CN117275675B

CN117275675B - Training scheme generation method, device, electronic equipment and storage medium

Info

Publication number: CN117275675B
Application number: CN202311525935.7A
Authority: CN
Inventors: 傅云凤; 吴珊珊; 冯慎行; 郭芷含; 熊晓夙
Original assignee: Beijing Wujiang Naozhi Technology Co ltd
Current assignee: Beijing Wujiang Naozhi Technology Co ltd
Priority date: 2023-11-16
Filing date: 2023-11-16
Publication date: 2024-03-26
Anticipated expiration: 2043-11-16
Also published as: CN117275675A

Abstract

The disclosure provides a training scheme generation method, a training scheme generation device, electronic equipment and a storage medium, wherein a first training item set is acquired; the following basic scheme generation operation is executed until a preset basic scheme generation end condition is satisfied: selecting a first number of training items from the first training item set to generate a training scheme; determining whether the generated training scheme meets the preset basic training scheme screening conditions; in response to determining that the generated training scheme is added to the base training scheme set. Thus, specific situations of users can be considered through presetting screening conditions, and targeted automatic generation of the training scheme is realized.

Description

Training scheme generation method, device, electronic equipment and storage medium

Technical Field

The embodiment of the disclosure relates to the technical field of data processing, in particular to a training scheme generation method, a training scheme generation device, electronic equipment and a storage medium.

Background

Cognitive training refers to a series of training systems designed by combining psychology professional theory, paradigm and gambling thinking. The system combines the current situation and psychological development characteristics of the trained person, and mainly trains various large cognitive abilities such as attention, perception, memory, thinking force, emotion ability, cognitive flexibility and the like, thereby helping the trained person to improve the cognitive level.

There are many training items for cognitive training in the prior art, and how to train the training items for a period of time needs to be manually determined by a user. Therefore, the expert evaluation is too subjective, has no objectivity, cannot consider the complete user situation, and has weak training pertinence and poor effect.

Disclosure of Invention

The embodiment of the disclosure provides a training scheme generation method, a training scheme generation device, electronic equipment and a storage medium.

In a first aspect, embodiments of the present disclosure provide a training scheme generating method, including:

acquiring a first training item set;

the following basic scheme generation operation is executed until a preset basic scheme generation end condition is satisfied: selecting a first number of training items from the first training item set to generate a training scheme; determining whether the generated training scheme meets the preset basic training scheme screening conditions; in response to determining that the generated training scheme is added to the base training scheme set.

In some optional embodiments, each training item corresponds to at least one training object in a training object set, the training object set comprising a subset of core training objects, the subset of core training objects comprising at least two core training objects;

And

The selecting a first number of training items from the first training item set to generate a training scheme includes:

determining a current training target in the core training target subset;

generating an empty training scheme as a current training scheme;

the following training scheme generating operation is performed until the number of training items in the current training scheme reaches the first number: acquiring training items corresponding to the current training target from the first training item set to obtain a training item set to be selected; extracting a training item from the training item set to be selected as a selected training item, wherein the selected training item is not in the current training scheme; adding the selected training items into the current training scheme; determining a next training target based on a preset training target selection rule; replacing the current training target with the next training target, and continuously executing the training scheme generating operation;

and determining the current training scheme as the generated training scheme.

In some optional embodiments, the determining the next training target based on the preset training target selection rule includes:

Determining whether the number of training items in the current training scheme is smaller than a second number;

in response to determining that the subset of core training targets is the first set of training targets to be screened;

in response to determining no, determining the training target set as a first training target set to be screened;

determining a first filterable training target subset from the first training target set to be filtered, wherein the first filterable training target comprises training items which do not belong to the current training scheme in the training items corresponding to the first training item set;

and acquiring a first filterable training target with the least training items corresponding to the current training scheme in the first filterable training target subset as a next training target.

In some optional embodiments, the determining whether the generated training scheme meets the preset basic training scheme screening condition includes:

generating an equilibrium comparison set by using the number of training items corresponding to each training target in the training target set in the generated training scheme;

determining whether the absolute value of the difference between any two numbers in the balanced comparison number set is not greater than a third number;

In response to determining that the generated training scheme satisfies the preset base training scheme screening condition, the generated training scheme is marked as an equalization scheme.

acquiring a bias training target set, wherein the bias training target set is a subset set with the number of training targets smaller than that of the core training target subset set;

determining the minimum number of the items in the scheme according to the first number and the number of the training targets in the bias training target set;

determining whether the number of training items in the current training scheme is less than the minimum number of items in the scheme;

in response to determining that the biased training target set is the second training target set to be screened;

in response to determining no, determining a difference set between the subset of core training targets and the set of bias training targets as a set of secondary bias training targets;

determining whether each training target in the secondary bias training target set has no corresponding training item in the current training scheme;

in response to determining that the secondary bias training target set is the second training target set to be screened;

In response to determining no, determining the training target set as the second training target set to be screened;

determining a second filterable training target subset from the second training target set to be filtered, wherein the second filterable training target comprises training items which do not belong to the current training scheme in the training items corresponding to the first training item set;

and acquiring a second screenable training target with the least training items corresponding to the current training scheme in the second screenable training target subset as a next training target.

In some alternative embodiments, the above method further comprises:

the following scheme deletion operation is performed until at least a fourth number of different training items are included between any two training schemes in the basic training scheme set described above: for any two of the set of base training schemes, deleting any one of the two base training schemes from the set of base training schemes in response to determining that at least a fourth number of different training items are not included between the two base training schemes.

In some alternative embodiments, the above method further comprises:

Acquiring a second training item set, wherein the average difficulty of the first training item set is lower than that of the second training item set;

for each of the above basic training schemes, the following reinforcement training scheme set generation operations are performed: determining a set of selectable replacement items from the second set of training items, wherein the selectable replacement items are not in the base training scheme; replacing any fifth number of training items in the basic training scheme with any fifth number of training items in the selectable replacement item set to obtain at least one replaced training scheme corresponding to the basic training scheme; for each obtained post-replacement training scheme, determining whether the post-replacement training scheme meets the preset reinforcement training scheme conditions, and in response to the determination that the post-replacement training scheme is added into the reinforcement training scheme set corresponding to the basic training scheme;

and determining an overall strengthening training scheme set based on the strengthening training scheme set corresponding to each basic training scheme.

In some alternative embodiments, the training items correspond to difficulty scores; and

replacing any fifth number of training items in the basic training scheme with any fifth number of training items in the optional replacement item set to obtain at least one post-replacement training scheme corresponding to the basic training scheme, where the method includes:

Generating an original training item set by using training items included in the basic training scheme;

selecting a fifth number of training items from the original training item set by adopting at least one selection mode to obtain at least one replaced training item set;

for each of the above-described set of substituted training items, the following post-substitution training scheme generation operations are performed: acquiring a difference set between the original training item set and the replaced training item set as a reserved training item set; acquiring a training item with the lowest difficulty score in the reserved training item set as the lowest difficulty training item; acquiring training items with difficulty scores larger than those of the lowest-difficulty training items from the selectable replacement item set as a selectable enhanced replacement item set; obtaining a fifth number of training items from the selectable enhanced replacement item set by adopting at least one selection mode to obtain at least one replacement training item set; and generating a post-replacement training scheme corresponding to the basic training scheme by using the reserved training item set and each of the replacement training item sets.

In some optional embodiments, determining whether the post-replacement training scheme meets the preset reinforcement training scheme condition includes:

Aiming at the post-replacement training scheme, training targets with the largest number of corresponding training items in the post-replacement training scheme in the training target set are used as strengthening bias training targets; and in response to the enhanced bias training target not being in the core training target subset, determining that the post-replacement training scheme does not meet the preset enhanced training scheme condition.

determining the difficulty score of the post-replacement training scheme based on the difficulty scores of the training items in the post-replacement training scheme; and in response to determining that the difference of the difficulty score of the post-replacement training scheme minus the difficulty score of the base training scheme is not greater than a preset difficulty difference threshold, determining that the post-replacement training scheme does not satisfy preset reinforcement training scheme conditions.

determining whether the absolute value of the difference between the numbers of the corresponding training items in the replaced training scheme of any two training targets in the core training target subset is smaller than the sixth number;

In response to determining that the post-replacement training scheme is a scheme type labeled equalization scheme;

in response to determining no, determining whether two different core training targets exist in the subset of core training targets, a difference between the numbers of corresponding training items in the post-replacement training scheme for the two different core training targets being greater than a seventh number;

in response to determining that the solution exists, marking the solution type of the post-replacement training solution as a solution biased toward a training target;

in response to determining that no solution exists, marking a solution type of the post-replacement training solution as a solution biased toward a plurality of training targets;

determining a subset of training schemes to be compared according to the scheme type of the replaced training scheme;

and in response to determining that the training schemes with the number of the difference training items smaller than the eighth number exist in the subset of training schemes to be compared and the replaced training scheme, determining that the replaced training scheme does not meet the preset reinforced training scheme condition.

