Multi-task Training Method, Apparatus, Device, and Storage Medium

Abstract

The present application discloses a multi-task training method, apparatus, device, and storage medium. The method includes: determining an initial difficulty coefficient for training the trainee from multiple difficulty coefficients based on the first individual parameter of the trainee; determining a target combined training task from multiple first combined training tasks corresponding to the initial difficulty coefficient based on the second individual parameter of the trainee; presenting the multiple target training tasks to the trainee, and obtaining the total feedback data of the trainee after performing the target combined training task and the sub-feedback data of each target training task; and performing multiple trainings on the trainee based on the total feedback data of the target combined training task and the sub-feedback data of each target training task. The present application is beneficial to improving the effect and efficiency of multi-task training.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular, to a multi-task training method, apparatus, device, and storage medium. Background Art

[0002] Multi-task processing is a processing process of executing multiple tasks simultaneously within a period of time. In real life, people often need to perform multiple tasks simultaneously. The human ability to process information is limited. Since multiple tasks need to be processed simultaneously, the cognitive resources obtained by a single task will be reduced, and the interference between tasks will lead to situations such as distraction of attention and decline in execution efficiency. In reality, in order to be able to process multiple tasks simultaneously, people need to use advanced cognitive abilities such as prediction and planning, and perform attention allocation, time scheduling, and reaction coordination among multiple tasks in the three stages of sensory processing of stimulus information, response selection, and response processing. Although resource competition will occur in any of these three stages for multiple tasks, the resource competition and the resulting cognitive control ability in the response selection stage are the most neuroplastic. In this process of response selection, different task processing flows can be integrated, or can be performed simultaneously due to the proficient and automated execution of a single task, which reduces the interference between tasks, or can be alternated by rapid switching. Therefore, a technology is needed to train people's multi-task cognitive ability.

[0003] Currently, common multi-task training programs adopt the combination of two simple tasks or similar tasks to train specific abilities of trainees. When performing multi-task training, it is necessary to set the difficulty coefficient of training, and by continuously adjusting the difficulty coefficient during training, trainees are trained with different difficulty coefficients. For example, by increasing the number of training tasks performed simultaneously, trainees are trained with different difficulty coefficients.

[0004] However, currently, the difficulty coefficient of multi-task training is usually adjusted in a form of increasing step by step, and it is impossible to adjust the difficulty coefficient of training according to the actual perceptual ability and training performance of trainees, resulting in low training effect and efficiency, and poor user experience. Summary of the Invention

[0005] In order to solve the above problems existing in the prior art, the embodiments of the present application provide a multi-task training method, apparatus, device, and storage medium, which can adjust the difficulty coefficient of multi-task training according to the feedback data of trainees during multi-task training, and adjust the training tasks of trainees to improve the training effect and efficiency.

[0006] In a first aspect, the embodiments of the present application provide a multi-task training method, including:

[0007] Determine an initial difficulty coefficient for training the trainee from multiple difficulty coefficients based on the first personal parameter of the trainee;

[0008] Determine a target combined training task from multiple first combined training tasks corresponding to the initial difficulty coefficient based on the second personal parameter of the trainee, where the target combined training task includes multiple target training tasks;

[0009] Show multiple target training tasks to the trainee, and obtain the total feedback data after the trainee performs the target combined training task and the sub-feedback data of each target training task;

[0010] Train the trainee multiple times based on the total feedback data of the target combined training task and the sub-feedback data of each target training task.

[0011] In a possible embodiment, determining a target combined training task from multiple first combined training tasks corresponding to the initial difficulty coefficient based on the second personal parameter of the trainee includes:

[0012] Obtain multiple first training tasks in the target scenario; the target scenario is the training scenario of the trainee;

[0013] Determine multiple first combined training tasks according to the preset difficulty coefficient of each first training task in the multiple first training tasks, where each first combined training task is composed of multiple second training tasks, and the second training task is any one of the multiple first training tasks, and the product of the preset difficulty coefficients of the second training tasks constituting each first combined training task is equal to the initial difficulty coefficient;

[0014] Determine the target combined training task from the multiple first combined training tasks according to the second personal parameter.

[0015] In a possible embodiment, before obtaining multiple first training tasks in the target scenario, it further includes:

[0016] Determine the perceptual abilities of multiple sensory systems of the trainee according to the second personal parameter;

[0017] Determine the trainee population to which the trainee belongs based on the perceptual abilities of multiple sensory systems of the trainee;

[0018] Obtain the training scores of the trainee population in multiple training scenarios;

[0019] Take the training scenario with the lowest training score as the target scenario.

[0020] In a possible embodiment, the second personal parameter includes: the perceptual ability of the trainee and the perceptual ability of the trainee to multiple types of stimulus content;

[0021] Determining a target combined training task from multiple first combined training tasks according to a second individual parameter, including:

[0022] Obtaining multiple sensory systems of the trainee for supporting training in a target scenario;

[0023] Determining at least one target sensory system from multiple sensory systems based on the trainee's perception ability;

[0024] Determining multiple initial stimulus contents corresponding to the trainee based on at least one target sensory system and the trainee's perception ability of various types of stimulus contents; the initial stimulus content is any one of various types of stimulus contents;

[0025] Determining the target combined training task from multiple first combined training tasks based on the multiple initial stimulus contents; wherein, multiple target training tasks of the target combined training task correspond one-to-one to the multiple initial stimulus contents.

[0026] In a possible embodiment, determining at least one target sensory system from multiple sensory systems based on the trainee's perception ability includes:

[0027] Determining the perception ability scores of the trainee in each sensory system among multiple sensory systems based on the trainee's perception ability;

[0028] Taking at least one sensory system with a perception ability score less than a first threshold as at least one target sensory system;

[0029] If the perception ability scores of each sensory system are all greater than or equal to the first threshold, taking the sensory system with the lowest perception ability score as the target sensory system.

[0030] In a possible embodiment, presenting multiple target training tasks to the trainee includes:

[0031] Determining the presentation order and presentation time interval of multiple target training tasks;

[0032] Presenting multiple target training tasks to the trainee in sequence according to the presentation order and presentation time interval;

[0033] Wherein, each target training task is presented in the following manner:

[0034] Presenting the attention content of the target training task;

[0035] After a preset first time interval, a plurality of training materials corresponding to the target training task are sequentially displayed, and buffer content corresponding to the target training task is inserted between the displays of any two adjacent training materials; wherein, the time interval between any buffer content and the training material before the buffer content is a preset second time interval, and the time interval between the buffer content and the training material after the buffer content is a preset third time interval;

[0036] After the display of the training materials of the target training task is completed, a question answering interface for each target training task is displayed to the trainee for the trainee to make a response.

[0037] In a possible implementation, determining the display order and display time interval of a plurality of target training tasks includes:

[0038] Obtain the weighted correct rate of the trainee during the historical training of a plurality of target training tasks, and the weighted correct rate is determined by the historical correct rate of each target training task when the trainee performs a plurality of target training tasks;

[0039] Based on the weighted correct rate, determine the display time interval;

[0040] Sort the plurality of target training tasks according to the historical correct rate of each target training task, and use the sorted order as the display order.

[0041] In a second aspect, an embodiment of the present application provides a multi-task training device, and the device includes:

[0042] An initial module, configured to determine an initial difficulty coefficient for training the trainee from a plurality of difficulty coefficients based on the first individual parameter of the trainee;

[0043] A training module, configured to determine a target combined training task from a plurality of first combined training tasks corresponding to the initial difficulty coefficient based on the second individual parameter of the trainee, and the target combined training task includes a plurality of target training tasks;

[0044] Display a plurality of target training tasks to the trainee, and obtain the total feedback data of the trainee after performing the target combined training task and the sub-feedback data of each target training task;

[0045] Based on the total feedback data of the target combined training task and the sub-feedback data of each target training task, train the trainee multiple times.

[0046] In a third aspect, an embodiment of the present application provides an electronic device, including: a processor, the processor is connected to a memory, the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory so that the electronic device executes the method as described in the first aspect.

[0047] Fourthly, an embodiment of the present application provides a computer-readable storage medium storing a computer program, which causes a computer to execute the method according to the first aspect.

[0048] Fifthly, an embodiment of the present application provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer is operable to cause the computer to execute the method according to the first aspect.

