Animation dialogue difficulty adaptive method based on user cognitive level

Abstract

The present invention relates to an animation dialogue difficulty adaptation method based on user cognitive level, and specifically to the field of intelligent education. According to the user's score in an animation dialogue test, the user cognitive level score is mapped and the user cognitive level is judged, so as to improve the accuracy and effectiveness of the test, and the animation dialogue text is preprocessed, which is helpful to reduce noise and variants, improve the clarity and analyzability of the text, and comprehensively evaluate the animation dialogue difficulty level through different word frequencies, word lengths, root complexity, text lengths, and dependency relationships between main clauses and subordinate clauses, and the animation dialogue difficulty level based on the user cognitive level is obtained by weighted average, and the animation dialogue difficulty level based on the user cognitive level is divided into simple difficulty, medium difficulty and difficult difficulty, and the animation dialogue difficulty is adapted based on different difficulty levels, so that users can better understand animation content at different difficulty levels, and enhance the user's attraction and satisfaction with the animation content.

Description

Technical Field

[0001] The present invention relates to the field of intelligent education, and more specifically, to a method for adaptively adjusting the difficulty of animation lines based on user cognitive levels. Background Art

[0002] With the development and popularization of educational technology, more and more educational resources are presented to users in a digital and online way. Animation, as a vivid and vivid way of expression, is widely used in the field of education, providing a more intuitive and vivid learning experience for young users.

[0003] Due to differences in users’ cognitive levels and learning abilities, traditional animation education resources cannot meet the needs of all users, causing some users to feel that the animation education content is too simple or too complex to achieve the best learning results. Traditional animation education resources usually have fixed difficulty and content, and cannot be personalized according to the individual cognitive level needs of users, limiting the user’s learning experience and effect.

[0004] Traditional animation education resources lack an evaluation mechanism for users’ cognitive level and learning ability, and cannot accurately understand users’ learning status and needs. The lack of personalized cognitive level evaluation and adaptive change mechanism leads to confusion and frustration in users’ learning process, affecting their learning enthusiasm and effectiveness. Summary of the invention

[0005] The present invention aims at the technical problems existing in the prior art and provides an adaptive method for the difficulty of animation lines based on user cognitive level to solve the problems raised in the above background technology.

[0006] The technical solution of the present invention to solve the above technical problem is as follows: a method for adaptively adjusting the difficulty of animation lines based on user cognitive level, comprising the following steps:

[0007] S101. Collect user age information and establish an animation dialogue test question bank, map the user's cognitive level score according to the user's score in the animation dialogue test and determine the user's cognitive level;

[0008] S102. Preprocess the animation dialogue text and comprehensively evaluate the difficulty level of the animation dialogue through different word frequencies, word lengths, root complexity, text lengths, and dependency relationships between main clauses and subordinate clauses;

[0009] S103. Compare the predicted values ​​of the current animation dialogue difficulty level by integrating the influence of the interval characteristics of the user's cognitive level score on the groups divided by the user's cognitive level, and use weighted average to obtain the animation dialogue difficulty level based on the user's cognitive level;

[0010] S104. Dividing the difficulty level of the animation lines based on the user's cognitive level into simple difficulty, medium difficulty and difficult difficulty, and performing animation line difficulty adaptation based on different difficulty levels;

[0011] In a preferred embodiment, in S101, user age information is collected and an animation line test question bank is established. The animation line test question bank is divided into a first animation line test question bank and a second animation line test question bank. The first animation line test question bank corresponds to a user age group of 3-5 years old, and the second animation line test question bank corresponds to a user age group of 5-7 years old. Each question bank is adapted to animation lines corresponding to users of different age groups. The animation lines corresponding to users aged 3-5 years old are derived from animation lines in fairy tales, and the animation lines corresponding to users aged 5-7 years old are derived from animation lines in ancient books. The user's cognitive level score is mapped according to the user's score in the animation line test and the user's cognitive level is judged. The specific formula for the mapping is:

[0012]

[0013] Among them, y represents the user's cognitive level score, x represents the user's score in the animation dialogue test, S min Indicates the highest score in the cognitive level group, S max It represents the lowest score of the cognitive level group, floor() represents the rounding function, and divides the user's cognitive level into primary cognitive level, intermediate cognitive level and advanced cognitive level.

[0014] In a preferred embodiment, in S102, animation lines from different sources are collected, regular expressions are used to match all non-alphabetic, non-numeric and non-blank characters in the text of the animation lines, special characters and punctuation marks of the animation lines are removed by replacing empty strings, a stop word list is established and the animation lines are segmented into single words, each word is traversed to check whether it is a stop word using the stop word list and the stop words are removed, stemming is performed using a lemma restoration tool, and the animation lines are segmented into word sequences for word segmentation.

