Intelligent English learning system and device
Through the intelligent English learning system, automatic speech recognition and deep learning models are used to evaluate users' pronunciation and writing status, and learning strategies are automatically adjusted, solving the complex operation of existing English learning equipment and improving learning efficiency and user experience.
Patent Information
- Application Number
- CN202411438226.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-15
- Publication Date
- 2024-12-06
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing English learning equipment is complex in operation, especially unfriendly to elderly users, resulting in low learning efficiency and reduced enthusiasm.
Design an intelligent English learning system, including data collection module, information classification module, reading and writing module, receiving module and judgment module, to obtain English words in real time through the Internet, and automatically adjust the playback time of words according to the user's follow-up and copying and dictation status. , frequency and copy time, provide electronic pen and handwriting modes, and use automatic speech recognition and deep learning models to evaluate user pronunciation and writing status.
It simplifies the operation process, reduces visual fatigue, provides personalized learning, adjusts learning strategies in real time, improves learning efficiency, and helps users understand learning status and direction of improvement through instant feedback.
Smart Images

Figure CN119091700A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to an English learning device, and in particular to an intelligent English learning system and device. Background Art
[0002] English teaching is a systematic and in-depth process, which aims to impart English knowledge to learners of English as their first language or non-first language. This process integrates a diversified professional theoretical framework, covering the foundation of linguistics, second language acquisition theory, the essence of lexicology, syntactic analysis, stylistics, corpus linguistics application and cognitive psychology principles. In the current era of rapid globalization, English, as a key medium for international communication, is particularly critical and important for everyone to learn.
[0003] With the acceleration of global integration, the status of English as a global common language has become increasingly prominent, making English teaching in vocational education occupy an irreplaceable position in the education system. Therefore, continuously optimizing English teaching strategies and improving teaching quality are not only to meet the needs of personal growth and career development, but also to meet the new challenges of the era of globalization. Therefore, more and more elderly people are starting to learn English at home, trying to keep up with the times.
[0004] However, although the existing English learning devices are quite powerful in terms of functional design and cover a wide range of learning needs, this complexity also leads to a cumbersome operating interface, which is particularly unfriendly to the elderly user group. The complex operating process and the less intuitive human-computer interaction design not only fail to give full play to the learning assistance effect of the equipment, but may also reduce the enthusiasm and initiative of the elderly in learning English.
[0005] Therefore, there is an urgent need for an intelligent English learning system and equipment to solve the technical problems existing in the above-mentioned prior art. Summary of the invention
[0006] The present invention overcomes the deficiencies of the prior art and provides an intelligent English learning system and equipment.
[0007] To achieve the above object, the technical solution adopted by the present invention is: an intelligent English learning system, including: a data collection module, an information classification module, a reading and writing module, a receiving module, and a judgment module; including the following steps:
[0008] S1. The data collection module automatically obtains various English words on the Internet based on real-time Internet collection technology and stores them in the database as a knowledge source;
[0009] S2, the information classification module divides English words into three levels: simple, medium and difficult according to their relevant attributes, and each is stored in a separate vocabulary library;
[0010] S3, the reading and writing module randomly extracts multiple words to form a vocabulary group according to the vocabulary library selected by the user and shuffles the order;
[0011] S4, the receiving module feeds back the vocabulary group randomly selected in step S3 to the user in the form of loudspeaker playback, and obtains the user's follow-up reading and copying of the word by setting the playback duration, frequency and copying time of a single word, and repeating it multiple times;
[0012] S5, the judgment module obtains the user's reading and copying and writing in step S4, and obtains the user's word mastery according to the pronunciation judgment standard principle and the copying and writing fluency judgment principle; the judgment module feeds back the word mastery to the receiving module, and the receiving module deletes and re-sorts the words in the obtained vocabulary group according to the user's word mastery, and repeats steps S3-S5 until the user fully masters all the words in the vocabulary group.
[0013] In a preferred embodiment of the present invention, the copying and dictation situation in the receiving module includes two modes: electronic pen copying and handwriting; the electronic pen copying mode captures the movement trajectory and pressure change information of the pen tip on the writing screen of the electronic device, and sends it to the electronic device in the form of an electrical signal to obtain the copying situation in the electronic pen copying mode; the handwriting mode is applied to users who are not accustomed to using the electronic pen copying mode, and the electronic device obtains the user's handwriting situation through scanning imaging technology, and the copying and dictation situation includes the copying situation and the handwriting situation.
