Interactive management method and system for english adaptive learning

Abstract

The application discloses an interactive management method and system for English adaptive learning, and is applied to the technical field of data processing.The method comprises the following steps: obtaining an interactive learning data set in a first learning state and an interactive learning data set in a second learning state by identifying the interactive learning data set; segmenting the interactive learning data set in the first learning state according to a preset learning duration; performing feedback learning on the interactive learning data set in the first learning state and the interactive learning data set in the second learning state by a first adaptive network layer, performing feedback learning on the interactive learning data set in the second learning state by a second adaptive network layer, and obtaining adaptive feedback data; and optimizing the learning data of a first user according to the adaptive feedback data.The technical problem that the result acquisition subjectivity is strong and the accuracy of the result acquisition is low in the process of acquiring the English learning data analysis method in the prior art is solved.

Description

Technical Field

[0001] This invention relates to the field of data processing, and more particularly to an interactive management method and system for adaptive English learning. Background Technology

[0002] Learning data analysis is commonly used in various learning software, such as English learning software and vocabulary memorization software, to help users improve their self-awareness in learning. However, current English learning data analysis methods mostly rely on questionnaires. Since questionnaires are largely completed subjectively by users, the results are highly subjective, affecting the accuracy of the final analysis.

[0003] Therefore, existing methods for obtaining English learning data suffer from the technical problems of high subjectivity and low accuracy in the acquisition of results. Summary of the Invention

[0004] This application provides an interactive management method and system for adaptive English learning, which solves the technical problems of high subjectivity and low accuracy in the acquisition of English learning data analysis methods in the prior art.

[0005] This application provides an interactive management method for adaptive English learning, the method comprising: collecting an interactive learning dataset of a first user; identifying the interactive learning dataset to obtain an interactive learning dataset in a first learning state and an interactive learning dataset in a second learning state, wherein the first learning state is a learning state with a learning duration longer than a preset learning duration, and the second learning state is a learning state with a learning duration shorter than a preset learning duration; segmenting the interactive learning dataset of the first learning state according to the preset learning duration to obtain a pre-interactive learning dataset and a post-interactive learning dataset of the first learning state; performing feedback learning by a first adaptive network layer based on the pre-interactive learning dataset of the first learning state and the interactive learning dataset of the second learning state, and performing feedback learning by a second adaptive network layer based on the post-interactive learning dataset of the second learning state to obtain adaptive feedback data, wherein the weight factor of the first adaptive network layer is greater than the weight factor of the second adaptive network layer; and optimizing the learning data of the first user based on the adaptive feedback data.

[0006] This application also provides an interactive management system for adaptive English learning, the system comprising: a data acquisition module for acquiring an interactive learning dataset of a first user; a data processing module for identifying the interactive learning dataset to obtain an interactive learning dataset in a first learning state and an interactive learning dataset in a second learning state, wherein the first learning state is a learning state with a learning duration longer than a preset learning duration, and the second learning state is a learning state with a learning duration shorter than a preset learning duration; a data segmentation module for segmenting the interactive learning dataset of the first learning state according to the preset learning duration to obtain a pre-interactive learning dataset and a post-interactive learning dataset of the first learning state; a feedback data acquisition module for performing feedback learning by a first adaptive network layer based on the pre-interactive learning dataset of the first learning state and the interactive learning dataset of the second learning state, and performing feedback learning by a second adaptive network layer based on the post-interactive learning dataset of the second learning state to obtain adaptive feedback data, wherein the weight factor of the first adaptive network layer is greater than the weight factor of the second adaptive network layer; and an optimization module for optimizing the learning data of the first user based on the adaptive feedback data.

[0007] This application also provides an electronic device, including:

[0008] Memory, used to store executable instructions;

[0009] The processor, when executing executable instructions stored in the memory, implements the interactive management method for adaptive English learning provided in this application.

[0010] This application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the interactive management method for adaptive English learning provided in this application.

