Method and device for improving word learning efficiency of primary and secondary school students

Abstract

The application relates to a method and device for improving the word learning efficiency of primary and secondary school students, and relates to the technical field of recommendation learning, which comprises the following steps: S1, defining a feature vector of a word and a word list of learning materials; S2, establishing the feature vector of all words in an English learning textbook, initializing a word recommendation value dictionary and performing learning material warehousing; S3, dynamically updating the feature vector of the word and the recommendation value dictionary according to the performance of students in different learning types in the learning process; and S4, screening out candidate learning materials, calculating the recommendation value of the candidate learning materials through the word dictionary of the candidate learning materials and the word recommendation value dictionary, and pushing the learning materials with the highest recommendation value to the students; the application solves the problems that traditional word learning lacks personalized dynamic recommendation and is difficult to adapt to multimodal learning scenes and individual memory decay rules, realizes long-term learning effect visualized closed-loop optimization through the combination of dynamic feature engineering and multi-scene recommendation, and effectively improves the word learning efficiency.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of recommendation learning, in particular to a method and device for improving the word learning efficiency of primary and secondary school students. BACKGROUND

[0002] An important link for primary and secondary school students to learn English is to memorize words. After mastering words, a solid foundation is laid for oral English, dictation, listening, reading and writing. Then, students often spend a lot of time on repeatedly memorizing words that they have already mastered. Relatively speaking, for words that are not well mastered, the learning content may not involve enough of these words, and not enough time is spent on learning them.

[0003] At present, it is very common for students to purchase educational electronic products such as student tablets to learn English. In the past, educational electronic products mainly judged the mastery of words by word tests, and recommended word learning content based on this. The recommended way is often to list the words that have not been mastered to relearn them, without identifying the words to be strengthened from the usual oral English, dictation, listening, reading and writing, resulting in inaccurate and comprehensive mastery of students' words, and it is difficult to achieve accurate push of oral English, dictation, listening, reading and writing materials.

[0004] Therefore, there is an urgent need for a method that can fully consider the difficulty, importance, frequency of occurrence, mastery level and forgetting law of words and other factors, provide personalized learning recommendations for students, meet the learning needs of different students, and effectively improve the word learning efficiency of primary and secondary school students. SUMMARY

[0005] In order to overcome the deficiencies in the background art, the present application provides a method and device for improving the word learning efficiency of primary and secondary school students.

[0006] To achieve the above-mentioned application purposes, the present application adopts the following technical solutions:

[0007] In a first aspect, the present application provides a method for improving the word learning efficiency of primary and secondary school students, comprising the following steps:

[0008] S1, defining a feature vector of a word and a word list of learning materials; the feature vector includes the number of phonetic units of the word, the importance of the word, the inverse of the cumulative number of occurrences of the word, the inverse of the mastery level at the last learning, and the time stamp of the last learning;

[0009] S2, establishing the feature vector of all words in the English learning materials according to the outline requirements and the content of the teaching materials, then calculating the word recommendation value according to the feature vector, initializing the word recommendation value dictionary and performing learning material warehousing; the learning materials contain the corresponding word dictionary;

[0010] S3, dynamically updating the word feature vector and the recommended value dictionary according to the performance of the student in different learning types in the learning process; the learning types include word learning, oral, dictation, listening, reading and writing;

[0011] S4, filtering out the candidate learning materials according to the grade information and the learning type, calculating the recommended value of the candidate learning materials through the word dictionary of the candidate learning materials and the word recommended value dictionary, and pushing the learning material with the highest recommended value of the candidate learning materials to the student.

[0012] Specifically, the feature vector in step S2 calculates the word recommended value WR through formula (1), and the formula (1) is as follows:

[0013] WR=W1*v1+W2*v2+W3*v3+W4*v4+W5*v5’ (1)

[0014] Wherein, v1 is the number of phonemes of the word, W1 is the weight of the number of phonemes of the word; v2 is the word importance, W2 is the word importance weight; v3 is the reciprocal of the cumulative number of occurrences of the word, W3 is the reciprocal weight of the cumulative number of occurrences of the word; v4 is the reciprocal of the degree of mastery of the last learning, W4 is the reciprocal weight of the degree of mastery of the last learning; v5' is the forgetting coefficient obtained by converting the last learning time stamp v5, W5 is the forgetting coefficient weight;

[0015] Specifically, the calculation formula of the forgetting coefficient is as shown in formula (2):

[0016] Fc=1-R (2)

[0017] Wherein, Fc is the forgetting coefficient; R is the memory retention rate of Ebbinghaus, that is: R=e^(-t / S), wherein e is the base number of natural logarithm, t is the forgetting time, unit: day, t=(ts-v5) / 86400; S is the relative memory strength; ts is the current time stamp, v5 is the last learning time stamp in the feature vector.

[0018] Specifically, the process of step S2 includes:

[0019] (1) generating a unique identifier material_id of the material by using self-increment ID, UUID or hash algorithm;

[0020] (2) integrating the material content, word dictionary, grade, learning type and ID into a structured object;

[0021] (3) saving the structured object into the database through the database for subsequent use.

[0022] Specifically, step S3 specifically includes:

[0023] The reciprocal of the cumulative occurrence number of the word, the reciprocal of the mastery level at the last learning, and the time stamp of the last learning of the corresponding feature vector are updated during the word learning, word learning follow-up reading and spelling process, and the word recommendation value is recalculated, and then the word recommendation value dictionary is updated;

[0024] The reciprocal of the cumulative occurrence number of the word is obtained from the reciprocal of the reciprocal of the cumulative occurrence number of the word in the word feature vector, and the latest reciprocal of the cumulative occurrence number of the word is obtained by taking the reciprocal of the cumulative occurrence number of the word after adding 1.

[0025] The time stamp of the last learning is updated to the time stamp when the current word is learned;

[0026] The latest mastery level reciprocal v4' of the word is calculated by formula (5)-(6) through the word follow-up reading accuracy score Fl, the spelling accuracy score Sp and the time efficiency score Te, and then the reciprocal of the mastery level at the last learning of the word feature vector is replaced; finally, the word recommendation value WR of the word is recalculated according to the updated word feature vector by using the calculation formula of the word recommendation value, and then the word recommendation value dictionary is updated; formula (5)-(6) are as follows:

[0027] Mn=[Fl*a+Sp*b+Te*c] (5)

[0028] Wherein, Mn is the current mastery level of the word, a is the follow-up reading accuracy score weight, b is the spelling accuracy score weight, and c is the time efficiency score weight; a+b+c=1;

[0029] The calculation formula of the latest mastery level reciprocal v4' is shown in formula (6):

[0030] v4'=R*v4+(1-R)*(1 / Mn) (6)

[0031] Wherein, v4' is the latest mastery level reciprocal, v4 is the mastery level reciprocal at the last learning in the word feature vector, R is the Ebbinghaus memory retention rate, i.e. R=e^(-t / S); Wherein e is the base number of natural logarithm, t is the forgetting time, unit is day, t=(ts-v5) / 86400; S is the relative memory strength, the value is 1.84; ts is the current time stamp, and v5 is the time stamp of the last learning in the feature vector.

[0032] Specifically, the word follow-up reading accuracy score Fl is obtained by scoring the voice of the follow-up reading word through the third-party voice recognition technology;

[0033] The spelling accuracy score Sp is determined according to formula (3):

[0034] Sp = [(correctNum / totalNum) * 100] (3)

[0035] Wherein, correctNum is the number of correct letters, totalNum is the total number of letters in a word, and [] is the rounding symbol; the time efficiency score Te is determined according to the time for spelling a correct word, as shown in formula (4);

[0036] Te = Min[(T / t)*100,100] (4)

[0037] Wherein, Te is the time efficiency score, T = n*T1, T1 is the experience time length for inputting an English letter on an electronic device, in ms, n represents the number of letters in a word, and t is the time length actually spent by the user for inputting a word, in ms.

[0038] Specifically, step S3 further comprises:

[0039] Oral learning, the pronunciation score of each word in the read sentence is recognized according to the speech recognition technology, the current mastery degree of each word is calculated according to the pronunciation score of each word, the inverse of the latest mastery degree of the word is calculated according to formula (6), and the inverse of the cumulative number of times of the word, the inverse of the mastery degree at the last learning, and the time stamp of the last learning of the corresponding feature vector are updated, the word recommendation value is recalculated, and then the word recommendation value dictionary is updated.

[0040] Specifically, step S3 further comprises:

[0041] Listening and writing learning, different current mastery degrees of words are determined according to the spelling accuracy score of the word, the inverse of the latest mastery degree of the word is calculated according to formula (6) according to the current mastery degree of the word, then the inverse of the cumulative number of times of the word, the inverse of the mastery degree at the last learning, and the time stamp of the last learning of the corresponding feature vector are updated, the word recommendation value is recalculated, and then the word recommendation value dictionary is updated;

[0042] When the spelling of the word is completely correct, the time efficiency score Te is calculated according to formula (4), and is taken as the current mastery degree Mn of the word, that is, Mn = Te;

[0043] When the spelling of the word is not completely correct, the current mastery degree Mn of the word is calculated according to formula (7):

[0044] Mn = U1*Sp+ (1-U1)*Te (7)

[0045] Wherein, U1 is an experience value, which is a floating point number between 0 and 1.

