Reading-after training method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention discloses a listen-and-read training method and device, electronic equipment and a storage medium. The method comprises the steps of obtaining a listen-and-read voice overall score of a user for a target sentence; under the condition that the integral score of the listen-and-read voice is smaller than or equal to a first threshold value, a target object is obtained according to the object score of each object in the multiple objects included in the target sentence, and the target object is the object with the object score smaller than or equal to a second threshold value; according to the target object, layered read-after training is conducted on the user, the layered read-after training comprises at least two of object read-after training, short sentence read-after training and whole sentence read-after training, and the number of objects included in the short sentence read-after training is smaller than the number of objects included in the whole sentence read-after training. By implementing the embodiment of the invention, the pronunciation weak points of the user can be accurately positioned and trained.

Description

Technical Field

[0001] This application relates to the field of intelligent learning technology, and relates to, but is not limited to, a shadowing training method, device, electronic device, and storage medium. Background Art

[0002] With the development of globalization, the demand for language learning has increased sharply. Listening and speaking abilities have become the key indicators to measure language proficiency. As an effective means to improve listening and speaking abilities, shadowing training has received extensive attention. The existing shadowing training methods have relatively single functions, mostly simple audio playback and shadowing evaluation. However, relying solely on simple audio playback and basic shadowing evaluation cannot accurately locate and target train the pronunciation weaknesses of users. Summary of the Invention

[0003] In view of this, the shadowing training method, device, electronic device, and storage medium provided by the embodiments of this application can accurately locate and target train the pronunciation weaknesses of users.

[0004] The first aspect of the embodiments of this application discloses a shadowing training method, which is applied to a terminal device. The method includes:

[0005] Obtain an overall score of the user's shadowing speech for the target sentence;

[0006] In the case where the overall score of the shadowing speech is less than or equal to a first threshold, obtain a target object according to the object scores of each object included in the target sentence, where the target object is an object whose object score is less than or equal to a second threshold;

[0007] Perform hierarchical shadowing training on the user according to the target object. The hierarchical shadowing training includes at least two of object shadowing training, short sentence shadowing training, and whole sentence shadowing training. The number of objects included in the short sentence shadowing training is less than the number of objects included in the whole sentence shadowing training.

[0008] In some possible embodiments, the hierarchical shadowing training includes object shadowing training. The performing hierarchical shadowing training on the user according to the target object includes:

[0009] Perform object shadowing training on the user according to the syllable spelling speech of the target object and the user's spelling shadowing result for the syllable spelling speech. The syllable spelling speech includes multiple syllables, and the multiple syllables are obtained by splitting the target object according to the pronunciation rules of the target object.

[0010] In some possible embodiments, the hierarchical shadowing training includes short sentence shadowing training. The method further includes:

[0011] Perform short sentence shadowing training on the user according to at least one target short sentence corresponding to the target sentence and the short sentence shadowing result of the user for the at least one target short sentence, where one of the at least one target short sentences includes the target object.

[0012] In some possible embodiments, the hierarchical shadowing training includes object shadowing training and full sentence shadowing training. The performing hierarchical shadowing training on the user according to the target object includes:

[0013] Play the syllable spelling pronunciation of the target object and obtain the spelling shadowing result of the user;

[0014] Obtain the shadowing voice score of the user's spelling shadowing result;

[0015] When the shadowing voice score of the spelling shadowing result is greater than or equal to a third threshold, perform full sentence shadowing training on the user according to the target sentence and the user's full sentence shadowing result for the target sentence;

[0016] When the shadowing voice score of the user's full sentence shadowing result is greater than or equal to the third threshold, end the hierarchical shadowing training on the user.

[0017] In some possible embodiments, the hierarchical shadowing training includes short sentence shadowing training and full sentence shadowing training. The performing hierarchical shadowing training on the user according to the target object includes:

[0018] Play the at least one target short sentence corresponding to the target sentence and obtain the short sentence shadowing result of the user;

[0019] Obtain the shadowing voice score of the user's short sentence shadowing result;

[0020] When the shadowing voice score of the short sentence shadowing result is greater than or equal to the third threshold, perform full sentence shadowing training on the user according to the target sentence and the user's full sentence shadowing result for the target sentence;

[0021] When the shadowing voice score of the user's full sentence shadowing result is greater than or equal to the third threshold, end the hierarchical shadowing training on the user.

[0022] In some possible embodiments, the hierarchical shadowing training includes object shadowing training, short sentence shadowing training and full sentence shadowing training. The performing hierarchical shadowing training on the user according to the target object includes:

[0023] Play the syllable spelling pronunciation of the target object and obtain the spelling shadowing result of the user;

[0024] Obtain the follow-up speech score of the user's spelling and follow-up result;

[0025] When the follow-up speech score of the spelling and follow-up result is greater than or equal to a third threshold, play the at least one target short sentence corresponding to the target sentence, and obtain the short sentence follow-up result of the user;

[0026] Obtain the follow-up speech score of the user's short sentence follow-up result;

[0027] When the follow-up speech score of the short sentence follow-up result is greater than or equal to the third threshold, perform whole sentence follow-up training on the user according to the target sentence and the user's whole sentence follow-up result of the target sentence;

[0028] When the follow-up speech score of the user's whole sentence follow-up result is greater than or equal to the third threshold, end the hierarchical follow-up training of the user.

[0029] In some possible embodiments, the performing hierarchical follow-up training on the user according to the target object includes:

[0030] When the overall follow-up speech score is in the first interval, perform object follow-up training and whole sentence follow-up training on the user according to the target object;

[0031] When the overall follow-up speech score is in the second interval, perform short sentence follow-up training and whole sentence follow-up training on the user according to the target object;

[0032] When the overall follow-up speech score is in the third interval, perform object follow-up training, short sentence follow-up training and whole sentence follow-up training on the user according to the target object;

[0033] Wherein, the minimum value of the first interval is greater than or equal to the maximum value of the second interval, and the minimum value of the second interval is greater than or equal to the maximum value of the third interval.

[0034] In some possible embodiments, the method further includes:

[0035] Obtain the identity information of the user, where the identity information includes excellent students or non-excellent students;

[0036] When the identity information of the user is the non-excellent student and the overall follow-up speech score is greater than the first threshold, perform hierarchical follow-up training on the user according to the target object obtained by the object score of each object included in the target sentence.

[0037] In some possible embodiments, the method further includes:

[0038] When the identity information of the user is the non-excellent student, the overall score of the shadowing speech is greater than the first threshold, and the target object is not obtained based on the object score of each object included in the target sentence, play the next sentence of the target sentence.

[0039] In some possible embodiments, the method further includes:

[0040] When the identity information of the user is the excellent student and the overall score of the shadowing speech of the user for the target sentence is greater than the first threshold, play the next sentence of the target sentence.