[0011] This application proposes an interactive management method and system for adaptive English learning. By identifying the interactive learning dataset, two interactive learning datasets are obtained: one for a first learning state and another for a second learning state. The interactive learning dataset for the first learning state is segmented according to a preset learning duration. A first adaptive network layer performs feedback learning based on the pre-interactive learning dataset for the first learning state and the interactive learning dataset for the second learning state. A second adaptive network layer performs feedback learning based on the post-interactive learning dataset for the second learning state, obtaining adaptive feedback data. The learning data of the first user is optimized based on the adaptive feedback data. By processing and segmenting the user's interactive learning dataset, learning data at different stages is acquired, improving the accuracy of user learning data acquisition. This enables objective and accurate matching analysis of the user's English learning process, allowing for adaptive feedback adjustments to address user English learning deficiencies, thereby improving the accuracy of user learning data analysis. This solves the technical problems of existing English learning data analysis methods, such as strong subjectivity and low accuracy in obtaining results.

[0012] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description

[0013] To more clearly illustrate the technical solutions of the embodiments of this disclosure, the accompanying drawings of the embodiments of this disclosure will be briefly described below. Obviously, the drawings described below only relate to some embodiments of this disclosure and are not intended to limit this disclosure.

[0014] Figure 1 A flowchart illustrating the interactive management method for adaptive English learning provided in an embodiment of this application;

[0015] Figure 2 A flowchart illustrating the process of obtaining a penalty factor in an interactive management method for adaptive English learning provided in an embodiment of this application;

[0016] Figure 3 A flowchart illustrating the process of optimizing and adjusting weight factors in the interactive management method for adaptive English learning provided in this application embodiment;

[0017] Figure 4 A schematic diagram of the structure of an interactive management system for adaptive English learning provided in an embodiment of this application;

[0018] Figure 5This is a schematic diagram of the structure of an electronic device for an interactive management system for adaptive English learning, provided in an embodiment of the present invention.

[0019] Explanation of reference numerals in the attached drawings: data acquisition module 11, data processing module 12, data segmentation module 13, feedback data acquisition module 14, optimization module 15, processor 31, memory 32, input device 33, output device 34. Detailed Implementation

[0020] Example 1

[0021] To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as limitations on this application. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0022] In the following description, references are made to “some embodiments,” which describe a subset of all possible embodiments. However, it is understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0023] In the following description, the terms "first, second, third" are used merely to distinguish similar objects and do not represent a specific ordering of objects. It is understood that "first, second, third" may be interchanged in a specific order or sequence where permitted, so that the embodiments of this application described herein can be implemented in an order other than that illustrated or described herein.

[0024] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only.

[0025] While this application makes various references to certain modules of the system according to embodiments of this application, any number of different modules may be used and run on user terminals and / or servers. These modules are merely illustrative, and different aspects of the system and method may use different modules.

[0026] This application uses flowcharts to illustrate the operations performed by the system according to embodiments of this application. It should be understood that the preceding or following operations are not necessarily performed in exact order. Instead, various steps can be processed in reverse order or simultaneously as needed. Furthermore, other operations can be added to these processes, or one or more steps can be removed from them.

[0027] like Figure 1As shown in the embodiments of this application, an interactive management method for adaptive English learning is provided, the method comprising:

[0028] Collect the first user's interactive learning dataset;

[0029] By identifying the interactive learning dataset, an interactive learning dataset in a first learning state and an interactive learning dataset in a second learning state are obtained, wherein the first learning state is a learning state with a preset learning time, and the second learning state is a learning state with a preset learning time.

[0030] According to the preset learning duration, the interactive learning dataset of the first learning state is divided into a pre-interactive learning dataset of the first learning state and a post-interactive learning dataset of the first learning state.

[0031] An interactive learning dataset is collected from the first user, containing various English dialogues, English repetitions, and English learning content. By identifying this dataset, interactive learning datasets under a first learning state and a second learning state are obtained. The first learning state is a learning state with a preset learning duration, and the second learning state is a learning state with a preset learning duration. The preset learning duration is a pre-set learning time limit. When the user's current learning time exceeds the preset duration, learning attention decreases, and the effectiveness of the learning data is poor, which will affect the analysis results. Therefore, the learning data is differentiated based on the preset learning duration. The interactive learning dataset under the first learning state is then segmented according to the preset learning duration to obtain a pre-interactive learning dataset and a post-interactive learning dataset for the first learning state. In other words, the interactive learning dataset under the first learning state is further divided into a pre-interactive learning dataset and a post-interactive learning dataset for the first learning state.

