Learning scheme adjustment method and device, equipment and storage medium

Abstract

The invention provides a learning scheme adjustment method and device, equipment and a storage medium, and relates to the field of computers.The method comprises the steps that executed data of a user for a target learning scheme is obtained; determining a target execution capability of the user on the target learning scheme based on the executed data; and adjusting the target learning scheme based on the target execution capability. The target execution capability of the user can be determined based on the executed data of the user in the process of executing the target learning scheme by the user, so that the target learning scheme is dynamically adjusted according to the actual target execution capability of the user, the adjusted target learning scheme is more suitable for the actual situation of the user, and the user experience is improved. And the flexibility of generating the target learning scheme is improved.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and particularly to a method, device, equipment and storage medium for adjusting a learning plan. Background Art

[0002] In recent years, with the rapid development of artificial intelligence and intelligent devices, a large number of devices or applications with learning or competitive functions have emerged, such as Go robots, chess robots, vocabulary learning applications, and various learning machines.

[0003] Currently, these devices and applications can provide specific learning functions for users and formulate learning goals and learning plans for a certain period according to the needs of users. Users only need to follow the learning plans provided by the devices or applications to complete specific learning tasks.

[0004] However, the flexibility of generating the learning plan in the above process is poor. Summary of the Invention

[0005] The present invention provides a method, device, equipment and storage medium for adjusting a learning plan to solve the defect that the flexibility of generating the learning plan in the prior art is poor, and to improve the flexibility of generating the learning plan.

[0006] The present invention provides a method for adjusting a learning plan, including: Obtaining the executed data of the user for the target learning plan; Based on the executed data, determining the target execution ability of the user for the target learning plan; Based on the target execution ability, adjusting the target learning plan.

[0007] According to the method for adjusting a learning plan provided by the present invention, the determining the target execution ability of the user for the target learning plan based on the executed data includes: Based on the correspondence between the execution data and the execution ability, determining the target execution ability corresponding to the executed data.

[0008] According to the method for adjusting a learning plan provided by the present invention, the executed data includes the target completion degree, the target execution duration and the target completion quality of the target learning plan; The determining the target execution ability of the user for the target learning plan based on the executed data includes: Based on the correspondence between the completion degree and the score, determining the first score corresponding to the target completion degree; Based on the correspondence between the execution duration and the score, determining the second score corresponding to the target execution duration; Determine the third score corresponding to the target completion quality based on the correspondence between the completion quality and the score; Perform a weighted average of the first score, the second score, and the third score to obtain a target score; Determine the target execution ability corresponding to the target score based on the correspondence between the score and the execution ability.

[0009] According to an adjustment method of a learning plan provided by the present invention, the target learning plan includes an execution duration and a target learning level; Adjusting the target learning plan based on the target execution ability includes: When the level of the target execution ability is the first level, shorten the execution duration and / or increase the target learning level; When the level of the target execution ability is the second level, extend the execution duration and / or lower the target learning level, where the second level is lower than the first level.

[0010] According to an adjustment method of a learning plan provided by the present invention, the target learning plan includes learning content; Adjusting the target learning plan based on the target execution ability includes: Generate a prompt message based on the target execution ability and the learning content, where the prompt message is used to instruct a large language model to adjust the learning content based on the target execution ability; Input the prompt message into the large language model to obtain the adjusted learning content output by the large language model.

[0011] According to an adjustment method of a learning plan provided by the present invention, the method further includes: Obtain the user's current learning level; Determine the current test questions based on the current learning level; Obtain the user's answer results for the current test questions; Input the answer results and user requirement information into the large language model to obtain the target learning plan output by the large language model, where the user requirement information includes the user's expected learning level and expected execution duration.

[0012] According to an adjustment method of a learning plan provided by the present invention, the target learning plan is a learning plan for board games.

[0013] The present invention also provides an adjustment device for a learning plan, including: An acquisition module for acquiring the executed data of the user for the target learning plan; A determination module, configured to determine the target execution ability of the user for the target learning plan based on the executed data; An adjustment module, configured to adjust the target learning plan based on the target execution ability.

[0014] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the adjustment method of the learning plan as described in any one of the above is implemented.

[0015] The present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the adjustment method of the learning plan as described in any one of the above is implemented.

