Teaching interaction system and method based on embedded artificial intelligence

Abstract

The invention relates to the technical field of intelligent teaching, and discloses a teaching interaction system and method based on embedded artificial intelligence, and the method comprises the steps: obtaining historical learning data and current learning data of a target object, forming analysis data, and forming first comparison data or second comparison data, according to the teaching interaction system and method based on the embedded artificial intelligence, the learning state of the student in the semester is judged, the anti-influence force of the student is judged, and according to the learning states of other students in the semester under the similar conditions of the student, the anti-influence force of the student is judged. According to the method, the learning condition of the student in the semester is judged, so that data sources of evaluation of the student are diversified, the evaluation accuracy is improved, a teacher is prevented from being incapable of determining the reason for the decline of the learning state of the student, and the teacher can respond to noses to improve the learning ability of the student, improve the confidence of the student in learning and improve the learning interest.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent teaching, and in particular to a teaching interaction system and method based on embedded artificial intelligence. Background Art

[0002] The teaching interaction system based on embedded artificial intelligence can effectively improve the interactivity and personalization of classroom teaching, enhance students' learning experience, improve classroom participation and learning effects through real-time feedback and interaction, provide personalized learning suggestions and resources according to students' learning situation, and use data analysis technology to help teachers better understand students' needs and performance. The system can be widely used in different disciplines and educational stages, supports multiple teaching modes, can effectively improve teaching quality, promote students' active learning and in-depth understanding, and provide new solutions for modern education;

[0003] Based on the embedded artificial intelligence teaching interaction system, determine the teaching objectives and needs, understand the specific needs of teachers and students, design the functions of embedded AI modules and interactive terminals, ensure the availability and flexibility of the system, develop rich teaching resources and interactive content, ensure that they meet the curriculum standards and student needs, conduct system tests in a small range, collect feedback and optimize, train teachers and students on the use of the system to ensure that they can operate and use the system proficiently, and continuously optimize the system functions and teaching content based on usage and feedback to ensure its adaptability and effectiveness;

[0004] The existing teaching interaction system and method based on embedded artificial intelligence cannot judge the student's learning status in this semester based on all the student's grades in this semester and historical grades in other semesters, cannot judge the student's own resistance to influence based on the learning status of the students around him in this semester, and cannot judge the student's learning situation in this semester based on the learning status of other students in this semester under similar conditions as the student. This makes the data source for student evaluation single, which is easy to cause inaccurate evaluation, resulting in the teacher's inability to determine the reason for the decline in students' learning status, and then unable to prescribe the right medicine to improve students' learning ability, which is easy to cause students to lose confidence in learning and lose interest in learning. Its practicality has certain limitations. Summary of the invention

[0005] The present invention provides a teaching interaction system and method based on embedded artificial intelligence, which are used to promote the solution of the problems mentioned in the background technology.

[0006] The present invention provides the following technical solution: a teaching interaction method based on embedded artificial intelligence, comprising:

[0007] Get the target object;

[0008] Get the current time;

[0009] Set the collection duration;

[0010] Calculate the collection time, collection time = current time - collection duration;

[0011] The collection time is taken as the start time and the current time is taken as the end time to form a collection cycle;

[0012] According to the target object and collection cycle, execute the data collection strategy to form the current learning data;

[0013] Get the target object's enrollment time;

[0014] If the enrollment time = the collection time, it is determined that the target object has historical data, and the historical learning data of the target object is obtained;

[0015] The historical learning data includes historical concentration scores and historical learning scores;

[0016] Execute a first comparison strategy based on the historical learning data and the current learning data to form first comparison data;

[0017] If the enrollment time ≠ the collection time, it is determined that the target object does not have historical learning data, and the data analysis strategy is executed to form analysis data;

[0018] Execute a second comparison strategy based on the analysis data and the current learning data to form second comparison data;

[0019] A scoring strategy is executed according to the first comparison data or the second comparison data to form a period evaluation score for the target object learned during the acquisition period.

