An intelligent English teaching method and system
By analyzing the historical record data of target students and other students, calculating field similarity and reference indicators, and recommending suitable learning projects, the problems of low learning efficiency and high cost in traditional intelligent English teaching systems are solved, and personalized learning and The effect of cost reduction.
Patent Information
- Application Number
- CN202411187079.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-28
- Publication Date
- 2024-11-22
- Estimated Expiration
- 2044-08-28
AI Technical Summary
Due to the huge amount of data and the one-sided nature of students' independent selection of learning projects, traditional intelligent English teaching systems have low learning efficiency and high cost.
By counting the historical data of target students and other students, calculating similarity and reference indicators of the field and project, we recommend learning projects suitable for target students, improve learning efficiency and reduce teaching costs.
It realizes personalized English learning project recommendations, improves students' learning efficiency, and reduces the cost of English teaching.
Smart Images

Figure CN118710137B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of intelligent English teaching, and in particular to an intelligent English teaching method and system. Background Art
[0002] Intelligent English teaching refers to a teaching system that is adaptively designed to assist English teaching through artificial intelligence technology, so as to use artificial intelligence technology to assist, improve and optimize the English teaching process. Intelligent English teaching can provide students with personalized learning experience and help teachers to teach and evaluate more efficiently. However, because traditional intelligent English teaching systems contain knowledge in various fields, the types of learning projects are complicated and the amount of data is huge, when students choose traditional intelligent English teaching to learn English, they usually rely on their own preferences and habits to choose the corresponding learning projects to learn. However, relying on students' own preferences and habits to choose learning projects is one-sided. Usually, due to inappropriate learning project selection, it greatly affects students' learning efficiency, so that students' learning effect using traditional intelligent English teaching is poor. Summary of the invention
[0003] In view of the above, it is necessary to provide an intelligent English teaching method and system, which improves students' English learning efficiency compared with traditional intelligent English teaching methods and systems, so as to further reduce the cost of English teaching.
[0004] The first aspect of the present application provides an intelligent English teaching method, which is applied to the field of intelligent English teaching, and the method comprises: collecting historical record data of a target student and other students, wherein the historical record data includes a number of fields, each field includes a number of projects, and the other students refer to other students who have studied the target project corresponding to the target student; calculating the corresponding field similarity between the target student and the other students based on the difference in the number of fields and projects in the historical record data of the target student and the other students; confirming the reference index corresponding to the target student and the other students according to the category value, distance measurement index and the field similarity corresponding to the classification category to which the target student and the other students belong; calculating the recommendation rate corresponding to the target project corresponding to the target student through the field feature value corresponding to the target student and the reference index corresponding to the target student and the other students; sorting the recommendation rates corresponding to a number of projects, and confirming that the projects corresponding to the recommendation rates in the sorting order of the preset number are the recommended projects for the target student.
[0005] In one of the embodiments, the corresponding field similarity between the target student and other students is calculated based on the difference in the number of fields and projects in the historical record data of the target student and other students, specifically including: obtaining the number of projects that the target student and other students have studied in each field they have studied according to the historical record data of the target student and other students; inputting the number of projects that the target student and other students have studied in each field they have studied into a preset field similarity calculation formula, and calculating the corresponding field similarity between the target student and other students.
[0006] In one embodiment, the number of fields studied by the target student and other students, as well as the number of projects studied in each field, are input into a preset field similarity calculation formula to calculate the corresponding field similarity between the target student and other students, specifically including:
[0007]
[0008] in, For target students and The corresponding domain similarity between other students, For the target students The number of projects studied in the field, The number of programs that the target students have studied in all fields, For the Other students in The number of projects studied in the field, For the The number of programs studied by other students in all fields, The number of areas that the target students have studied, A preset positive constant.
[0009] In one embodiment, the determining of reference indicators corresponding to the target student and other students according to the category values, distance measurement indicators and the field similarity corresponding to the classification categories to which the target student and other students belong specifically includes: constructing learning level indicators corresponding to the target student and other students respectively based on the number of valid items, the number of learning times and the corresponding learning time respectively confirmed by the historical record data of the target student and other students, wherein the valid items refer to items with a learning time greater than a preset threshold; calculating new field interest indicators corresponding to the target student and other students respectively according to the number of learned fields and their items confirmed by the historical record data of the target student and other students; calculating the distance measurement indicators corresponding to the target student and other students by the difference in learning level indicators corresponding to the target student and other students and the difference in new field interest indicators corresponding to the target student and other students; classifying the target student and other students to define classification categories based on a preset clustering algorithm and the distance measurement indicators corresponding to the target student and other students to determine the category values corresponding to the classification categories to which the target student and other students belong; inputting the category values, distance measurement indicators and the field similarity corresponding to the classification categories to which the target student and other students belong into a preset reference indicator calculation formula to calculate the reference indicators corresponding to the target student and other students.
