A database task configuration method

Abstract

The present invention relates to the field of data processing technology, and in particular to a database task configuration method, comprising: collecting the execution time, completion degree and execution times of various learning tasks completed by several users, and generating execution data of each learning task; constructing several learning classification models, and selecting the optimal learning classification model; dividing users into single type and mixed type; configuring several learning tasks for a user's single learning, generating a task forgetting curve, and executing a task completion model to generate a task execution log; adjusting the task forgetting curve to adjust the time ratio between new learning tasks and past learning tasks; dividing learning tasks into special learning tasks and general learning tasks, dividing general learning tasks into hot tasks and cold tasks, and generating a task completion model by combining past learning tasks and hot tasks; the present invention improves the accuracy of database task configuration while effectively allocating learning tasks to different students in a targeted manner.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a database task configuration method. Background Art

[0002] Every student is different in learning ability, learning style, knowledge base, etc. Some students have strong comprehension ability and learn quickly; some students need more time and practice to master knowledge; some students are good at visual learning, some prefer auditory learning, and some students are better at taking notes, writing and reading. By pushing learning tasks in a targeted manner, the personalized needs of different students can be met and learning effects can be improved. Traditional education often adopts a unified teaching content and progress, which makes it difficult to take into account the specific situation of each student. Targeted learning task push can avoid the waste of educational resources.

[0003] Chinese patent application publication number CN112651678A discloses a big data-based educational affairs management system and method. The system includes a teaching task management module, a cloud module, a performance management module, and a teaching task planning module. The teaching task management module is configured to send teaching tasks to the cloud module and student information to the performance management module. The cloud module is configured to combine teaching tasks with historical data in a teaching task database, fragment the teaching tasks, and obtain the time and grade corresponding to the fragmented tasks. The performance management module is configured to obtain student grades based on student information, determine student types based on the grades, and assign student information to the corresponding student types. The learning task planning module is configured to recommend fragmented tasks with corresponding time and grade based on student types and generate corresponding teaching plans based on the fragmented tasks. This system can accurately plan student learning tasks, save students' study time, and improve their learning efficiency.

[0004] Chinese patent application publication number CN118333582A discloses a teaching equipment management control system and method. The invention provides a teaching equipment management control system and method, comprising: a device control unit for controlling the reception and parsing of teaching instructions, outputting teaching content, collecting learning data, processing device input feedback, and transmitting the data to a central control unit via a communication control unit; a central control unit for receiving data from the device control unit and generating device control instructions and device status analysis; a detection and alarm unit for receiving device parameters from the central control unit, monitoring the operating status of the teaching equipment in real time, and performing fault analysis; a communication control unit for data transmission and communication between units; and a power control unit for supplying power to each unit. By integrating a multi-module design and enabling the coordinated operation of each unit, the invention improves the adaptability and accuracy of teaching strategies, significantly enhancing teaching efficiency, learning experience, equipment operation and maintenance, and energy efficiency.

[0005] It can be seen from this that the existing technology allocates tasks to students based solely on their grades without taking into account the students' learning process and learning habits, and fails to reasonably allocate learning tasks by adjusting the students' learning forgetting curve. Summary of the Invention

[0006] To this end, the present invention provides a database task configuration method to overcome the problem in the prior art that tasks are assigned to students solely based on their grades without considering the students' learning process and learning habits, and failing to reasonably assign learning tasks by adjusting the students' learning forgetting curve.

[0007] To achieve the above object, the present invention provides a database task configuration method, comprising:

[0008] Collecting the execution time, completion degree, and execution times of each learning task completed by several users to generate execution data of each learning task, wherein the execution data includes the average execution time, average completion degree, and average execution times of each learning task;

[0009] Incorporating the average degree of completion and the average number of executions into a plurality of learning tasks to construct a plurality of learning classification models, and selecting an optimal learning classification model;

[0010] Classifying the users into single type and mixed type according to the users' performance on the optimal learning classification model;

[0011] Based on the user's single learning time and the average execution time, the user is configured with a number of learning tasks for single learning, the single completion rate of each learning task is counted to generate a task forgetting curve, and based on the different categories of the user and the average completion rate, the task completion model is matched and executed for the user to generate a task execution log;

[0012] Adjusting the task forgetting curve using a time series analysis algorithm based on the task execution log to adjust the time ratio of the newly added learning task to the previous learning task;

[0013] The learning tasks are divided into special learning tasks and general learning tasks according to the completion status of the learning tasks, and the general learning tasks are divided into hot tasks and cold tasks. The task completion model is generated by combining the past learning tasks and the hot tasks.