[0014] In a preferred embodiment of the present invention, the determination process of the pronunciation determination standard principle includes the following steps:
[0015] S501, obtaining the pronunciation of the word when the user follows the reading, converting it into a voice signal that can be received by the computer system, and pre-processing the voice signal to obtain acoustic features representing the pronunciation quality;
[0016] S502, establishing a speech model, using automatic speech recognition technology to convert the pre-processed speech signal into a phoneme sequence, and combining it with the acoustic features obtained in step S501 to obtain a feature vector;
[0017] S503, collecting and arranging speech data of standard pronunciation, and using it as a judgment basis for pronunciation standard, and obtaining a familiarity score based on the feature vector obtained in step S502;
[0018] S504: Establish a scoring model, map the similarity score to a specific score or grade, and feed back the obtained score or grade to the user in real time.
[0019] In a preferred embodiment of the present invention, the determination process of the fluency principle of copying and dictation includes the following steps:
[0020] S511, establishing a deep learning model, clarifying the obtained copying and dictation situation, converting the user's input into a standard text format, and then evaluating the accuracy of the obtained text format and the correct answer;
[0021] S512, monitoring the speed at which the user writes words, analyzing whether there is any unsmoothness during the writing process, and evaluating the standardization of the written word shape;
[0022] S513. A mapping relationship between the fluency index and the word mastery proficiency is established, and a user's word mastery proficiency score is given in combination with factors such as writing speed, continuity, and character shape standardization.
[0023] In a preferred embodiment of the present invention, the word mastery conditions include three conditions: proficient mastery of a single word, hearing and reading difficulties, and copying and dictation difficulties; in the case of proficient mastery, the receiving module deletes the mastered word from the vocabulary group; when hearing and reading difficulties occur, the receiving module adjusts the playback duration and frequency of the single word in real time; when copying and dictation difficulties occur, the receiving module adjusts the copying and dictation time of the single word in real time, and adds the amplified playback during the copying and dictation process.
[0024] In a preferred embodiment of the present invention, the preprocessing includes: noise removal, speech enhancement, and endpoint detection; the acoustic features include: Mel-frequency cepstral coefficients, fundamental frequency, and resonance peaks.
[0025] In a preferred embodiment of the present invention, the deep learning model is a convolutional neural network, a recurrent neural network or one of their variants, and the clarity processing includes: image denoising, binarization, and normalization; by recording the timestamp information of the user's writing process, the writing speed of the word is calculated, and by analyzing the continuity and smoothness characteristics of the writing trajectory, the writing fluency of the word is evaluated.
[0026] In a preferred embodiment of the present invention, there is provided an intelligent English learning device for loading the intelligent English learning system provided above, comprising: a control unit, a display unit and a pad; characterized in that: the display unit comprises: a display screen, a button group, an electronic pen and a power cord; the pad comprises: a limit card block, a column and a scanning imager; the limit card block is used to fix the display unit, and the scanning imager is fixed at the end of the column for scanning words handwritten by the user.
[0027] In a preferred embodiment of the present invention, the button group includes: a power button, a voice transcription button, a voice dictation button, a silent dictation button, a pause button, a repeat button, a volume up button and a volume down button; when the voice transcription button is pressed, the display screen displays the word accompanied by amplified playback; when the voice dictation button is pressed, the display screen hides the word accompanied by amplified playback; when the silent dictation button is pressed, the display screen hides the word and turns off the amplified playback.
[0028] In a preferred embodiment of the present invention, the scanning imager is one of a charge coupled device, a complementary metal oxide semiconductor sensor or an OCR engine; the scanning imager is also provided with a video recording system for real-time monitoring of the user's writing situation.
[0029] The present invention solves the defects existing in the background technology and has the following beneficial effects:
[0030] (1) The present invention is provided with a button group with different functions, so that when using it, the elderly can understand and operate it more easily, thereby intuitively reducing the complexity of operation, so that the elderly can achieve the desired functions without complicated menu navigation, and by using amplified playback to feedback vocabulary, the elderly do not need to stare at the screen for a long time, reducing visual fatigue; at the same time, two modes of electronic pen copying and handwriting are provided, especially the handwriting mode, which is more friendly to the elderly who are accustomed to traditional writing methods and reduces the obstacles to learning new tools.
