learning preferences, historical learning data, etc.), output (such as learning plan, learning resource recommendation, etc.) of the target learning plan model, as well as the structure and parameters of the target learning plan model.

[0054] In order to verify the performance of the target learning plan model, the historical learning data and learning results are used as training sets to train the model. During the training process, the target learning plan model will learn and optimize its own parameters and structure based on the input data to better meet the needs of the learning task. After the training is completed, the performance of the target learning plan model is verified by generating evaluation indicators (such as accuracy, recall rate, F1 score, etc.). The evaluation indicators can objectively reflect the accuracy and effectiveness of the model in learning plan generation, resource recommendation, etc.

[0055] Finally, the verified qualified target learning plan model is determined as the preset learning plan model. This model will serve as the core part of the learning machine control method and is used to generate personalized learning plans and learning resource recommendations for users during the actual learning process. As the user's learning progress progresses and feedback is collected, the target learning plan model can also continuously optimize and adjust itself to better meet the user's learning needs and improve learning results.

[0056] Further, see Figure 6 Another embodiment of the present invention provides a control method for a learning machine, based on the above Figure 1 In the embodiment shown, according to the control instruction, the step of controlling the learning machine to perform the display action according to the personalized learning plan includes S410-S440, wherein: S410, obtaining display interface data and display preference data of the user's learning machine; S420, determining the user's current learning progress according to the control instruction, and generating learning resources corresponding to the learning progress; S430, generating a page layout corresponding to the display interface of the learning machine according to the display interface data, the display preference data and the learning resources; S440: According to the page layout, control the display interface of the learning machine to perform a display action.

[0057] In this embodiment, the display interface data may include hardware parameters such as the size, resolution, and color mode of the current display interface of the learning machine, as well as the layout and style of existing elements on the interface (such as navigation bars, toolbars, status bars, etc.). These display interface data are crucial for optimizing the display of learning resources and improving user experience. Display preference data reflects the user's personalized needs for the display interface, such as font size, color theme, layout style, etc. By collecting and analyzing these display preference data, users can be provided with a display interface that is more in line with their visual habits and learning preferences.

[0058] In this embodiment, when the learning machine receives the control instruction and determines the user's current learning progress, the control device will retrieve the corresponding learning materials from the preset learning resource library according to this progress. These learning resources may include text, pictures, videos, audio and other forms, aiming to help users deeply understand and master knowledge points. Next, the control device will automatically generate a page layout corresponding to the display interface of the learning machine based on the display interface data, display preference data and the determined learning resources. The design of this page layout will comprehensively consider the type, quantity, importance of learning resources, as well as the user's learning progress and preferences, to ensure that the presentation of learning content is both clear and efficient.

[0059] The page layout can include multiple areas, such as the main learning area, auxiliary information area, interactive operation area, etc. The main learning area is used to display the core learning resources of the current learning progress, such as the text content of the textbook chapter, video explanation or chart display, to ensure that users can acquire key knowledge intuitively and attentively. The design of this area will be optimized according to the characteristics of the learning resources and the user's display preferences, such as adjusting the font size, color contrast and layout structure to improve the reading experience and learning effect.

[0060] The auxiliary information area is used to display additional information related to learning resources, such as knowledge point summaries, key tips, related links, etc. This information helps users build a knowledge framework during the learning process, deepen their understanding, and promote the transfer and application of knowledge. The layout of the auxiliary information area should be concise and clear, avoid excessive interference, and provide convenient navigation and interaction methods for users to view and switch at any time.

[0061] The interactive operation area is designed to enhance user participation and learning effects. It may contain interactive elements such as exercises, test questions, and discussion areas to encourage users to actively think and explore during the learning process, and to test their learning results in a timely manner. The layout of the interactive operation area should take into account the user's operating habits and learning needs, ensure smooth operation, timely feedback, and effectively record the user's learning behavior and achievements, providing a basis for subsequent adjustments to the learning plan.

