Physical, chemical and biological experiment AI teaching assistant for self-adaptive learning path planning and implementation method of physical, chemical and biological experiment AI teaching assistant

Abstract

The invention discloses a physical, chemical and student experiment AI teaching assistant for adaptive learning path planning and an implementation method, and the method comprises the steps: carrying out the planning of a first learning path for a student, carrying out the analysis of the hand tracking data of the student in an experiment process, obtaining the scoring data, and carrying out the re-planning of the learning path, analysis can be carried out according to the conditions of students and the operation performance in the experiment, so that adaptive change of subsequent experiments is carried out according to the experiment quality of the students, it is guaranteed that the students can obtain experiment guidance conforming to the students, and the defect that in the prior art, targeted experiment guidance cannot be carried out according to the students is overcome; the first learning path is used for adjusting the preset standard value of each experiment of the student, the preset standard value is in positive correlation with the academic record, the learning ability of the student is matched by adjusting the preset standard value, and the teaching strategy can be dynamically adjusted according to the learning progress and the academic record change of the student so as to adapt to the constantly changing learning requirements of the student.

Description

Technical Field

[0001] The present invention relates to the technical field of management systems, in particular to the technical field of education management systems, and in particular to an AI teaching assistant for physics, chemistry and biology experiments with adaptive learning path planning and an implementation method thereof. Background Art

[0002] With the continuous advancement of educational concepts, secondary education pays more and more attention to cultivating students' practical ability and scientific literacy. As an important part of science teaching in secondary schools, physics, chemistry and biology experiments are becoming increasingly important. Physics, chemistry and biology laboratories are important places for students to conduct scientific exploration. By personally operating experimental equipment, observing and analyzing experimental phenomena, students can understand scientific principles and natural laws more intuitively. This practical learning method helps to deepen students' grasp of theoretical knowledge and effectively improve their practical operation ability and problem-solving ability.

[0003] However, in the experiment, students paid too much attention to the experimental results and ignored the details and significance of the experimental process. The teacher's evaluation of the experimental process was not comprehensive enough, which led to students' insufficient attention to the experimental process and many incorrect operations during the experiment. The teacher was unable to provide corresponding experimental guidance for each student, and could not provide corresponding guidance for students with different operating bases. As a result, students with a good operating foundation could not receive high-standard guidance and were prone to mistakes during the experiment. Students with a poor operating foundation were given guidance with too high difficulty standards, which resulted in poor experimental completion and poor experimental results.

[0004] Therefore, targeted guidance is needed for the physical, chemical and biological experimental processes. Summary of the invention

[0005] The present invention overcomes the shortcomings of the prior art and provides an AI teaching assistant for physics, chemistry and biology experiments with adaptive learning path planning and an implementation method, aiming to solve the problem that the prior art cannot provide targeted experimental guidance according to students.

[0006] To achieve the above-mentioned purpose, the technical solution adopted by the present invention is: a method for implementing an AI teaching assistant for physics, chemistry and biology experiments with adaptive learning path planning, comprising:

[0007] Plan the first learning path based on student information;

[0008] Acquire experimental data of the student's experimental process, the experimental data including: hand tracking data, hand error data and scoring data, the hand tracking data is the hand data of the student's experimental process, the hand error data is the difference between the hand tracking data and a preset standard value, the preset standard value is established according to the learning path, and the scoring data is established based on the hand error data and the preset standard value;

[0009] The first learning path is replanned according to the scoring data to obtain a second learning path.

[0010] In a preferred embodiment of the present invention, the student information includes: academic performance, age, height, and hand joint size. The academic performance includes the scores of individual subjects and the average score of the student. The academic performance is used to determine the student's learning situation. The age and height are used to determine the operating height during the experiment. The hand joint size is used to determine the specific operating position of the hand joints during the experiment.

[0011] In a preferred embodiment of the present invention, the first learning path is used to adjust the preset standard value of each experiment of the student respectively, and the preset standard value is positively correlated with the learning performance. The higher the single subject score, the higher the preset standard value, and the greater the positive gap between the single subject score and the average score of the student. The higher the preset standard value, the positive gap is the value by which the single subject score exceeds the average score of the student.