[0031] (2) The present invention automatically divides the words into three levels: simple, medium and difficult according to their difficulty. Users can choose a suitable vocabulary library to learn according to their own level, thus realizing personalized learning. At the same time, the system can adjust the playback duration, frequency and copying time of the words in real time according to the user's reading and copying situation, ensuring that the learning difficulty matches the user's actual mastery and improving learning efficiency.
[0032] (3) The system provided by the present invention can accurately judge the pronunciation and writing of users, and accurately identify the listening and reading difficulties and copying and dictation difficulties of users. And for the identified learning shortcomings, the system can automatically adjust the learning strategy, such as increasing the number of playbacks, extending the copying time, etc., to help users conduct targeted intensive training. At the same time, the system can also continuously track the user's learning progress to ensure that each word is fully mastered, and provide instant feedback to help users clarify their learning status and improvement direction. BRIEF DESCRIPTION OF THE DRAWINGS
[0033] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art are briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work.
[0034] Figure 1 is a schematic diagram of the structure of a display unit of the present invention;
[0035] Figure 2 It is a structural schematic diagram of the pad of the present invention;
[0036] Figure 3 is a flow chart of the English learning system of the present invention;
[0037] Figure 4 It is a judgment flow chart of the pronunciation judgment standard principle of the present invention;
[0038] Figure 5 It is a judgment flow chart of the smoothness principle of copying and dictation of the present invention.
[0039] In the figure:
[0040] 1. Display unit; 1.1. Display screen; 1.2. Button group; 1.3. Electronic pen; 1.4. Power cord;
[0041] 2. Pad; 2.1. Limiting block; 2.2. Column; 2.3. Scanning imager. DETAILED DESCRIPTION
[0042] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0043] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.
[0044] In the description of the present application, it should be understood that the terms "center", "longitudinal", "lateral", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the scope of protection of the present application. In addition, the terms "first", "second", etc. are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, features defined as "first", "second", etc. may explicitly or implicitly include one or more of the features. In the description of the invention, unless otherwise specified, "multiple" means two or more.
[0045] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood by specific circumstances.
[0046] like Figure 1 As shown, an English learning device for loading the above-mentioned intelligent English learning system is provided, comprising: a control unit, a display unit 1 and a pad 2; characterized in that: the display unit 1 comprises: a display screen 1.1, a button group 1.2, an electronic pen 1.3 and a power cord 1.4; the pad 2 comprises: a limit card block 2.1, a column 2.2 and a scanning imager 2.3; the limit card block 2.1 is used to fix the display unit 1, and the scanning imager 2.3 is fixed at the end of the column 2.2 for scanning the user's handwritten words.
[0047] In a preferred embodiment, the control unit is used to ensure that the system can accurately execute various programs and commands and maintain the program of the English learning system.
[0048] like Figure 2 As shown, the button group includes: a power button, an audio transcription button, an audio dictation button, a silent dictation button, a pause button, a repeat button, a volume up button, and a volume down button; when the audio transcription button is pressed, the display screen displays the word accompanied by loudspeaker playback; when the audio dictation button is pressed, the display screen hides the word accompanied by loudspeaker playback; when the silent dictation button is pressed, the display screen hides the word and turns off the loudspeaker playback.
[0049] The scanning imager is one of a charge coupled device, a complementary metal oxide semiconductor sensor or an OCR engine; the scanning imager is also provided with a video recording system for real-time monitoring of the user's writing situation.