[0062] Finally, according to the generated page layout, the control device performs corresponding display actions by controlling the display hardware and software of the learning machine. This includes rendering learning resources on the screen, adjusting the layout and style of elements, and processing user interaction operations. Through these steps, the learning machine can provide users with a personalized, dynamic and interactive learning environment, thereby improving the user's learning experience and effect.

[0063] Further, see Figure 7 Another embodiment of the present invention provides a control method for a learning machine, based on the above Figure 6 In the embodiment shown, the step of generating a page layout corresponding to the display interface of the learning machine according to the display interface data, the display preference data and the learning resources includes S431-S434, wherein: S431, obtaining the width, height and resolution range of the window of the display interface, determining the optimal resolution information of the display interface, and generating screen display information corresponding to the optimal resolution information; S432, determining display elements of the display interface according to the learning resources; S433, analyzing the user's visual habits and interface operation habits according to the screen display information and the display preference data to determine the optimal size and optimal position of the display element; S434: Adjust the page layout corresponding to the display interface according to the optimal size and the optimal position.

[0064] In this embodiment, the width of the window of the display interface, the height of the window and the resolution range are the basic parameters for generating a high-quality page layout. First, by obtaining these key data, the physical limitations and performance characteristics of the learning machine display interface can be accurately understood, providing a strong basis for subsequent optimization design.

[0065] Next, the optimal resolution information for the display interface is determined by using the data of the window width, window height, and resolution range. This is an important step to ensure the clear display of learning resources and the visual comfort of users. The selection of the optimal resolution should take into account the capabilities of the display hardware, the user's visual habits, and the presentation requirements of learning resources to ensure that the content is neither too compact to make it difficult to read nor too loose to waste space.

[0066] After determining the optimal resolution, the control device will identify and determine the display elements that need to be displayed on the display interface according to the type and content of the current learning resource. These display elements may include text paragraphs, pictures, video players, interactive buttons, etc. These display elements together constitute the visual focus and operation objects in the user's learning process. By accurately identifying and classifying these display elements, the layout design can be more targeted to ensure the effective communication of learning resources and smooth interaction of users.

[0067] After determining the display elements, combined with the screen information and the user's display preference data, the user's visual habits and interface operation habits can be deeply analyzed. The user's visual habits may include preferences for font size, color matching, and layout structure, while the operation habits may involve expectations for navigation methods, interaction processes, and response speed. By comprehensively using this data, the user's needs and preferences can be more accurately grasped, and the optimal size and position can be assigned to the display elements.

[0068] The selection of the best size should ensure that the display elements remain clear and readable while not occupying too much display space, so that the entire page looks harmonious and unified. The determination of the best position should take into account the user's visual focus movement trajectory and operating habits, and place important elements in a position that is easy for users to find and operate, thereby improving user experience and learning efficiency. In this process, we may apply some interface design principles and psychological principles, such as F-shaped layout and rule of thirds composition, to optimize the page layout and guide the user's line of sight and attention distribution.

[0069] Finally, according to the optimal size and optimal position, the page layout corresponding to the display interface is adjusted. This step may involve fine-tuning element spacing, alignment, hierarchy, etc. to ensure that the page layout is both beautiful and practical. During the adjustment process, it is also necessary to maintain a high degree of flexibility and sensitivity, and make fine-tuning and optimization at any time based on user feedback and actual results to ensure that the learning machine can provide users with a personalized and efficient learning interface.

[0070] Further, see Figure 8 Another embodiment of the present invention provides a control method for a learning machine, based on the above Figure 1 In the embodiment shown, the step of generating control instructions corresponding to the learning machine according to the personalized learning plan includes S310-S340, wherein: S310, determining the learning tasks corresponding to the current stage according to the personalized learning plan; S320, identifying the required learning resource type according to the learning task, and retrieving matching learning resources from a preset learning resource library; S330, sorting and organizing the retrieved learning resources according to the learning sequence and learning time allocation, and generating a detailed learning resource list; S340: Generate corresponding control instructions according to the learning resource list.

