Word group training data generating device, word group training device and method, electronic device, storage medium and computer program

Abstract

The present application provides a word formation training data generation device, a word formation training device and method, an electronic device, a storage medium and a computer program. The word formation training data generation device includes a first data processing module, which creates multiple Chinese character data sets according to the character difficulty level and character similarity attribute of Chinese character data, each Chinese character data set includes a character table difficulty level and a group of similar Chinese character data; a second data processing module, which traverses the Chinese character data in each Chinese character data set, and for each Chinese character data in each Chinese character data set, determines the matching Chinese character data and corresponding word data that can form a word with the Chinese character data; determines the word difficulty level of each word data according to at least the character table difficulty level of the Chinese character data set where the corresponding Chinese character data is located; creates a corresponding matching Chinese character data set using the matching Chinese character data of the Chinese character data in the Chinese character data set, and creates a corresponding word data set using the word data corresponding to the Chinese character data in the Chinese character data set.

Description

Technical Field

[0001] The present application relates to data processing technology, and in particular, to a word group training data generating device, a word group training device and method, an electronic device, a storage medium and a computer program. Background Art

[0002] Children and non-native Chinese beginners often confuse similar Chinese characters when learning Chinese characters. Chinese dyslexics also misuse similar characters when reading and writing. Therefore, it is very important for Chinese learners and Chinese dyslexics to accurately distinguish similar characters, which can effectively improve their learning efficiency.

[0003] Word grouping training is a relatively effective way to learn Chinese characters by distinguishing similar characters. Providing context clues through word settings can help Chinese learners and Chinese dyslexics accurately distinguish and master similar characters. The effect of word grouping training is closely related to the selection of word grouping training data and the design of training questions. Therefore, a scientific and effective word grouping training data generation scheme and training question design scheme are needed to ensure the effect of word grouping training. Summary of the invention

[0004] In order to solve the above problems, the purpose of the embodiments of the present application is to provide a word group training data generating device, a word group training device and method, an electronic device, a storage medium and a computer program.

[0005] In a first aspect, an embodiment of the present application provides a device for generating word group training data, comprising:

[0006] A Chinese character data set creation module is used to select Chinese character data from a basic Chinese character database according to the character difficulty level and similar character attributes of the Chinese character data, and create multiple Chinese character data sets using the selected Chinese character data, each Chinese character data set includes a character table difficulty level and a group of similar Chinese character data, there are a total of P character table difficulty levels, each character table difficulty level corresponds to at least one Chinese character data set, and the character table difficulty level of each Chinese character data set is determined by the character difficulty level of the included Chinese character data; Chinese character data with the same similar character attributes belong to similar Chinese character data;

[0007] A matching word determination module is used to traverse the Chinese character data in each Chinese character data set, and for each Chinese character data in each Chinese character data set, determine the matching Chinese character data and corresponding word data that can form a word with the Chinese character data;

[0008] A word difficulty level determination module, used to determine the word difficulty level of each word data at least according to the word table difficulty level of the Chinese character data set where the corresponding Chinese character data is located;

[0009] A matching Chinese character data set creation module, used to create a matching Chinese character data set corresponding to each Chinese character data set, wherein the matching Chinese character data set includes matching Chinese character data for each Chinese character data in the corresponding Chinese character data set;

[0010] A word data set creation module, used to create a word data set corresponding to each Chinese character data set, wherein the word data set includes word data corresponding to each Chinese character data in the corresponding Chinese character data set;

[0011] Among them, each word formation training question corresponds to a target Chinese character data, matching data for word formation with the target Chinese character data and the formed target word data, all or part of the Chinese character data in the Chinese character data set where the target Chinese character data is located serves as candidate Chinese character data for the corresponding word formation training question, and the word difficulty level of the target word data is positively correlated with the difficulty level of the corresponding word formation training question.

[0012] In a second aspect, the present application also provides a word group training device, including:

[0013] A training difficulty determination module is used to determine the difficulty level of the current word formation training task;

[0014] The training task acquisition module is used to acquire a group of word formation training questions with the difficulty level of the current word formation training task, each of the group of word formation training questions corresponds to a target Chinese character data, matching data of the word formation of the target Chinese character data and the formed target word data, all or part of the Chinese character data in the Chinese character data set where the target Chinese character data is located is used as candidate Chinese character data for the corresponding word formation training question, and the difficulty level of the target word data is positively correlated with the difficulty level of the current word formation training task; each Chinese character data set includes a character table difficulty level and a group of similar Chinese character data , there are P word table difficulty levels, each word table difficulty level corresponds to at least one Chinese character data set, and the word table difficulty level of each Chinese character data set is determined by the word difficulty level of the included Chinese character data; Chinese character data with the same similar character attributes belong to similar Chinese character data; the word difficulty level of the target word data is determined at least according to the word table difficulty level of the Chinese character data set corresponding to the target Chinese character data; each word group training question includes question stem data and candidate item data; the question stem data includes matching character data that constitute the target word data with the target Chinese character data, and the candidate item data includes candidate Chinese character data;

[0015] The training task push module is used to display each word group training topic in the current word group training task;

[0016] The training result feedback module is used to obtain the response result of each word group training question in the current word group training task, compare the response result with the target word data, and determine the training score of the corresponding word group training question according to the comparison result.

[0017] In a third aspect, the present application also provides a method for generating word group training data, including:

[0018] Selecting Chinese character data from a basic Chinese character database according to the character difficulty level and similar character attributes of the Chinese character data, creating multiple Chinese character data sets using the selected Chinese character data, each Chinese character data set including a character table difficulty level and a group of similar Chinese character data, a total of P character table difficulty levels, each character table difficulty level corresponds to at least one Chinese character data set, and the character table difficulty level of each Chinese character data set is determined by the character difficulty level of the included Chinese character data; Chinese character data with the same similar character attributes belong to similar Chinese character data;

[0019] Traversing the Chinese character data in each Chinese character data set, and for each Chinese character data in each Chinese character data set, determining matching Chinese character data and corresponding word data that can form a word with the Chinese character data;

[0020] Determine the word difficulty level of each word data at least according to the word table difficulty level of the Chinese character data set where the corresponding Chinese character data is located;

[0021] Creating a matching Chinese character data set corresponding to each Chinese character data set, wherein the matching Chinese character data set includes matching Chinese character data for each Chinese character data in the corresponding Chinese character data set;

[0022] Creating a word data set corresponding to each Chinese character data set, wherein the word data set includes word data corresponding to each Chinese character data in the corresponding Chinese character data set;

[0023] Among them, each word formation training question corresponds to a target Chinese character data, matching data for word formation with the target Chinese character data and the formed target word data, all or part of the Chinese character data in the Chinese character data set where the target Chinese character data is located serves as candidate Chinese character data for the corresponding word formation training question, and the word difficulty level of the target word data is positively correlated with the difficulty level of the corresponding word formation training question.

[0024] In a fourth aspect, the present application also provides a word group training method, including:

[0025] Determine the difficulty level of the current word formation training task;

[0026] A group of word formation training questions with the difficulty level of the current word formation training task is obtained, each of the group of word formation training questions corresponds to a target Chinese character data, matching data of the word formation of the target Chinese character data and the target word data formed, all or part of the Chinese character data in the Chinese character data set where the target Chinese character data is located is used as candidate Chinese character data of the corresponding word formation training question, and the difficulty level of the target word data is positively correlated with the difficulty level of the current word formation training task; each Chinese character data set includes a character table difficulty level and a group of similar Chinese character data, there are a total of P character table difficulty levels, each character table difficulty level corresponds to at least one Chinese character data set, and the character table difficulty level of each Chinese character data set is determined by the character difficulty level of the included Chinese character data; Chinese character data with the same similar character attributes belong to similar Chinese character data; the word difficulty level of the target word data is determined at least according to the character table difficulty level of the Chinese character data set where the corresponding target Chinese character data is located; each word formation training question includes stem data and candidate item data; the stem data includes matching character data that constitute the target word data with the target Chinese character data, and the candidate item data includes candidate Chinese character data;

[0027] Display each word group training question in the current word group training task respectively;

[0028] The response result of each word combination training question in the current word combination training task is obtained, the response result is compared with the target word data, and the training score of the corresponding word combination training question is determined according to the comparison result.

[0029] In a fifth aspect, an embodiment of the present application further provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program; the processor executes the computer program stored in the memory to implement the steps in the word formation training data generation method described in any of the above embodiments; or, the processor executes the computer program stored in the memory to implement the steps in the word formation training method described in any of the above embodiments.

[0030] In a sixth aspect, an embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the steps in the method for generating word group training data described in any of the above embodiments are implemented; or, when the computer program is executed by a processor, the steps in the method for generating word group training data described in any of the above embodiments are implemented.