[0032] The first adaptive network layer performs feedback learning based on the pre-interactive learning dataset of the first learning state and the interactive learning dataset of the second learning state, and the second adaptive network layer performs feedback learning based on the post-interactive learning dataset of the second learning state to obtain adaptive feedback data. The weight factor of the first adaptive network layer is greater than the weight factor of the second adaptive network layer.

[0033] The learning data of the first user is optimized based on the adaptive feedback data.

[0034] Based on the pre-interactive learning dataset of the first learning state and the interactive learning dataset of the second learning state, a first adaptive network layer performs feedback learning; based on the post-interactive learning dataset of the second learning state, a second adaptive network layer performs feedback learning, obtaining adaptive feedback data. The weight factor of the first adaptive network layer is greater than that of the second adaptive network layer. The first adaptive network layer processes the interactive learning dataset of the first learning state, and the second adaptive network layer processes the interactive learning dataset of the second learning state. Finally, the learning data of the first user is optimized based on the adaptive feedback data. By processing and segmenting the user's interactive learning dataset, learning data at different stages is acquired, improving the accuracy of user learning data acquisition. This enables objective and accurate matching analysis of the user's English learning process, allowing for adaptive feedback adjustments to address user English learning deficiencies, thereby improving the accuracy of user learning data analysis.

[0035] like Figure 2 As shown, the method provided in this application embodiment further includes:

[0036] Record the learning duration of the first user in the first learning state;

[0037] Determine whether the learning duration of the first user in the first learning state is a continuous learning duration. If the learning duration of the first user in the first learning state is a continuous learning duration, set a penalty factor.

[0038] The weight factors of the second adaptive network layer are penalized using the penalty factor to obtain the penalized weight factors of the second adaptive network layer, and then feedback learning is performed on the post-interaction learning dataset of the first learning state.

[0039] The learning duration of the first user in the first learning state is recorded, i.e., the actual learning time of the first user in the first learning state is recorded. This data is recorded by the tutor or teacher. Then, it is determined whether the learning duration of the first user in the first learning state is a continuous learning duration, i.e., whether the learning duration meets a preset learning duration. If it is less than the preset learning duration, it is a non-continuous learning duration; if it is equal to the preset learning duration, it is a continuous learning duration. When the learning duration of the first user in the first learning state is a continuous learning duration, if there is a continuous learning duration greater than the preset learning duration, the learning efficiency may decrease. Therefore, a penalty factor is set. The penalty factor is a preset fixed percentage parameter, and the penalty factor is less than 1. The penalty factor is used to penalize the weight factor of the second adaptive network layer. The initial weight factor values ​​of the first and second adaptive network layers are 1. When penalizing, the penalty factor is multiplied by the initial weight factor to obtain the penalized weight factor of the second adaptive network layer. Then, feedback learning is performed on the post-interaction learning dataset of the first learning state.

[0040] like Figure 3 As shown, the method provided in this application embodiment further includes:

[0041] Obtain the learning environment information of the first user;

[0042] Based on the learning environment information, multiple interference factors are obtained, including an ambient sound signal interference index, an ambient temperature interference index, and an ambient light interference index.

[0043] An environmental impact assessment was conducted using the aforementioned multiple interference factors to obtain the first impact coefficient.

[0044] The weight factors of the first adaptive network layer and the weight factors of the second adaptive network layer are optimized and adjusted according to the first influence coefficient.

[0045] The learning environment information of the first user is obtained. Based on this information, multiple interference factors are acquired, including environmental sound signal interference indicators, environmental temperature interference indicators, and environmental light interference indicators. The environmental sound signal interference indicator is the ambient volume in decibels, the environmental temperature interference indicator is the ambient temperature, and the environmental light interference indicator is the ambient light intensity. Before conducting an environmental impact assessment, optimal interference factor parameters are obtained based on big data. These optimal interference factor parameters represent the index data of the optimal learning environment interference factors. The environmental impact assessment is completed based on the deviation ratio between each interference factor and the optimal interference factor parameter. The deviation ratios of each interference factor are obtained and summed to obtain a first influence coefficient. The first influence coefficient is then subtracted from the weight factors of the first adaptive network layer and the second adaptive network layer to optimize the weight factors. Finally, the obtained results are multiplied to obtain accurate feedback data.

