Training task allocation method and device, electronic equipment and storage medium
By acquiring multimodal data of users' historical training tasks, proficiency is determined, and target training tasks are selected and assigned from the training task knowledge graph. This solves the problem of inaccurate training task assignment and achieves precise assignment of training tasks and improvement of capabilities.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-11-18
- Publication Date
- 2026-04-07
AI Technical Summary
In existing technologies, the assignment of training tasks is inaccurate, resulting in wasted user time and insufficient improvement in capabilities.
By acquiring multimodal data from users' historical training tasks, including task completion time, mouse movement trajectory, keyboard input frequency, client page switching frequency, emotional data, and physiological indicators, the user's proficiency with each knowledge point is determined, and target training tasks are selected and assigned from the training task knowledge graph based on training difficulty and proficiency.
It enables precise allocation of training tasks, enhances users' ability to grasp target knowledge points, meets personalized training difficulty requirements, and improves training effectiveness.
Smart Images
Figure CN121809883A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of artificial intelligence technology, and in particular to a training task allocation method, apparatus, electronic device, and storage medium. Background Technology
[0002] Every industry needs to assign training tasks to users to improve their skills. The accurate allocation of training tasks has a decisive impact on the training effect. If the training tasks are not allocated reasonably, it will not only waste users' time but also fail to improve their skills. Therefore, it is necessary to consider how to accurately allocate training tasks. Summary of the Invention
[0003] This invention provides a training task allocation method, apparatus, electronic device, and storage medium to solve the technical problem of how to accurately allocate training tasks to users.
[0004] This invention provides a training task allocation method, comprising: Acquire multimodal data generated by users when processing historical training tasks. The multimodal data includes at least one of the following: task completion time, mouse movement trajectory, keyboard input frequency, client page switching frequency, emotion data, and physiological indicators. The user's proficiency with each knowledge point in each of the historical training tasks is determined based on the multimodal data. Based on the set target knowledge points, each candidate training task is retrieved from the training task knowledge graph. The target training task is selected from each of the candidate training tasks based on the set training difficulty and the proficiency level. The target training task is assigned to the user.
[0005] According to a training task allocation method provided by the present invention, the step of determining the user's proficiency with each knowledge point in each of the historical training tasks based on the multimodal data includes: Based on the principle that the proficiency is negatively correlated with the task completion time, client page switching frequency, and physiological indicators corresponding to the historical training task, and the principle that the proficiency is positively correlated with the keyboard input frequency corresponding to the historical training task, the user's proficiency in each knowledge point in the historical training task is determined according to the multimodal data.
[0006] According to a training task allocation method provided by the present invention, the step of selecting a target training task from each candidate training task based on a set training difficulty and the proficiency level includes: If the training difficulty is easy, then the candidate training task in which the proficiency of all knowledge points contained therein is greater than a preset threshold is taken as the target training task.
[0007] According to a training task allocation method provided by the present invention, the step of selecting a target training task from each candidate training task based on a set training difficulty and the proficiency level includes: If the training difficulty is moderate, then the candidate training task containing some knowledge points with a proficiency level less than a preset threshold and some knowledge points with a proficiency level greater than a preset threshold will be used as the target training task.
[0008] According to a training task allocation method provided by the present invention, the step of selecting a target training task from each candidate training task based on a set training difficulty and the proficiency level includes: If the training difficulty is "difficult", then the candidate training task in which the proficiency of all knowledge points is less than a preset threshold will be used as the target training task.
[0009] According to a training task allocation method provided by the present invention, after selecting a target training task from each candidate training task based on the set training difficulty and the proficiency level, and before allocating the target training task to the user, the method further includes: If the target training task is not selected, the large language model is invoked to generate the target training task based on the target knowledge points, the training difficulty, and the proficiency level.
[0010] According to a training task allocation method provided by the present invention, the step of allocating the target training task to a user includes: The number of times each of the target training tasks has been assigned is sorted in ascending order; The target training task ranked highest among the assigned attempts will be assigned to the user.
[0011] According to a training task allocation method provided by the present invention, after allocating the target training task to the user, the method further includes: Based on the multimodal data generated by the user when processing the target training task, update the user's proficiency with each knowledge point in the target training task.