[0031] In the seventh aspect, an embodiment of the present application also provides a computer program, including computer instructions, which, when executed by a processor, implement the steps of the word group training data generating method described in any of the above embodiments; or, when executed by a processor, implement the steps of the word group training method described in any of the above embodiments.

[0032] The present application has the following beneficial effects: through the word group training data generation device and method provided by the present application, Chinese character data can be selected in combination with the difficulty and similarity rules of the characters, thereby generating word group training data, and literacy training can be carried out through word group training to achieve better training effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The drawings described herein are used to provide further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute improper limitations on the present application.

[0034] Figure 1 A flowchart of a method for generating word group training data provided by an embodiment of the present application is shown;

[0035] Figure 2 A schematic diagram of a cross matrix for determining a word difficulty level provided by an embodiment of the present application is shown;

[0036] Figure 3 A flow chart of a word group training method provided in an embodiment of the present application is shown;

[0037] Figure 4 A schematic diagram of a word group training data generating device provided in an embodiment of the present application is shown;

[0038] Figure 5 A schematic diagram of a word group training device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0039] In order to make the technical solutions and advantages in the embodiments of the present application more clearly understood, the exemplary embodiments of the present application are further described in detail below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than an exhaustive list of all the embodiments. It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict.

[0040] In addition, 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 the indicated technical features. 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, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0041] The word group training scheme and the corresponding word group training data generation scheme provided in the embodiments of the present application are suitable for Chinese learners or people with dyslexia to learn Chinese characters. In the following embodiments, children are used as examples to illustrate the specific implementation of the embodiments of the present application. It should be pointed out that the embodiments of the present application are not only suitable for children, but also for teenagers, adults, and the elderly.

[0042] Figure 1 A flowchart of a method for generating word group training data provided by an embodiment of the present application is shown. Figure 1 As shown, the process includes at least the following steps:

[0043] Step 101, select Chinese character data from a basic Chinese character database according to the character difficulty level and similar character attributes of the Chinese character data, and create multiple Chinese character data sets using the selected Chinese character data, each Chinese character data set includes a character table difficulty level and a group of similar Chinese character data, there are a total of P character table difficulty levels, each character table difficulty level corresponds to at least one Chinese character data set, and the character table difficulty level of each Chinese character data set is determined by the character difficulty level of the included Chinese character data; Chinese character data with the same similar character attributes belong to similar Chinese character data.

[0044] In the embodiment of the present application, if applied to an electronic device, then the Chinese character data refers to the electronic data corresponding to the Chinese characters, and the character difficulty level of the Chinese character data is the difficulty level of the Chinese characters; if applied to a non-electronic scenario, then the Chinese character data is equivalent to the Chinese characters.

[0045] Step 102, traverse the Chinese character data in each Chinese character data set, and for each Chinese character data in each Chinese character data set, determine the matching Chinese character data and corresponding word data that can form a word with the Chinese character data.

[0046] In the embodiment of the present application, if applied to an electronic device, then the word data refers to the electronic data corresponding to the word, and the word difficulty level of the word data is the difficulty level of the word; if applied to a non-electronic scenario, then the word data is equivalent to the word.

[0047] Step 103: Determine the word difficulty level of each word data at least according to the word table difficulty level of the Chinese character data set where the corresponding Chinese character data is located.

[0048] Step 104: Create a matching Chinese character data set corresponding to each Chinese character data set, where the matching Chinese character data set includes matching Chinese character data for each Chinese character data in the corresponding Chinese character data set.

[0049] Step 105: Create a word data set corresponding to each Chinese character data set, where the word data set includes word data corresponding to each Chinese character data in the corresponding Chinese character data set.

[0050] Among them, each word - forming training question corresponds to a target Chinese character data, matching data that forms words with the target Chinese character data, and target word data. All or part of the Chinese character data in the Chinese character data set where the target Chinese character data is located serves as the candidate Chinese character data for the corresponding word - forming training question, and the word difficulty level of the target word data is positively correlated with the difficulty level of the corresponding word - forming training question.

[0051] In the embodiments of the present application, it is possible but not limited to using a specified Chinese character recognition table or an electronic database constructed based on the Chinese character recognition table as the basic Chinese character database. For example, using the "Chinese Character Recognition Table of the Ministry - compiled Edition Textbook" or an electronic database based on the "Chinese Character Recognition Table of the Ministry - compiled Edition Textbook" as the basic Chinese character database. The above - mentioned Chinese character data and matching Chinese character data are both selected from the basic Chinese character database.

[0052] Based on the time when children come into contact with and learn, there is a clear difficulty gradient for both the target Chinese characters and the matching Chinese character data: the earlier the contact and learning time of a Chinese character, the lower its difficulty; conversely, the greater its difficulty. However, even if both the target Chinese character data and the matching Chinese character data belong to low - difficulty Chinese characters for early contact, the words formed by them may be semantically difficult.

[0053]

Example

[0054] Therefore, in the design of the embodiments of the present application, standards suitable for characters and words are adopted respectively to define their difficulty levels.

[0055] The embodiments of the present application do not limit the specific determination method and data format of the character difficulty level of Chinese character data. By way of example rather than limitation, the character difficulty level of Chinese character data can adopt the difficulty level specified for Chinese characters in the corresponding Chinese character recognition table; the character difficulty level of Chinese character data can also be the age of first acquisition determined through tests; the character difficulty level of Chinese character data can also be the age at which a Chinese character should be acquired or the serial number of the textbook semester in which it first appears in the textbook.

[0056] In the embodiments of the present application, similar Chinese character data can refer to Chinese character data with similar glyphs, can also refer to Chinese character data with related semantics, or can also refer to Chinese character data with similar pronunciations.

[0057] First, an explanation is given for Chinese character data with similar glyphs, Chinese character data with related semantics, and Chinese character data with similar pronunciations.

[0058] Data of Chinese characters with similar glyphs: Chinese characters are world-famous for their visual complexity. Each Chinese character is a unique combination of strokes or components, and there are always visually similar Chinese characters with highly similar structures, components, or strokes. Accurately distinguishing and differentiating Chinese characters with similar glyphs is an important prerequisite for avoiding confusion errors.

[0059] Data of semantically related Chinese characters: Although Chinese characters have meanings, in daily spoken and written languages, words are the basic units of use. Therefore, Chinese characters always appear in combinations as words, and semantically related Chinese characters are prone to causing confusion with each other.

[0060] Data of Chinese characters with similar pronunciations: Generally speaking, the number of syllables in Chinese (about 400 syllables) is much smaller than the number of Chinese characters. Considering only about 3,000 commonly used Chinese characters, on average, each syllable needs to correspond to 7 - 8 Chinese characters. There are a large number of homophonic characters in Chinese, that is, one syllable corresponds to multiple characters. The more Chinese characters a syllable corresponds to, the greater the difficulty of accurately corresponding to a specific Chinese character through pronunciation. Therefore, differentiating and mastering homophonic characters is of great significance for Chinese learning.

[0061] Among them, data of Chinese characters with similar glyphs refer to Chinese character data with high visual similarity in glyphs. Data of Chinese characters with similar glyphs can belong to the same orthographic family. Then, each piece of Chinese character data in the same Chinese character data set belongs to the same orthographic family. Correspondingly, the similar character attribute is used to indicate the orthographic family to which the Chinese character data belongs. Specifically, the target character A can be transformed into the target character B through the overlap or change of the glyph structure, strokes, or components (for example, 甲, 申, 由).

[0062] The core of the word - formation training for data of Chinese characters with similar glyphs is to achieve the mastery and reinforcement of Chinese characters with similar glyphs on the basis of strengthening the connection among form, sound, and meaning.

[0063] Data of semantically related Chinese characters can belong to the same level in the semantic hierarchy network model. Each piece of Chinese character data in the same Chinese character data set belongs to the same level in the semantic hierarchy network model. Correspondingly, the similar character attribute is used to indicate the level of the Chinese character data in the semantic hierarchy network model.

[0064] The core of the word - formation training for data of semantically related Chinese characters is to achieve the mastery and reinforcement of Chinese characters with similar semantics on the basis of strengthening the connection among form, sound, and meaning.

[0065] Data of Chinese characters with similar pronunciations can belong to the same homophone family. Each piece of Chinese character data in the same Chinese character data set belongs to the same homophone family. Correspondingly, the similar character attribute is used to indicate the homophone family to which the Chinese character data belongs.

[0066] The core of word group training for phonetically similar Chinese character data is to achieve the mastery and strengthening of phonetically similar characters (including homophones) on the basis of strengthening the connection between form, sound and meaning. Therefore, the selection of Chinese character data also refers to the information of the "Common Chinese Character List" and defines the difficulty based on the number of syllables and phonetic components corresponding to Chinese characters (homophone families).