[0046] The method provided in this application embodiment also includes:

[0047] The first adaptive network layer and the second adaptive network layer are a Siamese network model. The first adaptive network layer and the second adaptive network layer calculate the fitness by calling the fitness function, and the weights of the first adaptive network layer and the second adaptive network layer are not shared.

[0048] After obtaining the first adaptive feedback data corresponding to the first adaptive network layer and the second adaptive feedback data corresponding to the second adaptive network layer, the first adaptive feedback data and the second adaptive feedback data are regularized to obtain the adaptive feedback data.

[0049] The first and second adaptive network layers form a Siamese network model. They calculate fitness by calling a fitness function, and their weights are not shared. The fitness function is used to calculate user learning features, obtaining preference feature fitness, content completion fitness, and plan achievement fitness data. After obtaining the first adaptive feedback data corresponding to the first adaptive network layer and the second adaptive feedback data corresponding to the second adaptive network layer, regularization is applied to the first and second adaptive feedback data to obtain the adaptive feedback data.

[0050] The method provided in this application also includes:

[0051] The fitness function is connected to a preset fitness index, wherein the fitness function includes multiple fitness indices, and the multiple fitness indices include at least preference feature fitness, content completion fitness, and plan achievement fitness.

[0052] Based on the preset fitness index, the first user's multiple fitness indices are compared and evaluated to obtain a defect dataset.

[0053] Based on the defect dataset, the learning data of the first user is adjusted to compensate for defects, thereby obtaining adaptive feedback data.

[0054] The fitness function is connected to a preset fitness index. The fitness function includes multiple fitness indices, at least including preference feature fitness, content completion fitness, and plan achievement fitness. Preference feature fitness is obtained by calculating the feature evaluation data of each learning content in the learning dataset, and selecting the preference feature data with higher evaluation data as the preference feature fitness. Content completion fitness and plan achievement fitness are both obtained from the feature evaluation data of the learning content. The multiple fitness indices of the first user are compared and evaluated according to the preset fitness index, and data that does not meet the preset fitness index are obtained, resulting in a defect dataset. Based on the defect dataset, defect compensation adjustment is performed on the first user's learning data, that is, a corresponding learning plan is formulated for the defects existing in the defect dataset. The specific plan can be obtained using big data or by matching the learning plan corresponding to the preset defect data, thereby obtaining adaptive feedback data.

[0055] The method provided in this application also includes:

[0056] By extracting learning features from the interactive learning dataset of the first user in the first learning state and the interactive learning dataset in the second learning state, user learning features are obtained.

[0057] Based on the user learning characteristics, an analogous user group for the first user is obtained. The analogous user group is a set of users whose learning characteristics in the first learning state and their learning characteristics in the second learning state both reach a preset similarity.

[0058] The authorization request calls upon the learning data of the analog user group to set the preset fitness index.

[0059] Before connecting the fitness function with the preset fitness index, the method further includes: extracting learning features from the interactive learning dataset of the first user in the first learning state and the interactive learning dataset in the second learning state to obtain user learning features. These user learning features reflect the quality of the user's learning data. For example, in English dialogues, data reflecting the quality of the dialogue, such as the duration of pauses and the number of corrections, are obtained, and corresponding scoring results are acquired to obtain feature data. Specific learning data feature extraction objects can be obtained based on evaluation criteria, such as English learning test scores or the accuracy of English repetition. Based on the user learning features, a search is performed in a historical user learning feature database, which records the corresponding learning features of each user's learning dataset. This results in an analogous user group for the first user. The analogous user group is a set of users whose learning features in both the first and second learning states reach a preset similarity. The preset similarity is a pre-set similarity threshold between the user's learning features and the corresponding learning features in the retrieved data of the historical user learning feature database. When the similarity is greater than or equal to this preset similarity, the corresponding user has a high similarity to the first user's learning features, and the corresponding user is added to the user group. Finally, the authorization request calls the learning data of the analog user group to set the preset fitness index. The preset fitness index includes at least preference feature fitness, content completion fitness, and plan achievement fitness. The above fitness is calculated based on the corresponding user learning features through a fitness function, and the average calculation result or mode calculation result of the analog user group is obtained to obtain the preset fitness index.

[0060] The method provided in this application also includes:

[0061] By identifying the data source of the interactive learning dataset, multiple data storage blocks are obtained, and each data storage block is used to record interactive learning data from one data source.