[0016] The present invention also provides a computer program product, including a computer program. When the computer program is executed by a processor, the adjustment method of the learning plan as described in any one of the above is implemented.

[0017] The adjustment method, device, equipment, and storage medium of the learning plan provided by the present invention obtain the executed data of the user for the target learning plan, and based on the executed data, determine the target execution ability of the user for the target learning plan. Then, based on the target execution ability, the target learning plan is adjusted. Since the target execution ability of the user can be determined based on the executed data of the user during the execution of the target learning plan, the target learning plan can be dynamically adjusted according to the actual target execution ability of the user, making the adjusted target learning plan more in line with the actual situation of the user and improving the flexibility of generating the target learning plan. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0019] Figure 1 It is one of the flowcharts of the adjustment method of the learning plan provided by the embodiment of the present invention.

[0020] Figure 2 It is another flowchart of the adjustment method of the learning plan provided by the embodiment of the present invention.

[0021] Figure 3 It is a third flowchart of the adjustment method of the learning plan provided by the embodiment of the present invention.

[0022] Figure 4The structural schematic diagram of the learning plan adjustment device provided by the embodiment of the present invention.

[0023] Figure 5 The physical structure schematic diagram of an electronic device provided by the embodiment of the present invention. Detailed implementation manners

[0024] To make the objectives, technical solutions and advantages of the present invention clearer, the technical solutions in the present invention will be clearly and completely described below with reference to the accompanying drawings in the present invention. Apparently, the described embodiments are some but not all of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present invention without making creative efforts shall fall within the protection scope of the present invention.

[0025] The terms "first", "second", etc. in the specification and claims of the present invention and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that such terms can be interchanged under appropriate circumstances, which is only a way of distinguishing objects with the same attributes when describing the embodiments of the present invention. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion, so that a process, method, system, product or device comprising a series of units does not have to be limited to those units, but may include other units not explicitly listed or inherent to these processes, methods, products or devices.

[0026] Currently, for some devices or applications with learning functions, users can set learning plans by themselves, or the devices formulate learning goals and learning plans for a certain period according to the users' needs. However, there are certain limitations in the setting and execution methods of existing learning devices or applications. For example, a go robot or a vocabulary memorization application usually generates a learning plan according to the goals initially set by the user or a preset generation method, and strictly follows the generated plan during the execution process. Although this method can provide users with a clear learning path, in actual applications, there are significant differences in the self-control and learning abilities of different users. For users with strong self-control, they can better execute the learning plan and achieve the goals, but the relatively low goal setting may not fully utilize their potential. For users with limited self-control, they may give up halfway when executing the learning plan, resulting in unsatisfactory learning effects.

[0027] Once the learning plan is set in the prior art, it will not be adjusted anymore. This method cannot meet the personalized needs of different users, resulting in an inflexible learning plan generation method.

[0028] In view of the above problems, an embodiment of the present invention provides a method for adjusting a learning plan. In this method, after formulating a learning plan, the executed data of the user during the execution of the learning plan can be continuously obtained to determine the user's execution ability, and the learning plan can be dynamically adjusted according to the user's execution ability. In the above manner, the learning plan can be dynamically adjusted and optimized based on the user's execution situation, so that the adjusted learning plan can better conform to the actual situation of the user, and the flexibility of generating the learning plan is improved.

[0029] The following will describe Figures 1 to 3 the method for adjusting the learning plan provided by the embodiment of the present invention. The embodiment of the present invention can be applied to scenarios where learning is carried out by formulating a learning plan for the user, such as learning vocabulary, Go learning, or chess learning. The execution subject of this method can be various devices with learning functions, or various devices installed with application programs with learning functions, such as Go robots, chess robots, servers, server clusters, or specially designed learning plan adjustment devices and other electronic devices, or it can also be a learning plan adjustment device set in the electronic device, and the learning plan adjustment device can be implemented by software, hardware, or a combination of both.

[0030] Figure 1 One of the flow diagrams of the method for adjusting the learning plan provided by the embodiment of the present invention is shown in Figure 1 as follows. The method includes: Step 101: Obtain the executed data of the user for the target learning plan.

