English learning system and method based on mobile device

Abstract

The invention belongs to the technical field of English education, and discloses an English learning system and method based on mobile equipment. A learning data set and a student data set are collected and preprocessed, the learning data set comprises score data, unit data and duration data, and the student data set comprises age data, gender data and preference data; analyzing the learning data set and the student data set to obtain a learning reference value, and classifying the learning reference value to obtain a learning classification result; analyzing the learning classification result to obtain a user decision result; in general, the method has the remarkable advantages of being high in user learning ability monitoring performance, large in auxiliary decision making effect and high in rapid adjustment accuracy.

Description

Technical Field

[0001] The present invention relates to the technical field of English education, and more specifically, to an English learning system and method based on a mobile device. Background Art

[0002] Due to the strong demand for English learning, how to combine modern technology with English learning so that users can learn English more efficiently, easily and conveniently has become a major challenge in the English learning industry.

[0003] The patent application publication number CN109841101A discloses an English learning system based on a mobile device. Students select the object to communicate (foreign teacher or intelligent system) in the student UI module, enter their grade information, enter the sentence to be communicated, that is, the student language information, and collect the required grade information and the corresponding required difficulty level information through the teaching affairs module. If the student wants to communicate with the foreign teacher, the difficulty level judgment module is used to judge the required difficulty level information according to the student's grade and send the required difficulty level information to the foreign teacher UI module. At the same time, the student language information will also be displayed in the foreign teacher UI module. The foreign teacher replies to the student language information through the foreign teacher UI module. The replied language is called the foreign teacher language information. At the same time, the difficulty level judgment module reviews the foreign teacher language information. If it does not meet the standards, the foreign teacher will be asked to re-enter the foreign teacher UI module until it meets the standards. Finally, the foreign teacher language information is output. Finally, through a combination of intelligence and manual methods, the students' English listening and speaking abilities are trained from simple to complex, which helps students effectively improve their English listening and speaking abilities.

[0004] However, the above-mentioned English learning system based on mobile devices, although it screens the user's oral proficiency and provides a training method based on the user's oral level, it has achieved to a certain extent the provision of matching oral and listening training for users. However, in the process of learning English, not only oral practice is needed, but English grammar, semantics and writing are also extremely important. Therefore, how to enable users to obtain comprehensive and fast feedback on their own comprehensive English learning level and corresponding decision-making plans is related to the good or bad experience of users in the process of English learning.

[0005] In view of this, the present invention proposes an English learning system and method based on a mobile device to solve the above problems. Summary of the invention

