Personalized English teaching intelligent software system, electronic equipment and medium

Abstract

The invention discloses a personalized English teaching intelligent software system, an electronic device and a medium, and relates to the technical field of data analysis, the personalized English teaching intelligent software system comprises an acquisition module, an analysis module, an evaluation module and a construction module, and is used for calculating concentration validity, mood pleasure and result validity, setting screening conditions, performing hierarchical screening on variable groups, calculating and recording as a first sum value, and establishing a second sum value; setting an ideal variable group, and establishing a first mapping relation between the user information and the ideal variable group; by providing personalized learning feedback, the user can master English knowledge points more quickly, learning efficiency is improved by analyzing the attention state of the user, learning interest and enthusiasm of the user are improved by recognizing the emotional state of the user and adjusting a teaching strategy, the learning effect of the user is accurately evaluated, and the learning efficiency of the user is improved. The teaching method and content are optimized, and the learning path is dynamically adjusted according to the real-time feedback of the user to adapt to the learning requirements and emotion changes of different users.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis, and in particular to a personalized English teaching intelligent software system, electronic equipment and medium. Background Art

[0002] In recent years, the development of personalized English teaching intelligent software technology has made learning more flexible, efficient and interactive. Using artificial intelligence algorithms, personalized English learning software can analyze students' learning habits, ability levels and interests, dynamically adjust learning content and rhythm, and design personalized courses according to students' personal needs and learning goals to ensure the relevance and effectiveness of learning content. It has introduced virtual teachers or chatbots to provide learning support and enhance students' interactive experience.

[0003] At present, in the Chinese invention patent with publication number CN 107085618 A, a target-driven recommendation of learning points and learning paths based on data graphs, information graphs and knowledge graphs for 5W is disclosed. This method further refines the learning points from three progressive levels of data, information and knowledge, maps the learners' learning goals into questions guided by Who), When, Where, What and How, and recommends reasonable learning point content and learning strategies to learners in a layered manner, guides learners to achieve their learning goals, helps learners improve their learning efficiency and optimizes learning effects. However, the relevant technology does not screen courses in many aspects according to the user's own mood, prior knowledge reserves and listening status, lacks the thoughtfulness, comprehensiveness and serviceability of educational services, does not evaluate the teaching quality based on subjective mood and objective results, and easily causes one-sided judgment. Summary of the invention

[0004] The technical problem solved by the present invention is that the related technology does not conduct multi-faceted screening of courses based on the user's own mood, prior knowledge reserves and listening status, lacks the thoughtfulness, comprehensiveness and serviceability of educational services, and does not evaluate the teaching quality based on subjective mood and objective results, which easily leads to one-sided judgment.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: In the first aspect, a personalized English teaching intelligent software system includes a collection module, an analysis module, an evaluation module and a construction module; The collection module sets a control group, takes digital human information and teaching information as variable groups, takes user information as a constant, starts the teaching mode, and collects the user information within the class duration; The analysis module pre-processes the user information, extracts frequency domain features of the pre-processed user information, obtains the attention state through the frequency domain features, counts the concentration state duration within the class time, calculates the concentration effectiveness according to the concentration state duration, sets key time points within the class time, obtains the user's facial image at the key time point, matches the corresponding user mood according to the user's facial image at the key time point, and calculates the user's mood pleasure according to the user's mood; The evaluation module matches the corresponding evaluation questions according to the teaching information, evaluates the user according to the evaluation questions, calculates the result validity according to the evaluation score, sets the result validity threshold, the concentration validity threshold and the mood pleasure threshold, and sets the screening conditions, hierarchically screens the variable group, sets the effective variable group according to the screening results, obtains the result validity, mood pleasure and concentration validity corresponding to the effective variable group, calculates the sum of the result validity, mood pleasure and concentration validity corresponding to the effective variable group, records it as the first sum, and sets it as the ideal variable group according to the first sum; The construction module establishes a first mapping relationship between user information and an ideal variable group.

