Training Method, Device, Electronic Device and Storage Medium

Abstract

The present application discloses a training method, apparatus, electronic device, and storage medium. The method includes: determining an initial training level of the trainee among a plurality of preset training levels according to the personal parameters of the trainee; presenting a first training topic corresponding to the initial training level to the trainee, and obtaining feedback data of the trainee on the first training topic; and performing multiple trainings on the trainee according to the feedback data and the personal parameters. Using this method, it is possible to accurately match the training corresponding to the initial level for the trainee, determine subsequent training levels according to the performance of the trainee during the training, and then improve the training effect and efficiency.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and particularly to a training method, device, electronic device and storage medium. Background Art

[0002] The ability to maintain short-term information refers to an individual's ability to hold information within a relatively short period of time. This ability is an important component of working memory and is closely related to attention, memory, and executive function, etc. Currently, there are also some cognitive training websites or programs on the market that help people train their own ability to maintain short-term information.

[0003] To meet the training needs of people with different ability levels, cognitive training is usually divided into multiple difficulties. The difficulty of a cognitive task refers to the degree of cognitive resources or effort required to complete a certain task, and it is related to the complexity, abstraction, speed requirements, interference factors, etc. of the task. For cognitive training tasks, difficulty setting is an important factor. An inappropriate difficulty setting will affect the performance, motivation, and emotion of the practitioners. Some studies have shown that the effect of cognitive training presents an inverted U-shaped relationship with the task difficulty, that is, a moderate difficulty can bring the greatest effect, while too low or too high a difficulty will reduce the effect. Tasks that are too simple will lead to the ceiling effect, that is, most practitioners perform well and their abilities cannot be exercised. While tasks that are too difficult will lead to the floor effect, that is, no matter how hard the practitioners try, they cannot complete the tasks. The best difficulty design is to make the difficulty that the practitioners need to exert a certain amount of effort to achieve, and the best learning effect is produced in the process of continuous difficulty-ability mismatch.

[0004] However, the training tasks in existing cognitive training websites or programs start from the same difficulty for all practitioners, and the promotion settings of difficulty levels are often fixed, regardless of whether the practitioners can adapt to the next level, resulting in low training effect and efficiency and poor user experience. Summary of the Invention

[0005] To solve the above problems existing in the prior art, the embodiments of the present application provide a training method, device, electronic device and storage medium, which can accurately match the training of the corresponding initial level for the trainees and determine the subsequent training levels according to the performance of the trainees in the training, thereby improving the training effect and efficiency.

[0006] In a first aspect, an embodiment of the present application provides a training method, which includes:

[0007] Determine the initial training level of the trainee among a plurality of preset training levels according to the personal parameters of the trainee;

[0008] Show the first training topic corresponding to the initial training level to the trainee, and obtain the feedback data of the trainee on the first training topic;

[0009] Conduct multiple trainings on the trainee according to the feedback data and personal parameters;

[0010] Among them, the i-th training includes:

[0011] Determine the target training level Ci in the candidate training level pool Bi according to the training data Ai and personal parameters. Among them, when i = 1, the training data A1 is the feedback data of the first training topic, and the candidate training level pool B1 is the remaining training levels after removing the initial training level from multiple training levels;

[0012] Show the second training topic corresponding to the target training level Ci to the trainee, and obtain the target feedback data Di of the trainee on the second training topic;

[0013] Take the target feedback data Di of the second training topic as the training data Ai+1 of the (i + 1)-th training, remove the target training level Ci from the candidate training level pool Bi to obtain the candidate training level pool Bi+1, and conduct the (i + 1)-th training until multiple trainings are completed.

[0014] In a possible implementation manner, determining the initial training level of the trainee among the preset multiple training levels according to the personal parameters of the trainee includes:

[0015] Determine the first group to which the trainee belongs according to the personal parameters;

[0016] Determine the coefficients of the random error and personal parameters according to the first group;

[0017] Determine the initial training level of the trainee among the multiple training levels according to the personal parameters, coefficients and random error.

[0018] In a possible implementation manner, the personal parameters include: age, gender, basic cognitive ability, achievement motivation characteristics, stress level and sleep quality. Based on this, determining the coefficients of the personal parameters according to the first group includes:

[0019] Determine the contribution rates of age, gender, basic cognitive ability, achievement motivation characteristics, stress level and sleep quality to training respectively according to the historical training data of the first group;

[0020] Normalize the contribution rates corresponding to age, gender, basic cognitive ability, achievement motivation characteristics, stress level and sleep quality to obtain the respective coefficients of age, gender, basic cognitive ability, achievement motivation characteristics, stress level and sleep quality.

[0021] In a possible implementation, a first training topic corresponding to an initial training level is presented to a trainee, and feedback data of the trainee on the first training topic is obtained, including:

[0022] Obtain training pictures according to the first training topic;

[0023] Present a fixation point to the trainee so that the trainee fixates on the fixation point;

[0024] After a preset first time interval, present the training pictures to the trainee;

[0025] After a preset second time interval, present a blank interface to the trainee;

[0026] After a preset third time interval, present a question answering interface to the trainee, where the question answering interface includes training questions and answer options, and the training questions are related to the training pictures;

[0027] Receive the operation data of the trainee on the answer options, and use the operation data and the time used for this training as feedback data.

[0028] In a possible implementation, a target training level Ci is determined in a candidate training level pool Bi according to training data Ai and personal parameters, including:

[0029] Determine the second group to which the trainee belongs according to personal parameters;

[0030] Obtain the payoff table of the second group, where the payoff table is used to record the payoff probabilities of the second group at each training level;

[0031] Determine the target training level Ci in the candidate training level pool Bi according to the training data Ai and the payoff table.

[0032] In a possible implementation, a target training level Ci is determined in a candidate training level pool Bi according to training data Ai and the payoff table, including:

[0033] Determine the predicted payoff probability of the first training level according to the training data Ai and the payoff table, where the first training level is any one of the candidate levels in the candidate training level pool Bi;

[0034] Use the training level corresponding to the maximum value in the predicted payoff probabilities as the target training level Ci.