[0012] In a preferred embodiment of the present invention, the preset standard value includes a baseline score, a hand data standard value and an experimental standard value, the hand data standard value includes a preset standard average value and a preset threshold value, the preset standard average value is the experimental standard operation value, the preset threshold value is the error range of the preset standard average value, and the preset threshold value is manifested as a spherical shell surface of the preset standard average value in actual operation. When the hand joint is located inside or on the spherical shell surface formed by the preset threshold value, it is determined that the hand tracking data is located within the preset threshold value, that is, the hand tracking data meets the preset standard value.

[0013] In a preferred embodiment of the present invention, the hand tracking data acquisition process is to determine the preset standard average value and the predetermined threshold value according to a reference point, and the reference point is one of the wrist center or the palm center.

[0014] In a preferred embodiment of the present invention, the hand error data is the difference between the hand tracking data and the preset standard average value. When the hand joint is located outside the spherical shell surface formed by the preset threshold, it is determined that the hand tracking data is not within the preset threshold, that is, the hand tracking data does not meet the preset standard value.

[0015] In a preferred embodiment of the present invention, the scoring data is based on the standards of the hand error data, namely, the numerical value of the hand error data, the current number of occurrences and the current time ratio, the current number of occurrences is the number of times the hand error data appears in the current experiment, the time ratio is the ratio of the time when the hand error data appears to the current experiment time, and the experimental standard value is the preset number of occurrences and the preset time ratio of the hand error data in the experiment. According to the numerical value of the hand error data, the value of the current number of occurrences being greater than the preset number of occurrences, and the value of the preset time ratio being greater than the preset time ratio, weighted deduction processing is performed respectively, and the scoring data is obtained after the weighted deduction processing is performed on the full score.

[0016] In a preferred embodiment of the present invention, the scoring data is compared with the benchmark score. If the scoring data is greater than the benchmark score, it is determined that the student's experiment is in compliance with the first learning path, and the first learning path is replanned to increase the preset standard value of subsequent experiments. If the scoring data is less than the benchmark score, it is determined that the student's experiment is not in compliance with the first learning path, and the first learning path is replanned to lower the preset standard value of subsequent experiments.

[0017] In a preferred embodiment of the present invention, the higher the preset standard value means the higher the benchmark score, the smaller the predetermined threshold, the fewer the preset occurrence times and the smaller the preset time proportion, and the preset standard value is respectively affected by the positive gap weights of the single subject score and the single subject score and the average score of the student.

[0018] To achieve the above purpose, the second set of technical solutions adopted by the present invention is: an AI teaching assistant for physical, chemical and biological experiments with adaptive learning path planning, comprising:

[0019] Student information unit, used to enter student information;

[0020] A planning unit, used for planning the first learning path according to student information;

[0021] Image unit, used to obtain experimental data of students' experimental process;

[0022] A storage unit, used for storing a preset standard value;

[0023] A comparison unit, used for processing the hand tracking data to obtain hand error data;

[0024] A processing unit, used for comparing the hand error data with a preset standard value and calculating and obtaining scoring data;

[0025] The adjustment unit is used to adjust the first path and the preset standard value according to the scoring data.

[0026] The present invention solves the defects existing in the background technology and has the following beneficial effects:

[0027] (1) The present invention provides a method for implementing an AI teaching assistant for physics, chemistry and biology experiments with adaptive learning path planning. After planning a first learning path for students, the hand tracking data of the students is analyzed during the experiment, and the learning path is re-planned after obtaining the scoring data. Compared with the physics, chemistry and biology experiment guidance method in the prior art, the method can analyze the students' own situation and the operation performance in the experiment, so as to make adaptive changes to the subsequent experiments according to the students' experimental qualities, thereby ensuring that students can obtain experimental guidance that suits them, and solving the defect that the prior art cannot provide targeted experimental guidance according to students.