[0006] As a preferred solution of the personalized English teaching intelligent software system of the present invention, wherein: the acquisition module sets a control group, takes digital human information and teaching information as variable groups, takes user information as invariant, starts the teaching mode, and collects the user information within the class duration; The digital human information includes appearance, speaking speed, timbre, volume, number of expression changes and number of gesture changes; the teaching information includes the difficulty of the lesson, the duration of the lesson and the chapter to which the lesson belongs; the user information includes EEG waveform, gender, age, prior knowledge level, preference for English courses and personality; The number of gesture changes is represented by the number of changes in the relative positions of the fingers, that is, the changes in the opening or closing of the fingers or the pointing of the fingers. The number of expression changes is represented by the number of changes in the relative positions of the face, that is, the changes in the relative positions of the eyes, nose, mouth and eyebrows. The relative positions of the fingers are represented by the changes in the positions between the fingers, which are irrelevant to the changes in the overall position of the hand. The changes in the relative positions of the face are represented by the changes in the positions between the eyes, nose, mouth and eyebrows, which are irrelevant to the changes in the overall position of the head. The appearance, speaking speed, timbre and volume are obtained from the virtual digital teacher database, the teaching information is obtained from the online English teaching database, the class difficulty is evaluated by English education experts, and the class difficulty includes the first level difficulty, the second level difficulty, the third level difficulty and the fourth level difficulty; The EEG waveform is monitored by an EGG device. The prior knowledge level is evaluated by obtaining the average value of the user's history English score. When the average value of the history English score is distributed between 0 and 60 points, the prior knowledge level is set to weak. When the average value of the history English score is distributed between 60 and 80 points, the prior knowledge level is set to good. When the average value of the history English score is distributed between 80 and 100 points, the prior knowledge level is set to excellent. The degree of preference for the English course is obtained by user input, and the degree of preference for the English course is distributed between 0 and 10.

[0007] As a preferred solution of the personalized English teaching intelligent software system of the present invention, the logic for obtaining the number of gesture changes includes: Obtain a digital human appearance picture, automatically extract the hand parts in the digital human appearance picture through machine vision, track the hand parts, call a hand acupoint distribution database, input a hand part image into the hand acupoint distribution database, match the hand acupoints corresponding to the hand part image, set hand monitoring points for the hand acupoints corresponding to the hand part image, the monitoring points are respectively distributed at Hegu point, Neiguan point, Waiguan point, Shaoshang point, Zhongchong point, Yangchi point, Daling point and Taibai point, calculate the three-dimensional distances between the hand monitoring points respectively, and when the three-dimensional distances between the hand monitoring points change, count the change in the number of gesture changes; The logic for obtaining the number of expression changes includes: Get the appearance picture of the digital human, automatically extract the face in the appearance picture of the digital human through machine vision, track the face, set the eye head point, eye tail point, eye highest point, eye lowest point, nose root midpoint, nose tip lowest point, mouth corner point, upper lip highest point, lower lip lowest point, eyebrow tail point, eyebrow head point and eyebrow peak highest point as facial monitoring points, calculate the three-dimensional distance between facial monitoring points, and when the three-dimensional distance between facial monitoring points changes, count the change in the number of expression changes.

[0008] As a preferred solution of the personalized English teaching intelligent software system of the present invention, the analysis module preprocesses the EEG waveform, the preprocessing includes filtering and segmentation, extracts the frequency domain features of the preprocessed EEG waveform, the frequency domain features are represented by the distribution interval features of the waveform frequency, and the attention state is obtained through the frequency domain features. The attention state includes a relaxed state, a concentrated state and a regulating state. The regulating state is represented by intermittent switching between the concentrated state and the relaxed state. The acquisition logic of the attention state includes: Performing filtering and segmentation processing on the EEG waveform to obtain a brain electronic waveform, obtaining the amplitude of the brain electronic waveform, comparing the amplitude of the brain electronic waveform with a waveform standard distribution interval, obtaining a waveform name of the brain electronic waveform, retrieving a waveform database, inputting the waveform name into the waveform database, and matching the corresponding attention state according to the waveform name; When the amplitude of the brain electronic waveform is distributed between 8 and 12 Hz, the waveform name of the brain electronic waveform is set to α waveform, and the matching attention state is the relaxation state; When the amplitude of the brain electronic waveform is distributed between 12 and 30 Hz, the waveform name of the brain electronic waveform is set to be a β waveform, and the matching attention state is a concentration state; When the amplitude of the brain electronic waveform is distributed between 30 and 100 Hz, the waveform name of the brain electronic waveform is set to γ ​​waveform, and the matching attention state is the adjustment state.