[0035] In a possible implementation, determining the predicted payoff probability of the first training level according to the training data Ai and the payoff table includes:

[0036] Obtain the first historical payoff probability corresponding to the first training level in the payoff table;

[0037] Obtain the second historical return probability corresponding to the second training level in the return table, where the second training level is the training level corresponding to the training data Ai;

[0038] Obtain the training parameters of the second group for the first training level, where the training parameters are used to identify the degree of performance of the second group when performing the training tasks of the first training level;

[0039] Determine the actual return probability of the second training level according to the training data Ai;

[0040] Determine the predicted return probability of the first training level according to the first historical return probability, the second historical return probability, the training parameters, and the actual return probability.

[0041] In a second aspect, an embodiment of the present application provides a training device, including:

[0042] An initial module for determining the initial training level of the trainee in a preset plurality of training levels according to the personal parameters of the trainee;

[0043] A training module for presenting the first training task corresponding to the initial training level to the trainee, obtaining the feedback data of the trainee on the first training task, and performing multiple trainings on the trainee according to the feedback data and the personal parameters;

[0044] Wherein, in the i-th training, the training module is used for:

[0045] Determine the target training level Ci in the candidate training level pool Bi according to the training data Ai and the personal parameters, where when i = 1, the training data A1 is the feedback data of the first training task, and the candidate training level pool B1 is the remaining training levels after removing the initial training level from the plurality of training levels;

[0046] Present the second training task corresponding to the target training level Ci to the trainee, and obtain the target feedback data Di of the trainee on the second training task;

[0047] Use the target feedback data Di of the second training task as the training data Ai+1 for the (i + 1)-th training, remove the target training level Ci from the candidate training level pool Bi to obtain the candidate training level pool Bi+1, and perform the (i + 1)-th training until multiple trainings are completed.

[0048] 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 in the first aspect.

[0049] 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 as described in the first aspect.

[0050] 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 as described in the first aspect.

[0051] Implementing the embodiments of the present application has the following beneficial effects:

[0052] In the embodiment of the present application, by determining the user characteristics of the trainee according to the personal parameters of the trainee, and then according to the historical test data of the people with the same characteristics, a suitable initial training level is determined for the trainee among a plurality of preset training levels. Then, the first training topic corresponding to the initial training level is presented to the trainee, and the feedback data of the trainee on the first training topic is obtained. Finally, the trainee is trained multiple times according to the feedback data and personal parameters. Specifically, according to the feedback data and personal parameters of each training of the trainee, the most suitable training level can be determined from the remaining training levels as the level for the next training. Thus, through personal parameters, the historical data of the people similar to the trainee in the historical training is obtained as a reference for determining the level, and at the same time, combined with the feedback data, when determining the next level, the personal characteristics and group characteristics of the trainee can be taken into account at the same time, and then a more accurate training level is obtained to train the trainee. Compared with the existing fixed-level mode, each level received by the trainee in this solution can play a good training role for the trainee, without wasting time in inappropriate training levels, and can take into account both good training effects and high training efficiency, and greatly improves the user experience of the trainee. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order 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 following drawings are some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained according to these drawings without creative efforts.

[0054] Figure 1 It is a schematic diagram of a training system provided by an embodiment of the present application;

[0055] Figure 2 It is a schematic diagram of the basic process of a training task provided by an embodiment of the present application;

[0056] Figure 3Schematic flowchart of a training method provided by an embodiment of the present application;

[0057] Figure 4 Schematic diagram of training by presenting a first training topic to a user provided by an embodiment of the present application;

[0058] Figure 5 Schematic flowchart of the i-th training provided by an embodiment of the present application;

[0059] Figure 6 Block diagram of the functional modules of a training device provided by an embodiment of the present application;

[0060] Figure 7 Schematic diagram of the structure of an electronic device provided by an embodiment of the present application. Specific embodiments

[0061] 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. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts fall within the scope of protection of the present application.

[0062] The terms "first", "second", "third", "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 "include" and "have" 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.

[0063] Referring to "embodiments" herein means that the specific features, results, or characteristics described in connection with the embodiments may be included in at least one embodiment of the present application. The phrase appears in various places in the specification and 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 will explicitly and implicitly understand that the embodiments described herein may be combined with other embodiments.

[0064] First, refer to Figure 1 , Figure 1 Schematic diagram of a training system provided by an embodiment of the present application.

[0065] Exemplarily, the training system may include a training device, a processing device, and a database. Among them, the training device may be an operable device with a display function such as a smart phone (such as an Android phone, an iOS phone, a Windows Phone), a tablet computer, a personal digital assistant, a laptop computer, a mobile Internet device MID (Mobile Internet Devices), a robot, or a wearable device, etc. The present application does not make specific limitations thereto. The processing device may be a server. For example, it may be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery network (CDN), and big data and artificial intelligence platforms. The present application does not make specific limitations thereto. The database may also be a server or a memory that provides data storage services. For example: a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM), or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disk storage media, or any other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer. The present application also does not make specific limitations thereto.

[0066] Specifically, the trainee can initiate a training request through the training device. After receiving the training request, the training device obtains the identity identifier of the trainee. For example, the identity identifier of the trainee can be obtained through login ID, facial recognition, fingerprint recognition, etc. Then, the training device sends the identity identifier and the training request to the processing device. The processing device obtains the personal parameters of the trainee from the database according to the identity identifier, and determines the initial training level of the trainee according to the personal parameters. Then, the processing device obtains the corresponding materials from the database according to the initial training level, and generates a first training topic to be sent to the training device for display to the trainee through the training device. The trainee can train by operating the training device in response to the displayed first training topic. The training device collects the data of the trainee during the training process as the feedback data of the trainee on the first training topic. Then, the training device sends the feedback data to the processing device, and the processing device determines the next training level of the trainee. Thus, by repeating the above process of obtaining materials, generating training topics, displaying training topics, obtaining feedback data, and determining the next training level, the trainee is trained multiple times.