[0010] In one of the embodiments, the number of valid items confirmed based on the historical record data of the target student and other students, the number of learning times and the corresponding learning time, respectively, are used to construct the learning level indicators of the target student and other students, wherein the valid items refer to items with a learning time greater than a preset threshold, specifically including: based on the historical record data, comparing the learning time of the items studied by the target student and other students with the preset threshold, so as to confirm the items with a learning time greater than the preset threshold as valid items; counting the number of valid items corresponding to the target student and other students, the number of learning times and the corresponding learning time, and the correct rate of exercises corresponding to each learning; constructing the learning level indicators of the target student and other students according to the number of valid items corresponding to the target student and other students, the number of learning times and the corresponding learning time, and the correct rate of exercises corresponding to each learning.
[0011] In one embodiment, constructing a learning level indicator corresponding to the target student according to the number of valid items corresponding to the target student, the number of learning times and the corresponding learning time, and the correct rate of practice corresponding to each learning of each valid item specifically includes:
[0012]
[0013] in, The learning level indicators corresponding to the target students, is the number of valid items, For the Number of effective items learned, For the target students Valid items The correct rate of practice corresponding to the learning time, For the target students Valid items Correspondingly, the target student's corresponding new field interest index is calculated based on the target student's historical record data and the number of fields and projects studied, including:
[0014]
[0015] in, New field interest indicators corresponding to target students, The number of areas that the target students have studied, is the number of all domains in the system, is the variance corresponding to the items that the target students have learned in different fields, is the maximum number of projects in the field that the target student has studied, It is the minimum number of projects in the field studied by the target students.
[0016] In one embodiment, calculating the distance measurement index corresponding to the target student and other students by using the difference in the learning level index corresponding to the target student and other students, and the difference in the new field interest index corresponding to the target student and other students, specifically includes:
[0017]
[0018] in, Target students and The distance metric corresponding to other students is New field interest indicators corresponding to target students, No. New field interest indicators corresponding to other students, The learning level indicators corresponding to the target students, For the New field interest indicators corresponding to other students, For An exponential function with base .
[0019] In one embodiment, the inputting of the category values, distance measurement indicators and field similarity corresponding to the classification categories to which the target student and other students belong into a preset reference indicator calculation formula to calculate the reference indicators corresponding to the target student and other students specifically includes:
[0020]
[0021] in, For target students and The reference indicators corresponding to other students, For target students and The distance metric corresponding to other students is For target students and The corresponding domain similarity between other students, is the category value corresponding to the classification category to which the target student belongs, For the The category values corresponding to the classification categories of other students, A preset positive constant.
[0022] In one embodiment, the calculation of the recommendation rate corresponding to the target project corresponding to the target student by using the domain feature value corresponding to the target student and the reference index corresponding to the target student and other students specifically includes:
[0023]
[0024] in, The recommendation rate of the target project corresponding to the target students, is the domain feature value corresponding to the target student, is the number of other students, For target students and The reference indicators corresponding to other students, where when the field to which the target project belongs is the field that the target student has studied, the field characteristic value The value is 1. When the target project belongs to a field that the target student has not studied, the field feature value The value is the new field interest index corresponding to the target students .
[0025] The first aspect of the present application provides an intelligent English teaching system, which is applied to the field of intelligent English teaching, and the system includes: a statistical module, which is used to count historical record data of a target student and other students, wherein the historical record data includes a number of fields, each project data includes a number of projects, and the other students refer to other students who have studied the target project corresponding to the target student; a calculation module, which is used to calculate the corresponding field similarity between the target student and other students based on the difference in the number of fields and projects in the historical record data of the target student and other students; a confirmation module, which is used to confirm the reference index corresponding to the target student and other students according to the category value, distance measurement index and the field similarity corresponding to the classification category to which the target student and other students belong; an analysis module, which is used to calculate the recommendation rate corresponding to the target project corresponding to the target student through the field feature value corresponding to the target student and the reference index corresponding to the target student and other students; a recommendation module, which is used to sort the recommendation rates corresponding to a number of projects, and confirm that the projects corresponding to the recommendation rates in the sorting order of the preset number are the recommended projects of the target student.
[0026] The embodiment of the present application first counts the historical record data of the target student and other students, wherein the historical record data includes a number of fields, each field includes a number of projects, and the other students refer to other students who have studied the target project corresponding to the target student, and then based on the number of differences in fields and projects in the historical record data of the target student and other students, calculate the field similarity corresponding to the target student and other students, and then confirm the reference index corresponding to the target student and other students according to the category value, distance measurement index and field similarity corresponding to the classification category to which the target student and other students belong, and calculate the recommendation rate corresponding to the target project corresponding to the target student through the field feature value corresponding to the target student and the reference index corresponding to the target student and other students, and finally sort the recommendation rates corresponding to the number of projects, and confirm that the recommendation rate corresponding to the project in the preset number sorting order is the recommended project for the target student. Through the historical record data of the target student and other students, calculate the recommendation rate corresponding to the target project corresponding to the target student, and finally confirm the preset number of projects with the highest recommendation rate as the recommended project for the target student to learn English, so as to improve the efficiency of students' English learning and further reduce the cost of English teaching compared with the traditional students' self-selection of projects for learning. BRIEF DESCRIPTION OF THE DRAWINGS
[0027] Figure 1 It is a flow chart of an intelligent English teaching method according to an embodiment of the present application.