[0020] As a teaching interactive method based on embedded artificial intelligence described in the present invention, wherein: the data collection strategy is specifically:

[0021] Obtain all subjects of the target object within the collection period to form a subject set;

[0022] Perform the learning data analysis strategy on each element in the subject set in turn;

[0023] Set the subject ratio of each element in the subject set;

[0024] Get the element score of each element in the subject set, element score = the sum of all elements in the score set corresponding to the element × the subject ratio of the element;

[0025] Calculate the current learning score, current learning score = the sum of the element scores of all elements in the subject set;

[0026] Get the number of elements in the subject set and set it as the number of subjects;

[0027] Get the number of elements in the subject set that determine the progress of grades, and define it as the progress number;

[0028] If the number of improvements ≥ the number of subjects × 60%, the current concentration score will not be calculated;

[0029] If the number of improvements is less than the number of subjects × 60%, all attendance dates of the target object within the collection period are obtained to form an attendance set;

[0030] Identify each element in the attendance set as an analysis element in turn and implement a focused data collection strategy;

[0031] Obtain all elements in the attendance set that are judged to have high concentration today to form an analysis set;

[0032] Get the number of elements in the attendance set and set it as the attendance number;

[0033] Get the number of elements in the analysis set and set it as the analysis number;

[0034] Calculate the current focus score: Current focus score = (number of analyses ÷ number of attendances) × 100.

[0035] As a teaching interactive method based on embedded artificial intelligence described in the present invention, wherein: the learning data analysis strategy is specifically:

[0036] Obtain all learning scores of the target object within the collection period to form a score set;

[0037] The data collection time for each learning score is obtained, which is defined as the score time;

[0038] Match each score time with each element in the score set one by one to form a score collection set;

[0039] Sort all elements in the score collection set according to the order of score time to form a score sequence set;

[0040] Starting from the first element in the score sequence set, two adjacent elements in the score sequence set are sequentially extracted and defined as the front collection element and the back collection element respectively;

[0041] Calculate the element difference, element difference = later collected element - earlier collected element;

[0042] If the element difference is ≥ 0, the collected element is determined to be a positive element;

[0043] If the element difference is less than 0, the collected element is determined to be a negative element;

[0044] Get the number of elements in the grade sequence set and set it as the grade number;

[0045] Get the number of positive elements in the score sequence set and define it as the improvement amount;

[0046] If the improvement data ≥ (score data - 1) × 60%, the score is considered to have improved;

[0047] If the improvement data is less than (score data - 1) × 60%, the score is judged to have declined.

[0048] As a teaching interactive method based on embedded artificial intelligence described in the present invention, wherein: the focus data collection strategy is specifically:

[0049] Get the number of courses for the analyzed element;

[0050] Get the unit course duration;

[0051] Calculate the attendance time per day: attendance time per day = number of courses × unit course time;

[0052] Obtaining the first acquisition point of the target object;

[0053] Acquire a second acquisition point of the target object;

[0054] Taking the first acquisition point as the starting point, an analysis line is formed through the second acquisition point;

[0055] Get the target area;

[0056] Obtaining a first determination time and a second determination time;

[0057] Set the interval time;

[0058] Taking the first determination time as the starting time, obtaining the intersection of the analysis line and the target area at intervals, and determining it as the analysis point;

[0059] Obtain the number of analysis points, which is defined as the determination number;

[0060] If the number of judgments = 1, then it is judged that there is concentration;

[0061] If the number of judgments = 0, it is judged that there is no concentration;

[0062] Obtaining the number of times the concentration is determined to exist between the first determination time and the second determination time, and defining it as the number of concentrations;

[0063] Calculate the concentration time, concentration time = number of concentration times × interval time;

[0064] If the concentration duration ≥ the attendance duration per day × 70%, the target object is judged to have high concentration on that day;

[0065] If the concentration time is less than the attendance time per day × 70%, the impact analysis strategy will be executed.

[0066] As a teaching interactive method based on embedded artificial intelligence described in the present invention, wherein: the impact analysis strategy is specifically:

[0067] Get the position of the target object and set it as the target position;

[0068] Set the interval length;

[0069] The determination range is formed with the target position as the center and the interval length as the radius;

[0070] Get all students within the judgment range to form a judgment student set;

[0071] The focused data collection strategy is executed sequentially for each element in the judgment student set;

[0072] Obtain the number of elements in the student set whose concentration duration is less than the attendance duration per day × 70%, and define it as the influence quantity;

[0073] If the number of influences is less than 1, the target object is judged to have low concentration today;

[0074] If the number of influences is ≥ 1 and the target object's concentration duration is ≥ the single-day attendance duration × 60%, the target object is judged to have high concentration today;

[0075] If the number of influences is ≥ 1 and the target object's concentration duration is less than the single-day attendance duration × 60%, the target object is judged to have low concentration today.

