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

Abstract

The invention provides a training scheme generation method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring a scale data set of a target user; for each course theme, determining the priority of the course theme for the target user according to the scale data set and the association degree of each scale in the scale data set for the course theme; determining at least one target course theme matched with the target user according to the priority of each course theme for the target user; aiming at each target course theme, executing a training scheme generation operation: obtaining at least one target difficulty factor associated with the target course theme; based on at least one scale having a first association relationship with each target difficulty factor and a scale data set, determining a target difficulty level combination matched with the target user; and generating an initial training scheme of the target course theme for the target user according to the difficulty level corresponding to each target difficulty factor in the target difficulty level combination.

Description

Technical Field

[0001] The embodiments disclosed herein relate to the field of computer technology, and more specifically to a training scheme generation method, apparatus, electronic device, and storage medium. Background Technology

[0002] Social learning for individuals with autism and Asperger's syndrome aims to improve their social skills through personalized training programs.

[0003] In existing training programs, users' social skills are typically roughly graded based on the assessment results of a single scale, and the grading results are directly mapped to the pre-set course content.

[0004] However, the above training programs ignore the compatibility between users' performance in multiple dimensions (such as emotional health and social cognition) and the training programs, making it difficult for recommended courses to accurately match individual needs, thus affecting training effectiveness and user experience. In addition, most training programs have fixed course formats, which may cause users to find that the course format is not suitable for them after the course starts, and they have to adapt temporarily, increasing unnecessary learning costs.

[0005] Therefore, it is necessary to propose a training scheme generation method to solve at least one of the above-mentioned technical problems. Summary of the Invention

[0006] The embodiments of this disclosure propose a training scheme generation method, apparatus, electronic device, and storage medium. It can select suitable course topics for users based on multiple scales. On this basis, it can match course content with a suitable user difficulty level based on multiple difficulty factors. The generated training scheme can more accurately match the specific needs of different individuals, enhance training effect and user experience, and reduce learning cost.

[0007] Firstly, this disclosure provides a method for generating training schemes, including:

[0008] Obtain a scale dataset of the target user, wherein the scale dataset includes each item of at least one scale and the target user's response to the item;

[0009] For each course topic in the preset course topic set, the priority of the course topic for the target user is determined based on the scale dataset and the correlation between each scale in the scale dataset and the course topic.

[0010] Based on the priority of each course topic for the target user, determine at least one target course topic that matches the target user;

[0011] For each target course topic, the following training scheme generation operation is performed: Based on a preset mapping relationship between course topics and difficulty factors, at least one target difficulty factor associated with the target course topic is obtained; based on at least one scale with a first correlation relationship to each target difficulty factor and the scale dataset, a target difficulty level combination matching the target user is determined, wherein the target difficulty level combination is composed of the target difficulty levels of each of the at least one target difficulty factor; based on the target difficulty levels corresponding to each target difficulty factor in the target difficulty level combination, an initial training scheme for the target course topic for the target user is generated.

[0012] In some optional implementations, determining the priority of each course topic for the target user based on the scale dataset and the relevance of each scale in the scale dataset to the course topic includes:

[0013] For each course topic in the pre-defined course topic set, perform the following priority determination operation:

[0014] Determine the relevance of each scale in the scale dataset to the course topic; generate a priority assessment result for the course topic based on the scale dataset and the relevance of each scale in the scale dataset to the course topic; and determine the priority of the course topic for the target user based on the priority assessment result of the course topic.

[0015] In some optional implementations, generating a priority assessment result for the course topic based on the scale dataset and the relevance of each scale in the scale dataset to the course topic includes:

[0016] Generate scale assessment results for each scale in the scale dataset based on the scale dataset;

[0017] For each scale, the scale evaluation result is normalized according to the normalization direction of the scale to obtain the normalized scale evaluation result.

[0018] Based on the normalized scale evaluation results of each scale and the correlation between each scale in the scale dataset and the course topic, a priority evaluation result for the course topic is generated.

[0019] In some optional implementations, each scale in the scale dataset includes at least one item dimension, each item in each scale belongs to one of the item dimensions, and the scale dataset also includes the item dimension for each item in the at least one scale; and

[0020] The step of normalizing the scale assessment results according to the normalization direction of the scale to obtain the normalized scale assessment results includes:

[0021] For each item dimension in the scale, the dimension evaluation result of that item dimension in the scale is determined based on the target user's answers to each item belonging to that item dimension;

[0022] The dimensional assessment results of each item dimension in the scale are normalized according to the normalization direction of each item dimension to obtain the normalized dimensional assessment results of each item dimension in the scale. Based on the normalized dimensional assessment results of each item dimension in the scale, the normalized scale assessment results of the scale are determined.

[0023] In some optional implementations, each of the target difficulty factors has at least one difficulty level; and

[0024] Based on at least one scale having a first correlation with each of the target difficulty factors and the scale dataset, determine the target difficulty level combination matching the target user, including:

[0025] Based on the difficulty levels of each of the target difficulty factors, a first set of difficulty level combinations corresponding to the target course theme is generated, wherein the first set of difficulty level combinations includes a combination of difficulty levels of at least one of the target difficulty factors with different difficulty levels.

[0026] Based on the first set of difficulty level combinations, at least one scale having a first correlation with each of the target difficulty factors, and the scale dataset, a target difficulty level combination matching the target user is determined.

[0027] In some optional implementations, determining the target difficulty level combination matching the target user based on the first difficulty level combination set, at least one scale having a first correlation with each of the target difficulty factors, and the scale dataset includes:

[0028] Based on the preset difficulty assessment method, determine the difficulty level assessment result of each difficulty level combination in the first difficulty level combination set;

[0029] Based on the priority evaluation results of the course topic and the difficulty level evaluation results of each difficulty level combination in the first difficulty level combination set, the training difficulty range for the target user is determined.

[0030] A second difficulty level combination set is generated based on the difficulty level evaluation results corresponding to the first difficulty level combination set that belong to the training difficulty range.

[0031] Based on the second set of difficulty level combinations, at least one scale having a first correlation with each of the target difficulty factors, and the scale dataset, a target difficulty level combination matching the target user is determined.

[0032] In some optional implementations, determining the target difficulty level combination matching the target user based on the second difficulty level combination set, at least one scale having a first correlation with each of the target difficulty factors, and the scale dataset includes:

[0033] Based on the scale assessment results of at least one scale that has a first correlation with each of the target difficulty factors and the difficulty level of each target difficulty factor in each difficulty level combination in the second difficulty level combination set, a third difficulty level combination set is generated, wherein the third difficulty level combination set includes difficulty level combinations that match the scale assessment results of at least one scale that has a first correlation with each target difficulty factor.

[0034] Based on the third set of difficulty level combinations, determine the target difficulty level combination that matches the target user.

[0035] In some optional implementations, the method further includes:

[0036] Obtain the learning styles of the target users;

[0037] Determine whether the learning style of the target user falls within a preset learning style range;

[0038] In response to the determination, the initial training scheme is adjusted according to the learning style of the target user to obtain a first adjusted training scheme;

[0039] In response to a no-response, the target user's interests and preferences are obtained;

[0040] Based on the interests and preferences of the target users, the initial training scheme is adjusted to obtain a second adjusted training scheme.

[0041] In some alternative implementations, the preset learning style includes visual learning, auditory learning, kinesthetic learning, and multisensory learning.

[0042] In some optional implementations, the method further includes:

[0043] For each target difficulty factor associated with the target course theme, the following difficulty level adjustment operation is performed: determine at least one scale that has a second association with the target difficulty factor; adjust the difficulty level of the target difficulty factor based on the difficulty level of the target difficulty factor in the target difficulty level combination and the scale assessment results of at least one scale that has a second association with the target difficulty factor;

[0044] The difficulty level of each target difficulty factor associated with the target course theme after the difficulty level adjustment is determined as the target difficulty level combination that matches the target user;

[0045] The initial training scheme, the first adjusted training scheme, or the second adjusted training scheme are adjusted according to the target difficulty level combination of at least one target difficulty factor to obtain a third adjusted training scheme.

[0046] Secondly, this disclosure provides a training scheme generation apparatus, including:

[0047] The first acquisition unit is used to acquire a scale dataset of the target user, wherein the scale dataset includes each item of at least one scale and the target user's answer to the item;

[0048] The first determining unit is used to determine the priority of each course topic for the target user for each course topic in the preset course topic set, based on the scale dataset and the correlation between each scale in the scale dataset and the course topic.

[0049] The second determining unit is used to determine at least one target course topic that matches the target user based on the priority of each course topic for the target user.

[0050] The generation unit is configured to perform the following training scheme generation operation for each target course topic: obtain at least one target difficulty factor associated with the target course topic according to a preset mapping relationship between course topics and difficulty factors; determine a target difficulty level combination matching the target user based on at least one scale with a first correlation relationship with each of the target difficulty factors and the scale dataset, wherein the target difficulty level combination is composed of the target difficulty level combination of each of the at least one target difficulty factor; and generate an initial training scheme for the target course topic for the target user according to the target difficulty level corresponding to each target difficulty factor in the target difficulty level combination.

[0051] In some alternative implementations, the first determining unit may be further used to:

[0052] For each course topic in the pre-defined course topic set, perform the following priority determination operation:

[0053] Determine the relevance of each scale in the scale dataset to the course topic; generate a priority assessment result for the course topic based on the scale dataset and the relevance of each scale in the scale dataset to the course topic; and determine the priority of the course topic for the target user based on the priority assessment result of the course topic.

[0054] In some alternative implementations, the first determining unit may be further used to:

[0055] Generate scale assessment results for each scale in the scale dataset based on the scale dataset;

[0056] For each scale, the scale evaluation result is normalized according to the normalization direction of the scale to obtain the normalized scale evaluation result.