[0067] In a feasible implementation, if the similar Chinese character data includes phonetically similar Chinese character data, the character table difficulty level of the Chinese character data set can also be determined based on the character difficulty level of each Chinese character data in the Chinese character data set and the syllable difficulty level of the corresponding homophone family, and the syllable difficulty level of the homophone family is positively correlated with the number of Chinese characters contained in the homophone family. Among them, the mapping relationship between the character difficulty level, syllable difficulty level and character table difficulty level of the Chinese character data can be determined according to actual conditions, and this application does not limit this.

[0068] In another feasible implementation, if the similar Chinese character data includes phonetically similar Chinese character data, the Chinese character data may be selected from a basic Chinese character database based on the character difficulty level, similar character attributes and the syllable difficulty level of the corresponding homophone family.

[0069] As an example but not a limitation, after selecting the target syllable, further target Chinese character data is selected. The following features should be considered in selecting the target syllable:

[0070] (1) The selected target syllable must contain at least n corresponding Chinese characters (homophones, regardless of tone);

[0071] Each group contains n phonetically similar target words;

[0072] (2) Determine the difficulty of a syllable based on the number of Chinese characters that correspond to the same syllable;

[0073] The fewer Chinese characters that correspond to the same syllable (for example, lower than the average "syllable-Chinese character" number), the lower the difficulty of distinguishing, and thus it is defined as a lower difficulty syllable;

[0074] The more Chinese characters that correspond to the same syllable (for example, higher than the average "syllable-Chinese character" number), the more difficult it is to distinguish, and it is therefore defined as a higher-difficulty syllable.

[0075] Based on any of the above method embodiments, optionally, the number of Chinese character data included in each Chinese character data set meets a preset number requirement. For example, it is preset that each Chinese character data set includes n Chinese character data.

[0076] Based on any of the above method embodiments, optionally, the character difficulty level distribution of the Chinese character data included in each Chinese character data set satisfies a preset character difficulty level distribution rule. The present application embodiment does not limit the specific content of the character difficulty level distribution rule, and the character difficulty level distribution rule can be defined according to actual conditions.

[0077] Based on any of the above method embodiments, optionally, Chinese character data sets with the same character table difficulty level correspond to the same character difficulty level distribution rule.

[0078] Based on any of the above method embodiments, optionally, each Chinese character data has a unique pronunciation in the corresponding word data.

[0079] Based on any of the above method embodiments, optionally, each matching Chinese character data only forms a word with the corresponding Chinese character data in the Chinese character data set to which the corresponding Chinese character data belongs.

[0080] On the basis of any of the above method embodiments, optionally, the word difficulty level of the word data may also be determined according to the word table difficulty level of the Chinese character data set corresponding to the Chinese character data and the preset word difficulty level.

[0081] Furthermore, when determining the word difficulty level of word data, the number of word data of the same word difficulty level may also be considered. For example, if the number of word data of a certain word difficulty level is too small, the low difficulty level may be incorporated into the adjacent word difficulty level, thereby adjusting the word difficulty level.

[0082] As an example and not limitation, the above-mentioned preset word difficulty level may adopt the word difficulty defined in the "Common Word List for Compulsory Education (Draft)".

[0083] The embodiment of the present application does not limit the mapping relationship among the difficulty level of the word list, the difficulty level of the preset word, and the word difficulty level of the word data, and the mapping relationship may be defined according to actual conditions.

[0084] Based on any of the above method embodiments, optionally, a word formation training topic can also be generated, the word formation training topic includes stem data and candidate item data; the stem data includes matching character data that constitutes target word data with target Chinese character data, and the candidate item data includes candidate Chinese character data.

[0085] In a more specific implementation, it is determined that K Chinese character data sets need to be created, each of which includes n Chinese character data, and the K Chinese character data sets are divided into P character table difficulty levels. Based on the "Ministry Edition Textbook Literacy Table", that is, the time when children formally come into contact with learning, the time when children formally come into contact with learning (number of textbooks) is defined as the character difficulty level (1-12 volumes) of a single Chinese character data. The difficulty level of preset words is defined based on the "Common Word List for Compulsory Education (Draft)".

[0086] Take the electronic implementation as an example to illustrate:

[0087] Create K Chinese character data sets.

[0088] For each Chinese character data set, by traversing the basic Chinese character database obtained from the "Chinese Character Table of the Ministry of Education Textbook", n Chinese character data corresponding to the character table difficulty level of the Chinese character data set and the preset character difficulty level distribution law are selected, and the selected Chinese character data are added to the Chinese character data set. Among them, the average value of the character difficulty level of the n Chinese character data is the character table difficulty level of the Chinese character data set.

[0089] The distribution pattern of character difficulty levels of Chinese character data in a Chinese character data set is as follows: 1) the character difficulty levels are the same or similar (for example, all come from the first textbook, or all come from the ninth textbook); or, 2) the difference in character difficulty levels increases (for example, they come from the first, third, sixth, ... textbooks respectively).

[0090] The character difficulty level distribution rules of different Chinese character data sets with the same character table difficulty level have the following characteristics: 1) the character difficulty levels are the same or similar; or, 2) the differences in character difficulty levels are similar.

[0091] The distribution rules of character difficulty levels of different Chinese character data sets with different character table difficulty levels have the following characteristics: 1) the differences in character difficulty levels of Chinese character data within the same group increase (for example, the Chinese character data come from the 1st, 4th, 9th... textbooks respectively); 2) the character difficulty level of a single Chinese character data increases; 3) Chinese character data of level one difficulty (the lowest difficulty) all come from lower grade textbooks (for example, grade 1); as the difficulty increases, Chinese character data gradually disperse in textbooks of different grades, and the proportion of Chinese character data from lower grade textbooks gradually decreases.

[0092] Assume that there are 26 Chinese character data sets, each of which contains 4 Chinese character data, and the 26 Chinese character data sets are divided into four character table difficulty levels. The difficulty levels of the Chinese character data sets and the distribution rules of the character difficulty levels are shown in Table 1 below.

[0093] Table 1 Difficulty levels of Chinese character data sets and distribution patterns of character difficulty levels

[0094]

[0095] The number of Chinese characters and syllables refers to the average number of Chinese character data corresponding to the same syllable, without distinguishing between tones.

[0096] After the creation of the Chinese character data set is completed, the Chinese character data in each Chinese character data set is traversed, and for each Chinese character data in each Chinese character data set, word data that can correspond to the matching Chinese character data set that forms a word with it is determined. The selection rule of the matching Chinese character data is the same as that of the Chinese character data.

[0097] For each Chinese character data, the matching Chinese character data selected for it constitutes a matching Chinese character data set corresponding to the Chinese character data (referred to as matching character table 1), and the word data composed of each matching Chinese character data constitutes a word data set corresponding to the Chinese character data (referred to as word table 1).

[0098] Vocabulary 1 must meet the following conditions: the pronunciation of the Chinese character data in vocabulary 1 is unique; the Chinese character data that matches the Chinese character data can only form a word with the Chinese character data.

[0099] The word table 1 (n in total) corresponding to the n Chinese character data of the same group constitutes a word data set (referred to as word table 2) corresponding to the Chinese character data set, and the n matching word tables 1 corresponding to the n Chinese character data of the same group constitute a matching Chinese character data set (referred to as matching word table 2) corresponding to the Chinese character data set.

[0100] Furthermore, the word table 2 corresponding to all Chinese character data sets constitutes the word table 3 as a total word library, and the matching word table 2 corresponding to all Chinese character data sets constitutes the matching word table 3 as a total matching word library.

[0101] The difficulty level of the preset words in each word data is assessed in combination with the "Common Vocabulary List of Compulsory Education (Draft)"; if the corresponding word level is not found, manual level determination is performed in combination with words with similar semantic concepts in the "Common Vocabulary List of Compulsory Education (Draft)".