[0012] The present invention also provides a training task allocation device, comprising: The acquisition module is used to acquire multimodal data generated by the user when processing historical training tasks. The multimodal data includes at least one of the following: task completion time, mouse movement trajectory, keyboard input frequency, client page switching frequency, emotion data, and physiological indicators. The determination module is used to determine the user's proficiency with each knowledge point in each of the historical training tasks based on the multimodal data. The retrieval module is used to retrieve each candidate training task from the training task knowledge graph based on the set target knowledge points. The filtering module is used to filter out the target training task from each of the candidate training tasks based on the set training difficulty and the proficiency level. The allocation module is used to assign the target training task to the user.
[0013] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the training task allocation method as described above.
[0014] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the training task allocation method as described above.
[0015] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the training task allocation method as described above.
[0016] The training task allocation method, apparatus, electronic device, and storage medium provided by this invention determine the user's proficiency with each knowledge point based on multimodal data from the user's processing of historical training tasks. Based on the set training difficulty and the user's proficiency with each knowledge point, the target training task is selected from each candidate training task containing the target knowledge point and allocated to the user. This enables the allocated training task to train the user's ability to target knowledge points and meets the user's required training difficulty, thus achieving precise allocation of training tasks. Attached Figure Description
[0017] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.
[0018] Figure 1 This is a flowchart illustrating the training task allocation method provided by the present invention.
[0019] Figure 2 This is a schematic diagram of the training task allocation device provided by the present invention.
[0020] Figure 3 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation
[0021] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.
[0022] The following is combined with Figures 1-3 This invention describes the training task allocation method, apparatus, electronic device, and storage medium provided by the present invention.
[0023] Figure 1 This is a flowchart illustrating the training task allocation method provided by the present invention, as shown below. Figure 1 As shown, steps S1, S2, S3, S4 and S5 are included but are not limited to.
[0024] Step S1: Obtain multimodal data generated by the user when processing historical training tasks. The multimodal data includes at least one of the following: task completion time, mouse movement trajectory, keyboard input frequency, client page switching frequency, emotion data, and physiological indicators.
[0025] The training tasks of this invention are diverse, and each training task generally includes multiple knowledge points. For example, a training task can be a multiple-choice question, and the four options of the multiple-choice question may each cover a knowledge point.
[0026] It is understandable that the longer it takes a user to complete a training task, the lower their proficiency in that task is considered; conversely, the shorter it takes a user to complete a training task, the higher their proficiency in that task is considered.
[0027] Generally, users tend to move the mouse randomly and unconsciously when performing unfamiliar training tasks, while they move the mouse more consciously and deliberately when performing familiar training tasks. Therefore, if the mouse movement is chaotic, it can be assumed that the user has a low level of proficiency in the training task; if the mouse movement is orderly, it can be assumed that the user has a high level of proficiency in the training task.
[0028] Keyboard input frequency represents the speed at which a user inputs the answers to a training task. A higher keyboard input frequency indicates that the user can complete the training task proficiently, and thus has a higher level of proficiency; a lower keyboard input frequency indicates that the user cannot complete the training task proficiently, and thus has a lower level of proficiency.
[0029] The client page switching frequency is the frequency at which the user switches to the page containing the training task. This represents the frequency at which the user searches for reference materials from other pages. The higher the client page switching frequency, the more frequently the user consults reference materials, and the lower the user's proficiency with the training task.
[0030] Emotional data can include a user's facial expressions and tone of voice when performing training tasks. The more relaxed the facial expression and the smoother and more even the tone of voice, the higher the user's proficiency in the training task. The more serious the facial expression and the more hesitant and fluctuating the tone of voice, the lower the user's proficiency in the training task.
[0031] Step S2: Determine the user's proficiency with each knowledge point in each historical training task based on multimodal data.
[0032] For a specific knowledge point, you can select several recent historical training tasks that contain that knowledge point. Based on the multimodal data of each historical training task, determine the user's proficiency with that knowledge point in that historical training task. Then, calculate the average proficiency of the user with that knowledge point in each historical training task as the user's proficiency with that knowledge point.
[0033] Step S3: Based on the set target knowledge points, retrieve each candidate training task from the training task knowledge graph.