[0031] In this step, the target learning plan includes the ultimate goal to be achieved and the specific content required to achieve the ultimate goal. For example, if the user is a beginner in Go and the goal to be achieved is to be promoted to the second dan within six months, in one implementation, the Go robot can automatically generate a six-month user-machine practice plan for the user according to the user's current dan level and the goal to be achieved as the target learning plan. The target learning plan can include the daily or weekly practice duration, the difficulty of the game, or specific chess game training, etc. In another implementation, the user can also customize a six-month user-machine practice plan as the target learning plan according to their own learning habits and preferences. For example, the user can set to increase the training intensity in certain stages, or extend the training duration in a certain time period, etc. Among them, in the above target learning plan, the ultimate goal to be achieved is to be promoted to the second dan, and the user-machine practice plan is the specific content to be executed.

[0032] After formulating the target learning plan, the executed data of the user during the execution of the target learning plan will be continuously obtained. Among them, the executed data includes the plan data that the user has executed for the specific content in the target learning plan, such as execution progress, learning effect, completion duration, and completion quality, etc. For example, for a 6-month user-computer practice plan, the user has executed it for 1 month, the completion rate is 80%, and the execution duration is 130 minutes, etc.

[0033] In the specific implementation process, the executed data of the user during the execution of the target learning plan can be collected in real time or periodically through sensors, log records, or user input, etc. In addition, as the target learning plan continues to be executed, there will be more executed data, so that the target execution ability of the user can be better determined based on this executed data, providing a better basis for the adjustment of the subsequent target learning plan.

[0034] Step 102: Determine the target execution ability of the user for the target learning plan based on the executed data.

[0035] In this step, the target execution ability of the user for the target learning plan can be understood as the completion situation after the user learns according to the specific content in the target learning plan. It can be represented by several levels such as strong, medium, and weak execution ability, or it can be scored based on the executed data, and the target execution ability of the user can be characterized by the final score.

[0036] In practical applications, after obtaining the executed data of the user for the target learning plan, the executed data can be first cleaned, removing outliers, duplicate data, and invalid data, and then the target execution ability can be obtained by analyzing the cleaned data.

[0037] Exemplarily, the corresponding relationship between the executed data and the execution ability can be preset. By looking up the above corresponding relationship, the target execution ability corresponding to the current executed data can be quickly determined. It can also be through a deep learning algorithm. By pre-training an execution ability determination model and inputting the current executed data into the pre-trained execution ability determination model, the target execution ability can be obtained. Among them, the deep learning algorithm can, for example, include Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), or Long Short-Term Memory (LSTM), etc. Of course, the current executed data can also be input into a large language model, and by inputting prompt words, the large language model can be used to determine the target execution ability of the user for the target learning plan.

[0038] The target execution ability can characterize the performance and ability of the user during the execution of the target learning plan. If the determined target execution ability is strong, it means that the user can execute the preset target learning plan well. If the determined target execution ability is weak, it means that the user does not execute according to the specific content in the target learning plan.

[0039] Step 103: Adjust the target learning plan based on the target execution ability.

[0040] In this step, after determining the target execution ability of the user, the target learning plan can be dynamically adjusted according to the target execution ability. For example, if the user's target execution ability is strong, the final learning goal in the target learning plan can be increased, or the daily learning task volume can be increased, or the learning duration can be shortened. If the user's target execution ability is weak, the final learning goal can be decreased, or the daily learning task volume can be decreased, or the learning duration can be extended, etc.

[0041] After adjusting the target learning plan, the adjusted target learning plan can be output to the user. In this way, the user can perform subsequent learning based on the adjusted target learning plan. During the subsequent learning process, new executed data of the user for the adjusted target learning plan can also be continuously obtained, and the new target execution ability of the user can be determined according to the new executed data, so as to continuously optimize and adjust the target learning plan, making the finally adjusted target learning plan gradually approach the user's actual learning ability.

[0042] In addition, after outputting the adjusted target learning plan, the user can also manually optimize the adjusted target learning plan according to their own needs, such as reducing the training difficulty in their weak aspects or increasing the daily learning task volume, etc., so that the finally obtained target learning plan better meets the user's own needs and makes the target learning plan more personalized.