[0102] Furthermore, a cross matrix is ​​formed by combining the word table difficulty level of the Chinese character data set where the Chinese character data is located with the preset word difficulty level, and the word data in the word table 3 can be divided into several word difficulty levels. The specific implementation method of determining the word difficulty level according to the cross matrix can refer to Figure 2 As shown, in Figure 2There are 4 character table difficulty levels and 4 preset word difficulty levels in the cross matrix. The same color represents the same word difficulty level. There are 5 word difficulty levels in total. Among them, word difficulty level 1: character table difficulty level + preset word difficulty level ≤ 3; word difficulty level 2: character table difficulty level + preset word difficulty level = 4; word difficulty level 3: character table difficulty level + preset word difficulty level = 5; word difficulty level 4: character table difficulty level + preset word difficulty level = 6; word difficulty level 5: character table difficulty level + preset word difficulty level ≥ 7. Specifically: the word table difficulty level is level 1 and the preset word difficulty level is level 1 or level 2, corresponding to the word difficulty level 1 of the word data; the word table difficulty level is level 2 and the preset word difficulty level is level 1, corresponding to the word difficulty level 1 of the word data; the word table difficulty level is level 3 and the preset word difficulty level is level 1, corresponding to the word difficulty level 2 of the word data; the word table difficulty level is level 2 and the preset word difficulty level is level 2, corresponding to the word difficulty level 2 of the word data; the word table difficulty level is level 1 and the preset word difficulty level is level 3, corresponding to the word difficulty level 2 of the word data; the word table difficulty level is level 4 and the preset word difficulty level is level 1, corresponding to the word difficulty level 3 of the word data; the word table difficulty level is level 3 and the preset word difficulty level is level 2, corresponding to the word difficulty level 3 of the word data The word difficulty level of the word data is 4; the word difficulty level of the word table is 1 and the preset word difficulty level is 4, which corresponds to the word difficulty level of the word data; the word difficulty level of the word table is 4 and the preset word difficulty level is 2, which corresponds to the word difficulty level of the word data; the word difficulty level of the word table is 3 and the preset word difficulty level is 3, which corresponds to the word difficulty level of the word data; the word difficulty level of the word table is 2 and the preset word difficulty level is 4, which corresponds to the word difficulty level of the word data; the word difficulty level of the word table is 4 and the preset word difficulty level is 3 or 4, which corresponds to the word difficulty level of the word data 5; the word difficulty level of the word table is 3 and the preset word difficulty level is 4, which corresponds to the word difficulty level of the word data 5.

[0103] Figure 2 The implementation method of determining the word difficulty level based on the cross matrix shown takes into account that the number of word data of the same word difficulty level is as balanced as possible. If the balance of the number of word data is not considered, the word difficulty level can also be divided based on the diagonal of the cross matrix. For example, each word data on the diagonal of the cross matrix is ​​divided into a word difficulty level, and the word data on each parallel line of the diagonal is divided into a word difficulty level.

[0104] Figure 3 A flowchart of a word group training method provided in an embodiment of the present application is shown. Figure 3 As shown, the process includes at least the following steps:

[0105] Step 301: Determine the difficulty level of the current word formation training task.

[0106] The difficulty level of the current word group training task may be determined, but is not limited to, based on the training score of the previous word group training task.

[0107] Step 302: Obtain a group of word formation training questions having the difficulty level of the current word formation training task.

[0108] Each word formation training topic in a group of word formation training topics corresponds to a target Chinese character data, matching data of word formation of the target Chinese character data and the target word data formed, all or part of the Chinese character data in the Chinese character data set where the target Chinese character data is located is used as candidate Chinese character data of the corresponding word formation training topic, and the difficulty level of the target word data is positively correlated with the difficulty level of the current word formation training task; each Chinese character data set includes a character table difficulty level and a group of similar Chinese character data, there are a total of P character table difficulty levels, each character table difficulty level corresponds to at least one Chinese character data set, and the character table difficulty level of each Chinese character data set is determined by the character difficulty level of the included Chinese character data; Chinese character data with the same similar character attributes belong to similar Chinese character data; the word difficulty level of the target word data is determined at least according to the character table difficulty level of the Chinese character data set where the corresponding target Chinese character data is located; each word formation training topic includes stem data and candidate item data; the stem data includes matching character data that constitute the target word data with the target Chinese character data, and the candidate item data includes candidate Chinese character data;

[0109] Step 303: Display each word group training topic in the current word group training task respectively.

[0110] Step 304: Obtain the response result of each word combination training question in the current word combination training task, compare the response result with the target word data, and determine the training score of the corresponding word combination training question according to the comparison result.

[0111] Specifically, the difficulty level of the current word formation training task may be determined based on the training scores of each word formation training question in the previous word formation training task.

[0112] In one implementation, if the difficulty level needs to be lowered, the position of the target Chinese character data in the target word data is prompted in each word combination training question of the current word combination training task based on the training scores of each word combination training question in the previous word combination training task, so that the difficulty level is lower than that of the previous word combination training task; if the difficulty level needs to be increased, the position of the target Chinese character data in the target word data is not prompted in each word combination training question of the current word combination training task based on the training scores of each word combination training question in the previous word combination training task, so that the difficulty level is higher than that of the previous word combination training task.

[0113] In another implementation, if the difficulty level needs to be lowered, the difficulty level of the current word group training task is determined to be lowered according to the training scores of each word group training topic in the previous word group training task, so that the difficulty level is lower than that of the previous word group training task; if the difficulty level needs to be increased, the difficulty level of the current word group training task is determined to be increased according to the training scores of each word group training topic in the previous word group training task, so that the difficulty level is higher than that of the previous word group training task; if the difficulty level needs to be maintained, the difficulty level of the current word group training task is determined to be maintained according to the training scores of each word group training topic in the previous word group training task. In this implementation, the difficulty level of the word group training task is the same as the word difficulty level of the corresponding target word. The difficulty level of the word group training task can also be composed of two levels of difficulty levels, wherein the first level of difficulty level is the same as the word difficulty level of the corresponding target word, and the second level of difficulty level is adjusted by whether the position of the target Chinese character data in the target word is indicated, or the second level of difficulty level is adjusted by the number of candidate Chinese character data.

[0114] In another implementation method, if the difficulty level needs to be lowered, the number of candidate Chinese character data of each word combination training question in the previous word combination training task is determined to be reduced according to the training scores of each word combination training question in the previous word combination training task, so that the difficulty level of the previous word combination training task is lowered; if the difficulty level needs to be increased, the difficulty level of the current word combination training task is increased according to the training scores of each word combination training question in the previous word combination training task, so that the difficulty level of the previous word combination training task is increased.

[0115] In an embodiment of the present application, there are multiple ways to obtain word combination training questions. In one feasible implementation method, a group of word data with a word difficulty level corresponding to the difficulty level of the current word combination training task is selected from at least one word data set (for example, at least one word table 2, or word table 3), and each word data in the group of word data is marked as target word data of a word combination training question; matching character data corresponding to each target word data is selected from at least one matching character database, and the stem data of the word combination training question is obtained by using the matching character data; candidate Chinese character data including the target Chinese character data is selected from the Chinese character data set corresponding to each target word data, and candidate item data of the word combination training question is obtained by using the candidate Chinese character data, and the target Chinese character data is marked as the target Chinese character data, and the remaining candidate Chinese character data is marked as interference Chinese character data.

[0116] Based on the same inventive concept, the present application provides a device for generating word group training data, comprising:

[0117] A first data processing module is used to select Chinese character data from a basic Chinese character database according to the character difficulty level and character similarity attribute of the Chinese character data, and create a plurality of Chinese character data sets, each of which includes a character table difficulty level and a group of similar Chinese character data, there are a total of P character table difficulty levels, each character table difficulty level corresponds to at least one Chinese character data set, and the character table difficulty level of each Chinese character data set is determined by the character difficulty level of the included Chinese character data; the character similarity attribute is used to identify similar Chinese character data;

[0118] The second data processing module is used to traverse the Chinese character data in each Chinese character data set, and for each Chinese character data in each Chinese character data set, determine the matching Chinese character data and corresponding word data that can form a word with the Chinese character data; determine the word difficulty level of each word data at least according to the word table difficulty level of the Chinese character data set where the corresponding Chinese character data is located; respectively use the matching Chinese character data of each Chinese character data in each Chinese character data set to create a matching Chinese character data set corresponding to each Chinese character data set, and respectively use the word data corresponding to each Chinese character data in each Chinese character data set to create a word data set corresponding to each Chinese character data set;

[0119] Among them, one word combination training task corresponds to one Chinese character data set, all or part of the Chinese character data in the Chinese character data set are used as candidate Chinese character data for each word combination training question in the corresponding word combination training task, and in a word combination training question, only one Chinese character data among the candidate Chinese character data is used as the target Chinese character data, and the remaining candidate Chinese character data are used as interference Chinese character data, the word data corresponding to the target Chinese character data is the target word data of the word combination training question, the word difficulty level of the target word data is positively correlated with the difficulty level of the corresponding word combination training question, and the difficulty level of each word combination training question in a word combination training task is the same.

[0120] Optionally, the similar Chinese character data includes Chinese character data with similar glyphs, and each Chinese character data in the same Chinese character data set belongs to the same orthographic family, and the character similarity attribute is used to indicate the orthographic family to which the Chinese character data belongs;

[0121] or,

[0122] The similar Chinese character data include semantically related Chinese character data, each Chinese character data in the same Chinese character data set belongs to the same level in the semantic hierarchical network model, and the character similarity attribute is used to indicate the level of the Chinese character data in the semantic hierarchical network model;

[0123] or,

[0124] The similar Chinese character data include phonetically similar Chinese character data. Each Chinese character data in the same Chinese character data set belongs to the same homophone family. The character similarity attribute is used to indicate the homophone family to which the Chinese character data belongs.