[0006] In order to overcome the above-mentioned defects of the prior art and to achieve the above-mentioned purpose, the present invention provides the following technical solutions: comprising: The data collection module is used to collect learning data sets and student data sets and perform preprocessing. The learning data sets include score data, unit data, and duration data, and the student data sets include age data, gender data, and preference data. Furthermore, the methods of collecting the learning data set and the student data set include: By reading the database, the most recent target English unit test score is collected to obtain the score data; By installing the readability assessment tool, collecting the target English unit learning materials, and calculating the sum of the grammatical difficulty value and the semantic difficulty value in the quantified learning materials, the unit data is obtained; By manually inputting, the target English unit learning time and the user's gender are collected to obtain time data and gender data; The user's age value is collected by manual input, substituted into the preset age threshold interval (3, 5, 10, 15, 18, 25, 34, 42, 50), and the corresponding value is (1, 2, 3, 4, 4, 3, 2, 1) to obtain the age data; By installing the assessment tool, collect the assessment scores of the three categories and substitute them into the calculation formula: Get preference data, where is the listening category test score, is the grammatical category test score, To score the writing category, is the total test score; Preprocessing methods include data cleaning, data denoising, and data normalization; The data processing module is used to analyze the learning data set and the student data set to obtain the learning reference value, and classify them to obtain the learning classification result; Furthermore, the steps of analyzing the learning dataset and the student dataset include: Q1: By substituting into the calculation formula: Get the score reference value, where For fractional data, is the unit data, is the duration data, The standard study time; Q2: By substituting into the calculation formula: Get the user reference value, where For age data, For gender data, For preference data, , and are the corresponding weight factors respectively; Q3: Collect L groups of historical feature vectors as sample sets, and divide the sample sets into 70%L training sets, 15%L test sets, and 15%L validation sets; Q4: Establish a learning state classification model based on the training set, obtain the historical feature vector in the training set, preset the higher data cluster P1, normal data cluster P2 and lower data cluster P3, and randomly select three data points in the training set as the original cluster centers, representing the higher data cluster P1, normal data cluster P2 and lower data cluster P3 respectively; Q5: By substituting into the calculation formula: Get the distance between data items, calculate the distance between the data items in the training set and the higher data cluster P1, normal data cluster P2 and lower data cluster P3, and assign the data items to the data cluster with the closest distance, and get three new data clusters as the initial cluster centers, where and is the coordinate value of the data point, and For two data points, The value of the sub-data item, is the number of sub-data items; Q6: Calculate the means of the three new data clusters in the initial cluster center respectively, and calculate them again as the new original cluster center; Q7: Repeat Q5 and Q6 until the preset number of iterations is reached to obtain the user status classification model; Q8: Input the feature vector into the user state classification model and output the learning reference value; Further, the classification methods include: A learning threshold interval (E1, E2) is preset. When the learning reference value is less than E1, a low signal is generated. When the learning reference value is greater than or equal to E1 or less than or equal to E2, a normal signal is generated. When the learning reference value is greater than or equal to E2, a high signal is generated. The lower signal contains a set of fields representing that the user's learning status is poor, the normal signal contains a set of fields representing that the user's learning status is normal, and the higher signal contains a set of fields representing that the user's learning status is good; Pack lower signals, normal signals, and higher signals to obtain learning classification results; Real-time feedback module, used to analyze the learning classification results and obtain the user decision results; Further, the methods for analyzing the learning classification results include: When the learning classification result is a lower signal, an alarm SMS is sent to the user receiving end through the communication unit; when the learning classification result is a normal signal, a normal SMS is sent to the user receiving end through the communication unit; when the learning classification result is a higher signal, a higher SMS is sent to the user receiving end through the communication unit; The alert message includes an explanation of the user's current poor learning status of the target English unit, reminding the user to enhance basic knowledge accumulation, increase learning time or seek educational tutoring support; Normal text messages include explaining that the user's current learning status of the target English unit is normal, reminding the user to complete learning regularly, maintain the current learning status, or contact materials with higher learning difficulty; Higher-level text messages include explaining that the user is currently in a good state of learning the target English unit, reminding the user to relieve learning pressure, increase the duration of other learning goals, or add social practice projects; Pack alarm SMS, normal SMS and high-level SMS to get the user's decision result; The effectiveness evaluation module is used to analyze the score data and obtain the effectiveness evaluation results; Further, the methods for analyzing the score data include: Collect K groups of historical score data and substitute them into the calculation formula: Get the score reference value, where is the coefficient of variation; A score threshold interval (W1, W2) is preset. When the score reference value is less than W1, a decreasing signal is obtained. When the score reference value is greater than or equal to W1 and less than or equal to W2, a flat signal is obtained. When the score reference value is greater than or equal to W2, an increasing signal is obtained. The decreasing signal includes a group of fields representing that the user's total English learning stage score is decreasing, the keeping-alive signal includes a group of fields representing that the user's total English learning stage score is keeping the same, and the increasing signal includes a group of fields representing that the user's total English learning stage score is increasing; Pack the falling signals, the flat signals and the rising signals to obtain the effectiveness evaluation results; Further, S1: collecting a learning data set and a student data set and performing preprocessing, the learning data set includes score data, unit data and duration data, and the student data set includes age data, gender data and preference data; S2: Analyze the learning data set and the student data set to obtain the learning reference value, and classify them to obtain the learning classification result; S3: Analyze the learning classification results to obtain the user decision results; S4: Analyze the score data to obtain effectiveness evaluation results.

[0007] Technical effects and advantages of the English learning system and method based on mobile devices of the present invention: The present invention analyzes the learning data set and the student data set to obtain a learning reference value, which can intuitively reflect the user's current comprehensive level of English learning, greatly improving the user's awareness of his or her own English learning status. The user decision result obtained by analyzing the learning classification results can assist the user to make rapid and accurate adjustments based on his or her own comprehensive level of English learning, greatly improving the accuracy and convenience of the user in the English learning process. The effectiveness evaluation result obtained by analyzing the score data can intuitively show the effect of the user in the overall stage of English learning, assist the user to quickly detect the status of his or her own English learning level, and then quickly adjust his or her own learning. Generally speaking, the present invention has the significant advantages of strong user learning ability monitoring performance, large auxiliary decision-making function and high rapid adjustment accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Figure 1 A schematic diagram of an English learning system based on a mobile device of the present invention; Figure 2 The present invention is a schematic diagram of an English learning method based on a mobile device. DETAILED DESCRIPTION

[0009] 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.