[0076] As a teaching interactive method based on embedded artificial intelligence described in the present invention, wherein: the first comparison strategy is specifically:

[0077] Get the current concentration score and current learning score of the target object;

[0078] If the target object does not have a current focus score, obtain the target object's historical learning score;

[0079] If the target object has a current concentration score, obtain the target object's historical concentration score and historical learning score;

[0080] If the current learning score ≥ historical learning score × (1 + 10%), it is determined to meet the first progress data;

[0081] If the current learning score is less than the historical learning score × (1 + 10%), it is determined that it does not meet the first progress data;

[0082] If the current concentration score ≥ historical concentration score × (1 + 20%), it is determined to meet the second improvement data;

[0083] If the current concentration score ≥ historical concentration score × (1 + 20%), it is determined that the second improvement data is not met.

[0084] As a teaching interactive method based on embedded artificial intelligence described in the present invention, wherein: the data analysis strategy is specifically:

[0085] Get the target student range;

[0086] Obtain the grade number of the target object and set it as the target grade number;

[0087] Extract all students whose target grade numbers are within the target student range to form an analysis student set;

[0088] The data collection strategy is executed sequentially for each element in the analysis student set;

[0089] Get the current concentration score and current learning score of each element in the analyzed student collection;

[0090] Get the number of elements in the analyzed student set and set it as the number of students;

[0091] Calculate the reference learning score, reference learning score = the sum of the current learning scores of all elements in the analyzed student set ÷ the number of students;

[0092] Calculate the reference concentration score, reference concentration score = the sum of the current concentration scores of all elements in the analyzed student set ÷ the number of students.

[0093] As a teaching interactive method based on embedded artificial intelligence described in the present invention, wherein: the second comparison strategy is specifically:

[0094] Get the current concentration score and current learning score of the target object;

[0095] If the target object does not have a current concentration score, obtain the reference learning score;

[0096] If the target object has a current concentration score, obtain the reference concentration score and the reference learning score;

[0097] If the current learning score ≥ reference learning score × (1 + 10%), it is determined to meet the third progress data;

[0098] If the current learning score is less than the reference learning score × (1 + 10%), it is determined that it does not meet the third progress data;

[0099] If the current concentration score ≥ reference concentration score × (1 + 20%), it is determined to meet the fourth improvement data;

[0100] If the current concentration score ≥ reference concentration score × (1 + 20%), it is determined that the fourth progress data is not met.

[0101] As a teaching interactive method based on embedded artificial intelligence described in the present invention, wherein: the scoring strategy is specifically:

[0102] Setting assessment scores;

[0103] If it is determined to meet the first progress data or the third progress data, the first score is calculated, the first score = (assessment score × 40%) × 80%;

[0104] If it is determined that it does not meet the first progress data or the third progress data, the first score is calculated, and the first score = (assessment score × 40%) × 20%;

[0105] If it is determined to meet the second progress data or the fourth progress data, the second score is calculated, the second score = (assessment score × 60%) × 80%;

[0106] If it is determined that it does not meet the second progress data or it is determined that it does not meet the fourth progress data, the second score is calculated, and the second score = (assessment score × 60%) × 20%;

[0107] Calculate the periodic evaluation score, periodic evaluation score = first score + second score.

[0108] The present invention also discloses a system for executing a teaching interaction method based on embedded artificial intelligence, which includes:

[0109] Collection module: used to collect the current learning data and historical learning data of the target object, and to collect the current learning data of other students under similar conditions to the target object;

[0110] Analysis module: used to analyze the current learning data of other students under similar conditions to the target object to form analysis data;

[0111] Comparison module: used for comparing the current learning data and the historical learning data of the target object or the current learning data and the analysis data of the target object to form first comparison data or second comparison data;

[0112] Evaluation module: used to form a periodic evaluation score for the target object during the acquisition cycle.

[0113] The present invention has the following beneficial effects:

[0114] 1. The teaching interaction system and method based on embedded artificial intelligence obtains all the students' grades in this semester and historical grades in other semesters to determine whether the students' academic performance in this semester has declined. If the grades have declined, it determines whether the students' concentration in this semester has declined. Students' learning is evaluated based on grades and concentration, which diversifies the data sources for student evaluation, avoids teachers evaluating students' learning only based on grades, improves recognition of students who study hard but have poor grades, improves the accuracy of evaluation, and enables teachers to prescribe the right medicine to improve students' learning ability, increase students' self-confidence in learning, and increase their interest in learning.

[0115] 2. When it is determined that a student's concentration has declined in this semester, the teaching interaction system and method based on embedded artificial intelligence determines whether the student's concentration has declined due to the influence of the surrounding environment by obtaining the learning status of the student's classmates in this semester, and determines the student's own ability to resist the influence. If the student is affected by the surrounding environment but still maintains a certain degree of concentration, it means that the student has a certain degree of self-control. The student's ability to resist the influence is recognized, which diversifies the data sources for student evaluation, improves the accuracy of evaluation, avoids the teacher's inability to determine the reason for the decline in students' learning status, and enables the teacher to prescribe the right medicine to improve students' learning ability, increase students' self-confidence in learning, and increase their interest in learning.