In some alternative embodiments, determining the subset of training patterns to be compared according to the pattern type of the post-replacement training pattern includes:

responding to the scheme that the replaced training scheme is an equalization scheme or a scheme biased to a training target, and determining a union of the reinforced training scheme set of the basic training scheme and the basic training scheme set as a training scheme subset to be compared;

And in response to the replaced training scheme being a scheme biased towards a plurality of training targets, determining a scheme of which each scheme type is biased towards the plurality of training targets in the enhanced training scheme set of the basic training scheme as a training scheme subset to be compared.

In some optional embodiments, the reinforcement training scheme generating operation further includes:

determining whether a training scheme marked as an equalization scheme or biased to a training target does not exist in the enhanced training scheme set corresponding to the basic scheme;

and deleting the enhanced training scheme set corresponding to the basic scheme in response to the determination.

and in response to determining that the number of training items corresponding to at least one training target in the training target set in the post-replacement training scheme is zero, determining that the post-replacement training scheme does not meet the preset reinforcement training scheme condition.

the method further comprises the following steps:

any basic training scheme or reinforcement training scheme is obtained as a target training scheme;

Acquiring a ninth previous number of training items with the lowest difficulty scores in the target training scheme, and generating a low-difficulty item set;

determining a screening training scheme set based on the low-difficulty item set, wherein the screening training scheme comprises a tenth number of training items in the low-difficulty item set, and the tenth number is smaller than the ninth number;

sorting all the screening training schemes according to the order of low difficulty scores from high, sorting the screening training schemes of the number of subcycles before sorting according to the difficulty scores of the corresponding screening training schemes, and sequentially determining the screening training schemes as first-stage training schemes of corresponding sorting subcycles in a preset training period;

for each sub-period of the preset training period, performing the following intra-sub-period phase training scheme generation operations: determining a first stage training scheme of the sub-period as a current stage training scheme; generating a subcycle historical training item set by using each training item in the training scheme of the current stage; starting from the second stage of the sub-period until the last stage, for each stage, the following sub-period stage scheme generation operations are performed in accordance with the temporal ordering of the respective stages in the sub-period: generating a next-stage replacement item set by using training items except for the historical training items in the target training scheme, and generating the stage training scheme of the subcycle by replacing the training item with the lowest difficulty score in the current-stage training scheme by using the training item with the lowest difficulty score in the next-stage replacement item set; adding each training item in the stage training scheme to the history training item set, and determining the stage training scheme as the current stage training scheme.

In some alternative embodiments, each training item corresponds to at least one training target in the training target set; and

the method further comprises the following steps:

acquiring any stage training scheme corresponding to any sub-period of the target training scheme as a target stage training scheme;

for each training target, determining the number of stage training items corresponding to the training target in the target stage training scheme;

determining whether a difference obtained by subtracting the number of stage training items corresponding to the secondary multiple training targets from the number of stage training items corresponding to the maximum training target is larger than an eleventh number, wherein the maximum training target and the secondary multiple training target are respectively the training targets with the maximum number and the secondary multiple stage training items corresponding to the training targets;

in response to determining that the target phase training scenario is a phase training scenario biased toward the maximum training target;

in response to determining no, the target phase training scheme is marked as an equalization phase training scheme.

In a second aspect, embodiments of the present disclosure provide a training scheme generating apparatus, including:

the acquisition module is used for acquiring a first training item set;

The basic scheme generation module is used for executing the following basic scheme generation operation until a preset basic scheme generation ending condition is met: selecting a first number of training items from the first training item set to generate a training scheme; determining whether the generated training scheme meets the preset basic training scheme screening conditions; in response to determining that the generated training scheme is added to the base training scheme set.

In a third aspect, embodiments of the present disclosure provide an electronic device, comprising: one or more processors; and a storage device having one or more programs stored thereon, which when executed by the one or more processors, cause the one or more processors to implement the method as described in any of the implementations of the first aspect.

In a fourth aspect, embodiments of the present disclosure provide a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by one or more processors, implements a method as described in any of the implementations of the first aspect.

In order to improve pertinence of training scheme generation, the training scheme generation method, device, electronic equipment and storage medium provided by the embodiment of the disclosure acquire a first training item set; then, the following basic scenario generation operation is performed until a preset basic scenario generation end condition is satisfied: selecting a first number of training items from the first training item set to generate a training scheme; determining whether the generated training scheme meets the preset basic training scheme screening conditions; in response to determining that the generated training scheme is added to the base training scheme set. The first training items including different combinations are selected from the first training item set, and the first training items are added to the basic training scheme set under the condition that the screening conditions of the basic training scheme are met, so that the training scheme can be selected from the basic training schemes to train conveniently.

Drawings

Other features, objects and advantages of the present disclosure will become more apparent upon reading of the detailed description of non-limiting embodiments made with reference to the following drawings. The drawings are only for purposes of illustrating particular embodiments and are not to be construed as limiting the disclosure. In the drawings:

FIG. 1 is an exemplary system architecture diagram in which an embodiment of the present disclosure may be applied;

FIG. 2A is a flow chart of one embodiment of a training scheme generation method according to the present disclosure;

FIG. 2B is a flow chart of one embodiment of the base schema generation operation in step 202 according to the present disclosure;

FIG. 2C is a flow chart of one embodiment of step 2021 according to the present disclosure;

FIG. 2D is a flow chart of one embodiment of the training scheme generation operation in step 20213 in accordance with the present disclosure;

fig. 2E is a flow chart of one embodiment of step 202134 according to the present disclosure;

fig. 2F is a flow chart of yet another embodiment of step 202134 according to the present disclosure;

FIG. 2G is a flow chart of one embodiment of step 2022 according to the present disclosure;

FIG. 2H is a flow chart of one embodiment of the reinforcement training scenario set generation operation in step 205 according to the present disclosure;

FIG. 2I is a flow chart according to one embodiment of step 2052 of the present disclosure;

FIG. 2J is a flow chart of one embodiment of step 2053 according to the present disclosure;

FIG. 2K is a flow chart of one embodiment of step 2053 according to the present disclosure;

FIG. 2L is a flow chart of one embodiment of step 2053 according to the present disclosure;

FIG. 2M is a flow chart of one embodiment of step 2053 according to the present disclosure;

FIG. 3 is a flow chart of yet another embodiment of a training scheme generation method according to the present disclosure;

FIG. 4 is a schematic diagram of the structure of one embodiment of a training scheme generating device according to the present disclosure;

fig. 5 is a schematic diagram of a computer system suitable for use in implementing embodiments of the present disclosure.

Detailed Description

The present disclosure is described in further detail below with reference to the drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be noted that, for convenience of description, only the portions related to the present invention are shown in the drawings.

It should be noted that, without conflict, the embodiments of the present disclosure and features of the embodiments may be combined with each other. The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.

FIG. 1 illustrates an exemplary system architecture 100 in which embodiments of training scheme generation methods, apparatus, electronic devices, and storage media of the present disclosure may be applied.

As shown in fig. 1, a system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 is used as a medium to provide communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.

The user may interact with the server 105 via the network 104 using the terminal devices 101, 102, 103 to receive or send messages or the like. Various communication client applications, such as a scheme generation class application, a voice recognition class application, a short video social class application, an audio-video conference class application, a video live broadcast class application, a document editing class application, an input method class application, a web browser application, a shopping class application, a search class application, an instant messaging tool, a mailbox client, social platform software, and the like, can be installed on the terminal devices 101, 102, 103.

The terminal devices 101, 102, 103 may be hardware or software. When the terminal devices 101, 102, 103 are hardware, they may be various electronic devices with display screens, including but not limited to smartphones, tablet computers, electronic book readers, MP3 players (Moving Picture Experts Group Audio Layer III, dynamic video expert compression standard audio plane 3), MP4 (Moving Picture Experts Group Audio Layer IV, dynamic video expert compression standard audio plane 4) players, laptop and desktop computers, and the like. When the terminal apparatuses 101, 102, 103 are software, they can be installed in the above-listed terminal apparatuses. Which may be implemented as multiple software or software modules (e.g., to provide a scenario generation service), or as a single software or software module. The present invention is not particularly limited herein.

In some cases, the training scheme generation method provided by the present disclosure may be performed by the terminal devices 101, 102, 103, and accordingly, the training scheme generation apparatus may be provided in the terminal devices 101, 102, 103. In this case, the system architecture 100 may not include the server 105.

In some cases, the training scenario generation method provided by the present disclosure may be performed jointly by the terminal device 101, 102, 103 and the server 105, for example, the step of "obtaining the first training item set" may be performed by the terminal device 101, 102, 103, "the following basic scenario generation operation is performed until a preset basic scenario generation end condition is satisfied: selecting a first number of training items from the first training item set to generate a training scheme; determining whether the generated training scheme meets the preset basic training scheme screening conditions; in response to determining that the steps of adding the generated training scheme to the base training scheme set, etc. may be performed by the server 105. The present disclosure is not limited in this regard. Correspondingly, the training scheme generating means may also be provided in the terminal devices 101, 102, 103 and the server 105, respectively.

In some cases, the training scheme generating method provided by the present disclosure may be executed by the server 105, and accordingly, the training scheme generating apparatus may also be set in the server 105, where the system architecture 100 may also not include the terminal devices 101, 102, 103.

The server 105 may be hardware or software. When the server 105 is hardware, it may be implemented as a distributed server cluster formed by a plurality of servers, or as a single server. When server 105 is software, it may be implemented as a plurality of software or software modules (e.g., to provide distributed services), or as a single software or software module. The present invention is not particularly limited herein.