[0028] Figure 2This is a schematic diagram of the first sub-process of an intelligent English teaching method according to an embodiment of the present application.
[0029] Figure 3 This is a schematic diagram of the second sub-process of an intelligent English teaching method according to an embodiment of the present application.
[0030] Figure 4 This is a schematic diagram of the third sub-process of an intelligent English teaching method according to an embodiment of the present application.
[0031] Figure 5 It is a block diagram of an intelligent English teaching system according to an embodiment of the present application. DETAILED DESCRIPTION
[0032] In the description of the embodiments of the present application, words such as "exemplary", "or", "for example" and the like are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary", "or", "for example" and the like is intended to present related concepts in a concrete manner.
[0033] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field in this application. The terms used in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application. It should be understood that, unless otherwise specified in this application, " / " means or. For example, A / B can represent A or B. "And / or" in this application is only a description of the association relationship of associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. "At least one" means one or more. "Multiple" means two or more than two. For example, at least one of a, b or c can represent: a, b, c, a and b, a and c, b and c, a, b and c seven situations.
[0034] It should also be noted that the terms "first" and "second" in the specification, claims and drawings of this application are used to distinguish similar objects, rather than to describe a specific order or sequence. The method disclosed in the embodiments of this application or the method shown in the flowchart includes one or more steps for implementing the method. Without departing from the scope of the claims, the execution order of multiple steps can be interchanged with each other, and some steps can also be deleted.
[0035] The present application embodiment first proposes an intelligent English teaching method, which is applied to the field of intelligent English teaching. Figure 1 , the method comprising:
[0036] S101. Collect historical record data of the target student and other students, wherein the historical record data includes a number of fields, each project data includes a number of projects, and the other students refer to other students who have studied the target project corresponding to the target student.
[0037] It should be noted that the intelligent English teaching method is executed in an intelligent English teaching system, and the intelligent English teaching system records the historical record data of the target student and other students. The historical record data of the target student and other students refers to the data recorded by the target student and other students in the intelligent English teaching system before learning English, including but not limited to the fields learned, the projects learned, the learning time of each field, the learning time of each project, the practice accuracy of each field, the practice accuracy of each project, the statistical data of students who have learned each field, the statistical data of students who have learned each project, and other related data. The historical record data includes a number of fields, and the fields can be astronomy, geography, history, customs and other learning fields. Each field includes a number of projects, and the projects can be reading articles, word groups, long and short sentence exercises, reading comprehension, cloze and other learning projects. The other students refer to other students who have learned the target project corresponding to the target student, that is, the system traverses each project according to the target student, and the historical record data records the students who have learned each project. In the target project currently determined by the system, except for the target student, the students who have learned the target project recorded in the historical record data are defined as other students.
[0038] It is necessary to analyze that the historical record data records some previous learning data of the target student and other students, for example, the target student has learned English knowledge in 10 fields, has learned 36 exercises in total, and has studied for 48 hours in total. The purpose of recording the historical record data corresponding to the target student and other students is that after the target student logs into the intelligent English teaching system, the system can analyze and calculate the learning projects that are more suitable for the target student based on the historical record data corresponding to the target student and other students. The system recommends these learning projects to the target student for selection. Compared with the traditional method of selecting projects for learning based on students' subjective judgment, it can greatly improve students' learning efficiency and further improve the teaching effect of English teaching.
[0039] S102: Calculate the corresponding field similarities between the target student and other students based on the differences in the number of fields and items in the historical record data of the target student and other students.
[0040] Among them, after the intelligent English teaching system determines the data of the fields and projects recorded in the historical record data of the target student and other students, the field similarity between the target student and other students is calculated according to the difference in the number of fields and projects in the historical record data of the target student and other students. The field similarity between the target student and other students refers to the similarity of the field selection of the target student and other students in the previous English learning. The field similarity between the target student and other students can reflect to a certain extent whether the learning methods and types of the target student and other students are similar. If the learning methods and types are similar to a certain extent, the project that other students have learned and the target student has not learned is recommended to the target student, which can improve the learning enthusiasm and learning efficiency of the target student. The difference in the number of fields and projects in the historical record data of the target student and other students can be the difference in the number of fields that the target student and other students have learned before, or the difference in the number of projects in the fields that the target student and other students have learned before.