[0043] The learning plan adjustment method provided by the embodiments of the present invention determines the target execution ability of the user for the target learning plan by obtaining the executed data of the user for the target learning plan and based on the executed data, and then adjusts the target learning plan based on the target execution ability. Since the target execution ability of the user can be determined based on the executed data of the user during the execution of the target learning plan, the target learning plan can be dynamically adjusted according to the actual target execution ability of the user, making the adjusted target learning plan more in line with the actual situation of the user and improving the flexibility of generating the target learning plan.

[0044] Exemplarily, based on the above embodiments, the target execution ability of the user for the target learning plan can be determined in the following two ways: In a possible implementation, the target execution capability corresponding to the executed data can be determined based on the correspondence between the execution data and the execution capability.

[0045] Specifically, the executed data of multiple sample users during the execution of the target learning plan can be collected in advance, and the execution capabilities corresponding to different executed data can be determined by means of manual analysis or deep learning model analysis. For example, for a Go learning plan in which users practice human-computer interaction and are finally upgraded to the second dan within 6 months, after multiple sample users have all executed the plan, the executed data of these sample users can be collected one month later. For example, the executed data of sample user a includes a task completion rate of 80% and an execution time of 130 minutes, the executed data of sample user b includes a task completion rate of 100% and an execution time of 60 minutes, and the executed data of sample user c includes a task completion rate of 100% and an execution time of 30 minutes.

[0046] After manual analysis, it is found that the execution time of sample user a is relatively long and the task is not completed, so the execution capability of sample user a can be set to weak. The task of sample user b has been completed and the time is within a reasonable range, so the execution capability of sample user a can be set to medium. The execution time of sample user c is short and the task has been completed, so the execution capability of sample user c can be set to strong.

[0047] After analyzing the execution data of multiple sample users and setting the corresponding execution capabilities, the correspondence between the execution data and the execution capabilities can be established. Therefore, when determining the target execution capability of a user subsequently, the set correspondence can be directly queried to determine the target execution capability corresponding to the executed data, thereby improving the efficiency of determining the target execution capability.

[0048] In another possible implementation, the above-mentioned executed data includes the target completion degree, target execution duration, and target completion quality of the target learning plan. When determining the target execution capability of the user for the target learning plan based on the executed data, the first score corresponding to the target completion degree can be determined based on the correspondence between the completion degree and the score, the second score corresponding to the target execution duration can be determined based on the correspondence between the execution duration and the score, the third score corresponding to the target completion quality can be determined based on the correspondence between the completion quality and the score, and the first score, the second score, and the third score are weighted and averaged to obtain the target score. Then, based on the correspondence between the score and the execution capability, the target execution capability corresponding to the target score is determined.

[0049] Specifically, the target completion degree of the target learning plan can be understood as the proportion of the preset tasks in the target learning plan completed by the user within the specified time. For example, if the target learning plan stipulates memorizing 100 words in the previous month and the user only memorizes 60 words, the target completion degree is 60%. The target execution duration can be understood as the total duration actually invested by the user in learning, and the target completion quality can be understood as the effect or success of the user in completing the task, which can usually be measured by indicators such as the correct rate, winning rate, or score.

[0050] In addition, it is necessary to pre-set the corresponding relationship between the completion degree and the score. The higher the completion degree, the higher the score, indicating that more tasks are completed. When the target completion degree is included in the obtained executed data, by querying the corresponding relationship between the completion degree and the score, the first score corresponding to the target completion degree can be obtained. It is also possible to set the corresponding relationship between the execution duration and the score. The shorter the execution duration, the higher the score, indicating that the user is more focused and has higher execution ability when completing the task. When the target execution duration is included in the obtained executed data, by querying the corresponding relationship between the execution duration and the score, the second score corresponding to the target execution duration can be obtained. It is also possible to set the corresponding relationship between the completion quality and the score. The higher the completion quality, the higher the score, indicating that the user has better results in completing the task. When the target completion quality is included in the obtained executed data, by querying the corresponding relationship between the completion quality and the score, the third score corresponding to the target completion quality can be obtained.