[0049] Implementing the embodiments of the present application has the following beneficial effects:

[0050] In the embodiments of the present application, based on the first individual parameter of the trainee, the basic perception ability of the trainee can be determined. Then, according to the basic perception ability of the trainee and the historical training data, an initial difficulty coefficient for training the trainee is determined among multiple difficulty coefficients. Next, based on the second individual parameter of the trainee, multiple first combined training tasks corresponding to the initial difficulty coefficient in the target scenario can be determined for the trainee, and according to the second individual parameter, a target combined training task is determined among the multiple first combined training tasks. Further, multiple target training tasks corresponding to the target combined training task are sequentially presented to the trainee, and the total feedback data of the trainee after performing the target combined training task and the sub-feedback data of each target training task are obtained. Finally, based on the total feedback data of the target combined training task and the sub-feedback data of each target training task, the trainee can be trained multiple times. Among them, the difficulty coefficient of the trainee's next training can be determined according to the total feedback data of the target combined training task and the first individual parameter during each training. The target combined training task for the trainee's next training can be determined according to the sub-feedback data of each target training task and the second individual parameter during each training. Thus, based on the first individual parameter and the second individual parameter of the trainee, as well as the total feedback data and sub-feedback data of each training, the difficulty coefficient of the next training can be adjusted, and a suitable combined training task can be selected to perform more accurate training for each trainee. Moreover, there is no need to gradually adjust the difficulty coefficient of training, and the training effect and training efficiency are better. Description of the Drawings

[0051] To more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0052] Figure 1 It is a schematic flowchart of a dual-task training provided by an embodiment of the present application;

[0053] Figure 2 Schematic diagram of a multi - task training system provided by an embodiment of the present application;

[0054] Figure 3 Flow schematic diagram of a multi - task training method provided by an embodiment of the present application;

[0055] Figure 4 Schematic diagram of a combined training task display method provided by an embodiment of the present application;

[0056] Figure 5 Flow schematic diagram of the n - th training provided by an embodiment of the present application;

[0057] Figure 6 Block diagram of the functional modules of a multi - task training device provided by an embodiment of the present implementation manner of the present application;

[0058] Figure 7 Schematic diagram of the structure of an electronic device provided by an embodiment of the present implementation manner of the present application. Detailed implementation manners

[0059] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0060] The terms "first", "second", "third", and "fourth", etc. in the specification and claims of the present application and the accompanying drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non - exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but optionally further includes steps or units not listed, or optionally further includes other steps or units inherent to these processes, methods, products, or devices.

[0061] Referring to "embodiments" herein means that specific features, results, or characteristics described in conjunction with the embodiments can be included in at least one embodiment of the present application. The phrase appears in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0062] To facilitate understanding of the technical solutions of the present application, first, the related technologies involved in the present application are explained and described.

[0063] Multitasking is a processing process that executes multiple tasks simultaneously within a period of time. Multitasking training refers to training the ability of a trainee to execute multiple tasks simultaneously, and is mainly applied to training the trainee's sensory processing, cognitive ability, reaction ability, attention allocation ability, and so on.

[0064] Current multitasking training usually uses multiple simple tasks, and the most common one is composed of two sensorimotor tasks. As Figure 1 shown, when conducting dual-task training on a trainee, Task 1 is a visual training task and Task 2 is an auditory training task. When the training starts, the multitasking training device will show the trainee the content to focus on, so that the trainee can focus on each training task. After a period of time, the multitasking training device will show the training materials and buffer content of each training task to the trainee. For example, in Task 1, the multitasking training device will show the trainee multiple pictures, and these multiple pictures are the training materials. Between the display of each picture, buffer content will be inserted, and this buffer content is used to enable the trainee to respond to each picture. In Task 2, the multitasking training device will play a preset audio for the trainee, and multiple audio segments in this preset audio are the training materials. Between each audio segment, buffer content will be inserted, and this buffer content is used to enable the trainee to respond to each audio segment. When the display of the training materials of each training task is completed, the multitasking training device will show the answer interface of each training task to the trainee for the trainee to make a response. After the trainee's response is completed, the performance of the trainee in each training task will be shown. For example, in Task 1, when the trainee sees a specific picture among multiple pictures, a response is made on the answer interface. In Task 2, when the trainee hears a specific audio segment among multiple audio segments, a response is made on the answer interface. Thus, based on the trainee's response performance in each training task, feedback on the trainee's training performance can be provided, and the feedback data includes the correct rate of each training task and the correct rate of all training tasks.

[0065] It should be noted that existing multitasking training usually uses multiple simple tasks or tasks with relatively high similarity for training. For example, a trainee needs to conduct two arithmetic task trainings, one is a digital addition and subtraction arithmetic task, and the other is a spatial arithmetic task. In addition, there is also dual-task training designed for specific problems. For example, in a simulated driving program, the trainee needs to use the mouse to track a car and make a key response when seeing a specific sign. It can be seen that the combination form of existing multitasking training is fixed and it is difficult to be transferred to other multitasking training scenarios.

[0066] Secondly, most existing multi-task training scenarios are fixed training scenarios. When trainees are training, they usually complete multiple training tasks with similar steps. Due to the fixed training scenario and the steps of the training tasks, after multiple trainings, trainees will gradually become familiar with the training steps, and the training process for trainees will gradually transform into a rapid response to a specific process, and the advanced cognitive functions of trainees cannot be trained.

[0067] Moreover, the sensory systems of the existing multi-task training stimuli are relatively single. For example, they are all presented in the form of visual stimuli and all require the participation of the visual system (eyeball - optic nerve - primary visual processing brain region of the occipital lobe - higher-level visual processing brain region of the occipital parietal lobe). When multiple visual stimuli need to be processed, it will lead to information overload in the visual system, and information can only be processed sequentially in the sensory processing stage, resulting in the information in the two stages of response selection and response processing in multi-tasks also being processed sequentially, thus unable to exercise the attention allocation, scheduling, and coordination abilities under multi-task parallel processing.

[0068] It should be noted that compared with the single-task training program, the multi-task training program involves more factors. Therefore, the setting of the difficulty coefficient during training needs to be considered from multiple aspects. However, the difficulty of the existing multi-task training program mainly lies in increasing the number of training tasks, and the setting of the training difficulty coefficient is unreasonable. Moreover, the existing multi-task training program requires trainees to train step by step, and it is impossible to adjust the training difficulty coefficient and training tasks according to the training effect of trainees, resulting in low training effect and efficiency, and poor experience for trainees.

[0069] To solve the above problems, the embodiments of the present application provide a multi-task training method. Next, the multi-task training system to which the multi-task training method is applied will be introduced.

[0070] Refer to Figure 2 , Figure 2 which is a schematic diagram of a multi-task training system provided by the embodiments of the present application. As Figure 2 shown, the multi-task training system may include, for example: a database, a processing device, and a training device.

[0071] Exemplarily, the database may be a server composed of one or more computers running in a local area network and a database management system, mainly used to provide functions such as data query, data update, data maintenance, caching, secure access, and data recovery. For example, the database may be a rack-mounted server, a cabinet server, a cloud server, a file server, etc. The database may also be a memory with data storage, reading, and writing functions, such as a random access memory (RAM), a read-only memory (ROM), a flash memory, a disk memory, an optical memory, etc., and the present application does not make specific limitations in this regard. In the embodiments of the present application, the database is mainly used to store the first individual parameter, the second individual parameter of the trainee, and the training data of each training. The processing device refers to a hardware device used to process and execute computer programs, instructions, and data, such as a Central Processing Unit (CPU). The processing device may also be a server for computing and data processing functions, such as a rack-mounted server, a Web server, a domain name server, a cloud server, etc., and the present application does not make specific limitations in this regard. In the embodiments of the present application, the processing device may be a multi-task training device, mainly used to calculate and process the training data of the trainee. The training device may be an electronic device with communication functions and installed with a training program, such as a personal computer, a laptop, a tablet computer, a smart phone, etc. The training device may also be an operable wearable device or an operating device, such as a smart watch, a remote control, a robot, an earphone, etc., and the present application does not make specific limitations in this regard.

[0072] Among them, a multi-task training program is installed on the training device, and the trainee can operate on the training device to enter the multi-task training program. It should be noted that the trainee needs to perform identity verification when running the multi-task training program on the training device, such as password verification, face recognition, fingerprint recognition, etc. When the trainee's identity verification is passed, in response to the trainee's operation, the training device sends a training request to the processing device, and the training request includes the trainee's identity information to request to enter the multi-task training program. Then, the processing device receives the request sent by the training device, and in response to the request, obtains the first individual parameter and the second individual parameter of the trainee from the database. Thus, based on the first individual parameter and the second individual parameter of the trainee, an initial difficulty coefficient and a target combined training task suitable for the trainee are determined, and the target combined training task is displayed and sent to the training device together with the corresponding training materials, so as to display the training materials of the target combined training task through the training device to train the trainee. When training, the trainee can respond to the target combined training task on the answer interface of the training device.

[0073] Thus, after the training is completed, the processing device will obtain the trainee's reaction performance during the target combination training task from the training device in real time. Based on this reaction performance, the total feedback data of the target combination training task and the sub-feedback data of each target training task in the target combination training task, that is, the trainee's score in this training, are determined. And it is fed back to the trainee after the target combination training task is completed. At the same time, based on the above total feedback data and sub-feedback data, the difficulty coefficient and combination training task of the next training can be determined, so that targeted training can be carried out on the trainee based on the trainee's training situation and his own conditions, improving the training efficiency and training effect.

[0074] The multi-task training method of the embodiments of the present application will be introduced below. This method is applied to a multi-task training device or the processing device in the above multi-task training system. Refer to Figure 3 , Figure 3 which is a schematic flowchart of a multi-task training method provided by an embodiment of the present application. This method includes but is not limited to the following steps:

[0075] 301: Determine the initial difficulty coefficient for the trainee's training from multiple difficulty coefficients based on the trainee's first individual parameter.