[0116] 3. When a student has no historical learning data, the teaching interaction system and method based on embedded artificial intelligence can determine whether the student's learning status in this semester is in a better learning state among students of the same grade by obtaining the learning status of other students in this semester under similar conditions as the student. This diversifies the data sources for student evaluation, improves the accuracy of evaluation, and avoids teachers being unable to determine the reasons for the decline in students' learning status, so that teachers can prescribe the right medicine to improve students' learning ability, increase students' self-confidence in learning, and increase their interest in learning. BRIEF DESCRIPTION OF THE DRAWINGS

[0117] Figure 1 This is a flow chart of the teaching interaction method based on embedded artificial intelligence of the present invention;

[0118] Figure 2 The system block diagram of the present invention is a system block diagram for executing the teaching interaction method based on embedded artificial intelligence. DETAILED DESCRIPTION

[0119] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0120] Embodiment 1, a teaching interaction method based on embedded artificial intelligence, see Figure 1 ,include:

[0121] Acquire a target object, where the target object is a student;

[0122] Get the current time;

[0123] Setting the collection time, which is one semester;

[0124] Calculate the collection time, collection time = current time - collection duration;

[0125] The collection time is taken as the start time and the current time is taken as the end time to form a collection cycle;

[0126] According to the target object and collection cycle, execute the data collection strategy to form the current learning data;

[0127] Get the target object's enrollment time;

[0128] If the enrollment time = the collection time, it is determined that the target object has historical data, and the historical learning data of the target object is obtained;

[0129] The historical learning data includes historical concentration scores and historical learning scores;

[0130] Execute a first comparison strategy based on the historical learning data and the current learning data to form first comparison data;

[0131] If the enrollment time ≠ the collection time, it is determined that the target object does not have historical learning data, and the data analysis strategy is executed to form analysis data;

[0132] Execute a second comparison strategy based on the analysis data and the current learning data to form second comparison data;

[0133] A scoring strategy is executed according to the first comparison data or the second comparison data to form a period evaluation score for the target object learned during the acquisition period.

[0134] Through the above method, the student's learning status in this semester is judged according to all the student's grades in this semester and historical grades in other semesters, the student's own resistance to influence is judged according to the learning status of the students around him in this semester, and the student's learning situation in this semester is judged according to the learning status of other students in this semester under similar conditions as the student. This makes the data sources for student evaluation diversified, improves the accuracy of evaluation, avoids teachers being unable to determine the reasons for the decline in students' learning status, and enables teachers to prescribe the right medicine to improve students' learning ability, increase students' self-confidence in learning, and increase their interest in learning.

[0135] Embodiment 2: This embodiment is an improvement made on the basis of embodiment 1. The teaching interaction method based on embedded artificial intelligence, the data collection strategy, is specifically:

[0136] Obtain all subjects of the target object within the collection period to form a subject set;

[0137] Perform the learning data analysis strategy on each element in the subject set in turn;

[0138] Setting a subject ratio for each element in the subject set, wherein the subject ratio is the proportion of the subject in the total score set according to the importance of the subject determined by the regulations;

[0139] Get the element score of each element in the subject set, element score = the sum of all elements in the score set corresponding to the element × the subject ratio of the element;

[0140] Calculate the current learning score, current learning score = the sum of the element scores of all elements in the subject set;

[0141] Get the number of elements in the subject set and set it as the number of subjects;

[0142] Get the number of elements in the subject set that determine the progress of grades, and define it as the progress number;

[0143] If the number of improvements ≥ the number of subjects × 60%, the current concentration score will not be calculated;

[0144] If the number of improvements is less than the number of subjects × 60%, all attendance dates of the target object within the collection period are obtained to form an attendance set;

[0145] Identify each element in the attendance set as an analysis element in turn and implement a focused data collection strategy;

[0146] Obtain all elements in the attendance set that are judged to have high concentration today to form an analysis set;

[0147] Get the number of elements in the attendance set and set it as the attendance number;

[0148] Get the number of elements in the analysis set and set it as the analysis number;

[0149] Calculate the current focus score: Current focus score = (number of analyses ÷ number of attendances) × 100.