[0057] Based on the normalized scale evaluation results of each scale and the correlation between each scale in the scale dataset and the course topic, a priority evaluation result for the course topic is generated.

[0058] In some optional implementations, each scale in the scale dataset includes at least one item dimension, each item in each scale belongs to one of the item dimensions, and the scale dataset also includes the item dimension for each item in the at least one scale; and

[0059] The second determining unit can be further used to: for each item dimension in the scale, based on the target user's answers to each item belonging to that item dimension, determine the dimension evaluation result of that item dimension in the scale;

[0060] The dimensional assessment results of the item dimension in the scale are normalized according to the normalization direction of the item dimension to obtain the normalized dimensional assessment results of the item dimension in the scale. Based on the normalized dimensional assessment results of each item dimension in the scale, the normalized scale assessment results of the scale are determined.

[0061] In some optional implementations, each of the target difficulty factors has at least one difficulty level; and

[0062] The second determining unit can be further used to: generate a first difficulty level combination set corresponding to the target course theme based on each difficulty level of each of the target difficulty factors, wherein the first difficulty level combination set includes a combination of difficulty levels of at least one of the target difficulty factors with different difficulty levels.

[0063] Based on the first set of difficulty level combinations, at least one scale having a first correlation with each of the target difficulty factors, and the scale dataset, a target difficulty level combination matching the target user is determined.

[0064] In some optional implementations, the second determining unit may be further used to: determine the difficulty level assessment result of each difficulty level combination in the first difficulty level combination set according to a preset difficulty assessment method;

[0065] Based on the priority evaluation results of the course topic and the difficulty level evaluation results of each difficulty level combination in the first difficulty level combination set, the training difficulty range for the target user is determined.

[0066] A second set of difficulty level combinations is generated based on the difficulty level evaluation results corresponding to the first set of difficulty level combinations that belong to the training difficulty range.

[0067] Based on the second set of difficulty level combinations, at least one scale having a first correlation with each of the target difficulty factors, and the scale dataset, a target difficulty level combination matching the target user is determined.

[0068] In some optional implementations, the second determining unit may be further configured to: generate a third difficulty level combination set based on the scale assessment results of at least one scale having a first correlation with each of the target difficulty factors and the difficulty level of each target difficulty factor in each difficulty level combination in the second difficulty level combination set, wherein the third difficulty level combination set includes difficulty level combinations that match the scale assessment results of at least one scale having a first correlation with each target difficulty factor.

[0069] Based on the third set of difficulty level combinations, determine the target difficulty level combination that matches the target user.

[0070] In some alternative embodiments, the device further includes:

[0071] The second acquisition unit is used to acquire the learning style of the target user;

[0072] The second determining unit is used to determine whether the learning style of the target user is within a preset learning style range;

[0073] The first adjustment unit is configured to adjust the initial training scheme according to the learning style of the target user in response to the determination, so as to obtain a first adjusted training scheme.

[0074] The third acquisition unit is used to acquire the target user's interest preferences in response to a yes or no determination.

[0075] The second adjustment unit is used to adjust the initial training scheme according to the interests and preferences of the target user to obtain a second adjusted training scheme.

[0076] In some alternative implementations, the preset learning style includes visual learning, auditory learning, kinesthetic learning, and multisensory learning.

[0077] In some alternative embodiments, the device further includes:

[0078] The third adjustment unit is used to perform the following difficulty level adjustment operation for each target difficulty factor associated with the target course theme: determine at least one scale that has a second association with the target difficulty factor; and adjust the difficulty level of the target difficulty factor based on the difficulty level of the target difficulty factor in the target difficulty level combination and the scale assessment results of at least one scale that has a second association with the target difficulty factor.

[0079] The fourth determining unit is used to determine the difficulty level of each target difficulty factor associated with the target course theme after the difficulty level adjustment as a target difficulty level combination that matches the target user.

[0080] The obtaining unit is used to adjust the initial training scheme, the first adjusted training scheme, or the second adjusted training scheme according to the target difficulty level combination of at least one target difficulty factor to obtain a third adjusted training scheme.

[0081] Thirdly, this disclosure provides an electronic device, including:

[0082] One or more processors;

[0083] Storage device, on which one or more programs are stored,

[0084] When the above-described one or more programs are executed by the above-described one or more processors, the above-described one or more processors implement the method as described in any embodiment of the first aspect of this disclosure.

[0085] Fourthly, this disclosure provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by one or more processors, implements the method described in any embodiment of the first aspect of this disclosure.

[0086] Fifthly, this disclosure provides a computer program product, including a computer program / instructions that, when executed by a processor, implement the method described in any embodiment of the first aspect of this disclosure.

[0087] The training scheme generation method, apparatus, electronic device, and storage medium provided in the embodiments of this disclosure acquire a scale dataset of a target user, wherein the scale dataset includes each item of at least one scale and the target user's answer to the item; for each course topic in a preset course topic set, the priority of the course topic for the target user is determined based on the scale dataset and the correlation between each scale in the scale dataset and the course topic; based on the priority of each course topic for the target user, at least one target course topic matching the target user is determined; for each target course topic, the following training scheme generation operation is performed: based on a preset course topic-difficulty factor mapping relationship, at least one difficulty factor associated with the target course topic is acquired; based on at least one scale with a first correlation relationship with each target difficulty factor and the scale dataset, a target difficulty level combination matching the target user is determined, wherein the target difficulty level combination is composed of the target difficulty level combination of each target difficulty factor in the at least one target difficulty factor; based on the target difficulty level corresponding to each target difficulty factor in the target difficulty level combination, an initial training scheme for the target course topic for the target user is generated. This disclosure can determine the priority of course topics based on multiple scales, and then select target course topics that match the user according to the priority of course topics. It can also determine the target difficulty level combination of at least one target difficulty factor that matches the target user based on at least one target difficulty factor associated with the target course topic, so as to determine the most suitable course content difficulty for the target user under the target course topic. This can more accurately match the specific needs of individuals, enhance training effect and user experience, and reduce learning costs. Attached Figure Description

[0088] Other features, objects, and advantages of this disclosure will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings. The drawings are for illustrative purposes only and are not intended to limit the invention. In the drawings:

[0089] Figure 1 This is a system architecture diagram in which an embodiment of the training scheme generation method of this disclosure can be applied;

[0090] Figure 2 This is a flowchart of an embodiment of the training scheme generation method according to the present disclosure;

[0091] Figure 3 This is an exploded flowchart of one embodiment of step 204 of this disclosure;

[0092] Figure 4 This is a schematic diagram of the structure of an embodiment of the training scheme generation apparatus according to the present disclosure;

[0093] Figure 5 This is a schematic diagram of the structure of a computer system suitable for implementing embodiments of the present disclosure. Detailed Implementation

[0094] Social learning for individuals with autism and Asperger's syndrome aims to improve their social skills through personalized training programs.

[0095] In existing social training programs, users' social skills are typically roughly categorized into "low / medium / high" levels based on assessments using a single scale (e.g., a social skills knowledge scale or an anxiety scale). These categorizations are then directly mapped to pre-set course content. The selection of course topics often only considers the linear difficulty of the course itself, neglecting the differences in user adaptability to different course topics in terms of emotional health, social cognition, and behavioral characteristics. Furthermore, existing training programs fail to fully consider the impact of users' learning styles, interests, and preferences on the course topics.

[0096] Therefore, the training solutions of the existing technologies mentioned above cannot fully reflect the combined characteristics of learners' language ability, social motivation, conflict coping, and interest preferences. The recommended courses are difficult to accurately match the specific needs of individuals, causing learners to face excessive challenges or lack of targeted problems in the early stages of the course, which affects the subsequent learning process, thereby affecting the training effect and user experience. Furthermore, the training solutions of the existing technologies do not fully take into account the influence of users' learning styles, interest preferences, and other factors on the course topics, which may lead some learners to find that the course format is not suitable for them after the formal start of the course, and they have to adapt temporarily, thereby increasing ineffective costs.

[0097] In summary, current social training programs have significant shortcomings in the course recommendation process. These problems work together to make the social training programs provided to individuals with autism and Asperger's syndrome less precise and flexible, and unable to adequately adapt to the different needs of individuals.

[0098] The present disclosure will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and not intended to limit it. Furthermore, it should be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings.

[0099] It should be noted that, unless otherwise specified, the embodiments and features described in this disclosure can be combined with each other. This disclosure will now be described in detail with reference to the accompanying drawings and embodiments.

[0100] Figure 1An exemplary system architecture 100 is shown, in which embodiments of training scheme generation methods, apparatuses, electronic devices, and storage media of the present disclosure can be applied.

[0101] like Figure 1 As shown, system architecture 100 may include terminal devices 101, 102, and 103, network 104, and server 105. Network 104 is used to provide communication links between terminal devices 101, 102, and 103 and server 105. Network 104 may include various communication connection types, such as wired communication links, wireless communication links, etc.

[0102] Users can use terminal devices 101, 102, and 103 to interact with server 105 via network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, and 103, such as social training solution generation applications, learning style testing applications, voice interaction applications, video conferencing applications, short video social applications, web browser applications, shopping applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0103] Terminal devices 101, 102, and 103 can be either hardware or software. When terminal devices 101, 102, and 103 are hardware, they can be various electronic devices with microphones and speakers, including but not limited to smartphones, tablets, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III), MP4 players (Moving Picture Experts Group Audio Layer IV), portable computers, and desktop computers, etc. When terminal devices 101, 102, and 103 are software, they can be installed in the aforementioned electronic devices. They can be implemented as multiple software programs or software modules (e.g., acquiring target user scale datasets) or as a single software program or software module. No specific limitations are imposed here.

[0104] Server 105 can be a server that provides various services, such as a backend server that processes the target user's scale dataset and learning style obtained from terminal devices 101, 102, and 103. The backend server can perform corresponding processing based on the target user's scale dataset and learning style obtained from the terminal devices.