[0125] Optionally, if the similar Chinese character data includes phonetically similar Chinese character data, the first data processing module is further configured to:

[0126] Determine the character table difficulty level of the Chinese character data set according to the character difficulty level of each Chinese character data in the Chinese character data set and the syllable difficulty level of the corresponding homophone family, wherein the syllable difficulty level of the homophone family is positively correlated with the number of Chinese characters included in the homophone family; or

[0127] Chinese character data are also selected from the basic database according to the syllable difficulty level of the homophone family to which the Chinese character data corresponds.

[0128] Optionally, the character difficulty level distribution of the Chinese character data included in each Chinese character data set satisfies a preset character difficulty level distribution rule.

[0129] Optionally, Chinese character data sets with the same character table difficulty level correspond to the same character difficulty level distribution pattern.

[0130] Optionally, the number of Chinese character data included in each Chinese character data set meets a preset quantity requirement.

[0131] Optionally, the pronunciation of each Chinese character data in the corresponding word data is unique, and / or each word data only corresponds to the corresponding Chinese character data in the Chinese character data set to which the corresponding Chinese character data belongs.

[0132] Optionally, the second data processing module is used to determine the word difficulty level of the word data according to the character table difficulty level of the Chinese character data set corresponding to the Chinese character data and the preset word difficulty level.

[0133] Based on the same inventive concept, the present application provides a word group training device, comprising:

[0134] A training difficulty determination module is used to determine the difficulty level of the current word formation training task;

[0135] A training task acquisition module is used to acquire a group of word-combination training questions corresponding to a determined difficulty level, wherein the candidate Chinese character data in the group of word-combination training questions are part or all of the Chinese character data in a Chinese character data set, and in a word-combination training question, only one Chinese character data in the candidate Chinese character data is used as the target Chinese character data, and the remaining candidate Chinese character data are used as interference Chinese character data; each word-combination training question in the group of word-combination training questions corresponds to a word, the difficulty level of the word is positively correlated with the difficulty level of the current word-combination training task, and the word includes the target Chinese character data of the corresponding word-combination training question;

[0136] The training task push module is used to display each word group training question in the current word group training task.

[0137] Optionally, the training difficulty determination module is configured to: determine the difficulty level of the current word formation training task according to the response results of each word formation training question in the previous word formation training task.

[0138] Optionally, when the training difficulty determination module is configured to determine that the difficulty level needs to be reduced according to the response results of each word formation training question in the previous word formation training task, it determines that the difficulty level of the current word formation training task is one level lower than that of the previous word formation training task; when it is determined that the difficulty level needs to be increased according to the response results of each word formation training question in the previous word formation training task, it determines that the difficulty level of the current word formation training task is one level higher than that of the previous word formation training task;

[0139] The difficulty level of the word formation training task is the same as the difficulty level of the corresponding word.

[0140] Optionally, when the training difficulty determination module is configured to determine that the difficulty level needs to be reduced according to the response results of each word formation training question in the previous word formation training task, it determines that the difficulty level of the current word formation training task maintains the current first-level difficulty level, but is one second-level difficulty level lower than that of the previous word formation training task; when it is determined that the difficulty level needs to be increased according to the response results of each word formation training question in the previous word formation training task, it determines that the difficulty level of the current word formation training task maintains the current first-level difficulty level, but is one second-level difficulty level higher than that of the previous word formation training task;

[0141] The first-level difficulty level of the word formation training task is the same as the difficulty level of the corresponding word;

[0142] The second-level difficulty level of the word formation training task is positively correlated with the number of candidate Chinese character data; alternatively, the second-level difficulty level of the word formation training task is related to whether the position of the target Chinese character data in the word is prompted.

[0143] In the embodiments of the present application, the question form of the word formation training question is: presenting the matching characters of the target word as the question stem, and presenting candidate Chinese characters including the target Chinese character, and requiring the respondent to select the target Chinese character that can form the target word with the matching characters from the candidate Chinese characters.

[0144] Among them, the position of the target Chinese character can be prompted in the question stem, for example, "? Ship", and the "?" prompts that the target Chinese character is on the left side of the matching characters; the position can also not be prompted in the question stem. Among them, the question with the position prompted has a lower difficulty level than the question without the position prompted.

[0145] Among them, the number of candidate Chinese characters will also determine the difficulty level of the question. The more the number of candidate Chinese characters, the higher the difficulty level of the question.

[0146] In the electronic implementation scheme, the target word data corresponding to the word formation training topic can be selected from the word table 2 or the word table 3, and the corresponding matching Chinese character data can be selected from the matching character table 2 or the matching character table 3, and a specified number of Chinese character data can be selected from the corresponding Chinese character data set as candidate Chinese character data, and the candidate Chinese character data includes the target Chinese character data. The selected matching Chinese character data is used to generate the question stem data, and the question stem data can specifically be a question stem display control. The selected candidate Chinese character data is used to generate the candidate item data, and the candidate item data can specifically be a candidate item display control. The target word data is marked as the target word data of the corresponding word formation training topic, and the target Chinese character data is marked as the target Chinese character data of the corresponding word formation training topic. Optionally, the prompt sound data of the matching Chinese character is also generated, and the prompt sound data can specifically be a sound control for playing the pronunciation of the matching Chinese character. Optionally, the prompt sound data of the target Chinese character is also generated, and the prompt sound data can specifically be a sound control for playing the pronunciation of the target Chinese character data.

[0147] When displaying word formation training questions, the question stem data can be displayed in the first display area of ​​the display screen, and the candidate item data can be displayed in the second display area of ​​the display screen. Optionally, the prompt sound data of the matching Chinese characters is displayed overlapping with the display area of ​​the matching Chinese characters in the question stem data, and the prompt sound data is higher than the display layer of the question stem data. Optionally, the prompt sound data of the candidate Chinese character data is displayed overlapping with the display area of ​​each candidate Chinese character data in the candidate item data, and the prompt sound data is higher than the display layer of the candidate item data.

[0148] The word formation training provided in the embodiment of the present application provides context clues through word settings, and at the same time, with the assistance of voice information, establishes or enhances the connection between character shape, voice and semantics, and helps children accurately distinguish and master similar Chinese characters. For Chinese characters that can already be accurately recognized, the vocabulary can be further expanded by forming words with different matching characters, thereby assisting and enhancing language and reading abilities.

[0149] In one implementation, there are 10 word-combination training questions in a word-combination training task, 1 point is awarded for each correct answer, and the player can move on to the next difficulty level if 6 correct answers are given to the word-combination training task.

[0150] Based on the same inventive concept, the present application embodiment also provides a word group training data generating device, such as Figure 4 As shown, including:

[0151] A Chinese character data set creation module is used to select Chinese character data from a basic Chinese character database according to the character difficulty level and similar character attributes of the Chinese character data, and create multiple Chinese character data sets using the selected Chinese character data, each Chinese character data set includes a character table difficulty level and a group of similar Chinese character data, there are a total of P character table difficulty levels, each character table difficulty level corresponds to at least one Chinese character data set, and the character table difficulty level of each Chinese character data set is determined by the character difficulty level of the included Chinese character data; Chinese character data with the same similar character attributes belong to similar Chinese character data;

[0152] A matching word determination module is used to traverse the Chinese character data in each Chinese character data set, and for each Chinese character data in each Chinese character data set, determine the matching Chinese character data and corresponding word data that can form a word with the Chinese character data;

[0153] A word difficulty level determination module, used to determine the word difficulty level of each word data at least according to the word table difficulty level of the Chinese character data set where the corresponding Chinese character data is located;

[0154] A matching Chinese character data set creation module, used to create a matching Chinese character data set corresponding to each Chinese character data set, wherein the matching Chinese character data set includes matching Chinese character data for each Chinese character data in the corresponding Chinese character data set;

[0155] A word data set creation module, used to create a word data set corresponding to each Chinese character data set, wherein the word data set includes word data corresponding to each Chinese character data in the corresponding Chinese character data set;

[0156] Among them, each word formation training question corresponds to a target Chinese character data, matching data for word formation with the target Chinese character data and the formed target word data, all or part of the Chinese character data in the Chinese character data set where the target Chinese character data is located serves as candidate Chinese character data for the corresponding word formation training question, and the word difficulty level of the target word data is positively correlated with the difficulty level of the corresponding word formation training question.