[0041] It should be noted that when the similarity between the target student and other students is greater, it means that the fields and projects studied by the other students are similar to those of the target student, and the fields and projects studied by the other students but not studied by the target student are more likely to be suitable for the target student. When the similarity between the target student and other students is smaller, it means that the fields and projects studied by the other students are not similar to those of the target student, and the fields and projects studied by the other students are more likely to be unsuitable for the target student.
[0042] S103. Confirm reference indicators corresponding to the target student and other students based on the category values, distance measurement indicators and field similarities corresponding to the classification categories to which the target student and other students belong.
[0043] Among them, the distance measurement index corresponding to the target student and other students refers to an index that measures the similarity or difference between the target student and other students in project selection. In the fields of machine learning, data mining and statistics, distance measurement plays an important role in tasks such as clustering, classification and recommendation systems. The classification category to which the target student and other students belong is obtained by clustering the distance measurement index corresponding to the target student and other students with a preset classification algorithm to obtain a number of classification categories, each of which corresponds to a category value.
[0044] It should be noted that the category values corresponding to the classification categories to which the target student and other students belong are obtained by calculating the mean of the subcategory values corresponding to each student in each classification category. The subcategory value corresponding to each student represents the learning ability of each student. The higher the subcategory value, the stronger the student's learning ability.
[0045] It should be noted that the classification categories of the target students and other students are obtained through clustering. The learning abilities and learning interests of students in the same classification category are relatively similar. For example, in the same category, student A is interested in the relevant knowledge, but student B has not completed the relevant learning, but may also be interested in the relevant knowledge. Therefore, the corresponding learning part of student A can be adaptively recommended to student B. Moreover, the learning ability difference of students in the same category is small, and student B can often complete the part learned by student A. For different categories with small differences (the average learning ability difference of students corresponding to the category is the smallest), the learning of students with poor learning ability can also be guided according to the learning habits of students with better learning ability. It can better enable different students to learn from each other and improve learning efficiency.
[0046] S104. Calculate the recommendation rate of the target project corresponding to the target student by using the domain feature value corresponding to the target student and the reference indicators corresponding to the target student and other students.
[0047] Among them, after obtaining the domain characteristic value corresponding to the target student and the reference index corresponding to the target student and other students, they are used as calculation parameters, and the preset calculation rules are input to calculate the recommendation rate corresponding to the target project corresponding to the target student. The recommendation rate corresponding to the target project corresponding to the target student refers to the recommendation degree of the target project relative to the target student. When the recommendation rate corresponding to the target project corresponding to the target student is larger, the target project is more in line with the interests and abilities of the target student, and the student learns more efficiently and effectively. When the recommendation rate corresponding to the target project corresponding to the target student is smaller, the target project is not very in line with the interests and abilities of the target student, and the student learns less efficiently.
[0048] S105, sorting the recommendation rates corresponding to a number of items, and confirming that the items corresponding to the recommendation rates in the preset sorting order are the recommended items for the target students.
[0049] After obtaining the recommendation rates corresponding to all the items of a certain number, they are sorted according to the recommended size, and the items corresponding to the preset number of recommendation rates that are ranked first in the sorting order are confirmed as the recommended items for the target students. For example, if the preset number is 10, the items corresponding to the top ten recommendation rates in the sorting order are confirmed as the recommended items for the target students to learn English.
[0050] The embodiment of the present application first counts the historical record data of the target student and other students, wherein the historical record data includes a number of fields, each field includes a number of projects, and the other students refer to other students who have studied the target project corresponding to the target student, and then based on the number of differences in fields and projects in the historical record data of the target student and other students, calculate the field similarity corresponding to the target student and other students, and then confirm the reference index corresponding to the target student and other students according to the category value, distance measurement index and field similarity corresponding to the classification category to which the target student and other students belong, and calculate the recommendation rate corresponding to the target project corresponding to the target student through the field feature value corresponding to the target student and the reference index corresponding to the target student and other students, and finally sort the recommendation rates corresponding to the number of projects, and confirm that the recommendation rate corresponding to the project in the preset number sorting order is the recommended project for the target student. Through the historical record data of the target student and other students, calculate the recommendation rate corresponding to the target project corresponding to the target student, and finally confirm the preset number of projects with the highest recommendation rate as the recommended project for the target student to learn English, so as to improve the efficiency of students' English learning and further reduce the cost of English teaching compared with the traditional students' self-selection of projects for learning.
[0051] In one embodiment of the present application, see the attached Figure 2 S102, based on the quantitative differences in fields and items in the historical record data of the target student and other students, calculating the corresponding field similarities between the target student and other students, specifically includes:
[0052] S201. According to the historical record data of the target student and other students, respectively obtain the number of items that the target student and other students have studied in each field that they have studied.
[0053] After obtaining the registration information of the target student, the intelligent English teaching system collects historical record data of the target student and other students to retrieve data on fields studied by the target student and other students, and data on items studied in the fields studied.
[0054] S202, input the number of items studied by the target student and other students in each field studied into a preset field similarity calculation formula, and calculate the corresponding field similarity between the target student and other students.