[0009] As a preferred solution of the personalized English teaching intelligent software system of the present invention, the analysis module counts the concentration state duration within the class time, and calculates the concentration effectiveness according to the concentration state duration. The calculation logic of the concentration effectiveness includes: Acquire the duration of the concentrated state and the duration of the class, calculate the ratio of the duration of the concentrated state to the duration of the class, record it as a first ratio, and set the first ratio as the concentration effectiveness; Set key time points within the duration of the class, obtain the user's facial image at the key time points, filter and grayscale the user's facial image, extract the feature value of the upward angle of the corner of the mouth of the user's facial image after filtering and grayscale processing, call the mood database, input the upward angle of the corner of the mouth into the mood database, match the mood corresponding to the upward angle of the corner of the mouth, set the mood as the user's mood, the mood includes happy, calm and unhappy, assign values ​​to the mood, set happy to the second value, set calm to the third value, set unhappy to the fourth value, obtain the assigned value of the user's mood at the key time points, calculate the average value of the amplitude of the user's mood, and set the average value of the amplitude of the user's mood as the mood pleasure.

[0010] As a preferred solution of the personalized English teaching intelligent software system of the present invention, wherein: the evaluation module calls the English teaching database, inputs the difficulty of the lesson and the chapter to which the lesson belongs into the English teaching database, and matches the corresponding evaluation questions; The user is assessed according to the assessment questions, and the validity of the result is calculated according to the assessment score. The calculation logic of the validity of the result includes: The total score and the assessment score of the assessment test questions are obtained, the ratio of the assessment score to the total score is calculated, recorded as the second ratio, and the second ratio is set as the result validity threshold.

[0011] As a preferred solution of the personalized English teaching intelligent software system of the present invention, wherein: the evaluation module sets the fourth value as the result validity threshold, the fifth value as the concentration validity threshold, and the sixth value as the mood pleasure threshold; The variable group is hierarchically screened using the result validity threshold as the first screening condition, the mood pleasure as the second screening condition, and the concentration validity as the third screening condition. The first screening condition is greater than or equal to the fourth value, the second screening condition is greater than or equal to the fifth value, and the third screening condition is greater than or equal to the sixth value. The variable group that meets the first screening condition, the second screening condition and the third screening condition is set as a valid variable group, the result validity, mood pleasure and concentration validity corresponding to the valid variable group are obtained, and the sum of the result validity, mood pleasure and concentration validity corresponding to the valid variable group is calculated and recorded as the first sum; Traverse the first sum value, select the valid variable group corresponding to the first sum value with the largest value, and set the valid variable group corresponding to the first sum value with the largest value as the ideal variable group.

[0012] As a preferred solution of the personalized English teaching intelligent software system described in the present invention, wherein: the construction module stores user information and corresponding ideal variable groups, establishes a first mapping relationship between user information and corresponding ideal variable groups, obtains current user information, and obtains digital human information and teaching information corresponding to the current user information according to the first mapping relationship.

[0013] In a second aspect, the present invention provides an electronic device comprising a memory, a processor and storage in the memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the steps in the personalized English teaching intelligent software system as described in any one of the above items are executed.

[0014] In a third aspect, the present invention provides a storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the steps in the personalized English teaching intelligent software system as described in any one of the above items are executed.

[0015] The beneficial effects of the present invention are as follows: through real-time collected user information, personalized learning feedback is provided, so that users can master English knowledge points more quickly; by analyzing the user's attention state, the teaching content and rhythm are adjusted in time to improve learning efficiency; by identifying the user's emotional state, the teaching strategy is adjusted to create a more positive learning atmosphere, thereby improving the user's learning interest and enthusiasm; the user can obtain real-time feedback in the learning process, enhance the interactivity and fun of learning, and improve the user's learning experience; through the evaluation module, the user's learning effect is accurately evaluated, data support is provided for teachers and education managers, and teaching methods and content are optimized; based on the analysis of the effective variable group, an ideal learning model can be constructed to provide a basis for subsequent teaching; the learning path is dynamically adjusted according to the user's real-time feedback to ensure the effectiveness and pertinence of the learning plan, adapt to the learning needs and emotional changes of different users, and enable each user to obtain a suitable learning experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A basic flow chart of a personalized English teaching intelligent software system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0017] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, but not all of the embodiments.