[0076] In the embodiments of the present application, the trainee's first individual parameter may be the trainee's basic perception ability for various sensory stimuli. For example, the trainee's reaction ability to visual stimulus content and the trainee's reaction ability to auditory stimulus content. Optionally, the trainee's first individual parameter can be obtained by pre-testing the trainee. For example, by providing the trainee with multiple pictures and asking the trainee to react to the image content included in each picture, based on the reaction time and accuracy rate of the trainee during the test, the trainee's reaction ability to visual stimulus content is obtained. By playing multiple audio segments to the trainee and asking the trainee to react to the audio content included in each audio segment, based on the reaction time and accuracy rate of the trainee during the test, the trainee's reaction ability to auditory stimulus content is obtained.

[0077] In a possible embodiment, for example, based on the trainee's reaction ability to various sensory stimulus contents, the perception ability of each sensory stimulus of the trainee can be scored to obtain the score corresponding to each sensory stimulus. The score corresponding to each sensory stimulus is used as the trainee's first individual parameter. Thus, the trainee's first individual parameter can be obtained and stored in the database.

[0078] Exemplarily, when a trainee initiates a training request through a training device, identity verification needs to be performed on the training device to obtain the identity information of the trainee. After the identity verification is passed, the training device sends the training request including the trainee's identity information to the processing device. In response to the training request, the processing device obtains the first individual parameter of the trainee from the database based on the trainee's identity information. Then, the processing device determines the initial difficulty coefficient for the trainee's training from multiple difficulty coefficients based on the trainee's first individual parameter.

[0079] In the embodiments of the present application, the multi-task training program is provided with multiple difficulty coefficients, and the difficulty coefficient is used to identify the training difficulty after combining multiple training tasks. Therefore, the difficulty coefficient is determined by the preset difficulty coefficients of each training task. For example, in dual-task training, assume there are four types of single tasks. Among them, task A is a simple continuous motion task, that is, a task of continuous or regular motion. Task B is a sensorimotor task, that is, a task that can immediately respond after perceiving an external stimulus. Task C is a decision-making task of medium difficulty, that is, a task that requires certain thinking before reacting after perceiving an external stimulus. Task D is a decision-making task of high difficulty, that is, a task that requires highly concentrated thinking before reacting after perceiving an external stimulus. These four types of training tasks can be combined pairwise arbitrarily, and there are 10 combined training tasks in total, namely AA, BB, CC, DD, AB, AC, AD, BC, BD, CD. Among them, the difficulty coefficient of each combined training task is equal to the product of the preset difficulty coefficients of each training task in the combined training task, as shown in Table 1:

[0080] Table 1:

[0081] Combined training task Difficulty coefficient AA 1*1＝1 AB 1*2＝2 AC 1*3＝3 AD 1*4＝4 BB 2*2＝4 BC 2*3＝6 BD 2*4＝8 CC 3*3＝9 CD 3*4＝12 DD 4*4＝16

[0082] As can be seen from Table 1, through pairwise combination of each training task, the formed combined training task corresponds to a difficulty coefficient, and the difficulty coefficient is the product of the preset difficulty coefficients of each training task. For example, the preset difficulty coefficient of task A is 1, the preset difficulty coefficient of task B is 2, the preset difficulty coefficient of task C is 3, and the preset difficulty coefficient of task D is 4. Thus, the difficulty coefficient of the combined training task AB is 1*2 = 2, and the difficulty coefficient of the combined training task CD is 3*4 = 12. It can be understood that the present application only takes the example that the difficulty coefficient of the combined training task is equal to the product of the preset difficulty coefficients of each training task for illustration. Those skilled in the art can also determine the difficulty coefficient of the combined training task through other operation methods of the preset difficulty coefficients of each training task, which is not limited herein.

[0083] It should be noted that the embodiments of the present application are only described by taking the dual-task training including 4 types of training tasks as an example. Those skilled in the art can independently set the types and the number of training tasks, so as to form multiple difficulty coefficients and multiple combined training tasks, which are not limited herein.

[0084] Thus, the processing device can determine the initial difficulty coefficient for training the trainee from multiple difficulty coefficients based on the first individual parameter of the trainee. In a possible embodiment, when the first individual parameter of the trainee is the score corresponding to each sensory stimulus of the trainee, multiply the score corresponding to each sensory stimulus by the difficulty weight corresponding to each sensory stimulus to obtain multiple weighted scores. Accumulate the multiple weighted scores to obtain the difficulty score corresponding to the first individual parameter of the trainee. Use the difficulty coefficient equal to the difficulty score among the multiple difficulty coefficients as the initial difficulty coefficient.

[0085] It can be seen that the initial training difficulty of the trainee is determined by the first individual parameter of the trainee. The processing device can select a suitable difficulty coefficient for the trainee according to the first individual parameter of each trainee for targeted training, improving the training efficiency and training effect.

[0086] 302: Determine the target combined training task from multiple first combined training tasks corresponding to the initial difficulty coefficient based on the second individual parameter of the trainee.

[0087] In the embodiments of the present application, the second individual parameter of the trainee may include the perceptual ability of the trainee and the perceptual ability of the trainee for various types of stimulus content. The second individual parameter can be obtained by performing a perception test on the trainee. For example, by showing multiple test images to the trainee and inserting an image answering interface between the display of each test image, the image answering interface includes questions corresponding to each test image, and the trainee needs to react on the image answering interface. Use the correct rate and reaction time of the trainee's reaction as the visual perceptual ability of the trainee. By showing multiple test audio segments to the trainee and inserting an audio answering interface between the display of each test audio segment, the audio answering interface includes questions corresponding to each test audio segment, and the trainee needs to react on the audio answering interface. Use the correct rate and reaction time of the trainee's reaction as the auditory perceptual ability of the trainee. It can be understood that the other perceptual abilities of the trainee can also be obtained by the above method, which is not limited herein.

[0088] Among them, the target combined training task includes multiple target training tasks. The training scenario of the target training task is the target scenario, each target training task includes the training material corresponding to the target training task, and the training material of each target training task is determined by the sensory system and the initial stimulus content corresponding to the target training task.

[0089] In a feasible embodiment, the processing device may obtain the perceptual abilities of multiple sensory systems of a trainee during training in a target scenario. Based on the trainee's perceptual abilities, at least one target sensory system suitable for the trainee's perceptual abilities is determined among the multiple sensory systems. Then, based on the trainee's perceptual abilities for various types of stimulus content, multiple initial stimulus contents corresponding to the at least one target sensory system are determined. Further, based on the multiple initial stimulus contents, multiple first combined training tasks are determined from multiple first training tasks in the target scenario. Finally, according to the preset difficulty coefficient of each first training task in the multiple first training tasks, the combined difficulty coefficient of each first combined training task is determined, and the first combined training task with the combined difficulty coefficient being the initial difficulty coefficient is used as the target combined training task.

[0090] In another feasible embodiment, the processing device may obtain the second individual parameters of the trainee from a database, and based on the second individual parameters of the trainee, determine the target scenario for training the trainee. Then, the second combined training task with the difficulty coefficient being the initial difficulty coefficient among the multiple second combined training tasks corresponding to the target scenario is used as the multiple first combined training tasks. Finally, according to the trainee's perceptual abilities and the perceptual abilities for various types of stimulus content, the target combined training tasks, that is, the multiple target training tasks for training the trainee, are determined from the multiple first combined training tasks.

[0091] Exemplarily, determining the target combined training task from the multiple first combined training tasks corresponding to the initial difficulty coefficient based on the second individual parameters of the trainee may include the following steps:

[0092] Obtain multiple first training tasks in the target scenario;

[0093] According to the preset difficulty coefficient of each first training task in the multiple first training tasks, determine multiple first combined training tasks;

[0094] According to the second individual parameters, determine the target combined training task among the multiple first combined training tasks.

[0095] In the embodiments of the present application, each first combined training task is composed of a preset number of multiple second training tasks. The second training task is any one of the multiple first training tasks, and the product of the preset difficulty coefficients of the second training tasks that make up each first combined training task is equal to the initial difficulty coefficient. The target scenario is the training scenario of the trainee. Optionally, the training scenario of the trainee may include, for example: laboratory scenario, indoor scenario, and outdoor scenario. The training tasks in the laboratory scenario may include: Oddball task, N-back task, etc. For example, among multiple training materials with a higher display frequency, stimulus materials with a lower display frequency are interspersed, and the trainee needs to respond to the stimulus materials. Or, during the display of multiple training materials, the trainee needs to recall the previous N training materials. The embodiments of the present application are only described with the above multiple training tasks, and do not specifically limit the training tasks in the laboratory scenario.

[0096] Exemplarily, the indoor scenario may include: cooking scenario, housework scenario, etc. When the training scenario is the cooking scenario, one of the training tasks may be a simple continuous movement task, such as continuously cutting vegetables, and another training task may be a sensorimotor task, paying attention to the heat while stir-frying. The processing device can obtain the video image of the trainee cooking through the video image acquisition device, analyze the time when the trainee cuts vegetables and the size of the cut vegetables in the video image, as well as the size of the flame and the stir-frying time when stir-frying, and use the analysis result as the feedback data during the trainee's training to train the trainee multiple times. When the training scenario is the housework scenario, one of the training tasks may be a sensorimotor task, such as tidying up items, and another training task is a decision-making task of medium difficulty, such as making a phone call. The processing device can obtain the video image of the trainee doing housework through the video image acquisition device, analyze the time and neatness of the trainee tidying up items in the video image, as well as the language expression ability when making a phone call, and use the analysis result as the feedback data during the trainee's training to train the trainee multiple times. The embodiments of the present application are only described with the above multiple training tasks, and do not specifically limit the training tasks in the indoor scenario.