[0105] In some cases, the training scheme generation method provided in this disclosure can be jointly executed by terminal devices 101, 102, and 103 and server 105. For example, the step of "obtaining the target user's scale dataset" can be executed by terminal devices 101, 102, and 103, and the step of "determining the priority of the course topic for the target user based on the scale dataset and the correlation between each scale in the scale dataset and the course topic" can be executed by server 105. This disclosure does not limit this. Accordingly, the training scheme generation device can also be respectively set in terminal devices 101, 102, and 103 and server 105.

[0106] In some cases, the training scheme generation method provided in this disclosure can be executed by server 105. Accordingly, the training scheme generation device can also be set in server 105. In this case, the system architecture 100 may not include terminal devices 101, 102, and 103.

[0107] In some cases, the training scheme generation method provided in this disclosure can be executed by terminal devices 101, 102, and 103. Correspondingly, the training scheme generation device can also be set in terminal devices 101, 102, and 103. In this case, the system architecture 100 may not include server 105.

[0108] It should be noted that server 105 can be either hardware or software. When server 105 is hardware, it can be implemented as a distributed server cluster consisting of multiple servers, or as a single server. When server 105 is software, it can be implemented as multiple software programs or software modules (e.g., used to provide distributed services), or as a single software program or software module. No specific limitations are made here.

[0109] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0110] All information, data, and signals disclosed herein are authorized by the user or by all parties, and the collection, use, and processing of such data comply with the relevant laws, regulations, and standards of the relevant countries and regions.

[0111] Continue to refer to Figure 2 , Figure 2 A flowchart 200 is shown as an embodiment of the training scheme generation method according to the present disclosure. Figure 2 The training scheme generation method shown can be applied to Figure 1 The terminal device or server shown. This process 200 includes at least the following steps 201-204.

[0112] Step 201: Obtain the target user's scale dataset.

[0113] In this embodiment, the scale may refer to a tool used to assess the social abilities of users with autism and Asperger's syndrome.

[0114] A scale typically consists of a series of standard questions. By analyzing the target user's answers to the questions in the scale, the target user's social skills can be analyzed.

[0115] Here, the target users can refer to users with autism and Asperger's syndrome.

[0116] In some alternative implementations, the scale may include, but is not limited to, mental health scales, anxiety level scales, social response scales, social skills and knowledge scales, and behavioral characteristic scales for the target users.

[0117] Among them, mental health scales can be used to assess the overall mental health status of target users, including but not limited to the degree of emotional disorders such as depression and anxiety.

[0118] Mental health scales can include childhood depression scales, such as the PSI-100 questionnaire, which can be used to assess depressive symptoms in target users.

[0119] Anxiety severity scales can be used to assess the severity and type of anxiety in target users. Anxiety types can include separation anxiety, anxiety, panic attacks, specific phobias, generalized anxiety, etc.

[0120] Anxiety scales can include children's anxiety scales, such as the Hamilton Anxiety Rating Scale, which can be used to assess the anxiety symptoms of target users.

[0121] Social responsiveness scales can be used to assess target users’ response patterns in social interactions, including their understanding of others’ behavior and their response methods.

[0122] Social responsiveness scales, such as the Social Response Scale, can be used to assess the degree of deficiency in target users' social interactions.

[0123] Social skills knowledge scales can be used to assess the social skills knowledge level of target users, including their ability to understand nonverbal cues, maintain conversations, and build friendships.

[0124] Social skills knowledge scales may include the Adolescent Social Skills Knowledge Test Scale (TASSK), which is used to assess the target users' understanding and application of social skills.

[0125] Behavioral trait scales can be used to assess the behavioral patterns of target users, including repetitive behaviors, narrow interests, and other behavioral characteristics that may affect daily life.

[0126] Behavioral characteristic scales, such as the Autism Behavior Scale and the Autism Quotient Test, can be used to assess behavioral problems in users with intellectual disabilities and are also applicable to users with autism spectrum disorders.

[0127] The scale dataset may include each item of at least one of the above scales and the target user's response to each item.

[0128] In this embodiment, one item of the scale can correspond to one question in the scale.

[0129] The target user's response to each question can refer to the specific answer given by the target user for that question. The answer can be the one selected by the target user from a set of preset options.

[0130] Preset multiple selections can refer to multiple preset scores (e.g., 1-5) or multiple preset behavior levels (e.g., never, rarely, sometimes, often, always).

[0131] Step 202: For each course topic in the preset course topic set, determine the priority of the course topic for the target user based on the scale dataset and the correlation between each scale in the scale dataset and the course topic.

[0132] In this embodiment, the preset course theme set may include multiple course themes, and a course theme may refer to the core content around which each specific learning module revolves.

[0133] In some alternative implementations, course topics may include exchanging information, two-way communication, choosing suitable friends, starting and joining conversations, leaving conversations, online communication and the use of social media, appropriate use of humor, teamwork, inviting friends, properly handling disagreements, changing public opinion, dealing with ridicule and embarrassment, properly handling rumors and gossip, and dealing with bullying.

[0134] Since different users may have different levels of social skills in various aspects, determining the priority of the course topic for the target users based on the scale dataset and the correlation between each scale in the scale dataset and the course topic can help identify and respond to these differences, determine the most suitable course topic for the target users, and maximize the effect of social training.

[0135] In some optional implementations, for each course topic in a preset course topic set, the following priority determination operations A1-A3 can be performed:

[0136] A1, determine the relevance of each scale in the scale dataset to the course topic.

[0137] In some optional implementations, the relevance of each scale to each course topic can be obtained based on a preset mapping relationship between the scale and the course topic.

[0138] A high correlation between a scale and the course topic indicates that the scale has a high impact on the course topic, while a low correlation indicates that the scale has a low impact on the course topic.

[0139] A2 generates a priority assessment result for the course topic based on the scale dataset and the relevance of each scale in the scale dataset to the course topic.

[0140] For each course topic in the preset course topic set, the system can traverse from the first course topic in the set. When traversing to that course topic, the system obtains the priority evaluation result of that course topic by using the preset priority evaluation method, the items of each scale in the scale dataset, the target user's answer to the item, and the correlation between each scale and the course topic.

[0141] In some optional implementations, the preset priority evaluation method may be the following priority evaluation formula:

[0142]

[0143] Among them, Score (Course) i ) represents the calculated priority assessment result for course topic i, where i is a natural number between 1 and M, M is the number of course topics in the course topic set, j is a natural number between 1 and N, N is the number of scales in the scale dataset, and w i,j This can represent the weight of scale j on course topic i, f i,j The label can represent the scale evaluation results of scale j for the target user. j This can represent the identifier of scale j, where f i,j It can be obtained through the following A21-A22.

[0144] The priority assessment results for course topics can be obtained using the priority assessment formula above.

[0145] In some alternative implementations, A2, generating a priority assessment result for the course topic based on the scale dataset and the relevance of each scale in the scale dataset to the course topic, can be achieved through the following A21-A23.

[0146] A21 generates scale assessment results for each scale in the scale dataset, based on the scale dataset.

[0147] In this embodiment, for each scale in the scale dataset, the answer result of each item in the scale can be converted into a quantifiable score. Then, the total scale score is obtained through the score of each item, and the total scale score is determined as the scale evaluation result.

[0148] For example, if the response to each item of a scale is a score, the total scale score can be obtained directly based on the score of each item, and this total scale score is used as the scale's assessment result. If the response to each item of a scale is a behavioral level, a corresponding score can be preset for each behavioral level (e.g., never = 1 point, rarely = 2 points, sometimes = 3 points, often = 4 points, always = 5 points), and the total scale score can be obtained through the score of each item, and this total scale score is used as the scale's assessment result.

[0149] In some alternative implementations, the total scale score can be calculated by simply adding up the scores of all items, or by assigning a weight to each item and obtaining the total scale score through weighted summation.

[0150] A22. For each scale, the scale assessment results are normalized according to the normalization direction of the scale to obtain the normalized scale assessment results.

[0151] After obtaining the total score of each scale, for each scale, the scale evaluation result (total score) can be normalized according to the normalization direction of the scale. In this embodiment, normalization can refer to converting the total score of the scale into a standardized score range, such as 0-1, to facilitate comparison and comprehensive analysis between different scales.

[0152] Suppose we have two scales: Scale A: used to assess language ability, with a score range of 1 to 5. Scale B: used to assess emotional health, with a score range of 1 to 100. It is unreasonable to directly compare the total scores of the two scales without normalizing them.

[0153] For example, a target user scores 4 on scale A and 60 on scale B. Although these two scores seem very different, after normalization, we may find that these two scores actually represent similar levels of ability.

[0154] The normalization direction of a scale refers to the method used when normalizing the scale assessment results.

[0155] The normalization direction of a scale includes forward normalization and reverse normalization.

[0156] In this context, forward normalization refers to the total scale score before normalization; the higher the score, the higher the score after normalization. Backward normalization refers to the total scale score before normalization; the higher the score, the lower the score after normalization.

[0157] In some alternative implementations, the normalization direction of each scale can be determined based on the normalization direction of the scale assessment results (the higher the total scale score, the more severe the depression, anxiety, social impairment, etc., or the higher the total scale score, the milder the depression, anxiety, social impairment, etc.).

[0158] Specifically, when the total score of the scale is higher and the symptoms of depression, anxiety, and social impairment are more severe, reverse normalization can be used.

[0159] For example, in a child depression scale, the higher the total score, the more severe the depression of the target user. The reverse normalization method can be used to normalize the total score.

[0160] When the total score of the scale is higher and the symptoms of depression, anxiety, and social impairment are milder, positive normalization can be used.