[0067] Thus, through the personal parameters, the historical data of the people similar to the trainee in previous trainings is obtained as a reference for determining the level. At the same time, combined with the feedback data, when determining the next level, the personal characteristics and group characteristics of the trainee can be taken into account, and then a more accurate training level can be obtained to train the trainee, improving the training efficiency and training effect.

[0068] Secondly, it should be noted that the training method provided by the embodiment of the present application can be applied to scenarios where abilities such as short-term information maintenance ability, flexibility ability, and comprehension ability can be trained. Hereinafter, taking the training scenario of short-term information maintenance ability as an example, a training method proposed by the present application will be described. The training methods in other scenarios are similar to those in the training scenario of short-term information maintenance ability and will not be elaborated here.

[0069] In this embodiment, the short-term information maintenance ability refers to the ability of an individual to maintain information within a relatively short period of time. The short-term information maintenance ability is an important component of working memory and is closely related to attention, memory, and executive function, etc. In existing cognitive training tasks for short-term information maintenance ability, there are often multiple cognitive components mixed together. For example, in the most commonly used N-back task in current working memory training, individuals are required to judge whether the current stimulus is the same as a certain previous stimulus when observing a series of stimuli (such as letters, graphics, sounds, etc.); the N-back task contains three main cognitive components: information maintenance, updating, and interference suppression. Different cognitive function components compete for cognitive resources such as attention, memory, and executive control. When a training task involves multiple cognitive function components, the practitioner needs to allocate cognitive resources, which will lead to a decline in the training effect on specific cognitive functions. Moreover, due to the stronger form specificity of complex training tasks with multiple cognitive components, the transfer range of the training effect will be narrower. Suppose a certain muscle in the body atrophies. One way is to mobilize multiple muscles for complex exercise training (such as playing badminton), while the other way is to train only the specific muscle. The effect of the latter way may be more significant, require less time, and can have a transfer effect in various situations where short-term information maintenance is required.

[0070] At the same time, existing cognitive training tasks for information maintenance ability only use one or a few types of task forms and do not combine the individual's life experience and background knowledge, resulting in the training effect often being reflected only in the same cognitive domain or similar tasks and being difficult to extend to other cognitive domains or life practices. For example: The Memory Match game has only one form, which is geometric figures of different shapes in different colors.

[0071] In this embodiment, based on the defects of previous cognitive training tasks, a training method for short-term information maintenance ability based on the delayed matching task is designed. Specifically, this is an experimental method for short-term memory and working memory. The classic paradigm process of this task is as follows: The subject first sees a sample stimulus. After a period of delay, the subject then sees two or more comparison stimuli and needs to select one that is the same as or similar to the sample stimulus to obtain a reward or feedback. The delayed matching task mainly involves the short-term maintenance ability of short-term information and does not involve cognitive function components such as updating, impulse inhibition, and flexibility.

[0072] Specifically, such as Figure 2As shown, based on the delayed matching task paradigm, this embodiment has gamified this task paradigm and modified it into a short-term memory training task suitable for different populations. The basic process of the training task is that the subject encodes and memorizes information within a short period of time. After a period of time, the subject recognizes the information content again. The specific process consists of five steps: attention preparation (fixation point) - presentation of multiple picture materials (information encoding and memorization) - short-term delay (interference can be inserted) - judgment response to the presented single picture (whether it appeared during the information encoding stage) - feedback on the subject's response (correct or incorrect).

[0073] In this embodiment, the information materials used in cognitive training are closely related to and diverse in life practice. The information materials can be any materials that can stimulate the memory of the trainees, such as images, sounds, colors, etc. At the same time, in order to prevent strategies from emerging after getting familiar with the information materials, the content of the information materials includes both concrete and abstract types. Taking image materials as an example, the concrete materials have 9 categories, namely clothing, tools, daily necessities, food, toys, fruits and vegetables, flowers and plants, sports supplies, transportation tools, and marine organisms, all of which are related to daily life and can help practitioners better handle memory tasks related to daily life. The abstract materials have 4 categories, namely letters, abstract symbols, abstract graphics, and radicals. Thus, it is possible to prevent practitioners from using specific strategies to memorize information, thereby expanding the adaptive range of information maintenance ability.

[0074] In this embodiment, difficulty gradients are set from 4 dimensions, namely the content of the information, the presentation time of the information, the quantity of the information, and whether there is interfering information. According to the principles of cognitive psychology, the difficulty gradients show a slow progressive increase in small steps, which conforms to the training rules of the general population. Practitioners will gradually improve their information maintenance ability in different situations, enabling practitioners to be continuously challenged. This can maintain the interest and motivation of practitioners, promote the sense of achievement of practitioners, and improve the cognitive ability and training effect of practitioners.

[0075] According to the 4 dimensions of the quantity of materials, the content of materials, the delay time, and whether there is interference, the training program in this application divides 40 levels of difficulty. Among them, the quantity of materials presented in the pictures has five levels, namely 3, 4, 5, 6, and 7 materials; the content of the picture materials has two levels, namely concrete materials and abstract materials; the delay time has two levels, namely a 3-second delay and a 5-second delay; whether there is interference has two levels, with or without. Different levels of the four elements will produce 40 combinations, which constitute 40 difficulty levels of the training program, as shown in Table 1:

[0076] Table 1:

[0077]

[0078]

[0079]

[0080] It should be noted that the above 40-level difficulty is only an example for helping to understand the implementation manner of the present application, and does not represent a limitation on the division of the difficulty level in the solution proposed by the present application. In actual application, the number of elements can be adjusted according to the actual situation, and the element level can also be adjusted, and then difficulty levels of other orders of magnitude can be obtained, and the present application does not limit this.

[0081] In this implementation manner, other display methods are also applicable to the present application, and the present application does not limit this.