[0071] In this embodiment, the personalized learning plan is the core of the customized learning experience provided by the learning machine. First, the control device will accurately identify the learning tasks corresponding to the current learning stage according to the user's personalized learning plan. These learning tasks may be comprehensively formulated based on multiple dimensions such as the user's age, subject, interest, ability level, etc., aiming to provide users with content that best suits their learning needs and development direction.

[0072] Next, in order to support the completion of these learning tasks, the control device will identify the types of learning resources required. There are many types of learning resources, including but not limited to textbooks, teaching videos, online courses, exercises, simulation test questions, etc. By intelligently analyzing the specific requirements of the learning tasks, the control device can accurately select the matching learning resources to ensure the pertinence and effectiveness of the learning content.

[0073] After determining the required learning resources, the control device will carefully sort and organize these resources according to the learning sequence and learning time allocation. The setting of the learning sequence follows the principle of starting from the simplest to the most complex and progressing step by step, ensuring that users gradually deepen their knowledge on the basis of mastering the basic knowledge; while the arrangement of learning time allocation takes into account the user's daily routine and learning habits, avoiding over-concentration or dispersion of learning, so as to achieve the best learning effect.

[0074] Finally, according to the organized list of learning resources, the control device will generate corresponding control instructions. These control instructions are the key to driving the operation of the learning machine hardware and software. They guide the learning machine on how to display learning resources, how to respond to user operations, how to record learning progress and results, etc. By accurately executing these control instructions, the learning machine can provide users with a highly personalized and intelligent learning environment, helping users to efficiently complete learning tasks and achieve learning goals.

[0075] It is worth noting that in the process of generating control instructions, the control device will also fully consider the user's interactive experience. For example, by optimizing the presentation of learning resources, providing convenient navigation and search functions, and setting reasonable prompts and feedback mechanisms, the user's operational convenience and satisfaction can be improved, and the attractiveness and competitiveness of the learning machine can be enhanced.

[0076] In addition, as the user's learning progress continues and the personalized learning plan is continuously adjusted, the control device will also update the learning resource list and control instructions in real time to ensure that the learning machine can always provide the content and services that best suit the user's current learning status and needs. This dynamic adjustment capability is one of the important guarantees for the learning machine to achieve personalized learning.

[0077] The present invention also proposes a control device, which includes: the control device includes: a memory, a processor, and a control program of a learning machine stored in the memory and executable on the processor, wherein the control program of the learning machine is configured to implement the control method of the learning machine as described above.

[0078] It is worth noting that since the control device of the present invention is based on the control method of the above-mentioned learning machine, the embodiments of the control device of the present invention include all technical solutions of all embodiments of the control method of the above-mentioned learning machine, and the technical effects achieved are also exactly the same, which will not be repeated here.

[0079] The present invention also provides a learning machine, which includes the control device as described in the above embodiment.

[0080] It is worth noting 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 technical solutions of all embodiments of the above-mentioned control device, and the technical effects achieved are also exactly the same, which will not be repeated here.

[0081] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0082] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0083] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course 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 is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, including a number of instructions for enabling a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0084] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A control method for a learning machine, characterized in that: The method comprises: Obtain the user's learning goal data; Generate a corresponding personalized learning plan based on the learning goal data and the preset learning plan model; Generate control instructions corresponding to the learning machine according to the personalized learning plan; According to the control instruction, the learning machine is controlled to perform display actions according to the personalized learning plan, and the user's learning progress is obtained in real time to generate a learning plan report for the user.

2. The control method of the learning machine according to claim 1, characterized in that: The step of generating a corresponding personalized learning plan according to the learning target data and the preset learning plan model includes: Determining the user's learning needs, learning time, and learning difficulty preferences based on the learning goal data; Input the learning needs, the learning time and the learning difficulty preference into the preset learning plan model, match and calculate through the model algorithm, and generate corresponding output results; Determine the corresponding learning content, learning sequence and learning time allocation according to the output results; The corresponding personalized learning plan is generated according to the learning content, the learning sequence and the learning time allocation.