[0050] like Figure 3 As shown, an intelligent English learning system includes: a data collection module, an information classification module, a reading and writing module, a receiving module, and a judgment module; including the following steps:
[0051] S1. The data collection module automatically obtains various English words on the Internet based on real-time Internet collection technology and stores them in the database as a knowledge source;
[0052] S2, the information classification module divides English words into three levels: simple, medium and difficult according to their relevant attributes, and each is stored in a separate vocabulary library;
[0053] S3, the reading and writing module randomly extracts multiple words to form a vocabulary group according to the vocabulary library selected by the user and shuffles the order;
[0054] S4, the receiving module feeds back the vocabulary group randomly selected in step S3 to the user in the form of loudspeaker playback, and obtains the user's follow-up reading and copying of the words by setting the playback duration, frequency and copying time of a single word, and repeating it multiple times;
[0055] In a preferred embodiment, the copying and dictation conditions in the receiving module include two modes: electronic pen copying and handwriting; the electronic pen copying mode captures the movement trajectory and pressure change information of the pen tip on the writing screen of the electronic device, and sends it to the electronic device in the form of an electrical signal to obtain the copying conditions in the electronic pen copying mode; the handwriting mode is applied to users who are not accustomed to using the electronic pen copying mode, and the electronic device obtains the user's handwriting conditions through scanning imaging technology, and the copying and dictation conditions include copying conditions and handwriting conditions.
[0056] S5, the judgment module obtains the user's reading and copying and writing in step S4, and obtains the user's word mastery according to the pronunciation judgment standard principle and the copying and writing fluency judgment principle; the judgment module feeds back the word mastery to the receiving module, and the receiving module deletes and re-sorts the words in the obtained vocabulary group according to the user's word mastery, and repeats steps S3-S5 until the user fully masters all the words in the vocabulary group.
[0057] The word mastery conditions include three conditions: proficient mastery of a single word, listening and reading difficulties, and copying and dictation difficulties. In the case of proficient mastery, the receiving module deletes the mastered word from the vocabulary group; when listening and reading difficulties occur, the receiving module adjusts the playback duration and frequency of the single word in real time; when copying and dictation difficulties occur, the receiving module adjusts the copying and dictation time of the single word in real time, and adds amplified playback during the copying and dictation process.
[0058] like Figure 4 As shown, in a preferred embodiment, the determination process of the pronunciation determination standard principle includes the following steps:
[0059] S501, obtaining the pronunciation of the word when the user follows the reading, converting it into a voice signal that can be received by the computer system, and pre-processing the voice signal to obtain acoustic features representing the pronunciation quality;
[0060] Preprocessing includes: noise removal, speech enhancement, and endpoint detection; acoustic features include: Mel-frequency cepstral coefficients, fundamental frequency, and resonance peak.
[0061] What needs further explanation here is that acoustic features refer to the physical quantities that represent the acoustic characteristics of speech, and are also a general term for the acoustic manifestations of various sound elements.
[0062] S502, establishing a speech model, using automatic speech recognition technology to convert the pre-processed speech signal into a phoneme sequence, and combining it with the acoustic features obtained in step S501 to obtain a feature vector;
[0063] S503, collecting and arranging speech data of standard pronunciation, and using it as a judgment basis for pronunciation standard, and obtaining a familiarity score based on the feature vector obtained in step S502;
[0064] S504: Establish a scoring model, map the similarity score to a specific score or grade, and feed back the obtained score or grade to the user in real time.
[0065] Based on the above pronunciation judgment criteria, the specific process of obtaining the familiarity score is as follows:
[0066] The acoustic feature vector of the existing standard pronunciation S = {S1, S2, ..., S n-1 , S n};
[0067] The acoustic features of the user's pronunciation quality obtained in step S501 are combined with the phoneme sequence obtained in step S502 to obtain an acoustic feature vector F of the user's pronunciation = {f1, f2, ..., f n-1 , f n};
[0068] Among them, Sn is the nth acoustic feature corresponding to the standard pronunciation, f n is the nth acoustic feature of the user's pronunciation.
[0069] The difference between the user's pronunciation and the standard pronunciation is calculated by the acoustic feature similarity score calculation formula. The calculation expression is:
[0070]
[0071] Where, H is the acoustic feature similarity; f is n is the nth acoustic feature of the user’s pronunciation; S n is the nth acoustic feature corresponding to the standard pronunciation; d is the function that calculates the difference between the standard pronunciation and the user's pronunciation; N is the total number of acoustic features; max(d) is the sum of all d(f n , S n ); M is the number of phonemes that match the phoneme sequence pronounced by the user with the phoneme sequence of the standard pronunciation; L is the total number of phonemes in the phoneme sequence of the standard pronunciation.