[0097] Optionally, the outdoor scenario may include, for example, a shopping scenario. When the training scenario is the shopping scenario, one of the training tasks may be a sensorimotor task, such as selecting goods according to a list, and another training task may be a decision-making task of high difficulty, such as mentally calculating the total price of the goods. The processing device determines the feedback data based on the reaction performance of the trainee by taking the selected goods and the mentally calculated total price of the goods as the reaction performance of the trainee, and trains the trainee multiple times based on the feedback data. The embodiments of the present application are only described with the above multiple training tasks, and do not specifically limit the training tasks in the outdoor scenario.

[0098] It can be understood that the above training scenario can be a virtual scenario simulated in the program of the training device or an actual training scenario.

[0099] Thus, before determining the target training task, the processing device first determines the target scenario based on the second individual parameter of the trainee. Then, it obtains multiple first training tasks in the target scenario, that is, multiple first training tasks included in the target scenario.

[0100] Exemplarily, before obtaining multiple first training tasks in the target scenario, the method further includes the following steps:

[0101] Determine the perceptual abilities of multiple sensory systems of the trainee according to the second individual parameter;

[0102] Determine the trainee population to which the trainee belongs based on the perceptual abilities of multiple sensory systems of the trainee;

[0103] Obtain the training scores of the trainee population in multiple training scenarios;

[0104] Take the training scenario with the lowest training score as the target scenario.

[0105] In the embodiment of the present application, the processing device obtains the perceptual abilities of multiple sensory systems of the trainee from the database and determines the strengths and weaknesses of the multiple perceptual abilities of the trainee based on the perceptual abilities of the trainee. For example, the processing device determines the strength and weakness of the trainee's visual perceptual ability based on the trainee's visual perceptual ability, that is, the accuracy rate and reaction time during the visual perception test. The processing device determines the strength and weakness of the trainee's auditory perceptual ability based on the trainee's auditory perceptual ability, that is, the accuracy rate and reaction time during the auditory perception test.

[0106] Then, the processing device determines the trainee population to which the trainee belongs based on the perceptual abilities of multiple sensory systems of the trainee. It should be noted that the database also stores the second individual parameters and training data of multiple trainees. Based on the second individual parameter of each trainee, specifically, based on the strengths and weaknesses of the information reception and processing abilities of multiple sensory systems of each trainee, that is, the perceptual abilities of multiple sensory systems, the trainees are divided into multiple trainee populations. Based on the training data of multiple trainees in multiple training scenarios in each trainee population, the training scores of each trainee population in multiple training scenarios can be determined and stored in the database. Therefore, the processing device can determine the trainee population to which the trainee belongs based on the strengths and weaknesses of the perceptual abilities of multiple sensory systems of the trainee. Then, it obtains the training scores of this trainee population in multiple training scenarios from the database and takes the training scenario with the lowest training score as the target scenario.

[0107] It can be seen that in the embodiment of the present application, the processing device can determine a target scenario suitable for the trainee based on the second individual parameter of the trainee, so that the trainee can train in the target scenario. Compared with the existing training in a fixed scenario, the effect of training the trainee in this solution is better, and the training experience of the trainee is improved.

[0108] After determining the target scenario, the processing device obtains multiple first training tasks included in the target scenario and combines the multiple first training tasks to obtain multiple second combined training tasks. Wherein, the preset quantity is the quantity of the target training tasks for training the trainee. For example, when the preset quantity is 2 and the quantity of the first training tasks is 4, any two of the 4 first training tasks are combined to obtain 10 second combined training tasks.

[0109] Furthermore, the processing device can determine the combined difficulty coefficient of each second combined training task based on the preset difficulty coefficient of each first training task. Wherein, the combined difficulty coefficient of each second combined training task is the product of the preset difficulty coefficients of each third training task in the second combined training task. For example, when the second combined training task includes 2 third training tasks and the preset difficulty coefficients of the 2 third training tasks are 2 and 4 respectively, the combined difficulty coefficient of the second combined training task is 8. Thus, based on the preset difficulty coefficient of each first training task, the preset difficulty coefficient of the third training task corresponding to each second combined training task can be determined, and the product of the preset difficulty coefficients of the third training tasks corresponding to each second combined training task is used as the combined difficulty coefficient of the second combined training task.

[0110] It should be noted that multiple second combined training tasks may include multiple combined training tasks with equal combined difficulty coefficients. The processing device can use the multiple second combined training tasks with the combined difficulty coefficient being the initial difficulty coefficient as multiple first combined training tasks. And based on the second individual parameter of the trainee, determine a target combined training task among the multiple first combined training tasks to train the trainee using the target combined training task.

[0111] It can be seen that in the embodiments of the present application, the processing device can obtain multiple first training tasks in a target scenario, arbitrarily combine the multiple first training tasks to obtain multiple second combined training tasks, and then determine the combined difficulty coefficient of each second combined training task based on the preset difficulty coefficient of each first training task. Next, the multiple second combined training tasks with the combined difficulty coefficient being the initial difficulty coefficient are used as multiple first combined training tasks. Finally, based on the second individual parameter, a target combined training task is determined from the multiple first combined training tasks. Thus, a target combined training task suitable for the trainee can be determined from the multiple first combined training tasks corresponding to the initial difficulty coefficient based on the second individual parameter of the trainee. Compared with training the trainee with fixed training tasks, training the trainee with the target combined training task makes the combined form and training materials of each target training task more suitable for the trainee, improving the training effect and efficiency.

[0112] Exemplarily, the second individual parameter may include: the perceptual ability of the trainee and the perceptual ability of the trainee to various types of stimulus contents. Determining a target combined training task from the multiple first combined training tasks according to the second individual parameter may include the following steps, for example:

[0113] Obtain multiple sensory systems that support training of the trainee in the target scenario;

[0114] Based on the perceptual ability of the trainee, determine at least one target sensory system from the multiple sensory systems;

[0115] Based on the above at least one target sensory system and the perceptual ability of the trainee to various types of stimulus contents, determine multiple initial stimulus contents corresponding to the trainee;

[0116] Based on the multiple initial stimulus contents, determine a target combined training task from the multiple first combined training tasks.

[0117] In the embodiments of the present application, the sensory system may include, for example, the visual system, the auditory system, and so on. The stimulus content is the display form of the training materials under each sensory system. For example, the stimulus content corresponding to the visual system may include: shapes, colors, numbers, and so on. The stimulus content corresponding to the auditory system may include: letters, numbers, symbols, and so on. The initial stimulus content is any one of various types of stimulus contents. The multiple target training tasks of the target combined training task correspond one-to-one with the multiple initial stimulus contents. Among them, the multiple training materials corresponding to each target training task are determined by the initial stimulus content. Therefore, the processing device will first determine multiple initial stimulus contents when the trainee is training based on the second individual parameter of the trainee.

[0118] Specifically, the processing device first obtains multiple sensory systems that support training for the trainee in the target scenario. For example, in a laboratory scenario, the sensory systems that support training include: the visual system, the auditory system, and so on. Then, based on the trainee's perceptual ability, at least one target sensory system is determined among the multiple sensory systems, so as to train the trainee on the above at least one target sensory system.

[0119] Exemplarily, based on the trainee's perceptual ability, determining at least one target sensory system among the multiple sensory systems may include the following steps:

[0120] Based on the trainee's perceptual ability, determine the perceptual ability score of the trainee in each sensory system among the multiple sensory systems;

[0121] Take at least one sensory system whose perceptual ability score is less than the first threshold as the above at least one target sensory system;

[0122] If the perceptual ability score of each sensory system is greater than or equal to the first threshold, then take the sensory system with the lowest perceptual ability score as the target sensory system.

[0123] In the embodiments of the present application, the indicators for evaluating the trainee's perceptual ability are the correct rate and reaction time of the trainee during the perception test. Among them, the method of the perception test is similar to the above embodiments and will not be elaborated here.

[0124] Specifically, based on the correct rate and reaction time of the trainee during the perception test, the processing device can determine the perceptual ability scores of the trainee in different sensory systems. For example, based on the correct rate of the trainee during the visual perception test, the visual judgment score of the trainee is obtained. Based on the reaction time of the trainee during the visual perception test, the visual reaction score of the trainee is obtained. The sum of the visual judgment score and the visual reaction score is used as the perceptual ability score of the trainee in the visual system. Thus, the perceptual ability scores of the trainee in each sensory system can be obtained.

[0125] If there is at least one sensory system among the above multiple sensory systems whose perceptual ability score is less than the first threshold, then take at least one sensory system whose perceptual ability score is less than the first threshold as the above at least one target sensory system. Thus, at least one sensory system with relatively weak perceptual ability of the trainee can be determined as the target sensory system for training.