[0157] Optionally, the similar Chinese character data include Chinese character data with similar glyphs, and each Chinese character data in the same Chinese character data set belongs to the same orthographic family, and the similar character attributes are used to indicate the orthographic family to which the Chinese character data belongs; or, the similar Chinese character data include semantically related Chinese character data, and each Chinese character data in the same Chinese character data set belongs to the same level in a semantic hierarchical network model, and the similar character attributes are used to indicate the level of the Chinese character data in the semantic hierarchical network model; or, the similar Chinese character data include phonetically similar Chinese character data, and each Chinese character data in the same Chinese character data set belongs to the same homophonic family, and the similar character attributes are used to indicate the homophonic family to which the Chinese character data belongs.

[0158] Optionally, if the similar Chinese character data include phonetically similar Chinese character data, the Chinese character data set creation module is further used to: determine the character table difficulty level of the Chinese character data set according to the character difficulty level of each Chinese character data in the Chinese character data set and the syllable difficulty level of the corresponding homophone family, and the syllable difficulty level of the homophone family is positively correlated with the number of Chinese characters included in the homophone family; or, if the similar Chinese character data include phonetically similar Chinese character data, the Chinese character data set creation module selects Chinese character data from a basic Chinese character database according to the character difficulty level and similar character attributes of the Chinese character data, and is used to: select Chinese character data from a basic Chinese character database according to the character difficulty level, similar character attributes and corresponding syllable difficulty level of the homophone family of the Chinese character data.

[0159] Optionally, the character difficulty level distribution of the Chinese character data included in each Chinese character data set satisfies a preset character difficulty level distribution rule.

[0160] Optionally, Chinese character data sets with the same character table difficulty level correspond to the same character difficulty level distribution pattern.

[0161] Optionally, the number of Chinese character data included in each Chinese character data set meets a preset quantity requirement.

[0162] Optionally, the pronunciation of each Chinese character data in the corresponding word data is unique, and / or each matching Chinese character data can only be used to form a word with the corresponding Chinese character data in the Chinese character data set to which the corresponding Chinese character data belongs.

[0163] Optionally, the word difficulty level determination module is used to determine the word difficulty level of the word data according to the character table difficulty level of the Chinese character data set in which the corresponding Chinese character data is located and a preset word difficulty level.

[0164] Optionally, it also includes a training topic generation module for generating word combination training topics, wherein the word combination training topics include topic stem data and candidate item data; the topic stem data includes matching character data that constitutes target word data with target Chinese character data, and the candidate item data includes candidate Chinese character data.

[0165] Optionally, the word formation training topic also includes target word prompt data and / or matching word prompt data.

[0166] Based on the same inventive concept, the present application also provides a word group training device, such as Figure 5 As shown, including:

[0167] A training difficulty determination module is used to determine the difficulty level of the current word formation training task;

[0168] The training task acquisition module is used to acquire a group of word formation training questions with the difficulty level of the current word formation training task, each of the group of word formation training questions corresponds to a target Chinese character data, matching data of the word formation of the target Chinese character data and the formed target word data, all or part of the Chinese character data in the Chinese character data set where the target Chinese character data is located is used as candidate Chinese character data for the corresponding word formation training question, and the difficulty level of the target word data is positively correlated with the difficulty level of the current word formation training task; each Chinese character data set includes a character table difficulty level and a group of similar Chinese character data , there are P word table difficulty levels, each word table difficulty level corresponds to at least one Chinese character data set, and the word table difficulty level of each Chinese character data set is determined by the word difficulty level of the included Chinese character data; Chinese character data with the same similar character attributes belong to similar Chinese character data; the word difficulty level of the target word data is determined at least according to the word table difficulty level of the Chinese character data set corresponding to the target Chinese character data; each word group training question includes question stem data and candidate item data; the question stem data includes matching character data that constitute the target word data with the target Chinese character data, and the candidate item data includes candidate Chinese character data;

[0169] The training task push module is used to display each word group training topic in the current word group training task;

[0170] The training result feedback module is used to obtain the response result of each word group training question in the current word group training task, compare the response result with the target word data, and determine the training score of the corresponding word group training question according to the comparison result.

[0171] Optionally, the training difficulty determination module is used to determine the difficulty level of the current word formation training task according to the training scores of each word formation training question in the previous word formation training task.

[0172] Optionally, the training difficulty determination module is used to:

[0173] According to the training scores of each word formation training question in the previous word formation training task, the position of the target Chinese character data in the target word data is determined in each word formation training question of the current word formation training task, so that the difficulty level is lower than that of the previous word formation training task; or,

[0174] According to the training scores of each word formation training question in the previous word formation training task, it is determined that the position of the target Chinese character data in the target word data is not prompted in each word formation training question of the current word formation training task, so that the difficulty level is higher than that of the previous word formation training task.

[0175] Optionally, the training difficulty determination module is used to:

[0176] Deciding to lower the difficulty level of the current word formation training task according to the training scores of each word formation training question in the previous word formation training task, so that the difficulty level is lower than that of the previous word formation training task; or,

[0177] Determine to increase the difficulty level of the current word formation training task according to the training scores of each word formation training question in the previous word formation training task, so that the difficulty level of the current word formation training task is higher than that of the previous word formation training task; or,

[0178] Determine the difficulty level of the current word formation training task based on the training scores of each word formation training question in the previous word formation training task;

[0179] The difficulty level of the word formation training task was the same as the word difficulty level of the corresponding target word.

[0180] Optionally, the training difficulty determination module is used to:

[0181] Deciding to reduce the number of candidate Chinese character data for each word formation training question in the current word formation training task according to the training scores of each word formation training question in the previous word formation training task, so that the difficulty level is lower than that of the previous word formation training task; or,

[0182] The difficulty level of the current word formation training task is increased according to the training scores of each word formation training question in the previous word formation training task, so that the difficulty level of the current word formation training task is higher than that of the previous word formation training task.

[0183] Optionally, the training task acquisition module is used to:

[0184] Selecting a group of word data having a word difficulty level corresponding to the difficulty level of the current word combination training task from at least one word data set, and marking each word data in the group of word data as target word data of a word combination training task;

[0185] Selecting matching word data corresponding to each target word data from at least one matching word database, and using the matching word data to obtain stem data of the word combination training question;

[0186] Select candidate Chinese character data including the target Chinese character data from the Chinese character data set corresponding to each target word data, use the candidate Chinese character data to obtain candidate item data for the word formation training question, and mark the target Chinese character data as the target Chinese character data, and mark the remaining candidate Chinese character data as interference Chinese character data.

[0187] The specific functional implementation of each of the above modules can refer to the word group training data generation method or word group training method provided in the embodiment of the present application, which will not be repeated here. Each module can be a virtual functional module or an actual hardware module.

[0188] Based on the same inventive concept, an embodiment of the present application also provides an electronic device, including a memory and a processor, wherein the memory stores a computer program; the processor executes the computer program stored in the memory to implement the steps in the word formation training data generation method described in any of the above embodiments; or, the processor executes the computer program stored in the memory to implement the steps in the word formation training method described in any of the above embodiments.

[0189] Based on the same inventive concept, an embodiment of the present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps in the word combination training data generation method described in any of the above embodiments are implemented; or, when the computer program is executed by a processor, the steps in the word combination training method described in any of the above embodiments are implemented.

[0190] Based on the same inventive concept, an embodiment of the present application also provides a computer program, including computer instructions, which, when executed by a processor, implement the steps in the word group training data generation method described in any of the above embodiments; or, when executed by a processor, the computer instructions implement the steps in the word group training method described in any of the above embodiments.

[0191] The basic unit of the Chinese writing system is the Chinese character, and most Chinese characters are a combination of shape, syllable and morpheme. Therefore, learning and mastering the Chinese shape, sound and meaning are of great significance for children's language and reading development. The purpose of the embodiments of the present application is to enable children to establish and strengthen the connection between the shape, sound and meaning of Chinese characters during the learning process; gradually learn to distinguish the following types of Chinese characters: (1) visually similar Chinese characters; (2) semantically related Chinese characters; (3) phonetically similar Chinese characters; (4) different meanings of the same Chinese characters in different contexts, and ultimately promote the learning of all Chinese characters. The embodiments of the present application can be applied to: (1) intervention for children with a tendency to lag behind in language development, (2) intervention for children at risk of dyslexia, and (3) promotion and improvement of language and reading development of non-risk ordinary children.

[0192] The solutions in the embodiments of the present application can be implemented using various computer languages, for example, the object-oriented programming language Java and the interpreted scripting language JavaScript.

[0193] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt 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 codes.

[0194] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes 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 processor, 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.

[0195] 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.

[0196] 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. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0197] Although the preferred embodiments of the present application 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 falling within the scope of the present application.