[0161] For example, in a social skills knowledge test scale for adolescents, a higher total score indicates a milder social barrier for the target user. A positive normalization method can be used to normalize the total score of the scale.

[0162] In some alternative implementations, the forward normalization method can be the following forward normalization formula:

[0163] s = (xx min ) / (x max -x min )

[0164] Where x can represent the total score of the scale, x max x can represent the total score of the maximum scores of all items in the scale. min It can represent the total score of the minimum scores of all items in the scale.

[0165] For example, a child depression scale may include 27 items, each item corresponding to a score of 0, 1, or 2. Then x max The sum of the 2 points for each of these 27 items is 54, x. min The sum of the 0 points in these 27 questions is 0.

[0166] In some alternative implementations, the inverse normalization method can be the following inverse normalization formula:

[0167] s=(x max -x) / (x max -x min )

[0168] Where x can represent the total score of the scale, x max x can represent the total score of the maximum scores of all items in the scale. min It can represent the total score of the minimum scores of all items in the scale.

[0169] For example, if the target user's total score on the Child Depression Scale is 41, the normalized total score after applying the above reverse normalization formula is 0.24.

[0170] In some optional implementations, the system can start by traversing the first scale in the scale set, determine the normalization direction of the scale, determine the normalization method of the scale based on the normalization direction, and then normalize the total scale score of the scale according to the corresponding normalization method, until the normalization of the total scale score of each scale is completed, and obtain the normalized scale evaluation result of each scale. The normalized scale evaluation result of each scale can refer to the total scale score after normalization.

[0171] In some alternative implementations, each scale in the scale dataset may include at least one item dimension, each item dimension being used to measure a user’s performance or state in different aspects.

[0172] For example, the Child Depression Scale does not have multiple item dimensions (that is, it only has one item dimension: depression), the Child Anxiety Scale can include five item dimensions: separation anxiety, anxiety, panic attacks, specific phobias, and generalized anxiety, the Social Response Scale can include five item dimensions: social perception, social cognition, social communication, social motivation, and autistic behavior, the Adolescent Social Skills Knowledge Test Scale does not have multiple item dimensions (that is, it only has one item dimension), and the Autism Behavior Scale can include five item dimensions: sensory abilities, social skills, motor skills, language skills, and self-care abilities.

[0173] Each item in each scale belongs to one of the item dimensions. That is, for a scale, each item dimension of the scale can contain some of the items from all the items in the scale.

[0174] For example, the Child Anxiety Scale contains 30 items. Among them, there may be 5 items corresponding to separation anxiety, 4 items corresponding to anxiety, 6 items corresponding to panic attacks, 7 items corresponding to specific phobias, and 8 items corresponding to generalized anxiety.

[0175] The scale dataset may also include at least one item dimension for each item in the scale.

[0176] In some alternative implementations, the normalized scale assessment results for each scale can also be obtained in the following manner.

[0177] First, for each item dimension in the scale, the dimension evaluation result of that item dimension in the scale is determined based on the target users' answers to each item belonging to that item dimension. Then, the dimension evaluation result of that item dimension is normalized according to the normalization direction of that item dimension in the scale to obtain the normalized dimension evaluation result of that item dimension in the scale. Finally, the normalized scale evaluation result of the scale is determined based on the normalized dimension evaluation results of each item dimension in the scale.

[0178] In this embodiment, the answer results of each item can be converted into quantifiable scores. Then, for each item dimension of each scale, the dimension score of that item dimension in the scale is obtained through the scores of each item in that item dimension. The dimension scores are determined as the dimension evaluation results of each item dimension of each scale.

[0179] For example, if the answer to each item is a score, the dimension score of that item dimension can be obtained directly based on the scores of each item in each item dimension, and the dimension score is determined as the dimension evaluation result of that item dimension; if the answer to each item is a behavioral level, each behavioral level can be converted into a corresponding score (e.g., never = 1 point, rarely = 2 points, sometimes = 3 points, often = 4 points, always = 5 points), and then the dimension score of that item dimension can be obtained through the scores of each item in each item dimension, and the dimension score is determined as the dimension evaluation result of that item dimension.

[0180] In some alternative implementations, the dimension score of a topic dimension can be calculated by simply adding up the scores of each topic in that topic dimension, or by assigning appropriate weights to each topic and obtaining the dimension score of the topic dimension through weighted summation.

[0181] After obtaining the dimension score of each item dimension of the scale, the dimension score of each item dimension of the scale can be normalized according to the normalization direction of each item dimension. In this embodiment, normalization can refer to converting the dimension score of the item dimension into a standardized score range, such as 0-1, to facilitate comparison and comprehensive analysis between item dimensions.

[0182] The normalization direction for item dimensions includes forward normalization and backward normalization. Forward normalization refers to the dimension score before normalization; the higher the score, the higher the score after normalization. Backward normalization refers to the dimension score before normalization; the higher the score, the lower the score after normalization.

[0183] In some alternative implementations, the normalization direction of each item dimension can be determined based on the normalization direction of the dimensional assessment results (the higher the dimensional score, the more severe the depression, anxiety, social impairment, etc., or the higher the dimensional score, the milder the depression, anxiety, social impairment, etc.).

[0184] In some alternative implementations, the normalization direction of the scale is generally the same as the normalization direction of each item dimension of the scale, or the normalization direction of the scale can be determined to be the normalization direction of each item dimension of the scale.

[0185] Specifically, when the dimensional scores are higher and the conditions such as depression, anxiety, and social impairment are more severe, reverse normalization can be used.

[0186] For example, in a child anxiety scale, the higher the scores of the item dimensions of separation anxiety, anxiety, and panic attacks, the more severe the separation anxiety, anxiety, and panic attacks of the target user. In this case, the item scores of the item dimensions can be normalized by using reverse normalization.

[0187] When the dimensional scores are higher and the symptoms of depression, anxiety, and social impairment are milder, positive normalization can be used.

[0188] For example, in a social skills knowledge test scale for adolescents, the higher the item score in the item dimension, the lighter the social barriers of the target user. A positive normalization method can be used to normalize the item scores.

[0189] In some alternative implementations, for scales that do not have multiple item dimensions (i.e., only one item dimension), such as the Adolescent Social Skills Knowledge Test Scale, the normalized total scale score can be directly determined as the item score of the normalized item dimension.

[0190] In some alternative implementations, the forward normalization method can be the following forward normalization formula:

[0191] s = (xx min ) / (x max -x min )

[0192] Where x represents the dimension score of the item dimension, x max x represents the total score of all items in this item dimension, where x is the maximum score. min This represents the total score of all items in this item dimension, with the minimum score being the minimum score.

[0193] For example, separation anxiety in a child anxiety scale may include five items, each with a score of 0, 1, or 2. Then x max The sum of the 2-point items in the 5 questions is 10, x.min The sum of the 0 points in these 27 questions is 0.

[0194] In some alternative implementations, the inverse normalization method can be the following inverse normalization formula:

[0195] s=(x max -x) / (x max -x min )

[0196] Where x represents the dimension score of the item dimension, x max x can represent the total score of the maximum score of all items in the item dimension. min It can represent the total score of the minimum scores of all items in the item dimension.

[0197] For example, the separation anxiety dimension score on the Children's Anxiety Scale is 6 points. After normalization using the above reverse normalization formula, the normalized dimension score is 0.4 points.

[0198] In some optional implementations, the dimensional assessment results of the item dimension can be normalized according to the normalization direction of that item dimension in the scale, resulting in the normalized dimensional assessment result of that item dimension in the scale. Furthermore, based on the normalized dimensional assessment results of each item dimension in the scale, the normalized scale assessment result can be determined. This can be done by traversing the scale starting from the first item dimension to determine the normalization direction of each item dimension, or by determining the normalization direction of each scale as the normalization direction of each item dimension corresponding to that scale. The normalization direction is determined first, and then the normalization method for each item dimension is determined based on the normalization direction of each item dimension. Then, the item scores are normalized according to the corresponding normalization method until the item scores for each item dimension are normalized. This process is repeated until the normalization of item scores for each item dimension is completed, thus obtaining the normalized dimension assessment results for each item dimension of the scale. The normalized dimension assessment results for each item dimension can refer to the dimension scores after normalization. Finally, the dimension scores for each item dimension of the scale are summed to obtain the normalized scale assessment results for the scale.

[0199] A23. Based on the scale evaluation results of each normalized scale and the importance of each scale in the scale dataset to the course topic, generate the priority evaluation results of the course topic.

[0200] In some alternative implementations, priority assessment results for each course topic can be obtained using a priority assessment formula based on the normalized scale assessment results (e.g., total scale score) and the relevance of each scale to the course topic.

[0201] The priority evaluation result of each course topic in the preset course topic set can be denoted as P, and the priority evaluation result set composed of the priority evaluation results of each course topic in the preset course topic set can be denoted as P_s.

[0202] For example, the priority assessment result can be a priority score. The higher the priority score, the higher the priority of the course topic.

[0203] A3. Based on the priority assessment results of this course topic, determine the priority of this course topic for the target users.

[0204] In this embodiment, the priority evaluation result of the course topic is as follows: for example, the higher the priority score, the higher the priority of the course topic for the target user; the lower the priority score, the lower the priority of the course topic for the target user.

[0205] Step 203: Based on the priority of each course topic for the target user, determine at least one target course topic that matches the target user.

[0206] In some alternative implementations, after obtaining the priority of each course topic for the target user, the course topics can be sorted in descending order of priority according to their priority for the target user to determine at least one target course topic that matches the target user.

[0207] For example, course topics can be sorted in descending order of priority score, and at least one course topic with the highest priority score can be identified as at least one target course topic that matches the target user.

[0208] For example, the top 3 course topics with the highest priority scores can be identified as the 3 target course topics that match the target users.

[0209] Each target course topic can be denoted as C, and the target course topic set consisting of three target course topics that match the target user can be denoted as C_s.