[0014] Furthermore, the process of calling a plurality of the learning tasks to construct a plurality of learning classification models in combination with the average degree of completion and the average number of executions, and selecting the optimal learning classification model includes:

[0015] In combination with the average degree of completion and the average number of executions, calling a plurality of the learning tasks to construct a plurality of learning classification models;

[0016] Calculating the estimated execution time of each of the learning classification models based on the average execution time;

[0017] The optimal learning classification model is selected based on the user's single learning time and the estimated execution time.

[0018] Furthermore, the process of classifying the users into the single type and the mixed type according to the execution of the optimal learning classification model by the users includes:

[0019] Counting the memory occupied by text, audio, and video in each learning task in the optimal learning classification model;

[0020] Allocating each of the learning tasks to different learning modules according to the task classification corresponding to the maximum value of the memory size;

[0021] Calculating dimension scores based on how the user uses each of the learning modules in the optimal learning classification model, and classifying the user into the single type and the mixed type according to the dimension scores;

[0022] The task categories include visual, auditory and reading and writing types. The single type refers to users with only one of the task categories. The mixed type refers to users with two or more of the task categories. The learning modules include text modules, audio modules and video modules.

[0023] Furthermore, a dimension score is calculated based on the user's use of each learning module in the optimal learning classification model, and a process of classifying the user into the single type and the mixed type according to the dimension score includes:

[0024] Counting the number of times the user selects different learning modules and the duration of their use in the optimal learning classification model;

[0025] Calculate the dimension scores based on the number of selections and the usage duration, and sort the dimension scores;

[0026] The user is determined to be the single type based on the difference between the highest dimension score and the second highest dimension score, or each dimension score is compared with a preset dimension score.

[0027] Furthermore, the process of configuring the plurality of learning tasks for the user's single learning based on the user's single learning time and the average execution time includes:

[0028] Adding up the average execution time corresponding to each learning task to obtain the total configuration time;

[0029] Calculating a configuration time difference between the total configuration time and the single learning time;

[0030] Comparing the configured time difference with a preset configuration time difference, and configuring a plurality of learning tasks for the user to learn in a single session according to the comparison result;

[0031] The preset configuration time difference is positively correlated with the user's single learning time.

[0032] Furthermore, several single completion degrees of each learning task in each single learning are counted, and the task forgetting curve is generated by combining the time interval of each single learning and the corresponding single completion degree.

[0033] Furthermore, in combination with the different categories of the users and the average completion degree, the process of matching and executing the task completion model for the users to generate the task execution log includes:

[0034] Collecting the classification of each user and the average degree of completion of each learning task in the learning classification model;

[0035] Matching the task completion model consistent with the user classification and the average completion degree in a learning task database;

[0036] Recording the user's completion of the task completion model to generate the task execution log;

[0037] The task completion model includes the classification of each user and the corresponding completed learning tasks.

[0038] Furthermore, based on the task execution log, the time series analysis algorithm is used to predict the completion degree of the past learning task to adjust the extreme point of the task forgetting curve. The time series analysis algorithm predicts the extreme point of the task forgetting curve corresponding to the past learning task by analyzing the completion degree and execution time of the past learning task. The extreme point is the point with the largest curvature on the task forgetting curve.

[0039] Furthermore, according to the task forgetting curve that has been adjusted, the time ratio of the newly added learning task to the past learning task is reduced at the extreme point, the single learning time includes the time to execute the newly added learning task and the time to execute the past learning task, and the time ratio is the ratio of the time taken by the user to execute the newly added learning task to the time taken by the user to execute the past learning task.

[0040] Furthermore, the learning tasks are divided into special learning tasks and general learning tasks according to the completion status of the learning tasks, and the general learning tasks are divided into hot tasks and cold tasks. The process of generating the task completion model by combining the past learning tasks and the hot tasks includes:

[0041] Classifying the uncompleted learning tasks of the user in the single learning as special learning tasks, and the learning task database pushes relevant information of the special learning tasks to the user according to the classification of the user;

[0042] Classifying the learning tasks completed by the user in the single learning session into general learning tasks, and determining whether the general learning tasks are hot or cold tasks based on the completion time;

[0043] A single allocation method is adopted for the hot tasks, and a mixed allocation method is adopted for the cold tasks;

[0044] A learning task that is the same as the past learning task and the hot task is selected to generate the task completion model.

[0045] Compared with the prior art, the beneficial effect of the present invention is that the present invention divides the users into visual, auditory and reading and writing types by using the learning classification model. Different types of learners have different ways of receiving and processing information. Visual learners are sensitive to visual information such as images, charts, and videos; auditory learners are better at learning by listening to explanations and audio; and reading and writing learners prefer reading text materials and writing records. After the users are classified, they can be provided with learning tasks, resources and methods that suit their learning styles, thereby improving learning efficiency and effectiveness. Learning resources are reasonably allocated based on the students' learning types. After students understand their own learning types, they can more clearly understand their learning characteristics and advantages, which helps them to give full play to their strengths and improve their shortcomings in the learning process. When learning tasks and resources match the students' learning types, students are more likely to engage in learning and feel the joy of learning. This can effectively reduce the boredom and frustration in the learning process, improve students' participation and persistence, and improve the accuracy of database task configuration.