[0055] After obtaining the number of items that the target student and other students have studied in each field they have studied, it is used as a calculation parameter and input into a preset field similarity calculation formula to calculate the corresponding field similarity between the target student and other students.
[0056] Specifically, the number of fields studied by the target student and other students, as well as the number of projects studied in each field, are input into a preset field similarity calculation formula to calculate the corresponding field similarity between the target student and other students, specifically including:
[0057]
[0058] in, For target students and The corresponding domain similarity between other students, For the target students The number of projects studied in the field, The number of programs that the target students have studied in all fields, For the Other students in The number of projects studied in the field, For the The number of programs studied by other students in all fields, The number of areas that the target students have studied, A preset positive constant.
[0059] It should be noted that when the target student The corresponding domain similarity between other students The larger the If the fields and projects studied by other students are similar to those of the target student, then Fields and projects that other students have studied and that the target student has not studied are more likely to be suitable for the target student. The corresponding domain similarity between other students The smaller the The fields and projects studied by other students are not similar to those of the target student. The fields and projects studied by other students may not be suitable for the target students.
[0060] In one embodiment of the present application, refer to the attached Figure 3 S103: According to the category values, distance measurement indicators and field similarities corresponding to the classification categories to which the target student and other students belong, the reference indicators corresponding to the target student and other students are confirmed, specifically including:
[0061] S301. Based on the number of valid projects, the number of learning times and the corresponding learning time confirmed by the historical record data of the target student and other students, the learning level indicators corresponding to the target student and other students are constructed respectively, wherein the valid project refers to the project with a learning time greater than a preset threshold.
[0062] Among them, according to the historical record data of the target student and other students, the number of valid items with learning time greater than the preset threshold, the number of learning times and the corresponding learning time can be counted and calculated to judge the learning level of the target student and other students. The learning level index corresponding to the target student and other students refers to the degree of learning level of the target student and other students calculated respectively through the data recorded in the historical record data.
[0063] For details, please refer to the attached Figure 4 , the number of valid items, the number of learning times and the corresponding learning time confirmed based on the historical record data of the target student and other students respectively, respectively construct the learning level indicators corresponding to the target student and other students, wherein the valid items refer to items with a learning time greater than a preset threshold, specifically including:
[0064] S401. Based on the historical record data of the target student and other students, compare the study time of the projects studied by the target student and other students with a preset threshold value, so as to confirm the projects with a study time longer than the preset threshold value as valid projects.
[0065] Among them, based on the historical record data of the target student and other students, the study time of the projects studied by the target student and other students is counted, and then the study time of each project studied is compared with the preset threshold one by one, and the projects with a study time greater than the preset threshold are confirmed as valid projects, and the projects with a study time less than or equal to the preset threshold are confirmed as invalid projects. That is, because the study time of invalid projects is short, they can be judged as invalid learning and will not enter the subsequent calculation. It should be noted that the preset threshold is preferably set to one tenth of the average study time of all students studying the learning project.
[0066] S402, counting the number of valid items corresponding to the target student and other students, the number of learning times and the corresponding learning time, and the correct rate of exercises corresponding to each learning.
[0067] Among them, after determining the valid items corresponding to the target student, the number of valid items corresponding to the target student and other students, the number of learning times of each valid item, the learning time corresponding to each valid item each time, and the practice accuracy rate corresponding to each valid item each time are counted.
[0068] S403. Construct learning level indicators corresponding to the target student and other students based on the number of valid items corresponding to the target student and other students, the number of learning times and the corresponding learning time, and the correct rate of exercises corresponding to each learning.
[0069] Among them, after obtaining the number of valid items corresponding to the target students and other students, the number of learning times and the corresponding learning time, and the exercise accuracy corresponding to each learning, they are used as construction parameters to construct the learning level indicators corresponding to the target students and other students.
[0070] Specifically, the learning level indicator corresponding to the target student is constructed according to the number of valid items corresponding to the target student, the number of learning times and the corresponding learning time, and the correct rate of practice corresponding to each valid item each time of learning, and specifically includes:
[0071]
[0072] in, The learning level indicators corresponding to the target students, is the number of valid items, For the Number of effective items learned, For the target students Valid items The correct rate of practice corresponding to the learning time, For the target students Valid items The learning time corresponding to each learning session.
[0073] S302, calculating the new field interest indexes corresponding to the target student and other students respectively according to the number of studied fields and items confirmed by the historical record data of the target student and other students.
[0074] Among them, based on the historical record data of the target student and other students, the number of fields studied by the target student and other students and the number of projects studied in each field can be counted, so as to further calculate the variance corresponding to the projects studied by the target student and other students in different fields, as well as the maximum and minimum values of the number of projects in the studied fields, which are used to calculate the new field interest indicators corresponding to the target student and other students respectively.