[0051] In order to more accurately reflect the importance of parameters in different dimensions for evaluating the overall execution ability of the user and avoid deviation in the evaluation results, it is usually possible to set the respective weights corresponding to the completion degree, execution duration, and completion quality. Among them, these three weights can be the same or different. For example, the weights of the completion degree and the completion quality can be set higher, while the weight of the execution duration can be set lower, etc. Of course, the size of the weight can also be flexibly adjusted according to the dimension that the user focuses on. If it is necessary to focus on the learning effect of the user, the completion quality is more important than the execution duration. Therefore, the weight of the completion quality will be set larger. If it is necessary to focus on the duration of the user's continuous learning, the execution duration is more important. Therefore, the weight of the execution duration will be set larger.

[0052] After determining the first score, the second score, and the third score, the three scores will be weighted and averaged according to the respective weights corresponding to the completion degree, execution duration, and completion quality to obtain the target score.

[0053] By querying the pre-set correspondence between scores and execution capabilities, the target execution capability corresponding to the target score can be determined. For example, it can be pre-set that when the score is between 70 and 100, the corresponding execution capability is strong; when the score is between 50 and 79, the corresponding execution capability is medium; when the score is between 0 and 49, the corresponding execution capability is weak, etc.

[0054] In this embodiment, after calculating the scores corresponding to the target completion degree, target execution duration, and target completion quality respectively, and performing a weighted average on the scores, the target execution capability of the user is determined based on the finally obtained target score. This method can evaluate the user's target execution capability from multiple dimensions, and through the weighted average method, it can avoid the phenomenon that the scores of other dimensions are ignored due to the excessive score of a certain dimension, thereby improving the accuracy of the determined target execution capability.

[0055] Figure 2 This is the second flowchart of the adjustment method for the learning plan provided by the embodiment of the present invention. Based on the embodiment shown in Figure 1 when the target learning plan includes the execution duration and the target learning level, the process of how to adjust the target learning plan based on the target execution capability will be introduced in detail. As shown in Figure 2 the method includes: Step 201: Obtain the executed data of the user for the target learning plan.

[0056] Exemplarily, the target learning plan can include a learning plan for board games such as Go, Chinese chess, or Five-in-a-Row, or can also include other types of learning plans such as English or mathematics learning plans.

[0057] During the process of the user executing the target learning plan, the executed data of the user is obtained through sensors, log records, or user input, etc.

[0058] Step 202: Determine the target execution capability of the user for the target learning plan based on the executed data.

[0059] In this step, after obtaining the executed data, by querying the correspondence between the execution data and the execution capability, the target execution capability corresponding to the executed data can be determined, or by using a pre-trained execution capability determination model, the executed data is input into the execution capability determination model, and thus the target execution capability output by the execution capability determination model can be obtained.

[0060] Step 203: In the case where the level of the target execution capability is the first level, shorten the execution duration and / or increase the target learning level.

[0061] In this step, the target learning plan includes the execution duration and the target learning level. The execution duration can include the total duration when the user executes the specific content in the target learning plan. For example, it can be the total duration of practicing Go within one month. The target learning level is the final target level to be achieved. For example, reaching the second dan level of Go after six months, or it can also be the phased target in the target learning plan, such as completing 30 duels within one month.

[0062] Among them, the first level is used to represent that the user has strong learning ability or strong execution ability. The user can complete the learning tasks well and achieve good learning results. This first level can be, for example, strong execution ability.

[0063] When it is determined that the level of the user's target execution ability is the first level, it indicates that the user has strong execution ability in executing the target learning plan and can complete the learning tasks efficiently. Therefore, the execution duration can be shortened. For example, adjusting the original plan of reaching the second dan level of Go in six months to reaching it in four months, or the target learning level can be improved. For example, adjusting the original plan of reaching the second dan level of Go in six months to reaching the third dan level of Go in six months. It can also both shorten the execution duration and improve the target learning level.

[0064] Step 204: When the level of the target execution ability is the second level, extend the execution duration and / or lower the target learning level.

[0065] Among them, the second level is lower than the first level.

[0066] In this step, the second level is used to represent that the user has weak learning ability or weak execution ability. The user may have certain difficulties in executing the target learning plan. This second level can be, for example, weak execution ability.