[0041] A second aspect of the embodiments of the present application discloses a shadowing training device applied to a terminal device, and the device includes:

[0042] A score acquisition module, configured to acquire the overall score of the shadowing speech of the user for the target sentence;

[0043] A target object acquisition module, configured to, when the overall score of the shadowing speech is less than or equal to the first threshold, acquire a target object based on the object score of each object included in the target sentence, where the target object is an object whose object score is less than or equal to the second threshold;

[0044] A shadowing training module, configured to perform hierarchical shadowing training on the user according to the target object, where the hierarchical shadowing training includes at least two of object shadowing training, short sentence shadowing training, and whole sentence shadowing training, and the number of objects included in the short sentence shadowing training is less than the number of objects included in the whole sentence shadowing training.

[0045] A third aspect of the embodiments of the present application discloses an electronic device, including a memory and a processor, where a computer program is stored in the memory, and when the computer program is executed by the processor, the processor implements the method as described above.

[0046] A fourth aspect of the embodiments of the present application discloses a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the method as described above is implemented.

[0047] Compared with the related art, the embodiments of the present application at least include the following beneficial effects:

[0048] The terminal device obtains the overall score of the user's follow - up reading voice for the target sentence; when the overall score of the follow - up reading voice is less than or equal to the first threshold, the target object is obtained according to the object score of each object included in the target sentence, and the target object is the object whose object score is less than or equal to the second threshold; hierarchical follow - up reading training is performed on the user according to the target object, and the hierarchical follow - up reading training includes at least two of object follow - up reading training, short - sentence follow - up reading training, and whole - sentence follow - up reading training, and the number of objects included in the short - sentence follow - up reading training is less than the number of objects included in the whole - sentence follow - up reading training.

[0049] In this solution, the terminal device can accurately locate the weak points of the user's pronunciation and conduct targeted training by obtaining the target object and performing hierarchical follow - up reading training on the user according to the target object. The hierarchical follow - up reading training includes at least two of object follow - up reading training, short - sentence follow - up reading training, and whole - sentence follow - up reading training. Brief Description of the Drawings

[0050] The accompanying drawings here are incorporated into the specification and form a part of this specification. These drawings show embodiments consistent with the present application and, together with the specification, are used to explain the technical solutions of the present application.

[0051] Figure 1 It is a schematic flowchart of the follow - up reading training method in an embodiment;

[0052] Figure 2 It is a schematic diagram of object follow - up reading training in an embodiment;

[0053] Figure 3 It is a schematic diagram of short - sentence follow - up reading training in an embodiment;

[0054] Figure 4 It is a schematic diagram of hierarchical follow - up reading training in an embodiment;

[0055] Figure 5 It is a schematic diagram of hierarchical follow - up reading training in another embodiment;

[0056] Figure 6 It is a schematic diagram of hierarchical follow - up reading training in yet another embodiment;

[0057] Figure 7 It is a schematic flowchart of the follow - up reading training method in another embodiment;

[0058] Figure 8 It is a block diagram of the structure of the follow - up reading training device in an embodiment;

[0059] Figure 9 It is a block diagram of the structure of an electronic device in an embodiment. Detailed Embodiments

[0060] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the following will further describe the specific technical solutions of this application in detail in conjunction with the accompanying drawings in the embodiments of this application. The following embodiments are used to illustrate this application, but are not used to limit the scope of this application.

[0061] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0062] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments. However, it can be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments, and can be combined with each other without conflict.

[0063] It should be noted that the terms "first / second / third" involved in the embodiments of this application are used to distinguish similar or different objects, and do not represent a specific order for the objects. It can be understood that "first / second / third" can be interchanged with a specific order or sequence when allowed, so that the embodiments of this application described here can be implemented in an order other than that illustrated or described here.

[0064] The embodiments of this application disclose a shadowing training method, device, electronic device, and storage medium, which can accurately locate and target train the pronunciation weaknesses of users. The following will be described in detail respectively.

[0065] It should be understood that the execution subject of each method embodiment of this application is various types of terminal devices. For example, it can be a smart phone, a tablet computer, a wearable device, a learning machine, a tutoring machine, a learning tablet, an augmented reality (AR) / virtual reality (VR) device, a notebook computer, an ultra-mobile personal computer (UMPC), a netbook, a personal digital assistant (PDA), and so on. The specific type of the terminal device is not limited in the embodiments of this application.

[0066] Please refer to Figure 1 , Figure 1 which is a schematic flowchart of the shadowing training method in an embodiment. This method is applied to a terminal device, as Figure 1 shown, and this method may include the following steps:

[0067] Step 101, obtain an overall score of the user's shadowing speech for the target sentence.

[0068] In the embodiments of the present application, the target sentence refers to a sentence that the user needs to follow and read selected from pre-set language learning materials. The target sentence can be user-defined or selected from a pre-set corpus. The types of target sentences can be Chinese or foreign languages. Foreign languages can include English, Japanese, French, German, etc., which are not limited in the embodiments of the present application. In the embodiments of the present application, the follow-up reading training in English is taken as an example for illustration, but it is not limited to the follow-up reading training in English. The follow-up reading training method provided in the embodiments of the present application is also applicable to the follow-up reading training scenarios of other languages.

[0069] In some embodiments, obtaining the overall score of the user's follow-up reading voice for the target sentence includes:

[0070] According to the user's follow-up reading result of the target sentence and a pre-set scoring rule, obtain the overall score of the user's follow-up reading voice for the target sentence. The pre-set scoring rule includes the sentence fluency, sentence integrity, and sentence accuracy of the follow-up reading result.

[0071] The sentence fluency score can be determined by factors such as the pause duration and pause times in the user's follow-up reading voice of the target sentence. That is, the longer the user's voice pause duration and the more the pause times, the lower the sentence fluency score. The sentence integrity score mainly evaluates whether the user has read out all the contents in the target sentence completely. If the user omits or adds extra contents, the sentence integrity score will be reduced accordingly. The sentence accuracy score mainly evaluates the accuracy of the user's pronunciation, including whether the pronunciation of phonemes, syllables, and words is correct. For example, the terminal device can calculate the similarity score between each phoneme in the user's follow-up reading voice and the standard phoneme through a neural network model. The word syllable score is calculated by taking the average value of the phoneme similarity scores, the word overall score is calculated by taking the average value of the word syllable scores, and the sentence score is calculated by taking the average value of the word overall scores, so as to obtain the sentence accuracy score.

[0072] The user's follow-up reading result of the target sentence can be the user's follow-up reading voice of the target sentence. The terminal device can perform weighted summation on the scores of sentence fluency, sentence integrity, and sentence accuracy according to the pre-set scoring rule and pre-set weights to obtain the overall score of the user's follow-up reading voice for the target sentence.