[0046] Specifically, step S3 further comprises:

[0047] For writing learning, the reciprocal of the mastery degree at the last learning time of the word is calculated when the word in the writing content is in the word recommendation value dictionary and the spelling of the word is correct, then the reciprocal of the word cumulative occurrence frequency of the corresponding feature vector, the reciprocal of the mastery degree at the last learning time and the time stamp of the last learning are updated, and the word recommendation value is recalculated, and then the word recommendation value dictionary is updated;

[0048] When the writing is completed, all words are obtained according to the writing content, and all words are traversed: if the word is in the word recommendation value dictionary, the calculation time efficiency score Te is calculated by formula (4) according to the time length spent by the word input, and is taken as the current mastery degree Mn of the word; The current mastery degree Mn of the word obtained by calculation is used to calculate the reciprocal v4' of the latest mastery degree according to formula (6), and then the reciprocal of the latest mastery degree is used to replace the reciprocal of the mastery degree at the last learning time of the word feature vector; Finally, the word recommendation value of the word is recalculated according to the updated word feature vector by using the calculation formula of the word recommendation value, and then the word recommendation value dictionary is updated;

[0049] Specifically, step S3 further comprises:

[0050] For listening / reading, if the listening / reading answer is completely correct, all words in the word dictionary of the listening / reading material are traversed, and if the traversed word is in the recommendation value dictionary, the reciprocal of the word cumulative occurrence frequency of the corresponding feature vector of the word and the time stamp of the last learning are updated, and the current mastery degree Mn of the word is set to 100; Then the latest mastery degree reciprocal v4' of the word is calculated according to formula (6) through the current mastery degree Mn of the word;

[0051] If the listening / reading answer is not completely correct, all words in the word dictionary of the listening / reading material are traversed to find the n words with the highest word recommendation value in the word recommendation value dictionary as the words not understood, and the reciprocal of the word cumulative occurrence frequency of the corresponding feature vector of the words not understood and the time stamp of the last learning are updated; The value of n is determined according to the length of the word dictionary of the listening material; The reciprocal v4' of the latest mastery degree is calculated according to formula (8):

[0052] v4'=R1*R*v4+(1-R1)*(1-R)*(1 / Mn) (8)

[0053] Wherein, v4' is the reciprocal of the latest mastery degree, v4 is the reciprocal of the mastery degree at the last learning time in the word feature vector, R is the memory retention rate of Ebbinghaus, Mn is the current mastery degree of the word; The value of Mn is determined by multiplying the proportion of the final score of the listening to the total score by 100; R1 is the memory influence coefficient;

[0054] Then, the inverse of the latest mastery degree v4' replaces the inverse of the mastery degree at the last learning of the word feature vector; finally, the word recommendation value of the word is recalculated according to the updated word feature vector by using the calculation formula of the word recommendation value, and then the word recommendation value dictionary is updated.

[0055] Specifically, step S4 specifically includes the following steps:

[0056] S41, when recommending learning materials, first, according to the grade information and learning type of the student, the learning materials suitable for the age of the student are selected as the candidate learning materials;

[0057] S42, according to all the words in the word dictionary of the candidate learning materials, the word recommendation value dictionary is traversed, the m words with the highest word recommendation value are found out, and the material recommendation dictionary is generated;

[0058] S43, if the learning type is oral, dictation, listening, reading or writing, the total recommendation value of the learning materials is calculated according to the material recommendation dictionary and formula (9), and the candidate learning materials with the highest total recommendation value of the learning materials are pushed to the student;

[0059] ,

[0060] Wherein, MLR is the total recommendation value of the learning materials, is the number of times that the i-th word in the material recommendation dictionary accumulatively appears in the learning materials; is the word recommendation value of the i-th word in the material recommendation dictionary;

[0061] S44, if the learning type is word learning, the total recommendation value of the learning materials is calculated according to the material recommendation dictionary and formula (9), and the words in the word dictionary of the candidate learning materials with the highest total recommendation value of the learning materials are sorted according to their recommendation values in the word recommendation value dictionary from high to low and pushed to the student.

[0062] Specifically, W1+W2+W3+W4+Wn=1 in formula (1).

[0063] Specifically, W1 is 0.15; W2 is 0.35; W3 is 0.1; W4 is 0.25; and W5 is 0.15.

[0064] Specifically, the value of U1 in formula (7) is 0.75.

[0065] Specifically, the memory influence coefficient R1 in formula (8) is 0.85.

[0066] In a second aspect, the present application provides a device for improving the efficiency of word learning of primary and secondary school students, based on the method for improving the efficiency of word learning of primary and secondary school students described above, comprising the following units:

[0067] An initialization unit is configured to define a feature vector of a word and a word list of learning materials; the feature vector comprises the number of phonemes of the word, the importance of the word, the inverse of the cumulative number of occurrences of the word, the inverse of the mastery level at the last learning, and the timestamp of the last learning;

[0068] A construction unit is configured to establish the feature vector of all words in the English learning materials according to the outline requirements and the content of the teaching materials, then calculate the word recommendation value according to the feature vector, initialize the word recommendation value dictionary and perform learning material warehousing; the learning materials contain the corresponding word dictionary;

[0069] An updating unit is configured to dynamically update the feature vector of the word and the recommendation value dictionary according to the performance of the students in different learning types during the learning process; the learning types include word learning, oral English, dictation, listening, reading and writing;

[0070] A recommendation unit is configured to filter out the candidate learning materials according to the grade information and the learning type, calculate the recommendation value of the candidate learning materials through the word dictionary of the candidate learning materials and the word recommendation value dictionary, and push the learning materials with the highest recommendation value of the candidate learning materials to the students.

[0071] In a third aspect, the present application further provides an electronic device comprising a processor, a memory, a communication interface, and one or more programs stored in the memory and configured to be executed by the processor, the programs comprising instructions for performing the steps in the method described in the first aspect.

[0072] The present application provides a method and device for improving the efficiency of word learning of primary and secondary school students, comprising: S1, defining a feature vector of a word and a word list of learning materials; S2, establishing the feature vector of all words in the English learning materials according to the outline requirements and the content of the teaching materials, then calculating the word recommendation value according to the feature vector, initializing the word recommendation value dictionary and performing learning material warehousing; S3, dynamically updating the feature vector of the word and the recommendation value dictionary according to the performance of the students in different learning types during the learning process; S4, filtering out the candidate learning materials according to the grade information and the learning type, calculating the recommendation value of the candidate learning materials through the word dictionary of the candidate learning materials and the word recommendation value dictionary, and pushing the learning materials with the highest recommendation value of the candidate learning materials to the students;

[0073] The application solves the problems of low efficiency of traditional word learning, lack of personalized dynamic recommendation mechanism, and difficulty in adapting to multi-modal learning scenarios and individual memory decay law, and identifies words to be strengthened from daily word learning, oral English, dictation, listening, reading and writing, realizes long-term learning effect visual closed-loop optimization by combining dynamic feature engineering and multi-scene recommendation, and effectively improves the efficiency of word learning.

[0074] Further, the traditional word learning adopts fixed order or random repetition, without considering the dynamic changes of word difficulty and student mastery level, resulting in inefficient repetition or omission of key words. The embodiment quantifies the word learning priority through feature vectors (such as the number of phonemes, importance, and cumulative appearance frequency reciprocal), adjusts the recommendation value in combination with the dynamic performance of students, realizes accurate learning, and through the dynamic recommendation value dictionary, preferentially pushes the words with low student mastery, high importance and consistent with the current learning type, reduces invalid repetition and shortens the time to meet the standard; multi-dimensional feature vectors (such as timestamp decay memory curve and cumulative appearance frequency reciprocal to avoid "high-frequency word monopoly") replace subjective experience ordering, making the learning path more consistent with the cognitive law.

[0075] Further, the traditional method lacks real-time feedback mechanism for student learning behavior, and cannot dynamically adjust the learning strategy. The embodiment realizes continuous optimization of the learning path by dynamically updating the word feature vector (such as adjusting "last mastery level reciprocal" according to the dictation error rate) through step S3, and reversely optimizes the word recommendation strategy in combination with the performance data of oral English, dictation and other scenes, forming a "learning-evaluation-optimization" closed loop.

[0076] Further, through the timestamp and mastery level reciprocal in the feature vector, the word memory decay curve can be tracked, and data support can be provided for subsequent review plan. BRIEF DESCRIPTION OF DRAWINGS

[0077] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed in the embodiments. Obviously, the drawings described below are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor on the basis of these drawings.

[0078] Figure 1 is a method for improving the efficiency of word learning of primary and secondary school students provided by the embodiment of the present application;

[0079] Figure 2 is a device for improving the efficiency of word learning of primary and secondary school students provided by the embodiment of the present application;

[0080] Figure 3It is a kind of device schematic diagram for improving the efficiency of primary and middle school students' word learning according to the embodiment of the application. DETAILED DESCRIPTION

[0081] The application can be explained in detail by the following examples, and the purpose of the application is to protect all technical improvements within the scope of the application. In the description of the application, it should be understood that the orientation or position relationship indicated by terms such as "up", "down", "front", "back", "left" and "right" only corresponds to the drawings of the application, and is for the convenience of describing the application, but does not indicate or imply that the device or element must have a specific orientation.

[0082] Embodiment one

[0083] Reference Figure 1 The embodiment provides a method for improving the efficiency of primary and middle school students' word learning, comprising the following steps:

[0084] S1, defining the feature vector of the word and the word list of the learning material; the feature vector includes the number of phonemes of the word, the importance of the word, the inverse of the cumulative number of occurrences of the word, the inverse of the mastery degree at the last learning and the time stamp of the last learning;

[0085] Defining the feature vector of the word specifically includes:

[0086] In the embodiment, each word required by the primary and middle school teaching materials is represented as a feature vector. In all feature values of the feature vector, except for the time stamp of the last learning, each feature value is a floating point number with a value of 0 to 1. The feature vector includes the following features:

[0087] 1) The number of phonemes of the word, representing the difficulty of the word, 0.1 for one phoneme, 0.2 for two phonemes, and so on;

[0088] The number of phonemes of an English word depends on the number of vowels and pronunciation rules in the word. Simply put, each vowel or vowel combination usually forms a phoneme. The number of phonemes can be obtained by writing corresponding code according to the above rules to divide the English word into phonemes, for example, directly obtaining the number of phonemes of the word by relying on a pre-stored pronunciation database (such as the CMU pronunciation dictionary), or counting the built-in phonemes of the English word by using an existing natural language processing (NLP) tool library. Further, the number of phonemes can be predicted according to the spelling characteristics (letter sequence, vowel and consonant combination, prefix / suffix, etc.) of the word by using a trained model. The embodiment does not limit the above methods, as long as the number of phonemes of the word can be obtained.

[0089] Preferably, it is considered that the CMU pronunciation dictionary has covered the vocabulary of primary and secondary school teaching materials, so the embodiment obtains the number of phonemes of a word by calling the API of a pre-stored pronunciation database, i.e., Pronouncing API.

[0090] The Pronouncing API is constructed based on the CMU Pronouncing Dictionary developed by Carnegie Mellon University, which contains a large number of English words and their corresponding phonetic (phoneme) representations, covering phoneme annotation of more than 130,000 English words. Pronouncing API provides a series of functions such as obtaining word pronunciation, finding rhyming words, and calculating the number of phonemes by parsing and indexing these phonetic data. The CMU dictionary annotates the phoneme sequence of a word, and the number of phonemes is determined by the number of vowel phonemes (Vowel) in the phoneme.