It should be understood that the number of terminal devices, networks and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.

With continued reference to fig. 2A, there is shown a flow 200 of one embodiment of a training scenario generation method according to the present disclosure, the training scenario generation method comprising the steps of:

step 201, a first training set of items is obtained.

An executing subject of the training scenario generation method (e.g., server 105 shown in fig. 1) may first acquire a first training item set.

The training program may be a program developed in advance for performing cognitive training, such as a game combined with a psychology theory. The first training set may include a portion of training items, and the specific number of training items and content of training items are not limited herein. For example, 35 games for training cognitive ability are developed in advance as 35 training items, and then the first training item set may correspond to the 35 games or to a part of the 35 games, such as 16 games.

Considering that the number of training items is large, the training targets of the bias training of different training items are different, and the user cannot train all the training items in one day, so that part of the training items need to be selected, and a training scheme is generated for training in a certain time period. The basic training scheme is a training scheme with low difficulty and can be used for initial training of users.

Alternatively, in practice, the difficulty of different training projects may be different. Thus, to generate a basic training scheme on a training item basis, when each training item has a corresponding training difficulty score, the first training item set may be the first N training items (N is less than M) of the pre-developed existing training item sets (assuming that there are M training items in the existing training item sets, M is a positive integer) with a difficulty ranking from low to high. Therefore, the difficulty of the basic training scheme generated based on the first training item set is relatively low, and the situation that the initial training difficulty is too high and the user is difficult to complete can be avoided. Therefore, the method can be adjusted to be more difficult later when the situation that the tested user is better in completion is detected.

As a possible implementation manner, the information of the training items may be stored in a knowledge graph, where each training item is used as a node, and the node ID is an identification of the training item. In addition, the knowledge graph can also include attribute information of training items, such as difficulty scores, corresponding training targets, psychological norms, single-task and double-task types and the like. In the knowledge graph, attribute information can also exist in the form of nodes, and association relations are established among the nodes through connecting lines. Therefore, when the first training item set is acquired, the identification of the training item can be acquired by reading the node information in the knowledge graph, so that the first training item set is generated.

Step 202, executing basic scheme generation operation until a preset basic scheme generation ending condition is met.

Here, the base schema generation operation may include steps 2021 to 2023 as shown in fig. 2B:

step 2021, selecting a first number of training items from the first set of training items, and generating a training scheme.

Here, various implementations may be employed to select a first number of training items from a first set of training items, generating a training scheme, where the training scheme includes the first number of training items in the first set of training items. Assuming that the first training set includes N training items, the first number is P, there may be And selecting P training items from the N training items in a selection mode, and generating a training scheme.

Alternatively, the first number may be set according to the periodic training period of the subject user, such that each training regimen includes a number of training items that match the periodic training period. For example, 8 items should be trained in a month period, i.e., one training regimen may be set to include 8 training items per training regimen (without distinguishing the order).

The training program is used for improving the cognitive ability of the tested user. In some alternative embodiments, each training program may correspond to training one or more training goals. That is, the subject user may achieve the goal of enhancing the corresponding training goals by executing a training program, which may be one or more specific cognitive abilities.

In order to improve the cognitive ability of the tested user, a corresponding training target set may be preset, where the first training item set or at least one training target corresponding to each training item in the foregoing existing training item set belongs to the training target set.

For example, the training target set may include attention, self-control, memory, conversion, perception, and the like. Any one of the training items may correspond to at least one training target in the set of training targets.

In the training target set, some training targets are training targets which are required to be lifted more at the core in cognitive training, namely core training targets. Therefore, part of the training targets in the training target set can be set as core training targets, namely a core training target subset can be formed, and the core training target subset comprises at least two core training targets.

For example, the subset of core training targets may include three training targets of attention, self-control, and memory.

Based on the alternative embodiments of the training target set and the core training target subset, the step 2021 may include the following steps 20211 to 20213 as shown in fig. 2C:

at step 20211, the current training objectives are determined from the subset of core training objectives.

The current training target may be any core training target in the core training target subset. For example, the current training goal is determined to be attention from a subset of core training goals (including attention, self-control, memory).

At step 20212, an empty training scenario is generated as the current training scenario.

Step 20213, performing a training scenario generation operation until the number of training items in the current training scenario reaches the first number:

The training scheme generation operation may include steps 202131 to 202135 as shown in fig. 2D:

step 202131, obtaining a training item corresponding to the current training target from the first training item set, thereby obtaining a training item set to be selected.

Because each training item corresponds to at least one training target, conversely, all training targets corresponding to the training items in the first training item set also correspond to the corresponding training items, and the training item corresponding to the current training target in the first training item set is obtained and used as the training item set to be selected.

Step 202132, extracting a training item from the training item set to be selected as the selected training item.

It should be noted that, since the current training scheme cannot include repeated training items, it is necessary to ensure that the selected training item is not in the current training scheme.

And 202133, adding the selected training item to the current training scheme.

In step 202134, the next training target is determined based on the preset training target selection rule.

The preset training target selection rule is used for setting a selection rule of a next training target, namely determining the training target to be trained by the current training scheme. Specific preset training target selection rules can be set according to actual needs, so that targeted scheme generation is performed. When the rules of selecting the next training targets are different, different types of training schemes are correspondingly generated, and specifically, for example, a balanced scheme for relatively balancing the training targets or a bias scheme for biasing at least one training target in the training target set can be generated.

As a possible implementation, when the preset training target selection rule is a scheme for generating equalization, the above step 202134 may include the following steps 2021341a to 2021345A as shown in fig. 2E:

in step 2021341a, it is determined whether the number of training items in the current training regimen is less than the second number.

The second number may be a preset value smaller than the first number, and is used for measuring whether the number of training items corresponding to the core training target reaches a preset requirement. For example, when the generated training scheme is a monthly training scheme, the first number is 8 and the second number may be 6.

If the number of the training items in the current training scheme is determined to be smaller than the second number, the training items corresponding to the core training targets are not enough, and in order to ensure that the generated training targets corresponding to the training items in the current training scheme are more balanced, the training items corresponding to the core training targets need to be selected later. Therefore, the generated scheme can train the core training targets more, and the training targets which are required to be lifted by the cores in the cognitive training are lifted. Accordingly, execution may proceed to step 2021342a to determine the subset of core training targets as the first set of training targets to be screened.

If the number of the training items in the current training scheme is not less than the second number, the training items corresponding to the core training targets are enough, and the rest training items can be selected from the training items corresponding to all the training targets, so that the training targets corresponding to the training items in the generated training scheme are more balanced and are not just the training core training targets. Accordingly, execution may proceed to step 2021342a to determine the training target set as a whole as the first training target set to be screened.

In step 2021342a, a subset of core training targets is determined as a first set of training targets to be screened.

After the execution of step 2021342a, the process goes to step 2021344 a.

In step 2021343a, a training target set is determined as a first training target set to be screened.

After the execution of step 2021343a, the process goes to step 2021344 a.

In step 2021344a, a first subset of screenable training objects is determined from the first set of training objects to be screened.

It should be noted that, in order to ensure that the first training target to be screened has a training item in the first training item set, which is not selected in the current training scheme, the first sub-set of selectable training targets may be determined from the first training target set to ensure that the first selectable training target includes, in the training items corresponding to the first training item set, a training item that does not belong to the current training scheme.

In step 2021345a, a first screenable training object with the least training items corresponding to the current training scheme in the first subset of screenable training objects is obtained as a next training object.

Because training targets are randomly selected from the first filterable training target subset, training items in the current training scheme intensively train a certain training target, and the training scheme is relatively unbalanced. Thus, the first screenable training object with the least training items corresponding to the current training scheme in the first screenable training object subset can be obtained as the next training object. In this way, the current training scheme can be made relatively more balanced and rational.

After step 2021345a is performed, i.e., the next training goal is determined, execution may proceed to step 202135.

As another possible implementation, when the preset training target selection rule is a bias scheme for generating at least one training target in the bias training target set, the above step 202134 may further include the following steps 2021341B to 20213410B as shown in fig. 2F:

in step 2021341B, a set of bias training targets is obtained.

The bias training targets are preset, the bias training targets can be one or more of the core training targets, but the number of the bias training targets is smaller than that of the core training targets, namely, the bias training target set is a subset of the core training target subset, and the number of the training targets in the bias training target set is smaller than that of the training targets in the core training target subset.

Therefore, after the bias training target set is obtained, the scheme generated by taking the bias training target set as a reference can be marked directly according to the bias training target set. Specifically, when the bias training target set includes one bias training target, marking the current training scheme as a scheme biased toward the one training target; when the set of biased training goals includes at least two biased training goals, the current training scenario is marked as a scenario biased toward multiple training goals. In addition, the generated scheme can be selectively marked as a scheme biased towards m training targets, and m is the number of training targets in the biased training target set.

In step 2021342B, the minimum number of items in the scheme is determined based on the first number and the number of training targets in the set of biased training targets.