[0126] If the perceptual ability score of each sensory system is greater than the first threshold, then take the sensory system with the lowest perceptual ability score as the target sensory system. Thus, when the trainee's perceptual ability is strong, the target sensory system with the weakest perceptual ability of the trainee can also be determined to train the trainee's target sensory system.

[0127] It should be noted that among the multiple target training tasks in the target combined training task, there can be multiple target training tasks with the same sensory system being trained. Therefore, when the number of determined target sensory systems is one, the sensory systems trained by the multiple target training tasks are all the same.

[0128] It can be seen that the processing device can determine at least one target sensory system from multiple sensory systems based on the perceptual ability of the trainee, so as to train the above at least one target sensory system of the trainee. Compared with only training a single sensory system, it can exercise the trainee's attention allocation, scheduling and coordination abilities under the training of multiple sensory systems, and improve the training effect and training efficiency.

[0129] Furthermore, the processing device will determine multiple initial stimulus contents based on the above at least one target sensory system and the trainee's perceptual ability to various types of stimulus contents. Specifically, the processing device will obtain the trainee's perceptual ability to various types of stimulus contents under the target sensory system from the database. For example, when the target sensory system is the visual system, the processing device obtains the trainee's perceptual ability to stimulus contents such as shapes, patterns, colors, etc. Among them, the trainee's perceptual ability to each type of stimulus content is specifically the response score to each type of stimulus content, and this response score can be obtained through a perceptual test. The method of the perceptual test is similar to the above embodiments and will not be elaborated here.

[0130] Then, the multiple stimulus contents with response scores less than the second threshold are used as the multiple initial stimulus contents. Among them, when the number of stimulus contents with response scores less than the second threshold is greater than the preset number, multiple initial stimulus contents are randomly selected from the multiple stimulus contents with response scores less than the second threshold, so that the number of initial stimulus contents is the preset number.

[0131] Finally, the processing device determines the target combined training task from multiple first combined training tasks based on the multiple initial stimulus contents. Specifically, the processing device obtains the multiple training materials corresponding to each training task in each first combined training task. Based on the multiple training materials corresponding to each training task, the training stimulus content of each training task is determined, so as to determine the multiple training stimulus contents corresponding to each first combined training task. Then, based on the multiple initial stimulus contents, the target combined training task is determined from the multiple first combined training tasks, where the training stimulus contents of the multiple target training tasks of the target combined training task correspond one by one to the multiple initial stimulus contents.

[0132] Accordingly, the processing device can determine at least one target sensory system among multiple sensory systems corresponding to the target scenario according to the trainee's sensory perception ability. Then, based on the above at least one target sensory system and the trainee's sensory perception ability for various types of stimulus content, multiple initial stimulus contents corresponding to the trainee are determined. Finally, based on the multiple initial stimulus contents, a target combined training task is determined from multiple first combined training tasks. Accordingly, the sensory system and stimulus content for the trainee's training can be determined based on the trainee's second individual parameter, so as to precisely train the trainee and improve the training effect and efficiency.

[0133] 303: Display multiple target training tasks to the trainee, and obtain the total feedback data of the trainee after performing the target combined training task and the sub-feedback data of each target training task.

[0134] In the embodiment of the present application, the processing device will sequentially display each target training task in the target combined training task to the trainee, so that the trainee can respond to each target training task. Then, based on the trainee's response performance, the total feedback data of the trainee after performing the target combined training task and the sub-feedback data of each target training task are determined.

[0135] Exemplarily, displaying multiple target training tasks to the trainee may include:

[0136] Determine the display order and display time interval of multiple target training tasks;

[0137] According to the display order and display time interval, sequentially display multiple target training tasks to the trainee;

[0138] Among them, each target training task is displayed in the following manner:

[0139] Display the attention content of the target training task;

[0140] After a preset first time interval, sequentially display multiple training materials corresponding to the target training task, and insert buffer content corresponding to the target training task between the displays of any two adjacent training materials;

[0141] After the display of the training materials of the target training task is completed, display the answer interface of each target training task to the trainee for the trainee to respond.

[0142] In the embodiment of the present application, the time interval between any buffer content and the previous training material before this buffer content is the preset second time interval, and the time interval between this buffer content and the next training material after this buffer content is the preset third time interval.

[0143] It should be noted that when the display time interval between the training materials of each target training task is shorter, due to the influence of the psychological refractory period of the trainee, after receiving the training materials of one target training task, the trainee's response to the training materials of several other target training tasks is worse. Therefore, when the display time interval of each target training task is shorter, the interference between multiple target training tasks is greater, and the difficulty coefficient of training is higher. When displaying each target training task, the processing device will first determine the display order and display time interval of each target training task.

[0144] Exemplarily, determining the display order and display time interval of multiple target training tasks may include, for example:

[0145] Obtain the weighted correct rate of the trainee during the historical training of multiple target training tasks, where the weighted correct rate is determined by the historical correct rate of each target training task when the trainee performs multiple target training tasks;

[0146] Based on the weighted correct rate, determine the display time interval;

[0147] Sort multiple target training tasks according to the historical correct rate of each target training task, and use the sorted order as the display order.

[0148] In the embodiment of the present application, the historical training data of the trainee is stored in the database, and the historical training data includes the correct rate of each target training task when the trainee performs the historical training of multiple target training tasks. Optionally, if the current training is the first training of the trainee, the processing device may use the default display time interval corresponding to the initial difficulty coefficient as the display time interval of the trainee's current training, and sort the preset difficulty coefficients of each target training task from large to small, and use the sorted order as the display order of multiple target training tasks. Otherwise, the processing device will determine the display time interval and display order of multiple target training tasks based on the historical training data of the trainee.

[0149] Specifically, the processing device will obtain the historical correct rate of each target training task when the trainee performs the historical training of multiple target training tasks from the database. Then, based on the preset difficulty coefficient of each target training task, determine the weight value of each target training task. For example, the preset difficulty coefficient of each target training task can be used as the numerator of the weight value of the target training task, and the sum of the preset difficulty coefficients of the above multiple target training tasks can be used as the denominator of the weight value of each target training task to obtain the weight value of each target training task.

[0150] Further, the processing device takes the product of the weight of each target training task and the historical correct rate of the target training task as the sub-weight correct rate of each target training task. Finally, the sum of the sub-weight correct rates of multiple target training tasks is used as the above-mentioned weight correct rate.

[0151] It should be noted that when the processing device obtains the historical training data of the trainee, it will obtain the historical display time interval when the trainee last trained on multiple target training tasks. Based on this, when the weight correct rate is greater than or equal to the third threshold, it indicates that the trainee has been relatively proficient in processing multiple target training tasks under the historical display time interval. In order to improve the training effect, the processing device shortens the historical display time interval by a preset duration and uses the shortened historical display time interval as the display time interval for the trainee's current training.

[0152] When the weight correct rate is less than or equal to the fourth threshold, it indicates that the trainee has difficulty processing multiple target training tasks under the historical display time interval. In order to maintain the trainee's enthusiasm for training, the processing device extends the historical display time interval by a preset duration and uses the extended historical display time interval as the display time interval for the trainee's current training.

[0153] When the weight correct rate is less than the third threshold and greater than the fourth threshold, it indicates that the trainee is conducting reasonable training on multiple target training tasks under the historical display time interval, but the trainee has not achieved the required training effect. At this time, the historical display time interval is used as the display time interval for the trainee's current training to continue training the trainee.

[0154] Optionally, the display time interval for the trainee's training can vary within a preset range. When the historical display time interval does not fall within the preset range after being shortened or extended, the historical display time interval is used as the display time interval for the trainee's current training.

[0155] For example, the preset interval can be 0 to 2.5 seconds, and the preset duration can be 0.5 seconds. When the historical display time interval during the trainee's last training for multiple target training tasks is 1 second, if the weighted correct rate during the trainee's historical training for multiple target training tasks is greater than or equal to the third threshold, the display time interval for the current training is 0.5 seconds. If the weighted correct rate is less than or equal to the fourth threshold, the display time interval for the current training is 1.5 seconds. If the weighted correct rate is less than the third threshold and greater than the fourth threshold, the display time interval for the current training is 1 second. When the historical display time interval during the trainee's last training for multiple target training tasks is 0 seconds, if the weighted correct rate is less than the third threshold and greater than the fourth threshold, the historical display time interval does not fall into the preset interval after being shortened by 0.5 seconds. At this time, the historical display time interval is used as the display time interval for the current training, that is, the display time interval for the current training is 0 seconds.

[0156] Thus, the processing device can adjust the display time interval between multiple target training tasks based on the training data of the trainee's last training. Compared with using a fixed display time interval to display multiple target training tasks, this solution can solve the problem that when the display time interval is too short or too long, the training difficulty is too low or too high, resulting in low enthusiasm for the trainee's training, and improves the training effect.

[0157] It should be noted that after the trainee completes the current training, the historical training data of the trainee will be updated in the database. For example, the display time interval of the current training is used as the historical display time interval for the next training, and the weighted correct rate during the trainee's historical training for multiple target training tasks is updated based on the training data of the current training. Thus, during each training, the processing device can determine the display time interval between multiple training tasks based on the trainee's historical training data to improve the accuracy of the trainee's training.