[0091] For example, the number of phonemes of the word "example" is 3, and the number of phonemes of the word "apple" is 2.

[0092] 2) Word importance, which is divided according to the vocabulary level of primary and secondary schools. In the embodiment, the vocabulary of primary and secondary school learning materials is divided into four categories, including primary and secondary school basic core vocabulary, primary and secondary school expansion commonly used vocabulary, primary and secondary school advanced vocabulary, and primary and secondary school non-essential vocabulary. According to the grade and experience value of 0.9 to 0.1, the greater the value, the more important the word.

[0093] In the embodiment, the value of the primary and secondary school basic core vocabulary is 0.9, the value of the primary and secondary school expansion commonly used vocabulary is 0.7, the value of the primary and secondary school advanced vocabulary is 0.4, and the value of the primary and secondary school non-essential vocabulary is 0.1.

[0094] In a possible implementation, the vocabulary of primary and secondary school learning materials can be divided into more or fewer types as needed, and the division can be made as needed. The importance of the divided words can also be adjusted as needed.

[0095] In another possible implementation, the scope of learning materials can also be expanded for division, such as introducing vocabulary of university, IELTS, TOEFL, etc. The above is not specifically limited.

[0096] 3) The reciprocal of the cumulative number of occurrences of a word, which is used to measure the frequency of the word in the learning process. The more frequently a word appears, the more likely it is to have been mastered, and the smaller the reciprocal of the cumulative number of occurrences. The initial value of this attribute of a word is the reciprocal of the cumulative number of occurrences of the word in the textbook. With the development of learning on a specific APP, the reciprocal of the cumulative number of occurrences of a word will change in real time. The initial value of the reciprocal of the cumulative number of occurrences of a word is set to 0.

[0097] 4) Reciprocal of the mastery level of the last learning, the mastery level is valued from 1 to 100, the smaller the mastery level value, the worse the mastery of the word, the larger the reciprocal of the mastery level; the initial value of the mastery level is 1; the mastery level is divided into 4 levels in this embodiment, which are:

[0098] 1-25: not mastered (completely unfamiliar, unable to recall)

[0099] 26-50: preliminary mastery (have a vague impression, need to prompt recall)

[0100] 51-75: basic mastery (can recall independently, but not enough proficiency)

[0101] 76-100: proficient mastery (accurate and rapid recall, flexible application).

[0102] 5) Time stamp of the last learning, the time stamp refers to the number of seconds from the current time to January 1, 1970, 00:00:00. The initial value of the reciprocal of the mastery level of the last learning is set to 0.

[0103] It is worth noting that the number of features of the feature vector in this embodiment is an integer greater than or equal to 5, which can be further expanded based on the above 5 feature vectors, which is not limited here.

[0104] In this way, a word word can be represented as a feature vector:

[0105] word=[v1,v2,v3,v4,v5,...vn];

[0106] Where n is the number of features, n is an integer greater than 5, v1 is the number of phonetic units of the word, v2 is the importance of the word, v3 is the reciprocal of the cumulative number of occurrences of the word, v4 is the reciprocal of the mastery level of the last learning, v5 is the time stamp of the last learning,... vn represents more feature vectors, and all feature values (i.e. v1, v2, v3, v4, v6,... vn) are floating-point numbers from 0 to 1, except that the time stamp of the last learning is an integer value.

[0107] The vector format of multiple words is as follows:

[0108] word1=[v11,v21,v31,...,vn1]

[0109] word2=[v12,v22,v32,...,vn2]

[0110] Except for the first two feature values (number of phonetic units of the word and importance of the word), other feature values are dynamically changing in the learning process of the student.

[0111] The word list WordDict of each learning material is defined as follows:

[0112] The word list WordDict is stored in a dictionary format, with the key name being the word and the value being the number of times the word appears in the learning material; the type of the learning material includes oral, dictation, listening, reading, and writing;

[0113] The definition of WordDict is: {"apple":5;"what":2;}, where "apple","what": refers to the word itself, and the number indicates the cumulative number of times the word appears in the learning material.

[0114] Take a reading type of learning material as an example:

[0115] The title of the learning material is: An Apple Adventure;

[0116] The content of the learning material is:

[0117] What a delicious apple! Emma picked a bright red apple from the tree.She wondered, What kind of apple is this? It smelled sweet and tasted crisp.Emma shared the apple with her friend, saying, 'What a joy to enjoy nature'sgift!' Her friend replied, 'What a perfect day for an apple picnic!'

[0118] The word list of the learning material WordDict = { "what": 4, "a": 4, "delicious": 1, "apple": 4, "emma": 2, "picked": 1, "bright": 1, "red": 1, "from": 1, "the": 3, "tree": 1, "she": 2, "wondered": 1, "kind": 1, "is": 1, "this": 1, "it": 1, "smelled": 1, "sweet": 1, "and": 1, "tasted": 1, "crisp": 1, "shared": 1, "with": 1, "her": 2, "friend": 2, "saying": 1, "joy": 1, "to": 1, "enjoy": 1, "natures": 1, "gift": 1, "replied": 1, "perfect": 1, "day": 1, "for": 1, "picnic": 1};

[0119] S2, according to the outline requirements and teaching material content, the feature vector of all words in English learning teaching material is established, then the word recommendation value is calculated according to the feature vector, the word recommendation value dictionary is initialized and the learning material is warehoused; The learning material contains the corresponding word dictionary;

[0120] The English learning teaching material is a primary and secondary school English learning teaching material;

[0121] The outline requirements refer to the national or local education department's teaching standards or guidance documents for primary and secondary school English teaching, which clearly defines the English knowledge and skills that students should master at different learning stages, including but not limited to vocabulary, grammar points, listening, speaking, reading and writing ability training targets, etc. The outline requirements are authoritative and guiding, and are the direct basis for textbook compilation and teaching.

[0122] The teaching material content refers to the content of the specific primary and secondary school English teaching material, which directly reflects the outline requirements and is the main material for students to learn English. The teaching material content usually includes texts, word dictionaries, exercises and other parts.

[0123] The official website of the national and local education departments usually releases the latest teaching syllabus and teaching material information. The textbook publishing house can also provide textbook catalogues, sample chapters and syllabus supporting resources.

[0124] When a word is represented as a feature vector, the first three feature values of the feature vector, i.e., the word phoneme number, the word importance, and the reciprocal of the cumulative occurrence number of the word, are initialized according to the outline requirements and the textbook content statistics, and the values of the two features of the word phoneme number and the word importance are always constant after initialization. The initial values of other feature values are 0 by default since there is no feedback information from students at the beginning.

[0125] In this step, we calculate the word recommendation value of all words in the primary and secondary school English teaching materials, and then initialize the word recommendation value dictionary WordRecommendDict of all words. Each item of data in the dictionary specifies a word and its corresponding recommendation value. The higher the recommendation value, the more unfamiliar the student is with the word, and the more learning materials containing the word need to be recommended. The recommendation value is stored in the form of a word-recommendation value key-value pair. The content of the recommendation value dictionary WordRecommendDict is similar to: {"apple": 0.496, "what": 0.323,}, where "apple", "what" refer to the word itself; 0.496, 0.323 is the corresponding recommendation value of the word. The larger the recommendation value, the greater the probability of recommending learning content containing the word in the future.

[0126] Specifically, the word recommendation value of a word is calculated by weighting and summing the feature vector of the word and the preset feature weight values.

[0127] As can be seen from the above, a word word can be represented as a feature vector:

[0128] word=[v1,v2,v3,v4,v5,...vn];

[0129] The calculation formula of the word recommendation value WR is as follows:

[0130] WR=W1*v1+W2*v2+W3*v3+W4*v4+W5*v5’+...+Wn*vn

[0131] Where v5’ is a forgetting coefficient obtained by converting v5 (the last learning timestamp). W1, W2..Wn represent the weights of v1, v2...vn in the calculation of the word recommendation value, representing the importance of v1, v2..vn for calculating the word recommendation value, taking a floating-point number between 0 and 1, and satisfying W1+W2+...+Wn=1.

[0132] In this embodiment, taking the word vector with 5 features as an example, the calculation formula of the word recommendation value WR is shown in formula (1):

[0133] WR=W1*v1+W2*v2+W3*v4+W4*v4+W5*v5’ (1)

[0134] wherein, v1 (number of phonemes of the word) represents the word difficulty, generally the more difficult word is more difficult to remember, W1 can be slightly larger, the number of phonemes of the word in the embodiment W1 is 0.15; v2 (word importance), the more important the word, the more it should be recommended, the less important the word is, the less it should be recommended, the word importance weight W2 should be larger than W1, W2 in the embodiment is 0.35; v3 (reciprocal of cumulative number of occurrences of the word) is relatively less important, the reciprocal of the cumulative number of occurrences of the word in the embodiment W3 is 0.1; v4 (reciprocal of the degree of mastery at the last learning) is more convincing for judging the degree of mastery of the word, this weight should be larger, the reciprocal of the degree of mastery at the last learning in the embodiment W4 is 0.25; v5' is the forgetting coefficient obtained by converting v5 (last learning timestamp), which is relatively important, the forgetting coefficient weight W5 in the embodiment is 0.15. W1, W2,..., Wn can also be fine-tuned according to actual test results;

[0135] The forgetting coefficient can be calculated by the last learning timestamp;

[0136] The formula for calculating the forgetting coefficient is shown in formula (2):

[0137] Fc=1-R (2)

[0138] Wherein, Fc is the forgetting coefficient; R is the memory retention rate of Ebbinghaus, that is: R=e^(-t / S), wherein e is the base number of natural logarithm (about 2.718), t is the forgetting time, the unit is day, t=(current timestamp-last learning timestamp) / 86400, wherein 86400 is the number of seconds in a day, S is the relative memory strength, the value is 1.84. In this way, the forgetting coefficient is a floating point number between 0 and 1, the time span t=(ts-v5) / 86400, the forgetting coefficient is also larger; ts is the current timestamp, v5 is the last learning timestamp in the feature vector;

[0139] The following are examples of several words:

[0140] Example 1: Primary and secondary school basic core vocabulary: the

[0141] Number of phonemes of the word v1: 1→0.1

[0142] Word importance v2: 0.9

[0143] Reciprocal of cumulative number of occurrences v3: 200 times in teaching material→1 / 200=0.005

[0144] Reciprocal of the degree of mastery at the last learning v4: 0

[0145] Timestamp of last learning v5: 0

[0146] Feature vector: [0.1, 0.9, 0.005, 0, 0]

[0147] Word recommendation value WR of the = 0.15*0.1 + 0.35*0.9 + 0.1*0.005 + 0 + 0 = 0.3305

[0148] Example 2: Commonly used vocabulary in primary and secondary schools: happy

[0149] Number of syllables of the word v1: 2 → 0.2

[0150] Importance of the word v2: 0.7

[0151] Cumulative appearance frequency reciprocal v3: 30 times in the textbook → 1 / 30 ≈ 0.033

[0152] Reciprocal of the degree of mastery at the time of last learning v4: 0

[0153] Timestamp of last learning v5: 0

[0154] Feature vector: [0.2, 0.7, 0.033, 0, 0]

[0155] Word recommendation value WR of happy = 0.15*0.2 + 0.35*0.7 + 0.1*0.033 + 0 + 0 = 0.2783

[0156] Example 3: Advanced vocabulary in primary and secondary schools: science

[0157] Number of syllables of the word v1: 2 → 0.2

[0158] Importance of the word v2: 0.4

[0159] Cumulative appearance frequency reciprocal v3: 8 times in the textbook → 1 / 8 = 0.125

[0160] Reciprocal of the degree of mastery at the time of last learning v4: 0

[0161] Timestamp of last learning v5: 0

[0162] Feature vector: [0.2, 0.4, 0.125, 0, 0]

[0163] Word recommendation value WR of science = 0.15*0.2 + 0.35*0.4 + 0.1*0.125 + 0 + 0 = 0.1825

[0164] Example 4: Non-mandatory vocabulary in primary and secondary schools: luxury

[0165] Word phonetic number v1: 2 → 0.2

[0166] Word importance v2: 0.1

[0167] Cumulative appearance frequency reciprocal v3: 3 appearances in the textbook → 1 / 3 ≈ 0.333

[0168] Reciprocal of mastery degree at last learning v4: 0

[0169] Timestamp of last learning v5: 0

[0170] Feature vector: [0.2, 0.1, 0.333, 0, 0]

[0171] Word recommendation value WR of luxury = 0.15*0.2 + 0.35*0.1 + 0.1*0.333 + 0 + 0 = 0.0983

[0172] The step also includes the warehousing of learning materials of the English learning materials. When the learning materials are warehoused, they are stored according to the grade information and the learning type, and the learning materials are additionally provided with a corresponding word dictionary WordDict, which corresponds to the warehousing storage of the learning materials. The learning type includes word learning, oral English, dictation, listening, reading, and writing. The grade information includes first grade, second grade, third grade, fourth grade, fifth grade, sixth grade, seventh grade (first year of junior high school), eighth grade (second year of junior high school), ninth grade (third year of junior high school), first year of high school, second year of high school, and third year of high school.

[0173] Taking a reading material as an example, each reading material is additionally provided with a word dictionary WordDict when it is warehoused, in addition to the full text of the material content itself, which contains all the words of the reading material and the number of appearances of each word.

[0174] The format of WordDict is similar to: {"apple":5;"what":2;}, where "apple", "what" refer to the word itself, and the number represents the cumulative number of appearances of the word in the learning content.

[0175] For example, taking a reading type of learning material for third grade as an example:

[0176] The title of the reading material is: An Apple Adventure.

[0177] The material content of the reading material is:

[0178] What a delicious apple! Emma picked a bright red apple from the tree. She wondered, What kind of apple is this? It smelled sweet and tasted crisp. Emma shared the apple with her friend, saying, 'What a joy to enjoy nature's gift!' Her friend replied, 'What a perfect day for an apple picnic!'

[0179] The word dictionary of the reading material WordDict = {"what": 4, "a": 4, "delicious": 1, "apple": 4, "emma": 2, "picked": 1, "bright": 1, "red": 1, "from": 1, "the": 3, "tree": 1, "she": 2, "wondered": 1, "kind": 1, "is": 1, "this": 1, "it": 1, "smelled": 1, "sweet": 1, "and": 1, "tasted": 1, "crisp": 1, "shared": 1, "with": 1, "her": 2, "friend": 2, "saying": 1, "joy": 1, "to": 1, "enjoy": 1, "nature's": 1, "gift": 1, "replied": 1, "perfect": 1, "day": 1, "for": 1, "picnic": 1}

[0180] The process of learning material warehousing includes:

[0181] (1) Generate a unique identifier material_id for the material using a self-incrementing ID, UUID (Universal Unique Identifier), or hash algorithm;

[0182] (2) Integrate the material content, word dictionary, grade, learning type, and ID into a structured object (such as a dictionary or JSON format);

[0183] {"material_id": "MAT_READ_ENG_GR3_20241015_001",

[0184] "title": "An Apple Adventure",

[0185] "content": "What a delicious apple! Emma picked a bright red apple from the tree. She wondered, What kind of apple is this? It smelled sweet and tasted crisp. Emma shared the apple with her friend, saying, 'What a joy to enjoy nature's gift!' Her friend replied, 'What a perfect day for an apple picnic!'",

[0186] "word_dict":{"what":4,"a":4,"delicious":1,"apple":4,"emma":2,"picked":1,"bright":1,"red":1,"from":1,"the":3,"tree":1,"she":2,"wondered":1,"kind":1,"is":1,"this":1,"it":1,"smelled":1,"sweet":1,"and":1,"tasted":1,"crisp":1,"shared":1,"with":1,"her":2,"friend":2,"saying":1,"joy":1,"to":1,"enjoy":1,"natures":1,"gift":1,"replied":1,"perfect":1,"day":1,"for":1,"picnic":1},

[0187] "grade_level": "Third grade",

[0188] "learning_type": "Reading",

[0189] "keywords": ["apple", "nature", "friendship"]}

[0190] It should be noted that there is a misspelling in the original "picnic", which is corrected to "picnic" in the translation for consistency with the English text structure speculation. In the actual translation, it should be "picnic" corrected to "picnic" (this may be a misspelling in the original text). And "三年级" is translated as "Third grade" according to the common English expression for grade levels.(3) The structured object is saved into a database through the database, so as to facilitate subsequent use; the database can be MySQL, SQL Server, Oracle, etc., as long as the database can achieve the effect of persistent storage, which is not limited here.

[0191] The above storage process and the structured process are only examples, and can be changed according to actual needs.

[0192] It is worth noting that the feature vector of all words and the word recommendation value dictionary WordRecommendDict are also stored persistently through a file or a database, so as to facilitate subsequent use.

[0193] S3, dynamically updating the word feature vector and the recommendation value dictionary according to the performance of students in different learning types in the learning process; the learning types include word learning, oral English, dictation, listening, reading and writing;

[0194] During the learning process of word learning, oral English, dictation, listening, reading and writing, the feature vector of each word is updated according to the performance of students, and the recommendation value dictionary is updated.

[0195] In this embodiment, the student is in the process of English learning through a specific application on the student tablet or mobile phone. Through the feedback information of the application, the student's mastery of the word is understood, and the feature vector and the recommendation value dictionary of the word are updated.

[0196] It can be understood that the above-mentioned specific application can be the operation of the student on the application page, for example, the voice can be collected for recording, and the writing operation of the student in the application can be collected, such as the start time and the end time, which is the prior art and will not be repeated here.

[0197] Different learning types have different ways of updating the word feature vector and the recommendation value dictionary, including the following cases:

[0198] Word learning: in the process of word learning and spelling, the reciprocal of the cumulative number of occurrences of the corresponding feature vector of the word, the reciprocal of the mastery degree of the last learning and the time stamp of the last learning are updated, and the word recommendation value is recalculated, and then the word recommendation value dictionary WordRecommendDict is updated;

[0199] The reciprocal of the cumulative number of occurrences of the word is obtained by taking the reciprocal of the reciprocal of the cumulative number of occurrences of the word in the word feature vector, and then taking the reciprocal of the cumulative number of occurrences of the word after adding 1 to obtain the latest reciprocal of the cumulative number of occurrences of the word;

[0200] The time stamp of the last learning is updated to the time stamp when the current word is learned;

[0201] The specific update process for the reciprocal of the mastery level from the last learning session is as follows:

[0202] Specifically, vocabulary learning often involves listening to, repeating, and spelling words. We can calculate a student's current level of mastery of a word by combining the accuracy of repeating (accuracy score Fl), the correctness of spelling (spelling accuracy score Sp), and the time spent spelling (time efficiency score Te).

[0203] Specifically, third-party speech recognition technologies are used to score the pronunciation of the words being read aloud, such as Tencent Cloud's Smart Listening Oral Evaluation (SOE), iFlytek's Spark Speech Big Model, and Unisound's AI Open Platform.

[0204] Smart Oral Evaluation (SOE) is a Chinese and English speech evaluation product launched by Tencent Cloud. It supports speech evaluation for all ages, from children to adults, and offers multiple modes such as word, sentence, paragraph, and free speech. It supports a comprehensive scoring mechanism that considers pronunciation accuracy, fluency, and completeness, with a similarity of over 95% to expert scores. It can be widely used in Chinese and English oral teaching.

[0205] Preferably, in this embodiment, the Smart Listening Oral Assessment is used to score the correct word pronunciation score Fl.

[0206] The Zhiling oral assessment can obtain a suggested score for the recording of an English word based on the recording of the word and the corresponding text. The suggested score is an integer from 1 to 100, which is used as the score for correct word pronunciation.

[0207] For example, the word we want to learn is "example". Based on the pronunciation recording and the accuracy score of "example" obtained through the Zhiling oral assessment, the pronunciation accuracy score is 96.

[0208] Furthermore, the spelling accuracy score Sp can be determined based on the proportion of correctly spelled letters in a word to the total number of letters in the word, with 100 representing completely correct spelling; the formula for calculating the spelling accuracy score Sp is shown in formula (3):

[0209] Sp = [(correctNum / totalNum) * 100] (3)

[0210] Where Sp is the spelling accuracy score, correctNum is the number of correctly spelled letters, totalNum is the total number of letters in the word, and [] is the rounding symbol;

[0211] For example, we want to evaluate the spelling accuracy score Sp of the word "example".