[0073] Step 102, in the case where the overall score of the follow-up reading voice is less than or equal to the first threshold, obtain the target object according to the object score of each object included in the target sentence. The target object is the object whose object score is less than or equal to the second threshold.

[0074] In some embodiments, the first threshold is a preset standard value. For example, the first threshold can be set to 90, which is not limited in the embodiments of the present application. When the overall score of the shadowing speech is less than or equal to the first threshold, the terminal device can further obtain the object score of each object included in the target sentence. Exemplarily, the objects included in the target sentence can be words, and the object score of each object can be the score for each word in the target sentence. The target object is a word with a word score less than or equal to the second threshold. The second threshold is a set standard value for determining whether each object in the target sentence is a target object. For example, the second threshold can be set to 60. Optionally, the word score can be obtained by calculating the similarity score between each phoneme in the user's shadowing speech and the standard phoneme, thereby obtaining the word score.

[0075] Step 103: Perform hierarchical shadowing training on the user according to the target object. The hierarchical shadowing training includes at least two of object shadowing training, short sentence shadowing training, and whole sentence shadowing training. The number of objects included in the short sentence shadowing training is less than the number of objects included in the whole sentence shadowing training.

[0076] In some embodiments, after the terminal device obtains the target object, it marks the target object and obtains the shadowing speech score of the user for the target object for secondary evaluation to prevent misjudgment. When the shadowing speech score of the user for the target object is less than or equal to the second threshold, hierarchical shadowing training can be performed on the user according to the target object.

[0077] In some possible embodiments, the hierarchical shadowing training includes object shadowing training. The performing hierarchical shadowing training on the user according to the target object includes:

[0078] Performing object shadowing training on the user according to the syllable spelling speech of the target object and the user's spelling shadowing result for the syllable spelling speech. The syllable spelling speech includes multiple syllables, and the multiple syllables are obtained by splitting the target object according to the pronunciation rules of the target object.

[0079] The syllable spelling speech refers to splitting the target object (word) into multiple syllables according to the pronunciation rules and having the user shadow each syllable one by one. A syllable is the smallest pronunciation unit in a language, usually consisting of one or more vowels and the consonants around them. By shadowing each syllable one by one, the user can more clearly master the pronunciation characteristics of each syllable and then better spell the whole word.

[0080] Please refer to Figure 2 , Figure 2 which is a schematic diagram of object shadowing training in an embodiment. As Figure 2As shown, exemplarily, the target object "grandma" is split into two syllables according to the pronunciation rules. "Grand" is the first syllable and "ma" is the second syllable. It should be noted that the terminal device can pre-split the target object into multiple syllables according to the pronunciation rules of the target object and store the split syllable information in the database. The syllable information may include the text representation, phonetic notation, and corresponding audio file of the syllable. When the user starts the hierarchical follow-up reading training, the terminal device retrieves the syllable information of the target object from the database, plays the syllable spelling voice, and obtains the user's spelling follow-up reading result of the syllable spelling voice.

[0081] After the user completes the syllable spelling follow-up reading of the target object, multiple syllables can be combined to guide the user to perform a complete follow-up reading of the target object. For example, the terminal device can play the standard audio of the word "grandma" and obtain the follow-up reading voice score of the user. When the follow-up reading voice score of the user for each target object is greater than or equal to the preset threshold (for example, the threshold can be 75 points), the object follow-up reading training for the user ends. It should be noted that if the follow-up reading voice score of the user for the target object is less than the preset threshold, the terminal device plays the syllable spelling voice of the target object again to perform object follow-up reading training for the user.

[0082] During the object follow-up reading training, if the user's spelling follow-up reading result of the syllable spelling voice or the follow-up reading result of the target object is not obtained for the first time, the terminal device plays the standard audio again. If the user's follow-up reading result is still not obtained for the second time, the terminal device automatically starts the object follow-up reading training for the next target object.

[0083] Through the above object follow-up reading training based on syllable spelling, it can help users better master the pronunciation details of the target object and gradually improve the pronunciation accuracy.

[0084] In some embodiments, the hierarchical follow-up reading training includes short sentence follow-up reading training, and the method further includes:

[0085] According to at least one target short sentence corresponding to the target sentence and the user's short sentence follow-up reading result of the at least one target short sentence, short sentence follow-up reading training is performed on the user, and one of the at least one target short sentences includes the target object.

[0086] As an optional implementation manner, the target short sentence may be obtained by splitting the target sentence according to the sentence structure and sentence pronunciation rules of the target sentence. The sentence pronunciation rules include liaison and intonation pauses, etc. In some other embodiments, the target short sentence may also be split according to the number of objects included in the target short sentence, and one of the at least one target short sentences includes the target object. The embodiments of the present invention do not make specific limitations.

[0087] Please refer to Figure 3 , Figure 3 , which is a schematic diagram of short sentence shadowing training in an embodiment. As Figure 3 shown, by way of example, taking the target sentence "This is my grandma" as an example, it can be split into the following short sentences: short sentence 1: "This is" and short sentence 2: "my grandma". It should be noted that the terminal device can pre-split the target sentence and store the short sentence information after splitting in the database. The short sentence information can include the text of the short sentence, audio files, etc. When the user starts the hierarchical shadowing training, the terminal device can retrieve the short sentence information of the target sentence from the database and play the standard audio of at least one target short sentence corresponding to the target sentence, guide the user to shadow each target short sentence one by one, and obtain the short sentence shadowing result of the user for at least one target short sentence.

[0088] For example, after obtaining the short sentence shadowing result of the user for short sentence 1, the terminal device can score the short sentence shadowing speech of the user. When the shadowing speech score of the user is greater than or equal to a preset threshold (for example, the threshold can be 75 points), the short sentence shadowing result of the user for short sentence 2 is obtained. When the shadowing speech score of the user for each target short sentence is greater than or equal to the preset threshold (for example, the threshold can be 75 points), the short sentence shadowing training of the user is ended. It should be noted that if the shadowing speech score of the user for short sentence 1 or short sentence 2 is less than the preset threshold, the terminal device plays the standard audio of short sentence 1 or short sentence 2 again to conduct short sentence shadowing training for the user.

[0089] During the short sentence shadowing training process, if the shadowing result of the user for the target short sentence is not obtained for the first time, the terminal device plays the standard audio again. If the shadowing result of the user is still not obtained for the second time, the terminal device automatically starts the short sentence shadowing training for the next target short sentence.

[0090] By adopting the above embodiment, through at least one target short sentence corresponding to the target sentence, short sentence shadowing training is carried out for the user, which can help the user gradually master the pronunciation of the target sentence and avoid pronunciation difficulties caused by the too long target sentence.

[0091] In some possible embodiments, step 103, performing hierarchical shadowing training on the user according to the target object, may at least include the following three exemplary methods.