[0075] Specifically, the calculation of the new field interest index corresponding to the target student based on the number of fields and projects studied confirmed by the historical record data of the target student specifically includes:
[0076]
[0077] in, New field interest indicators corresponding to target students, The number of areas that the target students have studied, is the number of all domains in the system, is the variance corresponding to the items that the target students have learned in different fields, is the maximum number of projects in the field that the target student has studied, It is the minimum number of projects in the field studied by the target students.
[0078] S303. Calculate the distance measurement index corresponding to the target student and other students based on the difference in learning level indexes corresponding to the target student and other students, and the difference in new field interest indexes corresponding to the target student and other students.
[0079] Specifically, after obtaining the learning level index corresponding to the target student and other students, and the new field interest index corresponding to the target student and other students, the distance measurement index corresponding to the target student and other students is further calculated according to the difference between the learning level index and the new field interest index of the two. The difference between the learning level index and the new field interest index of the two can be obtained by calculating the difference between the two.
[0080] Specifically, the distance measurement index corresponding to the target student and other students is calculated by using the difference in the learning level index corresponding to the target student and other students, and the difference in the new field interest index corresponding to the target student and other students, and specifically includes:
[0081]
[0082] in, Target students and The distance metric corresponding to other students is New field interest indicators corresponding to target students, No. New field interest indicators corresponding to other students, The learning level indicators corresponding to the target students, For the New field interest indicators corresponding to other students, For An exponential function with base .
[0083] S304: Based on a preset clustering algorithm and a distance measurement index corresponding to the target student and other students, the target student and other students are classified to define classification categories, so as to confirm the category values corresponding to the classification categories to which the target student and other students belong.
[0084] Wherein, the preset clustering algorithm may be a K-means clustering algorithm, which is an unsupervised learning algorithm for dividing an unlabeled data set into K different clusters. The goal of the K-means clustering algorithm is to classify data points with similar characteristics into the same cluster, while making the data points between different clusters as different as possible. The basic idea of the K-means clustering algorithm is to minimize the sum of the distances from the data points in each cluster to the cluster center through iterative optimization. The basic steps of the K-means clustering algorithm for classifying the target student and other students are as follows: 1) Initialization: Select K data points as the initial cluster centers. This can be achieved by random selection or other heuristic methods. 2) Assignment: Assign each data point to the nearest cluster center. Calculate using the distance metric corresponding to the target student and other students. 3) Update: For each cluster, calculate the mean of all data points in the cluster and use the mean as the new cluster center. 4) Iteration: Repeat steps 2 and 3 until the cluster center no longer changes significantly or the preset maximum number of iterations is reached. 5) Output: Return K clusters and their corresponding cluster centers. Among them, the obtained K clusters are the classification categories.
[0085] S305, inputting the category values, distance measurement indicators and the field similarity corresponding to the classification categories to which the target student and other students belong into a preset reference indicator calculation formula to calculate the reference indicators corresponding to the target student and other students.
[0086] Among them, after obtaining the category values, distance measurement indicators and the field similarity corresponding to the classification categories to which the target student and other students belong, they are used as calculation parameters and input into the preset reference indicator calculation formula to calculate the reference indicators corresponding to the target student and other students.
[0087] Specifically, the distance measurement index corresponding to the target student and other students is calculated by the difference in the learning level index corresponding to the target student and other students, and the difference in the new field interest index corresponding to the target student and other students, specifically including:
[0088]
[0089] in, Target students and The distance metric corresponding to other students is New field interest indicators corresponding to target students, No. New field interest indicators corresponding to other students, The learning level indicators corresponding to the target students, For the New field interest indicators corresponding to other students, For An exponential function with base .
[0090] In one embodiment of the present application, the calculation of the recommendation rate corresponding to the target project corresponding to the target student by using the domain feature value corresponding to the target student and the reference index corresponding to the target student and other students specifically includes:
[0091]
[0092] in, The recommendation rate of the target project corresponding to the target students, is the domain feature value corresponding to the target student, is the number of other students, For target students and The reference indicators corresponding to other students, where when the field to which the target project belongs is the field that the target student has studied, the field characteristic value The value is 1. When the target project belongs to a field that the target student has not studied, the field feature value The value is the new field interest index corresponding to the target students .
[0093] It should be noted that when the recommendation rate corresponding to the target project corresponding to the target student is higher, the target project is more in line with the interest and ability of the target student, and the student learns more efficiently and effectively. When the recommendation rate corresponding to the target project corresponding to the target student is lower, the target project is not very in line with the interest and ability of the target student, and the student learns less efficiently.