[0150] The learning data analysis strategy is specifically:

[0151] Obtain all learning scores of the target object within the collection period to form a score set;

[0152] The data collection time for each learning score is obtained, which is defined as the score time;

[0153] Match each score time with each element in the score set one by one to form a score collection set;

[0154] Sort all elements in the score collection set according to the order of score time to form a score sequence set;

[0155] Starting from the first element in the score sequence set, two adjacent elements in the score sequence set are sequentially extracted and defined as the front collection element and the back collection element respectively;

[0156] Calculate the element difference, element difference = later collected element - earlier collected element;

[0157] If the element difference is ≥ 0, the collected element is determined to be a positive element;

[0158] If the element difference is less than 0, the collected element is determined to be a negative element;

[0159] Get the number of elements in the grade sequence set and set it as the grade number;

[0160] Get the number of positive elements in the score sequence set and define it as the improvement amount;

[0161] If the improvement data ≥ (score data - 1) × 60%, the score is considered to have improved;

[0162] If the improvement data is less than (score data - 1) × 60%, the score is judged to have declined.

[0163] This embodiment also provides that the dedicated data collection strategy is specifically:

[0164] Get the number of courses for the analyzed element;

[0165] Get the unit course duration, where the unit course duration is the class duration of each course, such as 45 minutes;

[0166] Calculate the attendance time per day: attendance time per day = number of courses × unit course time;

[0167] Acquire a first acquisition point of the target object, where the first acquisition point is the sight point of the target object, that is, the position point where the eyes of the target object are located;

[0168] Acquire a second acquisition point of the target object, where the second acquisition point is a fixed point of the target object, that is, a position point where the center point of the head of the target object is located;

[0169] Taking the first acquisition point as the starting point, an analysis line is formed through the second acquisition point;

[0170] Get the target area;

[0171] Obtain a first determination time and a second determination time, wherein the first determination time is the start time of the first class of the day, and the second determination time is the end time of the last class of the day;

[0172] Set the interval time, the interval time is 1 minute;

[0173] Taking the first determination time as the starting time, obtaining the intersection of the analysis line and the target area at intervals, and determining it as the analysis point;

[0174] Obtain the number of analysis points, which is defined as the determination number;

[0175] If the number of judgments = 1, then it is judged that there is concentration;

[0176] If the number of judgments = 0, it is judged that there is no concentration;

[0177] Obtaining the number of times the concentration is determined to exist between the first determination time and the second determination time, and defining it as the number of concentrations;

[0178] Calculate the concentration time, concentration time = number of concentration times × interval time;

[0179] If the concentration duration ≥ the attendance duration per day × 70%, the target object is judged to have high concentration on that day;

[0180] If the concentration time is less than the attendance time per day × 70%, the impact analysis strategy will be executed.

[0181] The impact analysis strategy is specifically:

[0182] Get the position of the target object and set it as the target position;

[0183] Setting an interval length, wherein the interval length is the length between the center points of two seats;

[0184] The determination range is formed with the target position as the center and the interval length as the radius;

[0185] Get all students within the judgment range to form a judgment student set;

[0186] The focused data collection strategy is executed sequentially for each element in the judgment student set;

[0187] Obtain the number of elements in the student set whose concentration duration is less than the attendance duration per day × 70%, and define it as the influence quantity;

[0188] If the number of influences is less than 1, the target object is judged to have low concentration today;

[0189] If the number of influences is ≥ 1 and the target object's concentration duration is ≥ the single-day attendance duration × 60%, the target object is judged to have high concentration today, that is, the target object may be affected by the people around him, causing his concentration to decrease, but he himself maintains a certain degree of concentration, indicating that his concentration is high;

[0190] If the number of influences is ≥ 1 and the target object's concentration duration is less than the single-day attendance duration × 60%, the target object is judged to have low concentration today.

[0191] Embodiment 3: This embodiment is an improvement made on the basis of Embodiment 2. In this embodiment, the first comparison strategy is specifically:

[0192] Get the current concentration score and current learning score of the target object;

[0193] If the target object does not have a current focus score, obtain the target object's historical learning score;

[0194] If the target object has a current concentration score, obtain the target object's historical concentration score and historical learning score;

[0195] If the current learning score ≥ historical learning score × (1 + 10%), it is determined to meet the first progress data;

[0196] If the current learning score is less than the historical learning score × (1 + 10%), it is determined that it does not meet the first progress data;

[0197] If the current concentration score ≥ historical concentration score × (1 + 20%), it is determined to meet the second improvement data;

[0198] If the current concentration score ≥ historical concentration score × (1 + 20%), it is determined that the second improvement data is not met.

[0199] This embodiment also provides that the data analysis strategy is specifically:

[0200] Obtaining a target student range, where the target range is all students in the school where the target object is located;

[0201] Obtain the grade number of the target object, which is defined as the target grade number. The grade number is the grade of the target object. For example, if the target object is in the fifth grade, the grade number is 5.