[0072] In the above calculation expression,
[0073] Where m is the dimension of each acoustic feature, f ni and S mi are the values of the user and standard pronunciation on the i-th dimension of the n-th feature, respectively.
[0074] In a preferred embodiment, a scoring threshold is set in the system. When the score reaches or exceeds the set scoring threshold, the pronunciation can be considered correct or acceptable; if it is lower than the threshold, the pronunciation is considered to need improvement.
[0075] like Figure 5 As shown in the figure, the process of determining the fluency principle of copying and dictation includes the following steps:
[0076] S511, establishing a deep learning model, clarifying the obtained copying and dictation situation, converting the user's input into a standard text format, and then evaluating the accuracy of the obtained text format and the correct answer;
[0077] The accuracy is calculated by evaluating the calculation expression, which is:
[0078] In the formula, A is the accuracy rate; P is the correct characters copied from the dictation; and Q is the total number of characters in the standard answer.
[0079] S512, monitoring the speed at which the user writes words, analyzing whether there is any unsmoothness during the writing process, and evaluating the standardization of the written word shape;
[0080] The user's writing speed refers to the relationship between the time it takes for the user to complete the copying or dictation task and the total amount of writing, and its expression is:
[0081] Where W is the user's writing speed; R is the total number of words written by the user; and T is the time taken to write.
[0082] Disfluency refers to the ratio of the number of pauses during copying or memorizing to the total number of words. The calculation expression is:
[0083] Where D is the index of disfluency; G is the number of pauses the user makes during copying or memorizing; and Q is the total number of characters in the standard answer.
[0084] Standardization is calculated by comparing the degree to which each character written by the user matches the standard glyph. The calculation expression is:
[0085] Among them, L is the index of the standardization of the characters written by the user; X is the number of standard characters in the written characters; and R is the total number of characters written by the user.
[0086] S513. A mapping relationship between the fluency index and the word mastery proficiency is established, and a user's word mastery proficiency score is given in combination with factors such as writing speed, continuity, and character shape standardization.
[0087] Based on the accuracy rate and the index of disfluency obtained by the above calculation, the proficiency score is calculated, and its calculation expression is: E = α*A + β*W + δ*(1-D) + γ*L;
[0088] Among them, α, β, δ, and γ are the weights of different factors, which are adjusted according to the importance of the copying or dictation task, and the sum of α, β, δ, and γ is 1.
[0089] What needs to be further explained here is that the deep learning model is one of the convolutional neural network, recurrent neural network or its variants. The clarity processing includes: image denoising, binarization, and normalization. By recording the timestamp information of the user's writing process, the writing speed of the word is calculated, and by analyzing the continuity and smoothness of the writing trajectory, the writing fluency of the word is evaluated.
[0090] Embodiment 1
[0091] English words are collected from educational websites, online dictionaries and academic articles using crawler technology. The words and their attributes such as part of speech, meaning, and example sentences are also stored in the database.
[0092] Based on the frequency of word usage, difficulty and user feedback, words are divided into three levels: easy, medium and difficult, and an independent vocabulary library is established for each level.
[0093] After the user selects a learning level, the system randomly extracts 20 words from the corresponding vocabulary library, shuffles the order of the words, and forms a vocabulary group.
[0094] Use text-to-speech (TTS) technology to play words, set the playback parameters: play each word 3 times, with a 2-second interval between each play. The user reads and transcribes the words, and the system records the reading and transcription.
[0095] The system analyzes the user's reading and copying data, and evaluates the user's mastery of words based on pronunciation criteria and fluency principles for copying and writing.
[0096] Set pronunciation judgment criteria: Use speech recognition technology to convert the user's reading into text, and calculate the similarity score between the user's pronunciation and the standard pronunciation. If the similarity score is higher than the set threshold, the pronunciation is considered correct.
[0097] Optical character recognition (OCR) technology was used to assess handwriting transcription, calculate accuracy, writing speed, disfluency index, and formality index, and these indicators were combined to calculate the proficiency score.
[0098] In this embodiment, specifically, an elderly user is using the English device and learning system provided by the present invention to learn the following vocabulary group of 20 words:
[0099] Apple,banana,cat,dog,elephant,fish,goat,hat,ice cream,jelly,kite,lemon,mango,nut,orange,pen,queen,rabbit,sun,tree,umbrella,violin,watermelon,xylophone,yellow,zebra.