[0028] (2) In the present invention, the first learning path is used to adjust the preset standard value of each student's experiment respectively. The preset standard value is positively correlated with the learning performance. By adjusting the preset standard value to match the student's learning ability, the experimental task is ensured to be moderate. Compared with the existing technology, the relevance and effectiveness of teaching are improved, and the teaching strategy can be dynamically adjusted according to the student's learning progress and performance changes to adapt to the students' changing learning needs.

[0029] (3) In the present invention, the preset standard value includes a baseline score, a hand data standard value and an experimental standard value. The hand data standard value includes a preset standard average value and a predetermined threshold value. By subdividing the preset standard value into a baseline score, a hand data standard value and an experimental standard value, A can more accurately evaluate the students' experimental operation skills. Compared with the prior art, the introduction of the predetermined threshold value provides an error range for the preset standard average value, which can more flexibly adapt to the slight differences among students during the experiment and enhance the accuracy of judging the hand tracking data during the experiment. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art are briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work. Figure 1 is a method step diagram of a preferred embodiment of the present invention; Figure 2 It is a system flow chart of a preferred embodiment of the present invention. DETAILED DESCRIPTION

[0033] 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.

[0034] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0035] Application Overview

[0036] The AI ​​teaching assistant for physics, chemistry and biology experiments is an auxiliary tool based on artificial intelligence technology, which aims to improve the efficiency and quality of experimental teaching and provide more comprehensive and personalized support for students' learning. The AI ​​teaching assistant can provide personalized guidance and learning resources based on students' learning characteristics and ability levels. By intelligently analyzing students' learning data, the system can accurately identify students' learning preferences and problems, and recommend suitable learning materials and experimental plans to achieve teaching in accordance with their aptitude.

[0037] In response to the above technical problems, the concept of the present invention is to provide an implementation method of an AI teaching assistant for physics, chemistry and biology experiments with adaptive learning path planning. After planning the first learning path for the students, the students' hand tracking data is analyzed during the experiment, and the learning path is re-planned after obtaining the scoring data. The analysis can be performed based on the students' own situation and the operational performance in the experiment, so that adaptive changes can be made to subsequent experiments based on the students' experimental qualities, ensuring that students can obtain experimental guidance that suits them, and solving the defect in the prior art that targeted experimental guidance cannot be provided to students.

[0038] Exemplary Methods

[0039] like Figure 1 As shown, a method for implementing an AI teaching assistant for physics, chemistry and biology experiments with adaptive learning path planning includes:

[0040] Plan the first learning path based on student information; the first step of the AI ​​teaching assistant is to develop a preliminary learning path based on the student's specific information, which will serve as the basis for students to start experimental learning.

[0041] The experimental data of the student's experimental process is obtained. The experimental data include: hand tracking data, hand error data and scoring data. The hand tracking data is the hand data of the student's experimental process. The hand error data is the difference between the hand tracking data and the preset standard value. The preset standard value is established according to the learning path. The scoring data is established based on the hand error data and the preset standard value. The data is obtained by tracking the student's hand movements and compared with the preset standard values ​​to determine the accuracy of the student's operation. The scoring data is determined based on these comparison results.

[0042] The first learning path is replanned based on the scoring data to obtain the second learning path. The AI ​​teaching assistant will adjust the learning path based on the student's scoring data to ensure that students can receive more personalized guidance in subsequent learning.

[0043] Student information includes: academic performance, age, height, and hand joint size. Academic performance includes the scores of individual subjects and the student’s average score. Academic performance is used to determine the student’s learning situation. Age and height are used to determine the operating height during the experiment. Hand joint size is used to determine the specific operating position of the hand joints during the experiment.

[0044] By considering individual differences among students, such as academic performance and physical characteristics, the AI ​​teaching assistant can design a more personalized learning path for each student, thereby improving learning efficiency and effectiveness. Information on the size of the hand joints can help the AI ​​teaching assistant more accurately guide students' hand movements in experiments and improve the precision of operations. Age and height information helps determine the appropriate height for students when performing experimental operations, ensuring that students can perform experiments in a comfortable and safe posture.