[0092] The first example:

[0093] Please refer to Figure 4 , Figure 4Schematic diagram of hierarchical follow-up reading training in an embodiment. In some embodiments, the hierarchical follow-up reading training includes object follow-up reading training and whole-sentence follow-up reading training. The method for performing hierarchical follow-up reading training on a user according to a target object includes:

[0094] Play the syllable spelling pronunciation of the target object and obtain the user's spelling follow-up reading result;

[0095] Obtain the follow-up reading voice score of the user's spelling follow-up reading result;

[0096] When the follow-up reading voice score of the spelling follow-up reading result is greater than or equal to the third threshold, perform whole-sentence follow-up reading training on the user according to the target sentence and the user's whole-sentence follow-up reading result of the target sentence;

[0097] When the follow-up reading voice score of the user's whole-sentence follow-up reading result is greater than or equal to the third threshold, end the hierarchical follow-up reading training for the user.

[0098] As Figure 4 shown, for example, after the terminal device obtains the target object, it allows the user to follow up read the target object one by one for a second evaluation. If the follow-up reading result of the user is not obtained for the first time, the terminal device replays the standard audio of the target object. If the follow-up reading result of the user is still not obtained for the second time, the hierarchical follow-up reading training for the user is ended. When the follow-up reading voice score of the user for the target object is less than or equal to the second threshold, perform object follow-up reading training and whole-sentence follow-up reading training on the user. For example, when Figure 4 the follow-up reading voice score of the target object is less than 60, perform hierarchical follow-up reading training on the user. Correspondingly, when the follow-up reading voice score of the target object is greater than or equal to 60, obtain the follow-up reading result of the user for the next target object.

[0099] The terminal device plays the syllable spelling pronunciation of the target object. For example, the word "grandma" can be split into syllables "grand" and "ma". The user follows up read the syllable spelling pronunciation of the target object, and the terminal device obtains the user's spelling follow-up reading result. The follow-up reading voice score of the user's spelling follow-up reading result can be obtained by calculating the similarity score between each phoneme in the user's follow-up reading voice and the standard phoneme.

[0100] In some embodiments, after the user finishes syllable spelling and following reading of the target object, the terminal device can play the standard audio of the target object, obtain the following reading result of the user for the target object. When the following reading voice score of the user for the target object is greater than or equal to 75, the terminal device conducts object following reading training for the next target object. When the following reading voice score of the user for the target object is less than 75, the terminal device plays the syllable spelling voice of the target object again. During the object following reading training process, if the following reading result of the user for the syllable spelling voice is not obtained for the first time or the following reading result of the user for the target object is not obtained, the terminal device plays the standard audio again. If the following reading result of the user is still not obtained for the second time, the terminal device automatically starts object following reading training for the next target object.

[0101] When the following reading voice score of the following reading result is greater than or equal to the third threshold, or when the following reading voice score of the user for the target object is greater than or equal to the third threshold, sentence following reading training is conducted for the user. The third threshold can be set to 75. It should be noted that the sentence following reading training is started when all target objects are spelled.

[0102] Exemplarily, the terminal device can pre-store the standard audio of the target sentence. When the trigger condition for the above-mentioned sentence following reading training is met, the terminal device starts to execute the sentence following reading training process. For example, it calls the audio file of the target sentence for playing and outputs the standard pronunciation of the target sentence to the user through the speaker of the device. During the user's following reading process, the terminal device uses the built-in microphone to collect the user's following reading voice. When the following reading voice score of the user's sentence following reading result is greater than or equal to the third threshold, the hierarchical following reading training for the user ends, and the terminal device can play the next sentence of the target sentence to conduct the next round of hierarchical following reading training for the user.

[0103] In some embodiments, when the following reading voice score of the user's sentence following reading result is less than the third threshold, the terminal device can play the standard audio of the target sentence again to conduct sentence following reading training for the user. In some other embodiments, if the user wants to end the current hierarchical following reading training process, the user can choose to click the preset "Next Sentence" button on the terminal interface to start the hierarchical following reading training for the next sentence, or choose to click the "End" button to terminate the hierarchical following reading training.

[0104] By adopting the above embodiments, the hierarchical following reading training method can effectively improve the user's pronunciation accuracy, enhance the learning confidence, and improve the learning efficiency through refined syllable spelling training and gradually improved sentence following reading training.

[0105] The second example:

[0106] Please refer to Figure 5 ,Figure 5 It is a schematic diagram of hierarchical follow - up training in another embodiment. In some embodiments, the hierarchical follow - up training includes short - sentence follow - up training and whole - sentence follow - up training. Conducting hierarchical follow - up training for users according to the target object includes:

[0107] Play at least one target short sentence corresponding to the target sentence, and obtain the short - sentence follow - up result of the user;

[0108] Obtain the follow - up speech score of the user's short - sentence follow - up result;

[0109] When the follow - up speech score of the short - sentence follow - up result is greater than or equal to the third threshold, conduct whole - sentence follow - up training for the user according to the target sentence and the user's whole - sentence follow - up result of the target sentence;

[0110] When the follow - up speech score of the user's whole - sentence follow - up result is greater than or equal to the third threshold, end the hierarchical follow - up training for the user.

[0111] As Figure 5 shown, for example, the terminal device plays at least one target short sentence corresponding to the target sentence. For example, the terminal device plays short sentence 1: "This is", and obtains the short - sentence follow - up result of the user for short sentence 1. If the terminal device does not obtain the short - sentence follow - up result of the user for short sentence 1 for the first time, it plays the standard audio of short sentence 1 again. If it still does not obtain the follow - up result of the user for short sentence 1 for the second time, the terminal device automatically starts the short - sentence follow - up training for the next target short sentence, that is, the terminal device plays short sentence 2: "my grandma", and obtains the short - sentence follow - up result of the user for short sentence 2.

[0112] It should be noted that the user's short - sentence follow - up result includes the user's short - sentence follow - up speech. After the terminal device obtains the user's short - sentence follow - up result, it scores the user's short - sentence follow - up speech to obtain the follow - up speech score of the user's short - sentence follow - up result. The specific scoring method can refer to the above - mentioned embodiment and will not be elaborated here.

[0113] When the follow - up speech score of the short - sentence follow - up result is less than the third threshold, the terminal device can re - play the standard audio of the target short sentence to conduct short - sentence follow - up training for the user. When the follow - up speech score of the short - sentence follow - up result is greater than or equal to the third threshold, the terminal device conducts whole - sentence follow - up training for the user. When the follow - up speech score of the user's whole - sentence follow - up result is greater than or equal to the third threshold, end the hierarchical follow - up training for the user.

[0114] The specific method of conducting whole - sentence follow - up training for the user here can refer to the above - mentioned embodiment and will not be elaborated here. It should be noted that the whole - sentence follow - up training is started when the short - sentence follow - up training of all target short sentences is completed.