[0158] In the embodiment of the present application, the processing device sorts the historical correct rates of each target training task in ascending order, and uses the sorting order of the historical correct rates as the display order of each target training task. Thus, according to the display order, the next target training task can be displayed every other display time interval.

[0159] It can be seen that the processing device can determine the display order and display time interval of each target training task through the trainee's historical training data. Compared with directly displaying each target training task through a fixed display order and display time interval, this solution can train the trainee's multi-task processing ability under the influence of the psychological refractory period and improve the training effect.

[0160] Further, the processing device sequentially presents the attention content of each target training task to the trainee based on the presentation order and presentation time interval of each target training task. The attention content of each target training task is used to direct the trainee to pay attention to each target training task. For example, the attention content of each target training task may be the indication content of the target training task, and this indication content is used to direct the training materials that the trainee needs to pay attention to.

[0161] After each target training task has elapsed a preset first time interval, a plurality of training materials corresponding to each target training task are sequentially presented, and buffer content corresponding to each target training task is inserted between the presentations of any two adjacent training materials among the plurality of training materials corresponding to each target training task.

[0162] Exemplarily, as Figure 4 shown, when the target combined training task includes Task 1 and Task 2, Task 1 is to train the trainee's auditory system, and Task 2 is to train the trainee's visual system. After the training starts, the processing device sequentially presents the attention content of Task 1 and Task 2 to the trainee based on the presentation order and presentation time interval of Task 1 and Task 2. After the presentation duration of the attention content of Task 1 and Task 2 reaches the preset first time interval, the training materials 1 of Task 1 and Task 2 start to be presented. As Figure 4 shown, the training material 1 of Task 1 may be, for example, an audio segment of the number "5", and the training material 1 of Task 2 may be, for example, a pattern of a "pentagon". After the presentation duration of the training materials 1 of Task 1 and Task 2 reaches the preset second time interval, the buffer content of Task 1 and Task 2 starts to be presented to enable the trainee to react to the training material 1. After the presentation duration of the buffer content of Task 1 and Task 2 reaches the preset third time interval, the training material 2 is presented to the trainee. As Figure 4 shown, the training material 2 of Task 1 may be, for example, an audio segment of the number "2", and the training material 2 of Task 2 may be, for example, a pattern of a "pentagram". After the presentation duration of the training materials 2 of Task 1 and Task 2 reaches the preset second time interval, the buffer content of Task 1 and Task 2 starts to be presented. After the presentation duration of the buffer content of Task 1 and Task 2 reaches the preset third time interval, the training material 3 is presented to the trainee. As Figure 4 shown, the training material 3 of Task 1 may be, for example, an audio segment of the number "7", and the training material 3 of Task 2 may be, for example, a pattern of a "triangle". Each training material of Task 1 and Task 2 is presented in the above method until the presentation of the training materials of Task 1 and Task 2 is completed.

[0163] Further, after the training materials of each target training task are displayed, a question answering interface for each target training task is displayed to the trainee, so that the trainee can respond to the questions of each target training task. After the trainee's response is completed, feedback data is determined based on the trainee's response performance. The feedback data includes the total feedback data of the target combined training task and the sub-feedback data of each target training task. The feedback data is fed back to the trainee. As Figure 4 shown, after the training materials of Task 1 and Task 2 are displayed, the question answering interfaces of Task 1 and Task 2 are respectively displayed, so that the trainee can respond to the questions of Task 1 and Task 2. After the trainee's response is completed, the feedback data is fed back to the trainee, so that the trainee can understand the training performance of this training. Among them, the feedback data may include, for example, the performance feedback of the trainee's response to the questions of each target training task, including the correct rate and response time of a single task, and the total performance feedback calculated based on the sub-feedback data of each target training task, that is, the total correct rate and total response time of multiple target training tasks.

[0164] Thus, the processing device can display the target combined training task to the trainee, and obtain the total feedback data of the trainee after performing the target combined training task and the sub-feedback data of each target training task. Then, based on the total feedback data of the target combined training task and the sub-feedback data of each target training task, the training tasks for the next training are adjusted to improve the training effect and training efficiency.

[0165] 304: Based on the total feedback data of the target combined training task and the sub-feedback data of each target training task, the trainee is trained multiple times.

[0166] In the embodiment of the present application, the processing device can determine the difficulty coefficient of the next training based on the total feedback data of the trainee for the target combined training task and the first personal parameter of the trainee. Then, based on the sub-feedback data of the trainee for each target training task and the second personal parameter of the trainee, the combined training task for the next training is determined. Through the above method, the trainee determines the difficulty coefficient of the next training based on the total feedback data of the combined training task during each training and the second personal parameter of the trainee. Then, based on the sub-feedback data of each training task during each training and the second personal parameter of the trainee, the combined training task for the next training is determined, and so on in a cycle, and the trainee is trained multiple times.

[0167] Exemplarily, as Figure 5 shown, Figure 5 shows a schematic flow chart of the nth training. The nth training specifically includes:

[0168] 501: Determine the target difficulty coefficient for training the trainee from multiple difficulty coefficients based on the first training data En and the first individual parameter.

[0169] In the embodiment of the present application, when n = 1, the first training data E1 is the total feedback data of the trainee on the target combined training task.

[0170] Specifically, the processing device will obtain the first return table corresponding to the first individual parameter. The first return table is used to record the historical return probabilities of the first individual parameter at each difficulty coefficient. Among them, the difficulty coefficient with a larger historical return probability indicates that using this difficulty coefficient during this training can achieve a better training effect.

[0171] Then, based on the first training data En, the processing device can obtain the historical return probability of the difficulty coefficient corresponding to the first training data En in the first return table. And obtain the historical return probability of any one difficulty coefficient in the first return table. Then, based on the first training data En, determine the target return probability of the difficulty coefficient in the next training. Based on the historical return probability of the difficulty coefficient corresponding to the first training data En and the historical return probability of any one difficulty coefficient, determine the predicted return probability of each difficulty coefficient.

[0172] Specifically, if the current difficulty coefficient is i, then when the next difficulty coefficient is o, the predicted return probability can be expressed by formula (1):

[0173] Po(i, En) = Pi(i, En) + α[Ro + λPh(o, En + 1) - Ph(i, En)] Formula (1)

[0174] Among them, Po(i, En) represents the predicted return probability of the current difficulty coefficient i when the next difficulty coefficient is o. Pi(i, En) represents the actual return probability of the current difficulty coefficient i. Ro represents the reward at the o difficulty level. For example, Ro can be the average correct rate of the answer responses of the trainee population of the first individual parameter during training at the training level o. Ph(o, En + 1) represents the historical return probability of the training level o, and Ph(i, En) represents the historical return probability of the training level i. α represents the learning rate, and its value can vary between [0, 1]. This value reflects the update speed between difficulty coefficients. For example, this value can be assigned 0.5 at the initial difficulty coefficient. λ represents the discount factor, and its value can vary between [0, 1]. It reflects the importance trade-off between the current difficulty coefficient and the next difficulty coefficient. This value can be assigned 0.5 at the initial difficulty coefficient.

[0175] Thus, it is possible to determine the return probability of the current training for the trainee at the next difficulty coefficient for each difficulty coefficient, and then the training level with the maximum predicted return probability, that is, the training level with the minimum risk and the maximum return, can be used as the target difficulty coefficient, that is, the next difficulty coefficient.

[0176] 502: Based on the second training data Fn and the second individual parameter, determine the fourth combined training task from multiple third combined training tasks corresponding to the target difficulty coefficient.

[0177] In the embodiment of the present application, when n is 1, the second training data F1 is the sub-feedback data of the trainee for each target training task.

[0178] Specifically, the processing device will obtain the second return table corresponding to the second individual parameter, and the second return table is used to record the historical return probability of the second individual parameter in each combined training task. Then, based on the second training data Fn and the second return table, determine the fourth combined training task from multiple third combined training tasks corresponding to the target difficulty coefficient. Among them, the method of determining the fourth combined training task based on the second training data Fn and the second return table is similar to the method of determining the target difficulty coefficient based on the first training data En and the first return table in step 501, and will not be elaborated here.

[0179] 503: Display the fourth combined training task to the trainee, and obtain the total feedback data Gn of the trainee after performing the fourth combined training task and the sub-feedback data Hn of each fourth training task.

[0180] In the embodiment of the present application, the display method of the fourth combined training task, the total feedback data Gn of the fourth combined training task, and the acquisition method of the sub-feedback data Hn of each fourth training task are similar to those in step 303, and will not be elaborated here.

[0181] 504: Use the total feedback data Gn of the fourth combined training task as the first training data En+1 for the (n + 1)-th training, and use the sub-feedback data Hn of each fourth training task as the second training data Fn+1 for the (n + 1)-th training, and perform the (n + 1)-th training until multiple trainings are completed.

[0182] In this embodiment, the number of times the trainee receives training can be a preset number of times. Optionally, when the difficulty coefficient of the current training of the trainee reaches the highest difficulty coefficient and the trainee completes the training of multiple combined training tasks corresponding to the highest difficulty coefficient, it is determined that the trainee has completed the above multiple trainings. Among them, the number of combined training tasks corresponding to the highest difficulty coefficient that the trainee needs to complete can be preset based on the expected training effect.