[0010] Example 1 See also Figure 1 As shown, the English learning system based on a mobile device described in this embodiment includes: The data collection module is used to collect learning data sets and student data sets and perform preprocessing. The learning data sets include score data, unit data, and duration data, and the student data sets include age data, gender data, and preference data. Furthermore, the methods of collecting learning data sets and student data sets include: By reading the database, the most recent target English unit test score is collected to obtain the score data; It needs to be explained that the target English unit is the unit text content in the English textbook; By installing the readability assessment tool, collecting the target English unit learning materials, and calculating the sum of the grammatical difficulty value and the semantic difficulty value in the quantified learning materials, the unit data is obtained; It should be explained that the value of the unit data is an integer of 1, 2 or 3. The higher the sum of the quantified grammatical difficulty value and the semantic difficulty value, the higher the value of the unit data. By manually inputting, the target English unit learning time and the user's gender are collected to obtain time data and gender data; It should be explained that the gender data is taken as N1 for males or N2 for females, and N2 is greater than N1 based on physiological differences; The user's age value is collected by manual input, substituted into the preset age threshold interval (3, 5, 10, 15, 18, 25, 34, 42, 50), and the corresponding value is (1, 2, 3, 4, 4, 3, 2, 1) to obtain the age data; By installing the assessment tool, collect the assessment scores of the three categories and substitute them into the calculation formula: Get preference data, where is the listening category test score, is the grammatical category test score, To score the writing category, is the total test score; Preprocessing methods include data cleaning, data denoising, and data normalization; The data processing module is used to analyze the learning data set and the student data set to obtain the learning reference value, and classify them to obtain the learning classification result; Further, the steps of analyzing the learning dataset and the student dataset include: Q1: By substituting into the calculation formula: Get the score reference value, where For fractional data, is the unit data, is the duration data, The standard study time; It should be explained that the standard study time is the recommended study time based on the difficulty of the target English unit, such as 2 hours, 4 hours or 6 hours; Q2: By substituting into the calculation formula: Get the user reference value, where For age data, For gender data, For preference data, , and are the corresponding weight factors respectively; Q3: Collect L groups of historical feature vectors as sample sets, and divide the sample sets into 70%L training sets, 15%L test sets, and 15%L validation sets; It should be explained that the feature vector is the weighted sum of the score reference value and the user reference value; Q4: Establish a learning state classification model based on the training set, obtain the historical feature vector in the training set, preset the higher data cluster P1, normal data cluster P2 and lower data cluster P3, and randomly select three data points in the training set as the original cluster centers, representing the higher data cluster P1, normal data cluster P2 and lower data cluster P3 respectively; Q5: By substituting into the calculation formula: Get the distance between data items, calculate the distance between the data items in the training set and the higher data cluster P1, normal data cluster P2 and lower data cluster P3, and assign the data items to the data cluster with the closest distance, and get three new data clusters as the initial cluster centers, where and is the coordinate value of the data point, and For two data points, The value of the sub-data item, is the number of sub-data items; Q6: Calculate the means of the three new data clusters in the initial cluster center respectively, and calculate them again as the new original cluster center; Q7: Repeat Q5 and Q6 until the preset number of iterations is reached to obtain the user status classification model; Q8: Input the feature vector into the user state classification model and output the learning reference value; Further classification methods include: A learning threshold interval (E1, E2) is preset. When the learning reference value is less than E1, a low signal is generated. When the learning reference value is greater than or equal to E1 or less than or equal to E2, a normal signal is generated. When the learning reference value is greater than E2, a high signal is generated. The lower signal contains a set of fields representing that the user's learning status is poor, the normal signal contains a set of fields representing that the user's learning status is normal, and the higher signal contains a set of fields representing that the user's learning status is good; Pack lower signals, normal signals, and higher signals to obtain learning classification results; Real-time feedback module, used to analyze the learning classification results and obtain the user decision results; Further, the methods for analyzing the learning classification results include: When the learning classification result is a lower signal, an alarm SMS is sent to the user receiving end through the communication unit; when the learning classification result is a normal signal, a normal SMS is sent to the user receiving end through the communication unit; when the learning classification result is a higher signal, a higher SMS is sent to the user receiving end through the communication unit; The alert message includes an explanation of the user's current poor learning status of the target English unit, reminding the user to enhance basic knowledge accumulation, increase learning time or seek educational tutoring support; Normal text messages include explaining that the user's current learning status of the target English unit is normal, reminding the user to complete learning regularly, maintain the current learning status, or contact materials with higher learning difficulty; Higher-level text messages include explaining that the user is currently in a good state of learning the target English unit, reminding the user to relieve learning pressure, increase the duration of other learning goals, or add social practice projects; Pack alarm SMS, normal SMS and high-level SMS to get the user's decision result; The effectiveness evaluation module is used to analyze the score data and obtain the effectiveness evaluation results; Further, the methods for analyzing the score data include: Collect K groups of historical score data and substitute them into the calculation formula: Get the score reference value, where is the coefficient of variation; It should be explained that the coefficient of variation is calculated by substituting into the formula: get; A score threshold interval (W1, W2) is preset. When the score reference value is less than W1, a decreasing signal is obtained. When the score reference value is greater than W1 and less than or equal to W2, a flat signal is obtained. When the score reference value is greater than or equal to W2, an increasing signal is obtained. The decreasing signal includes a group of fields representing that the user's total English learning stage score is decreasing, the keeping-alive signal includes a group of fields representing that the user's total English learning stage score is keeping the same, and the increasing signal includes a group of fields representing that the user's total English learning stage score is increasing; Pack the falling signals, the flat signals and the rising signals to obtain the effectiveness evaluation results; The beneficial effects of this embodiment are as follows: the learning reference value obtained by analyzing the learning data set and the student data set can intuitively reflect the user's current comprehensive level of English learning, which greatly improves the user's awareness of his or her own English learning status; the user decision result obtained by analyzing the learning classification results can assist the user to make rapid and accurate adjustments based on his or her own comprehensive level of English learning, which greatly improves the accuracy and convenience of the user in the English learning process; the effectiveness evaluation result obtained by analyzing the score data can intuitively show the effect of the user in the overall stage of English learning, assist the user to quickly detect the status of his or her own English learning level, and then quickly adjust his or her own learning; in general, the present invention has the significant advantages of strong user learning ability monitoring performance, large auxiliary decision-making function and high rapid adjustment accuracy.