[0045] The first learning path is used to adjust the preset standard value of each student's experiment. The preset standard value is positively correlated with the learning performance. The higher the score of a single subject, the higher the preset standard value. The greater the positive difference between the single subject score and the average score of the student, the higher the preset standard value. The positive difference is the value by which the single subject score exceeds the average score of the student. The greater the negative difference between the single subject score and the average score of the student, the lower the preset standard value. The positive difference is the value by which the average score of the student exceeds the single subject score.

[0046] First Learning Path Formula D n It is expressed as:

[0047] Where n is the experiment number, a n is the basic difficulty score, which is the average difficulty score of the experiment in historical data, k n is the adjustment factor of the student's experiment, X is the student's single subject score, m is the student's experimental coefficient, X is the student's average score, k nThe value is 0.2-0.5, the value of m is 0.005-0.01, and the value of a n As the number of experiments increases, the value increases accordingly. n The overall performance is that as the experiment number increases, the difficulty of the experiment increases.

[0048] The AI ​​assistant adjusts the preset standard values ​​to match the students' learning abilities, ensuring that the experimental tasks are neither too easy nor too difficult, thereby improving the relevance and effectiveness of teaching. The AI ​​assistant can dynamically adjust the teaching strategy based on the students' learning progress and performance changes to adapt to the students' changing learning needs.

[0049] The preset standard values ​​include benchmark scores, hand data standard values ​​and experimental standard values. The hand data standard values ​​include preset standard average values ​​and preset threshold values. The preset standard average value is the standard operating value of this experiment. The preset threshold value is the error range of the preset standard average value. The preset threshold value is manifested as a spherical shell surface of the preset standard average value in actual operation. When the hand joint is located inside or on the spherical shell surface formed by the preset threshold value, it is determined that the hand tracking data is within the preset threshold value, that is, the hand tracking data meets the preset standard value.

[0050] By subdividing the preset standard values ​​into baseline scores, hand data standard values, and experimental standard values, the AI ​​assistant can more accurately evaluate students' experimental operation skills. The introduction of the preset threshold provides an error range for the preset standard average, which enables the AI ​​assistant to more flexibly adapt to the slight differences in students' experimental process, rather than relying solely on strict standard values. The spherical shell surface model of hand tracking data provides a clear, quantifiable and objective standard for evaluation, reduces the influence of subjective judgment, and provides a clear comparison for subsequent evaluation of hand tracking data. The absolute value of the predetermined threshold is the distribution radius of the spherical shell surface.

[0051] The hand tracking data acquisition process is to determine the preset standard average value and predetermined threshold value based on the reference point, which is one of the wrist center or palm center. The use of reference points can provide a stable reference for hand tracking, thereby improving the accuracy of tracking. The reference points can more easily define the standard average value and error range of hand movements, providing a clear standard for evaluating students' experimental operations.

[0052] The hand error data is the difference between the hand tracking data and the preset standard average value. When the hand joint is located outside the spherical shell surface formed by the preset threshold, it is determined that the hand tracking data is not within the preset threshold, that is, the hand tracking data does not meet the preset standard value.

[0053] By comparing hand tracking data with a preset standard average, the AI ​​assistant can accurately evaluate the student's operating skills in the experiment, thereby providing more accurate feedback. Through a predetermined threshold, the AI ​​assistant can quantify the error range of the operation, which helps to understand the acceptable deviation of the student's operation and thus adjust the teaching strategy.

[0054] The scoring data is based on the standards of hand error data, namely the numerical value of the hand error data, the current number of occurrences and the current time ratio. The current number of occurrences is the number of times the hand error data appears in the current experiment, the time ratio is the ratio of the time when the hand error data appears to the current experimental time, and the experimental standard value is the preset number of occurrences and the preset time ratio of the hand error data in the experiment. Weighted deduction is performed according to the numerical value of the hand error data, the value of the current number of occurrences being greater than the preset number of occurrences, and the value of the preset time ratio being greater than the preset time ratio, and the scoring data is obtained after weighted deduction from the full score.