[0202] Extract all students whose target grade numbers are within the target student range to form an analysis student set;

[0203] The data collection strategy is executed sequentially for each element in the analysis student set;

[0204] Get the current concentration score and current learning score of each element in the analyzed student collection;

[0205] Get the number of elements in the analyzed student set and set it as the number of students;

[0206] Calculate the reference learning score, reference learning score = the sum of the current learning scores of all elements in the analyzed student set ÷ the number of students;

[0207] Calculate the reference concentration score, reference concentration score = the sum of the current concentration scores of all elements in the analyzed student set ÷ the number of students.

[0208] This embodiment also provides that the second comparison strategy is specifically:

[0209] Get the current concentration score and current learning score of the target object;

[0210] If the target object does not have a current concentration score, obtain the reference learning score;

[0211] If the target object has a current concentration score, obtain the reference concentration score and the reference learning score;

[0212] If the current learning score ≥ reference learning score × (1 + 10%), it is determined to meet the third progress data;

[0213] If the current learning score is less than the reference learning score × (1 + 10%), it is determined that it does not meet the third progress data;

[0214] If the current concentration score ≥ reference concentration score × (1 + 20%), it is determined to meet the fourth improvement data;

[0215] If the current concentration score ≥ reference concentration score × (1 + 20%), it is determined that the fourth progress data is not met.

[0216] This embodiment also provides that the scoring strategy is specifically:

[0217] Setting an evaluation score, wherein the evaluation score is 100;

[0218] If it is determined to meet the first progress data or the third progress data, the first score is calculated, the first score = (assessment score × 40%) × 80%;

[0219] If it is determined that it does not meet the first progress data or the third progress data, the first score is calculated, and the first score = (assessment score × 40%) × 20%;

[0220] If it is determined to meet the second progress data or the fourth progress data, the second score is calculated, the second score = (assessment score × 60%) × 80%;

[0221] If it is determined that it does not meet the second progress data or it is determined that it does not meet the fourth progress data, the second score is calculated, and the second score = (assessment score × 60%) × 20%;

[0222] Calculate the periodic evaluation score, periodic evaluation score = first score + second score.

[0223] Embodiment 4: This embodiment also discloses a system for executing a teaching interaction method based on embedded artificial intelligence, see Figure 2 ,include:

[0224] Collection module: used to collect the current learning data and historical learning data of the target object, and to collect the current learning data of other students under similar conditions to the target object;

[0225] Analysis module: used to analyze the current learning data of other students under similar conditions to the target object to form analysis data;

[0226] Comparison module: used for comparing the current learning data and the historical learning data of the target object or the current learning data and the analysis data of the target object to form first comparison data or second comparison data;

[0227] Evaluation module: used to form a periodic evaluation score for the target object during the acquisition cycle.

[0228] In this embodiment, the student's learning status in this semester is judged based on all the student's grades in this semester and historical grades in other semesters, the student's own resistance to influence is judged based on the learning status of his or her classmates in this semester, and the student's learning situation in this semester is judged based on the learning status of other classmates in this semester under similar conditions as the student. This diversifies the data sources for student evaluation, improves the accuracy of evaluation, avoids teachers being unable to determine the reasons for the decline in students' learning status, and enables teachers to prescribe the right medicine to improve students' learning ability, increase students' self-confidence in learning, and increase their interest in learning.

[0229] The electronic device in the embodiments of the present disclosure may include, but is not limited to, mobile terminals such as laptop computers, PADs (tablet computers), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), and the like, as well as fixed terminals.

[0230] An electronic device may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) or a program loaded from a storage device into a random access memory (RAM). In the RAM, various programs and data required for the operation of the electronic device are also stored. The processing device, ROM, and RAM are connected to each other via a bus. An input / output (I / O) interface is also connected to the bus.

[0231] Typically, the following devices may be connected to the I / O interface: input devices including, for example, a touch screen, a touch pad, an image sensor, a microphone, etc.; output devices including, for example, a liquid crystal display (LCD), a speaker, etc.; storage devices including, for example, a magnetic tape, a hard disk, etc.; and communication devices. The communication devices may allow the electronic device to communicate with other devices wirelessly or by wire to exchange data.

[0232] The embodiments of the present disclosure also provide a non-transitory computer-readable storage medium, which stores computer instructions, and the computer instructions are used to enable the computer to execute the teaching interaction system and method based on embedded artificial intelligence in the aforementioned method embodiments.