[0015] Furthermore, statistical methods are used to count the word frequency and word length of the animation lines, and the word frequency is divided into high-frequency words, medium-frequency words and low-frequency words, and the word length is divided into short words, medium-length words and long words. The root complexity is determined according to the word frequency of the animation lines, and the root complexity is divided into complex roots and simple roots.

[0016] Furthermore, the number of words in the animation dialogue text is counted and combined with the word length to distinguish the text length of the animation dialogue, wherein animation dialogue text with more than 30 words is defined as a long sentence, and animation dialogue text with less than 30 words is defined as a short sentence. The difficulty level of the animation dialogue text is determined according to the dependency relationship between the main sentence and the subordinate clause in the animation dialogue text. When a main sentence in the animation dialogue text is followed by multiple subordinate clauses, the animation dialogue text is a difficult sentence, otherwise it is a simple sentence.

[0017] Furthermore, the difficulty level of animation dialogues is comprehensively evaluated by combining different word frequencies, word lengths, root complexity, text length, and the dependency relationship between main and subordinate clauses in a random combination method.

[0018] In a preferred embodiment, in S103, the user cognition level is used as the first target variable set, a linear regression model is constructed and the first target variable set is input, and the coefficient of the linear regression model is estimated by minimizing the difference between the groups divided by the actual user cognition level and the interval of the user cognition level score using the least squares method. The specific formula of the linear regression model is:

[0019] T=β0+β1W1+β2W2+…+β n W n +ε

[0020] Where T represents the first target variable set, β0 represents the intercept, β1, β2, …, β n The group features representing the user cognitive level division, W1, W2, ..., W n represents the interval feature of the user's cognitive level score, ε represents the error value, and the different word frequencies, word lengths and root complexities of the animation lines are used as the second target variable set. A decision tree model is constructed and the second target variable set is input. Different word frequencies, word lengths and root complexity features are selected as the partitioning features of the current node and the partitioning points are determined. The second variable set is divided into multiple subsets according to the partitioning features and the partitioning points. The partitioning steps are recursively repeated to establish a subtree until the maximum depth of the decision tree is reached, and the current node is marked as a leaf node and the predicted value of the leaf node is obtained. The predicted value of the current animation line difficulty level is compared with the current animation line difficulty level division. If the predicted value of the current animation line difficulty level corresponds to the current animation line difficulty level division, the linear regression model is integrated with the decision tree model and the weighted average is used to obtain the animation line difficulty level based on the user's cognitive level.

[0021] In a preferred embodiment, in S104, the difficulty level of the animation lines based on the user's cognitive level is divided into simple difficulty, medium difficulty and difficult difficulty, wherein the simple difficulty is to process the original animation lines into sentences, replace synonyms and simplify the vocabulary, simplify the sentence structure by removing clauses and complex modifying components, sort out the text containing complex logical relationships by reorganizing the text structure and adding conjunctions, and delete the redundant components of the animation lines; the medium difficulty is to process the original animation lines into sentences, replace synonyms and simplify the vocabulary, and the difficult difficulty introduces language conversion, sorts out the text with simple logical relationships by reorganizing the text structure and reducing conjunctions.

[0022] The beneficial effects of the present invention are as follows: providing a more targeted and adaptive animation dialogue test question bank based on the cognitive level and language ability of users of different ages, improving the accuracy and effectiveness of the test, removing special characters and punctuation marks by using regular expressions, establishing a stop word list and performing stemming processing, converting the animation dialogue text into the most basic form, helping to reduce noise and variants, and improving the clarity and analyzability of the text, dividing different levels of word frequency and word length by counting word frequency and word length, and determining root complexity according to word frequency, and judging the difficulty level of the animation dialogue in combination with the text length and the dependency relationship between the main clause and the subordinate clause, which helps to more accurately evaluate the difficulty of the animation dialogue and provide users with more challenging and adaptive learning content, and by comprehensively considering the user's cognitive level and the characteristics of the animation dialogue, the difficulty of the animation dialogue can be more accurately evaluated, and more appropriate learning content can be provided to users, and the learning effect and experience quality can be improved, and by processing the animation dialogue to different degrees, users can better understand the animation content at different difficulty levels, improve user participation and learning effect, enhance user attraction and satisfaction with the animation content, improve user experience, and promote the improvement of learning effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 is a flow chart of the method of the present invention; DETAILED DESCRIPTION

[0024] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0025] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, "plurality" means two or more, unless otherwise clearly and specifically defined.