3. The control method of the learning machine according to claim 2, characterized in that: The step of inputting the learning needs, the learning time and the learning difficulty preference into the preset learning plan model, matching and calculating through the model algorithm, and generating corresponding output results includes: Inputting the learning needs, the learning time and the learning difficulty preference into the preset learning plan model, and calculating the matching degree between each learning need and the preset learning resource; According to the matching degree, the weight of the learning time and the weight of the learning difficulty preference, a multi-objective optimization process is performed to screen out the optimal learning path and resource combination; Prioritize the selected optimal learning paths and resource combinations, and select the target learning resources that are most relevant to the user's current learning stage; The output result is generated according to the target learning resource.

4. The control method of the learning machine according to claim 3, characterized in that: The step of performing multi-objective optimization processing according to the matching degree, the weight of the learning time, and the weight of the learning difficulty preference to screen out the optimal learning path and resource combination includes: Establishing a corresponding objective function according to the matching degree, the weight of the learning time, and the weight of the learning difficulty preference; According to the objective function, corresponding constraint conditions are determined, and the objective function is solved to determine a global optimal solution; Constructing a multi-objective optimization model according to the objective function and the global optimal solution; The weight of the learning time and the weight of the learning difficulty preference are input into the multi-objective optimization model to screen out the optimal learning path and resource combination.

5. The control method of the learning machine according to claim 4, characterized in that: The control method further comprises: Acquire the user's historical learning data and historical learning achievements, and pre-process the historical learning data and the historical learning achievements; Based on the machine learning algorithm, the preprocessed historical learning data, and the preprocessed historical learning results, identify key factors that affect the learning effect; Based on the key factors, a target learning plan model is constructed; Using the historical learning data and the historical learning results as a training set to train the target learning plan model; Generate evaluation indicators based on the trained target learning plan model to verify the model performance; The verified target learning plan model is determined as the preset learning plan model.

6. The control method of a learning machine according to claim 1, characterized in that: The step of controlling the learning machine to perform a display action according to the personalized learning plan according to the control instruction includes: Obtaining display interface data and display preference data of the user's learning machine; Determining the user's current learning progress according to the control instruction, and generating learning resources corresponding to the learning progress; Generate a page layout corresponding to the display interface of the learning machine according to the display interface data, the display preference data and the learning resources; According to the page layout, the display interface of the learning machine is controlled to perform the display action.

7. The control method of the learning machine according to claim 6, characterized in that: The step of generating a page layout corresponding to the display interface of the learning machine according to the display interface data, the display preference data and the learning resource comprises: Acquire the width of the window of the display interface, the height of the window, and the resolution range, determine the optimal resolution information of the display interface, and generate screen display information corresponding to the optimal resolution information; Determining display elements of the display interface according to the learning resource; Analyze the user's visual habits and interface operation habits according to the screen display information and display preference data to determine the optimal size and optimal position of the display element; According to the optimal size and the optimal position, the page layout corresponding to the display interface is adjusted.

8. The control method of a learning machine according to claim 1, characterized in that: The step of generating control instructions corresponding to the learning machine according to the personalized learning plan includes: Determine the learning tasks corresponding to the current stage according to the personalized learning plan; According to the learning task, identify the required learning resource type and retrieve matching learning resources from a preset learning resource library; Sort and organize the retrieved learning resources according to the learning sequence and learning time allocation, and generate a detailed learning resource list; Generate corresponding control instructions based on the learning resource list.

9. A control device, characterized in that: The control device includes: a memory, a processor, and a control program of the learning machine stored in the memory and executable on the processor, wherein the control program of the learning machine is configured to implement the control method of the learning machine as described in any one of claims 1 to 8.

10. A learning machine, characterized in that: Comprising a control device as claimed in claim 9.

Citation Information

Patent Citations

  • Intelligent search recommendation method and system based on online learning course

    CN116257694A

  • Intelligent learning method and learning machine based on intelligent learning condition evaluation

    CN117994097A

  • Intelligent personalized learning path planning system and method

    CN118446474A