[0046] Furthermore, the present invention combines different classifications and average completion rates of users, matches the task completion models of past users with the same classification and average completion rate as the user in the learning task database, and uses the learning experience of past users to guide the current user. Each user has unique learning characteristics and levels. By classifying users and calculating the average completion rate, past users similar to the current user can be found more accurately. The task completion models of these past users are formed based on their actual learning experience, and can provide personalized learning paths and method suggestions for the current user to meet the specific needs of the current user and improve the pertinence and effectiveness of learning. Past users have accumulated successful experience and methods in the process of completing tasks, and the current user can directly learn from them. By referring to the task completion models of past users, users can quickly find a learning method that suits them, which can save a lot of time and energy, allowing current users to use learning resources more efficiently, focus on knowledge learning and ability improvement, and reduce wasted time. By analyzing the task completion models of past users and the feedback of current users, we can understand the needs and adaptation of different types of users to learning tasks, which helps to optimize the design of learning tasks. Different users may adopt different methods and strategies when facing the same task. By drawing on the experience of multiple past users, current users can broaden their learning ideas, learn to view and solve problems from different angles, and further improve the accuracy of database task configuration.

[0047] Furthermore, the present invention adjusts the user's task forgetting curve by collecting parameters in the user's learning process, and dynamically adjusts the learning task for the user. Each user has different learning rhythm, forgetting speed and knowledge mastery. By collecting parameters in the learning process, such as learning time, answering accuracy, review times, weak points in knowledge mastery, etc., we can deeply understand the user's learning characteristics and status. Adjusting the task forgetting curve based on these parameters can more accurately grasp the user's forgetting rules of knowledge, thereby dynamically adjusting the learning task to make it accurately match the user's current learning needs, improve the pertinence and effectiveness of learning, and arrange learning tasks according to the adjusted task forgetting curve. When the user is about to forget the knowledge point, it can review and consolidate it in time, avoid forgetting a large amount of knowledge, and reasonable tasks. Task arrangement can reduce the time users spend on repeatedly learning the knowledge they have already mastered, scientifically predict the task forgetting curve, and conduct targeted review and learning task arrangements according to the user's forgetting patterns, which helps to transform short-term memory into long-term memory. By reviewing and applying knowledge points multiple times at appropriate time points, users can grasp knowledge more firmly, reduce forgetting, improve knowledge retention, and lay a solid foundation for subsequent learning and application. Dynamically adjusting learning tasks according to the user's learning situation can avoid the waste of learning resources. For content that users have already mastered, the allocation of related resources can be reduced, and for the parts that users need to strengthen, more high-quality resources can be provided. This can improve the utilization efficiency of learning resources, make limited resources more reasonably allocated, and further improve the accuracy of database task configuration.

[0048] Furthermore, the present invention marks learning tasks according to their completion status, adopts different types of distribution methods for related materials for learning tasks of different popularity, and enables users to effectively handle different learning tasks through various task distribution methods. Learning tasks of different popularity may have different learning focuses and difficulties. Through marking and targeted material distribution, users can understand the characteristics of the tasks more clearly and obtain learning materials suitable for the tasks. Various task distribution methods can adapt to the learning styles and preferences of different users. Some users like to learn by reading text materials, while others prefer to watch videos or participate in practical operations. Different types of material distribution are adopted for tasks of different popularity according to the completion of tasks. After marking the popularity of the task, the order of learning tasks can be arranged according to the popularity and logical relationship of knowledge, and corresponding materials can be allocated. For popular basic tasks, basic knowledge materials are provided first to guide users to lay a solid foundation; for subsequent popular advanced tasks, more in-depth and comprehensive materials are provided to help users gradually build a complete knowledge system and achieve systematic learning. Appropriate material allocation and diverse task allocation methods can allow users to feel the orderliness and convenience of learning during the learning process. Users do not need to spend a lot of time looking for and screening materials, and can focus more on the learning content itself, reducing troubles and obstacles in the learning process, improving the overall learning experience, making the learning process smoother and more efficient, and further improving the accuracy of database task configuration. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 A flowchart of the database task configuration method of the present invention;

[0050] Figure 2 A flowchart for selecting the optimal learning classification model for an embodiment of the present invention;

[0051] Figure 3 This is a logic diagram for determining user type based on the difference between the highest dimension score and the second highest dimension score according to an embodiment of the present invention;

[0052] Figure 4 This is a logic diagram for determining user types based on scores in various dimensions according to an embodiment of the present invention. DETAILED DESCRIPTION

[0053] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are merely used to explain the present invention and are not intended to limit the present invention.