[0210] Step 204: For each target course topic, perform the following steps 2041-2043 to generate the training plan:

[0211] Step 2041: Based on the preset mapping relationship between course topics and difficulty factors, obtain at least one target difficulty factor associated with the target course topic.

[0212] In this embodiment, the preset course topic and difficulty factor mapping relationship can be a preset course topic and difficulty factor mapping relationship table, which can include at least one target difficulty factor associated with each course topic.

[0213] Among them, at least one target difficulty factor can refer to a subset of difficulty factors in the set of difficulty factors.

[0214] In some alternative implementations, the difficulty factor can refer to a specific factor used to measure the difficulty level of a course topic, and the target difficulty factor associated with the course topic refers to a specific factor that directly affects the learning difficulty of the course content of that course topic.

[0215] In some alternative implementations, the difficulty factor set may include multiple difficulty factors such as topic depth, emotional / conflict intensity, language complexity, AI guidance and error correction intensity, time / response pressure, dialogue dominance, and media presentation method, without specific limitations.

[0216] For each course topic in the pre-set course topic set, the target difficulty factor associated with each course topic can be the same or different.

[0217] For example, target difficulty factors associated with exchanging information on course topics may include language complexity and media presentation methods, while target difficulty factors associated with two-way communication on course topics may include dialogue leadership and AI guidance, error correction intensity, and media presentation methods.

[0218] Each target difficulty factor associated with the target course theme can be denoted as D, and the set of difficulty factors composed of each target difficulty factor associated with the target training course theme can be denoted as D_c.

[0219] Step 2042: Based on at least one scale that has a first correlation with each target difficulty factor and the scale dataset, determine the combination of target difficulty levels that matches the target user.

[0220] The target difficulty level combination is composed of the target difficulty level of each target difficulty factor in at least one target difficulty factor.

[0221] In some alternative implementations, each difficulty factor may have at least one difficulty level, where the target difficulty level refers to one of the at least one difficulty level.

[0222] In this embodiment, for each of the at least one target difficulty factor associated with the target course theme, the scale that is related to each target difficulty factor can be a scale that interacts or is related to that target difficulty factor.

[0223] At least one scale that has a primary correlation with each target difficulty factor can refer to at least one scale that has a strong interaction or strong correlation with that target difficulty factor.

[0224] In some optional implementations, scales associated with difficulty factors can be determined based on a preset mapping relationship between difficulty factors and scales. The preset mapping relationship between difficulty factors and scales can refer to a preset mapping relationship table, which may include the scales associated with each difficulty factor in the difficulty factor set, as well as the influence weight of each scale on that difficulty factor.

[0225] For example, the target difficulty factor corresponding to the exchange of information on the target course theme can be language complexity and media presentation. Scales related to language complexity can include the Child Depression Scale, the Child Anxiety Scale, and the Social Response Scale. Among them, the influence weights of the Child Depression Scale, the Child Anxiety Scale, and the Social Response Scale on language complexity are 0.3, 0.4, and 0.3, respectively. Scales related to media presentation can include the Autism Behavior Scale. Among them, the influence weight of the Autism Behavior Scale on media presentation is 1.

[0226] In some alternative implementations, for each target course topic, from all scales that are associated with all target difficulty factors related to the target course topic, the scale with the highest weight on all target difficulty factors related to the target course topic and the same number of all target difficulty factors associated with the target course topic can be selected as at least one scale that has a first association with each target difficulty factor.

[0227] For example, the target difficulty factor associated with exchanging information on the target course theme can be two difficulty factors: language complexity and media presentation. Then, from all the scales that are associated with language complexity and media presentation (Children's Depression Scale, Children's Anxiety Scale, Social Response Scale, and Autism Behavior Scale), two scales with the highest weights on language complexity and media presentation can be selected as at least one scale with the first association with language complexity and media presentation.

[0228] Specifically, (1) one can select the scale with the highest weight influencing language complexity from the scales that are related to language complexity, and select the scale with the highest weight influencing media presentation from the scales that are related to media presentation, as at least one scale that has the first correlation with language complexity and media presentation.

[0229] (2) All scales that are related to language complexity and media presentation can be sorted from high to low according to their influence weight. For example, the sorting results can be: Autism Behavior Scale, Child Anxiety Scale, Child Depression Scale and Social Response Scale. Then, the two scales with the highest influence weight (Autism Behavior Scale and Child Anxiety Scale) can be selected as at least one scale that has the first correlation with language complexity and media presentation.

[0230] In some alternative implementations, step 2042 can be implemented by the following B1-B2.

[0231] B1 generates a set of first difficulty level combinations corresponding to the target course theme, based on the difficulty levels of each target difficulty factor.

[0232] In some alternative implementations, each difficulty factor may have at least one difficulty level, which is determined based on the degree of influence of each difficulty factor on the difficulty of the course content.

[0233] For example, language complexity can be divided into five difficulty levels from low to high: Level 1, Level 2, Level 3, Level 4, and Level 5. Media presentation methods can be divided into three difficulty levels from low to high: Level 1, Level 2, Level 3, Level 4, and Level 5.

[0234] Different difficulty levels of the difficulty factor can correspond to different difficulty level scores.

[0235] By using different difficulty levels of the difficulty factor, we can measure the degree of difficulty that the difficulty factor reflects in the course topic, making it convenient to configure courses of appropriate difficulty according to the user's situation.

[0236] The first difficulty level combination set includes at least one combination of different difficulty levels of the target difficulty factor.

[0237] In this embodiment, for each target difficulty factor corresponding to the target course theme, different difficulty levels of each target difficulty factor can be combined to generate a first difficulty level combination set corresponding to the target training course theme.

[0238] For example, the target difficulty factor corresponding to the course theme exchange information can be language complexity and media presentation mode. The language complexity difficulty factor can be divided into difficulty level 1, difficulty level 2, difficulty level 3, difficulty level 4 and difficulty level 5, a total of 5 difficulty levels. Similarly, the media presentation mode difficulty factor can also be divided into difficulty level 1, difficulty level 2, difficulty level 3, difficulty level 4 and difficulty level 5, a total of 5 difficulty levels. Then, the different difficulty levels of the language complexity difficulty factor and the media presentation mode difficulty factor can be combined to generate the first difficulty level combination set corresponding to the course theme exchange information. This first difficulty level combination set can include a total of 25 different difficulty level combinations.

[0239] The set of combinations of the first difficulty level can be denoted as T_s.

[0240] B2, based on the first set of difficulty level combinations, at least one scale with a first correlation to each target difficulty factor, and the scale dataset, determine the target difficulty level combination that matches the target user.

[0241] It is important to understand that the first set of difficulty level combinations includes multiple difficulty level combinations, and each difficulty level combination can correspond to a training plan for the target course topic. This step can determine the target difficulty level combination that matches the target user based on the first set of difficulty level combinations, at least one scale that has a first correlation with each target difficulty factor, and the scale dataset. That is, the target difficulty level combination that best matches the target user is selected from the first set of difficulty level combinations, and then the training plan that is most suitable for the target user can be generated based on the target difficulty level combination.

[0242] In some alternative implementations, B2 can be implemented by the following C1-C4.

[0243] C1, based on the preset difficulty assessment method, determines the difficulty level assessment result of each difficulty level combination in the first difficulty level combination set.

[0244] In this embodiment, each combination of difficulty levels can correspond to a difficulty level assessment result.

[0245] For example, the difficulty level assessment result for each combination of difficulty levels can be the difficulty score corresponding to each combination of difficulty levels.

[0246] The difficulty assessment result of the combination of difficulty levels can be denoted as S, and the set of difficulty assessment results composed of the combinations of difficulty levels can be denoted as S_d.

[0247] C2. Based on the priority assessment results of the course topic and the difficulty level assessment results of each difficulty level combination in the first difficulty level combination set, determine the training difficulty range for the target user.

[0248] In this embodiment, the training difficulty range for the target user is determined based on the priority evaluation results of the course topic and the difficulty level evaluation results of each difficulty level combination in the first difficulty level combination set. This ensures that the target user will not feel bored because the course content is too simple, nor will they feel frustrated because the course content is too difficult, and can most effectively adapt to the target user's current ability.

[0249] In some alternative implementations, the training difficulty range can be {max(min(S_d), P-0.2,), min(max(S_d), P+0.2,)}.

[0250] For example, if the priority score of the target course topic is 0.8, and the difficulty level evaluation result set S_d composed of various difficulty level combinations has a difficulty level score range of 0.3-0.9, then the training difficulty interval for the target user can be {max(min(0.3-0.85), 0.8-0.2), min(max(0.3-0.85), 0.6+0.2)}, that is, {0.6, 0.8}.

[0251] C3 generates a second set of difficulty level combinations based on the difficulty assessment results of the first set of difficulty level combinations that belong to the training difficulty range.

[0252] The second difficulty level combination set includes difficulty level combinations whose difficulty level assessment results fall within the training difficulty range.

[0253] For example, the second difficulty level combination set can include difficulty level combinations with difficulty scores between 0.6 and 0.8.

[0254] In this way, at least one difficulty level combination that is a good match for the target user can be selected from the various difficulty level combinations.

[0255] C4. Based on the second set of difficulty level combinations, at least one scale with a first correlation to each target difficulty factor, and the scale dataset, determine the target difficulty level combination that matches the target user.

[0256] In C3, at least one difficulty level combination that is relatively suitable for the target user is selected from various difficulty level combinations. Based on this, C4 can further select the target difficulty level combination that is even more suitable for the target user.

[0257] In some alternative implementations, C4 can be implemented by the following D1-D2.

[0258] D1. Based on the scale assessment results of at least one scale that has a first correlation with each target difficulty factor and the difficulty level of each target difficulty factor in each difficulty level combination in the second difficulty level combination set, generate the third difficulty level combination set.