[0067] When it is determined that the level of the user's target execution ability is the second level, it indicates that the user has weak execution ability in executing the target learning plan and cannot complete the learning tasks on time. Therefore, the execution duration can be extended. For example, adjusting the original plan of reaching the second dan level of Go in six months to reaching it in eight months, or the target learning level can be lowered. For example, adjusting the original plan of reaching the second dan level of Go in six months to reaching the first dan level of Go in six months. It can also both extend the execution duration and lower the target learning level.

[0068] In addition, when the level of the user's target execution ability is medium, that is, the target learning plan can be executed on time, and both the execution duration and the completion quality are within a reasonable range, it can be considered not to adjust the target learning plan.

[0069] In this embodiment, by determining the level of the user's target execution ability and dynamically adjusting the execution duration and / or the target learning level in the target learning plan according to different levels, the purpose of flexibly adjusting the learning plan according to the user's actual learning ability can be achieved, so that the adjusted target learning plan meets the user's personalized needs, improving the user's learning effect and user satisfaction.

[0070] Figure 3 FIG. 3 is a schematic flowchart of the method for adjusting the learning plan provided by the embodiment of the present invention. On the basis of the embodiment shown in Figure 1 FIG. 6, when the target learning plan includes learning content, the process of how to adjust the target learning plan based on the target execution ability will be introduced in detail. As Figure 3 shown, the method includes: Step 301: Obtain the executed data of the user for the target learning plan.

[0071] Step 302: Based on the executed data, determine the target execution ability of the user for the target learning plan.

[0072] Step 303: Generate a prompt message based on the target execution ability and the learning content, where the prompt message is used to instruct the large language model to adjust the learning content based on the target execution ability.

[0073] In this step, the learning content includes specific learning tasks, such as the content of Go game practice, the word list to be memorized, math exercises, etc.

[0074] According to the currently determined target execution ability of the user and the specific learning content in the target learning plan, a prompt message can be constructed. For example, the prompt message may include "The user's target execution ability is relatively strong. The current learning content is Go game practice with a primary difficulty level. Please adjust the current learning content according to the user's target execution ability to increase the learning difficulty."

[0075] Step 304: Input the prompt message into the large language model to obtain the adjusted learning content output by the large language model.

[0076] In this step, the constructed prompt message is input into the large language model. Through semantic understanding and analysis of the prompt message by the large language model, the adjusted learning content is output. For example, the adjusted learning content includes "Increase the number of Go game practice sessions with an intermediate difficulty level", etc.

[0077] In this embodiment, after determining the user's target execution ability, a prompt message can be constructed based on the target execution ability and the learning content in the target learning plan. Then, the large language model can adjust the learning content based on the prompt message. Since the understanding ability of the large language model is utilized, a target learning plan that better meets the user's needs can be generated, improving the flexibility of generating the target learning plan.

[0078] Exemplarily, based on the above embodiments, when determining the target learning plan, the current learning level of the user can be obtained, the current test questions can be determined based on the current learning level, and after obtaining the user's answering results for the current test questions, the answering results and the user requirement information can be input into the large language model to obtain the target learning plan output by the large language model. The user requirement information includes the user's expected learning level and expected execution duration.

[0079] Specifically, the user's current learning level can include the user's level or ability in the current learning field, such as the current Go rank, English level, etc. For example, the user's current learning level can be evaluated through the user's historical learning data, which includes completed tasks or test scores. The current learning level can also be obtained by the user's input.

[0080] To more accurately determine the user's actual learning situation at the current learning level, after obtaining the user's current learning level, current test questions can be generated and output through the display interface. For example, for a beginner Go user, Go questions for the beginner rank can be generated, and for an intermediate English user, test questions for intermediate vocabulary can be generated, etc.

[0081] Furthermore, the user's answering results for the current test questions can be obtained, and the answering results can be used to evaluate the user's actual learning situation. For example, if a Go user wins 3 out of 5 games, the winning rate is 60%.

[0082] When generating a target learning plan, not only the user's current actual learning situation but also the user's demand information should be considered. Among them, the user's demand information includes the user's expected learning level and expected execution duration. For example, the expected learning level is the second dan in Go, and the expected execution duration is six months. Based on the user's answer results and the user's demand information, prompt information is constructed and input into the large language model, so that the target learning plan output by the large language model can be obtained. For example, the constructed prompt information may include "The user's current learning level is primary, wins 3 out of 5 games, with a winning rate of 60%. The user's expected learning level is the second dan, and the expected execution duration is six months. Please generate a target learning plan that meets the user's needs based on the above information." By analyzing and understanding the above content, the large language model can generate a target learning plan of "Complete 180 games of Go within six months, including 60 games for the primary dan level and 120 games for the intermediate dan level, and complete 7 games per week."