Here, a correspondence relationship between both the first number and the number of training targets and the minimum number of items in the scheme may be preset, and then, the minimum number of items in the scheme may be determined according to the number of training targets in the bias training target set. The minimum number of items in the solution is used to define the number of training items corresponding to the biased training goal in the generated solution. It will be appreciated that the minimum number of items in the solution should be positively correlated with both the first number and the training target number, respectively.

For example, when the generated training scheme is a monthly training scheme, the first number is 8, and correspondingly, when the number of training targets in the bias training target set is 1, that is, it is hoped that the training items in the current training scheme are biased to only one training target, the minimum number of the items in the scheme may be 5; when the number of training targets in the bias training target set is 2, that is, it is desirable that the training items in the current training scheme be biased to two training targets, the minimum number of items in the scheme may be 6.

In step 2021343B, it is determined whether the number of training items in the current training regimen is less than the minimum number of items in the regimen.

If the number of the training items in the current training scheme is determined to be smaller than the minimum number of the training items in the scheme, the fact that the number of the training items corresponding to the bias training targets does not reach the preset number is indicated, so that the training items corresponding to the bias training targets should be added in the current training scheme until the minimum number of the items in the scheme is reached, the generated scheme comprises training items corresponding to enough bias training targets, and the effect of bias training one or more training targets is achieved. Then, training items corresponding to other training targets are added, so that the scheme is balanced properly, and the training targets are not only the training targets with weight bias. Accordingly, execution may proceed to step 2021344B.

If the number of training items in the current training scheme is not less than the minimum number of the items in the scheme, the number of training items corresponding to the bias training targets is indicated to reach the preset number, so that the current training scheme is further ensured to comprise the training items corresponding to each core training target. Under the condition that each core training target has a corresponding training item in the current training scheme, training items corresponding to training targets which are not the core training targets are added. Accordingly, execution may proceed to step 2021345B.

In step 2021344B, the biased training object set is determined as the second training object set to be screened.

After the execution of step 2021344B, the process goes to step 2021349B to continue execution.

Step 2021345B, the difference set between the core training target subset and the bias training target set is determined to be the secondary bias training target set.

In step 2021346B, it is determined whether each training object in the set of secondary bias training objects has no corresponding training item in the current training scheme.

If yes, it is determined that there is no training item corresponding to the core training target other than the bias training target in the current training scheme, and a training item corresponding to the secondary bias training target needs to be added, so the step 2021347B may be executed.

If not, indicating that there are training items corresponding to core training targets other than the bias training target, any training item corresponding to the training target may be added, and thus the process may proceed to step 2021348B for execution.

In step 2021347B, the secondary bias training target set is determined as the second training target set to be screened.

After the execution of step 2021347B, the process goes to step 2021349B to continue execution.

In step 2021348B, the training target set is determined to be the second training target set to be screened.

After the execution of step 2021348B, the process goes to step 2021349B to continue execution.

Step 2021349B, determining a second subset of screenable training objects from the second set of training objects to be screened.

Similar to step 2021344a, it should be noted that, to ensure that the second training target to be screened has a training item in the first training item set that is not selected in the current training scheme, a second subset of the selectable training targets may be determined from the second training target set to be screened, so as to ensure that the second selectable training target includes a training item that does not belong to the current training scheme in the corresponding training item in the first training item set.

In step 20213410B, the second screenable training object in the second subset of screenable training objects having the least training items corresponding to the current training regimen is obtained as the next training object.

Similar to step 2021345a, the training goals selected from the subset of screenable training goals at random may result in training a training goal in the training set of the current training regimen, which may be relatively unbalanced. Thus, the second screenable training object in the second subset of screenable training objects, which has the smallest corresponding training item in the current training regimen, may be obtained as the next training object. In this way, the current training scheme can be made relatively more balanced and rational.

After step 20213410B is performed, i.e., the next training goal is determined, execution may proceed to step 202135.

The next training target may be determined, via step 202134. It should be noted that different next training objectives may be determined according to different strategies (e.g., two different implementations of steps 2021341a through 2021345A, 2021341B through 20213410B).

Step 202135, replacing the current training target with the next training target, and continuing to execute the training scheme generating operation.

That is, the current training target is replaced with the next training target, and then the process goes to step 202131 to continue execution until the number of training items in the current training scheme reaches the first number, and execution of the training scheme generating operation is stopped.

By executing step 20213, the current training regimen will include a first number of training items.

After step 20213 is performed, execution may proceed to step 20214.

At step 20214, the current training scheme is determined as the generated training scheme.

Through steps 20211 to 20214, i.e., through step 2021, a first number of training items may be selected from the first set of training items, generating a training scenario.

Then, the execution may proceed to step 2022.

Step 2022, determining whether the generated training scheme satisfies a preset basic training scheme screening condition.

Although the training scheme is generated in step 2021, as the basic training scheme, a preset basic training scheme screening condition needs to be satisfied. Here, the preset basic training scheme screening condition may be a screening condition preset according to the requirement of the actual training scenario. Therefore, here, it may be determined whether the generated training scheme satisfies the preset basic training scheme screening condition.

If it is determined that the generated training scheme satisfies the preset basic training scheme screening condition, it may go to step 2023 to execute, and add the scheme generated in step 2021, which satisfies the preset basic training scheme screening condition, to the basic training scheme set by executing step 2023.

As a possible implementation manner, when the preset training target selection rule adopted in step 202134 is adopted to generate an equilibrium scheme, that is, when steps 2021341a to 2021345A shown in fig. 2E are adopted to generate a more equilibrium training scheme, a preset basic training scheme screening condition may be set through step 2022, so as to screen out a scheme that the equilibrium degree meets the preset requirement. Specifically, step 2022 may include steps 20221 to 20223 as shown in fig. 2G:

in step 20221, an equalization comparison set is generated using the number of training items corresponding to each training object in the set of training objects in the generated training scheme.

Here, assume that training object set O has I training objects, O _i For the ith training target, I is a positive integer between 1 and I, the generated training scheme is F, N training items are included in F, and N is a first number. Step 20221 may be performed as follows:

first, for each training object O _i Determining training object O _i Number Num of corresponding training items in training scheme F _i ，Num _i I is the number of equilibrium comparison, I equilibrium comparison Num _i An equalized comparison set Num is formed.

Step 20222 determines whether the absolute value of the difference between any two of the set of equalized comparison numbers is not greater than a third number.

The third quantity can be set according to actual conditions, and the smaller the third quantity is, the smaller the difference value between the quantity of training items corresponding to different training targets in the generated training scheme is, and the more balanced the generated scheme is; the larger the third number, the more unbalanced the generated scheme.

If it is determined that none of the absolute values of the differences between any two of the sets of equalization ratios is greater than the third number, indicating that the generated training scheme is an equalization scheme, execution may proceed to step 20223.

Step 20223, determining that the generated training scheme meets the preset basic training scheme screening conditions, and marking the generated training scheme as an equalization scheme.

Through steps 20221 to 20223, only if the generated training scenario is sufficiently balanced, it is determined that the preset basic training scenario screening condition is satisfied, and marked as an balanced scenario, and then the step 2023 is performed, and the sufficiently balanced scenario generated in step 2021 is added to the basic training scenario set by performing step 2023.

On the contrary, if it is determined in step 20222 that the absolute value of the difference between the two numbers in the equalization comparison set is greater than the third number, that is, the generated scheme is not balanced enough, the generated training scheme is not determined to meet the preset basic training scheme screening condition, and the process will not go to step 2023 to continue, and the scheme generated in step 2021 and not balanced enough will not be added to the basic training scheme set.

Step 2023, adding the generated training scheme to the basic training scheme set.

After step 2023 is performed, the process may go to step 2021 to continue until a preset base scenario generation end condition is satisfied.

Here, the preset base scenario generation end condition may be an end condition preset according to a specific actual situation. Continuing with the assumption above, the first set of training items includes N training items, the first number being P. As an alternative embodiment, the preset base scheme generation end condition may be: for each selection mode of selecting P training items from the N training items, a corresponding training scheme is generated, i.e. steps 2021 to 2023 are performed for each selection mode. As another alternative embodiment, the preset base scheme generation end condition may also be: the basic training scheme set comprises a preset basic scheme number of training schemes. Here, the number of preset base schemes may be smaller than the number of selection manners of selecting P training items from the N training items, for example, one fourth, one third, one half, two thirds, or the like of the number of the selection manners.

A set of base training scenarios may be generated by performing step 202.

It should be noted that when multiple selection modes exist in any step, each selection mode may be traversed to correspondingly generate different results, and other steps after the step are performed with different results, so as to generate different training schemes, and finally, training schemes meeting the screening conditions in the generated training schemes are added to the basic training scheme set to generate a comprehensive basic training scheme set.

As a possible implementation manner, the execution body of the training scheme generating method may further selectively execute the following step 203 after executing step 202:

step 203, executing the scheme deleting operation until at least a fourth number of different training items are included between any two training schemes in the basic training scheme set.

Here, the scheme deleting operation includes: for any two of the set of base training schemes, deleting any one of the two base training schemes from the set of base training schemes in response to determining that at least a fourth number of different training items are not included between the two base training schemes.

Therefore, the training schemes with higher similarity in the generated basic training schemes can be deleted, at least a fourth number of different training items are included between any two basic training schemes in the final basic training scheme set, and a user can feel larger training difference when training different basic training schemes, is more willing to cooperate with subsequent training, and is beneficial to improving the training effect.