[0055] AI assistants can evaluate students' experimental operation skills more comprehensively, taking into account not only the accuracy of hand movements (numerical size), but also the frequency (number of occurrences) and duration (time percentage) of movement errors. By weighting the numerical size, number of occurrences and time percentage of hand error data, AI assistants can quantify the impact of each error on the overall performance, thereby more accurately evaluating students' mastery.

[0056] The scoring formula is: S n =100×(1-w1·f-w2·g-w3·h), where S n is the score of the nth experiment, f, g and h are the error score, occurrence score and time proportion score of the experiment respectively, w1, w2 and w3 are the error score coefficient, occurrence score coefficient and time proportion score coefficient respectively, w1, w2 and w3 are all between 0 and 1, and the sum of their values ​​is equal to 1.

[0057] The error score f has the relationship: Among them, i is the serial number of the hand error data in the experiment, j is the total number of hand errors in the experiment, and Y i is the value of the i-th hand error data, and Y0 is the predetermined threshold.

[0058] The occurrence score g has the relationship: Among them, j0 is the preset number of occurrences.

[0059] The time proportion score h has the relationship: Among them, h j is the time proportion of hand error data in this experiment, and h0 is the preset time proportion of hand error data in this experiment.

[0060] The scoring data is compared with the benchmark score. If the scoring data is greater than the benchmark score, it is determined that the student's experiment is in line with the first learning path, and the first learning path is re-planned to increase the preset standard value of subsequent experiments. If the scoring data is less than the benchmark score, it is determined that the student's experiment is not in line with the first learning path, and the first learning path is re-planned to lower the preset standard value of subsequent experiments.

[0061] The following relationship exists between comparing and changing the first learning path:

[0062] When D n ≠S n When k n+1 , Y0, j0 and h0 are adjusted, k n+1 is the adjustment factor for the next experiment of this experiment, and the adjustment relationship is where k n+1 ', Y0', j0' and h0' are k n+1 , Y0, j0 and h0 are changed in the latter experiment, and j0' is rounded up;

[0063] When D n =S n When k n+1 , Y0, j0 and h0 remain unchanged.

[0064] The AI ​​assistant is able to dynamically adjust the difficulty of subsequent experiments based on students' scoring data, ensuring that students always learn at an appropriate level of challenge. By adjusting the preset standard values, the AI ​​assistant helps students learn at the edge of their learning comfort zone, which helps maximize learning efficiency. By comparing with benchmark scores, the AI ​​assistant can more accurately measure students' learning outcomes and provide teachers with valuable feedback on students' progress.

[0065] The higher the preset standard value, the higher the benchmark score, the smaller the preset threshold, the fewer preset occurrences and the smaller the preset time proportion. The preset standard value is affected by the weight of the positive gap between the single subject score and the single subject score and the average score of the student.

[0066] The AI ​​assistant is able to provide each student with a tailored learning experience that takes into account their individual abilities and academic level, thereby improving the personalization of teaching. Students can be challenged at a level that is appropriate for them, which helps them learn more effectively and avoid being bored because the task is too easy or frustrated because the task is too difficult. This approach helps ensure that all students, regardless of their overall academic performance, are recognized and challenged in areas where they excel, thereby improving fairness in laboratory teaching.

[0067] Exemplary Devices

[0068] like Figure 2 As shown, an AI teaching assistant for physics, chemistry and biology experiments with adaptive learning path planning includes:

[0069] The student information unit is used to input student information; the student information unit is a computer and image acquisition device, which is responsible for collecting and recording students' personal information, such as academic performance, age, height, and hand joint size, etc. This information will be used to formulate and adjust the learning path to ensure the personalization and adaptability of experimental teaching.

[0070] The planning unit is used to plan the first learning path based on the student information; the planning unit is a computer program that develops a preliminary learning path based on the data provided by the student information unit. It sets appropriate experimental tasks and challenges based on the student's academic performance, physical characteristics and experimental skills.