[0115] With the above embodiments, the hierarchical shadowing training method enables users to first focus on the pronunciation and intonation of each short sentence through short-sentence shadowing training and whole-sentence shadowing training, gradually adapt to the sentence structure and rhythm, and thus gradually improve their mastery of the entire sentence.

[0116] The third example:

[0117] Please refer to Figure 6 , Figure 6 which is a schematic diagram of hierarchical shadowing training in yet another embodiment. In some embodiments, the hierarchical shadowing training includes object shadowing training, short-sentence shadowing training, and whole-sentence shadowing training. The hierarchical shadowing training of users according to the target object includes:

[0118] Play the syllable spelling pronunciation of the target object and obtain the user's spelling shadowing result;

[0119] Obtain the shadowing speech score of the user's spelling shadowing result;

[0120] When the shadowing speech score of the spelling shadowing result is greater than or equal to the third threshold, play at least one target short sentence corresponding to the target sentence and obtain the user's short-sentence shadowing result;

[0121] Obtain the shadowing speech score of the user's short-sentence shadowing result;

[0122] When the shadowing speech score of the short-sentence shadowing result is greater than or equal to the third threshold, conduct whole-sentence shadowing training on the user according to the target sentence and the user's whole-sentence shadowing result of the target sentence;

[0123] When the shadowing speech score of the user's whole-sentence shadowing result is greater than or equal to the third threshold, end the hierarchical shadowing training of the user.

[0124] In the embodiments of the present application, the specific manner in which the terminal device conducts object shadowing training on the user according to the target object may refer to the above embodiments and will not be elaborated here. After completing the object shadowing training of the user, the terminal device can first obtain the user's whole-sentence shadowing result of the target sentence. When the whole-sentence shadowing speech score of the user for the target sentence is less than 75, start the short-sentence shadowing training for the user. The specific manner in which the terminal device conducts short-sentence shadowing training on the user may refer to the above embodiments and will not be elaborated here; when the whole-sentence shadowing speech score of the user for the target sentence is greater than or equal to 75, end the hierarchical shadowing training of the user, and the terminal device can play the next sentence of the target sentence to conduct the next round of hierarchical shadowing training on the user.

[0125] Before the terminal device starts the short sentence shadowing training, obtain the user's shadowing speech score for the target sentence. If the score is greater than or equal to 75, it indicates that the user has reached a certain level of mastery of the whole sentence. Directly proceeding to the next sentence can improve the learning efficiency and avoid repeating the content that has already been mastered. If the score is less than 75, it means that the user has difficulty in shadowing the whole sentence. At this time, split the sentence into short sentences for shadowing training. Splitting a complex sentence into multiple short sentences helps to gradually overcome the difficulties and reduce the learning difficulty.

[0126] After completing the short sentence shadowing training for the user, according to the target sentence and the user's whole sentence shadowing result for the target sentence, conduct whole sentence shadowing training for the user. When the shadowing speech score of the user's whole sentence shadowing result is greater than or equal to the third threshold, end the hierarchical shadowing training for the user. The specific method for the terminal device to conduct whole sentence shadowing training for the user can refer to the above embodiments and will not be elaborated here.

[0127] Adopting the above embodiments, the hierarchical shadowing training method conducts object shadowing training, short sentence shadowing training, and whole sentence shadowing training, and uses a hierarchical training method to gradually guide students to conduct pronunciation training. Compared with the traditional single whole sentence shadowing training, this method can decompose complex pronunciation tasks into smaller and easier-to-master parts. This hierarchical training method conforms to the user's cognitive law, can effectively reduce the learning difficulty, and gradually improve the user's pronunciation level.

[0128] In some possible embodiments, the hierarchical shadowing training for the user according to the target object includes:

[0129] When the overall shadowing speech score is in the first interval, conduct object shadowing training and whole sentence shadowing training for the user according to the target object;

[0130] When the overall shadowing speech score is in the second interval, conduct short sentence shadowing training and whole sentence shadowing training for the user according to the target object;

[0131] When the overall shadowing speech score is in the third interval, conduct object shadowing training, short sentence shadowing training, and whole sentence shadowing training for the user according to the target object;

[0132] Wherein, the minimum value of the first interval is greater than or equal to the maximum value of the second interval, and the minimum value of the second interval is greater than or equal to the maximum value of the third interval.

[0133] In some embodiments, the three intervals can be set as successively decreasing hierarchical levels, representing different pronunciation levels of the user from high to low. For example, the first interval can be [80, 100], the second interval can be [60, 80], and the third interval can be [0, 60]. The embodiments of the present application do not make specific limitations.

[0134] During the hierarchical shadowing training process, the terminal device can also monitor the user's shadowing speech score in real time and dynamically adjust the shadowing training content according to the score. For example, if the overall score of the user's shadowing speech is in the third interval, after completing the object shadowing training for the user, obtain the shadowing speech score of the user for the target sentence. If the score is high, the short sentence shadowing training for the user can be omitted.

[0135] In the above embodiment, by setting different hierarchical shadowing training strategies according to the score, it is possible to make adaptive adjustments for the individual differences of users, be able to identify the pronunciation weak points of the user for the target sentence in real time, and make targeted adaptive adjustments, and can provide personalized shadowing training plans to improve the accuracy and fluency of the user's shadowing.

[0136] Please refer to Figure 7 , Figure 7 which is a schematic flowchart of the shadowing training method in another embodiment. As Figure 7 shown, the shadowing training method provided by the embodiments of the present application may further include the following steps:

[0137] Step 701, obtain the user's identity information, where the identity information includes excellent students or non-excellent students.

[0138] In some embodiments, with the user's authorization, the terminal device can collect multi-dimensional user data, such as daily learning habits, including daily learning duration, learning time period preferences, etc., or collect various behavior data of the user on the education platform, including but not limited to learning preferences, activity in participating in discussions, etc. By deeply analyzing these multi-dimensional behavior data, a precise user portrait can be outlined, thereby determining the user's identity information.

[0139] The terminal device can also make a judgment based on the stored historical learning data of the user, such as course grades, homework completion status, detailed data of historical shadowing training (including scores, completion duration, error type distribution, etc.). For example, those with long-term excellent grades, outstanding performance in shadowing training, and obvious progress can be determined as excellent students, and vice versa as non-excellent students.

[0140] In some embodiments, the terminal device can also, through the initial evaluation method, based on the evaluation results and in combination with a pre-set score line, mark users with scores higher than the score line as excellent students and users with scores lower than the score line as non-excellent students. This method can quickly and directly obtain the user's identity information.

[0141] Step 702, when the user's identity information is non-excellent and the overall score of the shadowing speech is greater than the first threshold, perform hierarchical shadowing training on the user according to the target object obtained based on the object score of each object included in the target sentence.