[0083] In this embodiment, the current test questions can be generated based on the user's current learning level, and the user's answer results for the current test questions can be obtained. Through the answer results, the user's actual learning situation at the current learning level can be obtained, so that the target learning plan that meets the user can be determined according to the user's actual learning situation, improving the accuracy of the target learning plan.

[0084] Next, the learning plan adjustment device provided by the present invention will be described. The learning plan adjustment device described below can be correspondingly referred to the learning plan adjustment method described above.

[0085] Figure 4 It is a schematic structural diagram of the learning plan adjustment device provided by the embodiment of the present invention. Refer to Figure 4 As shown, the learning plan adjustment device 400 includes: An acquisition module 11, configured to acquire the executed data of the user for the target learning plan; A determination module 12, configured to determine the target execution ability of the user for the target learning plan based on the executed data; An adjustment module 13, configured to adjust the target learning plan based on the target execution ability.

[0086] The adjustment device for the learning plan provided by the embodiment of the present invention obtains the executed data of the user for the target learning plan, determines the target execution ability of the user for the target learning plan based on the executed data, and then adjusts the target learning plan based on the target execution ability. Since the target execution ability of the user can be determined based on the executed data of the user during the execution of the target learning plan, the target learning plan can be dynamically adjusted according to the actual target execution ability of the user, making the adjusted target learning plan more in line with the actual situation of the user and improving the flexibility of generating the target learning plan.

[0087] In an exemplary embodiment, the determining module 12 is specifically configured to: Determine the target execution ability corresponding to the executed data based on the corresponding relationship between the executed data and the execution ability.

[0088] In an exemplary embodiment, the executed data includes the target completion degree, the target execution duration, and the target completion quality of the target learning plan; The determining module 12 is specifically configured to: Determine the first score corresponding to the target completion degree based on the corresponding relationship between the completion degree and the score; Determine the second score corresponding to the target execution duration based on the corresponding relationship between the execution duration and the score; Determine the third score corresponding to the target completion quality based on the corresponding relationship between the completion quality and the score; Perform a weighted average of the first score, the second score, and the third score to obtain a target score; Determine the target execution ability corresponding to the target score based on the corresponding relationship between the score and the execution ability.

[0089] In an exemplary embodiment, the target learning plan includes an execution duration and a target learning level; the adjustment module 13 is specifically configured to: In the case where the level of the target execution ability is the first level, shorten the execution duration and / or increase the target learning level; In the case where the level of the target execution ability is the second level, extend the execution duration and / or decrease the target learning level, where the second level is lower than the first level.

[0090] In an exemplary embodiment, the target learning plan includes learning content; the adjustment module 13 is specifically configured to: Generate a prompt message based on the target execution ability and the learning content, where the prompt message is used to instruct the large language model to adjust the learning content based on the target execution ability; Input the prompt information into the large language model to obtain the adjusted learning content output by the large language model.

[0091] In an example embodiment, the device further includes: an input module, where: The acquisition module 11 is further configured to acquire the current learning level of the user; The determination module 12 is further configured to determine the current test questions based on the current learning level; The acquisition module 11 is further configured to acquire the answering result of the user for the current test questions; The input module is configured to input the answering result and the user requirement information into the large language model to obtain the target learning plan output by the large language model, where the user requirement information includes the expected learning level and the expected execution duration of the user.

[0092] In an example embodiment, the target learning plan is a learning plan for board games.

[0093] The device in this embodiment can be used to execute the method of any one of the method embodiments of the learning plan adjustment method. The specific implementation process and technical effects are similar to those in the method embodiments of the learning plan adjustment method. Specifically, reference can be made to the detailed introduction in the method embodiments of the learning plan adjustment method, which will not be elaborated here.