[0026] In the description of the present application, the term "for example" is used to mean "used as an example, illustration or description". Any embodiment described as "for example" in the present application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid unnecessary details to obscure the description of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present application.

[0027] This embodiment provides Figure 1 The method for adaptively adjusting the difficulty of animation dialogues based on the user's cognitive level specifically includes the following steps:

[0028] S101. Collect user age information and establish an animation dialogue test question bank, map the user's cognitive level score according to the user's score in the animation dialogue test and determine the user's cognitive level;

[0029] Furthermore, user age information is collected and an animation dialogue test question bank is established. Based on the cognitive levels and language abilities of users of different ages, the animation dialogue question bank is differentiated more accurately and effectively. The animation dialogue test question bank is divided into a first animation dialogue test question bank and a second animation dialogue question bank. The first animation dialogue test question bank corresponds to a user age group of 3-5 years old, and the second animation dialogue test question bank corresponds to a user age group of 5-7 years old. Each question bank is adapted to animation dialogues corresponding to users of different age groups. The animation dialogues corresponding to users aged 3-5 years old are derived from animation dialogues in fairy tales, and the animation dialogues corresponding to users aged 5-7 years old are derived from animation dialogues in ancient books. Each animation dialogue test question bank contains fifty multiple-choice questions and fifty judgment questions. One point is awarded for each correct answer and no point is awarded for an incorrect answer. The user's cognitive level score is mapped according to the user's score in the animation dialogue test and the user's cognitive level is judged. The specific formula for the mapping is:

[0030]

[0031] Among them, y represents the user's cognitive level score, x represents the user's score in the animation dialogue test, S min Indicates the highest score in the cognitive level group, S max It represents the lowest score of the cognitive level group, floor() represents the rounding function, and divides the user's cognitive level into primary cognitive level, intermediate cognitive level and advanced cognitive level. The cognitive level score range of the primary cognitive level group is 0-50 points, the cognitive level score range of the intermediate cognitive level group is 51-80 points, and the cognitive level score range of the advanced cognitive level group is 81-100 points.

[0032] S102. Preprocess the animation dialogue text and comprehensively evaluate the difficulty level of the animation dialogue through different word frequencies, word lengths, root complexity, text lengths, and dependency relationships between main clauses and subordinate clauses;

[0033] Furthermore, animation lines are collected from different sources, and regular expressions are used to match all non-alphabetic, non-numeric and non-blank characters in the text of the animation lines. Special characters and punctuation marks of the animation lines are removed by replacing empty strings. A stop word list is established and the animation lines are segmented into single words. Each word is traversed to check whether it is a stop word using the stop word list and the stop words are removed. A lemma restoration tool is used to perform stemming, and the animation lines are segmented into word sequences for word segmentation to reduce noise in the animation line text. Stemming converts the animation line text into the most basic form to help reduce variants of the animation line text.

[0034] Furthermore, statistical methods are used to count the word frequency and word length of the animation lines, and the word frequency is divided into high-frequency words, medium-frequency words and low-frequency words, and the word length is divided into short words, medium-length words and long words. The root complexity is determined according to the word frequency of the animation lines, and the root complexity is divided into complex roots and simple roots.

[0035] Furthermore, the number of words in the animation dialogue text is counted and combined with the word length to distinguish the text length of the animation dialogue, wherein animation dialogue text with more than 30 words is defined as a long sentence, and animation dialogue text with less than 30 words is defined as a short sentence. The difficulty level of the animation dialogue text is determined according to the dependency relationship between the main sentence and the subordinate clause in the animation dialogue text. When a main sentence in the animation dialogue text is followed by multiple subordinate clauses, the animation dialogue text is a difficult sentence, otherwise it is a simple sentence.

[0036] Furthermore, by randomly combining different word frequencies, word lengths, root complexities, text lengths, and dependencies between main and subordinate clauses, the difficulty level of animation lines is comprehensively evaluated. The difficulty level of simple animation lines is divided into simple short sentences with high-frequency short words and simple roots, the difficulty level of more difficult animation lines is long and difficult sentences with low-frequency long words and complex or simple roots, and the difficulty level of difficult animation lines is long and difficult sentences with low-frequency long words and complex roots. This can serve as a more accurate standard for evaluating the difficulty of animation lines.