[0011] Example 2 See also Figure 2 As shown, the part not described in detail in this embodiment is described in Example 1, and an English learning method based on a mobile device is provided, including: S1: collecting a learning data set and a student data set, and preprocessing them, the learning data set includes score data, unit data and duration data, and the student data set includes age data, gender data and preference data; S2: Analyze the learning data set and the student data set to obtain the learning reference value, and classify them to obtain the learning classification result; S3: Analyze the learning classification results to obtain the user decision results; S4: Analyze the score data to obtain effectiveness evaluation results.

[0012] Example 3 This embodiment discloses an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the operation mode of the above-mentioned English learning method based on a mobile device is implemented.

[0013] Since the electronic device introduced in this embodiment is an electronic device used to implement an English learning method based on a mobile device in the embodiment of this application, based on the English learning method based on a mobile device introduced in the embodiment of this application, a person skilled in the art can understand the specific implementation of the electronic device of this embodiment and its various variations, so how the electronic device implements the method in the embodiment of this application is not described in detail here. As long as a person skilled in the art implements the electronic device used in the English learning method based on a mobile device in the embodiment of this application, it belongs to the scope of protection of this application.

[0014] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and thresholds in the formula are set by technicians in this field according to actual conditions.

[0015] The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technical users in this technical field, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of the present invention.

Claims

1. An English learning system based on a mobile device, characterized in that: include: The data collection module is used to collect learning data sets and student data sets and perform preprocessing. The learning data sets include score data, unit data, and duration data, and the student data sets include age data, gender data, and preference data. The data processing module is used to analyze the learning data set and the student data set to obtain the learning reference value, and classify them to obtain the learning classification result; Real-time feedback module, used to analyze the learning classification results and obtain the user decision results; The effectiveness evaluation module is used to analyze the score data and obtain the effectiveness evaluation results; Methods for collecting learning datasets and student datasets include: By reading the database, the most recent target English unit test score is collected to obtain the score data; By installing the readability assessment tool, collecting the target English unit learning materials, and calculating the sum of the grammatical difficulty value and the semantic difficulty value in the quantified learning materials, the unit data is obtained; By manually inputting, the target English unit learning time and the user's gender are collected to obtain time data and gender data; The user's age value is collected by manual input, substituted into the preset age threshold interval (3, 5, 10, 15, 18, 25, 34, 42, 50), and the corresponding value is (1, 2, 3, 4, 4, 3, 2, 1) to obtain the age data; By installing the assessment tool, collect the assessment scores of the three categories and substitute them into the calculation formula: Get preference data, where is the listening category test score, is the grammatical category test score, To score the writing category, is the total test score; Preprocessing methods include data cleaning, data denoising and data normalization.