[0094] The present application also provides an intelligent English teaching system, which is applied to the field of intelligent English teaching. Figure 5 , the system comprising:
[0095] A statistics module 1 is used to count the historical record data of the target student and other students, wherein the historical record data includes a number of fields, each field includes a number of projects, and the other students refer to other students who have studied the target project corresponding to the target student;
[0096] Calculation module 2, used for calculating the corresponding domain similarity between the target student and other students based on the quantitative differences of domains and items in the historical record data of the target student and other students;
[0097] Confirmation module 3, used for confirming reference indicators corresponding to the target student and other students according to the category values corresponding to the classification categories to which the target student and other students belong, the distance measurement indicators and the field similarity;
[0098] Analysis module 4, used to calculate the recommendation rate corresponding to the target project of the target student according to the domain characteristic value corresponding to the target student and the reference index corresponding to the target student and other students;
[0099] The recommendation module 5 is used to sort the recommendation rates corresponding to a number of items, and confirm that the items corresponding to the recommendation rates in the preset sorting order are the recommended items for the target students.
[0100] The implementation process of the intelligent English teaching system corresponds one-to-one to the intelligent English teaching method of the above embodiment, and will not be described in detail in this embodiment.
[0101] The embodiment of the present application first counts the historical record data of the target student and other students, wherein the historical record data includes a number of fields, each field includes a number of projects, and the other students refer to other students who have studied the target project corresponding to the target student, and then based on the number of differences in fields and projects in the historical record data of the target student and other students, calculate the field similarity corresponding to the target student and other students, and then confirm the reference index corresponding to the target student and other students according to the category value, distance measurement index and field similarity corresponding to the classification category to which the target student and other students belong, and calculate the recommendation rate corresponding to the target project corresponding to the target student through the field feature value corresponding to the target student and the reference index corresponding to the target student and other students, and finally sort the recommendation rates corresponding to the number of projects, and confirm that the recommendation rate corresponding to the project in the preset number sorting order is the recommended project for the target student. Through the historical record data of the target student and other students, calculate the recommendation rate corresponding to the target project corresponding to the target student, and finally confirm the preset number of projects with the highest recommendation rate as the recommended project for the target student to learn English, so as to improve the efficiency of students' English learning and further reduce the cost of English teaching compared with the traditional students' self-selection of projects for learning.
[0102] The flowchart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to the embodiment of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. In some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. In the description corresponding to the flowchart and the block diagram in the accompanying drawings, the operations or steps corresponding to different boxes can also occur in a different order from the order disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. Each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a dedicated hardware-based system that performs the specified functions or actions, or may be implemented by a combination of dedicated hardware and computer instructions.
[0103] It is obvious to those skilled in the art that the present application is not limited to the details of the above exemplary embodiments, and that the present application can be implemented in other specific forms without departing from the spirit or basic features of the present application. Therefore, no matter from which point of view, the above embodiments of the present application should be regarded as exemplary and non-restrictive, and the scope of the present application is defined by the attached claims rather than the above description, and therefore it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present application.
Claims
1. An intelligent English teaching method, applied in the field of intelligent English teaching, characterized in that: The method comprises: Collecting historical record data of the target student and other students, wherein the historical record data includes a number of fields, each field includes a number of projects, and the other students refer to other students who have studied the target project corresponding to the target student; Calculating the corresponding domain similarity between the target student and the other students based on the differences in the number of domains and items in the historical record data of the target student and the other students; According to the category values, distance measurement indicators and the field similarity corresponding to the classification categories to which the target student and other students belong, confirming the reference indicators corresponding to the target student and other students; Calculate the recommendation rate of the target project corresponding to the target student by using the domain feature value corresponding to the target student and the reference index of the target student and other students; Sorting the recommendation rates corresponding to a number of items, and confirming that the items corresponding to the recommendation rates in the preset number sorting order are the recommended items for the target students; The step of determining reference indicators corresponding to the target student and other students based on the category values, distance measurement indicators and field similarities corresponding to the classification categories to which the target student and other students belong specifically includes: Based on the number of valid items, the number of learning times and the corresponding learning time respectively confirmed by the historical record data of the target student and other students, the learning level indicators corresponding to the target student and other students are respectively constructed, wherein the valid items refer to items with a learning time greater than a preset threshold; Calculate the new field interest index corresponding to the target student and other students respectively according to the number of fields and projects studied confirmed by the historical record data of the target student and other students; Calculate the distance measurement index corresponding to the target student and other students by the difference between the learning level index corresponding to the target student and other students, and the difference between the new field interest index corresponding to the target student and other students; Based on a preset clustering algorithm and a distance measurement index corresponding to the target student and other students, the target student and other students are classified to define classification categories to confirm the category values corresponding to the classification categories to which the target student and other students belong; Inputting the category values, distance measurement indicators and field similarity corresponding to the classification categories to which the target student and other students belong into a preset reference indicator calculation formula to calculate the reference indicators corresponding to the target student and other students; The step of inputting the category values, distance measurement indicators and field similarity corresponding to the classification categories of the target student and other students into a preset reference indicator calculation formula to calculate the reference indicators corresponding to the target student and other students specifically includes: in, For target students and The reference indicators corresponding to other students, For target students and The distance metric corresponding to other students is For target students and The corresponding domain similarity between other students, is the category value corresponding to the classification category to which the target student belongs, For the The category values corresponding to the classification categories of other students, is a preset positive constant; The calculation of the recommendation rate corresponding to the target project corresponding to the target student by using the domain feature value corresponding to the target student and the reference index corresponding to the target student and other students specifically includes: in, The recommendation rate of the target project corresponding to the target students, is the domain feature value corresponding to the target student, is the number of other students, For target students and The reference indicators corresponding to other students, where when the field to which the target project belongs is the field that the target student has studied, the field characteristic value The value is 1. When the target project belongs to a field that the target student has not studied, the field feature value The value is the new field interest index corresponding to the target students .