[0037] S103. Compare the predicted values ​​of the current animation dialogue difficulty level by integrating the influence of the interval characteristics of the user's cognitive level score on the groups divided by the user's cognitive level, and use weighted average to obtain the animation dialogue difficulty level based on the user's cognitive level;

[0038] Furthermore, the user cognition level is taken as the first target variable set, a linear regression model is constructed and the first target variable set is input, and the coefficient of the linear regression model is estimated by minimizing the difference between the groups divided by the actual user cognition level and the interval of the user cognition level score using the least squares method. The specific formula of the linear regression model is:

[0039] T=β0+β1W1+β2W2+…+β n W n +ε

[0040] Where T represents the first target variable set, β0 represents the intercept, β1, β2, …, β n The group features representing the user cognitive level division, W1, W2, ..., W nrepresents the interval characteristics of the user's cognitive level score, ε represents the error value, where the coefficient of the linear regression model represents the degree of influence of the interval characteristics of the user's cognitive level score on the grouping of the user's cognitive level. The different word frequencies, word lengths and root complexities of the animation lines are used as the second target variable set, and a decision tree model is constructed and the second target variable set is input. Different word frequencies, word lengths and root complexity features are selected as the partitioning features of the current node and the partitioning points are determined. The second variable set is divided into multiple subsets according to the partitioning features and the partitioning points, where each subset corresponds to a different combination of word frequencies, word lengths and root complexity. The partitioning steps are recursively repeated to establish a subtree until the maximum depth of the decision tree is reached, and the current node is marked as a leaf node and the predicted value of the leaf node is obtained, that is, the current animation line difficulty level Other predicted values, compare the predicted value of the current animation lines difficulty level with the current animation lines difficulty level division, if the predicted value of the current animation lines difficulty level corresponds to the current animation lines difficulty level division, integrate the linear regression model with the decision tree model and use weighted average to obtain the animation lines difficulty level based on the user's cognitive level, divide the animation lines difficulty level based on the user's cognitive level into N equal-sized result subsets, where N is 5 and the result subsets are represented as folds, use one of the result subsets as a validation set in turn, and the remaining N-1 result subsets as training sets, repeat the division and as steps, and take the mean of the test results as the final integrated model performance evaluation indicator, and quantify the animation lines difficulty level based on the user's cognitive level by associating the user's cognitive level with the animation lines difficulty level.

[0041] S104. Dividing the difficulty level of the animation lines based on the user's cognitive level into simple difficulty, medium difficulty and difficult difficulty, and performing animation line difficulty adaptation based on different difficulty levels;

[0042] Furthermore, the difficulty levels of animation lines based on user cognitive levels are divided into simple difficulty, medium difficulty and difficult difficulty. The simple difficulty divides the original animation lines into sentences, replaces synonyms and simplifies the vocabulary, simplifies the sentence structure by removing clauses and complex modifying components, sorts out the text containing complex logical relationships by reorganizing the text structure and adding conjunctions, and deletes redundant components of the animation lines. The medium difficulty divides the original animation lines into sentences, replaces synonyms and simplifies the vocabulary. The difficult difficulty introduces language conversion, sorts out the text with simple logical relationships by reorganizing the text structure and reducing conjunctions, and through different degrees of processing of the animation lines, the animation lines at different difficulty levels are more in line with the user's understanding and acceptance ability, thereby improving the user's understanding and participation in the animation content.