[0062] Based on the twin network model, adaptive learning is performed on the multiple data storage blocks to obtain adaptive feedback data corresponding to each of the multiple data storage blocks.

[0063] By identifying the data source of the interactive learning dataset (the specific origin of the data), multiple data storage blocks are obtained. Each data storage block records interactive learning data from one data source. Adaptive learning is then performed on each of these multiple data storage blocks according to the Siamese network model to obtain adaptive feedback data corresponding to each data storage block, thereby improving the efficiency of adaptive feedback data acquisition.

[0064] The technical solution provided in this invention involves collecting an interactive learning dataset from a first user. By identifying the interactive learning dataset, interactive learning datasets in a first learning state and a second learning state are obtained. The first learning state is a learning state with a duration longer than a preset learning time, and the second learning state is a learning state with a duration shorter than the preset learning time. Based on the preset learning time, the interactive learning dataset in the first learning state is segmented to obtain a pre-interactive learning dataset and a post-interactive learning dataset for the first learning state. A first adaptive network layer performs feedback learning based on the pre-interactive learning dataset of the first learning state and the interactive learning dataset in the second learning state, and a second adaptive network layer performs feedback learning based on the post-interactive learning dataset of the second learning state to obtain adaptive feedback data. The weight factor of the first adaptive network layer is greater than the weight factor of the second adaptive network layer. The learning data of the first user is optimized based on the adaptive feedback data. By processing and segmenting the user's interactive learning dataset, learning data at different stages is acquired, improving the accuracy of user learning data acquisition. This enables objective and accurate matching analysis of the user's English learning process, adaptive feedback adjustment of user English learning deficiencies, and ultimately improves the accuracy of user learning data analysis. This invention addresses the technical problems of high subjectivity and low accuracy in the acquisition of results in existing English learning data analysis methods.

[0065] Example 2

[0066] Based on the same inventive concept as the interactive management method for English adaptive learning in the foregoing embodiments, this invention also provides an interactive management system for English adaptive learning. The system can be implemented in hardware and / or software, and is generally integrated into an electronic device to execute the methods provided in any embodiment of this invention. Figure 4 As shown, the system includes:

[0067] Data acquisition module 11 is used to collect the interactive learning dataset of the first user;

[0068] Data processing module 12 is used to identify the interactive learning dataset to obtain an interactive learning dataset in a first learning state and an interactive learning dataset in a second learning state, wherein the first learning state is a learning state with a learning duration greater than a preset learning duration, and the second learning state is a learning state with a learning duration less than a preset learning duration.

[0069] The data segmentation module 13 is used to segment the interactive learning dataset of the first learning state according to the preset learning time to obtain the pre-interactive learning dataset of the first learning state and the post-interactive learning dataset of the first learning state.

[0070] The feedback data acquisition module 14 is used to perform feedback learning by the first adaptive network layer based on the pre-interactive learning dataset of the first learning state and the interactive learning dataset of the second learning state, and to perform feedback learning by the second adaptive network layer based on the post-interactive learning dataset of the second learning state, to acquire adaptive feedback data, wherein the weight factor of the first adaptive network layer is greater than the weight factor of the second adaptive network layer.

[0071] The optimization module 15 is used to optimize the learning data of the first user based on the adaptive feedback data.

[0072] Furthermore, the feedback data acquisition module 14 is also used for:

[0073] Record the learning duration of the first user in the first learning state;

[0074] Determine whether the learning duration of the first user in the first learning state is a continuous learning duration. If the learning duration of the first user in the first learning state is a continuous learning duration, set a penalty factor.

[0075] The weight factors of the second adaptive network layer are penalized using the penalty factor to obtain the penalized weight factors of the second adaptive network layer, and then feedback learning is performed on the post-interaction learning dataset of the first learning state.

[0076] Furthermore, the feedback data acquisition module 14 is also used for:

[0077] Obtain the learning environment information of the first user;

[0078] Based on the learning environment information, multiple interference factors are obtained, including an ambient sound signal interference index, an ambient temperature interference index, and an ambient light interference index.

[0079] An environmental impact assessment was conducted using the aforementioned multiple interference factors to obtain the first impact coefficient.

[0080] The weight factors of the first adaptive network layer and the weight factors of the second adaptive network layer are optimized and adjusted according to the first influence coefficient.