[0054] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0055] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside", and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the accompanying drawings. This is only for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0056] Furthermore, it should be noted that, in the description of the present invention, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood in a broad sense. For example, they may refer to fixed connections, detachable connections, or integral connections; mechanical connections or electrical connections; direct connections or indirect connections through an intermediate medium; and internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on specific circumstances.

[0057] See also Figure 1 As shown, it is a flowchart of the database task configuration method of the present invention. An embodiment of the present invention provides a database task configuration method, including:

[0058] Step S1: Collect the execution time, completion degree, and execution times of each learning task completed by several users to generate execution data of each learning task, including the average execution time, average completion degree, and average execution times of each learning task;

[0059] Step S2: combining the average completion degree and the average number of executions to call several learning tasks to construct several learning classification models, and select the optimal learning classification model;

[0060] Step S3, classifying users into single type and mixed type according to their performance on the optimal learning classification model;

[0061] Step S4: Based on the user's single learning time and average execution time, configure several learning tasks for the user's single learning, calculate the single completion rate of each learning task to generate a task forgetting curve, and combine the different categories of users and the average completion rate to match and execute the task completion model to the user to generate a task execution log;

[0062] Step S5, adjusting the task forgetting curve using a time series analysis algorithm based on the task execution log to adjust the time ratio of the newly added learning task to the previous learning task;

[0063] Step S6: divide the learning tasks into special learning tasks and general learning tasks according to the completion status of the learning tasks, divide the general learning tasks into hot tasks and cold tasks, and generate a task completion model by combining past learning tasks and hot tasks.

[0064] See also Figure 2 As shown in FIG. , which is a flowchart of selecting the optimal learning classification model according to an embodiment of the present invention, in step S2, several learning tasks are called to construct several learning classification models based on the average completion degree and the average number of executions, and the process of selecting the optimal learning classification model includes:

[0065] Step S201, combining the average completion degree and the average number of executions to call a number of learning tasks to build a number of learning classification models;

[0066] Step S202, calculating the estimated execution time of each learning classification model based on the average execution time;

[0067] Step S203: Selecting the optimal learning classification model based on the user's single learning time and the estimated execution time.

[0068] During implementation, several learning tasks with an average completion degree greater than or equal to a preset completion degree and an average execution number greater than or equal to a preset execution number are called to construct several learning classification models; the average execution time of each learning task in the learning classification model is added together to calculate the expected execution time of the learning classification model; the learning classification model with the same user's single learning time and expected execution time is selected as the optimal learning classification model;

[0069] It can be understood that, if several optimal learning classification models are selected, the learning classification model containing the least learning tasks is selected as the optimal learning classification model.

[0070] The preset completion degree and preset execution times are positively correlated with the user's single learning time.

[0071] It is understandable that if the user's single learning time is longer and the more learning tasks are included, higher requirements are placed on the completeness and number of times the learning tasks are used. Therefore, the preset completion degree and the preset number of executions are positively correlated with the user's single learning time.

[0072] Optionally, the user's single learning time is 1 hour, the preset completion rate is 90%, and the preset execution times are 10 times;

[0073] The user's single learning time is 1.5 hours, the preset completion rate is 92%, and the preset execution times are 15 times;

[0074] The user's single learning time is 2 hours, the preset completion rate is 94%, and the preset execution times are 20 times;

[0075] Specifically, in step S3, the process of classifying users into single type and mixed type according to their performance on the optimal learning classification model includes:

[0076] Calculate the memory size occupied by text, audio, and video in each learning task in the optimal learning classification model;

[0077] Allocate each learning task to different learning modules based on the task classification corresponding to the maximum memory size;

[0078] Dimension scores are calculated based on the user's use of each learning module in the optimal learning classification model, and users are divided into single type and mixed type according to the dimension scores;

[0079] Task categories include visual, auditory, and reading and writing. The single type refers to users with only one task category, and the mixed type refers to users with two or more task categories. Learning modules include text modules, audio modules, and video modules.

[0080] It can be understood that the mixed type is divided into visual and auditory mixed type, auditory and literacy mixed type, visual and literacy mixed type, and visual, auditory and literacy mixed type.

[0081] It is understandable that the audio information contained in the video is not counted in the audio occupied memory, and the image information is counted in the video occupied memory.

[0082] It can be understood that the dimension score of the text module corresponds to the frequency of use of the reading and writing type, the dimension score of the audio module corresponds to the frequency of use of the auditory type, and the dimension score of the video module corresponds to the frequency of use of the visual type.