[0018] Example, see Figure 1 , is an embodiment of the present invention, providing a personalized English teaching intelligent software system, including a collection module, an analysis module, an evaluation module and a construction module; The collection module sets a control group, takes digital human information and teaching information as variable groups, takes user information as a constant, starts the teaching mode, and collects the user information within the class duration; The analysis module pre-processes the user information, extracts frequency domain features of the pre-processed user information, obtains the attention state through the frequency domain features, counts the concentration state duration within the class time, calculates the concentration effectiveness according to the concentration state duration, sets key time points within the class time, obtains the user's facial image at the key time point, matches the corresponding user mood according to the user's facial image at the key time point, and calculates the user's mood pleasure according to the user's mood; The evaluation module matches the corresponding evaluation questions according to the teaching information, evaluates the user according to the evaluation questions, calculates the result validity according to the evaluation score, sets the result validity threshold, the concentration validity threshold and the mood pleasure threshold, and sets the screening conditions, hierarchically screens the variable group, sets the effective variable group according to the screening results, obtains the result validity, mood pleasure and concentration validity corresponding to the effective variable group, calculates the sum of the result validity, mood pleasure and concentration validity corresponding to the effective variable group, records it as the first sum, and sets it as the ideal variable group according to the first sum; The construction module establishes a first mapping relationship between user information and an ideal variable group.

[0019] The present invention provides personalized learning feedback through real-time collected user information, so that users can master English knowledge points more quickly, analyzes the user's attention state, and timely adjusts the teaching content and rhythm to improve learning efficiency, and adjusts the teaching strategy by identifying the user's emotional state to create a more positive learning atmosphere, thereby improving the user's learning interest and enthusiasm. The user can obtain real-time feedback in the learning process, enhance the interactivity and fun of learning, and improve the user's learning experience. Through the evaluation module, the user's learning effect is accurately evaluated, data support is provided for teachers and education managers, and teaching methods and content are optimized. Based on the analysis of the effective variable group, an ideal learning model can be constructed to provide a basis for subsequent teaching. The learning path is dynamically adjusted according to the user's real-time feedback to ensure the effectiveness and pertinence of the learning plan, adapt to the learning needs and emotional changes of different users, and enable each user to obtain a suitable learning experience.

[0020] The collection module sets a control group, takes digital human information and teaching information as variable groups, takes user information as a constant, starts the teaching mode, and collects the user information within the class duration; The digital human information includes appearance, speaking speed, timbre, volume, number of expression changes and number of gesture changes; the teaching information includes the difficulty of the lesson, the duration of the lesson and the chapter to which the lesson belongs; the user information includes EEG waveform, gender, age, prior knowledge level, preference for English courses and personality; The number of gesture changes is represented by the number of changes in the relative positions of the fingers, that is, the changes in the opening or closing of the fingers or the pointing of the fingers. The number of expression changes is represented by the number of changes in the relative positions of the face, that is, the changes in the relative positions of the eyes, nose, mouth and eyebrows. The relative positions of the fingers are represented by the changes in the positions between the fingers, which are irrelevant to the changes in the overall position of the hand. The changes in the relative positions of the face are represented by the changes in the positions between the eyes, nose, mouth and eyebrows, which are irrelevant to the changes in the overall position of the head. The appearance, speaking speed, timbre and volume are obtained from the virtual digital teacher database, the teaching information is obtained from the online English teaching database, the class difficulty is evaluated by English education experts, and the class difficulty includes the first level difficulty, the second level difficulty, the third level difficulty and the fourth level difficulty; The EEG waveform is monitored by an EGG device. The prior knowledge level is evaluated by obtaining the average value of the user's history English score. When the average value of the history English score is distributed between 0 and 60 points, the prior knowledge level is set to weak. When the average value of the history English score is distributed between 60 and 80 points, the prior knowledge level is set to good. When the average value of the history English score is distributed between 80 and 100 points, the prior knowledge level is set to excellent. The degree of preference for the English course is obtained by user input, and the degree of preference for the English course is distributed between 0 and 10.

[0021] In the specific implementation, by collecting information such as the user's EEG waveform, gender, age, prior knowledge level, English course preference and personality, the system ensures that it has a comprehensive understanding of the user's learning status, so as to better meet personalized learning needs. The setting of digital human information and teaching information enables the system to analyze various data in the user's learning process from multiple dimensions, providing a solid foundation for subsequent analysis and evaluation. By analyzing the user's prior knowledge level and course preference, the system can adjust the teaching content and difficulty according to the user's actual needs to ensure the efficiency and pertinence of the learning process. The information such as the course preference input by the user makes the learning process more humane, enhances the user's sense of participation and initiative, and improves the enthusiasm for learning. It can match the appropriate course difficulty according to the user's prior knowledge level and course preference, and help users learn at an appropriate difficulty level. Based on the user's historical English scores and learning preferences, the system can formulate a personalized learning plan for the user to ensure the effectiveness of the learning path.