[0082] Specifically, the presentation manner of multiple picture materials can be tiled on the display interface at the same size simultaneously, or can be dispersed in different visual field ranges at different sizes, increasing the visual search range and improving the encoding difficulty.

[0083] The interference information can be information unrelated to the stimulus material to be memorized, such as text, mathematical calculations, sounds, images, etc. The appearance position can be given synchronously when presenting the picture, or can be given during a short delay time.

[0084] The delay time can vary, and the judgment rule can also be changed. For example, the subject is required to identify pictures that have not appeared in the pictures.

[0085] The process can add steps for processing the stimulus material, such as calculating the numbers in the material, rearranging the graphics, spatial flipping, etc.

[0086] The following will combine the above training scenarios for short-term information maintenance ability to detail a training method proposed by the present application.

[0087] Refer to Figure 3 , Figure 3 which is a schematic flowchart of a training method provided for the implementation manner of the present application. This method is applied to the training system in the above implementation manner. This training method may include the following steps:

[0088] 301: Determine the initial training level of the trainee among a plurality of preset training levels according to the personal parameters of the trainee.

[0089] In this embodiment, the personal parameters of the trainee can be confirmed through the identity identifier obtained by the training device. Specifically, the processing device can perform a match in the database through this identity identifier to obtain the personal parameters corresponding to this identity identifier. If the personal parameters cannot be matched in the database, a personal parameter acquisition request can be sent to the trainee through the training device, enabling the trainee to input the required personal parameters through the training device.

[0090] In this embodiment, the personal parameters may include: age, gender, basic cognitive ability, achievement motivation characteristics, stress level, and sleep quality. Exemplarily, the basic cognitive ability can be evaluated through the performance of the trainee in the sustained attention task (Flanker) and the digit span task (Digit Span); the achievement motivation characteristics of the trainee can be measured through the achievement motivation questionnaire (ASM); the life stress level of the trainee can be evaluated through the stress perception self-report scale; and the sleep quality of the trainee in the past month can be evaluated through the Pittsburgh Sleep Quality Index scale.

[0091] In this embodiment, after obtaining the personal parameters, first, the first group to which the trainee belongs can be determined according to the personal parameters. Exemplarily, based on the age, gender, basic cognitive ability, and achievement motivation characteristics in the personal parameters, a personal portrait of the trainee can be generated, and then the similarity between this personal portrait and the group portraits of each group in the database can be calculated, and the group corresponding to the group portrait with the highest similarity is used as the first group.

[0092] Then, the coefficients of the random error and the personal parameters can be determined according to the first group. Specifically, for the random error, the maximum and minimum values of the random error used by this first group when calculating the initial training level can be obtained, and then the range between this maximum and minimum value is used as the generation range of the random error used in this calculation of the initial training level, and a value is randomly obtained within this range as the random error ε used in this calculation. At the same time, according to the historical training data of the first group, the contribution rates of age, gender, basic cognitive ability, achievement motivation characteristics, stress level, and sleep quality to training are determined respectively, and then the contribution rates corresponding to age, gender, basic cognitive ability, achievement motivation characteristics, stress level, and sleep quality are normalized to obtain the respective coefficients of age, gender, basic cognitive ability, achievement motivation characteristics, stress level, and sleep quality.

[0093] Finally, the initial training level of the trainee can be determined from multiple training levels according to this personal parameter, coefficient, and random error. Specifically, the initial training level can be represented by formula ①:

[0094] Y = β1X1 + β2X2 + β3X3 + β4X4 + β5X5 + β6X6 + ε………①

[0095] Among them, Y represents the initial training level, X1 - X6 respectively represent the values after quantification of age, gender, basic cognitive ability, achievement motivation characteristics, stress level, and sleep quality, β1 - β6 respectively represent the coefficients of age, gender, basic cognitive ability, achievement motivation characteristics, stress level, and sleep quality, and ε represents the random error.

[0096] In this embodiment, through the above calculation, the training level Y can be obtained. Subsequently, the initial training level can be determined based on the Y value in Table 1. For example: if the Y value is 16, the training level is the 16th level.

[0097] 302: Show the first training topic corresponding to the initial training level to the trainee, and obtain the feedback data of the trainee on the first training topic.

[0098] In this embodiment, according to the initial training level, the material requirements and training rules of this training level can be determined. Subsequently, the first training topic is determined according to the material requirements, and the first training topic is shown to the trainee according to the training rules. Exemplarily, when the initial training level is the 16th level, according to the records in Table 1, its material requirements are: 4 abstract pictures, and the training rule is: 5 - second delay, with interference. Then the first training topic is the memory maintenance recognition of 4 abstract pictures under interference.

[0099] In this embodiment, after determining the first training topic, the training pictures can be obtained according to the first training topic. Continuing with the above example where the first training topic is the memory maintenance recognition of 4 abstract pictures under interference, 4 images are randomly obtained from the abstract picture library as training pictures. Then, as Figure 4As shown, a fixation point is displayed at the center of the display interface to enable the trainee to fixate on the fixation point and help the subject concentrate. After a preset first time interval, which can be 1 second, training pictures are shown to the trainee. Four abstract pictures are simultaneously displayed on the display interface in the same size. After a preset second time interval, which can be 5 seconds, a blank interface is shown to the trainee, meaning the trainee has 5 seconds to observe and memorize the 4 abstract pictures shown. After a preset third time interval, a question-and-answer interface is shown to the trainee. This third time interval is the delay time, which is determined by the training rules corresponding to the training level and is 5 seconds in this example. Meanwhile, in this example, due to the presence of interference, some interference items can be inserted during this delay time to interfere with the trainee. For example: showing other images different from the 4 abstract pictures, simple math calculation problems, a piece of text, etc. The question-and-answer interface includes training questions and answer options. Among them, the training questions are related to the training pictures. For example: a picture can be shown and the trainee is asked whether the picture is among the 4 abstract pictures shown just now. The insertion time and duration of the interference can be randomly determined, as long as it is ensured that the sum of the delay time and the interference time remains at 5 seconds after the interference is inserted. In a training task, multiple such question-and-answer sessions can be set, and then the operation data of the trainee's answer options in multiple question-and-answer sessions is received, and the operation data and the time used in this training are used as feedback data.