[0212] Target word: example (7 letters), current spelling: exampel (note that the 'l' and the second 'e' are reversed); compare letter by letter, count the number of correctly written letters. In "exampel", 'e', 'x', 'a','m', 'p' are correct, while the 'e' and 'l' are reversed, so 'e' is correct (if position is not considered, but here we strictly calculate according to position), actually 'l' is wrong, and the second 'e' is also wrong. Therefore, the correct letters are 'e', 'x', 'a','m', 'p', a total of 5, so the spelling accuracy score Sp = [(5 / 7)*100]=71 is calculated;

[0213] The time efficiency score Te is determined according to the time spent on spelling a correct word, as shown in formula (4);

[0214] Te = Min[(T / t)*100,100] (4)

[0215] Where Te is the time efficiency score, T=n*T1, T1 is the experienced time length of inputting an English letter on an electronic device, unit ms, n represents the number of letters of the word, t is the time length actually spent by the user to complete the input of a word, unit ms.

[0216] The value of T1 is generally between 150-300ms, and in this embodiment T1 is 250ms;

[0217] Take the spelling word "example" as an example, example has 7 letters, so n=7, T1=250ms, then T=7*250=1750ms. Assuming the user used 2500ms, then Te=(1750 / 2500)*100=70, so the score is 70. If the user uses a shorter time, such as 1500ms, then Te=(1750 / 1500)*100=116, but according to the formula, Te takes the minimum value 100, so the score is 100.

[0218] The current mastery degree Mn of the word is calculated according to formula (5):

[0219] Mn=[Fl*a+Sp*b+Te*c] (5)

[0220] Where a is the reading accuracy score weight, b is the spelling accuracy score weight, and c is the time efficiency score weight; a+b+c=1;

[0221] According to the language learning rule, pronunciation and spelling are the core, time efficiency is the auxiliary, so the reading accuracy score weight and the spelling accuracy score weight need to be larger, and the time efficiency score weight can be less, so in this embodiment, a=0.4; b=0.4; c=0.2;

[0222] For example, a student learns the word "example", the reading accuracy score is 96, the spelling accuracy score is 71, and the time efficiency score is 70, so the current mastery degree Mn of the student learning the word "example" is [96*0.4+71*0.4+70*0.2]=80.

[0223] The calculation formula of the reciprocal of the latest mastery degree v4' is shown in formula (6):

[0224] v4'=R*v4+(1-R)*(1 / Mn) (6)

[0225] Wherein, v4' is the reciprocal of the latest mastery degree, v4 is the reciprocal of the mastery degree at the last learning time in the feature vector of the word, R is the memory retention rate of Ebbinghaus, that is: R=e^(-t / S); Wherein e is the base of natural logarithm, t is the forgetting time, unit is day, t=(ts-v5) / 86400; S is the relative memory strength, the value is 1.84; ts is the current time stamp, v5 is the time stamp of the last learning in the feature vector;

[0226] Taking the word "example" as an example, the reciprocal of the mastery degree v4 at the last learning time of the word is 0.1 (that is, the mastery degree at the last learning time is 10), the time stamp of the last learning is v5=1700000000, the current time stamp ts=1700432000, and the current mastery degree Mn=80;

[0227] First, calculate the forgetting time t=(1700432000-1700000000) / 86400=5, then R=e^(-5 / 1.84)≈0.0655,

[0228] Then bring into the formula to get the reciprocal of the latest mastery degree:

[0229] v4'=0.0655*0.1+(1−0.0655)*1 / 80≈0.00655+0.01168=0.01823;

[0230] This embodiment analyzes the above process:

[0231] Since the forgetting time is 5 days, the memory retention rate R≈6.55%, it can be seen that the memory retention rate is very low, indicating that most of the memory has decayed; the mastery degree of the last learning is 10, indicating that the last learning effect is general, and the word is basically not mastered; and the current mastery degree is 80, indicating that the mastery degree is high, and the reciprocal 0.0125 has a greater impact on the final result, and the latest mastery degree is equal to 1 / v4'≈54.85, indicating that although the last learning effect is general, through this learning, the latest mastery degree is improved to basic mastery.

[0232] Then the reciprocal of the latest mastery degree replaces the reciprocal of the mastery degree of the last learning of the word feature vector;

[0233] Finally, the word recommendation value WR of the word is recalculated according to the updated word feature vector by using the calculation formula of the word recommendation value, and then the word recommendation value dictionary WordRecommendDict is updated;

[0234] Oral learning, according to the speech recognition technology, the pronunciation score of each word in the follow-up sentence is recognized, and the current mastery degree of each word is calculated according to the pronunciation score of each word, and the reciprocal of the latest mastery degree of the word is calculated according to formula (6), and the reciprocal of the cumulative number of times of the word, the reciprocal of the mastery degree of the last learning and the time stamp of the last learning of the corresponding feature vector are updated, and the word recommendation value is recalculated, and then the word recommendation value dictionary WordRecommendDict is updated;

[0235] The updating process of the cumulative number of times of the word and the time stamp of the last learning is the same as that in the word learning, which will not be repeated here.

[0236] Oral learning is mainly to judge the learning effect according to the English recording of the student's follow-up sentence, and the third-party speech recognition technology can also be used to score the words in the follow-up sentence.

[0237] In addition to scoring individual words, ZhiLing oral assessment can also score the entire recording based on a sentence of English recording and the corresponding sentence text. ZhiLing oral assessment can return the overall score of the recording based on a sentence of English recording and the corresponding sentence text, and also return the score of each phoneme in the sentence (each phoneme also carries the corresponding pronunciation letter information). Based on the word and the letter information carried by each phoneme in the sentence, the correspondence between each word and each phoneme in the sentence can be determined, and the average of the scores of each phoneme can be obtained as the word pronunciation score.

[0238] The word pronunciation score is taken as the value of the current mastery degree Mn of the word, and then the inverse of the latest mastery degree v4' of the word is calculated according to formula (6), and then the inverse of the mastery degree of the last learning of the word feature vector is replaced by the inverse of the latest mastery degree; finally, the word recommendation value WR of the word is recalculated according to the updated word feature vector by using the calculation formula of the word recommendation value, and then the word recommendation value dictionary WordRecommendDict is updated;

[0239] The writing learning adopts different current mastery degree determination manners of the word according to the spelling accuracy score of the word, and calculates the inverse of the latest mastery degree of the word according to the current mastery degree of the word, and then updates the inverse of the cumulative occurrence frequency of the corresponding feature vector, the inverse of the mastery degree of the last learning and the time stamp of the last learning, and recalculates the word recommendation value, and then updates the word recommendation value dictionary WordRecommendDict;

[0240] The calculation formula of the spelling accuracy score Sp is shown in formula (3):

[0241] Sp = [(correctNum / totalNum) * 100] (3)

[0242] Wherein, the spelling accuracy score Sp can be determined according to the proportion of the number of letters written correctly to the total number of letters of the word, and a value of 1 to 100, 100 indicates completely correct spelling;

[0243] When the word spelling is completely correct, the time efficiency score Te is calculated by formula (4), and is taken as the current mastery degree Mn of the word, that is, Mn=Te; formula (4) is as follows:

[0244] Te = Min[(T / t)*100,100] (4)

[0245] Wherein, Te is the time efficiency score, T=n*T1, T1 is the experience time length of inputting one English letter on the electronic device, unit: ms, n represents the number of letters of the word, t is the time length actually spent by the user to complete the input of one word, unit: ms.

[0246] When the word spelling is not completely correct, the current mastery degree Mn of the word is calculated by formula (7):

[0247] Mn = U1*Sp+(1-U1)*Te (7)

[0248] Wherein, U1 is an experience value, a floating point number with a value of 0 to 1, considering that the spelling accuracy of the word can better evaluate the mastery degree of the word than the time spent, U1 can be taken as a large point, therefore, the value of U1 in the embodiment is 0.75;

[0249] The process of updating the cumulative number of times a word appears with the timestamp of the last learning session is the same as in the word learning process, and will not be repeated here.

[0250] The current mastery level Mn of the word is calculated, and the reciprocal v4' of the latest mastery level of the word is calculated according to formula (6). Then, the reciprocal of the latest mastery level replaces the reciprocal of the mastery level of the word feature vector at the time of the last learning. Finally, the word recommendation value WR of the word is recalculated according to the updated word feature vector using the formula for calculating the word recommendation value, and then the word recommendation value dictionary WordRecommendDict is updated.

[0251] In writing learning, when a word in the writing content is in the WordRecommendDict dictionary and is spelled correctly, the inverse of the mastery level of the word at the last learning time is calculated. Then, the inverse of the cumulative occurrence of the word in the corresponding feature vector, the inverse of the mastery level at the last learning time, and the timestamp of the last learning time are updated, and the word recommendation value is recalculated, thereby updating the WordRecommendDict dictionary.

[0252] When learning to write, specific applications will recognize the handwriting of the user and generate corresponding letters. For example, they can use OCR technology or a pre-trained handwriting recognition model to recognize the handwriting and obtain the closest letters. Then, they will generate words based on the closest letter combinations. This is existing technology and will not be elaborated here. In addition, the start and end times of spelling are recorded for each word written.

[0253] Since students' spelling of words during writing is arbitrary, there is no answer that can determine whether the spelling of a word is correct. Therefore, this example only considers correctly spelled words.

[0254] Once the writing is complete, obtain all the words based on the content, and then iterate through all the words:

[0255] If a word is in the WordRecommendDict dictionary, the computation time efficiency score Te is calculated according to the time spent inputting the word using formula (4), and this score is used as the current mastery level Mn of the word. The current mastery level Mn is calculated using formula (6) to calculate the reciprocal v4' of the latest mastery level of the word. The reciprocal of the latest mastery level is then used to replace the reciprocal of the mastery level of the word feature vector during the last learning. Finally, the word recommendation value WR of the word is recalculated according to the updated word feature vector using the word recommendation value calculation formula, and the WordRecommendDict dictionary is updated accordingly.

[0256] The updating process of the accumulated occurrence number of a word and the last learning time stamp is consistent with that in word learning, which will not be described here.

[0257] If the word is not in the word recommendation value dictionary WordRecommendDict, it is either misspelled, or not spelled as an English word, or the word is beyond the range required to be learned in primary and secondary schools, and can be directly ignored.