[0022] The logic for obtaining the number of gesture changes includes: Obtain a digital human appearance picture, automatically extract the hand parts in the digital human appearance picture through machine vision, track the hand parts, call a hand acupoint distribution database, input a hand part image into the hand acupoint distribution database, match the hand acupoints corresponding to the hand part image, set hand monitoring points for the hand acupoints corresponding to the hand part image, the monitoring points are respectively distributed at Hegu point, Neiguan point, Waiguan point, Shaoshang point, Zhongchong point, Yangchi point, Daling point and Taibai point, calculate the three-dimensional distances between the hand monitoring points respectively, and when the three-dimensional distances between the hand monitoring points change, count the change in the number of gesture changes; The logic for obtaining the number of expression changes includes: Get the appearance picture of the digital human, automatically extract the face in the appearance picture of the digital human through machine vision, track the face, set the eye head point, eye tail point, eye highest point, eye lowest point, nose root midpoint, nose tip lowest point, mouth corner point, upper lip highest point, lower lip lowest point, eyebrow tail point, eyebrow head point and eyebrow peak highest point as facial monitoring points, calculate the three-dimensional distance between facial monitoring points, and when the three-dimensional distance between facial monitoring points changes, count the change in the number of expression changes.

[0023] In specific implementation, by monitoring the number of gesture changes and enhancing the interaction between users and digital teachers, it can improve learning initiative, encourage users to better participate in course content, identify users' emotional changes in the learning process, and adjust teaching methods in a timely manner, provide more help and support to promote users' learning progress. By introducing advanced machine vision technology, it can effectively improve the scientific and technological content of teaching, promote the transformation of the education industry towards intelligence and digitalization, and enrich the presentation methods and content of education.

[0024] The analysis module preprocesses the EEG waveform, and the preprocessing includes filtering and segmentation, extracts the frequency domain features of the preprocessed EEG waveform, and the frequency domain features are represented by the distribution interval features of the waveform frequency. The attention state is obtained through the frequency domain features, and the attention state includes a relaxed state, a concentrated state, and a regulating state. The regulating state is represented by intermittent switching between the concentrated state and the relaxed state. The acquisition logic of the attention state includes: Performing filtering and segmentation processing on the EEG waveform to obtain a brain electronic waveform, obtaining the amplitude of the brain electronic waveform, comparing the amplitude of the brain electronic waveform with a waveform standard distribution interval, obtaining a waveform name of the brain electronic waveform, retrieving a waveform database, inputting the waveform name into the waveform database, and matching the corresponding attention state according to the waveform name; When the amplitude of the brain electronic waveform is distributed between 8 and 12 Hz, the waveform name of the brain electronic waveform is set to α waveform, and the matching attention state is the relaxation state; When the amplitude of the brain electronic waveform is distributed between 12 and 30 Hz, the waveform name of the brain electronic waveform is set to be a β waveform, and the matching attention state is a concentration state; When the amplitude of the brain electronic waveform is distributed between 30 and 100 Hz, the waveform name of the brain electronic waveform is set to γ ​​waveform, and the matching attention state is the adjustment state.

[0025] In specific implementation, through filtering and segmentation processing, the noise in the EEG signal can be effectively removed, thereby improving the accuracy of the EEG waveform characteristics, laying the foundation for the subsequent attention state judgment. The attention state is divided into relaxation state, concentration state and regulation state, which can more carefully capture the user's psychological state changes, and then achieve more personalized teaching adjustments. Through the frequency domain feature analysis of the EEG waveform, the theory of cognitive science is combined with practice to provide a scientific basis and improve the effectiveness of English teaching.

[0026] The analysis module counts the duration of the concentration state within the class time, and calculates the concentration effectiveness according to the concentration state duration. The calculation logic of the concentration effectiveness includes: Acquire the duration of the concentrated state and the duration of the class, calculate the ratio of the duration of the concentrated state to the duration of the class, record it as a first ratio, and set the first ratio as the concentration effectiveness; Set key time points within the duration of the class, obtain the user's facial image at the key time points, filter and grayscale the user's facial image, extract the feature value of the upward angle of the corner of the mouth of the user's facial image after filtering and grayscale processing, call the mood database, input the upward angle of the corner of the mouth into the mood database, match the mood corresponding to the upward angle of the corner of the mouth, set the mood as the user's mood, the mood includes happy, calm and unhappy, assign values ​​to the mood, set happy to the second value, set calm to the third value, set unhappy to the fourth value, obtain the assigned value of the user's mood at the key time points, calculate the average value of the amplitude of the user's mood, and set the average value of the amplitude of the user's mood as the mood pleasure.