[0259] The third difficulty level combination set includes difficulty level combinations that match the scale assessment results of at least one scale that has a first correlation with each target difficulty factor.

[0260] In some optional implementations, for each difficulty level combination in the second difficulty level combination set, the difficulty level score of each difficulty factor in each difficulty level combination in the second difficulty level combination set can be denoted as a difficulty level score vector v. The dimension of v is the number of difficulty factors associated with the target course theme, and the set of difficulty score vectors composed of all difficulty level score vectors v can be V.

[0261] The total score of at least one scale that has a first correlation with each difficulty factor can be denoted as the scale score vector a, where the dimension of a is the number of scales that have a first correlation with each difficulty factor. The process can start by traversing the first difficulty level score vector v in the difficulty score vector set V, calculating the similarity between each difficulty level score vector v and the scale score vector a, sorting the similarity between each difficulty level score vector v and the scale score vector a, and selecting the difficulty level combination corresponding to at least one difficulty level score vector v with the highest similarity to form the third difficulty level combination set.

[0262] Methods for calculating the similarity between the difficulty level score vector v and the scale dimension score vector a may include, for example, cosine similarity, Euclidean distance, and Manhattan distance.

[0263] In this embodiment, the combination of difficulty levels corresponding to at least one difficulty level score vector v obtained by the above method is the combination of difficulty levels that matches the scale assessment results of at least one scale that has a first correlation with each difficulty factor.

[0264] D2, based on the third difficulty level combination set, determines the target difficulty level combination that matches the target user.

[0265] In some alternative implementations, the difficulty level combination with the lowest difficulty (lowest difficulty score) among the difficulty level evaluation results of all difficulty level combinations in the third difficulty level combination set can be determined as the target difficulty level combination that matches the target user.

[0266] Through the first set of difficulty level combinations, all difficulty level combinations corresponding to the target course theme were obtained. Through the second set of difficulty level combinations, a preliminary set of difficulty level combinations that are relatively well-matched to the target users were obtained, that is, difficulty level combinations that are relatively suitable for the current abilities of the target users. Through the second set of difficulty level combinations, further selection of difficulty level combinations that are even more well-matched to the current abilities of the target users was made. Finally, the lowest difficulty level combination in the third set of difficulty level combinations was determined as the target difficulty level combination that matches the target users. This allows the target users to train from the lowest difficulty training program among the difficulty level combinations that match them, making it easier for them to accept the course content and avoiding the frustration caused by the training program being too difficult at the beginning, thus maintaining the target users' enthusiasm for training.

[0267] Step 2043: Generate an initial training plan for the target course topic for the target user based on the difficulty level corresponding to each target difficulty factor in the target difficulty level combination.

[0268] In this embodiment, the course content of the target course topic can be configured according to the target difficulty level combination of each target difficulty factor in the target difficulty level combination, and the configured course content of the target course topic is determined as the initial training scheme for the target course topic for the target user. Here, the initial social training scheme includes the course content corresponding to the target course topic configured according to the target difficulty level combination of each target difficulty factor in the target difficulty level combination.

[0269] In some alternative implementations, steps 205-207 may be included after step 204.

[0270] Step 205: Obtain the learning style of the target user.

[0271] Here, learning style refers to the way course content is presented to users in relation to the initial training program.

[0272] It is important to understand that different users have different learning styles. Choosing a learning style that suits a user can improve their learning outcomes and achieve precise adaptation of the course.

[0273] Step 206: Determine whether the target user's learning style falls within the preset learning style range.

[0274] In some alternative implementations, the preset learning style may include visual learning, auditory learning, kinesthetic learning, and multisensory learning.

[0275] Among them, visual learners are more suited to learning through visual materials such as images, charts, and videos; auditory learners are more suited to learning through listening and speaking; kinesthetic learners learn through hands-on activities and physical activities; and multi-sensory learners can combine the above methods to learn.

[0276] First, the learning style of the target user can be matched with each preset learning style to determine whether the target user's learning style is within the preset learning style range. If the target user's learning style is within the preset learning style range, that is, if the target user's learning style belongs to visual learning, auditory learning, kinesthetic learning or multi-sensory learning, then proceed to step 207.

[0277] Step 207: In response to the determination, adjust the initial training scheme according to the learning style of the target user to obtain the first adjusted training scheme.

[0278] The first adjusted training plan is a training plan that adjusts the initial training plan based on the learning style of the target users.

[0279] Specifically, the initial training plan can be adjusted based on the learning styles of the target users, adjusting the proportions of video, audio, text, and practical exercises in the course content to obtain the first adjusted training plan.

[0280] In other words, the initial training program is adjusted according to the learning style of the target users, that is, the difficulty level of the media presentation is adjusted.

[0281] The medium of presentation can refer to the way course content is presented in the training program.

[0282] When video and audio constitute a high proportion of the course content, it indicates that the course content is simple and the corresponding media presentation method has a low level of difficulty. When video and audio constitute a low proportion of the course content, and text content and practical operation content constitute a high proportion of the course content, it indicates that the course content is difficult and the corresponding media presentation method has a high level of difficulty.

[0283] In some alternative implementations, if the target user's learning style is kinesthetic learning, it means that the target user is more suitable for learning through hands-on operation and physical activity. In this case, an additional m1 (e.g., 10%) of the course content corresponding to the initial training program can be extracted and presented in a form such as role-playing. That is, the difficulty level of the media presentation method can be increased by at least one level.

[0284] In some alternative implementations, if the target user's learning style is auditory learning, it means that the target user is more suitable to learn through listening, speech, etc. In this case, m2 (e.g., 10%) of the course content corresponding to the initial training plan can be extracted and presented in the form of speech, that is, the difficulty level of the media presentation method can be reduced by at least one level.

[0285] In some optional implementations, if the target user's learning style is visual learning, it means that the target user is more suitable for learning through visual materials such as images, charts, and videos. In this case, it can be determined whether the ratio of video to text in the course content corresponding to the initial training scheme meets the preset first condition, such as whether the ratio of video to text is greater than 0.6:0.4. If so, an additional m3 (e.g., 20%) of the course content corresponding to the initial training scheme is extracted and presented in the form of video, that is, the difficulty level of the media presentation method can be reduced by at least one level. If not, the course content corresponding to the initial training scheme is not adjusted, that is, the difficulty level of the media presentation method can remain unchanged.

[0286] In some optional implementations, if the target user's learning style is multi-sensory learning, it indicates that the target user is suitable for learning by combining multiple methods such as video, audio, and hands-on operation. In this case, based on the course content corresponding to the initial training plan, m4 (e.g., 3%) can be extracted and presented in the form of audio, m5 (e.g., 3%) can be extracted and presented in the form of video, and m6 (e.g., 3%) can be extracted and presented in the form of role-playing. That is, the difficulty level of at least one level of media presentation method can be reduced or increased, or the difficulty level of the media presentation method can remain unchanged.

[0287] In some alternative implementations, steps 208-209 may be included after step 206.

[0288] Step 208: In response to whether or not the target user is identified, obtain the target user's interests and preferences.

[0289] Here, even when the target user's learning style is outside the preset learning style range, the target user's interests and preferences can still be obtained.

[0290] The target user's interests and preferences can be, for example, a preference for sports or a preference for technology.

[0291] Step 209: Adjust the initial training scheme according to the interests and preferences of the target users to obtain the second adjusted training scheme.

[0292] The second adjusted training scheme is a training scheme that adjusts the initial training scheme based on the interests and preferences of the target users.

[0293] Specifically, the presentation scenario of the training scheme can be adjusted according to the interests and preferences of the target users to obtain a second adjusted training scheme.

[0294] For example, if the target users prefer sports, then a sports-themed scenario can be chosen; if the target users prefer technology, then a technology-themed scenario can be chosen.

[0295] In this way, by directly linking interest tags with the presentation scenario of the training program, the participation and immersion of the target users can be improved, thereby enhancing their training experience.

[0296] In some alternative implementations, steps 210-212 may be included after steps 204, 207, or 209.

[0297] Step 210: For each target difficulty factor associated with the target course topic, perform the following difficulty level adjustment operations for E1-E2.

[0298] E1, identify at least one scale that has a second association with the target difficulty factor.

[0299] Here, at least one scale that has a second correlation with the difficulty factor can be determined based on the preset mapping relationship between the difficulty factor and the scale.

[0300] At least one scale that has a second association with the target difficulty factor can refer to a scale that interacts with or is related to the target difficulty factor (i.e., a scale that is associated with each difficulty factor).

[0301] For example, the target difficulty factor corresponding to the exchange of information on the target course theme could be language complexity and media presentation style. Scales with a second correlation with language complexity could include the Childhood Depression Scale, the Childhood Anxiety Scale, and the Social Response Scale. Scales with a second correlation with media presentation style could include the Autism Behavior Scale.

[0302] E2, adjust the difficulty level of the target difficulty factor based on the difficulty level of the target difficulty factor in the target difficulty level combination and the scale assessment results of at least one scale that has a second correlation with the target difficulty factor.

[0303] Here, for each target difficulty factor associated with the target course theme, the process can be traversed starting from the first target difficulty factor. When traversing to the target difficulty factor, the difference between the difficulty score corresponding to the difficulty level of the target difficulty factor in the target difficulty level combination and the total score of each scale with the second correlation relationship of the target difficulty factor can be calculated to obtain the difference set E. It is then determined whether the number of positive numbers in the difference set E meets the preset quantity condition.

[0304] For example, the preset quantity conditions may include whether the number of positive numbers in the difference set is greater than, equal to or less than half of the total number of all differences in the difference set.

[0305] If the number of positive numbers in the difference set is greater than half the total number of all differences in the difference set, it means that the current difficulty level of the target difficulty factor is too high for the target user, and the current difficulty level of the target difficulty factor can be reduced by at least one level.