[0183] In summary, in the embodiments of the present application, based on the first individual parameter of the trainee, the basic perception ability of the trainee can be determined. Then, according to the basic perception ability of the trainee and the historical training data, an initial difficulty coefficient for training the trainee is determined from multiple difficulty coefficients. Next, based on the second individual parameter of the trainee, multiple first combined training tasks corresponding to the initial difficulty coefficient in the target scenario can be determined for the trainee, and a target combined training task is determined from the multiple first combined training tasks according to the second individual parameter. Further, multiple target training tasks corresponding to the target combined training task are sequentially presented to the trainee, and the total feedback data of the trainee after performing the target combined training task and the sub-feedback data of each target training task are obtained. Finally, based on the total feedback data of the target combined training task and the sub-feedback data of each target training task, the trainee can be trained multiple times. Among them, the difficulty coefficient of the trainee's next training can be determined according to the total feedback data of the target combined training task and the first individual parameter during each training of the trainee. The target combined training task of the trainee's next training can be determined according to the sub-feedback data of each target training task and the second individual parameter during each training of the trainee. Thus, based on the first individual parameter and the second individual parameter of the trainee, as well as the total feedback data and sub-feedback data of each training, the difficulty coefficient of the next training can be adjusted, and a suitable combined training task can be selected to perform more accurate training for each trainee. Moreover, there is no need to adjust the difficulty coefficient of training step by step, and there are good training effects and training efficiency.

[0184] Referring to Figure 6 , Figure 6 which is a functional module composition block diagram of a multi-task training device provided by an embodiment of the present application. The multi-task training device can be the above-mentioned processing device. As Figure 6 shown, the multi-task training device 600 includes:

[0185] An initial module 601, configured to determine an initial difficulty coefficient for training the trainee from multiple difficulty coefficients based on the first individual parameter of the trainee;

[0186] A training module 602, configured to determine a target combined training task from multiple first combined training tasks corresponding to the initial difficulty coefficient based on the second individual parameter of the trainee;

[0187] Present multiple target training tasks to the trainee, and obtain the total feedback data of the trainee after performing the target combined training task and the sub-feedback data of each target training task;

[0188] Based on the total feedback data of the target combined training task and the sub-feedback data of each target training task, train the trainee multiple times.

[0189] In some possible embodiments, in determining a target combined training task from multiple first combined training tasks corresponding to an initial difficulty coefficient based on a second individual parameter of the trainee, the training module 602 is specifically configured to:

[0190] Obtain multiple first training tasks in a target scenario;

[0191] Determine multiple first combined training tasks according to the preset difficulty coefficients of each first training task in the multiple first training tasks;

[0192] Determine a target combined training task from the multiple first combined training tasks according to the second individual parameter.

[0193] In some possible embodiments, before obtaining multiple first training tasks in a target scenario, the training module 602 is further configured to:

[0194] Determine the perceptual abilities of multiple sensory systems of the trainee according to the second individual parameter;

[0195] Determine the trainee population to which the trainee belongs based on the perceptual abilities of the multiple sensory systems of the trainee;

[0196] Obtain the training scores of the trainee population in multiple training scenarios;

[0197] Use the training scenario with the lowest training score as the target scenario.

[0198] In some possible embodiments, the second individual parameter includes: the perceptual ability of the trainee and the perceptual ability of the trainee to multiple types of stimulus contents;

[0199] In determining a target combined training task from the multiple first combined training tasks according to the second individual parameter, the training module 602 is specifically configured to:

[0200] Obtain multiple sensory systems that support training of the trainee in the target scenario;

[0201] Determine at least one target sensory system from the multiple sensory systems based on the perceptual ability of the trainee;

[0202] Determine multiple initial stimulus contents corresponding to the trainee based on at least one target sensory system and the perceptual ability of the trainee to multiple types of stimulus contents;

[0203] Determine a target combined training task from the multiple first combined training tasks based on the multiple initial stimulus contents.

[0204] In some possible embodiments, in determining at least one target sensory system from the multiple sensory systems based on the perceptual ability of the trainee, the training module 602 is specifically configured to:

[0205] Determine the perceptual ability scores of the trainee in each of the multiple sensory systems based on the trainee's perceptual ability.

[0206] Take at least one sensory system with a perceptual ability score less than the first threshold as at least one target sensory system.

[0207] If the perceptual ability scores of each sensory system are all greater than or equal to the first threshold, take the sensory system with the lowest perceptual ability score as the target sensory system.

[0208] In some possible embodiments, in terms of presenting multiple target training tasks to the trainee, the training module 602 is specifically configured to:

[0209] Determine the presentation order and presentation time interval of the multiple target training tasks;

[0210] Present the multiple target training tasks to the trainee in sequence according to the presentation order and presentation time interval;

[0211] Among them, each target training task is presented in the following manner:

[0212] Present the attention content of the target training task;

[0213] After a preset first time interval, present the multiple training materials corresponding to the target training task in sequence, and insert the buffer content corresponding to the target training task between the presentations of any two adjacent training materials;

[0214] After the presentation of the training materials of the target training task is completed, present the answering interface of each target training task to the trainee for the trainee to make a response.

[0215] In some possible embodiments, in terms of determining the presentation order and presentation time interval of the multiple target training tasks, the training module 602 is specifically configured to:

[0216] Obtain the weighted correct rate of the trainee during the historical training of the multiple target training tasks, and the weighted correct rate is determined by the historical correct rate of each target training task when the trainee performs the multiple target training tasks;

[0217] Determine the presentation time interval based on the weighted correct rate;

[0218] Sort the multiple target training tasks according to the historical correct rate of each target training task, and use the sorted order as the presentation order.

[0219] Refer to Figure 7 , Figure 7 is a schematic structural diagram of an electronic device provided by an embodiment of the present application. AsFigure 7 As shown in the figure, the electronic device 700 includes a transceiver 701, a processor 702, and a memory 703. They are connected through a bus 704. The memory 703 is used to store computer programs and data, and can transmit the data stored in the memory 703 to the processor 702. The electronic device 700 can be the above-mentioned multitask training device 600.

[0220] The processor 702 is used to read the computer program in the memory 703 and perform the following operations:

[0221] Based on the first personal parameter of the trainee, determine the initial difficulty coefficient for training the trainee from multiple difficulty coefficients;

[0222] Based on the second personal parameter of the trainee, determine the target combined training task from multiple first combined training tasks corresponding to the initial difficulty coefficient;

[0223] Show multiple target training tasks to the trainee, and obtain the total feedback data of the trainee after performing the target combined training task and the sub-feedback data of each target training task;

[0224] Based on the total feedback data of the target combined training task and the sub-feedback data of each target training task, train the trainee multiple times.

[0225] In some possible embodiments, in terms of determining the target combined training task from multiple first combined training tasks corresponding to the initial difficulty coefficient based on the second personal parameter of the trainee, the processor 702 is specifically used to perform the following operations:

[0226] Obtain multiple first training tasks in the target scenario;

[0227] According to the preset difficulty coefficient of each first training task in the multiple first training tasks, determine multiple first combined training tasks;

[0228] According to the second personal parameter, determine the target combined training task from the multiple first combined training tasks.

[0229] In some possible embodiments, before obtaining multiple first training tasks in the target scenario, the processor 702 is further used to perform the following operations:

[0230] According to the second personal parameter, determine the perceptual abilities of multiple sensory systems of the trainee;

[0231] Based on the perceptual abilities of multiple sensory systems of the trainee, determine the trainee population to which the trainee belongs;

[0232] Obtain the training scores of the trainee population in multiple training scenarios;

[0233] Take the training scenario with the lowest training score as the target scenario.

[0234] In some possible embodiments, the second individual parameter includes: the perceptual ability of the trainee and the perceptual ability of the trainee to various types of stimulus content;

[0235] In determining the target combined training task among multiple first combined training tasks according to the second individual parameter, the processor 702 is specifically configured to perform the following operations:

[0236] Obtain multiple sensory systems of the trainee that support training in the target scenario;

[0237] Based on the perceptual ability of the trainee, determine at least one target sensory system among multiple sensory systems;

[0238] Based on at least one target sensory system and the perceptual ability of the trainee to various types of stimulus content, determine multiple initial stimulus contents corresponding to the trainee;

[0239] Based on the multiple initial stimulus contents, determine the target combined training task from among the multiple first combined training tasks.

[0240] In some possible embodiments, in determining at least one target sensory system among multiple sensory systems based on the perceptual ability of the trainee, the processor 702 is specifically configured to perform the following operations:

[0241] Based on the perceptual ability of the trainee, determine the perceptual ability score of the trainee for each sensory system among the multiple sensory systems;

[0242] Take at least one sensory system with a perceptual ability score less than the first threshold as at least one target sensory system;

[0243] If the perceptual ability score of each sensory system is greater than or equal to the first threshold, take the sensory system with the lowest perceptual ability score as the target sensory system.