[0027] In specific implementation, by calculating the ratio of the concentration state duration to the class duration, the degree of student concentration in class can be accurately evaluated. By processing the user's facial image and extracting the upward angle feature of the mouth corners, the student's emotional changes can be dynamically captured, providing timely information to judge the student's acceptance of class content, and calculating the average value of the user's mood amplitude, providing a quantitative basis for the evaluation of mood pleasure, helping students better understand their emotional state, and promoting self-regulation and learning motivation.

[0028] The evaluation module calls an English teaching database, inputs the difficulty of a lesson and the chapter to which the lesson belongs into the English teaching database, and matches corresponding evaluation questions; The user is assessed according to the assessment questions, and the validity of the result is calculated according to the assessment score. The calculation logic of the validity of the result includes: The total score and the assessment score of the assessment test questions are obtained, the ratio of the assessment score to the total score is calculated, recorded as the second ratio, and the second ratio is set as the result validity threshold.

[0029] The evaluation module sets the fourth value as the result validity threshold, the fifth value as the concentration validity threshold, and the sixth value as the mood pleasure threshold; The variable group is hierarchically screened using the result validity threshold as the first screening condition, the mood pleasure as the second screening condition, and the concentration validity as the third screening condition. The first screening condition is greater than or equal to the fourth value, the second screening condition is greater than or equal to the fifth value, and the third screening condition is greater than or equal to the sixth value. The variable group that meets the first screening condition, the second screening condition and the third screening condition is set as a valid variable group, the result validity, mood pleasure and concentration validity corresponding to the valid variable group are obtained, and the sum of the result validity, mood pleasure and concentration validity corresponding to the valid variable group is calculated and recorded as the first sum; Traverse the first sum value, select the valid variable group corresponding to the first sum value with the largest value, and set the valid variable group corresponding to the first sum value with the largest value as the ideal variable group.

[0030] In the specific implementation, by setting the result validity threshold, concentration validity threshold and mood pleasure threshold, a clear standard is provided for the evaluation, which is helpful to identify high-quality variable groups in complex data sets, and combine multiple indicators for hierarchical screening to ensure that the selected variable group meets the requirements in terms of result validity, concentration validity and mood pleasure, so as to fully reflect the user's learning status. By setting the screening conditions, the variable groups that meet all the conditions at the same time can be effectively filtered out, avoiding the incomplete evaluation caused by a single indicator, and ensuring that the selected variable group is more representative and effective. By combining emotions, concentration and learning effects, the evaluation module forms a new comprehensive evaluation model, which helps to promote the integration of psychology and educational science and provide theoretical support for teaching reform.

[0031] The construction module stores the user information and the corresponding ideal variable group, establishes a first mapping relationship between the user information and the corresponding ideal variable group, obtains the current user information, and obtains the digital human information and teaching information corresponding to the current user information according to the first mapping relationship.

[0032] The present invention provides personalized learning feedback through real-time collected user information, so that users can master English knowledge points more quickly, analyzes the user's attention state, and timely adjusts the teaching content and rhythm to improve learning efficiency, and adjusts the teaching strategy by identifying the user's emotional state to create a more positive learning atmosphere, thereby improving the user's learning interest and enthusiasm. The user can obtain real-time feedback in the learning process, enhance the interactivity and fun of learning, and improve the user's learning experience. Through the evaluation module, the user's learning effect is accurately evaluated, data support is provided for teachers and education managers, and teaching methods and content are optimized. Based on the analysis of the effective variable group, an ideal learning model can be constructed to provide a basis for subsequent teaching. The learning path is dynamically adjusted according to the user's real-time feedback to ensure the effectiveness and pertinence of the learning plan, adapt to the learning needs and emotional changes of different users, and enable each user to obtain a suitable learning experience.

[0033] Another embodiment of the present invention provides an electronic device, including a memory, a processor, and a computer-readable instruction stored in the memory. When the computer-readable instruction is executed by the processor, the steps in the personalized English teaching intelligent software system as described in any one of the above items are executed.

[0034] Another embodiment of the present invention provides a storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps in the personalized English teaching intelligent software system as described in any one of the above items are executed.