[0306] If the number of positive numbers in the difference set is equal to half the total number of all differences in the difference set, it means that the current difficulty level of the target difficulty factor is suitable for the target user, and the current difficulty level of the target difficulty factor can be kept unchanged.

[0307] If the number of positive numbers in the difference set is less than half the total number of all differences in the difference set, it means that the current difficulty level of the target difficulty factor is too low for the target user, and the current difficulty level of the target difficulty factor can be increased by at least one level.

[0308] Thus, by calculating the difference between the difficulty score corresponding to the difficulty level of the target difficulty factor in the target difficulty level combination and the total score of each scale with a second correlation relationship to the target difficulty factor, the distribution of the difference can be used to determine whether the difficulty of the course content of the target course topic for the target user is unbalanced. Compared with the existing technology that relies on a single scale, this embodiment is based on a comprehensive comparison of the total scores of multiple scales, which can provide the accuracy of the appropriate difficulty of the course content for the target user.

[0309] Step 211: Determine the difficulty level of each target difficulty factor associated with the target course theme after the difficulty level adjustment as the target difficulty level combination that matches the target user.

[0310] After obtaining the adjusted difficulty level for each target difficulty factor associated with the target course topic, the adjusted difficulty level for each target difficulty factor associated with the target course topic can be determined as the target difficulty level combination that matches the target user.

[0311] Step 212: Adjust the initial training scheme, the first adjusted training scheme, or the second adjusted training scheme according to the target difficulty level combination of at least one target difficulty factor to obtain the third adjusted training scheme.

[0312] Here, the initial training scheme, the first adjusted training scheme, or the second adjusted training scheme can be adjusted based on the target difficulty level combination of at least one target difficulty factor after difficulty level adjustment, so as to obtain an adjusted training scheme that is more suitable for the target user. The training scheme generation method provided in the embodiments of this disclosure includes: obtaining a scale dataset of a target user, wherein the scale dataset includes each item of at least one scale and the target user's answer to the item; for each course topic in a preset course topic set, determining the priority of the course topic for the target user based on the scale dataset and the correlation between each scale in the scale dataset and the course topic; determining at least one target course topic matching the target user based on the priority of each course topic for the target user; and performing the following training scheme generation operation for each target course topic: obtaining at least one difficulty factor associated with the target course topic based on a preset mapping relationship between course topics and difficulty factors; determining a target difficulty level combination matching the target user based on at least one scale with a first correlation relationship with each target difficulty factor and the scale dataset, wherein the target difficulty level combination is composed of the target difficulty level combination of each target difficulty factor in the at least one target difficulty factor; and generating an initial training scheme for the target user for the target course topic based on the target difficulty level corresponding to each target difficulty factor in the target difficulty level combination. This disclosure can determine the priority of course topics based on multiple scales, and then select target course topics that match the user according to the priority of course topics. It can also determine the combination of target difficulty levels that match the target user based on at least one target difficulty factor associated with the target course topic, so as to determine the most suitable difficulty of course content for the target user under the target course topic. This can more accurately match the specific needs of individuals. It can also match the corresponding course format based on the learning style and learning interests of the target user, which can enhance the training effect and user experience of the training program and reduce the learning cost.

[0313] In addition, this disclosure also reserves channels for integrating new scales, difficulty factors and learning styles, so that when new scales, difficulty factors and learning styles appear in the future, they can be more smoothly integrated into the corresponding processes without rewriting the rules.

[0314] Further reference Figure 4 As an implementation of the methods shown in the above figures, this disclosure provides an embodiment of a training scheme generation device, which is similar to... Figure 2 Corresponding to the method embodiments shown, this device can be specifically applied to various terminal devices.

[0315] like Figure 4As shown, the training scheme generation device 400 of this embodiment includes: a first acquisition unit 401, a first determination unit 402, a second determination unit 403, and a generation unit 404.

[0316] The system comprises the following components: a first acquisition unit 401, used to acquire a scale dataset of the target user, wherein the scale dataset includes each item of at least one scale and the target user's answer to the item; a first determination unit 402, used to determine the priority of each course topic in a preset course topic set for the target user based on the scale dataset and the correlation between each scale in the scale dataset and the course topic; a second determination unit 403, used to determine at least one target course topic matching the target user based on the priority of each course topic for the target user; and a generation unit 404, used to perform the following training scheme generation operations for each target course topic: acquiring at least one target difficulty factor associated with the target course topic based on a preset mapping relationship between course topics and difficulty factors; determining a target difficulty level combination matching the target user based on at least one scale with a first correlation relationship with each target difficulty factor and the scale dataset, wherein the target difficulty level combination is composed of the target difficulty levels of each of the at least one target difficulty factors; and generating an initial training scheme for the target course topic for the target user based on the target difficulty levels corresponding to each target difficulty factor in the target difficulty level combination. In this embodiment, the specific processing of the first acquisition unit 401, the first determination unit 402, the second determination unit 403, and the generation unit 404, and the resulting technical effects, can be referred to respectively. Figure 2 The relevant descriptions of steps 201 to 205 in the corresponding embodiments will not be repeated here.

[0317] In some alternative implementations, the first determining unit 402 may be further used to:

[0318] For each course topic in the pre-defined course topic set, perform the following priority determination operation:

[0319] Determine the relevance of each scale in the scale dataset to the course topic; based on the scale dataset and the relevance of each scale in the scale dataset to the course topic, generate a priority assessment result for the course topic; based on the priority assessment result for the course topic, determine the priority of the course topic for the target users.

[0320] In some alternative implementations, the first determining unit 402 may be further used to:

[0321] Generate scale assessment results for each scale in the scale dataset based on the scale dataset;

[0322] For each scale, the scale assessment results are normalized according to the normalization direction of the scale to obtain the normalized scale assessment results.

[0323] Based on the normalized scale evaluation results and the correlation between each scale in the scale dataset and the course topic, a priority evaluation result for the course topic is generated.

[0324] In some optional implementations, each scale in the scale dataset includes at least one item dimension, and each item in each scale belongs to one of the item dimensions. The scale dataset also includes at least one item dimension for each item in each scale. The first determining unit 402 may be further configured to:

[0325] For each item dimension in the scale, the dimension evaluation result of that item dimension in the scale is determined based on the target user's answers to each item belonging to that item dimension and the item dimension of that item.

[0326] The dimensional assessment results of the item dimension in the scale are normalized according to the normalization direction of the item dimension to obtain the normalized dimensional assessment results of the item dimension in the scale. Based on the normalized dimensional assessment results of each item dimension in the scale, the normalized scale assessment results of the scale are determined.

[0327] In some optional implementations, each target difficulty factor has at least one difficulty level, and the second determining unit 403 may be further used to:

[0328] Based on the difficulty levels of each target difficulty factor, a first difficulty level combination set corresponding to the target course theme is generated, wherein the first difficulty level combination set includes a combination of difficulty levels of at least one target difficulty factor with different difficulty levels.

[0329] Based on the first set of difficulty level combinations, at least one scale with a first correlation to each target difficulty factor, and the scale dataset, determine the target difficulty level combination that matches the target user.

[0330] In some alternative implementations, the second determining unit 403 may be further used to:

[0331] Based on the preset difficulty assessment method, determine the difficulty level assessment result of each difficulty level combination in the first difficulty level combination set;

[0332] Based on the priority assessment results of the course topic and the difficulty level assessment results of each difficulty level combination in the first difficulty level combination set, the training difficulty range for the target users is determined.

[0333] A second set of difficulty level combinations is generated based on the difficulty level evaluation results corresponding to the first set of difficulty level combinations that belong to the training difficulty range.

[0334] Based on the second set of difficulty level combinations, at least one scale with a first correlation to each target difficulty factor, and the scale dataset, determine the target difficulty level combination that matches the target user.

[0335] In some alternative implementations, the second determining unit 403 may be further used to:

[0336] Based on the scale assessment results of at least one scale that has a first correlation with each target difficulty factor and the difficulty level of each target difficulty factor in each difficulty level combination in the second difficulty level combination set, a third difficulty level combination set is generated, wherein the third difficulty level combination set includes difficulty level combinations that match the scale assessment results of at least one scale that has a first correlation with each target difficulty factor.

[0337] Based on the third difficulty level combination set, determine the target difficulty level combination that matches the target user.

[0338] In some alternative embodiments, the device 400 further includes:

[0339] Second acquisition unit 405 Figure 4 (not shown), used to obtain the learning style of the target user;

[0340] Third determination unit 406 ( Figure 4 (Not shown), used to determine whether the target user's learning style falls within the preset learning style range;

[0341] First adjustment unit 407 ( Figure 4 (Not shown), used in response to a determination, to adjust the initial training scheme according to the learning style of the target user to obtain a first adjusted training scheme;

[0342] Third acquisition unit 408 Figure 4 (not shown), used to obtain the target user's interest preferences in response to a no-determined condition;

[0343] Second adjustment unit 409 ( Figure 4 (Not shown), used to adjust the initial training scheme according to the interests and preferences of the target user to obtain a second adjusted training scheme.

[0344] In some alternative implementations, the preset learning styles include visual learning, auditory learning, kinesthetic learning, and multisensory learning.

[0345] In some alternative embodiments, the device 400 further includes:

[0346] Third adjustment unit 410 Figure 4 (Not shown), for each target difficulty factor associated with the target course topic, to perform the following difficulty level adjustment operation: determine at least one scale that has a second association with the target difficulty factor; adjust the difficulty level of the target difficulty factor based on the difficulty level of the target difficulty factor in the target difficulty level combination and the scale assessment results of at least one scale that has a second association with the target difficulty factor;

[0347] Fourth Determined Unit 411 ( Figure 4 (Not shown), used to determine the difficulty level of each target difficulty factor associated with the target course topic after difficulty level adjustment, as a target difficulty level combination that matches the target user;

[0348] Obtain Unit 412 ( Figure 4 (Not shown), used to adjust the initial training scheme, the first adjusted training scheme or the second adjusted training scheme according to the target difficulty level combination of at least one target difficulty factor, to obtain a third adjusted training scheme.