[0083] Specifically, the present invention divides the users into visual, auditory and reading-writing types by using the learning classification model. Different types of learners have different ways of receiving and processing information. Visual learners are sensitive to visual information such as images, charts, and videos; auditory learners are better at learning by listening to explanations and audio; and reading-writing learners prefer reading text materials and writing records. After classifying the users, they can be provided with learning tasks, resources and methods that suit their learning styles, thereby improving learning efficiency and effectiveness. Learning resources are reasonably allocated based on the students' learning types. After students understand their own learning types, they can more clearly understand their learning characteristics and advantages, which helps them to give full play to their strengths and improve their shortcomings in the learning process. When learning tasks and resources match the students' learning types, students are more likely to engage in learning and feel the joy of learning. This can effectively reduce the boredom and frustration in the learning process, improve students' participation and persistence, and improve the accuracy of database task configuration.

[0084] See also Figure 3 As shown in FIG, it is a logic diagram for determining user types based on the difference between the highest dimension score and the second highest dimension score according to an embodiment of the present invention. In step S3, the dimension scores are calculated based on the user's use of each learning module in the optimal learning classification model. The process of classifying users into single type and mixed type according to the dimension scores includes:

[0085] Count the number of times users choose different learning modules and the duration of their use in the optimal learning classification model;

[0086] Calculate dimension scores based on the number of selections and usage duration, and sort the dimension scores;

[0087] Based on the difference between the highest dimension score and the second highest dimension score, the user is judged to be a single type or the score of each dimension is compared with the preset dimension score, where:

[0088] If the difference between the highest dimension score and the second highest dimension score is greater than or equal to the preset difference, the user is judged to be a single type.

[0089] If the difference between the highest dimension score and the second highest dimension score is less than the preset difference, the scores of each dimension are determined and compared with the preset dimension scores.

[0090] In implementation, dimension score = number of selections + usage time x 0.01. The above formula only selects various values ​​for calculation.

[0091] In a specific embodiment, it is assumed that the user uses the text module twice in a single study, the usage time is 240 seconds, the audio module is selected four times, the usage time is 560 seconds, and the video module is selected once, the usage time is 140 seconds. Then, the text dimension score is 4.4, the audio dimension score is 9.6, and the video dimension score is 2.4. The preset difference is set to 2;

[0092] Sorting the scores of each dimension from large to small, the highest dimension score is 9.6, the second highest dimension score is 4.4, and the lowest dimension score is 2.4. The difference between the highest dimension score and the second highest dimension score is 5.2, which is greater than the preset difference of 2. The user is judged to be a single type;

[0093] If the difference between the highest dimension score and the second highest dimension score is 1.6, which is less than the preset difference of 2, then it is determined that the scores of each dimension will be compared with the preset dimension scores;

[0094] The preset difference is positively correlated with the user's total learning time.

[0095] It is understandable that as the user's total learning time increases, the modules he chooses will highlight his own characteristics more. When he tends to choose more learning modules he likes, the time spent and the number of choices increase. Therefore, the preset difference is positively correlated with the user's total learning time.

[0096] Optionally, the user's total learning time is 1 hour, and the preset difference is 2;

[0097] The user's total learning time is 1.5 hours, and the preset difference is 3;

[0098] The user's total learning time is 2 hours, and the preset difference is 4.

[0099] See also Figure 4 As shown, it is a logic diagram of determining the user type based on the scores of each dimension according to an embodiment of the present invention, comparing the scores of each dimension with the preset dimension scores, wherein,

[0100] If the scores of each dimension are less than the preset dimension scores, the user is judged to be a mixed type;

[0101] If there is a single dimension score greater than or equal to the preset dimension score, the user is judged to be single type:

[0102] If there are two dimension scores that are greater than or equal to the preset dimension scores, the user is judged to be a mixed type;

[0103] If the scores of each dimension are greater than or equal to the preset dimension scores, the user is judged to be a mixed type:

[0104] In a specific embodiment, the preset dimension score is set to 5. If the text dimension score is 4.4, the audio dimension score is 2.3, and the video dimension score is 2.4, all of which are lower than the preset dimension score, the user is determined to be a mixed type.

[0105] If the text dimension score is 6.4, the audio dimension score is 2.3, and the video dimension score is 2.4, and the text dimension score of 6.4 is greater than the preset dimension score, then the user is determined to be single type:

[0106] If the text dimension score is 6.4, the audio dimension score is 7.3, and the video dimension score is 2.4, and the text dimension score and the audio dimension score are greater than the preset dimension score, the user is determined to be a mixed type;

[0107] If the text dimension score is 6.4, the audio dimension score is 7.3, and the video dimension score is 6.4, all of which are greater than the preset dimension scores, the user is determined to be a mixed type:

[0108] The preset dimension scores are positively correlated with the user's total learning time.