[0244] In some possible embodiments, in presenting multiple target training tasks to the trainee, the processor 702 is specifically configured to perform the following operations:

[0245] Determine the presentation order and presentation time interval of the multiple target training tasks;

[0246] According to the presentation order and presentation time interval, sequentially present the multiple target training tasks to the trainee;

[0247] Among them, each target training task is presented in the following manner:

[0248] Present the attention content of the target training task;

[0249] After a preset first time interval, a plurality of training materials corresponding to the target training task are sequentially displayed, and buffer content corresponding to the target training task is inserted between the display of any two adjacent training materials;

[0250] After the display of the training materials of the target training task is completed, a question answering interface for each target training task is displayed to the trainee for the trainee to make a response.

[0251] In some possible embodiments, in determining the display order and display time interval of a plurality of target training tasks, the processor 702 is specifically configured to perform the following operations:

[0252] Obtain the weighted correct rate of the trainee during the historical training of a plurality of target training tasks, and the weighted correct rate is determined by the historical correct rate of the trainee for each target training task of the plurality of target training tasks;

[0253] Based on the weighted correct rate, determine the display time interval;

[0254] Sort the plurality of target training tasks according to the historical correct rate of each target training task, and use the sorted order as the display order.

[0255] It should be understood that the multi-task training device in this application may include a smart phone, a tablet computer, a palm computer, a notebook computer, a mobile Internet device MID, a robot, or a wearable device, etc. The above multi-task training devices are only examples, not exhaustive, including but not limited to the above training devices. In practical applications, the above multi-task training device may further include: an intelligent vehicle-mounted terminal, a computer device, etc.

[0256] Through the description of the above embodiments, those skilled in the art can clearly understand that the present invention can be implemented by means of software combined with a hardware platform. Based on such an understanding, all or part of the technical solution of the present invention that contributes to the background technology can be embodied in the form of a software product. The computer software product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in various embodiments or some parts of the embodiments of the present invention.

[0257] Therefore, the embodiment of the present application further provides a computer-readable storage medium, and the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement some or all of the steps of any one of the multi-task training methods described in the above method embodiments. For example, the storage medium may include a hard disk, a floppy disk, an optical disk, a magnetic tape, a magnetic disk, a USB flash drive, a flash memory, etc.

[0258] The embodiments of the present application also provide a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program. The computer program is operable to cause a computer to execute some or all of the steps of any one of the multi-task training methods described in the above method embodiments.

[0259] It should be noted that, for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that the present application is not limited by the described action sequence, because according to the present application, some steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily essential to the present application.

[0260] In the above embodiments, the descriptions of the various embodiments have their own emphases. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0261] In several embodiments provided by the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces. The indirect coupling or communication connection of the device or unit can be in an electrical or other form.

[0262] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place, or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0263] In addition, in each embodiment of the present application, the functional units can be integrated into one processing unit, or each unit exists physically alone, or two or more units are integrated into one unit. The above integrated units can be implemented in the form of hardware or in the form of software program modules.

[0264] When the integrated unit is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions for causing a computer device (which can 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 this application. The aforementioned memory includes various media that can store program codes, such as USB flash drives, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), mobile hard disks, magnetic disks, or optical discs.

[0265] Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing relevant hardware through a program. This program can be stored in a computer-readable memory, and the memory can include: flash drives, read-only memories (English: Read-Only Memory, abbreviated: ROM), random access memories (English: Random Access Memory, abbreviated: RAM), magnetic disks, or optical discs, etc.

[0266] The above has introduced the embodiments of this application in detail. Specific examples are used in this article to elaborate on the principles and implementation manners of this application. The description of the above embodiments is only used to help understand the method and its core idea of this application; at the same time, for those of ordinary skill in the art, according to the idea of this application, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation on this application.

Claims

1. A multi-task training method, characterized in that, Including: Determine an initial difficulty coefficient for training the trainee from a plurality of difficulty coefficients based on a first personal parameter of the trainee; Determine a target combined training task from a plurality of first combined training tasks corresponding to the initial difficulty coefficient based on a second personal parameter of the trainee, where the target combined training task includes a plurality of target training tasks; Display the plurality of target training tasks to the trainee, and obtain total feedback data after the trainee performs the target combined training task and sub-feedback data for each target training task; Based on the total feedback data of the target combined training task and the sub-feedback data of each target training task, train the trainee multiple times, where The determining the target combined training task from a plurality of first combined training tasks corresponding to the initial difficulty coefficient based on the second personal parameter of the trainee includes: Obtain a plurality of first training tasks in a target scenario; the target scenario is the training scenario of the trainee; Determine the plurality of first combined training tasks according to the preset difficulty coefficients of each first training task in the plurality of first training tasks, where each first combined training task is composed of a plurality of second training tasks, and the second training task is any one of the plurality of first training tasks, and the product of the preset difficulty coefficients of the second training tasks constituting each first combined training task is equal to the initial difficulty coefficient; Determine the target combined training task from the plurality of first combined training tasks according to the second personal parameter.

2. The method according to claim 1, wherein Before obtaining the plurality of first training tasks in the target scenario, the method further includes: Determine the perceptual abilities of multiple sensory systems of the trainee according to the second personal parameter; Determine the trainee population to which the trainee belongs based on the perceptual abilities of the trainee's multiple sensory systems; Obtain the training scores of the trainee population in multiple training scenarios; Use the training scenario with the lowest training score as the target scenario.

3. The method according to claim 1, wherein The second personal parameter includes: the perceptual ability of the trainee and the perceptual ability of the trainee to multiple types of stimulus content; The determining the target combined training task from the plurality of first combined training tasks according to the second personal parameter includes: Obtain multiple sensory systems that support training of the trainee in the target scenario; Determine at least one target sensory system from the multiple sensory systems based on the perceptual ability of the trainee; Determine a plurality of initial stimulus contents corresponding to the trainee based on the at least one target sensory system and the perceptual ability of the trainee to the multiple types of stimulus content; the initial stimulus content is any one of the multiple types of stimulus content; Determine the target combined training task from the plurality of first combined training tasks based on the plurality of initial stimulus contents; where the multiple target training tasks of the target combined training task correspond one-to-one to the plurality of initial stimulus contents.

4. The method according to claim 3, wherein The determining at least one target sensory system from the multiple sensory systems based on the perceptual ability of the trainee includes: Determine the perceptual ability scores of the trainee in each of the multiple sensory systems based on the trainee's perceptual ability; Take at least one sensory system with a perceptual ability score less than the first threshold as the at least one target sensory system; If the perceptual ability scores of each sensory system are greater than or equal to the first threshold, take the sensory system with the lowest perceptual ability score as the target sensory system.

5. The method according to any one of claims 1-4, characterized in that, The presenting the multiple target training tasks to the trainee includes: Determine the display order and display time interval of the multiple target training tasks; Present the multiple target training tasks to the trainee in sequence according to the display order and the display time interval; Among them, each target training task is presented in the following manner: Present the attention content of this target training task; After a preset first time interval, present multiple training materials corresponding to this target training task in sequence, and insert buffer content corresponding to this target training task between the presentations of any two adjacent training materials; wherein, the time interval between any buffer content and the training material before this buffer content is the preset second time interval, and the time interval between this buffer content and the training material after this buffer content is the preset third time interval; After the presentation of the training materials of this target training task is completed, present the answering interface of each target training task to the trainee for the trainee to make a response.

6. The method according to claim 5, characterized in that, The determining the display order and display time interval of the multiple target training tasks includes: Obtain the weighted correct rate of the trainee during historical training of the multiple target training tasks, and the weighted correct rate is determined by the historical correct rate of each target training task when the trainee performs the multiple target training tasks; Determine the display time interval based on the weighted correct rate; Sort the multiple target training tasks according to the historical correct rate of each target training task, and use the sorted order as the display order.

7. A multi-task training device, characterized in that, The device includes: An initial module, configured to determine an initial difficulty coefficient for training the trainee from multiple difficulty coefficients based on the first individual parameter of the trainee; A training module, configured to determine a target combined training task from multiple first combined training tasks corresponding to the initial difficulty coefficient based on the second individual parameter of the trainee, and the target combined training task includes multiple target training tasks; Present the multiple target training tasks to the trainee, and obtain the total feedback data of the trainee after performing the target combined training task and the sub-feedback data of each target training task; Perform multiple trainings on the trainee based on the total feedback data of the target combined training task and the sub-feedback data of each target training task, wherein In terms of determining the target combined training task from multiple first combined training tasks corresponding to the initial difficulty coefficient based on the second individual parameter of the trainee, the training module is specifically configured to: Obtain multiple first training tasks in a target scenario; the target scenario is the training scenario of the trainee; Determine the multiple first combined training tasks according to the preset difficulty coefficients of each of the multiple first training tasks, where each first combined training task is composed of multiple second training tasks, the second training task is any one of the multiple first training tasks, and the product of the preset difficulty coefficients of the second training tasks constituting each first combined training task is equal to the initial difficulty coefficient; Determine the target combined training task from the multiple first combined training tasks according to the second individual parameter.

8. An electronic device, characterized in that, It includes a processor, a memory, a communication interface, and one or more programs, where the one or more programs are stored in the memory and are configured to be executed by the processor, and the one or more programs include instructions for performing the steps in the method according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the method according to any one of claims 1-6.

Images