[0035] It should be understood by those skilled in the art that the embodiments of the present invention may be provided as methods, systems or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware aspects. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program codes. Among them, the storage medium may be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic memory, flash memory, magnetic disk or optical disk. These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0036] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. Personalized English teaching intelligent software system, characterized by: It includes acquisition module, analysis module, evaluation module and construction module; The collection module is used to set up a control group, with digital human information and teaching information as variable groups, user information as invariant, start the teaching mode, and collect the user information within the class duration; The analysis module pre-processes the user information, extracts frequency domain features of the pre-processed user information, obtains the attention state through the frequency domain features, counts the concentration state duration within the class time, calculates the concentration effectiveness according to the concentration state duration, sets key time points within the class time, obtains the user's facial image at the key time point, matches the corresponding user mood according to the user's facial image at the key time point, and calculates the user's mood pleasure according to the user's mood; The evaluation module matches the corresponding evaluation questions according to the teaching information, evaluates the user according to the evaluation questions, calculates the result validity according to the evaluation score, sets the result validity threshold, the concentration validity threshold and the mood pleasure threshold, and sets the screening conditions, hierarchically screens the variable group, sets the effective variable group according to the screening results, obtains the result validity, mood pleasure and concentration validity corresponding to the effective variable group, calculates the sum of the result validity, mood pleasure and concentration validity corresponding to the effective variable group, records it as the first sum, and sets it as the ideal variable group according to the first sum; The construction module establishes a first mapping relationship between user information and an ideal variable group.

2. The personalized English teaching intelligent software system as claimed in claim 1, characterized in that: The collection module sets a control group, takes digital human information and teaching information as variable groups, takes user information as a constant, starts the teaching mode, and collects the user information within the class duration; The digital human information includes appearance, speaking speed, timbre, volume, number of expression changes and number of gesture changes; the teaching information includes the difficulty of the lesson, the duration of the lesson and the chapter to which the lesson belongs; the user information includes EEG waveform, gender, age, prior knowledge level, preference for English courses and personality; The number of gesture changes is represented by the number of changes in the relative positions of the fingers, that is, the changes in the opening or closing of the fingers or the pointing of the fingers. The number of expression changes is represented by the number of changes in the relative positions of the face, that is, the changes in the relative positions of the eyes, nose, mouth and eyebrows. The relative positions of the fingers are represented by the changes in the positions between the fingers, which are irrelevant to the changes in the overall position of the hand. The changes in the relative positions of the face are represented by the changes in the positions between the eyes, nose, mouth and eyebrows, which are irrelevant to the changes in the overall position of the head. The appearance, speaking speed, timbre and volume are obtained from the virtual digital teacher database, the teaching information is obtained from the online English teaching database, the class difficulty is evaluated by English education experts, and the class difficulty includes the first level difficulty, the second level difficulty, the third level difficulty and the fourth level difficulty; The EEG waveform is monitored by an EGG device. The prior knowledge level is evaluated by obtaining the average value of the user's history English score. When the average value of the history English score is distributed between 0 and 60 points, the prior knowledge level is set to weak. When the average value of the history English score is distributed between 60 and 80 points, the prior knowledge level is set to good. When the average value of the history English score is distributed between 80 and 100 points, the prior knowledge level is set to excellent. The degree of preference for the English course is obtained by user input, and the degree of preference for the English course is distributed between 0 and 10.

3. The personalized English teaching intelligent software system as claimed in claim 2, characterized in that: The logic for obtaining the number of gesture changes includes: Obtain a digital human appearance picture, automatically extract the hand parts in the digital human appearance picture through machine vision, track the hand parts, call a hand acupoint distribution database, input a hand part image into the hand acupoint distribution database, match the hand acupoints corresponding to the hand part image, set hand monitoring points for the hand acupoints corresponding to the hand part image, the monitoring points are respectively distributed at Hegu point, Neiguan point, Waiguan point, Shaoshang point, Zhongchong point, Yangchi point, Daling point and Taibai point, calculate the three-dimensional distances between the hand monitoring points respectively, and when the three-dimensional distances between the hand monitoring points change, count the change in the number of gesture changes; The logic for obtaining the number of expression changes includes: Get the appearance picture of the digital human, automatically extract the face in the appearance picture of the digital human through machine vision, track the face, set the eye head point, eye tail point, eye highest point, eye lowest point, nose root midpoint, nose tip lowest point, mouth corner point, upper lip highest point, lower lip lowest point, eyebrow tail point, eyebrow head point and eyebrow peak highest point as facial monitoring points, calculate the three-dimensional distance between facial monitoring points, and when the three-dimensional distance between facial monitoring points changes, count the change in the number of expression changes.