[0100] The acoustic feature values of the user pronunciation and standard pronunciation of banana and elephant are shown in the following table:
[0101] Table 1
[0102] Standard Pronunciation User Pronunciation banana 0.85 0.75 elephant 0.81 0.83
[0103] From the above, it can be seen that the acoustic feature value of the user's pronunciation of "banana" is lower than the acoustic feature value of the standard pronunciation. Therefore, there is still a certain error in the user's pronunciation of "banana" and further practice is needed; the acoustic feature value of the user's pronunciation of "elephant" is higher than the acoustic feature value of the standard pronunciation, which indicates that the user's pronunciation of "elephant" is more accurate.
[0104] When the user copied "banana", the writing speed was 36 letters per minute, and he paused twice during the copying process. The writing accuracy was 95%.
[0105] When the user copied "elephant", the writing speed was 29 letters per minute, and he paused 5 times during the copying process. The writing accuracy was 85%.
[0106] When the present invention is used, the user starts the English learning device, the device performs self-checking and loads the learning system, and automatically collects English words from the Internet and stores them in a database, and divides the words into simple, medium and difficult levels according to their difficulty, and stores them in the corresponding vocabulary library.
[0107] The user selects the learning level and selects the transcription mode. The system randomly extracts words from the selected vocabulary and shuffles the order, and displays the word list on the display screen 1.1 for the user to learn.
[0108] The user presses the "audio transcription key" or "audio dictation key", and the receiving module plays the pronunciation of the word through the loudspeaker, and the user follows along.
[0109] The user writes words using an electronic pen or by hand. When the electronic pen is selected, the pen tip movement and pressure changes are captured and converted into electrical signals; when the handwritten word is selected, the scanning imager captures the handwritten image.
[0110] The receiving module records the user's follow-up reading and transcription in real time; the judging module obtains the follow-up reading and transcription data and performs standard evaluation on the user's pronunciation and transcription.
[0111] Pronunciation judgment criteria: preprocess user voice signals, extract acoustic features, build a voice model, convert voice signals into phoneme sequences, compare with standard pronunciation, and calculate similarity scores.
[0112] Fluency Principles for Determining Dictation: Use a deep learning model to clarify the transcription situation and calculate the accuracy, writing speed, disfluency index, and standardization index. Finally, combine the evaluation results of pronunciation and transcription to calculate the proficiency score.
[0113] Users can adjust their learning plans based on their proficiency scores: the system will delete the proficient words from the list, and in subsequent use, adjust the playback duration and frequency for words with listening and reading difficulties, and adjust the copying time and playback strategy for words with copying and dictation difficulties, and repeat the learning process steps until the user masters all the words.
[0114] The above is based on the ideal embodiment of the present invention. Through the above description, relevant personnel can make various changes and modifications without departing from the technical concept of the present invention. The technical scope of the present invention is not limited to the content in the specification, and the technical scope must be determined according to the scope of the claims.
Claims
1. An intelligent English learning system, comprising: Data collection module, information classification module, reading and writing module, receiving module, and judgment module; characterized in that it includes the following steps: S1. The data collection module automatically obtains various English words on the Internet based on real-time Internet collection technology and stores them in the database as a knowledge source; S2, the information classification module divides English words into three levels: simple, medium and difficult according to their relevant attributes, and each is stored in a separate vocabulary library; S3, the reading and writing module randomly extracts multiple words to form a vocabulary group according to the vocabulary library selected by the user and shuffles the order; S4, the receiving module feeds back the vocabulary group randomly selected in step S3 to the user in the form of loudspeaker playback, and obtains the user's follow-up reading and copying of the word by setting the playback duration, frequency and copying time of a single word, and repeating it multiple times; S5, the judgment module obtains the user's reading and copying and writing in step S4, and obtains the user's word mastery according to the pronunciation judgment standard principle and the copying and writing fluency judgment principle; the judgment module feeds back the word mastery to the receiving module, and the receiving module deletes and re-sorts the words in the obtained vocabulary group according to the user's word mastery, and repeats steps S3-S5 until the user masters all the words in the vocabulary group.