[0258] Listening learning and reading learning

[0259] Generally, listening learning is to listen to a large amount of listening material, and then select the correct answer according to the questions. If the answer is correct, it is considered that the words in the listening material are all completed in the recommended value dictionary WordRecommendDict, and then the reciprocal of the accumulated occurrence number of the feature vector corresponding to the word and the last learning time stamp are updated, and the current mastery degree Mn of the word is set to 100. Then the reciprocal of the latest mastery degree of the word is calculated according to formula (6) through the current mastery degree Mn of the word, and finally the words in the listening material in the word recommendation value dictionary WordRecommendDict are updated; the updated last learning time stamp is the time stamp when the listening material is learned;

[0260] Specifically, if the listening answer is completely correct, all the words in the WordDict of the listening material are traversed, and if the traversed word is in the recommended value dictionary WordRecommendDict, the reciprocal of the accumulated occurrence number of the feature vector corresponding to the word and the last learning time stamp are updated, and the current mastery degree Mn of the word is set to 100.

[0261] The reciprocal of the latest mastery degree v4' of the word is calculated according to formula (6) through the current mastery degree Mn of the word, and then the reciprocal of the last learning mastery degree of the word feature vector is replaced; finally, the word recommendation value WR of the word is recalculated according to the updated word feature vector using the word recommendation value calculation formula, and the word recommendation value dictionary WordRecommendDict is updated.

[0262] In the case that the listening does not reach full score, it is difficult to judge which word or which words the student does not understand or understand. At this time, we can traverse WordRecommendDict according to the WordDict of the listening material to find the n words with the highest recommendation value as not understood, and n is selected according to a small proportion of WordDict (such as 5%).

[0263] It can be understood that the listening material will correspond to the corresponding text material.

[0264] Specifically, if the hearing answer is not completely correct, all the words in the WordDict of the listening material are traversed to find the n words with the highest word recommendation values in the word recommendation value dictionary WordRecommendDict as the words not understood, and the reciprocal of the cumulative number of times of occurrence of the feature vector corresponding to the words not understood and the time stamp of the last learning are updated; the value of n is determined according to the length of the WordDict of the listening material, and n is an integer obtained by rounding up 5% of the length of the WordDict; the value of n can also be adjusted according to specific needs;

[0265] Due to the listening material and the reading material, we cannot accurately know which words the students did not master to get full marks, so we estimate the words with the highest recommended values, so there may be a large error, therefore, when calculating the reciprocal of the final mastery of these words, a regulation factor R1 is introduced to calculate the reciprocal v4' of the latest mastery; the calculation formula is shown in formula (8):

[0266] v4'=R1*R*v4+(1-R1)*(1-R)*(1 / Mn) (8)

[0267] Where v4' is the reciprocal of the latest mastery, v4 is the reciprocal of the mastery at the last learning in the word feature vector, R is the memory retention rate of Ebbinghaus, that is: R = e^(-t / S); where e is the base number of natural logarithm, t is the forgetting time, the unit is day, t = (ts-v5) / 86400; S is the relative memory strength, the value is 1.84; ts is the current time stamp, taking the time stamp when the listening material is completed; v5 is the time stamp of the last learning in the word feature vector; Mn is the current mastery of the word; the value of Mn is determined by the proportion of the final score of the listening to the total score multiplied by 100;

[0268] For example, the total score of the current listening material is 60 points, and the final score is 48 points, then the latest mastery Mn = 48 / 60*100 = 80;

[0269] R1 is the memory influence coefficient, considering that the reciprocal of the mastery at the last learning has a greater influence on the listening learning, and the reciprocal of the latest mastery has a smaller influence, therefore, the memory influence coefficient R1 in this embodiment is 0.85;

[0270] Then the reciprocal v4' of the latest mastery is replaced by the reciprocal of the mastery at the last learning in the word feature vector; finally, the word recommendation value WR of the word is recalculated according to the updated word feature vector by using the calculation formula of the word recommendation value, and the word recommendation value dictionary WordRecommendDict is updated;

[0271] The updating process of the cumulative occurrence number of a word and the timestamp of the last learning in the listening learning is consistent with that in the word learning, which will not be repeated here.

[0272] The processing mode of reading learning is similar to that of listening learning. In general, a large amount of reading materials are read, and then the correct answers are selected according to the questions. If the answers are correct, it is considered that the words in the reading materials have completed a learning in the word recommendation value dictionary WordRecommendDict, then the reciprocal of the cumulative occurrence number of the word corresponding to the feature vector and the timestamp of the last learning are updated, and the current mastery degree Mn of the word is set to 100, then the reciprocal of the latest mastery degree of the word is calculated according to formula (6) through the current mastery degree Mn of the word, and finally the words in the reading materials in the word recommendation value dictionary WordRecommendDict are updated; the updated last learning timestamp is the timestamp when the reading material learning is completed.

[0273] Specifically, if the listening answers are completely correct, all the words in the word dictionary WordDict of the reading material are traversed, and if the traversed word is in the recommendation value dictionary WordRecommendDict, the reciprocal of the cumulative occurrence number of the word corresponding to the feature vector and the timestamp of the last learning are updated, and the current mastery degree Mn of the word is set to 100.

[0274] The reciprocal of the latest mastery degree v4' of the word is calculated according to formula (6) through the current mastery degree Mn of the word, and then the reciprocal of the last learning mastery degree of the word feature vector is replaced; finally, the word recommendation value WR of the word is recalculated according to the updated word feature vector using the word recommendation value calculation formula, and the word recommendation value dictionary WordRecommendDict is updated.

[0275] In the case of not reaching full marks in reading, it is difficult to judge which word or which words the student does not understand or understand. At this time, we can traverse WordRecommendDict according to the word dictionary WordDict of the reading material to find out the n words with the highest recommendation value as not understood, and n is selected in small proportion according to the dictionary length of the word dictionary WordDict (for example, 5%).

[0276] Specifically, if the hearing answer is not completely correct, all the words in the word dictionary WordDict of the reading material are traversed to find the n words with the highest word recommendation values in the word recommendation value dictionary WordRecommendDict as the words not understood, and the reciprocal of the cumulative number of times of occurrence of the feature vector corresponding to the words not understood and the time stamp of the last learning are updated; the value of n is determined according to the dictionary length of the word dictionary WordDict of the reading material, and n is an integer obtained by rounding up 5% of the dictionary length of the word dictionary WordDict;

[0277] For students learning reading materials, we also cannot accurately know which words the students did not master to cause them not to get full marks, and we also estimate according to the words with the highest recommendation values, so there may be a large error, so when calculating the reciprocal of the final mastery degree of these words, a memory influence coefficient R1 is introduced as an adjustment factor to calculate the reciprocal v4' of the latest mastery degree; the calculation formula is shown in formula (8):

[0278] v4'=R1*R*v4+(1-R1)*(1-R)*(1 / Mn) (8)

[0279] Where v4' is the reciprocal of the latest mastery degree, v4 is the reciprocal of the mastery degree at the last learning in the feature vector of the word, R is the memory retention rate of Ebbinghaus, that is: R = e^(-t / S); where e is the base number of natural logarithm, t is the forgetting time, in days, t = (ts-v5) / 86400; S is the relative memory strength, and the value is 1.84; ts is the current time stamp, and the time stamp when the reading material is completed is taken; v5 is the time stamp of the last learning in the word feature vector; Mn is the current mastery degree of the word; the value of Mn is determined by multiplying the final score by 100;

[0280] For example, if the total score of the current reading material is 60 points and the final score is 48 points, then the latest mastery degree Mn = 48 / 60*100 = 80;

[0281] R1 is the memory influence coefficient, and considering that the reciprocal of the mastery degree at the last learning has a greater influence and the reciprocal of the latest mastery degree has a smaller influence, the memory influence coefficient R1 in this embodiment is 0.85;

[0282] Then the reciprocal v4' of the latest mastery degree is replaced by the reciprocal of the mastery degree at the last learning in the word feature vector; finally, the word recommendation value WR of the word is recalculated according to the updated word feature vector using the calculation formula of the word recommendation value, and the word recommendation value dictionary WordRecommendDict is updated;

[0283] The updating process of the cumulative number of times of occurrence of a word in reading and learning and the timestamp of the last learning is consistent with that in word learning, which will not be described here.

[0284] S4, according to the grade information and the learning type, the selected learning materials are filtered out, the recommended value of the selected learning materials is calculated through the word dictionary WordDict and the word recommended value dictionary WordRecommendDict of the selected learning materials, and the learning material with the highest recommended value of the selected learning materials is pushed to the student.

[0285] Specifically, it includes:

[0286] S41, when recommending learning materials, first, according to the grade information and the learning type of the student, the learning materials suitable for the age of the student are selected as the selected learning materials;

[0287] The grade and the learning type are stored when the learning materials are stored in the warehouse, so they can be easily obtained. This is prior art, which will not be described here.

[0288] S42, according to all the words in the word dictionary of the selected learning materials, the word recommended value dictionary is traversed to find the m words with the highest word recommended value, and a material recommended dictionary is generated;

[0289] The format of the material recommended dictionary is consistent with that of the word dictionary WordDict. The m words with the highest word recommended value are selected from the word dictionary WordDict, and the m words are put into the material recommended dictionary according to the cumulative number of times of occurrence of the words in the learning materials from large to small;

[0290] The value of m is determined according to the dictionary length of the word dictionary WordDict of the selected learning materials. m is an integer obtained by rounding up 10% of the dictionary length of the word dictionary WordDict. The value of m can also be changed according to requirements, such as being changed to 15% or 20% of the dictionary length of the word dictionary WordDict, which is not limited here.

[0291] S43, if the learning type is oral, dictation, listening, reading or writing, the total recommended value of the learning materials is calculated according to the material recommended dictionary and formula (9), and the selected learning material with the highest total recommended value of the learning materials is pushed to the student;

[0292] ,

[0293] Wherein, MLR is the total recommended value of the learning materials, is the cumulative number of times of occurrence of the i-th word in the material recommended dictionary in the learning materials; is the word recommended value of the i-th word in the material recommended dictionary;

[0294] For example, all the learning materials with the age information of "third grade" and the learning type of "reading" are filtered from the learning material database, and a set of candidate materials is obtained. There are two candidate materials, material A and material B.