[0100] 303: Conduct multiple trainings on the trainee according to the feedback data and personal parameters;

[0101] In this embodiment, the feedback data can be the answering accuracy rate and time used by the trainee in the training task. Thus, the feedback data can indicate the performance of the trainee at this training level. Therefore, according to this feedback data and the personal parameters of the trainee, the next training level of the trainee can be determined among the remaining levels. Similarly, after the trainee completes the training of the next training level, the next-next training level can also be determined according to the feedback data of the trainee in the training of the next training level, combined with his personal parameters. In this way, it goes round and round, conducting multiple trainings on the trainee until the trainee reaches the highest training level or when the next training level cannot be determined, and then the training ends.

[0102] Specifically, as Figure 5 shown, Figure 5 shows a schematic flow diagram of the i-th training. The i-th training specifically includes:

[0103] 501: Determine the target training level Ci in the candidate training level pool Bi according to the training data Ai and personal parameters.

[0104] In this embodiment, when i = 1, the training data A1 is the feedback data of the first training topic, and the candidate training level pool B1 is the remaining training levels after removing the initial training level from multiple training levels.

[0105] Specifically, first, the second group to which the trainee belongs can be determined according to personal parameters. The method for determining the second group is similar to the method for determining the first group in step 301, and will not be elaborated here. Then, obtain the return table of the second group, which is used to record the return probabilities of the second group at each training level. Finally, according to the training data Ai and the return table, determine the target training level Ci in the candidate training level pool Bi.

[0106] In this embodiment, the return probability is the average value of the return probabilities of each training level calculated by each individual in the second group during training. In short, if there are 3 individuals in the second group, namely: individual 1, individual 2, and individual 3. Among them, during the training process of individual 1, the return probability of training level E is E1; during the training process of individual 2, the return probability of training level E is E2; during the training process of individual 3, the return probability of training level E is E3. Then, for the second group, the return probability of training level E is the average of E1, E2, and E3. And by organizing the return probabilities of each training level of this group into a table, the return table of each group can be obtained.

[0107] Based on this, in this embodiment, the predicted return probability of the first training level can be determined according to the training data Ai and the return table. The first training level can be any candidate level in the candidate training level pool Bi. Exemplarily, the first historical return probability corresponding to the first training level can be obtained from the return table, and the second historical return probability corresponding to the second training level can be obtained from the return table. The second training level is the training level corresponding to the training data Ai, or in other words, this training level is the training level of the currently executed training task. Then, obtain the training parameter of the second group for the first training level, which is used to identify the degree of performance of the second group when performing the training topic of the first training level. In this embodiment, the average correct rate can be used instead. Then, determine the actual return probability of the second training level according to the training data Ai. Finally, determine the predicted return probability of the first training level according to the first historical return probability, the second historical return probability, the training parameter, and the actual return probability.

[0108] Specifically, if the current training level is t, then when the next training level is u, the predicted return probability can be expressed by formula ②:

[0109] Q y (S t ,A t )=Qs (S t , A t ) + α[R u + λQ h (S u , A u ) - Q h (S t , A t )]………②

[0110] Among them, Qy(St, At) represents the predicted return probability when the current training level is t and the next training level is u, Qs(St, At) represents the actual return probability of the current training level t, Ru represents the average correct rate of the second group at the training level u, Qh(Su, Au) represents the first historical return probability of the training level u, Qh(St, At) represents the second historical return probability of the training level t, α represents the learning rate, and its value can vary between [0, 1]. This value reflects the update speed between training levels. In this embodiment, this value can be assigned 0.5 at the initial level. λ represents the discount factor, and its value can vary between [0, 1], reflecting the importance trade-off between new and old training levels. This value can be assigned 0.5 at the initial level.

[0111] Thus, for each candidate training level, the return probability of the current training for the trainee when this training level is the next level can be calculated. Subsequently, the maximum value in the predicted return probabilities, that is, the training level with the minimum risk and the maximum return, can be used as the target training level Ci, which is the next training level.

[0112] 502: Show the second training topic corresponding to the target training level Ci to the trainee, and obtain the target feedback data Di of the trainee for the second training topic.

[0113] In this embodiment, the display method and the acquisition method of the target feedback data Di are similar to the display method and the acquisition method of the feedback data in step 302, and will not be elaborated here.

[0114] 503: Use the target feedback data Di of the second training topic as the training data Ai+1 for the (i + 1)-th training, remove the target training level Ci from the candidate training level pool Bi to obtain the candidate training level pool Bi+1, and conduct the (i + 1)-th training until multiple trainings are completed.

[0115] In this embodiment, when the current training level is the highest training level, it can be determined that the trainee has completed multiple trainings; or, when the next level determined by the trainee for n consecutive times is less than or equal to the current level, it is determined that the current level is already the limit level acceptable to the trainee, and it is determined that the trainee has completed multiple trainings. Among them, the value of n can be determined according to the actual application scenario requirements, and the present application does not limit this.

[0116] In summary, in the training method provided by the present invention, by determining the user characteristics of the trainee according to the personal parameters of the trainee, and then according to the historical test data of the people with the same characteristics, a suitable initial training level is determined for the trainee among the preset multiple training levels. Then, the first training topic corresponding to the initial training level is displayed to the trainee, and the feedback data of the trainee on the first training topic is obtained. Finally, multiple trainings are carried out on the trainee according to the feedback data and personal parameters. Specifically, according to the feedback data and personal parameters of each training of the trainee, the most suitable training level is determined from the remaining training levels as the level for the next training. Thus, through personal parameters, the historical data of the people similar to the trainee in the historical training is obtained as a reference for determining the level, and at the same time, combined with the feedback data, when determining the next level, the personal characteristics and group characteristics of the trainee can be taken into account at the same time, and then a more accurate training level is obtained to train the trainee. Compared with the existing fixed-level mode, each level received by the trainee in this solution can play a good training role for the trainee, without wasting time in inappropriate training levels, which helps to maintain the trainee's sense of challenge and achievement, and then can take into account better training effects and higher training efficiency at the same time, and greatly improves the user experience of the trainee.