[0034] The target knowledge points are those that users need to improve their skills on. The training task knowledge graph stores a large number of training tasks, each with a label for the knowledge points it covers. Therefore, training tasks with labels containing the target knowledge points can be retrieved from the knowledge graph as candidate training tasks. The target knowledge points in the candidate training tasks can improve the user's ability to understand the target knowledge points.
[0035] Step S4: Select the target training task from the candidate training tasks based on the set training difficulty and proficiency.
[0036] Training difficulty can be categorized as easy, moderate, or difficult. If the training difficulty is easy, the user should have a high overall familiarity with the knowledge points in the target training task; if the training difficulty is moderate, the user's overall familiarity with the knowledge points in the target training task should be moderate; and if the training difficulty is difficult, the user's overall familiarity with the knowledge points in the target training task should be low. Therefore, target training tasks can be selected based on the above-mentioned facial expressions. There may be one or more selected target training tasks.
[0037] Step S5: Assign the target training task to the user.
[0038] You can assign all target training tasks to the user, or you can randomly select one or more target training tasks to assign to the user.
[0039] Furthermore, before assigning target training tasks to users, these tasks can be reviewed, including checks on knowledge consistency, language accuracy, and legal compliance. If risks are detected, tasks can be deleted or replaced to ensure a safe and controllable task assignment process. Knowledge consistency checks ensure that the target training task tags align with the knowledge graph; language accuracy checks review grammar, ambiguity, and sensitive words; and legal compliance checks assess the risk of politically sensitive, privacy-sensitive, or copyright-restricted content in accordance with the latest regulations and policies.
[0040] In addition, when a target training task is assigned to a user, an explanation of the target training task can be generated simultaneously, explaining the reasons for the recommendation and the learning objective, to help the user understand the meaning of the training.
[0041] As can be seen from the above, the training task allocation method of the present invention determines the user's proficiency with each knowledge point based on the multimodal data of the user when processing historical training tasks, and selects the target training task from each candidate training task containing the target knowledge point according to the set training difficulty and proficiency and allocates it to the user. This can enable the training task allocated to the user to train the user's ability to target knowledge points and meet the user's required training difficulty, and can achieve accurate allocation of training tasks.
[0042] In one embodiment, step S2 may specifically include: Based on the principle that proficiency is negatively correlated with the time taken to complete historical training tasks, the frequency of client page switching, and physiological indicators, and the principle that proficiency is positively correlated with the frequency of keyboard input corresponding to historical training tasks, the user's proficiency in each knowledge point in historical training tasks is determined based on multimodal data.
[0043] Based on the above explanation of the principles, step S2 can objectively and accurately determine the user's proficiency with each knowledge point.
[0044] In one embodiment, step S4 may specifically include: If the training difficulty is set to easy, then the candidate training task whose proficiency in all knowledge points is greater than the preset threshold will be used as the target training task.
[0045] If the proficiency of all knowledge points in the candidate training task is greater than the preset threshold, it means that each knowledge point in the candidate training task has a corresponding proficiency, that is, the user has trained all the knowledge points in the candidate training task.
[0046] Understandably, if the user's proficiency in all knowledge points in the target training task is greater than the preset threshold, it means that the user is relatively proficient in each knowledge point in the target training task, and the user can easily complete the target training task. Therefore, when the user needs an easy training task, an easy training task can be assigned to the user.
[0047] In one embodiment, step S4 may specifically include: If the training difficulty is moderate, then candidate training tasks with some knowledge points having a proficiency level below the preset threshold and some knowledge points having a proficiency level above the preset threshold will be used as target training tasks.
[0048] It is understandable that if the user's proficiency in some knowledge points of the target training task is greater than the preset threshold, it means that the user is relatively proficient in these knowledge points; if the user's proficiency in other knowledge points of the target training task is less than the preset threshold, it means that the user is relatively unfamiliar with these knowledge points; then the user's overall proficiency in the target training task is average, so when the user needs a training task of average difficulty, a training task of average difficulty can be assigned to the user.
[0049] In one embodiment, step S4 may specifically include: If the training difficulty is set to "hard", then the candidate training task whose proficiency in all knowledge points is less than the preset threshold will be used as the target training task.