[0198] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A device for generating word group training data, characterized in that: include: A Chinese character data set creation module is used to select Chinese character data from a basic Chinese character database according to the character difficulty level and similar character attributes of the Chinese character data, and create multiple Chinese character data sets using the selected Chinese character data, each Chinese character data set includes a character table difficulty level and a group of similar Chinese character data, there are a total of P character table difficulty levels, each character table difficulty level corresponds to at least one Chinese character data set, and the character table difficulty level of each Chinese character data set is determined by the character difficulty level of the included Chinese character data; Chinese character data with the same similar character attributes belong to similar Chinese character data; A matching word determination module is used to traverse the Chinese character data in each Chinese character data set, and for each Chinese character data in each Chinese character data set, determine the matching Chinese character data and corresponding word data that can form a word with the Chinese character data; A word difficulty level determination module, used to construct a cross matrix according to the word table difficulty level of the Chinese character data set corresponding to the Chinese character data and the preset word difficulty level, and determine the word difficulty level of the word data based on the cross matrix; A matching Chinese character data set creation module, used to create a matching Chinese character data set corresponding to each Chinese character data set, wherein the matching Chinese character data set includes matching Chinese character data for each Chinese character data in the corresponding Chinese character data set; A word data set creation module, used to create a word data set corresponding to each Chinese character data set, wherein the word data set includes word data corresponding to each Chinese character data in the corresponding Chinese character data set; Among them, each word formation training question corresponds to a target Chinese character data, matching data for word formation with the target Chinese character data and the formed target word data, all or part of the Chinese character data in the Chinese character data set where the target Chinese character data is located serves as candidate Chinese character data for the corresponding word formation training question, and the word difficulty level of the target word data is positively correlated with the difficulty level of the corresponding word formation training question.

2. The word group training data generating device according to claim 1, characterized in that: The similar Chinese character data includes Chinese character data with similar glyphs, each Chinese character data in the same Chinese character data set belongs to the same orthographic family, and the similar character attribute is used to indicate the orthographic family to which the Chinese character data belongs; or, The similar Chinese character data includes semantically related Chinese character data, each Chinese character data in the same Chinese character data set belongs to the same level in the semantic hierarchical network model, and the similar character attribute is used to indicate the level of the Chinese character data in the semantic hierarchical network model; or, The similar Chinese character data include phonetically similar Chinese character data. Each Chinese character data in the same Chinese character data set belongs to the same homophone family. The similar character attribute is used to indicate the homophone family to which the Chinese character data belongs.

3. The word group training data generating device according to claim 2, characterized in that: If the similar Chinese character data includes phonetically similar Chinese character data, the Chinese character data set creation module is further used to: determine the character table difficulty level of the Chinese character data set according to the character difficulty level of each Chinese character data in the Chinese character data set and the syllable difficulty level of the corresponding homophone family, wherein the syllable difficulty level of the homophone family is positively correlated with the number of Chinese characters included in the homophone family; or If the similar Chinese character data includes phonetically similar Chinese character data, the Chinese character data set creation module selects Chinese character data from a basic Chinese character database according to the character difficulty level and similar character attributes of the Chinese character data, and is used to: select Chinese character data from a basic Chinese character database according to the character difficulty level, similar character attributes and syllable difficulty level of the corresponding homophone family of the Chinese character data.

4. The word group training data generating device according to any one of claims 1 to 3, characterized in that: The character difficulty level distribution of the Chinese character data included in each Chinese character data set meets a preset character difficulty level distribution rule.

5. The word group training data generating device according to claim 4, characterized in that: Chinese character data sets with the same character table difficulty level correspond to the same character difficulty level distribution pattern.

6. The word group training data generating device according to any one of claims 1 to 3, characterized in that: The quantity of Chinese character data included in each Chinese character data set meets the preset quantity requirement.

7. The word group training data generating device according to any one of claims 1 to 3, characterized in that: The pronunciation of each Chinese character data in the corresponding word data is unique, and / or each matching Chinese character data is only combined with the corresponding Chinese character data in the Chinese character data set to which the corresponding Chinese character data belongs.

8. The word group training data generating device according to any one of claims 1 to 3, characterized in that: It also includes a training topic generation module for generating word combination training topics, wherein the word combination training topics include topic stem data and candidate item data; the topic stem data includes matching character data that constitutes target word data with target Chinese character data, and the candidate item data includes candidate Chinese character data.

9. The word group training data generating device according to claim 8, characterized in that: The word formation training topic also includes target word prompt sound data and / or matching word prompt sound data.

10. A word formation training device, characterized in that: include: A training difficulty determination module is used to determine the difficulty level of the current word formation training task; A training task acquisition module is used to acquire a group of word-combination training questions with a difficulty level of the current word-combination training task, wherein each word-combination training question in the group of word-combination training questions corresponds to a target Chinese character data, matching data of the word-combination of the target Chinese character data and the target word data formed, and all or part of the Chinese character data in the Chinese character data set where the target Chinese character data is located is used as candidate Chinese character data of the corresponding word-combination training question, and the difficulty level of the target word data is positively correlated with the difficulty level of the current word-combination training task; each Chinese character data set includes a character table difficulty level and a group of similar Chinese character data, and there are a total of P character table difficulty levels, each character table difficulty level corresponds to at least one Chinese character data set, and the character table difficulty level of each Chinese character data set is determined by the character difficulty level of the included Chinese character data; Chinese character data with the same similar character attribute belong to similar Chinese character data; the word difficulty level of the target word data is determined based on a cross matrix, and the cross matrix is ​​constructed according to the word table difficulty level of the Chinese character data set where the corresponding Chinese character data is located and the preset word difficulty level; each word combination training question includes question stem data and candidate item data; the question stem data includes matching character data that constitute the target word data with the target Chinese character data, and the candidate item data includes candidate Chinese character data; The training task push module is used to display each word group training topic in the current word group training task; The training result feedback module is used to obtain the response result of each word group training question in the current word group training task, compare the response result with the target word data, and determine the training score of the corresponding word group training question according to the comparison result.

11. The word formation training device according to claim 10, characterized in that: The training difficulty determination module is used to determine the difficulty level of the current word formation training task according to the training scores of each word formation training question in the previous word formation training task.

12. The word formation training device according to claim 11, characterized in that: The training difficulty determination module is used for: According to the training scores of each word formation training question in the previous word formation training task, the position of the target Chinese character data in the target word data is determined in each word formation training question of the current word formation training task, so that the difficulty level is lower than that of the previous word formation training task; or, According to the training scores of each word formation training question in the previous word formation training task, it is determined that the position of the target Chinese character data in the target word data is not prompted in each word formation training question of the current word formation training task, so that the difficulty level is higher than that of the previous word formation training task.

13. The word formation training device according to claim 11, characterized in that: The training difficulty determination module is used for: Determining to reduce the difficulty level of the current word formation training task according to the training scores of each word formation training question in the previous word formation training task, so that the difficulty level is lower than that of the previous word formation training task; or, Determining to increase the difficulty level of the current word formation training task according to the training scores of each word formation training question in the previous word formation training task, so that the difficulty level of the current word formation training task is increased compared with the previous word formation training task; or, Determine the difficulty level of the current word formation training task based on the training scores of each word formation training question in the previous word formation training task; The difficulty level of the word formation training task was the same as the word difficulty level of the corresponding target word.

14. The word formation training device according to claim 11, characterized in that: The training difficulty determination module is used for: According to the training scores of each word group training question in the previous word group training task, the number of candidate Chinese character data of each word group training question in the current word group training task is reduced so that the difficulty level is lower than that of the previous word group training task; or, The difficulty level of the current word formation training task is increased according to the training scores of each word formation training question in the previous word formation training task, so that the difficulty level of the current word formation training task is higher than that of the previous word formation training task.

15. The word formation training device according to claim 10, characterized in that: The training task acquisition module is used to: Selecting a group of word data having a word difficulty level corresponding to the difficulty level of the current word combination training task from at least one word data set, and marking each word data in the group of word data as target word data of a word combination training task; Selecting matching word data corresponding to each target word data from at least one matching word database, and using the matching word data to obtain stem data of the word combination training question; Select candidate Chinese character data including the target Chinese character data from the Chinese character data set corresponding to each target word data, use the candidate Chinese character data to obtain candidate item data for the word formation training question, and mark the target Chinese character data as the target Chinese character data, and mark the remaining candidate Chinese character data as interference Chinese character data.