2. The English learning system based on mobile device according to claim 1, characterized in that: The steps for analyzing the learning and student datasets include: Q1: By substituting into the calculation formula: Get the score reference value, where For fractional data, is the unit data, is the duration data, The standard study time; Q2: By substituting into the calculation formula: Get the user reference value, where For age data, For gender data, For preference data, , and are the corresponding weight factors respectively; Q3: Collect L groups of historical feature vectors as sample sets, and divide the sample sets into 70%L training sets, 15%L test sets, and 15%L validation sets; Q4: Establish a learning state classification model based on the training set, obtain the historical feature vector in the training set, preset the higher data cluster P1, normal data cluster P2 and lower data cluster P3, and randomly select three data points in the training set as the original cluster centers, representing the higher data cluster P1, normal data cluster P2 and lower data cluster P3 respectively; Q5: By substituting into the calculation formula: Get the distance between data items, calculate the distance between the data items in the training set and the higher data cluster P1, normal data cluster P2 and lower data cluster P3, and assign the data items to the data cluster with the closest distance, and get three new data clusters as the initial cluster centers, where and is the coordinate value of the data point, and For two data points, The value of the sub-data item, is the number of sub-data items; Q6: Calculate the means of the three new data clusters in the initial cluster center respectively, and calculate them again as the new original cluster center; Q7: Repeat Q5 and Q6 until the preset number of iterations is reached to obtain the user status classification model; Q8: Input the feature vector into the user state classification model and output the learning reference value.

3. The English learning system based on mobile device according to claim 2, characterized in that: The classification methods include: A learning threshold interval (E1, E2) is preset. When the learning reference value is less than E1, a low signal is generated. When the learning reference value is greater than or equal to E1 or less than or equal to E2, a normal signal is generated. When the learning reference value is greater than E2, a high signal is generated. The lower signal contains a set of fields representing that the user's learning status is poor, the normal signal contains a set of fields representing that the user's learning status is normal, and the higher signal contains a set of fields representing that the user's learning status is good; Pack the lower signal, normal signal and higher signal to get the learning classification result.

4. The English learning system based on mobile device according to claim 3, characterized in that: Methods for analyzing learning classification results include: When the learning classification result is a lower signal, an alarm SMS is sent to the user receiving end through the communication unit; when the learning classification result is a normal signal, a normal SMS is sent to the user receiving end through the communication unit; when the learning classification result is a higher signal, a higher SMS is sent to the user receiving end through the communication unit; The alert message includes an explanation of the user's current poor learning status of the target English unit, reminding the user to enhance basic knowledge accumulation, increase learning time or seek educational tutoring support; Normal text messages include explaining that the user's current learning status of the target English unit is normal, reminding the user to complete learning regularly, maintain the current learning status, or contact materials with higher learning difficulty; Higher-level text messages include explaining that the user is currently in a good state of learning the target English unit, reminding the user to relieve learning pressure, increase the duration of other learning goals, or add social practice projects; Pack the alarm SMS, normal SMS and higher SMS to get the user decision result.

5. The English learning system based on mobile device according to claim 4, characterized in that: The methods for analyzing the score data include: Collect K groups of historical score data and substitute them into the calculation formula: Get the score reference value, where is the coefficient of variation; A score threshold interval (W1, W2) is preset. When the score reference value is less than or equal to W1, a decreasing signal is obtained. When the score reference value is greater than or equal to W1 and less than or equal to W2, a flat signal is obtained. When the score reference value is greater than or equal to W2, an increasing signal is obtained. The decreasing signal includes a group of fields representing that the user's total English learning stage score is decreasing, the keeping-alive signal includes a group of fields representing that the user's total English learning stage score is keeping the same, and the increasing signal includes a group of fields representing that the user's total English learning stage score is increasing; Package the falling signals, flat signals and rising signals to obtain the effectiveness evaluation results.

6. A method for learning English based on a mobile device, implemented according to any one of claims 1 to 5, wherein: S1: Collect learning data sets and student data sets and perform preprocessing. The learning data sets include score data, unit data, and duration data, and the student data sets include age data, gender data, and preference data. S2: Analyze the learning data set and the student data set to obtain the learning reference value, and classify them to obtain the learning classification result; S3: Analyze the learning classification results to obtain the user decision results; S4: Analyze the score data to obtain effectiveness evaluation results.

Images