[0081] Furthermore, the feedback data acquisition module 14 is also used for:

[0082] The first adaptive network layer and the second adaptive network layer are a Siamese network model. The first adaptive network layer and the second adaptive network layer calculate the fitness by calling the fitness function, and the weights of the first adaptive network layer and the second adaptive network layer are not shared.

[0083] After obtaining the first adaptive feedback data corresponding to the first adaptive network layer and the second adaptive feedback data corresponding to the second adaptive network layer, the first adaptive feedback data and the second adaptive feedback data are regularized to obtain the adaptive feedback data.

[0084] The second search result is obtained using the aforementioned secondary search instruction.

[0085] Furthermore, the feedback data acquisition module 14 is also used for:

[0086] The fitness function is connected to a preset fitness index, wherein the fitness function includes multiple fitness indices, and the multiple fitness indices include at least preference feature fitness, content completion fitness, and plan achievement fitness.

[0087] Based on the preset fitness index, the first user's multiple fitness indices are compared and evaluated to obtain a defect dataset.

[0088] Based on the defect dataset, the learning data of the first user is adjusted to compensate for defects, thereby obtaining adaptive feedback data.

[0089] Furthermore, the feedback data acquisition module 14 is also used for:

[0090] By extracting learning features from the interactive learning dataset of the first user in the first learning state and the interactive learning dataset in the second learning state, user learning features are obtained.

[0091] Based on the user learning characteristics, an analogous user group for the first user is obtained. The analogous user group is a set of users whose learning characteristics in the first learning state and their learning characteristics in the second learning state both reach a preset similarity.

[0092] The authorization request calls upon the learning data of the analog user group to set the preset fitness index.

[0093] Furthermore, the feedback data acquisition module 14 is also used for:

[0094] By identifying the data source of the interactive learning dataset, multiple data storage blocks are obtained, and each data storage block is used to record interactive learning data from one data source.

[0095] Based on the twin network model, adaptive learning is performed on the multiple data storage blocks to obtain adaptive feedback data corresponding to each of the multiple data storage blocks.

[0096] The various units and modules included are divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of each functional unit are only for easy distinction between each other and are not used to limit the scope of protection of this invention.

[0097] Example 3

[0098] Figure 5 This is a schematic diagram of the structure of an electronic device provided in Embodiment 3 of the present invention, showing a block diagram of an exemplary electronic device suitable for implementing the embodiments of the present invention. Figure 5 The electronic device shown is merely an example and should not be construed as limiting the functionality or scope of the embodiments of the present invention. Figure 5 As shown, the electronic device includes a processor 31, a memory 32, an input device 33, and an output device 34; the number of processors 31 in the electronic device can be one or more. Figure 5 Taking a processor 31 as an example, the processor 31, memory 32, input device 33, and output device 34 in an electronic device can be connected via a bus or other means. Figure 5 Taking the example of a connection between China and Israel via a bus.

[0099] The memory 32, as a computer-readable storage medium, can be used to store software programs, computer-executable programs, and modules, such as the program instructions / modules corresponding to the interactive management method for adaptive English learning in this embodiment of the invention. The processor 31 executes various functional applications and data processing of the computer device by running the software programs, instructions, and modules stored in the memory 32, thereby realizing the aforementioned interactive management method for adaptive English learning.

[0100] Note that the above description is merely a preferred embodiment of the present invention and the technical principles employed. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments, and may include many other equivalent embodiments without departing from the concept of the present invention, the scope of which is determined by the scope of the appended claims.