[0071] The image unit is used to obtain experimental data during the students' experiment. The image unit is an image acquisition device that is responsible for obtaining the students' hand movement data during the experiment through image capture technology (such as video analysis, motion tracking, etc.). These data will be used for subsequent analysis and evaluation.

[0072] A storage unit for storing preset standard values; the storage unit is a computer program, and the storage unit is used to save preset standard values ​​related to the experiment. These standard values ​​may include operating standards, scoring standards, and experimental steps, etc., which are used to evaluate whether the students' experimental operations meet expectations.

[0073] The comparison unit is used to process the hand tracking data to obtain the hand error data; the comparison unit is a computer program, which is responsible for comparing the hand tracking data of the students during the experiment with the preset standard value to determine the accuracy and efficiency of the operation, thereby obtaining the hand error data.

[0074] The processing unit is used to compare the preset standard value according to the hand error data and calculate the scoring data; the processing unit is a computer program, and the processing unit compares the preset standard value according to the data provided by the comparison unit and calculates the scoring data. This scoring data will reflect the student's operation performance in the experiment, including the accuracy of hand movements, the number of errors and the proportion of time.

[0075] The adjustment unit is used to adjust the first path and the preset standard value according to the scoring data. The adjustment unit is a computer program, and the adjustment unit adjusts the learning path according to the scoring data calculated by the processing unit. If the scoring data shows that the student performs well, the difficulty of subsequent experiments may be increased; if the scoring data shows that the student needs more guidance, the difficulty may be reduced or more practice opportunities may be provided.

[0076] Exemplary Electronic Devices

[0077] To achieve the above object, the third technical solution adopted by the present invention is: an electronic device, comprising:

[0078] Processor; a processor may be a central processing unit (CPU) or other form of processing unit having data processing capability and / or instruction execution capability.

[0079] A memory stores computer program instructions, which, when executed by a processor, enable the processor to execute an implementation method of an AI teaching assistant for physics, chemistry and biology experiments with adaptive learning path planning.

[0080] The memory may include one or more computer program products, and the computer program product may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory and / or cache memory, etc. The non-volatile memory may include, for example, a read-only memory, a hard disk, a flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor may run the program instructions to implement the implementation method of the physics, chemistry and biology experiment AI teaching assistant for adaptive learning path planning of the various embodiments of the present application described above and / or other desired functions.

[0081] A computer-readable storage medium stores computer program instructions, which, when executed by a processor, enable the processor to execute an implementation method of an AI teaching assistant for physics, chemistry and biology experiments with adaptive learning path planning.

[0082] Computer readable storage media can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0083] The above is based on the ideal embodiment of the present invention. Through the above description, relevant personnel can make various changes and modifications without departing from the technical concept of the present invention. The technical scope of the present invention is not limited to the content in the specification, and the technical scope must be determined according to the scope of the claims.

Claims

1. A method for implementing an AI teaching assistant for physics, chemistry and biology experiments with adaptive learning path planning, characterized in that: include: Plan the first learning path based on student information; Acquire experimental data of the student's experimental process, the experimental data including: hand tracking data, hand error data and scoring data, the hand tracking data is the hand data of the student's experimental process, the hand error data is the difference between the hand tracking data and a preset standard value, the preset standard value is established according to the learning path, and the scoring data is established based on the hand error data and the preset standard value; The first learning path is replanned according to the scoring data to obtain a second learning path.

2. According to claim 1, the method for implementing an adaptive learning path planning AI teaching assistant for physical, chemical and biological experiments is characterized by: The student information includes: academic performance, age, height, and hand joint size. The academic performance includes the scores of individual subjects and the average score of the student. The academic performance is used to determine the student's learning situation. The age and height are used to determine the operating height during the experiment. The hand joint size is used to determine the specific operating position of the hand joints during the experiment.