4. The personalized English teaching intelligent software system as claimed in claim 1, characterized in that: The analysis module preprocesses the EEG waveform, and the preprocessing includes filtering and segmentation, extracts the frequency domain features of the preprocessed EEG waveform, and the frequency domain features are represented by the distribution interval features of the waveform frequency. The attention state is obtained through the frequency domain features, and the attention state includes a relaxed state, a concentrated state, and a regulating state. The regulating state is represented by intermittent switching between the concentrated state and the relaxed state. The acquisition logic of the attention state includes: Performing filtering and segmentation processing on the EEG waveform to obtain a brain electronic waveform, obtaining the amplitude of the brain electronic waveform, comparing the amplitude of the brain electronic waveform with a waveform standard distribution interval, obtaining a waveform name of the brain electronic waveform, retrieving a waveform database, inputting the waveform name into the waveform database, and matching the corresponding attention state according to the waveform name; When the amplitude of the brain electronic waveform is distributed between 8 and 12 Hz, the waveform name of the brain electronic waveform is set to α waveform, and the matching attention state is the relaxation state; When the amplitude of the brain electronic waveform is distributed between 12 and 30 Hz, the waveform name of the brain electronic waveform is set to be a β waveform, and the matching attention state is a concentration state; When the amplitude of the brain electronic waveform is distributed between 30 and 100 Hz, the waveform name of the brain electronic waveform is set to γ ​​waveform, and the matching attention state is the adjustment state.

5. The personalized English teaching intelligent software system as claimed in claim 4, characterized in that: The analysis module counts the duration of the concentration state within the class time, and calculates the concentration effectiveness according to the concentration state duration. The calculation logic of the concentration effectiveness includes: Acquire the duration of the concentrated state and the duration of the class, calculate the ratio of the duration of the concentrated state to the duration of the class, record it as a first ratio, and set the first ratio as the concentration effectiveness; Set key time points within the duration of the class, obtain the user's facial image at the key time points, filter and grayscale the user's facial image, extract the feature value of the upward angle of the corner of the mouth of the user's facial image after filtering and grayscale processing, call the mood database, input the upward angle of the corner of the mouth into the mood database, match the mood corresponding to the upward angle of the corner of the mouth, set the mood as the user's mood, the mood includes happy, calm and unhappy, assign values ​​to the mood, set happy to the second value, set calm to the third value, set unhappy to the fourth value, obtain the assigned value of the user's mood at the key time points, calculate the average value of the amplitude of the user's mood, and set the average value of the amplitude of the user's mood as the mood pleasure.

6. The personalized English teaching intelligent software system according to claim 1, characterized in that: The evaluation module calls an English teaching database, inputs the difficulty of a lesson and the chapter to which the lesson belongs into the English teaching database, and matches corresponding evaluation questions; The user is assessed according to the assessment questions, and the validity of the result is calculated according to the assessment score. The calculation logic of the validity of the result includes: The total score and the assessment score of the assessment test questions are obtained, the ratio of the assessment score to the total score is calculated, recorded as the second ratio, and the second ratio is set as the result validity threshold.

7. The personalized English teaching intelligent software system according to claim 6, characterized in that: The evaluation module sets the fourth value as the result validity threshold, the fifth value as the concentration validity threshold, and the sixth value as the mood pleasure threshold; The variable group is hierarchically screened using the result validity threshold as the first screening condition, the mood pleasure as the second screening condition, and the concentration validity as the third screening condition. The first screening condition is greater than or equal to the fourth value, the second screening condition is greater than or equal to the fifth value, and the third screening condition is greater than or equal to the sixth value. The variable group that meets the first screening condition, the second screening condition and the third screening condition is set as a valid variable group, the result validity, mood pleasure and concentration validity corresponding to the valid variable group are obtained, and the sum of the result validity, mood pleasure and concentration validity corresponding to the valid variable group is calculated and recorded as the first sum; Traverse the first sum value, select the valid variable group corresponding to the first sum value with the largest value, and set the valid variable group corresponding to the first sum value with the largest value as the ideal variable group.

8. The personalized English teaching intelligent software system according to claim 1, characterized in that: The construction module stores the user information and the corresponding ideal variable group, establishes a first mapping relationship between the user information and the corresponding ideal variable group, obtains the current user information, and obtains the digital human information and teaching information corresponding to the current user information according to the first mapping relationship.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the personalized English teaching intelligent software system according to any one of claims 1 to 8 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the personalized English teaching intelligent software system according to any one of claims 1 to 8 is implemented.

Images