16. A method for generating word group training data, characterized in that: include: Selecting Chinese character data from a basic Chinese character database according to the character difficulty level and similar character attributes of the Chinese character data, creating multiple Chinese character data sets using the selected Chinese character data, each Chinese character data set including a character table difficulty level and a group of similar Chinese character data, there are a total of P character table difficulty levels, each character table difficulty level corresponds to at least one Chinese character data set, and the character table difficulty level of each Chinese character data set is determined by the character difficulty level of the included Chinese character data; Chinese character data with the same similar character attributes belong to similar Chinese character data; Traversing the Chinese character data in each Chinese character data set, and for each Chinese character data in each Chinese character data set, determining matching Chinese character data and corresponding word data that can form a word with the Chinese character data; Constructing a cross matrix according to the character table difficulty level of the Chinese character data set corresponding to the Chinese character data and the preset word difficulty level, and determining the word difficulty level of the word data based on the cross matrix; Creating a matching Chinese character data set corresponding to each Chinese character data set, wherein the matching Chinese character data set includes matching Chinese character data for each Chinese character data in the corresponding Chinese character data set; Creating a word data set corresponding to each Chinese character data set, wherein the word data set includes word data corresponding to each Chinese character data in the corresponding Chinese character data set; Among them, each word formation training question corresponds to a target Chinese character data, matching data for word formation with the target Chinese character data and the formed target word data, all or part of the Chinese character data in the Chinese character data set where the target Chinese character data is located serves as candidate Chinese character data for the corresponding word formation training question, and the word difficulty level of the target word data is positively correlated with the difficulty level of the corresponding word formation training question.

17. The method for generating word group training data according to claim 16, characterized in that: The similar Chinese character data includes Chinese character data with similar glyphs, each Chinese character data in the same Chinese character data set belongs to the same orthographic family, and the similar character attribute is used to indicate the orthographic family to which the Chinese character data belongs; or, The similar Chinese character data includes semantically related Chinese character data, each Chinese character data in the same Chinese character data set belongs to the same level in the semantic hierarchical network model, and the similar character attribute is used to indicate the level of the Chinese character data in the semantic hierarchical network model; or, The similar Chinese character data include phonetically similar Chinese character data. Each Chinese character data in the same Chinese character data set belongs to the same homophone family. The similar character attribute is used to indicate the homophone family to which the Chinese character data belongs.

18. The method for generating word group training data according to claim 17, characterized in that: If the similar Chinese character data includes phonetically similar Chinese character data, the method further includes: determining a character table difficulty level of the Chinese character data set according to a character difficulty level of each Chinese character data in the Chinese character data set and a syllable difficulty level of a corresponding homophone family, wherein the syllable difficulty level of the homophone family is positively correlated with the number of Chinese characters included in the homophone family; or If the similar Chinese character data includes phonetically similar Chinese character data, selecting the Chinese character data from the basic Chinese character database according to the character difficulty level of the Chinese character data and the similar character attributes includes: selecting the Chinese character data from the basic Chinese character database according to the character difficulty level of the Chinese character data, the similar character attributes and the syllable difficulty level of the corresponding homophone family.

19. The method for generating word group training data according to any one of claims 16 to 18, characterized in that: The character difficulty level distribution of the Chinese character data included in each Chinese character data set meets a preset character difficulty level distribution rule.

20. The method for generating word group training data according to claim 19, characterized in that: Chinese character data sets with the same character table difficulty level correspond to the same character difficulty level distribution pattern.

21. The method for generating word group training data according to any one of claims 16 to 18, characterized in that: The quantity of Chinese character data included in each Chinese character data set meets the preset quantity requirement.

22. The method for generating word group training data according to any one of claims 16 to 18, characterized in that: The pronunciation of each Chinese character data in the corresponding word data is unique, and / or each matching Chinese character data can only be combined with the corresponding Chinese character data in the Chinese character data set to which the corresponding Chinese character data belongs.

23. The method for generating word group training data according to any one of claims 16 to 18, characterized in that: Also includes: Generate a word formation training topic, the word formation training topic includes question stem data and candidate item data; the question stem data includes matching character data that constitutes target word data with target Chinese character data, and the candidate item data includes candidate Chinese character data.

24. A word formation training method, characterized in that: include: Determine the difficulty level of the current word formation training task; A group of word formation training questions with the difficulty level of the current word formation training task is obtained, each of the group of word formation training questions corresponds to a target Chinese character data, matching data of the word formation of the target Chinese character data and the formed target word data, all or part of the Chinese character data in the Chinese character data set where the target Chinese character data is located is used as candidate Chinese character data of the corresponding word formation training question, and the difficulty level of the target word data is positively correlated with the difficulty level of the current word formation training task; each Chinese character data set includes a character table difficulty level and a group of similar Chinese character data, there are a total of P character table difficulty levels, each character table difficulty level corresponds to at least one Chinese character data set, and the character table difficulty level of each Chinese character data set is determined by the character difficulty level of the included Chinese character data; Chinese character data with the same similar character attribute belong to similar Chinese character data; the word difficulty level of the target word data is determined based on a cross matrix, and the cross matrix is ​​constructed according to the word table difficulty level of the Chinese character data set where the corresponding Chinese character data is located and the preset word difficulty level; each word combination training question includes question stem data and candidate item data; the question stem data includes matching character data that constitute the target word data with the target Chinese character data, and the candidate item data includes candidate Chinese character data; Display each word group training question in the current word group training task respectively; The response result of each word combination training question in the current word combination training task is obtained, the response result is compared with the target word data, and the training score of the corresponding word combination training question is determined according to the comparison result.

25. The word group training method according to claim 24, characterized in that: Determining the difficulty level of the current word formation training task includes: The difficulty level of the current word formation training task is determined according to the training scores of each word formation training question in the previous word formation training task.

26. The word group training method according to claim 25, characterized in that: The step of determining the difficulty level of the current word formation training task according to the training scores of each word formation training question in the previous word formation training task includes: According to the training scores of each word formation training question in the previous word formation training task, the position of the target Chinese character data in the target word data is determined in each word formation training question of the current word formation training task, so that the difficulty level is lower than that of the previous word formation training task; or, According to the training scores of each word formation training question in the previous word formation training task, it is determined that the position of the target Chinese character data in the target word data is not prompted in each word formation training question of the current word formation training task, so that the difficulty level is higher than that of the previous word formation training task.

27. The word group training method according to claim 25, characterized in that: The step of determining the difficulty level of the current word formation training task according to the training scores of each word formation training question in the previous word formation training task includes: Deciding to lower the difficulty level of the current word formation training task according to the training scores of each word formation training question in the previous word formation training task, so that the difficulty level is lower than that of the previous word formation training task; or, Determine to increase the difficulty level of the current word formation training task according to the training scores of each word formation training question in the previous word formation training task, so that the difficulty level of the current word formation training task is higher than that of the previous word formation training task; or, Determine the difficulty level of the current word formation training task based on the training scores of each word formation training question in the previous word formation training task; The difficulty level of the word formation training task was the same as the word difficulty level of the corresponding target word.

28. The word group training method according to claim 25, characterized in that: The step of determining the difficulty level of the current word formation training task according to the training scores of each word formation training question in the previous word formation training task includes: Deciding to reduce the number of candidate Chinese character data for each word formation training question in the current word formation training task according to the training scores of each word formation training question in the previous word formation training task, so that the difficulty level is lower than that of the previous word formation training task; or, The difficulty level of the current word formation training task is increased according to the training scores of each word formation training question in the previous word formation training task, so that the difficulty level of the current word formation training task is higher than that of the previous word formation training task.

29. The word group training method according to claim 24, characterized in that: The step of obtaining a group of word formation training questions having the difficulty level of the current word formation training task includes: Selecting a group of word data having a word difficulty level corresponding to the difficulty level of the current word combination training task from at least one word data set, and marking each word data in the group of word data as target word data of a word combination training task; Selecting matching word data corresponding to each target word data from at least one matching word database, and using the matching word data to obtain stem data of the word combination training question; Select candidate Chinese character data including the target Chinese character data from the Chinese character data set corresponding to each target word data, use the candidate Chinese character data to obtain candidate item data for the word formation training question, and mark the target Chinese character data as the target Chinese character data, and mark the remaining candidate Chinese character data as interference Chinese character data.

30. An electronic device, comprising a memory and a processor, characterized in that: The memory stores a computer program; The processor executes the computer program stored in the memory to implement the steps in the word group training data generation method as described in any one of claims 16 to 23; or, the processor executes the computer program stored in the memory to implement the steps in the word group training method as described in any one of claims 24 to 29.

31. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps in the method for generating word group training data as described in any one of claims 16 to 23 are implemented; or, when the computer program is executed by a processor, the steps in the method for generating word group training data as described in any one of claims 24 to 29 are implemented.

32. A computer program comprising computer instructions, characterized in that When the computer instructions are executed by the processor, the steps in the method for generating word group training data as described in any one of claims 16 to 23 are implemented; or, when the computer instructions are executed by the processor, the steps in the method for generating word group training data as described in any one of claims 24 to 29 are implemented.

Images