For example, when the generated training schemes are monthly training schemes, the first number may be 8, the second number may be 6, and the fourth number may be 3, i.e., at least 3 different training items are included between any two basic training schemes in the basic training scheme set.

As a possible implementation manner, the execution body of the training scheme generating method may further selectively perform the following steps 204 to 206 after performing step 202:

step 204, obtaining a second training item set.

A basic training scheme set has been generated through steps 201 to 203, and in practice, in order to make the tested user gradually increase the training ability, a basic training scheme with lower difficulty is generally adopted in the first or the first few times of training. Under the condition that the performance of the tested user is better, the difficulty of the training scheme is gradually improved, so that the second training item set is needed to be used as a basis for generating the enhanced training scheme, and the enhanced training scheme set is a training scheme set with overall difficulty higher than that of the basic training scheme set, and the aim of improving the training difficulty, namely enhancing training is fulfilled.

As a possible implementation manner, the average difficulty of the first training item set may be set to be lower than the average difficulty of the second training item set. For example, the training items in the training item set are arranged in order of low difficulty, and the first training item set may include the first X of the training item set before difficulty ordering ₁ The second training item set may include the first difficulty ranked X in the training item set ₂ Training items X ₁ And X ₂ Is a positive integer, and X ₁ Less than X ₂ . For example, there are 33 training items in the training item set, the first training item set is the first 16 training items in the difficulty order in the training item set, and the second training item set may include the first 20 training items in the difficulty order in the training item set. This may result in the average difficulty of the first set of training items being lower than the average difficulty of the second set of training items.

Step 205, for each basic training scheme, performing an intensive training scheme set generation operation.

Here, the reinforcement training scheme set generating operation may be performed for each base scheme to generate reinforcement training scheme sets corresponding to the respective base training schemes, and the reinforcement generating scheme sets corresponding to all base training schemes may constitute an overall reinforcement training scheme set.

Wherein the reinforcement training scenario set generation operation may include steps 2051 to 2056 as shown in fig. 2H:

step 2051, a set of selectable replacement items is determined from the second set of training items.

Because the average difficulty of the second training item set is greater than that of the first training item set, part of training items can be replaced on the basis of the original basic training scheme, and the overall difficulty of the replaced training scheme is mostly improved, namely the reinforced training scheme is generated. Thus, a set of selectable replacement items may first be determined from the second set of training items. Because the replaceable item needs to replace a training item in the original base training scheme, the replaceable item is a training item in the second set of training items that is not in the base training scheme.

Step 2052, replacing any fifth number of training items in the base training scheme with any fifth number of training items in the set of selectable replacement items to obtain at least one post-replacement training scheme corresponding to the base training scheme.

Here, any fifth number of training items may be selected from the set of selectable replacement items by using various implementation manners, and then any fifth number of training items in the basic training scheme are replaced by using the selected fifth number of training items, so that a post-replacement training scheme corresponding to the basic training scheme may be obtained, and the above operations may be repeated multiple times, so that at least one post-replacement training scheme corresponding to the basic training scheme may be obtained.

In an alternative embodiment, in order to ensure that the training difficulty of the reinforcement training scheme is higher than the training difficulty of the corresponding basic training scheme, and the difficulty is improved more smoothly, the above step 2052 may include the following steps 20521 to 20523 as shown in fig. 2I:

in step 20521, an original training item set is generated using training items included in the base training scheme.

Step 20522, selecting a fifth number of training items from the original training item set by at least one selection manner, to obtain at least one replaced training item set.

Here, included in the set of substituted training items are training items that are not included in the enhanced training scheme.

Step 20523, for each set of substituted training items, performs a post-replacement training scheme generation operation.

Here, the post-replacement training scheme generation operation may be performed as follows:

first, a difference set between an original training item set and the replaced training item set is obtained and used as a reserved training item set.

And then, acquiring the training item with the lowest difficulty score in the reserved training item set as the training item with the lowest difficulty.

Next, training items with difficulty scores greater than the lowest difficulty training item are obtained from the set of selectable replacement items as a set of selectable enhanced replacement items.

And obtaining a fifth number of training items from the selectable enhanced replacement item set by adopting at least one selection mode to obtain at least one replacement training item set.

And finally, respectively using the reserved training item set and each of the replacement training item sets to generate a replaced training scheme corresponding to the basic training scheme.

Through step 20523, the post-replacement training scheme does not include a set of replaced training items, but replaces the set of replaced training items with the set of replacement training items; meanwhile, the training items in the training item set are kept unchanged. The obtaining of the set of selectable enhanced replacement items may cause the generated post-replacement training scheme to include all schemes that cause the enhanced training scheme to be more difficult than its corresponding base training scheme.

At least one post-replacement training scenario corresponding to the base training scenario may be obtained, via step 2052.

Step 2053, for each obtained post-replacement training scheme, determining whether the post-replacement training scheme meets a preset reinforcement training scheme condition, and in response to determining that the post-replacement training scheme is added to the reinforcement training scheme set corresponding to the basic training scheme.

Here, for each post-replacement training scheme corresponding to the basic training scheme obtained in step 2052, it may be determined whether the post-replacement training scheme meets the preset reinforcement training scheme condition, and if it is determined that the post-replacement training scheme meets the preset reinforcement training scheme condition, the post-replacement training scheme may be added to the reinforcement training scheme set corresponding to the basic training scheme.

The preset conditions of the strengthening training scheme are preset, and the method is used for ensuring that the strengthening training scheme is more difficult than the basic training scheme.

Optionally, the preset conditions of the reinforcement training scheme may also be used to ensure that there is a certain difference between other reinforcement training schemes generated by the basic training scheme and enrich the training targets as much as possible.

Optionally, the preset training target conditions of the reinforcement training scheme can be used to ensure that the training target mainly trained by the reinforcement training scheme is a core training target.

As one possible implementation manner, in step 2053, determining whether the post-replacement training scheme meets the preset reinforcement training scheme condition may include the following steps 205311 and 205312 shown in fig. 2J:

step 205311, regarding the post-replacement training scheme, using the training target with the largest number of corresponding training items in the post-replacement training scheme as the training target for strengthening bias.

In step 205312, in response to the enhanced bias training target not being in the subset of core training targets, it is determined that the post-replacement training scheme does not satisfy the preset enhanced training scheme condition.

When the reinforced bias training target is not in the core training target subset, the training targets corresponding to most training items of the replaced training scheme are not training targets which are required to be lifted by cores in cognitive training, and the replaced training scheme cannot be used as the reinforced training scheme, so that the condition that the replaced training scheme does not meet the preset reinforced training scheme can be determined.

As one possible implementation manner, in step 2053, determining whether the post-replacement training scheme meets the preset training scheme condition may further include the following steps 205321 and 205322 in fig. 2K:

step 205321, determining the difficulty score of the post-replacement training scheme based on the difficulty scores of the training items in the post-replacement training scheme.

As one possible implementation, the difficulty scores of the training schemes may be calculated by summing or averaging the difficulty scores of the respective training items in the training schemes, which is not limited herein.

And step 205322, determining that the post-replacement training scheme does not meet the preset reinforcement training scheme condition in response to determining that the difference of the difficulty score of the post-replacement training scheme minus the difficulty score of the base training scheme is not greater than the preset difficulty difference threshold.

When the difficulty score of the post-replacement training scheme is not higher than the difficulty score of the basic training scheme to a certain extent, the fact that the post-replacement training scheme does not achieve a sufficient strengthening effect is indicated, and the post-replacement training scheme cannot be used as a strengthening training scheme, so that it can be determined that the post-replacement training scheme does not meet the preset strengthening training scheme conditions.

As one possible implementation manner, in step 2053, determining whether the post-replacement training scheme meets the preset training scheme condition may further include the following steps 205331 to 205337 in fig. 2L:

step 205331, determining whether the absolute value of the difference between the numbers of corresponding training items in the post-replacement training regimen for any two training targets in the subset of core training targets is less than the sixth number.

The sixth quantity can be set according to actual conditions, and the smaller the sixth quantity is, the smaller the difference value between the quantity of training items corresponding to different core training targets in the replaced training scheme is, and the more balanced the replaced training scheme is; the greater the sixth number, the more imbalanced the post-replacement training scheme.

If it is determined that the absolute value of the difference between the numbers of training items corresponding to any two training targets in the subset of core training targets in the post-replacement training scheme is less than the sixth number, indicating that the post-replacement training scheme is an equalization scheme, execution may proceed to step 205332. Conversely, if it is determined that the absolute values of the differences between the numbers of corresponding training items in the post-replacement training scenario for any two training goals in the subset of core training goals are not both less than the sixth number, indicating that the post-replacement training scenario is not an equalization scenario, execution may proceed to step 205333.

Step 205332, the scheme type of the post-replacement training scheme is labeled as an equalization scheme.

Step 205333, determining whether there are two different core training targets in the subset of core training targets, the difference between the numbers of corresponding training items in the post-replacement training scheme for the two different core training targets being greater than a seventh number.