[0117] Refer to Figure 6 , Figure 6 which is a block diagram of the functional modules of a training device provided by an embodiment of the present application. As Figure 6 shown, the training device 600 includes:

[0118] An initial module 601, configured to determine the initial training level of the trainee among the preset multiple training levels according to the personal parameters of the trainee;

[0119] A training module 602, configured to display the first training topic corresponding to the initial training level to the trainee, obtain the feedback data of the trainee on the first training topic, and perform multiple trainings on the trainee according to the feedback data and personal parameters;

[0120] Among them, in the i-th training, the training module 602 is specifically configured to:

[0121] Determine the target training level Ci in the candidate training level pool Bi according to the training data Ai and personal parameters, where when i = 1, the training data A1 is the feedback data of the first training topic, and the candidate training level pool B1 is the remaining training levels after removing the initial training level from multiple training levels;

[0122] Show the second training topic corresponding to the target training level Ci to the trainee, and obtain the target feedback data Di of the trainee for the second training topic;

[0123] Use the target feedback data Di of the second training topic as the training data Ai+1 for the (i + 1)-th training, remove the target training level Ci from the candidate training level pool Bi to obtain the candidate training level pool Bi+1, and perform the (i + 1)-th training until multiple trainings are completed.

[0124] In an embodiment of the present invention, in determining the initial training level of the trainee among a preset plurality of training levels according to the personal parameters of the trainee, the initial module 601 is specifically configured to:

[0125] Determine the first group to which the trainee belongs according to the personal parameters;

[0126] Determine the coefficients of the random error and the personal parameters according to the first group;

[0127] Determine the initial training level of the trainee among multiple training levels according to the personal parameters, the coefficients, and the random error.

[0128] In an embodiment of the present invention, the personal parameters include: age, gender, basic cognitive ability, achievement motivation characteristics, stress level, and sleep quality. Based on this, in determining the coefficients of the personal parameters according to the first group, the initial module 601 is specifically configured to:

[0129] Determine the contribution rates of age, gender, basic cognitive ability, achievement motivation characteristics, stress level, and sleep quality to training respectively according to the historical training data of the first group;

[0130] Normalize the contribution rates corresponding to age, gender, basic cognitive ability, achievement motivation characteristics, stress level, and sleep quality to obtain the respective coefficients of age, gender, basic cognitive ability, achievement motivation characteristics, stress level, and sleep quality.

[0131] In an embodiment of the present invention, in showing the first training topic corresponding to the initial training level to the trainee and obtaining the feedback data of the trainee for the first training topic, the training module 602 is specifically configured to:

[0132] Obtain training pictures according to the first training topic;

[0133] Show the fixation point to the trainee so that the trainee fixates on the fixation point;

[0134] After a preset first time interval, show the training picture to the trainee;

[0135] After a preset second time interval, show a blank interface to the trainee;

[0136] After a preset third time interval, show the answering interface to the trainee, where the answering interface includes training questions and answer options, and the training questions are related to the training pictures;

[0137] Receive the operation data of the trainee on the answer options, and use the operation data and the time used for this training as feedback data.

[0138] In an embodiment of the present invention, in determining the target training level Ci in the candidate training level pool Bi according to the training data Ai and personal parameters, the training module 602 is specifically configured to:

[0139] Determine the second group to which the trainee belongs according to the personal parameters;

[0140] Obtain the return table of the second group, where the return table is used to record the return probabilities of the second group at each training level;

[0141] Determine the target training level Ci in the candidate training level pool Bi according to the training data Ai and the return table.

[0142] In an embodiment of the present invention, in determining the target training level Ci in the candidate training level pool Bi according to the training data Ai and the return table, the training module 602 is specifically configured to:

[0143] Determine the predicted return probability of the first training level according to the training data Ai and the return table, where the first training level is any one of the candidate levels in the candidate training level pool Bi;

[0144] Use the training level corresponding to the maximum value in the predicted return probabilities as the target training level Ci.

[0145] In an embodiment of the present invention, in determining the predicted return probability of the first training level according to the training data Ai and the return table, the training module 602 is specifically configured to:

[0146] Obtain the first historical return probability corresponding to the first training level in the return table;

[0147] Obtain the second historical return probability corresponding to the second training level in the return table, where the second training level is the training level corresponding to the training data Ai;

[0148] Obtain the training parameters of the second group for the first training level, where the training parameters are used to identify the degree of performance of the second group when performing the training tasks of the first training level;

[0149] Determine the actual return probability of the second training level according to the training data Ai;

[0150] Determine the predicted return probability of the first training level according to the first historical return probability, the second historical return probability, the training parameters and the actual return probability.

[0151] Refer to Figure 7 , Figure 7 which is a schematic structural diagram of an electronic device provided by an embodiment of the present application. As Figure 7 shown, 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.

[0152] The processor 702 is used to read the computer program in the memory 703 and perform the following operations:

[0153] Determine the initial training level of the trainee among a preset plurality of training levels according to the personal parameters of the trainee;

[0154] Show the first training task corresponding to the initial training level to the trainee, and obtain the feedback data of the trainee on the first training task;

[0155] Train the trainee multiple times according to the feedback data and personal parameters;

[0156] Wherein, the i-th training includes:

[0157] Determine the target training level Ci in the candidate training level pool Bi according to the training data Ai and personal parameters, where when i = 1, the training data A1 is the feedback data of the first training task, and the candidate training level pool B1 is the remaining training levels after removing the initial training level from the multiple training levels;

[0158] Show the second training task corresponding to the target training level Ci to the trainee, and obtain the target feedback data Di of the trainee on the second training task;

[0159] Use the target feedback data Di of the second training task as the training data Ai+1 for the (i + 1)-th training, remove the target training level Ci from the candidate training level pool Bi to obtain the candidate training level pool Bi+1, and perform the (i + 1)-th training until multiple trainings are completed.