Claims

1. An interactive management method for adaptive English learning, characterized in that, The method includes: Collect the first user's interactive learning dataset; By identifying the interactive learning dataset, an interactive learning dataset in a first learning state and an interactive learning dataset in a second learning state are obtained, wherein the first learning state is a learning state with a learning duration longer than a preset learning duration, and the second learning state is a learning state with a learning duration shorter than a preset learning duration. According to the preset learning duration, the interactive learning dataset of the first learning state is divided into a pre-interactive learning dataset of the first learning state and a post-interactive learning dataset of the first learning state. The first adaptive network layer performs feedback learning based on the pre-interactive learning dataset of the first learning state and the interactive learning dataset of the second learning state, and the second adaptive network layer performs feedback learning based on the post-interactive learning dataset of the first learning state to obtain adaptive feedback data. The weight factor of the first adaptive network layer is greater than the weight factor of the second adaptive network layer. The learning data of the first user is optimized based on the adaptive feedback data; The first adaptive network layer and the second adaptive network layer are a Siamese network model. The first adaptive network layer and the second adaptive network layer calculate the fitness by calling the fitness function, and the weights of the first adaptive network layer and the second adaptive network layer are not shared. After obtaining the first adaptive feedback data corresponding to the first adaptive network layer and the second adaptive feedback data corresponding to the second adaptive network layer, the first adaptive feedback data and the second adaptive feedback data are regularized to obtain the adaptive feedback data. The fitness function includes: The fitness function is connected to a preset fitness index, wherein the fitness function includes multiple fitness indices, and the multiple fitness indices include at least preference feature fitness, content completion fitness, and plan achievement fitness. Based on the preset fitness index, the first user's multiple fitness indices are compared and evaluated to obtain a defect dataset. Based on the defect dataset, the learning data of the first user is adjusted to compensate for defects, thereby obtaining adaptive feedback data.

2. The method as described in claim 1, characterized in that, The method further includes: Record the learning duration of the first user in the first learning state; Determine whether the learning duration of the first user in the first learning state is a continuous learning duration. If the learning duration of the first user in the first learning state is a continuous learning duration, set a penalty factor. The weight factors of the second adaptive network layer are penalized using the penalty factor to obtain the penalized weight factors of the second adaptive network layer, and then feedback learning is performed on the post-interaction learning dataset of the first learning state.

3. The method as described in claim 1, characterized in that, The method further includes: Obtain the learning environment information of the first user; Based on the learning environment information, multiple interference factors are obtained, including an ambient sound signal interference index, an ambient temperature interference index, and an ambient light interference index. An environmental impact assessment was conducted using the aforementioned multiple interference factors to obtain the first impact coefficient. The weight factors of the first adaptive network layer and the weight factors of the second adaptive network layer are optimized and adjusted according to the first influence coefficient.

4. The method as described in claim 1, characterized in that, Before concatenating the fitness function with the preset fitness index, the method further includes: By extracting learning features from the interactive learning dataset of the first user in the first learning state and the interactive learning dataset in the second learning state, user learning features are obtained. Based on the user learning characteristics, an analogous user group for the first user is obtained. The analogous user group is a set of users whose learning characteristics in the first learning state and their learning characteristics in the second learning state both reach a preset similarity. The authorization request calls upon the learning data of the analog user group to set the preset fitness index.

5. The method as described in claim 1, characterized in that, The method further includes: By identifying the data source of the interactive learning dataset, multiple data storage blocks are obtained, and each data storage block is used to record interactive learning data from one data source. Based on the twin network model, adaptive learning is performed on the multiple data storage blocks to obtain adaptive feedback data corresponding to each of the multiple data storage blocks.

6. An interactive management system for adaptive English learning, characterized in that, The system is used to perform the method according to any one of claims 1-5, the system comprising: The data acquisition module is used to collect the interactive learning dataset of the first user; The data processing module is used to identify the interactive learning dataset to obtain the interactive learning dataset in a first learning state and the interactive learning dataset in a second learning state, wherein the first learning state is a learning state with a preset learning time, and the second learning state is a learning state with a preset learning time. The data segmentation module is used to segment the interactive learning dataset of the first learning state according to the preset learning time to obtain the pre-interactive learning dataset of the first learning state and the post-interactive learning dataset of the first learning state. The feedback data acquisition module is used to perform feedback learning by the first adaptive network layer based on the pre-interactive learning dataset of the first learning state and the interactive learning dataset of the second learning state, and to perform feedback learning by the second adaptive network layer based on the post-interactive learning dataset of the first learning state, to acquire adaptive feedback data, wherein the weight factor of the first adaptive network layer is greater than the weight factor of the second adaptive network layer. An optimization module is used to optimize the learning data of the first user based on the adaptive feedback data.

7. An electronic device, characterized in that, The electronic device includes: Memory, used to store executable instructions; The processor, when executing executable instructions stored in the memory, implements the interactive management method for adaptive English learning as described in any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by the processor, the program implements the interactive management method for adaptive English learning as described in any one of claims 1-5.

Images