[0233] It should be noted that more specific examples of computer-readable storage media may include portable computer disks, hard disks, erasable programmable read-only memories (EPROMs or flash memories), optical storage devices, magnetic storage devices, or any suitable combination thereof. In the present disclosure, computer-readable storage media may be any tangible medium that contains or stores a program, which may be used by or in combination with an instruction execution system, apparatus, or device, and the computer-readable medium may be contained in the electronic device; or it may exist independently without being assembled into the electronic device.

[0234] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device can implement the solution provided by the method embodiment.

[0235] Computer program code for performing operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, and may be executed entirely on a user's computer, partially on a user's computer, as a separate software package, partially on a user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0236] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0237] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A teaching interaction method based on embedded artificial intelligence, characterized by: include: Get the target object; Get the current time; Set the collection duration; Calculate the collection time, collection time = current time - collection duration; The collection time is taken as the start time and the current time is taken as the end time to form a collection cycle; According to the target object and collection cycle, execute the data collection strategy to form the current learning data; Get the target object's enrollment time; If the enrollment time = the collection time, it is determined that the target object has historical data, and the historical learning data of the target object is obtained; The historical learning data includes historical concentration scores and historical learning scores; Execute a first comparison strategy based on the historical learning data and the current learning data to form first comparison data; If the enrollment time ≠ the collection time, it is determined that the target object does not have historical learning data, and the data analysis strategy is executed to form analysis data; Execute a second comparison strategy based on the analysis data and the current learning data to form second comparison data; A scoring strategy is executed according to the first comparison data or the second comparison data to form a period evaluation score for the target object learned during the acquisition period.

2. The teaching interactive method based on embedded artificial intelligence according to claim 1, characterized in that: The data collection strategy is specifically as follows: Obtain all subjects of the target object within the collection period to form a subject set; Perform the learning data analysis strategy on each element in the subject set in turn; Set the subject ratio of each element in the subject set; Get the element score of each element in the subject set, element score = the sum of all elements in the score set corresponding to the element × the subject ratio of the element; Calculate the current learning score, current learning score = the sum of the element scores of all elements in the subject set; Get the number of elements in the subject set and set it as the number of subjects; Get the number of elements in the subject set that determine the progress of grades, and define it as the progress number; If the number of improvements ≥ the number of subjects × 60%, the current concentration score will not be calculated; If the number of improvements is less than the number of subjects × 60%, all attendance dates of the target object within the collection period are obtained to form an attendance set; Identify each element in the attendance set as an analysis element in turn and implement a focused data collection strategy; Obtain all elements in the attendance set that are judged to have high concentration today to form an analysis set; Get the number of elements in the attendance set and set it as the attendance number; Get the number of elements in the analysis set and set it as the analysis number; Calculate the current focus score: Current focus score = (number of analyses ÷ number of attendances) × 100.

3. The teaching interactive method based on embedded artificial intelligence according to claim 2, characterized in that: The learning data analysis strategy is specifically: Obtain all learning scores of the target object within the collection period to form a score set; The data collection time for each learning score is obtained, which is defined as the score time; Match each score time with each element in the score set one by one to form a score collection set; Sort all elements in the score collection set according to the order of score time to form a score sequence set; Starting from the first element in the score sequence set, two adjacent elements in the score sequence set are sequentially extracted and defined as the front collection element and the back collection element respectively; Calculate the element difference, element difference = later collected element - earlier collected element; If the element difference is ≥ 0, the collected element is determined to be a positive element; If the element difference is less than 0, the collected element is determined to be a negative element; Get the number of elements in the grade sequence set and set it as the grade number; Get the number of positive elements in the score sequence set and define it as the improvement amount; If the improvement data ≥ (score data - 1) × 60%, the score is considered to have improved; If the improvement data is less than (score data - 1) × 60%, the score is judged to have declined.

4. The teaching interactive method based on embedded artificial intelligence according to claim 2, characterized in that: The focused data collection strategy is specifically: Get the number of courses for the analyzed element; Get the unit course duration; Calculate the attendance time per day: attendance time per day = number of courses × unit course time; Obtaining the first acquisition point of the target object; Acquire a second acquisition point of the target object; Taking the first acquisition point as the starting point, an analysis line is formed through the second acquisition point; Get the target area; Obtaining a first determination time and a second determination time; Set the interval time; Taking the first determination time as the starting time, obtaining the intersection of the analysis line and the target area at intervals, and determining it as the analysis point; Obtain the number of analysis points, which is defined as the determination number; If the number of judgments = 1, it is judged that concentration exists; If the number of judgments = 0, it is judged that there is no concentration; Obtaining the number of times the concentration is determined to exist between the first determination time and the second determination time, and setting it as the number of concentration times; Calculate the concentration time, concentration time = number of concentration times × interval time; If the concentration duration ≥ the attendance duration per day × 70%, the target object is judged to have high concentration on that day; If the concentration time is less than the attendance time per day × 70%, the impact analysis strategy will be executed.