[0094] Figure 5 The following is a schematic physical structure diagram of an electronic device provided by an embodiment of the present invention. As Figure 5 shown, the electronic device may include: a processor 510, a communication interface 520, a memory 530, and a communication bus 540. Among them, the processor 510, the communication interface 520, and the memory 530 complete mutual communication through the communication bus 540. The processor 510 may call the logical instructions in the memory 530 to execute the learning plan adjustment method, and the method includes: acquiring the executed data of the user for the target learning plan; determining the target execution ability of the user for the target learning plan based on the executed data; and adjusting the target learning plan based on the target execution ability.

[0095] In addition, when the logical instructions in the above-mentioned memory 530 can be implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs that can store program codes.

[0096] On the other hand, the present invention also provides a computer program product. The computer program product includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the adjustment method of the learning scheme provided by the above-mentioned various methods. The method includes: obtaining the executed data of the user for the target learning scheme; based on the executed data, determining the target execution ability of the user for the target learning scheme; and based on the target execution ability, adjusting the target learning scheme.

[0097] On another aspect, the present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it realizes the adjustment method of the learning scheme provided by the above-mentioned various methods. The method includes: obtaining the executed data of the user for the target learning scheme; based on the executed data, determining the target execution ability of the user for the target learning scheme; and based on the target execution ability, adjusting the target learning scheme.

[0098] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. A person of ordinary skill in the art can understand and implement it without creative labor.

[0099] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0100] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for adjusting a learning scheme, characterized in that Including: Obtain the executed data of the user for the target learning plan; Based on the executed data, determine the target execution ability of the user for the target learning plan; Based on the target execution ability, adjust the target learning plan.

2. The method for adjusting the learning scheme according to claim 1, characterized in that The determining, based on the executed data, the target execution ability of the user for the target learning plan includes: Based on the correspondence between the execution data and the execution ability, determine the target execution ability corresponding to the executed data.

3. The method for adjusting the learning scheme according to claim 1, characterized in that, The executed data includes the target completion degree, the target execution duration, and the target completion quality of the target learning plan; The determining, based on the executed data, the target execution ability of the user for the target learning plan includes: Based on the correspondence between the completion degree and the score, determine the first score corresponding to the target completion degree; Based on the correspondence between the execution duration and the score, determine the second score corresponding to the target execution duration; Based on the correspondence between the completion quality and the score, determine the third score corresponding to the target completion quality; Perform a weighted average of the first score, the second score, and the third score to obtain a target score; Based on the correspondence between the score and the execution ability, determine the target execution ability corresponding to the target score.

4. The method for adjusting the learning scheme according to claim 1, characterized in that, The target learning plan includes an execution duration and a target learning level; The adjusting, based on the target execution ability, the target learning plan includes: In the case where the level of the target execution ability is the first level, shorten the execution duration and / or increase the target learning level; In the case where the level of the target execution ability is the second level, extend the execution duration and / or lower the target learning level, where the second level is lower than the first level.

5. The method for adjusting the learning scheme according to claim 1, characterized in that, The target learning plan includes learning content; The adjusting, based on the target execution ability, the target learning plan includes: Based on the target execution ability and the learning content, generate a prompt message for instructing a large language model to adjust the learning content based on the target execution ability; Input the prompt message into the large language model to obtain the adjusted learning content output by the large language model.

6. The method for adjusting the learning scheme according to claim 1, wherein The method further includes: Obtain the current learning level of the user; Determine the current test questions based on the current learning level; Obtain the user's answer results for the current test questions; Input the answer results and user requirement information into the large language model to obtain the target learning plan output by the large language model, where the user requirement information includes the user's expected learning level and expected execution duration.

7. The method for adjusting the learning scheme according to any one of claims 1-6, characterized in that, The target learning plan is a learning plan for board games.

8. An adjustment device for a learning scheme, characterized in that, Including: An acquisition module for acquiring the executed data of the user for the target learning plan; A determination module for determining the target execution ability of the user for the target learning plan based on the executed data; An adjustment module for adjusting the target learning plan based on the target execution ability.

9. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the adjustment method of the learning plan according to any one of claims 1 to 6.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the adjustment method of the learning scheme according to any one of claims 1 to 6.

11. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the adjustment method of the learning scheme according to any one of claims 1 to 6.

Images