[0050] It is understandable that if the proficiency of all knowledge points in the target training task is less than the preset threshold, it means that the user is unfamiliar with the target training task. Therefore, when the user needs a difficult training task, a difficult training task can be assigned to the user.
[0051] In one embodiment, after step S4 and before step S5, the training task allocation method of the present invention may further include: If no target training task is selected, the large language model is invoked to generate a target training task based on the target knowledge points, training difficulty, and proficiency.
[0052] Considering that the knowledge graph of this invention may not necessarily store the training tasks required by the user, for example, when the training difficulty is easy, there may not be a training task in the knowledge graph where the difficulty of all knowledge points is greater than the preset threshold, so it is necessary to generate new target training tasks for the user.
[0053] The method for generating target training tasks using a large language model is as follows: guide the large model to generate training tasks that contain target knowledge points and whose proficiency level for each knowledge point meets the training difficulty requirements.
[0054] In one embodiment, step S5 may include: The number of times each training task has been assigned is sorted in ascending order; The target training tasks with the highest number of assigned attempts will be assigned to the user.
[0055] Considering that the number of times each training task in the knowledge graph is assigned varies, some training tasks are frequently assigned to users, while others are not assigned for a long time, resulting in a waste of resources for some training tasks.
[0056] The present invention assigns target training tasks with fewer allocations to users, which can increase the allocation frequency of training tasks with fewer allocations, making the allocation of training tasks more balanced.
[0057] In one embodiment, after step S5, the training task allocation method of the present invention may further include: Update the user's proficiency in each knowledge point of the target training task based on the multimodal data generated by the user when processing the target training task.
[0058] After a user completes a target training task, their proficiency with each knowledge point in the task will generally improve. Therefore, it is necessary to update the user's proficiency with these knowledge points so that the proficiency used for the next assignment is more accurate and precise.
[0059] like Figure 2 As shown, the training task allocation device provided by the present invention includes, but is not limited to: The acquisition module is used to acquire multimodal data generated by users when processing historical training tasks. The multimodal data includes at least one of the following: task completion time, mouse movement trajectory, keyboard input frequency, client page switching frequency, emotion data, and physiological indicators. The determination module is used to determine the user's proficiency with each knowledge point in each historical training task based on multimodal data; The retrieval module is used to retrieve each candidate training task from the training task knowledge graph based on the set target knowledge points. The filtering module is used to select the target training task from various candidate training tasks based on the set training difficulty and proficiency. The assignment module is used to assign target training tasks to users.
[0060] It should be noted that the training task allocation device provided by the present invention can execute the training task allocation method described in any of the above embodiments during specific operation, which will not be elaborated in this embodiment.
[0061] Figure 3This is a schematic diagram of the structure of an electronic device provided by the present invention. The electronic device may include: a processor, a communication interface, a memory, and a communication bus. The processor, communication interface, and memory communicate with each other via the communication bus. The processor can call logical instructions in the memory to execute a training task allocation method. This method includes: acquiring multimodal data generated by the user while processing historical training tasks; the multimodal data includes at least one of the following: task completion time, mouse movement trajectory, keyboard input frequency, client page switching frequency, emotion data, and physiological indicators; determining the user's proficiency with each knowledge point in each historical training task based on the multimodal data; retrieving candidate training tasks from the training task knowledge graph based on set target knowledge points; selecting a target training task from the candidate training tasks based on set training difficulty and proficiency; and allocating the target training task to the user.
[0062] Furthermore, the logical instructions in the aforementioned memory can be implemented as software functional units and sold or used as independent products, and can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the 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 to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0063] On the other hand, the present invention also provides a computer program product, the computer program product comprising a computer program stored on a non-transitory computer-readable storage medium, the computer program comprising program instructions, and when the program instructions are executed by a computer, the computer is able to execute the training task allocation method provided in the above embodiments, the method comprising: acquiring multimodal data generated by a user when processing historical training tasks, the multimodal data including at least one of task completion time, mouse movement trajectory, keyboard input frequency, client page switching frequency, emotion data, and physiological indicators; determining the user's proficiency with each knowledge point in each historical training task based on the multimodal data; retrieving each candidate training task from the training task knowledge graph based on the set target knowledge points; selecting a target training task from each candidate training task based on the set training difficulty and proficiency; and allocating the target training task to the user.