[0142] In the embodiments of the present application, when the terminal device determines that the user's identity information is not that of an excellent student, even if the overall score of the user's follow-up reading voice for the target sentence is greater than the first threshold, the terminal device will further obtain the object scores of multiple objects included in the target sentence, and obtain the target object according to the object scores of the multiple objects included in the target sentence. The target object is an object whose object score is less than or equal to the second threshold. When the target object is obtained, hierarchical follow-up reading training is performed on the user according to the target object.

[0143] In the above embodiments, by determining the user's identity information, the terminal device can provide a personalized follow-up reading training path in combination with the user's basic ability. The user can gradually improve their ability at different stages, thereby improving their pronunciation level.

[0144] In some embodiments, the follow-up reading training method further includes:

[0145] When the user's identity information is not that of an excellent student, the overall score of the follow-up reading voice is greater than the first threshold, and no target object is obtained according to the object scores of each object included in the target sentence, the next sentence of the target sentence is played.

[0146] The terminal device determines that the user's identity information is not that of an excellent student, and the overall score of the user's follow-up reading voice for the target sentence is greater than the first threshold. However, no target object is obtained according to the object scores of each object included in the target sentence, that is, the object score of each object is greater than the second threshold. At this time, the terminal device can determine that there is no weak point in the user's pronunciation. In this case, the terminal device can play the next sentence of the target sentence and let the user perform follow-up reading training on the next sentence. This can avoid overtraining and save time and resources.

[0147] In some embodiments, the follow-up reading training method further includes:

[0148] When the user's identity information is that of an excellent student and the overall score of the user's follow-up reading voice for the target sentence is greater than the first threshold, the next sentence of the target sentence is played.

[0149] The terminal device determines that the user's identity information is that of an excellent student and the overall score of the user's follow-up reading voice for the target sentence is greater than the first threshold. At this time, there is no need to further obtain the object scores of multiple objects included in the target sentence, and the terminal device automatically plays the next sentence of the target sentence, which can avoid overtraining and save time and resources.

[0150] In some other embodiments, when the overall score of the user's shadowing speech for the target sentence is less than a third threshold and the target object cannot be obtained based on the object scores of each object included in the target sentence, the terminal device conducts whole-sentence shadowing training for the user. When the shadowing speech score of the user's whole-sentence shadowing result is greater than or equal to the third threshold, the next sentence of the target sentence is played. It can conduct targeted training based on the user's pronunciation weaknesses to ensure that the user can get sufficient practice and consolidation at each learning stage.

[0151] Please refer to Figure 8 , Figure 8 which is a structural block diagram of a shadowing training device in an embodiment. As Figure 8 shown, the shadowing training device 800 includes: a score acquisition module 810, a target object acquisition module 820, and a shadowing training module 830, where:

[0152] The score acquisition module 810 is configured to acquire the overall score of the user's shadowing speech for the target sentence;

[0153] The target object acquisition module 820 is configured to, when the overall score of the shadowing speech is less than or equal to a first threshold, acquire a target object based on the object scores of each object included in the target sentence, where the target object is an object whose object score is less than or equal to a second threshold;

[0154] The shadowing training module 830 is configured to conduct hierarchical shadowing training for the user based on the target object, where the hierarchical shadowing training includes at least two of object shadowing training, short-sentence shadowing training, and whole-sentence shadowing training, and the number of objects included in the short-sentence shadowing training is less than the number of objects included in the whole-sentence shadowing training.

[0155] In some embodiments, the shadowing training module 830 is specifically configured to:

[0156] Conduct object shadowing training for the user based on the syllable spelling speech of the target object and the user's spelling shadowing result for the syllable spelling speech, where the syllable spelling speech includes multiple syllables, and the multiple syllables are obtained by splitting the target object according to the pronunciation rules of the target object.

[0157] In some embodiments, the shadowing training module 830 is specifically configured to:

[0158] Conduct short-sentence shadowing training for the user based on at least one target short sentence corresponding to the target sentence and the user's short-sentence shadowing result for the at least one target short sentence, where one of the at least one target short sentences includes the target object.

[0159] In some embodiments, the shadowing training module 830 is specifically configured to:

[0160] Play the syllable spelling pronunciation of the target object, and obtain the spelling shadowing result of the user;

[0161] Obtain the shadowing voice score of the user's spelling shadowing result;

[0162] In the case where the shadowing voice score of the spelling shadowing result is greater than or equal to a third threshold, perform whole-sentence shadowing training on the user according to the target sentence and the user's whole-sentence shadowing result of the target sentence;

[0163] In the case where the shadowing voice score of the user's whole-sentence shadowing result is greater than or equal to the third threshold, end the hierarchical shadowing training for the user.

[0164] In some embodiments, the shadowing training module 830 is specifically configured to:

[0165] Play the at least one target short sentence corresponding to the target sentence, and obtain the short-sentence shadowing result of the user;

[0166] Obtain the shadowing voice score of the user's short-sentence shadowing result;

[0167] In the case where the shadowing voice score of the short-sentence shadowing result is greater than or equal to the third threshold, perform whole-sentence shadowing training on the user according to the target sentence and the user's whole-sentence shadowing result of the target sentence;

[0168] In the case where the shadowing voice score of the user's whole-sentence shadowing result is greater than or equal to the third threshold, end the hierarchical shadowing training for the user.

[0169] In some embodiments, the shadowing training module 830 is specifically configured to:

[0170] Play the syllable spelling pronunciation of the target object, and obtain the spelling shadowing result of the user;

[0171] Obtain the shadowing voice score of the user's spelling shadowing result;

[0172] In the case where the shadowing voice score of the spelling shadowing result is greater than or equal to a third threshold, play the at least one target short sentence corresponding to the target sentence, and obtain the short-sentence shadowing result of the user;

[0173] Obtain the shadowing voice score of the user's short-sentence shadowing result;

[0174] When the pronunciation score of the short sentence shadowing result is greater than or equal to the third threshold, perform whole sentence shadowing training on the user according to the target sentence and the user's whole sentence shadowing result of the target sentence;

[0175] When the pronunciation score of the user's whole sentence shadowing result is greater than or equal to the third threshold, end the hierarchical shadowing training for the user.

[0176] In some embodiments, the shadowing training module 830 is specifically configured to:

[0177] When the overall pronunciation score is in the first interval, perform object shadowing training and whole sentence shadowing training on the user according to the target object;

[0178] When the overall pronunciation score is in the second interval, perform short sentence shadowing training and whole sentence shadowing training on the user according to the target object;

[0179] When the overall pronunciation score is in the third interval, perform object shadowing training, short sentence shadowing training and whole sentence shadowing training on the user according to the target object;

[0180] Wherein, the minimum value of the first interval is greater than or equal to the maximum value of the second interval, and the minimum value of the second interval is greater than or equal to the maximum value of the third interval.