[0109] It is understandable that as the user's total learning time increases, the number of times he chooses modules that meet his preferences and the duration of use increase, and the corresponding dimension score increases. Therefore, the preset dimension score is positively correlated with the user's total learning time.

[0110] Optionally, the user's total learning time is 1 hour, and the preset dimension score is 5;

[0111] The user's total learning time is 1.5 hours, and the preset dimension score is 8;

[0112] The user's total learning time is 2 hours, and the preset dimension score is 11.

[0113] Specifically, in step S4, the process of configuring a plurality of learning tasks for a user's single learning based on the user's single learning time and average execution time includes:

[0114] The average execution time corresponding to each learning task is added up to get the total configuration time;

[0115] Calculate the configuration time difference between the total configuration time and the single learning time;

[0116] Comparing the configured time difference with the preset configured time difference, and configuring a number of learning tasks for the user's single learning according to the comparison result;

[0117] In a specific embodiment, the preset configuration time difference is set to 1 minute. If the configuration time difference is 0.6 minutes, which is smaller than the preset time difference, the configuration is determined to be successful.

[0118] If the time difference is 1.3 minutes and is greater than the preset time difference, it is determined to be reconfigured.

[0119] The preset configuration time difference is positively correlated with the user's single learning time.

[0120] It is understandable that the longer the user's single learning time is and the more learning tasks are performed, the greater the difference between each learning task combination and the single learning time will be. Therefore, the preset configuration time difference is positively correlated with the user's single learning time.

[0121] Optionally, the user's single learning time is 1 hour, and the preset configuration time difference is 1 minute;

[0122] The user's single learning time is 1.5 hours, and the preset configuration time difference is 3 minutes;

[0123] The user's single learning time is 2 hours, and the preset configuration time difference is 5 minutes.

[0124] Specifically, in step S4, several single completion degrees of each learning task in each single learning are counted, and a task forgetting curve is generated by combining the time interval of each single learning and the corresponding single completion degree.

[0125] It can be understood that the task forgetting curve is generated with the time interval of each single learning as the horizontal axis and the corresponding single completion degree as the vertical axis.

[0126] Specifically, in step S4, the process of matching and executing the task completion model to generate the task execution log for the user in combination with the different categories and average completion degree of the user includes:

[0127] Collect the classification of each user and the average completion degree of each learning task in the completed learning classification model;

[0128] Matching a task completion model consistent with the user's classification and average completion in the learning task database;

[0129] Record the user's completion of the task completion model to generate a task execution log;

[0130] The task completion model includes the classification of each user and the corresponding completed learning tasks.

[0131] Specifically, the present invention combines different classifications and average completion degrees of users, matches the task completion models completed by past users with the same classification and average completion degree as the user in the learning task database, and uses the learning experience of past users to guide the current user. Each user has unique learning characteristics and levels. By classifying users and calculating the average completion degree, past users similar to the current user can be found more accurately. The task completion models of these past users are formed based on their actual learning experience, and can provide personalized learning paths and method suggestions for current users to meet the specific needs of current users and improve the pertinence and effectiveness of learning. Past users have accumulated successful experience and methods in the process of completing tasks, and current users can directly learn from them. By referring to the task completion models of past users, users can quickly find a learning method that suits them, which can save a lot of time and energy, allowing current users to use learning resources more efficiently, focus on knowledge learning and ability improvement, and reduce wasted time. By analyzing the task completion models of past users and the feedback of current users, we can understand the needs and adaptation of different types of users to learning tasks, which helps to optimize the design of learning tasks. Different users may adopt different methods and strategies when facing the same task. By drawing on the experience of multiple past users, current users can broaden their learning ideas, learn to view and solve problems from different angles, and further improve the accuracy of database task configuration.

[0132] Specifically, in step S5, a time series analysis algorithm is used based on the task execution log to predict the completion degree of past learning tasks to adjust the extreme points of the task forgetting curve. The time series analysis algorithm predicts the extreme points of the task forgetting curve corresponding to the past learning tasks by analyzing the completion degree and execution time of the past learning tasks. The extreme points are the points with the largest curvature on the task forgetting curve.

[0133] Specifically, in step S5, based on the completed adjusted task forgetting curve, the time ratio of the new learning task and the past learning task is reduced at the extreme point. The single learning time includes the time to execute the new learning task and the time to execute the past learning task. The time ratio is the ratio of the time taken by the user to execute the new learning task to the time taken by the user to execute the past learning task.

[0134] It can be understood that at the time point corresponding to the extreme point, the time ratio of the new learning task to the past learning task is reduced by reducing the new learning task and increasing the past learning task in a single learning.