[0064] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the training task allocation method provided in the above embodiments. The method includes: acquiring multimodal data generated by a user while processing historical training tasks, the multimodal data including at least one of task completion time, mouse movement trajectory, keyboard input frequency, client page switching frequency, emotion data, and physiological indicators; determining the user's proficiency with each knowledge point in each historical training task based on the multimodal data; retrieving each candidate training task from a training task knowledge graph based on set target knowledge points; selecting a target training task from the candidate training tasks based on set training difficulty and proficiency; and allocating the target training task to the user.
[0065] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.
[0066] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.
[0067] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims
1. A training task allocation method, characterized in that, include: Acquire multimodal data generated by users when processing historical training tasks. The multimodal data includes at least one of the following: task completion time, mouse movement trajectory, keyboard input frequency, client page switching frequency, emotion data, and physiological indicators. The user's proficiency with each knowledge point in each of the historical training tasks is determined based on the multimodal data. Based on the set target knowledge points, each candidate training task is retrieved from the training task knowledge graph. The target training task is selected from each of the candidate training tasks based on the set training difficulty and the proficiency level. The target training task is assigned to the user.
2. The training task allocation method according to claim 1, characterized in that, Determining the user's proficiency with each knowledge point in each of the historical training tasks based on the multimodal data includes: Based on the principle that the proficiency is negatively correlated with the task completion time, client page switching frequency, and physiological indicators corresponding to the historical training task, and the principle that the proficiency is positively correlated with the keyboard input frequency corresponding to the historical training task, the user's proficiency in each knowledge point in the historical training task is determined according to the multimodal data.
3. The training task allocation method according to claim 1, characterized in that, The step of selecting the target training task from the candidate training tasks based on the set training difficulty and the proficiency level includes: If the training difficulty is easy, then the candidate training task in which the proficiency of all knowledge points contained therein is greater than a preset threshold is taken as the target training task.
4. The training task allocation method according to claim 1, characterized in that, The step of selecting the target training task from the candidate training tasks based on the set training difficulty and the proficiency level includes: If the training difficulty is moderate, then the candidate training task containing some knowledge points with a proficiency level less than a preset threshold and some knowledge points with a proficiency level greater than a preset threshold will be used as the target training task.
5. The training task allocation method according to claim 1, characterized in that, The step of selecting the target training task from the candidate training tasks based on the set training difficulty and the proficiency level includes: If the training difficulty is "difficult", then the candidate training task in which the proficiency of all knowledge points is less than a preset threshold will be used as the target training task.
6. The training task allocation method according to claim 1, characterized in that, After selecting the target training task from the candidate training tasks based on the set training difficulty and the proficiency level, and before assigning the target training task to the user, the method further includes: If the target training task is not selected, the large language model is invoked to generate the target training task based on the target knowledge points, the training difficulty, and the proficiency level.
7. The training task allocation method according to claim 1, characterized in that, Assigning the target training task to the user includes: The number of times each of the target training tasks has been assigned is sorted in ascending order; The target training task ranked highest among the assigned attempts will be assigned to the user.
8. The training task allocation method according to claim 1, characterized in that, After assigning the target training task to the user, the process further includes: Based on the multimodal data generated by the user when processing the target training task, update the user's proficiency with each knowledge point in the target training task.
9. A training task allocation device, characterized in that, include: The acquisition module is used to acquire multimodal data generated by the user when processing historical training tasks. The multimodal data includes at least one of the following: task completion time, mouse movement trajectory, keyboard input frequency, client page switching frequency, emotion data, and physiological indicators. The determination module is used to determine the user's proficiency with each knowledge point in each of the historical training tasks based on the multimodal data. The retrieval module is used to retrieve each candidate training task from the training task knowledge graph based on the set target knowledge points. The filtering module is used to filter out the target training task from each of the candidate training tasks based on the set training difficulty and the proficiency level. The allocation module is used to assign the target training task to the user.
10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the training task allocation method as described in any one of claims 1 to 8.
11. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the training task allocation method as described in any one of claims 1 to 8.
12. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the training task allocation method as described in any one of claims 1 to 8.