[0295] Material A: WordDict = {"apple": 5, "what": 2, "hello": 3...}, a total of 20 key-value pairs;

[0296] Material B: WordDict = {"apple": 3, "what": 4, "test": 2...}, a total of 20 key-value pairs;

[0297] WordRecommendDict = {"hello": 0.485, "apple": 0.378, "what": 0.395};

[0298] The m of the two materials is 20*10% = 2.

[0299] For material A:

[0300] The words in WordDict are sorted by the recommended value in WordRecommendDict, and the result is:

[0301] "hello" (WR=0.485) (recommended value 1), "what" (WR=0.395) (recommended value 2), "apple" (WR=0.378) (recommended value 3),..., and the first two words are obtained. Material recommendation dictionary A = {"hello": 3, "what": 2};

[0302] For material B:

[0303] The words in WordDict are sorted by the recommended value in WordRecommendDict, and the result is:

[0304] "what" (WR=0.395) (recommended value 1) > "apple" (WR=0.378) (recommended value 2) > "test" (0) (recommended value 3),..., and the first two words are obtained. Material recommendation dictionary B = {"what": 4, "apple": 3};

[0305] The total recommended value of the learning materials of material A is MLR_A = 3 / 1*0.485 + 2 / 2*0.395 = 1.85.

[0306] The total recommended value of the learning materials of material B is MLR_B = 4 / 1*0.395 + 3 / 2*0.378 = 2.336.

[0307] It can be seen that the total recommended value of the learning material of material B is greater than that of material A, so material B is pushed to the student for learning.

[0308] The dynamic weight formula of the total recommended value of the learning material of this embodiment balances the word recommended value and the actual use frequency, and the first m words are preferentially screened out according to the recommended value of WordRecommendDict, and then the dynamic weight Balancing the word recommended value and the actual occurrence frequency in the material, the system can accurately match the student's demand, preferentially push the material with high recommended value and high frequency, and this recommendation method combines the difficulty, importance, mastery degree and forgetting law of the word, and realizes more optimized personalized learning recommendation.

[0309] S44, if the learning type is word learning, the total recommended value of the learning material is calculated according to the material recommendation dictionary and formula (9), and the words in the word dictionary of the selected learning material with the highest total recommended value of the learning material are sorted according to their recommended value in the word recommended value dictionary from high to low and pushed to the student.

[0310] Further, the words in the WordDict of the selected learning material with the highest total recommended value of the learning material are sorted according to their recommended value in the WordRecommendDict from high to low, and a preset number of words can be selected and pushed according to the requirements. The preset number can be 5 by default, or it can be changed according to user needs.

[0311] Steps S3 and S4 form a closed loop, and the student will get learning materials containing the weakest words each time, and the learning results will be fed back to the feature vector and recommended value dictionary of each word. These information is used to determine the content of the next learning material, and so on, so as to greatly improve the efficiency of the student's English learning.

[0312] This embodiment solves the problems of low efficiency of traditional word learning, lack of personalized dynamic recommendation mechanism, and difficulty in adapting to multi-modal learning scenarios and individual memory decay law, and identifies the words to be strengthened from daily word learning, oral English, dictation, listening, reading and writing. Through the combination of dynamic feature engineering and multi-scene recommendation, long-term learning effect visualization closed loop optimization is realized, and the efficiency of word learning is effectively improved.

[0313] Further, the traditional word learning adopts fixed order or random repetition, without considering the dynamic changes of word difficulty and students' mastery level, resulting in inefficient repetition or omission of key words. The embodiment quantifies the word learning priority through feature vectors (such as the number of phonemes, importance, and cumulative appearance frequency reciprocal), adjusts the recommended value in combination with the dynamic performance of students, and realizes accurate learning; through the dynamic recommended value dictionary, the words with low mastery level, high importance, and consistent with the current learning type are preferentially pushed, reducing invalid repetition and shortening the time to meet the standard; the multi-dimensional feature vector (such as the timestamp decay memory curve and the cumulative appearance frequency reciprocal to avoid "high-frequency word monopoly") replaces the subjective experience ranking, making the learning path more consistent with the cognitive law.

[0314] Further, the traditional method lacks real-time feedback mechanism for students' learning behavior, and cannot dynamically adjust the learning strategy. The embodiment realizes continuous optimization of the learning path by dynamically updating the word feature vector (such as adjusting the "last mastery level reciprocal" according to the dictation error rate) through step S3, and reversely optimizes the word recommendation strategy (such as increasing the audio training weight of the error word in listening) in combination with the performance data in the oral and dictation scenarios, forming a "learning-evaluation-optimization" closed loop.

[0315] Further, through the timestamp and mastery level reciprocal in the feature vector, the word memory decay curve can be tracked, providing data support for subsequent review plan.

[0316] Embodiment two

[0317] Reference Figure 2 The embodiment provides a device for improving the word learning efficiency of primary and secondary school students, based on the above-mentioned method for improving the word learning efficiency of primary and secondary school students, comprising the following units:

[0318] An initialization unit is configured to define the feature vector of the word and the word list of the learning material; the feature vector includes the number of phonemes of the word, the importance of the word, the reciprocal of the cumulative appearance frequency of the word, the reciprocal of the mastery level in the last learning, and the timestamp of the last learning;

[0319] A construction unit is configured to establish the feature vector of all words in the English learning material according to the outline requirements and the content of the teaching material, then calculate the word recommended value according to the feature vector, initialize the word recommended value dictionary, and perform learning material warehousing; the learning material contains the corresponding word dictionary;

[0320] An updating unit is configured to dynamically update the word feature vector and the recommended value dictionary according to the performance of students in different learning types in the learning process; the learning types include word learning, oral English, dictation, listening, reading, and writing;

[0321] The recommendation unit is used to filter out alternative learning materials based on grade level and learning type. It calculates the recommendation value of the alternative learning materials using a vocabulary dictionary and a word recommendation value dictionary, and pushes the learning materials with the highest recommendation value to the students.

[0322] Example 3

[0323] refer to Figure 3 , Figure 3 This is a schematic diagram of the structure of a device for improving vocabulary learning efficiency for primary and secondary school students according to this embodiment. The device 20 for improving vocabulary learning efficiency for primary and secondary school students in this embodiment includes a processor 21, a memory 22, and a computer program stored in the memory 22 and executable on the processor 21. When the processor 21 executes the computer program, it implements the steps in the above method embodiments. Alternatively, when the processor 21 executes the computer program, it implements the functions of each module / unit in the above device embodiments.

[0324] For example, the computer program can be divided into one or more modules / units, which are stored in the memory 22 and executed by the processor 21 to complete the present invention. The one or more modules / units can be a series of computer program instruction segments capable of performing specific functions, which describe the execution process of the computer program in the device 20 for improving the vocabulary learning efficiency of primary and secondary school students. For example, the computer program can be divided into the modules shown in Embodiment 2. The specific functions of each module are described in the working process of the device described in the above embodiments, and will not be repeated here.

[0325] The device 20 for improving vocabulary learning efficiency for primary and secondary school students may include, but is not limited to, a processor 21 and a memory 22. Those skilled in the art will understand that the schematic diagram is merely an example of the device 20 for improving vocabulary learning efficiency for primary and secondary school students and does not constitute a limitation on the device 20. It may include more or fewer components than illustrated, or combine certain components, or use different components. For example, the device 20 for improving vocabulary learning efficiency for primary and secondary school students may also include input / output devices, network access devices, buses, etc.

[0326] The processor 21 can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic components, discrete hardware components, etc. The general-purpose processor can be a microprocessor or can also be any conventional processor. The processor 21 is a control center of the device 20 for improving the word learning efficiency of primary and secondary school students, and is connected to various parts of the device 20 for improving the word learning efficiency of primary and secondary school students through various interfaces and lines.

[0327] The memory 22 can be used to store computer programs and / or modules. The processor 21 realizes various functions of the device 20 for improving the word learning efficiency of primary and secondary school students by running or executing computer programs and / or modules stored in the memory 22, and calling data stored in the memory 22. The memory 22 can mainly include a program storage area and a data storage area. The program storage area can store an operating system, at least one application program required for a function (such as a sound playing function, an image playing function, etc.), etc. The data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory 22 can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one disk storage device, a flash memory device, or other volatile solid-state storage device.

[0328] The modules / units of the device 20 for improving the word learning efficiency of primary and secondary school students are integrated, and if they are realized in the form of software function units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the above-mentioned embodiment methods can also be completed by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when the processor 21 executes the computer program, the steps of the above-mentioned various method embodiments can be realized. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or some intermediate forms, etc. The computer-readable medium can include any entity or device that can carry the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc.

[0329] It should be noted that the above-described device embodiments are only illustrative, and the units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, i.e., they can be located in one place or distributed on multiple network units. Part or all of the modules can be selected to achieve the purpose of the embodiment according to actual needs. In addition, the connection relationship between the modules in the device embodiment provided by the present application indicates that there is a communication connection between them, which can be realized as one or more communication buses or signal lines. Those skilled in the art can understand and implement it without creative labor.

[0330] In this embodiment, the device can be a mobile phone or a tablet.

[0331] The parts of the present application not described in detail are prior art, and it is obvious to those skilled in the art that the present application is not limited to the details of the above-described exemplary embodiments, and the present application can be realized in other specific forms without departing from the spirit or basic characteristics of the present application; therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting, and all changes falling within the meaning and scope of the equivalent elements are intended to be included in the present application.