If it is determined that the difference between the numbers of the corresponding training items of the two different core training targets in the core training target subset is greater than the seventh number, indicating that one of the core training targets corresponds to a sufficiently large number of training items, the post-replacement training scheme may be considered as a training scheme biased toward the core training target, and thus the step 205334 may be performed to mark the scheme type of the post-replacement training scheme as a scheme biased toward one of the training targets.

Otherwise, if it is determined that the difference between the numbers of the training items corresponding to the two different core training targets in the post-replacement training scheme is greater than the seventh number, which indicates that the numbers of the training items corresponding to the two core training targets are not greatly different, it is a scheme biased toward the plurality of training targets, so the execution of step 205335 may be shifted to mark the scheme type of the post-replacement training scheme as a scheme biased toward the plurality of training targets.

Step 205334, marking the scheme type of the post-replacement training scheme as a scheme biased toward a training goal.

Step 205335, marking the scheme type of the post-replacement training scheme as a scheme biased toward a plurality of training targets.

Through steps 205331 to 205335 described above, marking the scheme type of the post-replacement training scheme can be implemented.

Step 205336, determining a subset of training schemes to be compared according to the scheme type of the replaced training scheme.

Specifically, step 205336 may be performed as follows:

first, in response to the post-replacement training scheme being an equalization scheme or a scheme biased toward a training goal, a union of the set of enhanced training schemes of the base training scheme and the set of base training schemes is determined as a subset of training schemes to be compared.

And secondly, in response to the replaced training scheme being a scheme biased towards a plurality of training targets, determining schemes with the types of schemes biased towards the plurality of training targets in the enhanced training scheme set of the basic training scheme as a subset of training schemes to be compared.

In this way, the generated subset of training patterns to be compared is all the existing reinforced training patterns of the generated basic pattern or patterns biased to a plurality of training targets, and based on the generated subset of training patterns, a plurality of reinforced training patterns with higher similarity are prevented from being generated.

In step 205337, in response to determining that there are training schemes in the subset of training schemes to be compared that have a number of different training items than the eighth number of training schemes, determining that the post-replacement training scheme does not satisfy the preset reinforcement training scheme condition.

If the number of the different training items between the training scheme subset to be compared and the replaced training scheme is determined to be smaller than the eighth number, the training scheme which has smaller difference with the replaced training scheme exists in the training scheme subset to be compared, and the fact that similar strengthening training schemes are generated for the current basic training scheme is indicated, and in order to prevent a plurality of schemes with smaller difference from being generated, the replaced training scheme cannot be used as the strengthening training scheme, so that the fact that the replaced training scheme does not meet the preset strengthening training scheme conditions is determined.

As one possible implementation manner, in step 2053, determining whether the post-replacement training scheme meets the preset training scheme condition may further include the following steps 205341 in fig. 2M:

in step 205341, in response to determining that there is at least one training target in the training target set corresponding to zero number of corresponding training items in the post-replacement training scheme, it is determined that the post-replacement training scheme does not satisfy the preset reinforcement training scheme condition.

When one or more than one training target does not have a corresponding training program in the post-replacement training scheme, the post-replacement training scheme is not trained to all the training targets, the comprehensive training capability is poor, and the post-replacement training scheme cannot be used as a strengthening training scheme, so that the post-replacement training scheme can be determined to not meet the preset strengthening training scheme conditions.

In step 2053, at least one of the four different implementations of steps 205311 through 205312, 205321 through 205322, 205331 through 205337, and 205341 described above may be combined.

Through step 2053, adding the training scheme meeting the preset training scheme conditions in the post-replacement training scheme corresponding to the basic training scheme to the training scheme set corresponding to the basic training scheme can be achieved.

As a possible implementation, after step 2053, the operation of generating the set of reinforcement training solutions in step 205 further includes the following steps 2054 and 2055:

step 2054, determining whether there is no training scheme in the set of enhanced training schemes corresponding to the base scheme that is labeled as an equalization scheme or biased towards a training goal.

If yes, the enhanced training schemes corresponding to the basic training scheme are all training schemes biased to a plurality of training targets, and no equalization scheme or a scheme biased to one training target is adopted. If the subject user trains the basic training scheme F in the present period (for example, in the present month) _A Basic training scheme F for the period training of the user possibly _A Thereafter, it is determined that the subject user is performing poorly on one or both of the training goals, then the next cycle (e.g., the next month) is followed ifIn basic training scheme F _A Corresponding enhanced training scheme set F _B The strengthening training scheme is selected, and when the user is trained, the basic training scheme F is used _A Corresponding enhanced training scheme set F _B There is no training target biased training scheme or equalization scheme that can be selected, which would be detrimental to training the subject user in one or both training targets that perform poorly during the present period. I.e. the basic training scheme F _A Corresponding enhanced training scheme set F _B The derived schemes are less in types and not abundant in types, so that the basic training scheme F is not needed _A Corresponding enhanced training scheme set F _B Added to the overall reinforcement training solution set. Thus, if step 2054 determines that it is, execution may proceed to step 2055.

Step 2055, deleting the set of reinforcement training schemes corresponding to the basic scheme.

The step 2055 may delete the reinforcement training scheme set with weak derivation capability from the reinforcement training scheme set generated based on the basic training scheme, so as to achieve the effect of improving the derivation capability of the reinforcement training scheme in the overall reinforcement training scheme set generated in step 206.

Step 206, determining an overall reinforcement training scheme set based on the reinforcement training scheme set corresponding to each basic training scheme.

Here, the reinforcement training schemes corresponding to the respective basic training schemes generated in step 205 may be combined together, so that an overall reinforcement training scheme set may be obtained.

According to the training scheme generation method provided by the embodiment of the disclosure, through the preset multiple conditions, the first number of training items comprising different combinations are selected from the first training item set, and the first number of training items are added into the basic training scheme set under the condition that the screening conditions of the basic training scheme are met, so that the training scheme can be selected from the basic training schemes to train conveniently.

Based on what is shown in fig. 2A and its alternative embodiments, after the basic training scheme set and/or the overall enhanced training scheme is generated, only the first number of training items are included, but in practice, when the user is trained using a specific training scheme, it is also necessary to determine different sub-periods within the training period, and which specific training items in the training scheme are used at different stages of the sub-period to train the user. With continued reference to fig. 3, fig. 3 illustrates a method for generating training schemes at each stage in different sub-periods based on the generated basic training scheme set or the overall enhanced training scheme set illustrated in fig. 2A and its alternative embodiments, which may specifically include the following steps:

step 301, any basic training scheme or reinforcement training scheme is obtained as a target training scheme.

Here, any one basic training scheme or reinforcement training scheme may be obtained as the target training scheme, and the training schemes of each stage in different sub-periods corresponding to the target training scheme may be generated, so that training may be performed stepwise in different sub-periods in one period.

Step 302, the ninth previous training items with the lowest difficulty scores in the target training scheme are obtained, and a low-difficulty item set is generated.

The low-difficulty items are used for generating training schemes of the first stage in different subcycles in one training period, so that the former ninth number of training items with low difficulty scores are selected to generate a low-difficulty item set. Here, since the first number of training items is included in the target training scheme, the ninth number is smaller than the first number. For example, when the target training regimen is a monthly training regimen, i.e., the training period is one month, and the target training regimen includes 8 training items, the ninth number may be 6, i.e., the low difficulty item set includes the first 6 training items of the target training regimen that are the lowest difficulty.

Step 303, determining a screening training scheme set based on the low-difficulty item set.

The screening training scheme comprises a tenth number of training items in the low-difficulty item set, wherein the tenth number is smaller than the ninth number. For example, the ninth number is 6, and the tenth number may be 5, that is, the low difficulty training program set includes 6 training programs, the screening training scheme set includes 5 training programs, and since there are many options for selecting 5 training programs from the 6 training programs, this step 303 may correspondingly generate a plurality of different screening training schemes, to form the screening training scheme set. The set of screening training schemes is used to generate training schemes for the first stage in different sub-periods of the training period, that is, the generated training schemes for the first stage in different sub-periods each include a tenth number (e.g., 5) of training items.

Step 304, sorting the screening training schemes according to the order of the difficulty scores from low to high, sorting the screening training schemes of the number of subcycles before sorting according to the difficulty scores of the corresponding screening training schemes, and sequentially determining the first stage training scheme of the corresponding sorting subcycle in the preset training period.

Here, the training period may include a number of different sub-periods ordered by time. Assuming that the number of sub-periods is T (T is a positive integer), there are J (J is a positive integer) screening training schemes F in the screening training scheme set _j J is a positive integer between 1 and J, and the number of subcycles T is less than the number of screening training schemes J. Each screening training program F _j There is a tenth number of training items. Step 304 is to select J screening training schemes F _j After the middle ranking, the screening training scheme of the top T ranking is F _t T is a positive integer between 1 and T. For each screening training scheme F ordered in top T _t F is to F _t And determining a first stage training scheme of a t-th subcycle in a preset training period. That is, the difficulty score of the training scheme in the first stage of each sub-period in the preset training period is gradually increased according to the time of the sub-period, so that the user can adapt to and gradually increase the training difficulty.

For example, the target training scheme may be a monthly training scheme, that is, the preset training period may be 28 days, each training period may include four sub-periods, each sub-period may be one week, and each sub-period may be internally divided into different stages according to actual situations. For example, the first and second days of the week are the first phase, the third and fourth days are the second phase, and the fifth through seventh days are the third phase, each of which is trained according to the same phase training regimen.