[0135] Specifically, the present invention adjusts the user's task forgetting curve by collecting parameters in the user's learning process, and dynamically adjusts the learning task for the user. Each user has different learning rhythm, forgetting speed and knowledge mastery. By collecting parameters in the learning process, such as learning time, answering accuracy, review times, weak points in knowledge mastery, etc., we can deeply understand the user's learning characteristics and status. Adjusting the task forgetting curve based on these parameters can more accurately grasp the user's forgetting rules of knowledge, thereby dynamically adjusting the learning task to make it accurately match the user's current learning needs, improve the pertinence and effectiveness of learning, and arrange learning tasks according to the adjusted task forgetting curve. When the user is about to forget the knowledge point, it can review and consolidate it in time, avoid forgetting a large amount of knowledge, and reasonable task Task arrangement can reduce the time users spend on repeatedly learning the knowledge they have already mastered, scientifically predict the task forgetting curve, and conduct targeted review and learning task arrangements according to the user's forgetting patterns, which helps to transform short-term memory into long-term memory. By reviewing and applying knowledge points multiple times at appropriate time points, users can grasp knowledge more firmly, reduce forgetting, improve knowledge retention, and lay a solid foundation for subsequent learning and application. Dynamically adjusting learning tasks according to the user's learning situation can avoid the waste of learning resources. For content that users have already mastered, the allocation of related resources can be reduced, and for the parts that users need to strengthen, more high-quality resources can be provided. This can improve the utilization efficiency of learning resources, make limited resources more reasonably allocated, and further improve the accuracy of database task configuration.

[0136] Specifically, in step S6, the learning tasks are divided into special learning tasks and general learning tasks according to the completion status of the learning tasks, and the general learning tasks are divided into hot tasks and cold tasks. The process of generating a task completion model by combining past learning tasks and hot tasks includes:

[0137] Classify the learning tasks that users have not completed in a single learning session into special learning tasks. The learning task database pushes relevant information about special learning tasks to users based on their classification.

[0138] The learning tasks completed by the user in a single learning session are divided into general learning tasks, and the general learning tasks are judged as hot and cold tasks based on the completion time;

[0139] A single allocation method is used for hot tasks, and a mixed allocation method is used for cold tasks;

[0140] Select learning tasks that have the same past learning tasks and hot tasks to generate task completion models.

[0141] It is understandable that when the user's classification is single type, the learning task related materials are pushed according to the corresponding classification, and when the user's classification is mixed type, the learning task related materials are pushed according to the corresponding mixed classification.

[0142] It can be understood that when the user is of a mixed type, the single-type allocation method for hot tasks is to select the single type with the highest dimension score to push learning task-related materials. When the user is of a single type, the mixed-type allocation method for cold tasks is to use a mixed type of vision, hearing, and reading and writing to push learning task-related materials.

[0143] Specifically, the present invention marks learning tasks according to their completion status, adopts different types of distribution methods for related materials for learning tasks of different popularity, and enables users to effectively handle different learning tasks through various task distribution methods. Learning tasks of different popularity may have different learning focuses and difficulties. Through marking and targeted material distribution, users can understand the characteristics of the tasks more clearly and obtain learning materials suitable for the tasks. Various task distribution methods can adapt to the learning styles and preferences of different users. Some users like to learn by reading text materials, while others prefer to watch videos or participate in practical operations. Different types of materials are distributed according to the completion of tasks. After marking the popularity of the task, the order of learning tasks can be arranged according to the popularity and logical relationship of knowledge, and corresponding materials can be allocated. For popular basic tasks, basic knowledge materials are provided first to guide users to lay a solid foundation; for subsequent popular advanced tasks, more in-depth and comprehensive materials are provided to help users gradually build a complete knowledge system and achieve systematic learning. Appropriate material allocation and diverse task allocation methods can allow users to feel the orderliness and convenience of learning during the learning process. Users do not need to spend a lot of time looking for and screening materials, and can focus more on the learning content itself, reducing troubles and obstacles in the learning process, improving the overall learning experience, making the learning process smoother and more efficient, and further improving the accuracy of database task configuration.

[0144] Thus far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art may make equivalent changes or substitutions to the relevant technical features, and the technical solutions after such changes or substitutions will fall within the scope of protection of the present invention.