[0349] It should be noted that the implementation details and technical effects of each unit in the training scheme generation device provided in the embodiments of this disclosure can be referred to the descriptions of other embodiments in this disclosure, and will not be repeated here.

[0350] The following is for reference. Figure 5 It shows a schematic diagram of the structure of a computer system 500 suitable for implementing the terminal device of this disclosure. Figure 5 The computer system 500 shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of this disclosure.

[0351] like Figure 5 As shown, the computer system 500 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage device 508 into a random access memory (RAM) 503. The RAM 503 also stores various programs and data required for the operation of the computer system 500. The processing device 501, ROM 502, and RAM 503 are interconnected via a bus 504. An input / output (I / O) interface 405 is also connected to the bus 504.

[0352] Typically, the following devices can be connected to I / O interface 505: input devices 506 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, etc.; output devices 507 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 508 including, for example, magnetic tapes, hard disks, etc.; and communication devices 509. Communication device 509 allows computer system 500 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 5 A computer system 500 with various electronic devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively.

[0353] In particular, according to embodiments of this disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 509, or installed from a storage device 508, or installed from a ROM 502. When the computer program is executed by the processing device 501, it performs the functions defined in the methods of embodiments of this disclosure.

[0354] It should be noted that the computer-readable medium described above in this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium can be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wires, optical fibers, RF (radio frequency), etc., or any suitable combination thereof.

[0355] The aforementioned computer-readable medium may be included in the aforementioned electronic device; or it may exist independently and not assembled into the electronic device.

[0356] The aforementioned computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to perform the following functions: Figure 2 The illustrated embodiments and their alternative implementations demonstrate a method for generating training schemes.

[0357] Computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and Python, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0358] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0359] The units described in the embodiments of this disclosure can be implemented in software or in hardware. The names of the units are not necessarily limiting in certain circumstances; for example, the first acquisition unit can also be described as "a unit for acquiring the target user's scale dataset and learning style".

[0360] The above description is merely a preferred embodiment of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features disclosed in this disclosure that have similar functions.

Claims

1. A method for generating a training scheme, characterized in that, The method includes: Obtain a scale dataset of the target user, wherein the scale dataset includes each item of at least one scale and the target user's response to the item; For each course topic in the preset course topic set, the priority of the course topic for the target user is determined based on the scale dataset and the correlation between each scale in the scale dataset and the course topic. Based on the priority of each course topic for the target user, determine at least one target course topic that matches the target user; For each target course topic, the following training scheme generation operation is performed: Based on a preset mapping relationship between course topics and difficulty factors, at least one target difficulty factor associated with the target course topic is obtained; based on at least one scale having a first correlation with each of the target difficulty factors and the scale dataset, a target difficulty level combination matching the target user is determined, wherein the target difficulty level combination is composed of the target difficulty levels of each of the at least one target difficulty factor; based on the target difficulty levels corresponding to each target difficulty factor in the target difficulty level combination, an initial training scheme for the target course topic for the target user is generated.

2. The method according to claim 1, characterized in that, For each course topic in the preset course topic set, determining the priority of that course topic for the target user based on the scale dataset and the relevance of each scale in the scale dataset to that course topic includes: For each course topic in the pre-defined course topic set, perform the following priority determination operation: Determine the relevance of each scale in the scale dataset to the course topic; generate a priority assessment result for the course topic based on the scale dataset and the relevance of each scale in the scale dataset to the course topic; and determine the priority of the course topic for the target user based on the priority assessment result of the course topic.

3. The method according to claim 2, characterized in that, The step of generating a priority assessment result for the course topic based on the scale dataset and the relevance of each scale in the scale dataset to the course topic includes: Generate scale assessment results for each scale in the scale dataset based on the scale dataset; For each scale, the scale evaluation result is normalized according to the normalization direction of the scale to obtain the normalized scale evaluation result. Based on the normalized scale evaluation results of each scale and the correlation between each scale in the scale dataset and the course topic, a priority evaluation result for the course topic is generated.

4. The method according to claim 3, characterized in that, Each scale in the scale dataset includes at least one item dimension, and each item in each scale belongs to one of the item dimensions. The scale dataset also includes the item dimensions of each item in the at least one scale. as well as The step of normalizing the scale assessment results according to the normalization direction of the scale to obtain the normalized scale assessment results includes: For each item dimension in the scale, the dimension evaluation result of that item dimension in the scale is determined based on the target user's answers to each item belonging to that item dimension; The dimensional assessment results of the item dimension in the scale are normalized according to the normalization direction of the item dimension to obtain the normalized dimensional assessment results of the item dimension in the scale. Based on the normalized dimensional assessment results of each item dimension in the scale, the normalized scale assessment results of the scale are determined.

5. The method according to claim 2, characterized in that, Each of the aforementioned target difficulty factors has at least one difficulty level; as well as Based on at least one scale having a first correlation with each of the target difficulty factors and the scale dataset, determine the target difficulty level combination matching the target user, including: Based on the difficulty levels of each of the target difficulty factors, a first set of difficulty level combinations corresponding to the target course theme is generated, wherein the first set of difficulty level combinations includes a combination of difficulty levels of at least one of the target difficulty factors with different difficulty levels. Based on the first set of difficulty level combinations, at least one scale having a first correlation with each of the target difficulty factors, and the scale dataset, a target difficulty level combination matching the target user is determined.

6. The method according to claim 5, characterized in that, The step of determining the target difficulty level combination matching the target user based on the first difficulty level combination set, at least one scale having a first correlation with each of the target difficulty factors, and the scale dataset includes: Based on the preset difficulty assessment method, determine the difficulty level assessment result of each difficulty level combination in the first difficulty level combination set; Based on the priority evaluation results of the course topic and the difficulty level evaluation results of each difficulty level combination in the first difficulty level combination set, the training difficulty range for the target user is determined. A second set of difficulty level combinations is generated based on the difficulty level evaluation results corresponding to the first set of difficulty level combinations that belong to the training difficulty range. Based on the second set of difficulty level combinations, at least one scale having a first correlation with each of the target difficulty factors, and the scale dataset, a target difficulty level combination matching the target user is determined.

7. The method according to claim 6, characterized in that, The step of determining the target difficulty level combination matching the target user based on the second difficulty level combination set, at least one scale having a first correlation with each of the target difficulty factors, and the scale dataset includes: Based on the scale assessment results of at least one scale that has a first correlation with each of the target difficulty factors and the difficulty level of each target difficulty factor in each difficulty level combination in the second difficulty level combination set, a third difficulty level combination set is generated, wherein the third difficulty level combination set includes difficulty level combinations that match the scale assessment results of at least one scale that has a first correlation with each target difficulty factor. Based on the third set of difficulty level combinations, determine the target difficulty level combination that matches the target user.

8. The method according to claim 1, characterized in that, The method further includes: Obtain the learning styles of the target users; Determine whether the learning style of the target user falls within a preset learning style range; In response to the determination, the initial training scheme is adjusted according to the learning style of the target user to obtain a first adjusted training scheme; In response to a no-response, the target user's interests and preferences are obtained; Based on the interests and preferences of the target users, the initial training scheme is adjusted to obtain a second adjusted training scheme.

9. The method according to claim 8, characterized in that, The preset learning styles include visual learning, auditory learning, kinesthetic learning, and multi-sensory learning.

10. The method according to claim 1 or 8, characterized in that, The method further includes: For each target difficulty factor associated with the target course theme, the following difficulty level adjustment operation is performed: determine at least one scale that has a second association with the target difficulty factor; adjust the difficulty level of the target difficulty factor based on the difficulty level of the target difficulty factor in the target difficulty level combination and the scale assessment results of at least one scale that has a second association with the target difficulty factor; The difficulty level of each target difficulty factor associated with the target course theme after the difficulty level adjustment is determined as the target difficulty level combination that matches the target user; The initial training scheme, the first adjusted training scheme, or the second adjusted training scheme are adjusted according to the target difficulty level combination of at least one target difficulty factor to obtain a third adjusted training scheme.

11. A training scheme generation device, characterized in that, include: The first acquisition unit is used to acquire a scale dataset of the target user, wherein the scale dataset includes each item of at least one scale and the target user's answer to the item; The first determining unit is used to determine the priority of each course topic for the target user for each course topic in the preset course topic set, based on the scale dataset and the correlation between each scale in the scale dataset and the course topic. The second determining unit is used to determine at least one target course topic that matches the target user based on the priority of each course topic for the target user. The generation unit is configured to perform the following training scheme generation operation for each target course topic: obtain at least one target difficulty factor associated with the target course topic according to a preset mapping relationship between course topics and difficulty factors; determine a target difficulty level combination matching the target user based on at least one scale with a first correlation relationship with each of the target difficulty factors and the scale dataset, wherein the target difficulty level combination is composed of the target difficulty level combination of each of the at least one target difficulty factor; and generate an initial training scheme for the target course topic for the target user according to the target difficulty level corresponding to each target difficulty factor in the target difficulty level combination.

12. An electronic device, characterized in that, include: One or more processors; Storage device, on which one or more programs are stored, When one or more programs are executed by one or more processors, the one or more processors implement the method as claimed in any one of claims 1-10.

13. A computer-readable storage medium, characterized in that, It stores a computer program thereon, wherein the computer program, when executed by one or more processors, implements the method as claimed in any one of claims 1-10.

14. A computer program product, characterized in that, Includes a computer program / instruction that, when executed by a processor, implements the method as described in any one of claims 1-10.

Images