Step 305, for each sub-period in the preset training period, performing a phase training scheme generating operation in the sub-period.

Determining a first stage training scheme of the sub-period as a current stage training scheme; generating a subcycle historical training item set by using each training item in the training scheme of the current stage; starting from the second stage of the sub-period until the last stage, for each stage, the following sub-period stage scheme generation operations are performed in accordance with the temporal ordering of the respective stages in the sub-period: generating a next-stage replacement item set by using training items except for the historical training items in the target training scheme, and generating the stage training scheme of the subcycle by replacing the training item with the lowest difficulty score in the current-stage training scheme by using the training item with the lowest difficulty score in the next-stage replacement item set; adding each training item in the stage training scheme to the history training item set, and determining the stage training scheme as the current stage training scheme.

Therefore, the difficulty score of the training scheme in the first stage of each sub-period in the preset training period can be gradually increased according to the time of the sub-period, and the training difficulty can be conveniently and gradually adapted to the user and gradually increased.

As one possible implementation, after the generation of the phase training scheme, the generated phase training scheme may be further marked to determine whether it is a phase training scheme biased towards a few training targets or an integrated sub-phase training scheme, which specifically includes the following steps 306 to 310:

step 306, obtaining any stage training scheme in any sub-period corresponding to the target training scheme as a target stage training scheme.

Step 307, for each training target, determining the number of stage training items corresponding to the training target in the target stage training scheme.

Step 308, determining whether the difference obtained by subtracting the number of stage training items corresponding to the next multiple training targets from the number of stage training items corresponding to the maximum training targets is greater than the eleventh number.

The maximum training targets and the secondary multiple training targets are respectively the training targets with the maximum number and the secondary multiple training items in the corresponding stage training items in each training target.

In response to determining that the target phase training scenario is a phase training scenario biased towards the maximum training target, step 309.

When the number difference between the most training targets and the training items corresponding to the next most training targets is large, the training items corresponding to the most training items are enough, and the training items can be marked as a stage training scheme biased to the most training targets.

In step 310, in response to determining no, the target stage training scheme is marked as an equalization stage training scheme.

When the number of training items corresponding to the maximum training target and the secondary multiple training targets is not great, the training items indicating the maximum training target are not very much, and the training items can be marked as a comprehensive stage training scheme.

According to the embodiment, aiming at each sub-period of each basic training scheme or enhanced training scheme, a plurality of stage training schemes are correspondingly generated, training items in the basic training scheme or the enhanced training scheme are further trained, and training effects and training experience of users are improved. The stage training schemes are marked, so that a user can know the training type of each stage training scheme.

With further reference to fig. 4, as an implementation of the method shown in the foregoing figures, the present disclosure provides an embodiment of a training scheme generating apparatus, where an embodiment of the apparatus corresponds to the embodiment of the method shown in fig. 2A, and the apparatus may be specifically applied to various electronic devices.

As shown in fig. 4, the training scheme generating apparatus 400 of the present embodiment includes: a first acquisition module 401 and a base scheme generation module 402. Wherein:

a first obtaining module 401, configured to obtain a first training item set;

the base scheme generating module 402 is configured to perform the following base scheme generating operations until a preset base scheme generating end condition is satisfied: selecting a first number of training items from the first training item set to generate a training scheme; determining whether the generated training scheme meets the preset basic training scheme screening conditions; in response to determining that the generated training scheme is added to the base training scheme set.

In some optional embodiments, each training item may correspond to at least one training target in a training target set, which may include a subset of core training targets including at least two core training targets;

and

determining a current training target in the core training target subset;

generating an empty training scheme as a current training scheme;

and determining the current training scheme as the generated training scheme.

In some alternative embodiments, the apparatus 400 may further include:

a deletion module 403, configured to perform the following scheme deletion operation until at least a fourth number of different training items are included between any two training schemes in the basic training scheme set described above: for any two of the set of base training schemes, deleting any one of the two base training schemes from the set of base training schemes in response to determining that at least a fourth number of different training items are not included between the two base training schemes.

In some alternative embodiments, the apparatus 400 may further include:

a second obtaining module 404, configured to obtain a second training item set, where an average difficulty of the first training item set is lower than an average difficulty of the second training item set;

the reinforcement scheme generating module 405 is configured to perform, for each of the above basic training schemes, the following reinforcement training scheme set generating operation: determining a set of selectable replacement items from the second set of training items, wherein the selectable replacement items are not in the base training scheme; replacing any fifth number of training items in the basic training scheme with any fifth number of training items in the selectable replacement item set to obtain at least one replaced training scheme corresponding to the basic training scheme; for each obtained post-replacement training scheme, determining whether the post-replacement training scheme meets the preset reinforcement training scheme conditions, and in response to the determination that the post-replacement training scheme is added into the reinforcement training scheme set corresponding to the basic training scheme;

The reinforcement scheme confirmation module 406 is configured to determine an overall reinforcement training scheme set based on the reinforcement training scheme sets corresponding to the basic training schemes.

the apparatus 400 may further include:

a target training scheme obtaining module 407, configured to obtain any one of the basic training scheme or the reinforcement training scheme as a target training scheme;

a low-difficulty item obtaining module 408, configured to obtain the first ninth number of training items with the lowest difficulty scores in the target training scheme, and generate a low-difficulty item set;

a screening solution determining module 409, configured to determine a screening training solution set based on the low-difficulty item set, where the screening training solution includes a tenth number of training items in the low-difficulty item set, and the tenth number is smaller than the ninth number;

a first stage training scheme generating module 410, configured to rank each of the above screening training schemes in order from low to high difficulty scores, rank a number of screening training schemes of the sub-period before ranking according to the difficulty scores of the corresponding screening training schemes, and sequentially determine the first stage training scheme as the corresponding ranking sub-period in the preset training period;

the following stage training scheme generation module 411 is configured to perform, for each sub-period in the preset training period, the following intra-sub-period stage training scheme generation operations: determining a first stage training scheme of the sub-period as a current stage training scheme; generating a subcycle historical training item set by using each training item in the training scheme of the current stage; starting from the second stage of the sub-period until the last stage, for each stage, the following sub-period stage scheme generation operations are performed in accordance with the temporal ordering of the respective stages in the sub-period: generating a next-stage replacement item set by using training items except for the historical training items in the target training scheme, and generating the stage training scheme of the subcycle by replacing the training item with the lowest difficulty score in the current-stage training scheme by using the training item with the lowest difficulty score in the next-stage replacement item set; adding each training item in the stage training scheme to the history training item set, and determining the stage training scheme as the current stage training scheme.

the apparatus 400 may further include:

a target stage training scheme obtaining module 412, configured to obtain, as a target stage training scheme, any stage training scheme in any sub-period corresponding to the target training scheme;

a training item number determining module 413, configured to determine, for each of the training targets, a number of stage training items corresponding to the training target in the target stage training scheme;

a training item number comparison module 414, configured to determine whether a difference obtained by subtracting the number of stage training items corresponding to the next-to-multiple training targets from the number of stage training items corresponding to the maximum training target is greater than an eleventh number, where the maximum training target and the next-to-multiple training target are the training targets with the maximum number and the next-to-multiple number of stage training items corresponding to the respective training targets;

a first stage marking module 415 for marking the target stage training scheme as a stage training scheme biased toward the maximum training target in response to determining that the target stage training scheme is the most training target;

a second stage marking module 416, configured to mark the target stage training scheme as an equalization stage training scheme in response to determining whether to.

Referring now to FIG. 5, there is illustrated a schematic diagram of a computer system 500 suitable for use in implementing the electronic device of the present disclosure. The computer system 500 shown in fig. 5 is merely an example and should not be construed as limiting the functionality and scope of use of embodiments of the present disclosure.

As shown in fig. 5, a computer system 500 may include a processing device (e.g., a central processing unit, a graphics processor, etc.) 501 that may perform various suitable actions and processes in accordance with programs stored in a Read Only Memory (ROM) 502 or loaded from a storage device 508 into a Random Access Memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the computer system 500 are also stored. The processing device 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input/output (I/O) interface 505 is also connected to bus 504.

In general, the following devices may be connected to the I/O interface 505: input devices 506 including, for example, a touch screen, touchpad, keyboard, mouse, camera, microphone, etc.; an output device 507 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage 508 including, for example, magnetic tape, hard disk, etc.; and communication means 509. The communication means 509 may allow the computer system 500 to communicate with other devices wirelessly or by wire to exchange data. While fig. 5 illustrates a computer system 500 having electronic devices with various means, it should be understood that not all illustrated means are required to be implemented or provided. More or fewer devices may be implemented or provided instead.

In particular, according to embodiments of the present disclosure, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method shown in the flowcharts. In such an embodiment, the computer program may be downloaded and installed from a network via the communication means 509, or from the storage means 508, or from the ROM 502. The above-described functions defined in the methods of the embodiments of the present disclosure are performed when the computer program is executed by the processing device 501.

It should be noted that the computer readable medium described in the present disclosure may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this disclosure, a computer-readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present disclosure, however, the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, fiber optic cables, RF (radio frequency), and the like, or any suitable combination of the foregoing.