[0043] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0044] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0045] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0046] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0047] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0048] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0049] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. An adaptive method for the difficulty of animation dialogues based on user cognitive level, characterized in that: The specific steps include: S101. Collect user age information and establish an animation dialogue test question bank, map the user's cognitive level score according to the user's score in the animation dialogue test and determine the user's cognitive level; S102. Preprocess the animation dialogue text and comprehensively evaluate the difficulty level of the animation dialogue through different word frequencies, word lengths, root complexity, text lengths, and dependency relationships between main clauses and subordinate clauses; The word frequency and word length of the animation lines are counted by using statistical methods, and the word frequency is divided into high-frequency words, medium-frequency words and low-frequency words, and the word length is divided into short words, medium-length words and long words. The root complexity is determined according to the word frequency of the animation lines, and the root complexity is divided into complex root words and simple root words. The number of words in the animation lines text is counted and the word length is combined to distinguish the text length of the animation lines, wherein the animation lines text with more than 30 words is defined as a long sentence, and the animation lines text with less than 30 words is defined as a short sentence. The difficulty level of the animation lines text is determined according to the dependency relationship between the main sentence and the subordinate clause in the animation lines text. When a main sentence in the animation lines text is followed by multiple subordinate clauses, the animation lines text is a difficult sentence, otherwise it is a simple sentence. The difficulty level of the animation lines is comprehensively evaluated by combining different word frequencies, word lengths, root complexity, text lengths and the dependency relationship between the main sentence and the subordinate clause in a random combination method; S103. Compare the predicted values ​​of the current animation dialogue difficulty level by integrating the influence of the interval characteristics of the user's cognitive level score on the groups divided by the user's cognitive level, and use weighted average to obtain the animation dialogue difficulty level based on the user's cognitive level; Taking the user's cognitive level as the first target variable set, constructing a linear regression model and inputting the first target variable set, using the least square method to estimate the coefficient of the linear regression model by minimizing the difference between the groups divided by the actual user's cognitive level and the interval of the user's cognitive level score, taking the different word frequencies, word lengths and root complexity of the animation lines as the second target variable set, constructing a decision tree model and inputting the second target variable set, comparing the predicted value of the current animation line difficulty level with the current animation line difficulty level division, if the predicted value of the current animation line difficulty level corresponds to the current animation line difficulty level division, integrating the linear regression model with the decision tree model and using weighted average to obtain the animation line difficulty level based on the user's cognitive level; S104. Divide the difficulty level of the animation lines based on the user's cognitive level into simple difficulty, medium difficulty and difficult difficulty, and perform animation line difficulty adaptation based on different difficulty levels.

2. The method for adaptively adjusting the difficulty of animation dialogues based on user cognitive level according to claim 1, characterized in that: In S101, the user's age information is collected and an animation dialogue test question bank is established. The animation dialogue test question bank is divided into a first animation dialogue test question bank and a second animation dialogue question bank. The user's cognitive level score is mapped according to the user's score in the animation dialogue test and the user's cognitive level is determined. The user's cognitive level is divided into a primary cognitive level, an intermediate cognitive level and an advanced cognitive level.

3. The method for adaptively adjusting the difficulty of animation dialogues based on user cognitive level according to claim 1, characterized in that: The specific formula of the mapping is: ； in, Indicates the user's cognitive level score, Indicates the user's score in the animation lines test. Indicates the highest score in the cognitive level group. Indicates the lowest score in the cognitive level group. Represents the rounding function.

4. The method for adaptively adjusting the difficulty of animation dialogues based on user cognitive level according to claim 1, characterized in that: In S102, preprocessing the animation lines text includes: using regular expressions to match all non-alphabetic, non-numeric and non-blank characters in the text of the animation lines, removing special characters and punctuation marks of the animation lines by replacing empty strings, establishing a stop word list and dividing the animation lines into single words, traversing each word and checking whether it is a stop word using the stop word list and removing the stop words, using a lemma restoration tool to perform stemming, and dividing the animation lines into word sequences for word segmentation.

5. The method for adaptively adjusting the difficulty of animation dialogues based on user cognitive level according to claim 1, characterized in that: In S103, the specific formula of the linear regression model is: ； in, represents the first target variable set, represents the intercept, The group characteristics representing the user's cognitive level classification, represents the interval feature of the user's cognitive level score, Indicates the error value.

6. The method for adaptively adjusting the difficulty of animation dialogues based on user cognitive level according to claim 1, characterized in that: In S103, the decision tree model specifically includes: selecting different features of word frequency, word length and root complexity as the partitioning features of the current node and determining the partitioning points, dividing the second variable set into multiple subsets according to the partitioning features and the partitioning points, recursively repeating the partitioning steps to establish subtrees until the maximum depth of the decision tree is reached, marking the current node as a leaf node and obtaining the predicted value of the leaf node.

7. The method for adaptively adjusting the difficulty of animation dialogues based on user cognitive level according to claim 1, characterized in that: In S104, the difficulty level of the animation dialogue based on the user's cognitive level is divided into simple difficulty, medium difficulty and difficult difficulty.

8. The method for adaptively adjusting the difficulty of animation dialogues based on user cognitive level according to claim 7, characterized in that: The simple difficulty level divides the original animation lines into sentences, replaces synonyms and simplifies the vocabulary. It simplifies the sentence structure by removing clauses and complex modifying elements. It sorts out the text containing complex logical relationships by reorganizing the text structure and adding conjunctions, and deletes redundant components of the animation lines. The medium difficulty level divides the original animation lines into sentences, replaces synonyms and simplifies the vocabulary. The difficult difficulty level introduces language conversion and sorts out the text with simple logical relationships by reorganizing the text structure and reducing conjunctions.

Images