[0160] In an embodiment of the present invention, in determining the initial training level of a trainee among a plurality of preset training levels according to the personal parameters of the trainee, the processor 702 is specifically configured to perform the following operations:

[0161] Determine the first group to which the trainee belongs according to the personal parameters;

[0162] Determine the coefficients of the random error and the personal parameters according to the first group;

[0163] Determine the initial training level of the trainee among the plurality of training levels according to the personal parameters, the coefficients, and the random error.

[0164] In an embodiment of the present invention, the personal parameters include: age, gender, basic cognitive ability, achievement motivation characteristics, stress level, and sleep quality. Based on this, in determining the coefficients of the personal parameters according to the first group, the processor 702 is specifically configured to perform the following operations:

[0165] Determine the contribution rates of age, gender, basic cognitive ability, achievement motivation characteristics, stress level, and sleep quality to training respectively according to the historical training data of the first group;

[0166] Normalize the contribution rates corresponding to age, gender, basic cognitive ability, achievement motivation characteristics, stress level, and sleep quality to obtain the respective coefficients of age, gender, basic cognitive ability, achievement motivation characteristics, stress level, and sleep quality.

[0167] In an embodiment of the present invention, in presenting the first training topic corresponding to the initial training level to the trainee and obtaining the feedback data of the trainee on the first training topic, the processor 702 is specifically configured to perform the following operations:

[0168] Obtain training pictures according to the first training topic;

[0169] Present a fixation point to the trainee so that the trainee fixates on the fixation point;

[0170] After a preset first time interval, present the training pictures to the trainee;

[0171] After a preset second time interval, present a blank interface to the trainee;

[0172] After a preset third time interval, present a question answering interface to the trainee, where the question answering interface includes training questions and answer options, and the training questions are related to the training pictures;

[0173] Receive the operation data of the trainee on the answer options, and use the operation data and the time used for this training as the feedback data.

[0174] In an embodiment of the present invention, in determining the target training level Ci in the candidate training level pool Bi according to the training data Ai and personal parameters, the processor 702 is specifically configured to perform the following operations:

[0175] Determine the second group to which the trainee belongs according to the personal parameters;

[0176] Obtain the return table of the second group, where the return table is used to record the return probabilities of the second group at each training level;

[0177] Determine the target training level Ci in the candidate training level pool Bi according to the training data Ai and the return table.

[0178] In an embodiment of the present invention, in determining the target training level Ci in the candidate training level pool Bi according to the training data Ai and the return table, the processor 702 is specifically configured to perform the following operations:

[0179] Determine the predicted return probability of the first training level according to the training data Ai and the return table, where the first training level is any one of the candidate levels in the candidate training level pool Bi;

[0180] Take the training level corresponding to the maximum value in the predicted return probabilities as the target training level Ci.

[0181] In an embodiment of the present invention, in determining the predicted return probability of the first training level according to the training data Ai and the return table, the processor 702 is specifically configured to perform the following operations:

[0182] Obtain the first historical return probability corresponding to the first training level in the return table;

[0183] Obtain the second historical return probability corresponding to the second training level in the return table, where the second training level is the training level corresponding to the training data Ai;

[0184] Obtain the training parameters of the second group for the first training level, where the training parameters are used to identify the degree of performance of the second group when performing the training tasks of the first training level;

[0185] Determine the actual return probability of the second training level according to the training data Ai;

[0186] Determine the predicted return probability of the first training level according to the first historical return probability, the second historical return probability, the training parameters, and the actual return probability.

[0187] It should be understood that the training device in the present application may include a smart phone, a tablet computer, a personal digital assistant, a laptop computer, a mobile Internet device (MID), a robot, or a wearable device, etc. The above-mentioned training devices are only examples, not an exhaustive list, and include but are not limited to the above-mentioned training devices. In practical applications, the above-mentioned training devices may further include: intelligent vehicle terminals, computer devices, and so on.

[0188] 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 art 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., and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments of the present invention.

[0189] Therefore, the embodiments of the present application further provide a computer-readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement part or all of the steps of any one of the 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.

[0190] The embodiments of the present application further provide a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute part or all of the steps of any one of the training methods described in the above method embodiments.

[0191] 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, certain steps may 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.

[0192] In the above embodiments, the descriptions of each embodiment have their own emphases. For the parts not detailed in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.

[0193] 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 merely 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.

[0194] 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.

[0195] In addition, in each embodiment of the present application, each functional unit can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software program modules.

[0196] If the above-mentioned 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 the present 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 to enable 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 each embodiment of the present application. The aforementioned memory includes: 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 and other various media that can store program codes.

[0197] 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. The memory can include: flash drives, read-only memories (abbreviation: ROM), random access memories (abbreviation: RAM), magnetic disks, or optical discs, etc.

[0198] The above has introduced the embodiments of the present application in detail. Specific examples are used herein to illustrate the principle and embodiments of the present application. The description of the above embodiments is only for helping to understand the method and its core idea of the present application; at the same time, for those of ordinary skill in the art, according to the idea of the present application, there will be changes in the specific embodiments and application scope. In summary, the content of this specification should not be construed as a limitation to the present application.