The computer readable medium may be contained in the electronic device; or may exist alone without being incorporated into the electronic device.

The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to implement the training scheme generation method shown in the embodiment and its alternative implementation shown in fig. 2A or fig. 3.

Computer program code for carrying out operations of the present disclosure may be written in one or more programming languages, including an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).

The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The modules or units referred to in the embodiments of the present disclosure may be implemented in software or in hardware. Where the name of a module or unit does not in some cases constitute a limitation of the module or unit itself.

The foregoing description is only of the preferred embodiments of the present disclosure and description of the principles of the technology being employed. It will be appreciated by persons skilled in the art that the scope of the disclosure referred to in this disclosure is not limited to the specific combinations of features described above, but also covers other embodiments which may be formed by any combination of features described above or equivalents thereof without departing from the spirit of the disclosure. Such as those described above, are mutually substituted with the technical features having similar functions disclosed in the present disclosure (but not limited thereto).

Claims

1. A training scheme generation method, which is applied to user cognitive ability training, comprising:

acquiring a first training item set, wherein each training item corresponds to at least one training target in a training target set, the training target set comprises a core training target subset, and the core training target subset comprises at least two core training targets;

the following basic scheme generation operation is executed until a preset basic scheme generation end condition is satisfied: selecting a first number of training items from the first training item set to generate a training scheme; determining whether the generated training scheme meets the preset basic training scheme screening conditions; in response to determining that the generated training scheme is added to the base training scheme set;

Wherein, the selecting a first number of training items from the first training item set, and generating a training scheme includes:

determining a current training target in the core training target subset;

generating an empty training scheme as a current training scheme;

the following training scheme generating operation is performed until the number of training items in the current training scheme reaches the first number: acquiring training items corresponding to the current training target from the first training item set to obtain a training item set to be selected; extracting a training item from the training item set to be selected as a selected training item, wherein the selected training item is not in the current training scheme; adding the selected training items to the current training scheme; determining a next training target based on a preset training target selection rule; replacing the current training target with the next training target, and continuing to execute the training scheme generation operation;

determining the current training scheme as the generated training scheme; and

the determining the next training target based on the preset training target selection rule comprises the following steps:

Determining whether the number of training items in the current training scheme is less than a second number;

determining a first filterable training target subset from the first training target set to be filtered, wherein the first filterable training target comprises training items which do not belong to the current training scheme in the corresponding training items in the first training item set;

acquiring a first screenable training target with the minimum training items corresponding to the current training scheme in the first screenable training target subset as a next training target; and

the determining whether the generated training scheme meets the preset basic training scheme screening condition comprises the following steps:

determining whether the absolute value of the difference between any two quantities in the set of balanced comparison quantities is no greater than a third quantity;

2. The method of claim 1, wherein determining the next training target based on the preset training target selection rule comprises:

in response to determining that the biased training object set is the second training object set to be screened;

In response to determining that the secondary biased training object set is the second training object set to be screened;

3. The method according to claim 1, wherein the method further comprises:

the following scheme deletion operation is performed until at least a fourth number of different training items are included between any two training schemes in the basic training scheme set: for any two of the set of base training schemes, deleting any one of the two base training schemes from the set of base training schemes in response to determining that at least a fourth number of different training items are not included between the two base training schemes.

4. The method according to claim 1, wherein the method further comprises:

for each basic training scheme, performing the following reinforcement training scheme set generation operations: determining a set of selectable replacement items from the second set of training items, wherein the selectable replacement items are not in the base training scheme; replacing any fifth number of training items in the basic training scheme with any fifth number of training items in the selectable replacement item set to obtain at least one replaced training scheme corresponding to the basic training scheme; for each obtained post-replacement training scheme, determining whether the post-replacement training scheme meets the preset reinforcement training scheme conditions, and in response to the determination that the post-replacement training scheme is added into the reinforcement training scheme set corresponding to the basic training scheme;

5. The method of claim 4, wherein the training items correspond to difficulty scores; and

Replacing any fifth number of training items in the basic training scheme with any fifth number of training items in the selectable replacement item set to obtain at least one post-replacement training scheme corresponding to the basic training scheme, wherein the method comprises the following steps:

for each set of said replaced training items, performing the following post-replacement training scheme generation operations: acquiring a difference set between the original training item set and the replaced training item set as a reserved training item set; acquiring a training item with the lowest difficulty score in the reserved training item set as the lowest difficulty training item; acquiring training items with difficulty scores larger than those of the lowest-difficulty training items from the selectable replacement item set as a selectable enhanced replacement item set; obtaining a fifth number of training items from the selectable enhanced replacement item set by adopting at least one selection mode to obtain at least one replacement training item set; and generating a post-replacement training scheme corresponding to the basic training scheme by using the reserved training item set and each of the replacement training item sets respectively.

6. The method of claim 4, wherein determining whether the post-replacement training scheme satisfies a preset reinforcement training scheme condition comprises:

7. The method of claim 4, wherein determining whether the post-replacement training scheme satisfies a preset reinforcement training scheme condition comprises:

8. The method of claim 4, wherein determining whether the post-replacement training scheme satisfies a preset reinforcement training scheme condition comprises:

Determining whether absolute values of differences between numbers of corresponding training items in the post-replacement training scheme for any two training targets in the subset of core training targets are all less than a sixth number;

in response to determining no, determining whether there are two different core training targets in the subset of core training targets, a difference between the numbers of corresponding training items in the post-replacement training scheme for the two different core training targets being greater than a seventh number;

and in response to determining that there are training schemes in the subset of training schemes to be compared, wherein the number of different training items between the training schemes is smaller than the eighth number, determining that the post-replacement training scheme does not meet the preset reinforcement training scheme condition.

9. The method of claim 8, wherein determining a subset of training patterns to be compared based on the pattern type of the post-replacement training patterns comprises:

in response to the post-replacement training scheme being an equalization scheme or a scheme biased toward a training target, determining a union of the set of reinforcement training schemes of the base training scheme and the set of base training schemes as a subset of training schemes to be compared;

10. The method of claim 8, wherein the reinforcement training scheme set generation operation further comprises:

determining whether a training scheme marked as an equalization scheme or biased to a training target does not exist in the enhanced training scheme set corresponding to the basic training scheme;

and deleting the enhanced training scheme set corresponding to the basic training scheme in response to the determination.

11. The method of claim 4, wherein determining whether the post-replacement training scheme satisfies a preset reinforcement training scheme condition comprises:

And in response to determining that the training target set has at least one training target corresponding to zero number of corresponding training items in the post-replacement training scheme, determining that the post-replacement training scheme does not meet the preset reinforcement training scheme conditions.

12. The method of claim 4, wherein the training items correspond to difficulty scores; and

the method further comprises the steps of:

acquiring a ninth previous number of training items with the lowest difficulty score in the target training scheme, and generating a low-difficulty item set;

sorting the screening training schemes according to the order of low difficulty scores from low to high, and sequentially determining the number of screening training schemes of sub-periods before sorting as a first stage training scheme of a corresponding sorting sub-period in a preset training period;

for each sub-period of the preset training period, performing the following intra-sub-period phase training scheme generation operations: determining a first stage training scheme of the sub-period as a current stage training scheme; generating a subcycle historical training item set by using each training item in the current stage training scheme; starting from the second stage of the sub-period until the last stage, for each stage, the following sub-period stage scheme generation operations are performed in accordance with the temporal ordering of the respective stages in the sub-period: generating a next-stage replacement item set by using training items except for each historical training item in the target training scheme, and generating the stage training scheme of the sub-period by replacing the training item with the lowest difficulty score in the current-stage training scheme by using the training item with the lowest difficulty score in the next-stage replacement item set; adding each training item in the stage training scheme to the historical training item set, and determining the stage training scheme as the current stage training scheme.

13. The method of claim 12, wherein each training item corresponds to at least one training object in a set of training objects; and

the method further comprises the steps of:

determining whether the difference obtained by subtracting the number of stage training items corresponding to the secondary multiple training targets from the number of stage training items corresponding to the maximum training target is larger than the eleventh number, wherein the maximum training target and the secondary multiple training target are respectively the training targets with the maximum number and the secondary multiple stage training items corresponding to the training targets;

in response to determining that the target phase training scenario is a phase training scenario biased toward the most training target;

14. A training scheme generation apparatus, for use in user cognitive training, comprising:

The system comprises an acquisition module, a first training program set and a second training program set, wherein each training program corresponds to at least one training target in the training target set, the training target set comprises a core training target subset, and the core training target subset comprises at least two core training targets;

the basic scheme generation module is used for executing the following basic scheme generation operation until a preset basic scheme generation ending condition is met: selecting a first number of training items from the first training item set to generate a training scheme; determining whether the generated training scheme meets the preset basic training scheme screening conditions; in response to determining that the generated training scheme is added to the base training scheme set;

determining a current training target in the core training target subset;

generating an empty training scheme as a current training scheme;

Determining the current training scheme as the generated training scheme; and

15. An electronic device, comprising:

one or more processors;

a storage device having one or more programs stored thereon,

the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of any of claims 1-13.

16. A computer readable storage medium, having stored thereon a computer program, wherein the computer program when executed by one or more processors implements the method of any of claims 1-13.