5. The teaching interactive method based on embedded artificial intelligence according to claim 4, characterized in that: The impact analysis strategy is specifically: Get the position of the target object and set it as the target position; Set the interval length; The determination range is formed with the target position as the center and the interval length as the radius; Get all students within the judgment range to form a judgment student set; The focused data collection strategy is executed sequentially for each element in the judgment student set; Obtain the number of elements in the student set whose concentration duration is less than the attendance duration per day × 70%, and define it as the influence quantity; If the number of influences is less than 1, the target object is judged to have low concentration today; If the number of influences is ≥ 1 and the target object's concentration duration is ≥ the single-day attendance duration × 60%, the target object is judged to have high concentration today; If the number of influences is ≥ 1 and the target object's concentration duration is less than the single-day attendance duration × 60%, the target object is judged to have low concentration today.

6. The teaching interactive method based on embedded artificial intelligence according to claim 1, characterized in that: The first comparison strategy is specifically: Get the current concentration score and current learning score of the target object; If the target object does not have a current focus score, obtain the target object's historical learning score; If the target object has a current concentration score, obtain the target object's historical concentration score and historical learning score; If the current learning score ≥ historical learning score × (1 + 10%), it is determined to meet the first progress data; If the current learning score is less than the historical learning score × (1 + 10%), it is determined that it does not meet the first progress data; If the current concentration score ≥ historical concentration score × (1 + 20%), it is determined to meet the second improvement data; If the current concentration score ≥ historical concentration score × (1 + 20%), it is determined that the second improvement data is not met.

7. The teaching interactive method based on embedded artificial intelligence according to claim 2, characterized in that: The data analysis strategy is specifically as follows: Get the target student range; Obtain the grade number of the target object and set it as the target grade number; Extract all students whose target grade numbers are within the target student range to form an analysis student set; The data collection strategy is executed sequentially for each element in the analysis student set; Get the current concentration score and current learning score of each element in the analyzed student collection; Get the number of elements in the analyzed student set and set it as the number of students; Calculate the reference learning score, reference learning score = the sum of the current learning scores of all elements in the analyzed student set ÷ the number of students; Calculate the reference concentration score, reference concentration score = the sum of the current concentration scores of all elements in the analyzed student set ÷ the number of students.

8. The teaching interactive method based on embedded artificial intelligence according to claim 1, characterized in that: The second comparison strategy is specifically: Get the current concentration score and current learning score of the target object; If the target object does not have a current concentration score, obtain the reference learning score; If the target object has a current concentration score, obtain the reference concentration score and the reference learning score; If the current learning score ≥ reference learning score × (1 + 10%), it is determined to meet the third progress data; If the current learning score is less than the reference learning score × (1 + 10%), it is determined that it does not meet the third progress data; If the current concentration score ≥ reference concentration score × (1 + 20%), it is determined to meet the fourth improvement data; If the current concentration score ≥ reference concentration score × (1 + 20%), it is determined that the fourth progress data is not met.

9. The teaching interactive method based on embedded artificial intelligence according to claim 1, characterized in that: The scoring strategy is specifically: Setting assessment scores; If it is determined to meet the first progress data or the third progress data, the first score is calculated, the first score = (assessment score × 40%) × 80%; If it is determined that it does not meet the first progress data or the third progress data, the first score is calculated, and the first score = (assessment score × 40%) × 20%; If it is determined to meet the second improvement data or the fourth improvement data, the second score is calculated, the second score = (assessment score × 60%) × 80%; If it is determined that it does not meet the second progress data or it is determined that it does not meet the fourth progress data, the second score is calculated, and the second score = (assessment score × 60%) × 20%; Calculate the periodic evaluation score, periodic evaluation score = first score + second score.

10. A system for executing the teaching interactive method based on embedded artificial intelligence according to claim 1, characterized in that: include: Collection module: used to collect the current learning data and historical learning data of the target object, and to collect the current learning data of other students under similar conditions to the target object; Analysis module: used to analyze the current learning data of other students under similar conditions to the target object to form analysis data; Comparison module: used for comparing the current learning data and the historical learning data of the target object or the current learning data and the analysis data of the target object to form first comparison data or second comparison data; Evaluation module: used to form a periodic evaluation score for the target object during the acquisition cycle.

Images