[0181] In some embodiments, the shadowing training module 830 is further configured to:

[0182] Obtain the identity information of the user, where the identity information includes excellent students or non-excellent students;

[0183] When the identity information of the user is the non-excellent student and the overall pronunciation score is greater than the first threshold, perform hierarchical shadowing training on the user according to the target object obtained by the object score of each object included in the target sentence.

[0184] In some embodiments, the shadowing training module 830 is further configured to:

[0185] When the identity information of the user is the non-excellent student, the overall pronunciation score is greater than the first threshold, and the target object cannot be obtained according to the object score of each object included in the target sentence, play the next sentence of the target sentence.

[0186] In some embodiments, the shadowing training module 830 is further configured to:

[0187] When the identity information of the user is that of an outstanding student and the overall score of the user's shadowing speech of the target sentence is greater than the first threshold, play the next sentence of the target sentence.

[0188] The description of the above device embodiments is similar to that of the above method embodiments and has similar beneficial effects to the method embodiments. For the technical details not disclosed in the device embodiments of the present application, please refer to the description of the method embodiments of the present application for understanding.

[0189] It should be noted that in the embodiments of the present application Figure 8 The division of the modules of the shadowing training device 800 shown is schematic, merely a logical function division, and there may be other division methods in actual implementation. In addition, in each embodiment of the present application, each functional unit may be integrated in a processing unit, may exist separately physically, or two or more units may be integrated in one unit. The above integrated unit may be implemented in the form of hardware, may also be implemented in the form of a software functional unit, or may be implemented in the form of a combination of software and hardware.

[0190] It should be noted that in the embodiments of the present application, if the above method is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the embodiments of the present application, in essence, or the part that contributes to the related technology, may be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing an electronic device to execute all or part of the methods described in the embodiments of the present application. The foregoing storage medium includes: various media such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a magnetic disk, or an optical disc that can store program codes. In this way, the embodiments of the present application are not limited to any specific combination of hardware and software.

[0191] Please refer to Figure 9 , Figure 9 which is a block diagram of the structure of an electronic device in an embodiment. As Figure 9 shown, the electronic device 900 may include: a processor 910, a memory 920, and a bus 930.

[0192] Among them, the processor 910 calls the executable program code stored in the memory 920 to execute any one of the shadowing training methods disclosed in the embodiments of the present application. Those skilled in the art can understand that Figure 9 the structure of the electronic device shown in does not constitute a limitation on the electronic device. The electronic device may include more or fewer components than shown in the figure, or combine some components, or have different component arrangements.

[0193] The processor 910 is configured to execute obtaining an overall score of the user's shadowing speech for the target sentence; in the case where the overall score of the shadowing speech is less than or equal to the first threshold, obtaining a target object according to the object score of each object among the multiple objects included in the target sentence, where the target object is an object whose object score is less than or equal to the second threshold; performing hierarchical shadowing training on the user according to the target object, and the hierarchical shadowing training includes at least two of object shadowing training, short sentence shadowing training, and whole sentence shadowing training, and the number of objects included in the short sentence shadowing training is less than the number of objects included in the whole sentence shadowing training. For specific details, please refer to the detailed description in the method example, which will not be elaborated here.

[0194] In the embodiments of the present application, the processor 910 may be a general-purpose processor, a digital signal processor, an application-specific integrated circuit, a field-programmable gate array, or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, and can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor may be a microprocessor or any conventional processor, etc. The steps of the method disclosed in combination with the embodiments of the present application can be directly embodied as being executed by a hardware processor, or executed by a combination of hardware and software modules in the processor.

[0195] The memory 920 can be used to store software programs and modules. The processor 910 executes various functional applications and data processing of the electronic device by running the software programs and modules stored in the memory 920. The memory 920 may mainly include a program storage area and a data storage area. Among them, the program storage area may store an operating system, application programs required for at least one function, etc.; the data storage area may store data created according to the use of the electronic device, etc. In addition, the memory 920 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0196] In the embodiments of the present application, the processor 910 and the memory 920 are connected through a bus 930. The bus 930 is represented by a thick line in Figure 9 For the connection manners between other components, only a schematic illustration is provided and is not limited thereto. The bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of convenience of representation, Figure 9 only a thick line is used to represent it in, but it does not mean that there is only one bus or one type of bus.

[0197] The embodiments of the present application provide a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps in the method provided in the above embodiments are implemented.

[0198] An embodiment of the present application provides a computer program product including instructions. When it runs on a computer, it causes the computer to execute the steps in the method provided by the above method embodiment.

[0199] Those of ordinary skill in the art can understand that all or part of the processes in the above method embodiments can be completed by instructing relevant hardware through a computer program. The program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the above method embodiments. Among them, the storage medium can be a magnetic disk, an optical disk, a ROM, etc.

[0200] It should be noted here that the descriptions of the above storage medium and device embodiments are similar to those of the above method embodiments and have similar beneficial effects to the method embodiments. For the technical details not disclosed in the storage medium, storage medium and device embodiments of the present application, please refer to the descriptions of the method embodiments of the present application for understanding.

[0201] It should be understood that the "one embodiment" or "an embodiment" or "some embodiments" mentioned throughout the specification means that the specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present application. Therefore, the "in one embodiment" or "in an embodiment" or "in some embodiments" that appear throughout the specification do not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. It should be understood that in various embodiments of the present application, the order numbers of the above processes do not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application. The serial numbers of the embodiments of the present application above are only for description and do not represent the advantages or disadvantages of the embodiments. The above descriptions of each embodiment tend to emphasize the differences between the embodiments. Their similarities or similarities can be referred to each other. For the sake of brevity, they will not be repeated here.

[0202] The term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, object A and / or object B can represent: object A exists alone, object A and object B exist simultaneously, and object B exists alone.

[0203] It should be noted that in this text, the term "including", "comprising" or any other variation thereof is intended to cover non-exclusive inclusion, such that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the phrase "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or device comprising such element.

[0204] In several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The embodiments described above are merely illustrative. For example, the division of the modules is only a logical function division. In actual implementation, there can be other division methods, such as multiple modules or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. Additionally, the coupling, direct coupling, or communication connection between the various components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or modules can be electrical, mechanical, or other forms.

[0205] The modules described above as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules; they can be located in one place or distributed to multiple network units; some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0206] In addition, in each embodiment of this application, the various functional modules can all be integrated in a processing unit, or each module can be separately a unit by itself, or two or more modules can be integrated in a unit; the above-mentioned integrated modules can be implemented in the form of hardware, or in the form of hardware plus software functional units.

[0207] Those of ordinary skill in the art can understand that all or part of the steps to implement the above method embodiments can be completed by hardware related to program instructions. The foregoing program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps including the above method embodiments; and the foregoing storage medium includes various media that can store program codes, such as removable storage devices, read-only memory (ROM), magnetic disks, or optical discs.