2. The intelligent English teaching method according to claim 1, characterized in that: The calculating of the corresponding domain similarity between the target student and other students based on the difference in the number of domains and items in the historical record data of the target student and other students specifically includes: According to the historical record data of the target student and other students, respectively obtain the number of fields that the target student and other students have studied, and the number of projects that they have studied in each field; The number of fields studied by the target student and other students, as well as the number of projects studied in each field, are input into a preset field similarity calculation formula to calculate the corresponding field similarity between the target student and other students.
3. The intelligent English teaching method according to claim 2, characterized in that: The number of fields studied by the target student and other students, as well as the number of items studied in each field, are input into a preset field similarity calculation formula to calculate the corresponding field similarity between the target student and other students, specifically including: in, For target students and The corresponding domain similarity between other students, For the target students The number of projects studied in the field, The number of programs that the target students have studied in all fields, For the Other students in The number of projects studied in the field, For the The number of programs studied by other students in all fields, The number of areas that the target students have studied, A preset positive constant.
4. The intelligent English teaching method according to claim 1, characterized in that: The number of valid items, the number of learning times and the corresponding learning time respectively confirmed based on the historical record data of the target student and other students, respectively construct the learning level indicators corresponding to the target student and other students, wherein the valid items refer to items with a learning time greater than a preset threshold, specifically including: Based on the historical record data of the target student and other students, compare the study time of the projects studied by the target student and other students with a preset threshold, so as to confirm the projects with a study time longer than the preset threshold as valid projects; Counting the number of valid items corresponding to the target student and other students, the number of learning times and the corresponding learning time, and the correct rate of exercises corresponding to each learning; According to the number of valid items corresponding to the target student and other students, the number of learning times and the corresponding learning time, and the accuracy rate of exercises corresponding to each learning, the learning level indicators corresponding to the target student and other students are constructed.
5. The intelligent English teaching method according to claim 4, characterized in that: The constructing of the learning level indicator corresponding to the target student according to the number of valid items corresponding to the target student, the number of learning times and the corresponding learning time, and the correct rate of practice corresponding to each valid item each time of learning specifically includes: in, The learning level indicators corresponding to the target students, is the number of valid items, For the Number of effective items learned, For the target students Valid items The correct rate of practice corresponding to the learning time, For target students Valid items The corresponding learning time of each learning session; the corresponding: The step of calculating the target student's corresponding new field interest index based on the target student's history record data confirming the number of fields and projects studied includes: in, New field interest indicators corresponding to target students, The number of areas that the target students have studied, is the number of all domains in the system, is the variance corresponding to the items that the target students have learned in different fields, is the maximum number of projects in the field that the target student has studied. It is the minimum number of projects in the field studied by the target students.
6. The intelligent English teaching method according to claim 5, characterized in that: The distance measurement index corresponding to the target student and other students is calculated by using the difference in the learning level index corresponding to the target student and other students, and the difference in the new field interest index corresponding to the target student and other students, specifically including: in, For target students and The distance metric corresponding to other students is New field interest indicators corresponding to target students, For the New field interest indicators corresponding to other students, The learning level indicators corresponding to the target students, For the The corresponding learning level indicators of other students, For An exponential function with base .
7. An intelligent English teaching system, applied in the field of intelligent English teaching, characterized in that: The system is used to implement an intelligent English teaching method according to any one of claims 1 to 6, and the system comprises: A statistics module is used to count the historical record data of the target student and other students, wherein the historical record data includes a number of fields, each field includes a number of projects, and the other students refer to other students who have studied the target project corresponding to the target student; A calculation module, used for calculating the corresponding field similarity between the target student and other students based on the quantitative differences of fields and items in the historical record data of the target student and other students; A confirmation module, used to confirm reference indicators corresponding to the target student and other students according to the category values corresponding to the classification categories to which the target student and other students belong, the distance measurement indicators and the field similarity; An analysis module, used to calculate the recommendation rate corresponding to the target project of the target student according to the domain characteristic value corresponding to the target student and the reference index corresponding to the target student and other students; The recommendation module is used to sort the recommendation rates corresponding to a number of items, and confirm that the items corresponding to the recommendation rates in the preset sorting order are the recommended items for the target students.