Claims

1. A method for improving vocabulary learning efficiency for primary and secondary school students, characterized in that, Specifically, the following steps are included: S1. Define the feature vector of a word and the word list of the learning material; the feature vector includes the number of syllables of the word, the word importance, the reciprocal of the cumulative number of times the word appears, the reciprocal of the mastery level at the time of the last learning, and the timestamp of the last learning. S2. Based on the syllabus requirements and textbook content, establish feature vectors for all words in the English learning materials, then calculate word recommendation values ​​based on the feature vectors, initialize the word recommendation value dictionary, and input the learning materials into the database; the learning materials include the corresponding word dictionary; S3. Dynamically update the word feature vector and word recommendation value dictionary based on the student's performance in different learning types during the learning process; the learning types include word learning, speaking, dictation, listening, reading, and writing; When the learning type is word learning, during the word learning, reading and spelling process, update the reciprocal of the cumulative number of times the word appears in the corresponding feature vector, the reciprocal of the mastery level at the last learning time, and the timestamp of the last learning time, and recalculate the word recommendation value, thereby updating the word recommendation value dictionary; The reciprocal of the cumulative occurrence count of a word is obtained as follows: take the reciprocal of the cumulative occurrence count of a word in the word feature vector, add 1, and then take the reciprocal again to obtain the latest reciprocal of the cumulative occurrence count of a word. Update the timestamp of the last learning session to the timestamp when the current word was learned; The word pronunciation accuracy score Fl, spelling accuracy score Sp, and time efficiency score Te are used to calculate the reciprocal v4' of the latest mastery level of the word using formulas (5)-(6). This reciprocal is then used to replace the reciprocal of the mastery level of the word feature vector at the time of the last learning. Finally, the word recommendation value WR is recalculated based on the updated word feature vector using the formula for calculating the word recommendation value, thereby updating the word recommendation value dictionary. Formulas (5)-(6) are shown below: Mn=[Fl*a+Sp*b+Te*c] (5) Where Mn represents the current mastery level of the word, a represents the weight of the reading accuracy score, b represents the weight of the spelling accuracy score, and c represents the weight of the time efficiency score; a+b+c=1; The formula for calculating the reciprocal v4' of the latest level of mastery is shown in formula (6): v4'=R*v4+(1-R)*(1 / Mn) (6) Where v4' is the reciprocal of the latest mastery level, v4 is the reciprocal of the mastery level at the last learning time in the feature vector of the word, and R is the Ebbinghaus forgetting curve retention rate; S4. Select alternative learning materials based on grade level and learning type. Calculate the recommendation value of the alternative learning materials using a vocabulary dictionary and a word recommendation value dictionary. Push the learning materials with the highest recommendation value to the students.

2. The method according to claim 1, characterized in that, In step S2, the feature vector is used to calculate the word recommendation value WR using formula (1), which is shown below: WR=W1*v1+W2*v2+W3*v3+W4*v4+W5*v5' (1) Wherein, v1 is the number of syllables in a word, and W1 is the weight of the number of syllables in a word; v2 is the importance of a word, and W2 is the weight of the importance of a word; v3 is the reciprocal of the cumulative number of occurrences of a word, and W3 is the weight of the reciprocal of the cumulative number of occurrences of a word; v4 is the reciprocal of the level of mastery at the time of the last learning, and W4 is the weight of the reciprocal of the level of mastery at the time of the last learning; v5' is the forgetting coefficient obtained by converting the timestamp v5 of the last learning, and W5 is the weight of the forgetting coefficient.

3. The method according to claim 2, characterized in that, The formula for calculating the forgetting coefficient is shown in formula (2): Fc=1-R (2) Where Fc is the forgetting coefficient; R is the Ebbinghaus forgetting curve, i.e., R=e^(-t / S), where e is the base of the natural logarithm, t is the forgetting time in days, t=(ts-v5) / 86400; S is the relative memory strength, with a value of 1.84; ts is the current timestamp, and v5 is the timestamp of the last learning in the feature vector.

4. The method according to claim 1, characterized in that: A word pronunciation accuracy score, Fl, is obtained by scoring the pronunciation of the words being read aloud using third-party speech recognition technology. The spelling accuracy score Sp is determined according to formula (3): Sp = [(correctNum / totalNum) * 100] (3) Where, correctNum is the number of letters spelled correctly, totalNum is the total number of letters in the word, and [] is the rounding symbol; the time efficiency score Te is determined based on the time to spell a correct word, as shown in formula (4); Te = Min[(T / t)*100,100] (4) Where Te is the time efficiency score, T=n*T1, T1 is the time taken to input an English letter on the electronic device, in ms, n represents the number of letters in the word, and t is the actual time taken for the user to input a word, in ms.

5. The method according to claim 1, characterized in that, Step S3 specifically also includes: When the learning type is spoken language, the pronunciation score of each word in the sentence is identified by speech recognition technology, and the current mastery level of each word is calculated based on the pronunciation score of each word. Then, the reciprocal of the latest mastery level of the word is calculated according to formula (6), and the reciprocal of the cumulative occurrence of the word in the corresponding feature vector, the reciprocal of the mastery level at the last learning time, and the timestamp of the last learning time are updated. Then, the word recommendation value is recalculated, and the word recommendation value dictionary is updated.

6. The method according to claim 4, characterized in that, Step S3 specifically also includes: When the learning type is dictation, different methods are used to determine the current mastery of words based on the spelling accuracy score of the words. Then, the current mastery of the words is calculated by formula (6) to calculate the reciprocal of the latest mastery of the words. Then, the reciprocal of the cumulative occurrence of the words in the corresponding feature vector, the reciprocal of the mastery at the last learning time, and the timestamp of the last learning time are updated. The word recommendation value is recalculated and the word recommendation value dictionary is updated. When the word is spelled completely correctly, the time efficiency score Te is calculated using formula (4) and used as the current mastery level Mn of the word, i.e., Mn=Te; When a word is not spelled completely correctly, the current mastery level Mn of the word is calculated using formula (7): Mn = U1*Sp+(1-U1)*Te (7) Where U1 is an empirical value, a floating-point number between 0 and 1.

7. The method according to claim 1, characterized in that, Step S3 specifically also includes: When the learning type is listening or reading, if the listening or reading answers are completely correct, iterate through all the words in the vocabulary of the listening or reading material. If the word iterates through is in the recommendation value dictionary, update the reciprocal of the cumulative occurrence of the word in the feature vector corresponding to the word and the timestamp of the last learning, and set the current mastery level Mn of the word to 100; then calculate the reciprocal v4' of the latest mastery level of the word according to formula (6) based on the current mastery level Mn of the word. If the listening or reading answers are not entirely correct, then the word recommendation value dictionary is traversed according to all words in the vocabulary dictionary of the listening or reading material to find the n words with the highest word recommendation value as the words that were not understood, and the inverse of the cumulative occurrence count of the word and the timestamp of the last learning are updated in the feature vector of the words that were not understood; the value of n is determined according to the length of the vocabulary dictionary of the listening material; the inverse of the latest mastery level v4' is calculated according to formula (8): v4'=R1*R*v4+(1-R1)*(1-R)*(1 / Mn) (8) Where v4' is the reciprocal of the latest mastery level, v4 is the reciprocal of the mastery level at the last learning time in the feature vector of the word, R is the Ebbinghaus forgetting curve retention rate, Mn is the current mastery level of the word, and R1 is the memory influence coefficient. Then, the reciprocal v4' of the latest mastery level is replaced with the reciprocal of the mastery level at the time of the last learning in the word feature vector; finally, the word recommendation value is recalculated using the word recommendation value calculation formula and the updated word feature vector, thereby updating the word recommendation value dictionary.

8. The method according to claim 1, characterized in that, Step S4 specifically includes the following steps: S41. When recommending learning materials, first select learning materials suitable for the student's age group as alternative learning materials based on the student's grade information and learning type. S42. Based on all the words in the vocabulary dictionary of the candidate learning materials, traverse the word recommendation value dictionary, find the m words with the highest word recommendation values, and generate a material recommendation dictionary; S43. If the learning type is oral, dictation, listening, reading or writing, the total recommendation value of the learning materials is calculated according to the material recommendation dictionary and formula (9), and the alternative learning materials with the highest total recommendation value are pushed to the students. ， Wherein, MLR is the overall recommendation score for learning materials. Recommend the cumulative number of times the i-th word in the dictionary appears in the learning material; Recommend the word value of the i-th word in the dictionary for the material.

9. A device for improving vocabulary learning efficiency for primary and secondary school students, characterized in that, Includes the following units: An initialization unit is used to define the feature vector of a word and the word list of the learning material; the feature vector includes the number of syllables of the word, the word importance, the reciprocal of the cumulative number of times the word appears, the reciprocal of the mastery level at the time of the last learning, and the timestamp of the last learning. The construction unit is used to build feature vectors for all words in the English learning materials according to the syllabus requirements and textbook content, then calculate word recommendation values ​​based on the feature vectors, initialize the word recommendation value dictionary, and input the learning materials into the database; the learning materials include the corresponding word dictionary; The update unit is used to dynamically update the word feature vector and word recommendation value dictionary based on the student's performance in different learning types during the learning process; the learning types include word learning, oral communication, dictation, listening comprehension, reading, and writing. When the learning type is word learning, during the word learning, reading and spelling process, update the reciprocal of the cumulative number of times the word appears in the corresponding feature vector, the reciprocal of the mastery level at the last learning time, and the timestamp of the last learning time, and recalculate the word recommendation value, thereby updating the word recommendation value dictionary; The reciprocal of the cumulative occurrence count of a word is obtained as follows: take the reciprocal of the cumulative occurrence count of a word in the word feature vector, add 1, and then take the reciprocal again to obtain the latest reciprocal of the cumulative occurrence count of a word. Update the timestamp of the last learning session to the timestamp when the current word was learned; The word pronunciation accuracy score Fl, spelling accuracy score Sp, and time efficiency score Te are used to calculate the reciprocal v4' of the latest mastery level of the word using formulas (5)-(6). This reciprocal is then used to replace the reciprocal of the mastery level of the word feature vector at the time of the last learning. Finally, the word recommendation value WR is recalculated based on the updated word feature vector using the formula for calculating the word recommendation value, thereby updating the word recommendation value dictionary. Formulas (5)-(6) are shown below: Mn=[Fl*a+Sp*b+Te*c] (5) Where Mn represents the current mastery level of the word, a represents the weight of the reading accuracy score, b represents the weight of the spelling accuracy score, and c represents the weight of the time efficiency score; a+b+c=1; The formula for calculating the reciprocal v4' of the latest level of mastery is shown in formula (6): v4'=R*v4+(1-R)*(1 / Mn) (6) Where v4' is the reciprocal of the latest mastery level, v4 is the reciprocal of the mastery level at the last learning time in the feature vector of the word, and R is the Ebbinghaus forgetting curve retention rate; The recommendation unit is used to filter out alternative learning materials based on grade level and learning type. It calculates the recommendation value of the alternative learning materials using a vocabulary dictionary and a word recommendation value dictionary, and pushes the learning materials with the highest recommendation value to the students.

Images