[0208] Alternatively, if the above-integrated units of the present application are implemented in the form of software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of the present application, in essence or the parts that contribute to the related technologies, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing an electronic device to execute all or part of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: various media such as removable storage devices, ROMs, magnetic disks, or optical discs that can store program codes.

[0209] The methods disclosed in several method embodiments provided by the present application can be arbitrarily combined without conflict to obtain new method embodiments.

[0210] The features disclosed in several product embodiments provided by the present application can be arbitrarily combined without conflict to obtain new product embodiments.

[0211] The features disclosed in several method or device embodiments provided by the present application can be arbitrarily combined without conflict to obtain new method embodiments or device embodiments.

[0212] The above is only the implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or substitutions, which should all be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A shadowing training method, characterized in that, Applied to a terminal device, the method includes: Obtaining an overall score of the user's shadowing speech for a target sentence; When the overall score of the shadowing speech is less than or equal to a first threshold, obtaining a target object according to the object scores of each object among a plurality of objects included in the target sentence, where the target object is an object whose object score is less than or equal to a second threshold; Performing hierarchical shadowing training on the user according to the target object, where the hierarchical shadowing training includes at least two of object shadowing training, short sentence shadowing training, and whole sentence shadowing training, and the number of objects included in the short sentence shadowing training is less than the number of objects included in the whole sentence shadowing training.

2. The method according to claim 1, wherein The hierarchical shadowing training includes object shadowing training. Performing the hierarchical shadowing training on the user according to the target object includes: Performing object shadowing training on the user according to the syllable spelling speech of the target object and the user's spelling shadowing result for the syllable spelling speech. The syllable spelling speech includes a plurality of syllables, and the plurality of syllables are obtained by splitting the target object according to its pronunciation rules.

3. The method according to claim 2, characterized in that, The hierarchical shadowing training includes short sentence shadowing training. The method further includes: Performing short sentence shadowing training on the user according to at least one target short sentence corresponding to the target sentence and the user's short sentence shadowing result for the at least one target short sentence, where one of the at least one target short sentences includes the target object.

4. The method according to claim 1, characterized in that The hierarchical shadowing training includes object shadowing training and whole sentence shadowing training. Performing the hierarchical shadowing training on the user according to the target object includes: Playing the syllable spelling speech of the target object and obtaining the user's spelling shadowing result; Obtaining the shadowing speech score of the user's spelling shadowing result; When the shadowing speech score of the spelling shadowing result is greater than or equal to a third threshold, performing whole sentence shadowing training on the user according to the target sentence and the user's whole sentence shadowing result for the target sentence; When the shadowing speech score of the user's whole sentence shadowing result is greater than or equal to the third threshold, ending the hierarchical shadowing training for the user.

5. The method according to claim 1, characterized in that, The hierarchical shadowing training includes short sentence shadowing training and whole sentence shadowing training. Performing the hierarchical shadowing training on the user according to the target object includes: Playing the at least one target short sentence corresponding to the target sentence and obtaining the user's short sentence shadowing result; Obtaining the shadowing speech score of the user's short sentence shadowing result; When the shadowing speech score of the short sentence shadowing result is greater than or equal to a third threshold, performing whole sentence shadowing training on the user according to the target sentence and the user's whole sentence shadowing result for the target sentence; When the shadowing speech score of the user's whole sentence shadowing result is greater than or equal to the third threshold, ending the hierarchical shadowing training for the user.

6. The method according to claim 1, wherein The hierarchical shadowing training includes object shadowing training, short sentence shadowing training, and whole sentence shadowing training. Performing the hierarchical shadowing training on the user according to the target object includes: Play the syllable spelling voice of the target object, and obtain the user's spelling follow-up reading result; Obtain the follow-up reading voice score of the user's spelling follow-up reading result; When the follow-up reading voice score of the spelling follow-up reading result is greater than or equal to the third threshold, play the at least one target short sentence corresponding to the target sentence, and obtain the user's short sentence follow-up reading result; Obtain the follow-up reading voice score of the user's short sentence follow-up reading result; When the follow-up reading voice score of the short sentence follow-up reading result is greater than or equal to the third threshold, perform whole sentence follow-up reading training on the user according to the target sentence and the user's whole sentence follow-up reading result of the target sentence; When the follow-up reading voice score of the user's whole sentence follow-up reading result is greater than or equal to the third threshold, end the hierarchical follow-up reading training for the user.

7. The method according to claim 1, wherein The performing hierarchical follow-up reading training on the user according to the target object includes: When the overall follow-up reading voice score is in the first interval, perform object follow-up reading training and whole sentence follow-up reading training on the user according to the target object; When the overall follow-up reading voice score is in the second interval, perform short sentence follow-up reading training and whole sentence follow-up reading training on the user according to the target object; When the overall follow-up reading voice score is in the third interval, perform object follow-up reading training, short sentence follow-up reading training and whole sentence follow-up reading training on the user according to the target object; Wherein, the minimum value of the first interval is greater than or equal to the maximum value of the second interval, and the minimum value of the second interval is greater than or equal to the maximum value of the third interval.

8. The method according to claim 1, wherein The method further includes: Obtain the user's identity information, where the identity information includes excellent students or non-excellent students; When the user's identity information is the non-excellent student and the overall follow-up reading voice score is greater than the first threshold, perform hierarchical follow-up reading training on the user according to the target object obtained by the object score of each object included in the target sentence; 9. The method according to claim 8, characterized in that, The method further includes: When the user's identity information is the non-excellent student, the overall follow-up reading voice score is greater than the first threshold, and the target object cannot be obtained according to the object score of each object included in the target sentence, play the next sentence of the target sentence.

10. The method according to claim 8, wherein The method further includes: When the user's identity information is the excellent student and the user's overall follow-up reading voice score of the target sentence is greater than the first threshold, play the next sentence of the target sentence.

11. A shadowing training device, characterized in that, Applied to a terminal device, the device includes: A score acquisition module, configured to acquire the overall follow-up reading voice score of the user for the target sentence; A target object acquisition module, configured to, when the overall follow-up reading voice score is less than or equal to the first threshold, acquire a target object according to the object score of each object included in the target sentence, where the target object is an object whose object score is less than or equal to the second threshold; The follow-up training module is used to conduct hierarchical follow-up training for the user according to the target object. The hierarchical follow-up training includes at least two of object follow-up training, short sentence follow-up training, and whole sentence follow-up training. The number of objects included in the short sentence follow-up training is less than the number of objects included in the whole sentence follow-up training.

12. An electronic device, characterized in that, It includes a memory and a processor. A computer program is stored in the memory. When the computer program is executed by the processor, the processor implements the method according to any one of claims 1 to 10.

13. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the method according to any one of claims 1 to 10.

Images