2. The intelligent English learning system according to claim 1, characterized in that: The copying and dictation situations in the receiving module include two modes: electronic pen copying and handwriting; the electronic pen copying mode captures the movement trajectory and pressure change information of the pen tip on the writing screen of the electronic device, and sends them to the electronic device in the form of an electrical signal to obtain the copying situation in the electronic pen copying mode; the handwriting mode is applied to users who are not accustomed to using the electronic pen copying mode, and the electronic device obtains the user's handwriting situation through scanning imaging technology, and the copying and dictation situation includes the copying situation and the handwriting situation.
3. The intelligent English learning system according to claim 1, characterized in that: The determination process of the pronunciation determination standard principle comprises the following steps: S501, obtaining the pronunciation of the word when the user follows the reading, converting it into a voice signal that can be received by the computer system, and pre-processing the voice signal to obtain acoustic features representing the pronunciation quality; S502, establishing a speech model, using automatic speech recognition technology to convert the pre-processed speech signal into a phoneme sequence, and combining it with the acoustic features obtained in step S501 to obtain a feature vector; S503, collecting and arranging speech data of standard pronunciation, and using it as a judgment basis for pronunciation standard, and obtaining a familiarity score based on the feature vector obtained in step S502; S504: Establish a scoring model, map the similarity score to a specific score or grade, and feed back the obtained score or grade to the user in real time.
4. The intelligent English learning system according to claim 1, characterized in that: The determination process of the fluency principle of copying and dictation includes the following steps: S511, establishing a deep learning model, clarifying the obtained copying and dictation situation, converting the user's input into a standard text format, and then evaluating the accuracy of the obtained text format and the correct answer; S512, monitoring the speed at which the user writes words, analyzing whether there is any unsmoothness during the writing process, and evaluating the standardization of the written word shape; S513. A mapping relationship between the fluency index and the word mastery proficiency is established, and a user's word mastery proficiency score is given in combination with factors such as writing speed, continuity, and character shape standardization.
5. The intelligent English learning system according to claim 1, characterized in that: The word mastery conditions include three conditions: proficient mastery of a single word, hearing and reading difficulties, and copying and dictation difficulties; in the case of proficient mastery, the receiving module deletes the mastered word from the vocabulary group; when hearing and reading difficulties occur, the receiving module adjusts the playback duration and frequency of the single word in real time; when copying and dictation difficulties occur, the receiving module adjusts the copying and dictation time of the single word in real time, and adds the amplified playback during the copying and dictation process.
6. The intelligent English learning system according to claim 3, characterized in that: The preprocessing includes: noise removal, speech enhancement, and endpoint detection; the acoustic features include: Mel-frequency cepstral coefficients, fundamental frequency, and resonance peak.
7. The intelligent English learning system according to claim 4, characterized in that: The deep learning model is a convolutional neural network, a recurrent neural network or one of its variants, and the clarity processing includes: image denoising, binarization, and normalization; by recording the timestamp information of the user's writing process, the writing speed of the word is calculated, and by analyzing the continuity and smoothness characteristics of the writing trajectory, the writing fluency of the word is evaluated.
8. An intelligent English learning device, based on an intelligent English learning system according to any one of claims 1 to 7, comprising: A control unit, a display unit and a pad; characterized in that the display unit includes a display screen, a button group, an electronic pen and a power cord; the pad includes a limit card block, a column and a scanning imager; the limit card block is used to fix the display unit, and the scanning imager is fixed at the end of the column to scan the user's handwritten words.
9. The intelligent English learning device according to claim 8, characterized in that: The button group includes: a power button, a voice transcription button, a voice dictation button, a silent dictation button, a pause button, a repeat button, a volume up button, and a volume down button; when the voice transcription button is pressed, the display screen displays the word accompanied by loudspeaker playback; when the voice dictation button is pressed, the display screen hides the word accompanied by loudspeaker playback; when the silent dictation button is pressed, the display screen hides the word and turns off loudspeaker playback.
10. The intelligent English learning device according to claim 8, characterized in that: The scanning imager is one of a charge coupled device, a complementary metal oxide semiconductor sensor or an OCR engine; the scanning imager is also provided with a video recording system for real-time monitoring of the user's writing situation.
Citation Information
Cited By
Hearing training answer analysis method and device
CN122598632A