Claims

1. A database task configuration method, characterized in that: include: Collecting the execution time, completion degree, and execution times of each learning task completed by several users to generate execution data of each learning task, wherein the execution data includes the average execution time, average completion degree, and average execution times of each learning task; Incorporating the average degree of completion and the average number of executions into a plurality of learning tasks to construct a plurality of learning classification models, and selecting an optimal learning classification model; Classifying the users into single type and mixed type according to the users' performance on the optimal learning classification model; Based on the user's single learning time and the average execution time, the user is configured with a number of learning tasks for single learning, the single completion rate of each learning task is counted to generate a task forgetting curve, and based on the different categories of the user and the average completion rate, the task completion model is matched and executed for the user to generate a task execution log; Adjusting the task forgetting curve using a time series analysis algorithm based on the task execution log to adjust the time ratio of the newly added learning task to the previous learning task; Dividing the learning tasks into special learning tasks and general learning tasks according to the completion status of the learning tasks, dividing the general learning tasks into hot tasks and cold tasks, and generating the task completion model by combining the past learning tasks and the hot tasks; The process of classifying the users into the single type and the mixed type according to the execution of the optimal learning classification model by the users includes: Counting the memory occupied by text, audio, and video in each learning task in the optimal learning classification model; Allocating each of the learning tasks to different learning modules according to the task classification corresponding to the maximum value of the memory size; Calculating dimension scores based on how the user uses each of the learning modules in the optimal learning classification model, and classifying the user into the single type and the mixed type according to the dimension scores; The task categories include visual, auditory and reading and writing types. The single type refers to users with only one of the task categories. The mixed type refers to users with two or more of the task categories. The learning modules include text modules, audio modules and video modules.

2. The database task configuration method according to claim 1, characterized in that: The process of calling a plurality of the learning tasks to construct a plurality of learning classification models in combination with the average degree of completion and the average number of executions, and selecting the optimal learning classification model includes: In combination with the average degree of completion and the average number of executions, calling a plurality of the learning tasks to construct a plurality of learning classification models; Calculating the estimated execution time of each of the learning classification models based on the average execution time; The optimal learning classification model is selected based on the user's single learning time and the estimated execution time.

3. The database task configuration method according to claim 2, characterized in that: A process of calculating dimension scores based on the user's use of each learning module in the optimal learning classification model and classifying the user into the single type and the mixed type according to the dimension scores includes: Counting the number of times the user selects different learning modules and the duration of their use in the optimal learning classification model; Calculate the dimension scores based on the number of selections and the usage duration, and sort the dimension scores; The user is determined to be the single type based on the difference between the highest dimension score and the second highest dimension score, or each dimension score is compared with a preset dimension score.

4. The database task configuration method according to claim 3, characterized in that: The process of configuring the plurality of learning tasks for a single learning of the user based on the single learning time of the user and the average execution time includes: Adding up the average execution time corresponding to each learning task to obtain the total configuration time; Calculating a configuration time difference between the total configuration time and the single learning time; Comparing the configured time difference with a preset configuration time difference, and configuring a plurality of learning tasks for the user to learn in a single session according to the comparison result; The preset configuration time difference is positively correlated with the user's single learning time.

5. The database task configuration method according to claim 4, characterized in that: The task forgetting curve is generated by counting the single completion degrees of each learning task in each single learning session, and combining the time intervals of each single learning session and the corresponding single completion degrees.

6. The database task configuration method according to claim 5, characterized in that: The process of matching and executing a task completion model for the user and generating a task execution log based on the different categories of the user and the average completion degree includes: Collecting the classification of each user and the average degree of completion of each learning task in the learning classification model; Matching the task completion model consistent with the user classification and the average completion degree in a learning task database; Recording the user's completion of the task completion model to generate the task execution log; The task completion model includes the classification of each user and the corresponding completed learning tasks.

7. The database task configuration method according to claim 6, characterized in that: Based on the task execution log, the time series analysis algorithm is used to predict the completion degree of the past learning task to adjust the extreme point of the task forgetting curve. The time series analysis algorithm predicts the extreme point of the task forgetting curve corresponding to the past learning task by analyzing the completion degree and execution time of the past learning task. The extreme point is the point with the largest curvature on the task forgetting curve.

8. The database task configuration method according to claim 7, characterized in that: According to the adjusted task forgetting curve, the time ratio of the newly added learning task to the past learning task is reduced at the extreme point. The single learning time includes the time to execute the newly added learning task and the time to execute the past learning task. The time ratio is the ratio of the time taken by the user to execute the newly added learning task to the time taken by the user to execute the past learning task.

9. The database task configuration method according to claim 8, characterized in that: The process of dividing the learning tasks into special learning tasks and general learning tasks according to the completion status of the learning tasks, dividing the general learning tasks into hot tasks and cold tasks, and combining the past learning tasks and the hot tasks to generate the task completion model includes: Classifying the uncompleted learning tasks of the user in the single learning as special learning tasks, and the learning task database pushes relevant information of the special learning tasks to the user according to the classification of the user; Classifying the learning tasks completed by the user in the single learning session into general learning tasks, and determining whether the general learning tasks are hot or cold tasks based on the completion time; A single allocation method is adopted for the hot tasks, and a mixed allocation method is adopted for the cold tasks; A learning task that is the same as the past learning task and the hot task is selected to generate the task completion model.

Images