Claims

1. A training method, characterized in that: The method comprises: Determining the trainee's initial training level from among a plurality of preset training levels according to the trainee's personal parameters, wherein the personal parameters include: age, gender, basic cognitive ability, achievement motivation characteristics, stress level, and sleep quality; showing the trainee a first training topic corresponding to the initial training level, and obtaining feedback data of the trainee on the first training topic; Performing multiple trainings on the trainee according to the feedback data and the personal parameters; Among them, the i-th training includes: According to the training data Ai and the personal parameters, determine the target training level Ci in the candidate training level pool Bi, wherein when i=1, the training data A1 is the feedback data of the first training topic, and the candidate training level pool B1 is the remaining training levels after removing the initial training level from the multiple training levels; Showing the trainee a second training topic corresponding to the target training level Ci, and obtaining target feedback data Di of the trainee on the second training topic; The target feedback data Di of the second training topic is used as the training data Ai+1 of the i+1th training, the target training level Ci is removed from the candidate training level pool Bi to obtain the candidate training level pool Bi+1, and the i+1th training is performed until the multiple trainings are completed; Wherein, determining the trainee's initial training level from a plurality of preset training levels according to the trainee's personal parameters includes: Determine the first group to which the trainee belongs according to the personal parameters, generate a personal portrait of the trainee according to the personal parameters, calculate the similarity between the personal portrait and the group portraits of each group in the database, and take the group corresponding to the group portrait with the highest similarity as the first group; determining coefficients of random error and the individual parameter based on the first population; An initial training level of the trainee is determined among the plurality of training levels based on the personal parameters, the coefficients and the random errors.

2. The method according to claim 1, characterized in that The step of determining the coefficient of the random error and the personal parameter according to the first population comprises: Obtaining the maximum and minimum values ​​of random errors used by the first population when calculating the initial training level; Using the range between the maximum value and the minimum value as the generation range of the random error; Randomly obtain a value in the generated range as the random error; determine the contribution rates of the age, the gender, the basic cognitive ability, the achievement motivation characteristics, the stress level and the sleep quality to the training respectively according to the historical training data of the first group; The contribution rates corresponding to the age, the gender, the basic cognitive ability, the achievement motivation characteristics, the stress level and the sleep quality are normalized to obtain respective coefficients of the age, the gender, the basic cognitive ability, the achievement motivation characteristics, the stress level and the sleep quality.

3. The method according to claim 1, characterized in that The step of presenting the first training topic corresponding to the initial training level to the trainee and obtaining feedback data of the trainee on the first training topic includes: Acquire training pictures according to the first training topic; showing a fixation point to the trainee so that the trainee fixates on the fixation point; After a preset first time interval, showing the training picture to the trainee; After a preset second time interval, a blank interface is displayed to the trainee; After a preset third time interval, presenting a question answering interface to the trainee, wherein the question answering interface includes a training question and answer options, and the training question is related to the training picture; The trainee's operation data on the answer options is received, and the operation data and the time taken for this training are used as the feedback data.

4. The method according to any one of claims 1 to 3, characterized in that: Determining the target training level Ci in the candidate training level pool Bi according to the training data Ai and the personal parameters includes: determining a second group to which the trainee belongs based on the personal parameters; Obtaining a reward table for the second group, wherein the reward table is used to record the reward probability of the second group in each training level; According to the training data Ai and the reward table, the target training level Ci is determined in the candidate training level pool Bi.

5. The method according to claim 4, characterized in that The step of determining the target training level Ci in the candidate training level pool Bi according to the training data Ai and the report table includes: Determine the predicted return probability of a first training level according to the training data Ai and the return table, wherein the first training level is any candidate level in the candidate training level pool Bi; The training level corresponding to the maximum value of the predicted reward probability is used as the target training level Ci.

6. The method according to claim 5, characterized in that The step of determining the predicted reward probability of the first training level according to the training data Ai and the reward table includes: Obtaining a first historical reward probability corresponding to the first training level in the reward table; Obtaining a second historical reward probability corresponding to a second training level in the reward table, wherein the second training level is a training level corresponding to the training data Ai; Acquiring training parameters of the second group for the first training level, wherein the training parameters are used to identify the performance level of the second group when performing the training topic of the first training level; Determine the actual reward probability of the second training level according to the training data Ai; Determine a predicted reward probability of the first training level according to the first historical reward probability, the second historical reward probability, the training parameters, and the actual reward probability.

7. A training device, characterized in that: The device comprises: An initial module, for determining an initial training level of the trainee from among a plurality of preset training levels according to the trainee's personal parameters, wherein the personal parameters include: age, gender, basic cognitive ability, achievement motivation characteristics, stress level and sleep quality; A training module, used for showing the trainee a first training topic corresponding to the initial training level, obtaining feedback data of the trainee on the first training topic, and performing multiple trainings on the trainee according to the feedback data and the personal parameters; Wherein, in the i-th training, the training module is used to: According to the training data Ai and the personal parameters, determine the target training level Ci in the candidate training level pool Bi, wherein when i=1, the training data A1 is the feedback data of the first training topic, and the candidate training level pool B1 is the remaining training levels after removing the initial training level from the multiple training levels; Showing the trainee a second training topic corresponding to the target training level Ci, and obtaining target feedback data Di of the trainee on the second training topic; The target feedback data Di of the second training topic is used as the training data Ai+1 of the i+1th training, the target training level Ci is removed from the candidate training level pool Bi to obtain the candidate training level pool Bi+1, and the i+1th training is performed until the multiple trainings are completed; Wherein, in determining the initial training level of the trainee from among a plurality of preset training levels according to the trainee's personal parameters, the initial module is specifically used for: Determine the first group to which the trainee belongs according to the personal parameters, generate a personal portrait of the trainee according to the personal parameters, calculate the similarity between the personal portrait and the group portraits of each group in the database, and take the group corresponding to the group portrait with the highest similarity as the first group; determining coefficients of random error and the individual parameter based on the first population; An initial training level of the trainee is determined among the plurality of training levels based on the personal parameters, the coefficients and the random errors.

8. An electronic device, characterized in that: The method comprises a processor, a memory, a communication interface and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the one or more programs include instructions for executing the steps in the method described in any one of claims 1 to 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 to 6.

Images