3. The method for implementing an adaptive learning path planning AI teaching assistant for physical, chemical and biological experiments according to claim 2 is characterized by: The first learning path is used to adjust the preset standard value of each experiment of the student respectively. The preset standard value is positively correlated with the learning performance. The higher the single subject score, the higher the preset standard value, and the greater the positive gap between the single subject score and the average score of the student. The higher the preset standard value, the positive gap is the value by which the single subject score exceeds the average score of the student.

4. The method for implementing an adaptive learning path planning AI teaching assistant for physical, chemical and biological experiments according to claim 3 is characterized by: The preset standard value includes a benchmark score, a hand data standard value and an experimental standard value. The hand data standard value includes a preset standard average value and a predetermined threshold value. The preset standard average value is the experimental standard operation value. The predetermined threshold value is the error range of the preset standard average value. The preset threshold value is expressed as a spherical shell surface of the preset standard average value in actual operation. When the hand joint is located inside or on the spherical shell surface formed by the preset threshold value, it is determined that the hand tracking data is located within the predetermined threshold value, that is, the hand tracking data meets the preset standard value.

5. The method for implementing an adaptive learning path planning AI teaching assistant for physical, chemical and biological experiments according to claim 4 is characterized by: The hand tracking data acquisition process is to determine the preset standard average value and the predetermined threshold value according to a reference point, and the reference point is one of the wrist center or the palm center.

6. The method for implementing an adaptive learning path planning AI teaching assistant for physical, chemical and biological experiments according to claim 4 is characterized by: The hand error data is the difference between the hand tracking data and the preset standard average value. When the hand joint is located outside the spherical shell surface formed by the preset threshold, it is determined that the hand tracking data is not within the preset threshold, that is, the hand tracking data does not meet the preset standard value.

7. The method for implementing an adaptive learning path planning AI teaching assistant for physical, chemical and biological experiments according to claim 4 is characterized by: The scoring data is based on the standards of the hand error data, namely, the numerical value of the hand error data, the current number of occurrences and the current time ratio, the current number of occurrences is the number of times the hand error data appears in the current experiment, the time ratio is the ratio of the time when the hand error data appears to the current experiment time, and the experimental standard value is the preset number of occurrences and the preset time ratio of the hand error data in the experiment. Weighted deduction processing is performed according to the numerical value of the hand error data, the value of the current number of occurrences being greater than the preset number of occurrences, and the value of the preset time ratio being greater than the preset time ratio, and the scoring data is obtained after the weighted deduction processing is performed on the full score.

8. The method for implementing an adaptive learning path planning AI teaching assistant for physical, chemical and biological experiments according to claim 7 is characterized by: According to the comparison between the scoring data and the benchmark score, if the scoring data is greater than the benchmark score, it is determined that the student's experiment is in compliance with the first learning path, and the first learning path is re-planned to increase the preset standard value of subsequent experiments; if the scoring data is less than the benchmark score, it is determined that the student's experiment is not in compliance with the first learning path, and the first learning path is re-planned to lower the preset standard value of subsequent experiments.

9. The method for implementing an adaptive learning path planning AI teaching assistant for physical, chemical and biological experiments according to claim 7 is characterized by: The higher the preset standard value is, the higher the benchmark score is, the smaller the predetermined threshold is, the fewer the preset occurrence times are, and the smaller the preset time ratio is. The preset standard value is affected by the positive gap weights of the single subject score and the single subject score and the average score of the student.

10. An AI teaching assistant for physical, chemical and biological experiments with adaptive learning path planning, a method for implementing an AI teaching assistant for physical, chemical and biological experiments with adaptive learning path planning based on any one of claims 1-9, characterized in that: include: Student information unit, used to enter student information; A planning unit, used for planning the first learning path according to student information; Image unit, used to obtain experimental data of students' experimental process; A storage unit, used for storing a preset standard value; A comparison unit, used for processing the hand tracking data to obtain hand error data; A processing unit, used for comparing the hand error data with a preset standard value and calculating and obtaining scoring data; The adjustment unit is used to adjust the first path and the preset standard value according to the scoring data.

Images